diff --git a/.DS_Store b/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..84a0055900f1b77d5295b50476a83b2bcd3f1db6 Binary files /dev/null and b/.DS_Store differ diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..7adcea3c87b14d53e345be7a4c0f9aa283920fc6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,98 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +data/gemini/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +data/gpt/content[[:space:]]2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +extra/android-in-the-wild-general-general-00001-of-00321 filter=lfs diff=lfs merge=lfs -text +extra/android-in-the-wild-general-general-00006-of-00321 filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +extra/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +extra/content[[:space:]]2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text diff --git a/.gradio/certificate.pem b/.gradio/certificate.pem new file mode 100644 index 0000000000000000000000000000000000000000..b85c8037f6b60976b2546fdbae88312c5246d9a3 --- /dev/null +++ b/.gradio/certificate.pem @@ -0,0 +1,31 @@ +-----BEGIN CERTIFICATE----- +MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw +TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh +cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4 +WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu +ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY +MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc +h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+ +0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U +A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW +T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH +B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC +B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv +KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn +OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn +jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw +qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI +rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV +HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq +hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL +ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ +3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK +NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5 +ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur +TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC +jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc +oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq +4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA +mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d +emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc= +-----END CERTIFICATE----- diff --git a/README.md b/README.md index 2cb8f8b29bd17abd1e35c051200ac595d5e24684..cb81d8f3dc3be324443364ea096c041df84df49d 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,6 @@ --- -title: MCQ Comparison -emoji: 📈 -colorFrom: yellow -colorTo: green +title: MCQ_Comparison +app_file: visualizer.py sdk: gradio sdk_version: 5.40.0 -app_file: app.py -pinned: false --- - -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/data/.gradio/certificate.pem b/data/.gradio/certificate.pem new file mode 100644 index 0000000000000000000000000000000000000000..b85c8037f6b60976b2546fdbae88312c5246d9a3 --- /dev/null +++ b/data/.gradio/certificate.pem @@ -0,0 +1,31 @@ +-----BEGIN CERTIFICATE----- +MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw +TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh +cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4 +WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu +ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY +MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc +h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+ +0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U +A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW +T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH +B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC +B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv +KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn +OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn +jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw +qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI +rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV +HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq +hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL +ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ +3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK +NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5 +ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur +TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC +jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc +oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq +4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA +mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d +emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc= +-----END CERTIFICATE----- diff --git a/data/gemini/.DS_Store b/data/gemini/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..4247665904648307829b6df3572e3cebdbfa2950 Binary files /dev/null and b/data/gemini/.DS_Store differ diff --git a/data/gemini/aitw_mcq_dataset_absolute_single_step copy.json b/data/gemini/aitw_mcq_dataset_absolute_single_step copy.json new file mode 100644 index 0000000000000000000000000000000000000000..8b1cc456738c84e987cb75b8e6f3269c35426789 --- /dev/null +++ b/data/gemini/aitw_mcq_dataset_absolute_single_step copy.json @@ -0,0 +1,188 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [491, 753]", + "Tap: [359, 561]", + "Type: 'ok'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [245, 415]", + "Type: 'search'", + "Tap: [128, 313]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [675, 182]", + "Type: 'ok'", + "Tap: [194, 108]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [350, 622]", + "Button: Press Back", + "Type: 'search'", + "Tap: [221, 296]" + ], + "correct_answer_index": 3 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [495, 743]", + "Tap: [363, 563]", + "Swipe: Right", + "Button: Press Enter" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [530, 763]", + "Button: Press Enter", + "Tap: [360, 110]", + "Swipe: Left" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [365, 528]", + "Type: 'search'", + "Tap: [494, 754]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [360, 670]", + "Tap: [320, 282]", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [662, 103]", + "Tap: [73, 103]", + "Button: Press Back", + "Type: 'search'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Type: 'search'", + "Tap: [323, 244]", + "Tap: [282, 180]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 8, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Type: 'search'", + "Tap: [380, 319]", + "Tap: [194, 1092]" + ], + "correct_answer_index": 3 + } + } + ] + } +} \ No newline at end of file diff --git a/data/gemini/aitw_mcq_dataset_absolute_single_step.json b/data/gemini/aitw_mcq_dataset_absolute_single_step.json new file mode 100644 index 0000000000000000000000000000000000000000..eca01e6c9fe56171b78ae047b9ebc533309594ec --- /dev/null +++ b/data/gemini/aitw_mcq_dataset_absolute_single_step.json @@ -0,0 +1,283 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [382, 838]", + "Type: 'ok'", + "Tap: [291, 838]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [224, 776]", + "Type: 'settings'", + "Tap: [287, 814]", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [156, 776]", + "Type: 'search'", + "Tap: [420, 775]", + "Button: Press Enter" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [468, 64]", + "Tap: [516, 64]", + "Button: Press Back", + "Swipe: Right" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [44, 78]", + "Type: 'search'", + "Tap: [150, 105]", + "Button: Press Enter" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [467, 62]", + "Type: 'ok'", + "Tap: [515, 62]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [514, 64]", + "Button: Press Home", + "Tap: [514, 116]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [370, 127]", + "Type: 'settings'", + "Tap: [370, 78]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Swipe: Left", + "Tap: [365, 826]", + "Tap: [277, 826]" + ], + "correct_answer_index": 2 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [85, 320]", + "Type: 'settings'", + "Tap: [379, 183]", + "Swipe: Left" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [499, 976]", + "Swipe: Left", + "Tap: [442, 976]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [302, 950]", + "Swipe: Down", + "Button: Press Enter", + "Tap: [270, 600]" + ], + "correct_answer_index": 0 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [289, 950]", + "Swipe: Left", + "Tap: [387, 852]", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png", + "action_history": "Step 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [286, 129]", + "Tap: [286, 193]", + "Button: Press Home", + "Type: 'settings'" + ], + "correct_answer_index": 0 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [78, 570]", + "Tap: [320, 974]", + "Type: 'ok'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png", + "action_history": "Step 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [185, 114]", + "Type: 'ok'", + "Swipe: Right", + "Tap: [199, 193]" + ], + "correct_answer_index": 0 + } + } + ] + } +} \ No newline at end of file diff --git a/data/gemini/content 2/.DS_Store b/data/gemini/content 2/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..0cc50955ee9481c515668d1bbbc91ea3e2c59d71 Binary files /dev/null and b/data/gemini/content 2/.DS_Store differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..af2e67ab941c9408bd3ae4486073a1d0f91e0ebc --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7088097b7da7759d200948f0dc34f874d57e9b567eaed7aed02d52bc095bba54 +size 183971 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e878afa05bcf6a79d53e7d8d57906b84a28f6d8b --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a28bac4fe5d6786cc7504fda57a7d6603ca1c854fb0ee7d9dab217b0f23f981 +size 125964 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..90197b8e64f1d9a518255644633fb06523937575 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a343af955ee958239aba067cc25ccfcd68c8699626304beb44a66b17f5ff66b +size 126394 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..59f25f7523e7e9425785ee725ab17c4676e566f8 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7c01e562c8d487c626872528d2b3397b084e42ec0c498b3aa48f5331a3784e +size 117440 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..afb5b43efe3182e63ce095ce10d79069ddcfa729 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..f0c177a08863d3fb3cea13fe9c255db2f83f4ce0 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9fb765509732f8eb1c49b1086e05509526a6f2deeb4aaf427e453bbd2cb67b +size 117347 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..97175f4a3687268b565361fcabba7b68372b22c5 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..198f36277fc51cd05d0644c70c6a647146818a4e Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..9141eba07655214299d5a6a5cc92c2e86f608be8 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf27762041f46b09457f35fe6a5270ff9ebbbe4e934b20dad309bd02f94b26ed +size 189122 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..d83dc012cc31687ed46fb7287aad5a42f668fc77 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..46e786b4d5760bf43f2fd60024052eeb332c919d --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5101572c4bab0f7f797ab23c9b077ea15ab2124af00a1ab8b8fbfdf11ee8d5 +size 189448 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..69cf25bf82c4debd8292c92a8518c7435441e7c1 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..80f600d70428b6e2dc9632c7153c9ceb1a306646 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1c4696612c56d20a32f2a2a9dcc5aac3f0888dee0f507d6179b681fbb031af +size 153211 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2cc574a37e46a3b45b459d5637d9cf9f012b2a08 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3bf01ec811b461af886f12bb8b56df48e4bc5b176eca5daf3940fe98cfa724 +size 369564 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..87d5596d2d3241e86bbc914c26a2799973b5d727 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c221c17cd7e4d0d58940d0ae725e439850a5f0b617d3a442317223b1f3dc4987 +size 136269 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..9381979149a0e114ec14768c6519e6189470821c Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..7e37c2baf8f8246b5479f9d7b4543c47ddfa9309 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..b9d969db80b09b62c22658f41f0abcd3942dffb9 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..965f63640efef962949b5749871d2cddb5f1ba0d Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..0b923c99281c1e5718b52744987cd80ea00a2679 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72214d17a912696d3cbff242f436d4bc94ebbafe4b8078f043a0055f33faa245 +size 189366 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..ed0f8cc92ec565347a32f7b8e7da523017b70483 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c50706aac36e57c93735f8f2c6c3766a85062c9596050ba611a0065d899032 +size 155428 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c912a8f71cdf21cfc0f8e98cb1a04da4f5e17112 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717ac561d7f1dc633fa01c86396a421d9169dd1cf26bf148801b7234ee919e86 +size 150259 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..afc905a42bac28caf3a3b0cc658a4fe66165c68a --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e1794961d98497d9882cb7a2c334be705afd83e07212d875216479ffb4f292 +size 156723 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a7a3c7be22a99cfa20e3b6ad21956c2d7c8ea43c --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49fe62cf6546e19500c2937a47229938f556059c56f5a8ac29e95a376a25f39 +size 371794 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..a8cebeab7f894ada7932258170d6a1f74d966390 Binary files /dev/null and b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png differ diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..bfe7c2616a4d320a37a67806f2090e9ad02929ae --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ab692f266e4ac2d632d2365bbec80e8ba08a0486b3803dc241f4e31cf17b54 +size 115195 diff --git a/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..5a7eaaf567c8621ca3c67e772d1cd0bd95f33030 --- /dev/null +++ b/data/gemini/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aad9cab1c5a1d1818349ae785b62710b232a81fa31f380a7c9c95d7c4f53fd3 +size 156495 diff --git a/data/gemini/content/.DS_Store b/data/gemini/content/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..a9ddfe71e36abacb5c2a207ae74318cacab7540f Binary files /dev/null and b/data/gemini/content/.DS_Store differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..af2e67ab941c9408bd3ae4486073a1d0f91e0ebc --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7088097b7da7759d200948f0dc34f874d57e9b567eaed7aed02d52bc095bba54 +size 183971 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e878afa05bcf6a79d53e7d8d57906b84a28f6d8b --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a28bac4fe5d6786cc7504fda57a7d6603ca1c854fb0ee7d9dab217b0f23f981 +size 125964 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..90197b8e64f1d9a518255644633fb06523937575 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a343af955ee958239aba067cc25ccfcd68c8699626304beb44a66b17f5ff66b +size 126394 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..59f25f7523e7e9425785ee725ab17c4676e566f8 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7c01e562c8d487c626872528d2b3397b084e42ec0c498b3aa48f5331a3784e +size 117440 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..afb5b43efe3182e63ce095ce10d79069ddcfa729 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..f0c177a08863d3fb3cea13fe9c255db2f83f4ce0 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9fb765509732f8eb1c49b1086e05509526a6f2deeb4aaf427e453bbd2cb67b +size 117347 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..97175f4a3687268b565361fcabba7b68372b22c5 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..198f36277fc51cd05d0644c70c6a647146818a4e Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..9141eba07655214299d5a6a5cc92c2e86f608be8 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf27762041f46b09457f35fe6a5270ff9ebbbe4e934b20dad309bd02f94b26ed +size 189122 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..d83dc012cc31687ed46fb7287aad5a42f668fc77 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..46e786b4d5760bf43f2fd60024052eeb332c919d --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5101572c4bab0f7f797ab23c9b077ea15ab2124af00a1ab8b8fbfdf11ee8d5 +size 189448 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..69cf25bf82c4debd8292c92a8518c7435441e7c1 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..80f600d70428b6e2dc9632c7153c9ceb1a306646 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1c4696612c56d20a32f2a2a9dcc5aac3f0888dee0f507d6179b681fbb031af +size 153211 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2cc574a37e46a3b45b459d5637d9cf9f012b2a08 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3bf01ec811b461af886f12bb8b56df48e4bc5b176eca5daf3940fe98cfa724 +size 369564 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..87d5596d2d3241e86bbc914c26a2799973b5d727 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c221c17cd7e4d0d58940d0ae725e439850a5f0b617d3a442317223b1f3dc4987 +size 136269 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..9381979149a0e114ec14768c6519e6189470821c Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..7e37c2baf8f8246b5479f9d7b4543c47ddfa9309 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..b9d969db80b09b62c22658f41f0abcd3942dffb9 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..965f63640efef962949b5749871d2cddb5f1ba0d Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..0b923c99281c1e5718b52744987cd80ea00a2679 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72214d17a912696d3cbff242f436d4bc94ebbafe4b8078f043a0055f33faa245 +size 189366 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..ed0f8cc92ec565347a32f7b8e7da523017b70483 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c50706aac36e57c93735f8f2c6c3766a85062c9596050ba611a0065d899032 +size 155428 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c912a8f71cdf21cfc0f8e98cb1a04da4f5e17112 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717ac561d7f1dc633fa01c86396a421d9169dd1cf26bf148801b7234ee919e86 +size 150259 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..afc905a42bac28caf3a3b0cc658a4fe66165c68a --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e1794961d98497d9882cb7a2c334be705afd83e07212d875216479ffb4f292 +size 156723 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a7a3c7be22a99cfa20e3b6ad21956c2d7c8ea43c --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49fe62cf6546e19500c2937a47229938f556059c56f5a8ac29e95a376a25f39 +size 371794 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..a8cebeab7f894ada7932258170d6a1f74d966390 Binary files /dev/null and b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png differ diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..bfe7c2616a4d320a37a67806f2090e9ad02929ae --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ab692f266e4ac2d632d2365bbec80e8ba08a0486b3803dc241f4e31cf17b54 +size 115195 diff --git a/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..5a7eaaf567c8621ca3c67e772d1cd0bd95f33030 --- /dev/null +++ b/data/gemini/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aad9cab1c5a1d1818349ae785b62710b232a81fa31f380a7c9c95d7c4f53fd3 +size 156495 diff --git a/data/gemini/images-3.zip b/data/gemini/images-3.zip new file mode 100644 index 0000000000000000000000000000000000000000..1994799a14a91748002ff13c14057f4ef3231310 --- /dev/null +++ b/data/gemini/images-3.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31b5482ca452a6df224a310b5e1a2f9244870e38c24882be4654e52b196b760 +size 1629420 diff --git a/data/gemini/imagesa.zip b/data/gemini/imagesa.zip new file mode 100644 index 0000000000000000000000000000000000000000..207e9ea5cf62598045255694fb9d9371b1dc2bef --- /dev/null +++ b/data/gemini/imagesa.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f5573bc7a633732cac1d9c0c53cbff72cb0bca47111a99ca08865f9765e3c8 +size 3398683 diff --git a/data/gpt/.DS_Store b/data/gpt/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..b12d224b0db889bb68ec90d50d63f60491a32a92 Binary files /dev/null and b/data/gpt/.DS_Store differ diff --git a/data/gpt/aitw_mcq_dataset_absolute_single_step copy.json b/data/gpt/aitw_mcq_dataset_absolute_single_step copy.json new file mode 100644 index 0000000000000000000000000000000000000000..138622fc58eadb0595fe232cf1a27dd7735e9ed2 --- /dev/null +++ b/data/gpt/aitw_mcq_dataset_absolute_single_step copy.json @@ -0,0 +1,188 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [700, 760]", + "Button: Press Back", + "Tap: [491, 753]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [128, 313]", + "Tap: [360, 1450]", + "Swipe: Left", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'ok'", + "Tap: [194, 108]", + "Button: Press Enter", + "Tap: [194, 150]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [221, 296]", + "Button: Press Enter", + "Type: 'settings'", + "Tap: [250, 750]" + ], + "correct_answer_index": 0 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Up", + "Tap: [495, 743]", + "Button: Press Back", + "Tap: [495, 640]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'search'", + "Tap: [530, 1000]", + "Tap: [530, 763]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [494, 754]", + "Type: 'search'", + "Tap: [576, 754]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [320, 282]", + "Swipe: Down", + "Button: Press Enter", + "Tap: [360, 1460]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [662, 150]", + "Tap: [662, 103]", + "Type: 'search'", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [280, 240]", + "Tap: [282, 180]", + "Type: 'settings'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 8, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [500, 460]", + "Swipe: Down", + "Tap: [194, 1092]", + "Type: 'ok'" + ], + "correct_answer_index": 2 + } + } + ] + } +} \ No newline at end of file diff --git a/data/gpt/aitw_mcq_dataset_absolute_single_step.json b/data/gpt/aitw_mcq_dataset_absolute_single_step.json new file mode 100644 index 0000000000000000000000000000000000000000..517374b6bb79da5ba61336be07f1f57c75d16a18 --- /dev/null +++ b/data/gpt/aitw_mcq_dataset_absolute_single_step.json @@ -0,0 +1,283 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [382, 838]", + "Type: 'settings'", + "Tap: [382, 780]", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Up", + "Tap: [224, 830]", + "Tap: [224, 776]", + "Type: 'settings'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'settings'", + "Tap: [410, 720]", + "Swipe: Up", + "Tap: [420, 775]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [468, 64]", + "Tap: [430, 64]", + "Type: 'search'", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [44, 78]", + "Swipe: Down", + "Tap: [520, 78]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [467, 62]", + "Tap: [525, 62]", + "Type: 'settings'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [514, 64]", + "Tap: [470, 64]", + "Type: 'ok'", + "Swipe: Left" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 7, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [370, 127]", + "Button: Press Home", + "Swipe: Up", + "Tap: [370, 180]" + ], + "correct_answer_index": 0 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [365, 826]", + "Tap: [370, 600]", + "Button: Press Enter", + "Type: 'settings'" + ], + "correct_answer_index": 0 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [379, 183]", + "Button: Press Home", + "Tap: [379, 250]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [499, 976]", + "Tap: [460, 940]", + "Type: 'ok'", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png", + "action_history": "Step 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'ok'", + "Swipe: Down", + "Tap: [452, 950]", + "Tap: [302, 950]" + ], + "correct_answer_index": 3 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 2, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [289, 950]", + "Type: 'search'", + "Tap: [390, 950]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png", + "action_history": "Step 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [480, 950]", + "Tap: [286, 129]", + "Type: 'search'" + ], + "correct_answer_index": 2 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 3, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'ok'", + "Tap: [80, 974]", + "Button: Press Home", + "Tap: [320, 974]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png", + "action_history": "Step 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [185, 114]", + "Tap: [50, 210]", + "Type: 'settings'", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + } + ] + } +} \ No newline at end of file diff --git a/data/gpt/content 2/.DS_Store b/data/gpt/content 2/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..a9ddfe71e36abacb5c2a207ae74318cacab7540f Binary files /dev/null and b/data/gpt/content 2/.DS_Store differ diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e9e686bfbec220d3e809fdf5b36142ae89edb10c --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465e0f45af62ec253eb928247168723700f0d60c26a180dd1187e059befd8727 +size 153930 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..9b92433fb7bd188c4c0e0fa9976e6ebb1301b1f6 --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3214d6fc061e74531c1f5a3bda6fde5a1ce7d73daf6c73a6df2ee3ee83e2c41c +size 369487 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..8f0ff94b44e76339e205af4b5b482a819295a7b9 --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138d2324260a191d8d4ed2ff9468ab96119ff0f37af8ab91be42129efd369e25 +size 136260 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..86e5d72798894f1174e495d981f846b583c0cccc Binary files /dev/null and b/data/gpt/content 2/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png differ diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..78a29579a700886a13d710fae5bf8d68bef5a33e --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a9677e7d1cb1eef02eab5070d26da3c4af6d83e10418f209e3895f2eb5b15b +size 156081 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..a26e36ddb2d81cf41665c324f893c3635159f114 --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064f6a5d995bba648bcd9cb3f646cca8ddc0a9e5ce121b9c0fcb0dfca81d05b0 +size 150289 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2e726e0d403a333b22506794e1bca05c2bbc0b38 --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c759e83e26b5ed51a15dd90ca9ae4961cbca4d32eebfa52f1ebd398300c48f4 +size 157141 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..0564dba68413284621ec3cdcaf70d29946e8067c --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c0409e4e6b211a9784d04bbd131c4a969f705734de05c7abb7a2f49824e10a +size 371942 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..34cded4fe4da2844934f6de0fc05599fbfa79612 Binary files /dev/null and b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png differ diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..d45255ad694b279a83b486dbd3286c7826a05b0c --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c449bd3fe3ac60d3b42206e8ee20e29560555b4d1495bb13cd3380036668de +size 115185 diff --git a/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..9c4f0ab8c9a6673bca4a83ac559d4cffc554174d --- /dev/null +++ b/data/gpt/content 2/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b9457d2eacb28b0859414c43dc8c167c00406672230dd772941fc8263b5a04 +size 156417 diff --git a/data/gpt/content/.DS_Store b/data/gpt/content/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..9976e8afa36b4c37b410c90aa50f4393703d2df2 Binary files /dev/null and b/data/gpt/content/.DS_Store differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..ec3b56a9817f8e6b916981b47d496cc4f8f9e7f7 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b824232e42bb1a1ec089ab5139b00c40ec4de34a6f273fe658623d2cf02e17 +size 184453 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..ba9dd10b26e418d1adb2e0977474e9eb8f79aae6 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f1f493465ac592be2af57f5c1c7f9ba3d51e55941962ef73cf903918e17fbb +size 125951 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..7a4db82ee3711987d035fbed3b434c489b5cc917 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1c9dcfb4431ec21dbba9d479b664684b7e24f092af9f5f89a3397bff0961da +size 126433 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8b84f35ad8bbe3c76ae53502fee6a82b460d9cc8 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7610e60f23fc3cc2b8c8fcd1790e039f258aab65b3abaa4cf6164921422d28a0 +size 117563 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..97995f035d822a4fe721bb91f4b54b245e1355b1 Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..3729da71502334289ce02b5aa91e0199b4dbc0e7 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3fd1a7b26ff4709bf61a2e1ae071e707493ecb1ba6c0a9b4358b988e06fe254 +size 117604 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..4b7e181038095e36d9ce6396f869d93cbf7c32c5 Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..c1a889bfc94b690401bf0347c3e6779dda89310f Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..ea2ea7d97668d9cdcb5b7a1a8248700222ca206f --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67eb15c1801afa4ad97a854adbe80da863cbfa0b31301771a59b77629a4103f +size 189262 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..6f829467da06d1c8abb9d4075dc4c7283576a9fd Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..029eae1464865d56c7bffe7c189464bd24614c66 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78106c1aea49743b236919b520b62a62b455f5ea07a25985c6ab2e791313c3f +size 189000 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..75854006ee211639745d56b3c59e7e1c340d0d11 Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e9e686bfbec220d3e809fdf5b36142ae89edb10c --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465e0f45af62ec253eb928247168723700f0d60c26a180dd1187e059befd8727 +size 153930 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..9b92433fb7bd188c4c0e0fa9976e6ebb1301b1f6 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3214d6fc061e74531c1f5a3bda6fde5a1ce7d73daf6c73a6df2ee3ee83e2c41c +size 369487 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..8f0ff94b44e76339e205af4b5b482a819295a7b9 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138d2324260a191d8d4ed2ff9468ab96119ff0f37af8ab91be42129efd369e25 +size 136260 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..86e5d72798894f1174e495d981f846b583c0cccc Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..678326893804288d20c9814c52692a950f6baffe Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..a8a520a67fe7412fc861667cae129399f680536f Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..14cf571e08796dd583a3d2235d27e07f77b691a8 Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..d9b4069f7c5c7f12a0d1da56724b5b5ec23a0858 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb157fcc2783c10fc4173f3d8bb68f5edaf9fcd778b8d88f130b13cab34f6c3d +size 190134 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..78a29579a700886a13d710fae5bf8d68bef5a33e --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a9677e7d1cb1eef02eab5070d26da3c4af6d83e10418f209e3895f2eb5b15b +size 156081 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..a26e36ddb2d81cf41665c324f893c3635159f114 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064f6a5d995bba648bcd9cb3f646cca8ddc0a9e5ce121b9c0fcb0dfca81d05b0 +size 150289 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2e726e0d403a333b22506794e1bca05c2bbc0b38 --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c759e83e26b5ed51a15dd90ca9ae4961cbca4d32eebfa52f1ebd398300c48f4 +size 157141 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..0564dba68413284621ec3cdcaf70d29946e8067c --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c0409e4e6b211a9784d04bbd131c4a969f705734de05c7abb7a2f49824e10a +size 371942 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..34cded4fe4da2844934f6de0fc05599fbfa79612 Binary files /dev/null and b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png differ diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..d45255ad694b279a83b486dbd3286c7826a05b0c --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c449bd3fe3ac60d3b42206e8ee20e29560555b4d1495bb13cd3380036668de +size 115185 diff --git a/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..9c4f0ab8c9a6673bca4a83ac559d4cffc554174d --- /dev/null +++ b/data/gpt/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b9457d2eacb28b0859414c43dc8c167c00406672230dd772941fc8263b5a04 +size 156417 diff --git a/data/gpt/images-3 copy.zip b/data/gpt/images-3 copy.zip new file mode 100644 index 0000000000000000000000000000000000000000..97c6d7efb4f9b5c36407b4f17d461b15160b2c58 --- /dev/null +++ b/data/gpt/images-3 copy.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc241ee5e9968b8cc458903a16c9ee39cfcc47ea98f72ea402946a4b43344dab +size 1772272 diff --git a/data/gpt/images-3.zip b/data/gpt/images-3.zip new file mode 100644 index 0000000000000000000000000000000000000000..9bd8e6cecd55c90ac62ddeab14ca3bae08929a7c --- /dev/null +++ b/data/gpt/images-3.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578468129e80b8ee78db34f6e248442494e33b178fec15bc1b16c98eb65948b1 +size 1630324 diff --git a/data/qwen/.DS_Store b/data/qwen/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..8cebc54c8b7e52a9f00693d2f3416961666a2dce Binary files /dev/null and b/data/qwen/.DS_Store differ diff --git a/data/qwen/aitw_mcq_dataset_absolute_single_step copy.json b/data/qwen/aitw_mcq_dataset_absolute_single_step copy.json new file mode 100644 index 0000000000000000000000000000000000000000..1b9f652b6363495899481b961ab96b66498977a3 --- /dev/null +++ b/data/qwen/aitw_mcq_dataset_absolute_single_step copy.json @@ -0,0 +1,188 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_16849016505201470177_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Tap: [630, 753]", + "Tap: [491, 753]", + "Button: Press Back" + ], + "answer": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_16849016505201470177_step_3.png", + "action_history": "Step 1: Tap: [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [664, 313]", + "Type: 'settings'", + "Swipe: Left", + "Tap: [128, 313]" + ], + "answer": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_16849016505201470177_step_5.png", + "action_history": "Step 1: Tap: [491, 753]\nStep 3: Tap: [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [194, 108]", + "Swipe: Right", + "Tap: [660, 108]", + "Button: Press Home" + ], + "answer": 0 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_16849016505201470177_step_7.png", + "action_history": "Step 1: Tap: [491, 753]\nStep 3: Tap: [128, 313]\nStep 5: Tap: [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Tap: [300, 450]", + "Button: Press Home", + "Tap: [221, 296]" + ], + "answer": 3 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [495, 743]", + "Swipe: Down", + "Tap: [630, 743]" + ], + "answer": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_2.png", + "action_history": "Step 1: Tap: [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [530, 763]", + "Swipe: Right", + "Tap: [640, 750]", + "Button: Press Home" + ], + "answer": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_3.png", + "action_history": "Step 1: Tap: [495, 743]\nStep 2: Tap: [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'search'", + "Tap: [494, 754]", + "Button: Press Home", + "Tap: [638, 754]" + ], + "answer": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_4.png", + "action_history": "Step 1: Tap: [495, 743]\nStep 2: Tap: [530, 763]\nStep 3: Tap: [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [320, 282]", + "Tap: [665, 305]", + "Swipe: Right" + ], + "answer": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_5.png", + "action_history": "Step 1: Tap: [495, 743]\nStep 2: Tap: [530, 763]\nStep 3: Tap: [494, 754]\nStep 4: Tap: [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Type: 'ok'", + "Tap: [662, 103]", + "Tap: [400, 103]" + ], + "answer": 2 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_7.png", + "action_history": "Step 1: Tap: [495, 743]\nStep 2: Tap: [530, 763]\nStep 3: Tap: [494, 754]\nStep 4: Tap: [320, 282]\nStep 5: Tap: [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [282, 180]", + "Swipe: Right", + "Tap: [660, 200]", + "Type: 'ok'" + ], + "answer": 0 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/images/episode_9836837435576948503_step_8.png", + "action_history": "Step 1: Tap: [495, 743]\nStep 2: Tap: [530, 763]\nStep 3: Tap: [494, 754]\nStep 4: Tap: [320, 282]\nStep 5: Tap: [662, 103]\nStep 7: Tap: [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [194, 1092]", + "Tap: [360, 1085]", + "Button: Press Back" + ], + "answer": 1 + } + } + ] + } +} \ No newline at end of file diff --git a/data/qwen/aitw_mcq_dataset_absolute_single_step.json b/data/qwen/aitw_mcq_dataset_absolute_single_step.json new file mode 100644 index 0000000000000000000000000000000000000000..5d740ca083b573c950f73ebb7e91a8217f53ac3c --- /dev/null +++ b/data/qwen/aitw_mcq_dataset_absolute_single_step.json @@ -0,0 +1,283 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/images/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [265, 965]", + "Tap: [382, 838]", + "Button: Press Back", + "Type: 'ok'" + ], + "answer": 1 + } + }, + { + "step_id": 1, + "screenshot_path": "/images/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tap: [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [224, 965]", + "Swipe: Right", + "Tap: [224, 776]", + "Type: 'ok'" + ], + "answer": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/images/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'ok'", + "Tap: [90, 790]", + "Swipe: Right", + "Tap: [420, 775]" + ], + "answer": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/images/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]\nStep 2: Tap: [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [468, 64]", + "Swipe: Right", + "Tap: [495, 70]" + ], + "answer": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/images/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]\nStep 2: Tap: [420, 775]\nStep 3: Tap: [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Type: 'search'", + "Tap: [235, 226]", + "Tap: [44, 78]" + ], + "answer": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/images/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]\nStep 2: Tap: [420, 775]\nStep 3: Tap: [468, 64]\nStep 4: Tap: [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'search'", + "Tap: [467, 62]", + "Tap: [495, 62]" + ], + "answer": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/images/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]\nStep 2: Tap: [420, 775]\nStep 3: Tap: [468, 64]\nStep 4: Tap: [44, 78]\nStep 5: Tap: [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'settings'", + "Tap: [30, 64]", + "Tap: [514, 64]" + ], + "answer": 3 + } + }, + { + "step_id": 7, + "screenshot_path": "/images/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tap: [382, 838]\nStep 1: Tap: [224, 776]\nStep 2: Tap: [420, 775]\nStep 3: Tap: [468, 64]\nStep 4: Tap: [44, 78]\nStep 5: Tap: [467, 62]\nStep 6: Tap: [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 65]", + "Swipe: Up", + "Tap: [370, 127]", + "Button: Press Enter" + ], + "answer": 2 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/images/episode_9027843537045096280_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [265, 970]", + "Button: Press Enter", + "Tap: [365, 826]", + "Swipe: Down" + ], + "answer": 2 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 1, + "screenshot_path": "/images/episode_2247237893045084693_step_1.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [379, 183]", + "Swipe: Left", + "Tap: [365, 390]", + "Type: 'search'" + ], + "answer": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/images/episode_2247237893045084693_step_2.png", + "action_history": "Step 1: Tap: [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'search'", + "Tap: [499, 800]", + "Tap: [499, 976]" + ], + "answer": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/images/episode_2247237893045084693_step_3.png", + "action_history": "Step 1: Tap: [379, 183]\nStep 2: Tap: [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [302, 950]", + "Type: 'settings'", + "Tap: [260, 750]", + "Swipe: Down" + ], + "answer": 0 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 2, + "screenshot_path": "/images/episode_12224608131504749719_step_2.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [289, 950]", + "Swipe: Right", + "Tap: [360, 845]" + ], + "answer": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/images/episode_12224608131504749719_step_4.png", + "action_history": "Step 2: Tap: [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'search'", + "Tap: [350, 175]", + "Tap: [286, 129]", + "Button: Press Home" + ], + "answer": 2 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 3, + "screenshot_path": "/images/episode_1307957808436696980_step_3.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 845]", + "Type: 'search'", + "Swipe: Up", + "Tap: [320, 974]" + ], + "answer": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/images/episode_1307957808436696980_step_5.png", + "action_history": "Step 3: Tap: [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [185, 114]", + "Type: 'settings'", + "Tap: [185, 365]" + ], + "answer": 1 + } + } + ] + } +} diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..c0bac5bffa3f3dfcd8f41bc93c59a0f072e55d68 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a66e21957d01071b5fe55357d16459cd6df8d627705a22931b95c2902edcec1 +size 184283 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..8ca9b91e92f1761450ea566c0d4db49af74f6011 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a35ade5031af834c99b1d0a2c0c3be4bafd270ca9ab7f97ccf7bb5fd128147c +size 125953 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..6ac8346b96bafc60fe80404a199e2b52b9b14108 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f3775125a85fef5fbabe077bf64c126433b781e94d1d842ffef6d69bb87dc1 +size 126223 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..bed54e5683501ec57fe7c145e6878de4cd63d74d --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd3184c0e1c671d02539a54cf32187f107a7796e4da76f129625c4c481b3336 +size 117697 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..4a045314b2f2cba502af6f91e93f603c1e3dbbf8 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..d4a73a6605136d4f2762b8ec8378759a0a2665ab --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5ad1f8eb661c9d7f7a98059dc3a18d27491e1d426de15410a8916d92a789b7 +size 117603 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..a4dd1cbb0d006f74a32e5008db4b1dd8c0ba7b53 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..48172fdf978c515c9e2b0ce06f512596d26b7bc9 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..813118365de60662e9211f6d04ed72e0fee24469 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01db69ca27e119c9ee6d319302b0f876fe43dc7218ca828c7c8506c167e376f0 +size 188968 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..d2b2b86047089d3f3209af2fe40d229fbd59af63 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..4b92497b20a62e699567200a8aff04fc0a3c2d4f --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550024d7eb9fc58dc44f2e6810d58ea2300e654b59268963fdcc92f92b58bb78 +size 188826 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..7cff0af37cf30c47bdbc02e99c3114f726361834 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e4d737249cce60fe09005c048ba1079903de9d51 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdafd4643cfaefd86708c55c91e70f45eea1cc99637a4a0a92b91757d7a37b05 +size 153661 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..16fbe96e5bb37a28f040e6cdb37a03cbad507e13 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dccdf23deb3eb2f3c651ad2cd7f149a86e91cc87c6803ebec35f239b667e8c9 +size 369140 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..be3b0c79680e154d8654bfd8d02bd6f1f2d89af6 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e6a1ce3b11bf9bc5bea902c32933dccccee21d1f3517a562b4031b1453b28c +size 135647 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..32c0580df2e87f56bb9f4037d5d58248ae025361 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_16849016505201470177_step_7.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..4eba7fbdb9ce6a569d23726f51fd77d9c0b56a7b Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..e91b16383aa1b5ac014961c3a9e45a9f9de5e57c Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..0b11aad9d9469ee72c0af8480f9d1819da3af3ff Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..d8814b91d6283b4687f1eb83c3e31f8f227c6e75 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13db53ee15eed1496f358acd48a87adf0ec82725af3a418ca4bb235aa90a56d3 +size 189720 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..661d1bf876b351de498166a237ef43d157335fc4 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7822571375d0b385eec8ce224367e14547ba67040dff6ce9ad3052e2b2b47d52 +size 155510 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..72983e0b4c26365ccda7240c1a878d91abb722f0 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088b269cb7f5b999184644dea2359a9624202d1ee25bdbb619e22ada84d14f13 +size 149854 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..e8c9e11821bfd2d77eedc8f10698db890a1952b7 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7b63fe58f4f5c8f9cf6af82c14b929b09296e419e0916b7b434ab678991f76 +size 156781 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..5303bfff9ad30958103ebeb88202f61de72a78b8 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e772bbe0a5f07f5dcb9ee7200bc5a90f25dc6284740c42874eb9c30f25b00a7f +size 371915 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..2afe62b2247fc49fa21965386796eec032e35878 Binary files /dev/null and b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_5.png differ diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..30e2dacae2d44835a31fac1e8ea99127cd8ecc58 --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b59de583116419c43bd5f1dfcd2de63e96ddb75e1af9fa3eb70870e7ab63c3e +size 114843 diff --git a/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..5e430976c8d8c0c48cb789c54eea9daa9ec9dc2a --- /dev/null +++ b/data/qwen/content/aitw_images_absolute_single_step/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da96c67d21b617126204a571e8d6470445c47c750c9ffaf270ef9ea514d82604 +size 156405 diff --git a/extra/.DS_Store b/extra/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..67877a0f01b06faa22e1785cb7bc1cfb9f1a6f9f Binary files /dev/null and b/extra/.DS_Store differ diff --git a/extra/android-in-the-wild-general-general-00001-of-00321 b/extra/android-in-the-wild-general-general-00001-of-00321 new file mode 100644 index 0000000000000000000000000000000000000000..3addb64690a39c36ea2e98a72f2d7fa889cad98a --- /dev/null +++ b/extra/android-in-the-wild-general-general-00001-of-00321 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283ced22d8411d02ea3f95ca60ac65ed2559554333142ce15bce3ac50771dd5c +size 3249449 diff --git a/extra/android-in-the-wild-general-general-00006-of-00321 b/extra/android-in-the-wild-general-general-00006-of-00321 new file mode 100644 index 0000000000000000000000000000000000000000..c5e1f63b01741a86b03e349c0179379b4e18efc7 --- /dev/null +++ b/extra/android-in-the-wild-general-general-00006-of-00321 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6719af69034ea22e3cdcfe264291d3dafbfa77157de62cca3e0bcbb66f8d10a0 +size 3810244 diff --git a/extra/content 2/.DS_Store b/extra/content 2/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..517a91f94fd6b386dcf22acef5f09b727124684b Binary files /dev/null and b/extra/content 2/.DS_Store differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..3faa2ba9bc9e8f0e4b34bf86ca36c22fa25b914e --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9735837318fb8702d873928015e9dbd8d8a06af103526e4ec179d3893595fa6a +size 183967 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..6deb5dc57860ec3bd5d10f1b1a629a8f2337f63d --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5501472e6900d500b9011043e9da3e56b43ca93138ddddd7d30ffd14019cc0d +size 125973 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..79aa44bd87010c72d4fb019847406594101dca66 --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0649f69db4208b1464fbbe6f6d3fb4f7413d1398ca60650957348e5d4d9bb688 +size 126448 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2f8f3cbcbaabf934f97679a718f60da9c8435510 --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdad52969ae2f07b5469bd7e044a0695fa8cc894d443a0ad225dcdcce24af05 +size 117652 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..8bdcbc917dc81af461f6c7adf212dac550c73cf3 Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..8cd794ce33eae1ee9557e332d3955f6738dfdf74 --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71bf5eaf1ebad3dd53de637ccf677cf4e288cb9983cc11f96f484dc93b22b268 +size 117420 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..793e76bbbdb3868cabd9f1c155480f298751839d Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..31fb1f09da45feed1ab4b11b0b49410d3fd7a45c Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..e98416a2c24657402cf395dfa921a6e32b2b5363 --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428ccf8ff95e90ce9e0329852ec8dcb039558eaae05ec73146d2b9e27336bc00 +size 189279 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..04a42157d8f1010ff9b853d8110225cb77ed7813 Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8db0ff9436a0178cd14144b560d84837cf11a58a --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5adba37d2e4f4f524a0ae1e07a3466561d71f27f4439ffd10c43b7e500ac1b02 +size 189139 diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..b290c0ce30ca674736b28d63905607940561f064 Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..8d57117dc6244bcdb60d9e0cdab247f9d6c6000c Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..cef83bf9293a076ad199553d07daf43739f3969c Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..f9aa6892d37026be39b4e397482af1a0a318a89f Binary files /dev/null and b/extra/content 2/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/extra/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/extra/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..04c26bffee30f615dc362b562a3591057af5c110 --- /dev/null +++ b/extra/content 2/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9fe6ed7b39236663fe0375beecfe7746cedbe1ca80275cabe1553a65f8519b +size 189464 diff --git a/extra/content/.DS_Store b/extra/content/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..1181a5a060668de9e681d615c88e72fbc67e933d Binary files /dev/null and b/extra/content/.DS_Store differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..7e5f5dfc4e45a4399fe47536a664c887cbd75567 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f12c3a2ea0721e5b662d975214466b6ab24de9c75af4e388dbd8b2df4429ac +size 183778 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..6deb5dc57860ec3bd5d10f1b1a629a8f2337f63d --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5501472e6900d500b9011043e9da3e56b43ca93138ddddd7d30ffd14019cc0d +size 125973 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..98225b2718912a9d33ff89aad0637e360fb7abe5 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1ae57929cdd9bb6903312438a14f64bc08e89c65f5e246db05035cf07db7fe +size 126426 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2f8f3cbcbaabf934f97679a718f60da9c8435510 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdad52969ae2f07b5469bd7e044a0695fa8cc894d443a0ad225dcdcce24af05 +size 117652 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..236a6de33e8f711836eeae84d79a242cce248822 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_4.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..2d1b2410d304c94899612196477936775277d1d0 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283ac4ad853b2cc54cfd0ce840ff359bcae22eda095d7d6bc95d9d7accabc804 +size 117611 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..95e76f4f82aa824bfd330d67a3e95c5dfa506a16 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_6.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..288323d467f0cb48bf8cfca274c0f83f18a76fd9 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_12172380859428428757_step_7.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png b/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..94007dd5844eda71a21d72e742dcd056c03c5754 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df110770b6561747ee834f3a72feda132140a83ce77e51468b81168f7dbb5ed2 +size 189283 diff --git a/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png b/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..20c19bb738c6f28195e8d1080f02678a1f6661d1 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_12224608131504749719_step_4.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png b/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..51a7bd7d2d591cb3319c2d3d7128623242f614bf --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3e417687a3b8ea6c5839e71b7efcbcb2d4296147871e1825a2fff1da4a56cb +size 189145 diff --git a/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png b/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..b290c0ce30ca674736b28d63905607940561f064 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_1307957808436696980_step_5.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..d18d3660b5c25cacbe7b8b106d0d34cda6468971 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_1.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c354ebbb449114a113443c2751fce9ff56b4e482 Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_2.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..f9aa6892d37026be39b4e397482af1a0a318a89f Binary files /dev/null and b/extra/content/aitw_images_absolute_single_step/episode_2247237893045084693_step_3.png differ diff --git a/extra/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png b/extra/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..dbe85142d65a2bb1e394d5b0a53cc82db81f8665 --- /dev/null +++ b/extra/content/aitw_images_absolute_single_step/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a906a6cd93e4b99188e3e54d8f30cadce867bf4c6dd1ac5eb270fa3fd6fbb0 +size 189701 diff --git a/extra/images-2.zip b/extra/images-2.zip new file mode 100644 index 0000000000000000000000000000000000000000..660713ead0952c2850f8f4f3d3570f072797e9b8 --- /dev/null +++ b/extra/images-2.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9e5c331ae1800f6a4da1fd25cb6df157be4bd83a9547556a9fcabdcaf905cc +size 1629252 diff --git a/extra/images.zip b/extra/images.zip new file mode 100644 index 0000000000000000000000000000000000000000..751b15d28af61906e78933ea9e964cf5119d708a --- /dev/null +++ b/extra/images.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf3718cf55bb3965a99b80e3c4eda5dc525e917e339beec093b48ee64bed5ac +size 1629202 diff --git a/visualizer.py b/visualizer.py new file mode 100644 index 0000000000000000000000000000000000000000..3cbfde4c45d2c5c736f83091cf6eb3c3c79b4096 --- /dev/null +++ b/visualizer.py @@ -0,0 +1,381 @@ +# import os +# import glob +# import json +# import base64 +# import pandas as pd +# import gradio as gr +# import re + +# # --- Data Loading --- +# ABS_DATA_PATH = "data" +# if os.path.exists(ABS_DATA_PATH): +# os.chdir(ABS_DATA_PATH) + +# AITW_DATA_ROOT = "." + +# MODEL_DISPLAY_MAPPING = { +# "gpt": "GPT-4o", +# "gemini": "Gemini 2.5 Pro", +# "qwen": "Qwen 2.5 VL 72B" +# } +# MODELS_IN_ORDER = ["gpt", "gemini", "qwen"] + +# def image_to_base64_markdown(img_path): +# if not img_path or not os.path.exists(img_path): +# return "Image not found" +# try: +# with open(img_path, "rb") as f: +# encoded = base64.b64encode(f.read()).decode("utf-8") +# ext = os.path.splitext(img_path)[-1].lstrip(".").lower() +# if ext not in ['png', 'jpg', 'jpeg', 'gif', 'bmp']: +# ext = 'png' +# return f"![image](data:image/{ext};base64,{encoded})" +# except Exception as e: +# print(f"Error encoding image {img_path}: {e}") +# return "Error loading image" + + +# def load_and_prepare_data(data_root_path): +# primary_model_dir = os.path.join(data_root_path, MODELS_IN_ORDER[0]) +# if not os.path.isdir(primary_model_dir): +# print(f"Error: Primary model directory not found at '{primary_model_dir}'") +# return pd.DataFrame() + +# all_rows = [] + +# json_files = glob.glob(os.path.join(primary_model_dir, "*.json")) + +# for json_path in json_files: +# with open(json_path, 'r', encoding='utf-8') as f: +# data = json.load(f) + +# for episode_id, episode_data in data.items(): +# episode_goal = episode_data.get("episode_goal", "N/A") + +# for step in episode_data.get("steps", []): +# question_block = step.get("questions", {}) +# question = question_block.get("question", "N/A") +# options = question_block.get("options", []) +# answer_index = question_block.get("correct_answer_index") + +# valid_answer_index = -1 +# if answer_index is not None: +# try: +# valid_answer_index = int(answer_index) +# except (ValueError, TypeError): +# pass + +# formatted_options = "\n".join(f"{i+1}. {opt}" for i, opt in enumerate(options)) + +# correct_option_text = "N/A" +# if 0 <= valid_answer_index < len(options): +# correct_option_text = options[valid_answer_index] + +# image_markdown = {} +# base_screenshot_path = step.get("screenshot_path", "").lstrip("/") + +# for model_key in MODELS_IN_ORDER: +# img_path = os.path.join(data_root_path, model_key, base_screenshot_path) +# image_markdown[model_key] = image_to_base64_markdown(img_path) + +# row = [ +# episode_goal, +# question, +# formatted_options, +# correct_option_text, +# image_markdown.get("gpt"), +# image_markdown.get("gemini"), +# image_markdown.get("qwen") +# ] +# all_rows.append(row) + +# headers = [ +# "Episode Goal", "Question", "Options", "Correct Option", +# MODEL_DISPLAY_MAPPING["gpt"], +# MODEL_DISPLAY_MAPPING["gemini"], +# MODEL_DISPLAY_MAPPING["qwen"] +# ] + +# return pd.DataFrame(all_rows, columns=headers) + + +# # --- CSS for the modal overlay --- +# modal_css = """ +# #image-modal { +# position: fixed; +# top: 0; +# left: 0; +# width: 100%; +# height: 100%; +# background-color: rgba(0, 0, 0, 0.8); +# display: flex; +# justify-content: center; +# align-items: center; +# z-index: 9999; +# } +# #image-modal .modal-content { +# background-color: white; +# padding: 20px; +# border-radius: 10px; +# max-width: 90vw; +# max-height: 90vh; +# display: flex; +# flex-direction: column; +# align-items: center; +# } +# #image-modal .modal-content img { +# max-width: 100%; +# max-height: calc(90vh - 80px); +# object-fit: contain; +# } +# #close-modal-btn { +# margin-top: 15px; +# } +# """ + +# # --- Gradio Interface --- +# with gr.Blocks(theme=gr.themes.Default(spacing_size=gr.themes.sizes.spacing_sm), +# css=modal_css) as demo: + +# gr.Markdown("# AITW Benchmark Visualizer") +# gr.Markdown("Visual comparison of model outputs for the Android in the Wild (AITW) benchmark.") + +# full_df_state = gr.State() + +# display_df = gr.DataFrame( +# headers=[ +# "Episode Goal", "Question", "Options", "Correct Option", +# MODEL_DISPLAY_MAPPING["gpt"], +# MODEL_DISPLAY_MAPPING["gemini"], +# MODEL_DISPLAY_MAPPING["qwen"] +# ], +# datatype=["markdown", "markdown", "markdown", "markdown", "markdown", "markdown", "markdown"], +# interactive=False, +# row_count=(20, "dynamic") +# ) + +# # --- The hidden modal for displaying the zoomed image --- +# with gr.Column(visible=False, elem_id="image-modal") as modal: +# # --- FIX: Replaced gr.Box with gr.Column --- +# with gr.Column(elem_classes=["modal-content"]): +# modal_image = gr.Image(interactive=False) +# close_modal_btn = gr.Button("Close", elem_id="close-modal-btn") + + +# def load_initial_data(): +# print(f"Current working directory: {os.getcwd()}") +# print("Loading and preparing AITW data...") +# prepared_df = load_and_prepare_data(AITW_DATA_ROOT) +# if prepared_df.empty: +# gr.Warning(f"No data loaded. Please check that the '{AITW_DATA_ROOT}' directory is structured correctly.") +# else: +# print(f"Successfully loaded {len(prepared_df)} steps.") +# return prepared_df, prepared_df + + +# def show_image_in_modal(df_state, evt: gr.SelectData): +# if evt.index is None or evt.value is None: +# return gr.update(visible=False), gr.update(visible=False) + +# if evt.index[1] not in [4, 5, 6]: +# return gr.update(visible=False), gr.update(visible=False) + +# match = re.search(r'\(data:image/[^)]+\)', evt.value) +# if not match: +# return gr.update(visible=False), gr.update(visible=False) + +# image_data_uri = match.group(0).strip('()') + +# return gr.update(visible=True), gr.update(value=image_data_uri, visible=True) + +# def close_modal(): +# return gr.update(visible=False), gr.update(visible=False) + +# # --- Event Wiring --- +# demo.load(fn=load_initial_data, inputs=None, outputs=[display_df, full_df_state]) +# display_df.select(fn=show_image_in_modal, inputs=[full_df_state], outputs=[modal, modal_image], show_progress=False) +# close_modal_btn.click(fn=close_modal, inputs=None, outputs=[modal, modal_image], show_progress=False) + + +# if __name__ == "__main__": +# demo.launch(share=True, debug=True) + +import os +import glob +import json +import pandas as pd +import gradio as gr +import re + +# --- Constants and Configuration --- +# Set the path to your data directory. +# The script will change its working directory to this path if it exists. +ABS_DATA_PATH = "data" +if os.path.exists(ABS_DATA_PATH): + os.chdir(ABS_DATA_PATH) + +AITW_DATA_ROOT = "." + +MODEL_DISPLAY_MAPPING = { + "gpt": "GPT-4o", + "gemini": "Gemini 2.5 Pro", + "qwen": "Qwen 2.5 VL 72B" +} +MODELS_IN_ORDER = ["gpt", "gemini", "qwen"] +MAX_CARDS_TO_DISPLAY = 50 # Let's create placeholders for up to 50 items. + +# --- Data Loading Logic (Unchanged) --- +def load_and_prepare_data(data_root_path): + """ + Loads step data from JSON files and prepares it as a list of dictionaries. + """ + primary_model_dir = os.path.join(data_root_path, MODELS_IN_ORDER[0]) + if not os.path.isdir(primary_model_dir): + print(f"Error: Primary model directory not found at '{primary_model_dir}'") + return [] + + all_steps = [] + json_files = glob.glob(os.path.join(primary_model_dir, "*.json")) + + for json_path in json_files: + with open(json_path, 'r', encoding='utf-8') as f: + data = json.load(f) + + for episode_id, episode_data in data.items(): + for step in episode_data.get("steps", []): + question_block = step.get("questions", {}) + question = question_block.get("question", "N/A") + options = question_block.get("options", []) + answer_index = question_block.get("correct_answer_index") + + correct_option_text = "N/A" + if answer_index is not None and 0 <= int(answer_index) < len(options): + correct_option_text = options[int(answer_index)] + + image_paths = {} + base_screenshot_path = step.get("screenshot_path", "").lstrip("/") + for model_key in MODELS_IN_ORDER: + img_path = os.path.join(data_root_path, model_key, base_screenshot_path) + image_paths[model_key] = img_path + + step_info = { + "episode_goal": episode_data.get("episode_goal", "N/A"), + "question": question, + "options": options, + "correct_option": correct_option_text, + "image_paths": image_paths + } + all_steps.append(step_info) + return all_steps + +# --- CSS for a better, full-width layout (Unchanged) --- +app_css = """ +.gradio-container { max-width: 95% !important; } +.comparison-card { + border: 1px solid #E5E7EB; border-radius: 8px; padding: 1rem; + margin-bottom: 1.5rem; box-shadow: 0 1px 3px 0 rgba(0,0,0,0.1), 0 1px 2px 0 rgba(0,0,0,0.06); +} +.card-title { + font-size: 1.1rem; font-weight: 600; color: #1F2937; + border-bottom: 1px solid #F3F4F6; padding-bottom: 0.5rem; margin-bottom: 1rem; +} +.info-column { min-width: 300px; } +.image-column .label-wrapper { display: none !important; } +.model-title { text-align: center; font-weight: 500; color: #4B5563; } +""" + +# --- Gradio Interface --- +with gr.Blocks(theme=gr.themes.Default(spacing_size=gr.themes.sizes.spacing_sm), css=app_css) as demo: + gr.Markdown("# AITW Benchmark Visualizer") + gr.Markdown("Visual comparison of model outputs for the Android in the Wild (AITW) benchmark.") + + # --- Create Static Placeholders --- + # We will create a fixed number of hidden cards and then make them visible with data. + placeholder_components = [] + for i in range(MAX_CARDS_TO_DISPLAY): + with gr.Group(visible=False) as card_group: + card_title = gr.Markdown(elem_classes=["card-title"]) + with gr.Row(): + with gr.Column(scale=1, elem_classes=["info-column"]): + info_md = gr.Markdown() + with gr.Column(scale=3): + with gr.Row(): + image_outputs = {} + for model_key in MODELS_IN_ORDER: + with gr.Column(elem_classes=["image-column"]): + gr.Markdown(f"

{MODEL_DISPLAY_MAPPING[model_key]}

") + image_outputs[model_key] = gr.Image( + show_label=False, show_download_button=True, interactive=False, + height=350, show_fullscreen_button=True + ) + placeholder_components.append({ + "card": card_group, + "title": card_title, + "info": info_md, + "images": image_outputs + }) + + # --- Function to update the placeholders --- + def load_and_update_ui(): + print("Loading and preparing AITW data...") + all_steps = load_and_prepare_data(AITW_DATA_ROOT) + + if not all_steps: + gr.Warning(f"No data loaded. Please check that the '{AITW_DATA_ROOT}' directory is structured correctly.") + else: + print(f"Successfully loaded {len(all_steps)} steps. Updating UI...") + + # Create a flat list of updates for all components + updates = [] + num_steps_to_show = min(len(all_steps), MAX_CARDS_TO_DISPLAY) + + for i in range(MAX_CARDS_TO_DISPLAY): + if i < num_steps_to_show: + step_data = all_steps[i] + + # Update card visibility and title + updates.append(gr.update(visible=True)) + updates.append(gr.update(value=f"### Main Goal: {step_data['episode_goal']}")) + + # Update text info + text_content = f""" + **Question:** +

{step_data['question']}

+ **Options:** +
    + {''.join([f'
  1. {opt}
    2. ' for opt in step_data['options']])} +
+ **Correct Answer:** +

{step_data['correct_option']}

+ """ + updates.append(gr.update(value=text_content)) + + # Update images + for model_key in MODELS_IN_ORDER: + img_path = step_data['image_paths'].get(model_key) + updates.append(gr.update(value=img_path if os.path.exists(img_path) else None)) + else: + # Hide unused placeholder cards + updates.append(gr.update(visible=False)) # Card group + updates.append(gr.update(value="")) # Title + updates.append(gr.update(value="")) # Info MD + for model_key in MODELS_IN_ORDER: + updates.append(gr.update(value=None)) # Images + + return updates + + # --- Flatten the list of placeholder components for the 'outputs' argument --- + output_components_flat = [] + for comp_dict in placeholder_components: + output_components_flat.append(comp_dict['card']) + output_components_flat.append(comp_dict['title']) + output_components_flat.append(comp_dict['info']) + for model_key in MODELS_IN_ORDER: + output_components_flat.append(comp_dict['images'][model_key]) + + # --- Event Wiring --- + demo.load(fn=load_and_update_ui, inputs=None, outputs=output_components_flat) + + +if __name__ == "__main__": + demo.launch(share=True, debug=True) \ No newline at end of file