Commit History

Rename Fock-Attention to 'Fock Attention (MLP V_theta)', fix stale pre-causal-leak-fix 9.30 PPL comparisons, add V_theta-vs-exchange-mechanism insight
6ae0deb
verified

dimitarpg13 commited on

Remove deprecated depth-cond OpenWebText row (retired due to causal leak) from SPLM Family Overview table
0099be8
verified

dimitarpg13 commited on

Move Verlet-instability row to the bottom of the SPLM Family Overview table
babdf2b
verified

dimitarpg13 commited on

Reorder SPLM Family Overview: all TinyStories rows before all OpenWebText rows
675915d
verified

dimitarpg13 commited on

Sync SPLM Family Overview table across the collection (order, completeness, corpus column)
a577161
verified

dimitarpg13 commited on

add effective damping value to parameter table row
6c688a5
verified

dimitarpg13 commited on

fix: use Unicode γ + HTML <sub> for gamma_eff (HF inline-math brace rendering issue)
5e28511
verified

dimitarpg13 commited on

clarify effective damping: LayerNorm makes gamma_eff << gamma_nominal (heavily underdamped)
ba8e2e4
verified

dimitarpg13 commited on

Add riemannian-geodesics tag
27b79e1
verified

dimitarpg13 commited on

fix: remove outer paren before \( math delimiter in CoT bullet
20b6bac
verified

dimitarpg13 commited on

fix: remove outer parens before math delimiters; revert to bare underscore
711eb9e
verified

dimitarpg13 commited on

fix: escape _ as \_ in prose inline math to prevent italic parsing
ed83d4b
verified

dimitarpg13 commited on

fix: use $...$ delimiters for inline math in bullet points
e8bf0d3
verified

dimitarpg13 commited on

docs: add damped Riemannian geometry framework (June 2026 diagnostic battery results)
c71b1a5
verified

dimitarpg13 commited on

Upload README.md with huggingface_hub
bd9489b
verified

dimitarpg13 commited on

Add links to Colab notebook and training results in companion repo
27e52f1
verified

dimitarpg13 commited on

Update Multi-Xi SPLM PPL to 11.51 (16k rerun) and add checkpoint docs
4b362ef
verified

dimitarpg13 commited on

Document available checkpoint and training artifacts in model card
f82be7e
verified

dimitarpg13 commited on

Add training_summary.md (Multi-Xi PARFLM, PPL 12.06)
10a57ef
verified

dimitarpg13 commited on

Add loss_curve.png (Multi-Xi PARFLM, PPL 12.06)
4a29ef8
verified

dimitarpg13 commited on

Add training_log.jsonl (Multi-Xi PARFLM, PPL 12.06)
434b492
verified

dimitarpg13 commited on

Add checkpoint/model.pt (Multi-Xi PARFLM, PPL 12.06)
61fdfe1
verified

dimitarpg13 commited on

Add 'riemannian-geometry' tag
78b32eb
verified

dimitarpg13 commited on

Add 'constant-memory-inference' tag
b426261
verified

dimitarpg13 commited on

Add 'non-transformer' tag
e228511
verified

dimitarpg13 commited on

Add 'attention-free' tag
279c8a1
verified

dimitarpg13 commited on

Add Geometric Capabilities section: Riemannian metric, geodesic reasoning, hallucination detection, native CoT
617f6b4
verified

dimitarpg13 commited on

Fix KaTeX rendering: remove bold wrapping and adjacent parens around math in table cells
84c8f88
verified

dimitarpg13 commited on

Add 'Why Not a Transformer?' section with O(1) complexity, parameter comparison, and runtime capacity figure; fix KaTeX inline math; add Inference column to family table
cab25f5
verified

dimitarpg13 commited on

Add runtime information capacity figure
58af667
verified

dimitarpg13 commited on

Fix inline math: use \\(...\\) for KaTeX on HuggingFace
0f262c4
verified

dimitarpg13 commited on

Fix math notation: convert plain text to LaTeX
9ddcdab
verified

dimitarpg13 commited on

Initial model card and config for semsimula-parflm-multixi
90d1781
verified

dimitarpg13 commited on

initial commit
114405c
verified

dimitarpg13 commited on