Add Kilo Bridge for LLM-driven ARC task analysis and ONNX export

Add TRM solver NN executor with 14 transform types and ONNX export

Upload SKILLS/kilo_agent/references/howto.md

Upload abstract reasoning corpus rl - Google Search.pdf

delete fles

move fles into pemf folder

Fix pyproject.toml: tell hatchling where the package is (itt_solver/)

Add pyproject.toml for uv install

Add Lightning.ai multi-GPU notebook with Ollama + Qwen2.5-Coder (auto-shards across GPUs)

Add Jupyter notebook for LLM synthesis (NVIDIA NIM / GLM 4.7 / DeepSeek V4)

Fix: default model is z-ai/glm4.7 on NVIDIA NIM

Add NVIDIA NIM provider (DeepSeek V4 Pro, GLM) — free tier

Add multi-provider LLM solver: Gemini, DeepSeek, GLM, Ollama

Add arc_results/already_solved.json

Add scripts/merge_results.py

Add scripts/kaggle_llm_solver.py

Update results: 70/400 (17.5%) — ITT:16 + Predicate:25 + DSL:29, zero regressions

Add predicate enumeration engine: neighborhood rules + enclosed fill + object predicates — 70/400 (17.5%)

Fix fill_color=0 bug + mixed->recolor fallback (980 lines)

Fix fill_color=0 bug in ITT rule learning + add mixed→recolor fallback

Update results: 47/400 (11.8%) — ITT solves 16, DSL solves 31, +7 new from ITT physics"

Add ITT physics engine (960 lines): PhiField, ρ_q, SigmaResidue, Fan Signatures, rule learning, FieldInvariants — 47/400 solved

Add ITT physics engine: PhiField dual-field, ρ_q boundary charge, SigmaResidue, Fan Signatures, TransformationRule, FieldInvariants — 47/400 (11.8%)"

Update LEARNING.md — add ITT source repo findings, object layer lessons, architecture direction

Update results: 40/400 (10.0%) solved — +9 new tasks, 0 regressions, greedy stacker working

Wire 14 new transforms (object + fill + connect + compress) into default_atomic_factory

Add greedy stacker: overlay(T1(x), T2(x)) composition after depth-1 beam search

Fix transforms.py upload — 33 transforms including object extraction, fill, connect, compress, proximity"

Add 14 new transforms: object extraction, fill interior, connect, compress, proximity, draw border — 33 total

Add object layer: connected components, color splitting, list reducers, overlay/paint/underpaint

Add ARC-AGI evaluation results: 31/400 (7.8%) solved, 17s total

Add ARC-AGI bulk evaluation script

Update LEARNING.md with lessons from σ=0 breakthrough

Update TODO.md — σ=0 achieved, all blockers resolved, document findings"

Add comprehensive test suite for all transforms (40 tests)

Fix wrong target in experiments_analysis.py and fix_and_inspect_logs.py (row 7 corrected)

Fix wrong target in entrypoint.py (row 7 corrected to match real ARC task 007bbfb7)

Fix wrong target in fix_and_inspect_logs.py (row 7 corrected)

Enriched default_atomic_factory with Kronecker, mirror, upscale, stack, symmetry transforms

Add 19 new transforms: Kronecker, mirror tiles, upscale, gravity, color ops, crop, transpose

Major update: fix wrong target, dual-strategy beam search, 19 new transforms, σ=0 achieved\n\n- Fixed wrong target for example1 (4 cells off vs real ARC task 007bbfb7)\n- Added dual-strategy beam: tries transforms on both resized AND original input\n- Added 19 new transforms: Kronecker, mirror tiles, upscale, gravity, color ops\n- Solver now achieves σ=0 on all 6 pairs of ARC task 007bbfb7"

Update TODO.md — mark completed items, add plan for σ-reduction blocker and next steps

Fix #8: Delete old README.md.md (replaced by README.md)

Fix #8: Rename README.md.md to README.md in itt_solver/

Fix #6: Correct README.md paths to match actual repo structure

Fix #7: Remove committed .pyc files from repo

Fix #7: Add .gitignore to exclude __pycache__ and .pyc files

Fix #2: Clean up duplicate imports and paste blocks in solver_core.py

Fix #1: Remove duplicate Transform class, import from solver_core

Fix #5: Use real task target instead of all-zeros in minimal_runner.py