Delete cofiber_circuit.safetensors with huggingface_hub

Cofiber detection circuit: depth-3 threshold network, 61520 INT8 params, 2.18M gates

Fix priority encoder circuit logic

Add IEEE 754 float16/float32 arithmetic circuits

Parameterize CPU circuits for N-bit data and address widths

Standardize build output filenames with explicit bit widths

Add 32-bit arithmetic support with cascaded byte comparison

Add 32-bit ALU support with 1KB memory profile

Move SmolLM2 analysis files into smollm2 subfolder

Add trained hybrid extractor model (64% accuracy)

Add operator-aware splitting for word number extraction

Switch HybridExtractor from 256-way softmax to digit prediction

Add HybridExtractor for digit lookup + word number learning

Add PositionalDigitExtractor with direct digit supervision

Add SmolLM2-360M architecture analysis, fix PositionExtractor tokenization

Refactor LLM integration: consolidate training scripts, add extraction strategies

Remove verbose batch progress output from train_llm.py

Add LLM hidden state extraction training (train_llm.py)

Clarify proof-of-concept status: circuit validation complete, LLM integration in progress

Validate proof of concept: 100% arithmetic fitness with frozen circuits

Add LLM integration proof-of-concept framework and baseline evaluation

Remove duplicate function definitions in build.py

Add (A + B) × C expression circuit (parenthetical grouping)

Fold threshold_cpu.py into eval.py

Add order of operations circuit (arithmetic.expr_add_mul)

Add 3-operand adder circuit (arithmetic.add3_8bit)

Update roadmap: remove completed items, add 16-bit and float

Add configurable memory partitioning for LLM integration

Add PUSH/POP/RET stack operation tests

Add barrel shifter and priority encoder tests

Fix DEC eval test, add INC/DEC/NEG/ROL/ROR tests

Add INC, DEC, NEG, ROL, ROR, stack ops, barrel shifter, priority encoder

Update README: reflect implemented MUL, DIV, SHL, SHR, comparators

Add SHL, SHR, MUL, DIV, and comparator circuits

Remove Python fallbacks, add Extension Roadmap

Remove completed TODO section from README

Wire all 8 conditional jumps into CPU via imm8[2:0] encoding

Remove eval/ folder, move prune_weights.py to root

Add unified eval.py consolidating iron_eval and comprehensive_eval

Remove routing/ folder, add schema docs to build.py

Add unified build.py with .inputs metadata for all gates

Consolidate CPU into threshold_cpu.py at root

Consolidate routing modules into single routing.py

Add execution model to README, remove tensors.txt and todo.md

Integrate LLM guide into README, remove llm folder

Consolidate LLM modules into single core.py

Consolidate CPU modules into single core.py

Revert "Unify eval files into single eval.py with 100% tensor coverage"

Unify eval files into single eval.py with 100% tensor coverage

Merge origin/main