---

name: exps-logistic description: Documentation for the logistic regression MI estimation experiment (exps_logistic)

exps_logistic - Logistic Regression MI Estimation

Purpose

Measure mutual information (MI) lower bound between CoT rationales and problem parameters using multinomial logistic regression on embeddings. Compares code vs NL representations.

Key Files

Kind Presets (in config.py)

CopyFG_KINDS = {"add", "sub", "mul", "lcs", "knap", "rod", "ilp_assign", "ilp_prod", "ilp_partition"}

CLRS_KINDS = {
    "activity_selector", "articulation_points", "bellman_ford", "bfs",
    "binary_search", "bridges", "bubble_sort", "dag_shortest_paths",
    "dfs", "dijkstra", "find_maximum_subarray_kadane", "floyd_warshall",
    "graham_scan", "heapsort", "insertion_sort", "jarvis_march",
    "kmp_matcher", "lcs_length", "matrix_chain_order", "minimum",
    "mst_kruskal", "mst_prim", "naive_string_matcher", "optimal_bst",
    "quickselect", "quicksort", "segments_intersect",
    "strongly_connected_components", "task_scheduling", "topological_sort",
}

NPHARD_KINDS = {"edp", "gcp", "ksp", "spp", "tsp"}

EXTENDED_KINDS = FG_KINDS | CLRS_KINDS | NPHARD_KINDS  # 44 total kinds

Gamma Labels

Format: {kind}|d{digits}|b{bin} (e.g., knap|d8|b24)

• Fine-grained kinds have parsed bin values based on problem parameters
• CLRS/NP-hard kinds get bNA (no fine-grained parsing)

CLI Arguments

Generated Plots (in src/exps_logistic/notebooks/)

Key Results (Extended Kinds - Jan 9, 2026)

• 28 successful runs across 6 models
• Pearson r = 0.486, p = 0.009 (MI vs accuracy correlation)
• 500 unique labels across 44 problem kinds
• Code representation shows higher MI lower bounds than NL
• Models tested: claude-haiku-4.5, gemini-2.5-flash, gpt-4o-mini, llama-3.1-405b-instruct, ministral-14b-2512, qwen-2.5-coder-32b-instruct

Running Commands

Copy# Dev run (single model)
bash src/exps_logistic/run.sh

# Production run (all models, all seeds)
bash src/exps_logistic/prod_logistic.sh

# Generate plots
uv run --no-sync python src/exps_logistic/notebooks/generate_plots.py