ProCreations's picture
Publish validated ICML reproduction
6c3fe2a verified
Raw
History Blame Contribute Delete
14.6 kB
{
"claims": {
"claim1": {
"implementation": {
"basic_lean_sha256": "a908c060d1031506ac5844b838b819391a001474eee88a5df184fa9bdac97dc4",
"solving_server_sha256": "76a8760c1651b63d33d26c1d0097896f61881210efbfc576811ba79f38bd474b"
},
"mdp": {
"actions": 8,
"deterministic_violations": 0,
"hidden_history_mutant_detected": true,
"repeated_transition_comparisons": 8192,
"states": 256,
"terminal_reward_hits": 16
}
},
"claim2": {
"backward_sound_pairs": 3280,
"by_domain": [
{
"backward_sound": 1,
"forward_complete": 1,
"iff": 1,
"n": 0,
"pairs": 1
},
{
"backward_sound": 3,
"forward_complete": 3,
"iff": 2,
"n": 1,
"pairs": 4
},
{
"backward_sound": 9,
"forward_complete": 9,
"iff": 4,
"n": 2,
"pairs": 16
},
{
"backward_sound": 27,
"forward_complete": 27,
"iff": 8,
"n": 3,
"pairs": 64
},
{
"backward_sound": 81,
"forward_complete": 81,
"iff": 16,
"n": 4,
"pairs": 256
},
{
"backward_sound": 243,
"forward_complete": 243,
"iff": 32,
"n": 5,
"pairs": 1024
},
{
"backward_sound": 729,
"forward_complete": 729,
"iff": 64,
"n": 6,
"pairs": 4096
},
{
"backward_sound": 2187,
"forward_complete": 2187,
"iff": 128,
"n": 7,
"pairs": 16384
}
],
"complete_and_sound_pairs": 255,
"domains": [
0,
1,
2,
3,
4,
5,
6,
7
],
"expected_closed_forms": {
"iff": 255,
"one_direction": 3280,
"pairs": 21845
},
"forward_complete_pairs": 3280,
"forward_only_complete_but_unsound": 3025,
"predicate_pairs": 21845
},
"claim3": {
"accepted_true_memberships": 4097,
"answer_predicate_cases": 8194,
"by_domain": [
{
"accepted": 1,
"answer_predicate_cases": 2,
"n": 1,
"rejected": 1
},
{
"accepted": 4,
"answer_predicate_cases": 8,
"n": 2,
"rejected": 4
},
{
"accepted": 12,
"answer_predicate_cases": 24,
"n": 3,
"rejected": 12
},
{
"accepted": 32,
"answer_predicate_cases": 64,
"n": 4,
"rejected": 32
},
{
"accepted": 80,
"answer_predicate_cases": 160,
"n": 5,
"rejected": 80
},
{
"accepted": 192,
"answer_predicate_cases": 384,
"n": 6,
"rejected": 192
},
{
"accepted": 448,
"answer_predicate_cases": 896,
"n": 7,
"rejected": 448
},
{
"accepted": 1024,
"answer_predicate_cases": 2048,
"n": 8,
"rejected": 1024
},
{
"accepted": 2304,
"answer_predicate_cases": 4608,
"n": 9,
"rejected": 2304
}
],
"domains": [
1,
2,
3,
4,
5,
6,
7,
8,
9
],
"proof_field_omission_mutant_false_accepts": 4097,
"rejected_false_memberships": 4097,
"soundness_violations": 0
},
"claim4": {
"complete_and_sound_pairs": 255,
"complete_pairs": 3280,
"one_direction_only_invalid_pairs": 3025,
"sound_pairs": 3280
},
"claim5": {
"benchmark_counts": {
"formal_math500": 387,
"minif2f_solving": 375,
"putnam_solving": 324
},
"details": [
{
"benchmark": "formal_math500",
"byte_mismatches": [],
"records": 387
},
{
"benchmark": "minif2f_solving",
"byte_mismatches": [],
"records": 375
},
{
"benchmark": "putnam_solving",
"byte_mismatches": [],
"records": 324
}
],
"export_mutant_detected": true,
"lean_files_expected": 1086,
"lean_files_regenerated_byte_exact": 1086,
"records_total": 1086,
"records_with_required_schema": 1086,
"unique_global_fingerprints": 1086,
"unique_within_benchmarks": 1086
},
"claim6": {
"expected_maxima": {
"formal_math500": {
"denominator": 387,
"percent": 23.77,
"solved": 92
},
"minif2f_solving": {
"denominator": 375,
"percent": 27.47,
"solved": 103
},
"putnam_solving": {
"denominator": 324,
"percent": 0.31,
"solved": 1
}
},
"files": 18,
"maxima": {
"formal_math500": {
"denominator": 387,
"method": "proof_search/internlm2.5-step-prover",
"percent": 23.77,
"solved": 92
},
"minif2f_solving": {
"denominator": 375,
"method": "proof_search/internlm2.5-step-prover",
"percent": 27.47,
"solved": 103
},
"putnam_solving": {
"denominator": 324,
"method": "whole_proof_generation/deepseek-prover-v1.5",
"percent": 0.31,
"solved": 1
}
},
"method_problem_records_present": 5779,
"method_problem_slots": 6516,
"methods": [
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "prompting_methods/hybrid_cot",
"records_present": 387,
"solved": 60,
"solved_percent": 15.503875968992,
"submitted_without_equivalence": 4
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "prompting_methods/hybrid_cot",
"records_present": 375,
"solved": 81,
"solved_percent": 21.6,
"submitted_without_equivalence": 0
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "prompting_methods/hybrid_cot",
"records_present": 324,
"solved": 0,
"solved_percent": 0.0,
"submitted_without_equivalence": 1
},
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "prompting_methods/icl",
"records_present": 387,
"solved": 53,
"solved_percent": 13.695090439276,
"submitted_without_equivalence": 0
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "prompting_methods/icl",
"records_present": 375,
"solved": 82,
"solved_percent": 21.866666666667,
"submitted_without_equivalence": 0
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "prompting_methods/icl",
"records_present": 324,
"solved": 0,
"solved_percent": 0.0,
"submitted_without_equivalence": 0
},
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "proof_search/internlm2.5-step-prover",
"records_present": 387,
"solved": 92,
"solved_percent": 23.772609819121,
"submitted_without_equivalence": 75
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "proof_search/internlm2.5-step-prover",
"records_present": 375,
"solved": 103,
"solved_percent": 27.466666666667,
"submitted_without_equivalence": 51
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "proof_search/internlm2.5-step-prover",
"records_present": 324,
"solved": 0,
"solved_percent": 0.0,
"submitted_without_equivalence": 91
},
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "proof_search/leanstar",
"records_present": 378,
"solved": 91,
"solved_percent": 23.514211886305,
"submitted_without_equivalence": 81
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "proof_search/leanstar",
"records_present": 370,
"solved": 91,
"solved_percent": 24.266666666667,
"submitted_without_equivalence": 54
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "proof_search/leanstar",
"records_present": 324,
"solved": 0,
"solved_percent": 0.0,
"submitted_without_equivalence": 133
},
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "whole_proof_generation/deepseek-prover-v1.5",
"records_present": 147,
"solved": 86,
"solved_percent": 22.222222222222,
"submitted_without_equivalence": 56
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "whole_proof_generation/deepseek-prover-v1.5",
"records_present": 128,
"solved": 84,
"solved_percent": 22.4,
"submitted_without_equivalence": 41
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "whole_proof_generation/deepseek-prover-v1.5",
"records_present": 102,
"solved": 1,
"solved_percent": 0.308641975309,
"submitted_without_equivalence": 72
},
{
"benchmark": "formal_math500",
"denominator": 387,
"method": "whole_proof_generation/theoremllama",
"records_present": 378,
"solved": 62,
"solved_percent": 16.020671834625,
"submitted_without_equivalence": 60
},
{
"benchmark": "minif2f_solving",
"denominator": 375,
"method": "whole_proof_generation/theoremllama",
"records_present": 370,
"solved": 49,
"solved_percent": 13.066666666667,
"submitted_without_equivalence": 33
},
{
"benchmark": "putnam_solving",
"denominator": 324,
"method": "whole_proof_generation/theoremllama",
"records_present": 324,
"solved": 0,
"solved_percent": 0.0,
"submitted_without_equivalence": 54
}
],
"missing_records_counted_unsolved": 737,
"solving_rule_mutant_detected": true,
"submission_only_mutant_maxima": {
"formal_math500": 172,
"minif2f_solving": 154,
"putnam_solving": 133
}
}
},
"gates": [
{
"name": "pinned_input_hashes",
"passed": true
},
{
"name": "paper_and_code_tokens",
"passed": true
},
{
"name": "mdp_exhaustive_determinism",
"passed": true
},
{
"name": "mdp_hidden_history_control",
"passed": true
},
{
"name": "dfps_all_predicate_pairs",
"passed": true
},
{
"name": "dfps_forward_completeness",
"passed": true
},
{
"name": "dfps_optional_backward_boundary",
"passed": true
},
{
"name": "dfps_full_iff",
"passed": true
},
{
"name": "dfps_closed_form_oracle",
"passed": true
},
{
"name": "fps_exhaustive_cases",
"passed": true
},
{
"name": "fps_soundness",
"passed": true
},
{
"name": "fps_proof_field_control",
"passed": true
},
{
"name": "benchmark_counts",
"passed": true
},
{
"name": "benchmark_schema",
"passed": true
},
{
"name": "benchmark_uniqueness",
"passed": true
},
{
"name": "official_export_byte_identity",
"passed": true
},
{
"name": "export_mutation_control",
"passed": true
},
{
"name": "initial_baseline_files",
"passed": true
},
{
"name": "initial_baseline_records",
"passed": true
},
{
"name": "table_1_exact_maxima",
"passed": true
},
{
"name": "table_1_solved_rule_control",
"passed": true
}
],
"input_sha256": {
"current_archive": "b144a1051b840f4b7f59428151ba8bf6f27e7665a3b9f950d165c39055ef2315",
"initial_archive": "cef6b9340b797355ab6e3fb425ee02a1e6c2cc7b76eff6fc77d79bf6e99753fe",
"paper_pdf": "bba3d0293dda50476bd07d7dab987d4ed5ded4fa21132837f35c4feff72403e3",
"paper_source": "b08c84c35b90d0128fc6ff512b60b07ead29ef6de847c8834948df660b00034a"
},
"paper_id": "hgMZraPlSv",
"scope": {
"current_official_commit": "3e8bafd18a080fe01263ff93b9c3db78d993e1a1",
"initial_release_commit": "39489d1f0c32b521845429e1cb26c48639d8f823",
"lean_compilation_executed": false,
"lean_scope_note": "Lean 4 was not installed in this environment. The exact Lean/Pantograph implementation and proof source are pinned and structurally audited; finite semantics, all benchmark exports, and all archived Table-1 records are executed independently."
},
"source_audits": [
{
"artifact": "paper/method.tex",
"missing": [],
"required_tokens": 6
},
{
"artifact": "paper/appendix.proofs.tex",
"missing": [],
"required_tokens": 4
},
{
"artifact": "official/Basic.lean",
"missing": [],
"required_tokens": 7
},
{
"artifact": "official/solving_server.py",
"missing": [],
"required_tokens": 4
},
{
"artifact": "paper/evaluation.tex",
"missing": [],
"required_tokens": 4
},
{
"artifact": "paper/experiment.tex",
"missing": [],
"required_tokens": 3
},
{
"artifact": "paper/main.tex",
"missing": [],
"required_tokens": 4
}
],
"summary": {
"all_passed": true,
"passed": 21,
"total": 21
}
}