{"artifacts": {"directed-0.jsonl": "5bc49b8f8534ef2c33e84aec6e4e2fb205da2103138a86a933ec10beacf245e6", "directed-1.jsonl": "a4c3d8872451be32cfd8ba9831ceec791b625d1df2dea3268965f26c1a3f1734", "directed-2.jsonl": "54627a794c450ca9a9f6aecbde31bf867425c5f3b072681e7b8b912353bd2b81", "reference.jsonl": "ce8b9dacbdf8fd812dcc08e8c676fc6bcf61acc752eb0d6653fc7a7f86fe8802", "sequential-0.jsonl": "746abf0ae1982d2c6cb247f06a67d575526052c8d8e7f26dc7f723a94acf86a2", "sequential-1.jsonl": "746abf0ae1982d2c6cb247f06a67d575526052c8d8e7f26dc7f723a94acf86a2", "sequential-2.jsonl": "746abf0ae1982d2c6cb247f06a67d575526052c8d8e7f26dc7f723a94acf86a2", "uniform-0.jsonl": "37ef9ceb7925f84420c588eb84b94f987d60de3331108d8f25696d0e611925c9", "uniform-1.jsonl": "9dad953ecf829e6915b7a5e79ad9ad6882c5beec05d16805f82519293fb09173", "uniform-2.jsonl": "47898837881e27d46262eac2c692066583e473879614310f5a37a90a9b6cad28"}, "claim_level": "bounded_policy_comparison", "config": {"budget": 64, "max_n": 10000, "seeds": [0, 1, 2]}, "created_at": "2026-10-09T22:04:24.427468+00:00", "metric": "recall of bottom 5% observed/asymptotic unordered partition ratios; ties included", "protocol": "docs/experiments/goldbach-policy-comparison.md", "provenance": {"commit": "c53ed23fd94f6b5b01f7a3073b6776510cfe1f7d", "dependencies": {"mpmath": "1.3.0", "numba": "0.66.0", "numpy": "2.4.6", "pandas": "3.0.5", "scikit-learn": "1.9.0", "scipy": "1.18.0", "sympy": "1.14.0"}, "machine": "AMD64", "platform": "Windows-11-10.0.26200-SP0", "python": "3.13.13", "source_sha256": {"packages/python/codebase/collatzx/Analytics/Analytics.py": "d191bcffa56934e529d452310bbb9d2631092d91a5dada58b2dcd5e4eed96dc8", "packages/python/codebase/collatzx/Analytics/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/bifurcation/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/bifurcation/bifurcation.py": "099d3189f77a9623782376e84fd029fadfb17564dc7b240a70049783b9ec23bf", "packages/python/codebase/collatzx/boundary/Boundary.py": "79ba965f643cbf0a6137dc73e2ad5fdeb4c0d76f6af33cc2aec14bd601b7b5e4", "packages/python/codebase/collatzx/boundary/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/pipeline/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/pipeline/pipeline.py": "d5a877c405f4cde23979961b3bbe1fa015ef1a40a379770172665bbf9a16ad7a", "packages/python/codebase/collatzx/prime_graph/PrimeGraph.py": "f882a88ad6186730bc2ecfb05ea10ca6a61b6d10300b50ba7d823c11672b1ecd", "packages/python/codebase/collatzx/prime_graph/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/processing/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/processing/speed.py": "eefcf8e53e9830bfb47016088993c677f394b4411a351cd70c377149bf3103fa", "packages/python/codebase/collatzx/rare_event/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/rare_event/rareeventx.py": "55d441c4b4892635466c5e6189dd2e17a99e7292eceea1d4877c6093b1684566", "packages/python/codebase/collatzx/rare_event/results/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/rare_event/results/results.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/collatzx/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/cross_engine_analysis/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/cross_engine_analysis/cross_engine.py": "8119c07daeed9dc1c4d7df86699b0d4acb5bd601f41d5d0c3eb053627d91e7ff", "packages/python/codebase/falsification_engine/engine.py": "bcc04e7d508c546a444bc97c19a83e4e0f66ee39ed26c20ce62889307b153cfc", "packages/python/codebase/falsification_engine/riemann_falsifier.py": "0b1bf5150abbaea0e92117bc4b1ac6b5e211c4f60cae7742eefb4beb47cdba88", "packages/python/codebase/falsification_engine/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/falsification_engine/calibration.py": "31b9c184d932a3378cac283e00914cbef89788b575619d082bcaf13c74fa3a66", "packages/python/codebase/goldbachx/algebraic_extensions/AlgebraicExtensions.py": "4fa171816fa2a567535626ad56f0d312bccdcbd2fad1a425cb94f126d7af2618", "packages/python/codebase/goldbachx/algebraic_extensions/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/goldbach_reasoner/SymbolicGoldbachReasoner.py": "8c9e0ba3e4b2368e2269ec66c5bead848bac8b8ad41f0286b7710bd3190a0792", "packages/python/codebase/goldbachx/goldbach_reasoner/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/meta_variant/MetaVariantSynthesizer.py": "77acbb77555b0a2ad0be7ca048a754400614ccb97cdbc6b12295bddff9bbd8cd", "packages/python/codebase/goldbachx/meta_variant/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/partition_enumerator/PartitionEnumerator.py": "13ddb85757aa8b12c05e4f330b780ce19e24bae51fd7474ba22599c22cb0a5ed", "packages/python/codebase/goldbachx/partition_enumerator/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/sequence_generator/SequenceGenerator.py": "a3aadaab7f0d0fde328ddb4b105894e92e145cdce4cbd1c968783247b2bd89ec", "packages/python/codebase/goldbachx/sequence_generator/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/sieve_engine/SieveEngine.py": "6e15edec76256e25bff61103d182de80156fd6ec5809d702046034e59155ab3d", "packages/python/codebase/goldbachx/sieve_engine/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/goldbachx/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/contour_truth/ContourTruth.py": "89a6942f6178835ad1c44cc14c04858671e8f8df94072dbdf69cc56d0ef2f56c", "packages/python/codebase/reimannx/contour_truth/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/keiper_li/KeiperLi.py": "08e97e756de02f1e1102066847df5c056f6aac5899c3245150930d3f801e4c65", "packages/python/codebase/reimannx/keiper_li/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/prime_echos/PrimeEchos.py": "94cc90817da1153b708827726ce51756966d1882f4332eb792f4c75300052090", "packages/python/codebase/reimannx/prime_echos/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/turing_threshold/TuringThreshold.py": "cad40fc8e847e765280c4416a911b62e290c774cc6ff61570402c80f35e20d84", "packages/python/codebase/reimannx/turing_threshold/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/ZeroProperties.py": "8dde7662af2eecf987745302b173e46aead6fc5e2d4fbcf8f617879fd5617ee0", "packages/python/codebase/reimannx/zero_properties/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/plugins/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/plugins/plugins.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/reports/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/reports/reports.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/rhvt_cache/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zero_properties/rhvt_cache/rhvt_cache.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/zeta_mirror/ZetaMirror.py": "f631aa395503c7ce61595540c4f8be2acfb356bf4b1da23e11f0ba6ec36a3c80", "packages/python/codebase/reimannx/zeta_mirror/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/reimannx/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "packages/python/codebase/benchmark.py": "92fd3a6a35b16f1f111919fbc0f6a1f1af98f307c3245966c96cad161f0cf1c1", "packages/python/codebase/cli.py": "525b49e2b5b793d97082d7b6f2a985fce2bcff785acf2c2e54582202b547f133", "packages/python/codebase/lean_export.py": "0cf7076da5ba333fc18f9b0780012c504a5c604fde3bc17531d300b30ea5b4c9", "packages/python/codebase/verified_runs.py": "f398feb191197a6d17e04d06c76d363f00d2125cccdeec6fff1dd9c6677b63dc"}, "tracked_tree_dirty": true}, "rare_set_size": 250, "reference_seconds": 0.19740080000337912, "reference_size": 4999, "reproduce": "python -m codebase.cli benchmark goldbach --max-n 10000 --budget 64 --seeds 0 1 2 --output-dir results/reproduction", "runs": [{"elapsed_s": 0.027937200000451412, "evaluated": 64, "ledger": "directed-0.jsonl", "median_candidate": 3707.0, "median_ratio": 1.214285155566695, "min_ratio": 0.7277806780387273, "policy": "directed", "rare_hits": 19, "rare_recall": 0.076, "seed": 0, "zero_partition_count": 0}, {"elapsed_s": 0.003155500002321787, "evaluated": 64, "ledger": "uniform-0.jsonl", "median_candidate": 5446.0, "median_ratio": 1.2801909007242656, "min_ratio": 0.6571197783724594, "policy": "uniform", "rare_hits": 8, "rare_recall": 0.032, "seed": 0, "zero_partition_count": 0}, {"elapsed_s": 0.0005650000020978041, "evaluated": 64, "ledger": "sequential-0.jsonl", "median_candidate": 67.0, "median_ratio": 1.205765511045388, "min_ratio": 0.3897252228151253, "policy": "sequential", "rare_hits": 26, "rare_recall": 0.104, "seed": 0, "zero_partition_count": 0}, {"elapsed_s": 0.0029900000008638017, "evaluated": 64, "ledger": "directed-1.jsonl", "median_candidate": 4877.0, "median_ratio": 1.2351485224019196, "min_ratio": 0.7277806780387273, "policy": "directed", "rare_hits": 12, "rare_recall": 0.048, "seed": 1, "zero_partition_count": 0}, {"elapsed_s": 0.0029635999962920323, "evaluated": 64, "ledger": "uniform-1.jsonl", "median_candidate": 4502.0, "median_ratio": 1.286983314466085, "min_ratio": 1.1150925458996015, "policy": "uniform", "rare_hits": 4, "rare_recall": 0.016, "seed": 1, "zero_partition_count": 0}, {"elapsed_s": 0.0005546000029426068, "evaluated": 64, "ledger": "sequential-1.jsonl", "median_candidate": 67.0, "median_ratio": 1.205765511045388, "min_ratio": 0.3897252228151253, "policy": "sequential", "rare_hits": 26, "rare_recall": 0.104, "seed": 1, "zero_partition_count": 0}, {"elapsed_s": 0.0029966000001877546, "evaluated": 64, "ledger": "directed-2.jsonl", "median_candidate": 4577.0, "median_ratio": 1.217508986198905, "min_ratio": 0.7277806780387273, "policy": "directed", "rare_hits": 19, "rare_recall": 0.076, "seed": 2, "zero_partition_count": 0}, {"elapsed_s": 0.002854899998055771, "evaluated": 64, "ledger": "uniform-2.jsonl", "median_candidate": 5312.0, "median_ratio": 1.276651754631637, "min_ratio": 0.9499584562010389, "policy": "uniform", "rare_hits": 4, "rare_recall": 0.016, "seed": 2, "zero_partition_count": 0}, {"elapsed_s": 0.0005535999953281134, "evaluated": 64, "ledger": "sequential-2.jsonl", "median_candidate": 67.0, "median_ratio": 1.205765511045388, "min_ratio": 0.3897252228151253, "policy": "sequential", "rare_hits": 26, "rare_recall": 0.104, "seed": 2, "zero_partition_count": 0}], "schema_version": "proofx.goldbach_benchmark.v1", "sieve_seconds": 0.000775100001192186, "timing_scope": "selection plus exact counts and ratios; excludes shared sieve, oracle and file I/O"}