{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT","short_pith_number":"pith:QD35AOPB","canonical_record":{"source":{"id":"2604.03922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T01:15:57Z","cross_cats_sorted":[],"title_canon_sha256":"1933a0131b8773a4f2fda92822fbd59f27c840ed9cbd55f9c42c32fe9d3ff427","abstract_canon_sha256":"2078fc0156308494a9f1d6959e2ee50ae782be1829cc5ae74c6197da9bcd0210"},"schema_version":"1.0"},"canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","source":{"kind":"arxiv","id":"2604.03922","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03922","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03922v2","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03922","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"QD35AOPB5NUK","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"QD35AOPB5NUKK4XV","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"QD35AOPB","created_at":"2026-07-14T01:20:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT","target":"record","payload":{"canonical_record":{"source":{"id":"2604.03922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T01:15:57Z","cross_cats_sorted":[],"title_canon_sha256":"1933a0131b8773a4f2fda92822fbd59f27c840ed9cbd55f9c42c32fe9d3ff427","abstract_canon_sha256":"2078fc0156308494a9f1d6959e2ee50ae782be1829cc5ae74c6197da9bcd0210"},"schema_version":"1.0"},"canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:58.244780Z","signature_b64":"d3yTEY0EaM55jSadFmYUc8tFdCJTm4r6phpKkoyjWnGhTro7OByKyFL4BskY3tFEbho4g9ofUAi0TtNufHgPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","last_reissued_at":"2026-07-14T01:20:58.243140Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:58.243140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.03922","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jS+vq8qjevk8tKKHpneskCG8opcTOF8PJSbGfBSgJnNoxY9OuXH7l/cnlA5UjvWXCPLBFOTzGJoJRqGqWKSgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:45:30.171126Z"},"content_sha256":"de5cbabed55a48bb745208114d9ccf64e4dc54461a3d9610fd56d3d987954dc6","schema_version":"1.0","event_id":"sha256:de5cbabed55a48bb745208114d9ccf64e4dc54461a3d9610fd56d3d987954dc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hui Sun, Ming Li, Ren-Biao Liu, Xin-Ye Li, Yali Du, Yun-Ji Zhang, Zheng Xie","submitted_at":"2026-04-05T01:15:57Z","abstract_excerpt":"Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test correctness requires knowing which codes are correct, creating a \\emph{circular dependency}. Our key insight is that we need not determine test correctness at all: \\emph{test votes should rank, not merely count}. What matters is not how many codes pass a test, but whether the test can \\emph{distinguish} correct from incorrect code. We break the"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Expected leave-one-out AUC of test j equals 1/2 plus a positive coefficient times the test's discriminative power δ_j = α_j − β_j (Theorem 3); consequently the closed-form ACES-C weights recover the sign of δ_j in expectation under Assumption 4 and approximate the oracle signal-to-noise ratio (Theorem 6, Corollary 8), while both ACES variants achieve state-of-the-art Pass@k among execution-only methods on HumanEval, HumanEval+ and MBPP.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Assumption 4: the average discriminative power of the generated test pool is positive and large enough that leaving any single test out still leaves the remaining ranking better than random (¯δ > 2√(ln 2 / m)). The closed-form guarantees of ACES-C and the positivity of the LOO-AUC coefficients rest on this average-quality condition; when it fails, only the iterative ACES-O variant is claimed to remain effective.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Leave-one-out AUC of each test against the ranking induced by the remaining tests is proportional to that test's latent discriminative power, yielding closed-form and optimized weights that raise Pass@k.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"431ab1cad14b0bca270cb31997212d25aceabef2b6527325a1036421c7a2ef4f"},"source":{"id":"2604.03922","kind":"arxiv","version":2},"verdict":{"id":"0ce40174-c50b-4edb-967f-bbf357a35dce","model_set":{"reader":"grok-4.5"},"created_at":"2026-07-13T11:58:43.055488Z","strongest_claim":"Expected leave-one-out AUC of test j equals 1/2 plus a positive coefficient times the test's discriminative power δ_j = α_j − β_j (Theorem 3); consequently the closed-form ACES-C weights recover the sign of δ_j in expectation under Assumption 4 and approximate the oracle signal-to-noise ratio (Theorem 6, Corollary 8), while both ACES variants achieve state-of-the-art Pass@k among execution-only methods on HumanEval, HumanEval+ and MBPP.","one_line_summary":"Leave-one-out AUC of each test against the ranking induced by the remaining tests is proportional to that test's latent discriminative power, yielding closed-form and optimized weights that raise Pass@k.","pipeline_version":"pith-pipeline@v1.1.0-grok45","weakest_assumption":"Assumption 4: the average discriminative power of the generated test pool is positive and large enough that leaving any single test out still leaves the remaining ranking better than random (¯δ > 2√(ln 2 / m)). The closed-form guarantees of ACES-C and the positivity of the LOO-AUC coefficients rest on this average-quality condition; when it fails, only the iterative ACES-O variant is claimed to remain effective.","pith_extraction_headline":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03922/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0ce40174-c50b-4edb-967f-bbf357a35dce"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zou1Iqv0yQMDm/2yMNTTNemhE/pm7tOmMu741MBdz4b5/1IlrAcdVAPDi8YXz5l3ufFMCwWKBl4XQendusrpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:45:30.171825Z"},"content_sha256":"5f3ebc2a0804af568c4cb7b355f988e58dd9e20dfaede936e52c7da4183f2a27","schema_version":"1.0","event_id":"sha256:5f3ebc2a0804af568c4cb7b355f988e58dd9e20dfaede936e52c7da4183f2a27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/bundle.json","state_url":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T05:45:30Z","links":{"resolver":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT","bundle":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/bundle.json","state":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2078fc0156308494a9f1d6959e2ee50ae782be1829cc5ae74c6197da9bcd0210","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T01:15:57Z","title_canon_sha256":"1933a0131b8773a4f2fda92822fbd59f27c840ed9cbd55f9c42c32fe9d3ff427"},"schema_version":"1.0","source":{"id":"2604.03922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03922","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03922v2","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03922","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"QD35AOPB5NUK","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"QD35AOPB5NUKK4XV","created_at":"2026-07-14T01:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"QD35AOPB","created_at":"2026-07-14T01:20:58Z"}],"graph_snapshots":[{"event_id":"sha256:5f3ebc2a0804af568c4cb7b355f988e58dd9e20dfaede936e52c7da4183f2a27","target":"graph","created_at":"2026-07-14T01:20:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Expected leave-one-out AUC of test j equals 1/2 plus a positive coefficient times the test's discriminative power δ_j = α_j − β_j (Theorem 3); consequently the closed-form ACES-C weights recover the sign of δ_j in expectation under Assumption 4 and approximate the oracle signal-to-noise ratio (Theorem 6, Corollary 8), while both ACES variants achieve state-of-the-art Pass@k among execution-only methods on HumanEval, HumanEval+ and MBPP."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Assumption 4: the average discriminative power of the generated test pool is positive and large enough that leaving any single test out still leaves the remaining ranking better than random (¯δ > 2√(ln 2 / m)). The closed-form guarantees of ACES-C and the positivity of the LOO-AUC coefficients rest on this average-quality condition; when it fails, only the iterative ACES-O variant is claimed to remain effective."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Leave-one-out AUC of each test against the ranking induced by the remaining tests is proportional to that test's latent discriminative power, yielding closed-form and optimized weights that raise Pass@k."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right."}],"snapshot_sha256":"431ab1cad14b0bca270cb31997212d25aceabef2b6527325a1036421c7a2ef4f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test correctness requires knowing which codes are correct, creating a \\emph{circular dependency}. Our key insight is that we need not determine test correctness at all: \\emph{test votes should rank, not merely count}. What matters is not how many codes pass a test, but whether the test can \\emph{distinguish} correct from incorrect code. We break the","authors_text":"Hui Sun, Ming Li, Ren-Biao Liu, Xin-Ye Li, Yali Du, Yun-Ji Zhang, Zheng Xie","cross_cats":[],"headline":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T01:15:57Z","title":"ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03922","kind":"arxiv","version":2},"verdict":{"created_at":"2026-07-13T11:58:43.055488Z","id":"0ce40174-c50b-4edb-967f-bbf357a35dce","model_set":{"reader":"grok-4.5"},"one_line_summary":"Leave-one-out AUC of each test against the ranking induced by the remaining tests is proportional to that test's latent discriminative power, yielding closed-form and optimized weights that raise Pass@k.","pipeline_version":"pith-pipeline@v1.1.0-grok45","pith_extraction_headline":"You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right.","strongest_claim":"Expected leave-one-out AUC of test j equals 1/2 plus a positive coefficient times the test's discriminative power δ_j = α_j − β_j (Theorem 3); consequently the closed-form ACES-C weights recover the sign of δ_j in expectation under Assumption 4 and approximate the oracle signal-to-noise ratio (Theorem 6, Corollary 8), while both ACES variants achieve state-of-the-art Pass@k among execution-only methods on HumanEval, HumanEval+ and MBPP.","weakest_assumption":"Assumption 4: the average discriminative power of the generated test pool is positive and large enough that leaving any single test out still leaves the remaining ranking better than random (¯δ > 2√(ln 2 / m)). The closed-form guarantees of ACES-C and the positivity of the LOO-AUC coefficients rest on this average-quality condition; when it fails, only the iterative ACES-O variant is claimed to remain effective."}},"verdict_id":"0ce40174-c50b-4edb-967f-bbf357a35dce"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:de5cbabed55a48bb745208114d9ccf64e4dc54461a3d9610fd56d3d987954dc6","target":"record","created_at":"2026-07-14T01:20:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2078fc0156308494a9f1d6959e2ee50ae782be1829cc5ae74c6197da9bcd0210","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T01:15:57Z","title_canon_sha256":"1933a0131b8773a4f2fda92822fbd59f27c840ed9cbd55f9c42c32fe9d3ff427"},"schema_version":"1.0","source":{"id":"2604.03922","kind":"arxiv","version":2}},"canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","first_computed_at":"2026-07-14T01:20:58.243140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:20:58.243140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d3yTEY0EaM55jSadFmYUc8tFdCJTm4r6phpKkoyjWnGhTro7OByKyFL4BskY3tFEbho4g9ofUAi0TtNufHgPDA==","signature_status":"signed_v1","signed_at":"2026-07-14T01:20:58.244780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de5cbabed55a48bb745208114d9ccf64e4dc54461a3d9610fd56d3d987954dc6","sha256:5f3ebc2a0804af568c4cb7b355f988e58dd9e20dfaede936e52c7da4183f2a27"],"state_sha256":"42afb84699b87e868e7885bed1419d361e29481613dbad7d43bec9cec000b744"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFQ2dmWYeleS1JvAuN+rb3ChHoWQVod1GE0KPTVRdafh+cbmSnuGeVDynw+Z7Loeccb6k8JwtH9DYQcgASwSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:45:30.175647Z","bundle_sha256":"e37a2e30eb27756bc028de147bff43d179f5b77bdd5241863108da0e2645761c"}}