{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT","short_pith_number":"pith:QD35AOPB","schema_version":"1.0","canonical_sha256":"80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec","source":{"kind":"arxiv","id":"2604.03922","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.03922","created_at":"2026-07-14T01:20:58.243603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.03922v2","created_at":"2026-07-14T01:20:58.243603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03922","created_at":"2026-07-14T01:20:58.243603+00:00"},{"alias_kind":"pith_short_12","alias_value":"QD35AOPB5NUK","created_at":"2026-07-14T01:20:58.243603+00:00"},{"alias_kind":"pith_short_16","alias_value":"QD35AOPB5NUKK4XV","created_at":"2026-07-14T01:20:58.243603+00:00"},{"alias_kind":"pith_short_8","alias_value":"QD35AOPB","created_at":"2026-07-14T01:20:58.243603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT","json":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT.json","graph_json":"https://pith.science/api/pith-number/QD35AOPB5NUKK4XV3LYGQS4KWT/graph.json","events_json":"https://pith.science/api/pith-number/QD35AOPB5NUKK4XV3LYGQS4KWT/events.json","paper":"https://pith.science/paper/QD35AOPB"},"agent_actions":{"view_html":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT","download_json":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT.json","view_paper":"https://pith.science/paper/QD35AOPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.03922&json=true","fetch_graph":"https://pith.science/api/pith-number/QD35AOPB5NUKK4XV3LYGQS4KWT/graph.json","fetch_events":"https://pith.science/api/pith-number/QD35AOPB5NUKK4XV3LYGQS4KWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/action/storage_attestation","attest_author":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/action/author_attestation","sign_citation":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/action/citation_signature","submit_replication":"https://pith.science/pith/QD35AOPB5NUKK4XV3LYGQS4KWT/action/replication_record"}},"created_at":"2026-07-14T01:20:58.243603+00:00","updated_at":"2026-07-14T01:20:58.243603+00:00"}