{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BDTSDLAPJSPJLL6YIDXNGDALZN","short_pith_number":"pith:BDTSDLAP","schema_version":"1.0","canonical_sha256":"08e721ac0f4c9e95afd840eed30c0bcb4e7b8eba5723d5eaa79649cd9e7b6ec3","source":{"kind":"arxiv","id":"2607.15388","version":1},"attestation_state":"computed","paper":{"title":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng-Hau Yang, Chih-Hsuan Yang, Eliu A. Huerta, Huihuo Zheng, Ian T. Foster, Jingyan Jiang, Le Chen, Rajeev Thakur, Venkatram Vishwanath, Vikram Vasudevan","submitted_at":"2026-07-16T18:38:10Z","abstract_excerpt":"Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in this harder regime, broadcast-style peer discussion reaches higher final accuracy than a planner-executor-reviewer pipeline (PER). We ask whether this gap is explained by reviewer quality or by whether"},"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":"2607.15388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T18:38:10Z","cross_cats_sorted":[],"title_canon_sha256":"ee2cd023f83c571e3c28fa29b23766f1b936135a98b1ea3aa30d55dd55368903","abstract_canon_sha256":"8b51aef4bbe3c10eb86e11c6842b21088852b7fa08d5ed0143aaea0ed05d8555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:30.789443Z","signature_b64":"VUvNnqZadmySN3eORNmPpYyRg2dysI5N6sWSy6Yf3RH5KAhFeWGeBRaRcjhRetz8OcZ1Wumb4a5gNeJqWk4LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08e721ac0f4c9e95afd840eed30c0bcb4e7b8eba5723d5eaa79649cd9e7b6ec3","last_reissued_at":"2026-07-20T00:18:30.788630Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:30.788630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng-Hau Yang, Chih-Hsuan Yang, Eliu A. Huerta, Huihuo Zheng, Ian T. Foster, Jingyan Jiang, Le Chen, Rajeev Thakur, Venkatram Vishwanath, Vikram Vasudevan","submitted_at":"2026-07-16T18:38:10Z","abstract_excerpt":"Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in this harder regime, broadcast-style peer discussion reaches higher final accuracy than a planner-executor-reviewer pipeline (PER). We ask whether this gap is explained by reviewer quality or by whether"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15388","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.15388/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":"2607.15388","created_at":"2026-07-20T00:18:30.789038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15388v1","created_at":"2026-07-20T00:18:30.789038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15388","created_at":"2026-07-20T00:18:30.789038+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDTSDLAPJSPJ","created_at":"2026-07-20T00:18:30.789038+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDTSDLAPJSPJLL6Y","created_at":"2026-07-20T00:18:30.789038+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDTSDLAP","created_at":"2026-07-20T00:18:30.789038+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/BDTSDLAPJSPJLL6YIDXNGDALZN","json":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN.json","graph_json":"https://pith.science/api/pith-number/BDTSDLAPJSPJLL6YIDXNGDALZN/graph.json","events_json":"https://pith.science/api/pith-number/BDTSDLAPJSPJLL6YIDXNGDALZN/events.json","paper":"https://pith.science/paper/BDTSDLAP"},"agent_actions":{"view_html":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN","download_json":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN.json","view_paper":"https://pith.science/paper/BDTSDLAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15388&json=true","fetch_graph":"https://pith.science/api/pith-number/BDTSDLAPJSPJLL6YIDXNGDALZN/graph.json","fetch_events":"https://pith.science/api/pith-number/BDTSDLAPJSPJLL6YIDXNGDALZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN/action/storage_attestation","attest_author":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN/action/author_attestation","sign_citation":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN/action/citation_signature","submit_replication":"https://pith.science/pith/BDTSDLAPJSPJLL6YIDXNGDALZN/action/replication_record"}},"created_at":"2026-07-20T00:18:30.789038+00:00","updated_at":"2026-07-20T00:18:30.789038+00:00"}