{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DDPANE5U62BLHG72L43AGKOAW5","short_pith_number":"pith:DDPANE5U","schema_version":"1.0","canonical_sha256":"18de0693b4f682b39bfa5f360329c0b74aed88749fa0a66b39dfd8ff991eee3b","source":{"kind":"arxiv","id":"2607.23931","version":1},"attestation_state":"computed","paper":{"title":"State-dependent error correlations shape voting thresholds in committees of AI agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Haifeng Li, Mo Hai","submitted_at":"2026-07-27T02:06:22Z","abstract_excerpt":"The aggregation benefit of a committee of artificial intelligence (AI) agents comes from complementary information across members. Classical voting guarantees assume independent errors. Language-model errors often co-occur on the same cases. We combine Sah-Stiglitz screening with error dependence that can differ between good and bad cases. In a homogeneous exchangeable Gaussian-copula model, shared errors create a positive asymptotic error floor for majority voting and can change the approval threshold that minimizes expected loss. We estimate a heterogeneous extension from 174,384 votes cast "},"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":"2607.23931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2026-07-27T02:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad4ba453047d047834c16105ddb6a6ab276df829fa01b363aa91aedfee6c2b1a","abstract_canon_sha256":"bcf224f50a532b2a3d197445a7b584b612afcb77c0e1979ac515e4ced0d1971c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:36.279136Z","signature_b64":"TJaBcqnU0ZnqoNxY6V0nkUBuPh9rtwMgLOnmdQLEb4rnukW6S04tnJ6tmQZ3XbGhJHgHAVvu05pD5Jn0iODDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18de0693b4f682b39bfa5f360329c0b74aed88749fa0a66b39dfd8ff991eee3b","last_reissued_at":"2026-07-28T01:23:36.278201Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:36.278201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-dependent error correlations shape voting thresholds in committees of AI agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Haifeng Li, Mo Hai","submitted_at":"2026-07-27T02:06:22Z","abstract_excerpt":"The aggregation benefit of a committee of artificial intelligence (AI) agents comes from complementary information across members. Classical voting guarantees assume independent errors. Language-model errors often co-occur on the same cases. We combine Sah-Stiglitz screening with error dependence that can differ between good and bad cases. In a homogeneous exchangeable Gaussian-copula model, shared errors create a positive asymptotic error floor for majority voting and can change the approval threshold that minimizes expected loss. We estimate a heterogeneous extension from 174,384 votes cast "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23931","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/2607.23931/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":"2607.23931","created_at":"2026-07-28T01:23:36.278655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23931v1","created_at":"2026-07-28T01:23:36.278655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23931","created_at":"2026-07-28T01:23:36.278655+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDPANE5U62BL","created_at":"2026-07-28T01:23:36.278655+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDPANE5U62BLHG72","created_at":"2026-07-28T01:23:36.278655+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDPANE5U","created_at":"2026-07-28T01:23:36.278655+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/DDPANE5U62BLHG72L43AGKOAW5","json":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5.json","graph_json":"https://pith.science/api/pith-number/DDPANE5U62BLHG72L43AGKOAW5/graph.json","events_json":"https://pith.science/api/pith-number/DDPANE5U62BLHG72L43AGKOAW5/events.json","paper":"https://pith.science/paper/DDPANE5U"},"agent_actions":{"view_html":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5","download_json":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5.json","view_paper":"https://pith.science/paper/DDPANE5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23931&json=true","fetch_graph":"https://pith.science/api/pith-number/DDPANE5U62BLHG72L43AGKOAW5/graph.json","fetch_events":"https://pith.science/api/pith-number/DDPANE5U62BLHG72L43AGKOAW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5/action/storage_attestation","attest_author":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5/action/author_attestation","sign_citation":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5/action/citation_signature","submit_replication":"https://pith.science/pith/DDPANE5U62BLHG72L43AGKOAW5/action/replication_record"}},"created_at":"2026-07-28T01:23:36.278655+00:00","updated_at":"2026-07-28T01:23:36.278655+00:00"}