{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NKS2CUGAHWESGWMZUK4KXYFIWX","short_pith_number":"pith:NKS2CUGA","schema_version":"1.0","canonical_sha256":"6aa5a150c03d89235999a2b8abe0a8b5f36a25c2f80013d511f2a03a68dc9935","source":{"kind":"arxiv","id":"2608.03506","version":1},"attestation_state":"computed","paper":{"title":"When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Connor Thomas Jerzak, Fangcong Yin, Nhat Ho, Omatharv Bharat Vaidya, Zayne Rea Sprague","submitted_at":"2026-08-04T11:45:46Z","abstract_excerpt":"Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On"},"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":"2608.03506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:45:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"32b69de850231074b5b14f25e7efd2db1df8150332266cacd6abe107af56ba1d","abstract_canon_sha256":"60de79e03d1e2a604ae0691435826a4924ece48c41161baeb7f0be2c839dd78a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:59.536016Z","signature_b64":"tIZZmQBLeb3zG9LuoC9+t7eZXTpRvkSDdaEyP9qBVD0PiEbMESkqufAnls+NWLQ5dtBkyPnhfCzBB2OaVLVfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa5a150c03d89235999a2b8abe0a8b5f36a25c2f80013d511f2a03a68dc9935","last_reissued_at":"2026-08-05T01:35:59.534568Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:59.534568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Connor Thomas Jerzak, Fangcong Yin, Nhat Ho, Omatharv Bharat Vaidya, Zayne Rea Sprague","submitted_at":"2026-08-04T11:45:46Z","abstract_excerpt":"Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03506","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/2608.03506/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":"2608.03506","created_at":"2026-08-05T01:35:59.535049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03506v1","created_at":"2026-08-05T01:35:59.535049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03506","created_at":"2026-08-05T01:35:59.535049+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKS2CUGAHWES","created_at":"2026-08-05T01:35:59.535049+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKS2CUGAHWESGWMZ","created_at":"2026-08-05T01:35:59.535049+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKS2CUGA","created_at":"2026-08-05T01:35:59.535049+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/NKS2CUGAHWESGWMZUK4KXYFIWX","json":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX.json","graph_json":"https://pith.science/api/pith-number/NKS2CUGAHWESGWMZUK4KXYFIWX/graph.json","events_json":"https://pith.science/api/pith-number/NKS2CUGAHWESGWMZUK4KXYFIWX/events.json","paper":"https://pith.science/paper/NKS2CUGA"},"agent_actions":{"view_html":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX","download_json":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX.json","view_paper":"https://pith.science/paper/NKS2CUGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03506&json=true","fetch_graph":"https://pith.science/api/pith-number/NKS2CUGAHWESGWMZUK4KXYFIWX/graph.json","fetch_events":"https://pith.science/api/pith-number/NKS2CUGAHWESGWMZUK4KXYFIWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX/action/storage_attestation","attest_author":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX/action/author_attestation","sign_citation":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX/action/citation_signature","submit_replication":"https://pith.science/pith/NKS2CUGAHWESGWMZUK4KXYFIWX/action/replication_record"}},"created_at":"2026-08-05T01:35:59.535049+00:00","updated_at":"2026-08-05T01:35:59.535049+00:00"}