{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NKS2CUGAHWESGWMZUK4KXYFIWX","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":"60de79e03d1e2a604ae0691435826a4924ece48c41161baeb7f0be2c839dd78a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:45:46Z","title_canon_sha256":"32b69de850231074b5b14f25e7efd2db1df8150332266cacd6abe107af56ba1d"},"schema_version":"1.0","source":{"id":"2608.03506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03506","created_at":"2026-08-05T01:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03506v1","created_at":"2026-08-05T01:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03506","created_at":"2026-08-05T01:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"NKS2CUGAHWES","created_at":"2026-08-05T01:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"NKS2CUGAHWESGWMZ","created_at":"2026-08-05T01:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"NKS2CUGA","created_at":"2026-08-05T01:35:59Z"}],"graph_snapshots":[{"event_id":"sha256:f203076ae6dbf77a294027ae5bb453e94c0a76d4afa1167247df1395c742cbf7","target":"graph","created_at":"2026-08-05T01:35:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.03506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Connor Thomas Jerzak, Fangcong Yin, Nhat Ho, Omatharv Bharat Vaidya, Zayne Rea Sprague","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:45:46Z","title":"When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03506","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:701d50b36d789982f5a17f72d72e6f37f4921e89e9ddb6fd093ae8907ae3c86e","target":"record","created_at":"2026-08-05T01:35:59Z","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":"60de79e03d1e2a604ae0691435826a4924ece48c41161baeb7f0be2c839dd78a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:45:46Z","title_canon_sha256":"32b69de850231074b5b14f25e7efd2db1df8150332266cacd6abe107af56ba1d"},"schema_version":"1.0","source":{"id":"2608.03506","kind":"arxiv","version":1}},"canonical_sha256":"6aa5a150c03d89235999a2b8abe0a8b5f36a25c2f80013d511f2a03a68dc9935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aa5a150c03d89235999a2b8abe0a8b5f36a25c2f80013d511f2a03a68dc9935","first_computed_at":"2026-08-05T01:35:59.534568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:59.534568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tIZZmQBLeb3zG9LuoC9+t7eZXTpRvkSDdaEyP9qBVD0PiEbMESkqufAnls+NWLQ5dtBkyPnhfCzBB2OaVLVfCw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:59.536016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:701d50b36d789982f5a17f72d72e6f37f4921e89e9ddb6fd093ae8907ae3c86e","sha256:f203076ae6dbf77a294027ae5bb453e94c0a76d4afa1167247df1395c742cbf7"],"state_sha256":"9b98b050cdb1816539888b3cc50cedc3a953764908dae932de654bade3284b62"}