{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDOZ6LRGOOMNHVOCJ3YX5M6UAQ","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":"4ef94f0553df7b034d400164b3f874eb66285d0ab7a1a40f7405f7f878e4563e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T20:17:10Z","title_canon_sha256":"7551d867c3ef313215e549411eb99acef7f76ef83c4ecbe03bf6ae79a2e0e6b9"},"schema_version":"1.0","source":{"id":"2403.09849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09849","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09849v1","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09849","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"NDOZ6LRGOOMN","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"NDOZ6LRGOOMNHVOC","created_at":"2026-07-05T07:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"NDOZ6LRG","created_at":"2026-07-05T07:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:cbb8fd6e3d84d066f28cc37c94de1ff143f4c7238f0415c6cf1760c025f9721f","target":"graph","created_at":"2026-07-05T07:56:26Z","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/2403.09849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development. We design three off-the-shelf calibration methods based on self-consistency (Wang et al., 2022) for math reasoning tasks. Evaluation on two popular benchmarks (GSM8K and MathQA) using strong open-source LLMs (Mistral and LLaMA2), our methods better bridge model confidence and accuracy than existing methods based on p(True) (Kadavath et al., 2022) or logit (Kadavath et al., 2022).","authors_text":"Ante Wang, Baolin Peng, Dong Yu, Haitao Mi, Jinsong Su, Lifeng Jin, Linfeng Song, Ye Tian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T20:17:10Z","title":"Self-Consistency Boosts Calibration for Math Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09849","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":"sha256:30159249062141755f34546bda6ae66bf7f022f590e320e720a4de136d72ebc5","target":"record","created_at":"2026-07-05T07:56:26Z","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":"4ef94f0553df7b034d400164b3f874eb66285d0ab7a1a40f7405f7f878e4563e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T20:17:10Z","title_canon_sha256":"7551d867c3ef313215e549411eb99acef7f76ef83c4ecbe03bf6ae79a2e0e6b9"},"schema_version":"1.0","source":{"id":"2403.09849","kind":"arxiv","version":1}},"canonical_sha256":"68dd9f2e267398d3d5c24ef17eb3d4041d24968f3bbcdb8346a62ce2e4169086","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68dd9f2e267398d3d5c24ef17eb3d4041d24968f3bbcdb8346a62ce2e4169086","first_computed_at":"2026-07-05T07:56:26.377095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:26.377095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E13qoJmmFyEIyFIhzmPIzJv4BQV6Oc8WsvpAQKhZcI1omCCFTLwyv1LHJ5F7E9/C09MQOuFeJunoy/FVmlfYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:26.377617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30159249062141755f34546bda6ae66bf7f022f590e320e720a4de136d72ebc5","sha256:cbb8fd6e3d84d066f28cc37c94de1ff143f4c7238f0415c6cf1760c025f9721f"],"state_sha256":"03b007c467e0d23abc344a24a596f55ead56df1c368b20ea5b541314705b6721"}