{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J3CY3Q7K2Z3N7ROO7J7UNCLU3A","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":"9fb670346ead3789426f466f72f90347ac5c9e0a7f973f6b83463647e48b65b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T17:00:32Z","title_canon_sha256":"d81e7e187964d1bda05ca9a9225c110ff3d2ffdf3a05e0634ed5d55d7ca88a8d"},"schema_version":"1.0","source":{"id":"2402.06544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06544","created_at":"2026-07-05T09:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06544v2","created_at":"2026-07-05T09:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06544","created_at":"2026-07-05T09:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"J3CY3Q7K2Z3N","created_at":"2026-07-05T09:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"J3CY3Q7K2Z3N7ROO","created_at":"2026-07-05T09:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"J3CY3Q7K","created_at":"2026-07-05T09:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:f0cd7d6a04e7a75883d74036b79e0b4afe8d5c0c8250e16887befe6b67fe8db7","target":"graph","created_at":"2026-07-05T09:26:24Z","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/2402.06544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods and calibration metrics typically rely on a binary true/false assessment of response correctness. This approach does not apply to long-form generation, where an answer can be partially correct. Addressing this gap, we introduce a unified calibration framework, in which both the correctness of the LLMs' responses and their associated confidence levels are tr","authors_text":"Arman Cohan, Bhuwan Dhingra, Raghuveer Thirukovalluru, Yixin Liu, Yukun Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T17:00:32Z","title":"Calibrating Long-form Generations from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06544","kind":"arxiv","version":2},"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":"sha256:173e63fb4a22f77fd70bd2955fa1eb8b5ef4783d9e4b2dd4a288b39c66ce9b48","target":"record","created_at":"2026-07-05T09:26:24Z","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":"9fb670346ead3789426f466f72f90347ac5c9e0a7f973f6b83463647e48b65b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T17:00:32Z","title_canon_sha256":"d81e7e187964d1bda05ca9a9225c110ff3d2ffdf3a05e0634ed5d55d7ca88a8d"},"schema_version":"1.0","source":{"id":"2402.06544","kind":"arxiv","version":2}},"canonical_sha256":"4ec58dc3ead676dfc5cefa7f468974d80d8e4e97689e81889732e70116f157f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ec58dc3ead676dfc5cefa7f468974d80d8e4e97689e81889732e70116f157f0","first_computed_at":"2026-07-05T09:26:24.253627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:24.253627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jkgr+/iPmnNgTuZJ73rppr4a6KW4E5aNpowiUp3UsyQK2RQN1zGUvcxVzpHlPwUgx9yRR1FBR9UVmFndtXgcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:24.254824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:173e63fb4a22f77fd70bd2955fa1eb8b5ef4783d9e4b2dd4a288b39c66ce9b48","sha256:f0cd7d6a04e7a75883d74036b79e0b4afe8d5c0c8250e16887befe6b67fe8db7"],"state_sha256":"01680691f9221b7ec6e5ce9ae7555819914d812a41d65a55f5023ec1a19b0eca"}