{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WY52G6L26HOPNJ47DZULGOPGSD","short_pith_number":"pith:WY52G6L2","schema_version":"1.0","canonical_sha256":"b63ba3797af1dcf6a79f1e68b339e690d473d087ae257406bfc2334256578b33","source":{"kind":"arxiv","id":"2602.17431","version":2},"attestation_state":"computed","paper":{"title":"Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Skarbrevik, Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj","submitted_at":"2026-02-19T15:02:29Z","abstract_excerpt":"Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form generation. We introduce a taxonomy for fine-grained uncertainty quantification in long-form LLM outputs that distinguishes methods by design choices at three stages: response decomposition, unit-level scoring, and response-level aggregation. We formalize several families of consistency-based black-box scorers, providing generalizations and extensions of existing methods. We also"},"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":"2602.17431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T15:02:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eb24dd0e63a3082b308862f6bcfbb2bad8973ac1731779f83878b30fedeab19a","abstract_canon_sha256":"687e6cb74e682ebf5dc8626a1909d63dcf18640782e1d2b29c8a474db0f1be7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.615925Z","signature_b64":"bSJhfTjnYtWllOM0YiBNppBpbCORFZvK29DKFycvzIVx9V/XLYLTCs+GWbhMYSg79q669PGLDPFrmWwYE5WMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63ba3797af1dcf6a79f1e68b339e690d473d087ae257406bfc2334256578b33","last_reissued_at":"2026-06-23T03:13:54.615486Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.615486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Skarbrevik, Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj","submitted_at":"2026-02-19T15:02:29Z","abstract_excerpt":"Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form generation. We introduce a taxonomy for fine-grained uncertainty quantification in long-form LLM outputs that distinguishes methods by design choices at three stages: response decomposition, unit-level scoring, and response-level aggregation. We formalize several families of consistency-based black-box scorers, providing generalizations and extensions of existing methods. We also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17431","kind":"arxiv","version":2},"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/2602.17431/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":"2602.17431","created_at":"2026-06-23T03:13:54.615544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17431v2","created_at":"2026-06-23T03:13:54.615544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17431","created_at":"2026-06-23T03:13:54.615544+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY52G6L26HOP","created_at":"2026-06-23T03:13:54.615544+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY52G6L26HOPNJ47","created_at":"2026-06-23T03:13:54.615544+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY52G6L2","created_at":"2026-06-23T03:13:54.615544+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/WY52G6L26HOPNJ47DZULGOPGSD","json":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD.json","graph_json":"https://pith.science/api/pith-number/WY52G6L26HOPNJ47DZULGOPGSD/graph.json","events_json":"https://pith.science/api/pith-number/WY52G6L26HOPNJ47DZULGOPGSD/events.json","paper":"https://pith.science/paper/WY52G6L2"},"agent_actions":{"view_html":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD","download_json":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD.json","view_paper":"https://pith.science/paper/WY52G6L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17431&json=true","fetch_graph":"https://pith.science/api/pith-number/WY52G6L26HOPNJ47DZULGOPGSD/graph.json","fetch_events":"https://pith.science/api/pith-number/WY52G6L26HOPNJ47DZULGOPGSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD/action/storage_attestation","attest_author":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD/action/author_attestation","sign_citation":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD/action/citation_signature","submit_replication":"https://pith.science/pith/WY52G6L26HOPNJ47DZULGOPGSD/action/replication_record"}},"created_at":"2026-06-23T03:13:54.615544+00:00","updated_at":"2026-06-23T03:13:54.615544+00:00"}