{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AXV2WLX6FQJOVWFFJNSDY7E5YM","short_pith_number":"pith:AXV2WLX6","schema_version":"1.0","canonical_sha256":"05ebab2efe2c12ead8a54b643c7c9dc3035b3aa72e935ecf7501803159d2db92","source":{"kind":"arxiv","id":"2407.21057","version":2},"attestation_state":"computed","paper":{"title":"Multi-group Uncertainty Quantification for Long-form Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Terrance Liu, Zhiwei Steven Wu","submitted_at":"2024-07-25T02:59:52Z","abstract_excerpt":"While past works have shown how uncertainty quantification can be applied to large language model (LLM) outputs, the question of whether resulting uncertainty guarantees still hold within sub-groupings of data remains open. In our work, given some long-form text generated by an LLM, we study uncertainty at both the level of individual claims contained within the output (via calibration) and across the entire output itself (via conformal prediction). Using biography generation as a testbed for this study, we derive a set of (demographic) attributes (e.g., whether some text describes a man or wo"},"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":"2407.21057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T02:59:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b4ef3420d85bdb26cf35484d1e06b63d984be0898f6175a0d94afe32253e78f6","abstract_canon_sha256":"607352464f057aab87079584b98d86e844967c8d9d32592b62bba13a6d0c144f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:36.877169Z","signature_b64":"+XyLOUgpB4O1qYCzjSpby7i7hTuHkFRzble9M1eI0jKq31Kw/MS8yydSIg0YDRscMGCt+CshWTfBgVtGcMxPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05ebab2efe2c12ead8a54b643c7c9dc3035b3aa72e935ecf7501803159d2db92","last_reissued_at":"2026-07-05T11:20:36.876462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:36.876462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-group Uncertainty Quantification for Long-form Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Terrance Liu, Zhiwei Steven Wu","submitted_at":"2024-07-25T02:59:52Z","abstract_excerpt":"While past works have shown how uncertainty quantification can be applied to large language model (LLM) outputs, the question of whether resulting uncertainty guarantees still hold within sub-groupings of data remains open. In our work, given some long-form text generated by an LLM, we study uncertainty at both the level of individual claims contained within the output (via calibration) and across the entire output itself (via conformal prediction). Using biography generation as a testbed for this study, we derive a set of (demographic) attributes (e.g., whether some text describes a man or wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21057","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/2407.21057/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":"2407.21057","created_at":"2026-07-05T11:20:36.876549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21057v2","created_at":"2026-07-05T11:20:36.876549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21057","created_at":"2026-07-05T11:20:36.876549+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXV2WLX6FQJO","created_at":"2026-07-05T11:20:36.876549+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXV2WLX6FQJOVWFF","created_at":"2026-07-05T11:20:36.876549+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXV2WLX6","created_at":"2026-07-05T11:20:36.876549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12587","citing_title":"Strategic Decision Support for AI Agents","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM","json":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM.json","graph_json":"https://pith.science/api/pith-number/AXV2WLX6FQJOVWFFJNSDY7E5YM/graph.json","events_json":"https://pith.science/api/pith-number/AXV2WLX6FQJOVWFFJNSDY7E5YM/events.json","paper":"https://pith.science/paper/AXV2WLX6"},"agent_actions":{"view_html":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM","download_json":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM.json","view_paper":"https://pith.science/paper/AXV2WLX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21057&json=true","fetch_graph":"https://pith.science/api/pith-number/AXV2WLX6FQJOVWFFJNSDY7E5YM/graph.json","fetch_events":"https://pith.science/api/pith-number/AXV2WLX6FQJOVWFFJNSDY7E5YM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM/action/storage_attestation","attest_author":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM/action/author_attestation","sign_citation":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM/action/citation_signature","submit_replication":"https://pith.science/pith/AXV2WLX6FQJOVWFFJNSDY7E5YM/action/replication_record"}},"created_at":"2026-07-05T11:20:36.876549+00:00","updated_at":"2026-07-05T11:20:36.876549+00:00"}