{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AS4DAEZVABMYELIARUAMGNPXFY","short_pith_number":"pith:AS4DAEZV","schema_version":"1.0","canonical_sha256":"04b83013350059822d008d00c335f72e23d76cc198fa19b992b58655f31f8d11","source":{"kind":"arxiv","id":"2404.03163","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty in Language Models: Assessment through Rank-Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Edgar Dobriban, Hamed Hassani, Insup Lee, Matteo Sesia, Mengxin Yu, Osbert Bastani, Shuo Li, Xinmeng Huang","submitted_at":"2024-04-04T02:31:05Z","abstract_excerpt":"Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures ($e.g.$, semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges ($e.g.$, $[0,\\infty)$ or $[0,1]$). In this work, we add"},"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":"2404.03163","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T02:31:05Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"f3bbf5a8242add9bad15359c33ee7ab1886bc588cc733fdf1e96a70d119d0084","abstract_canon_sha256":"9bcb62937505ea022432466a5d0713ed29b92891e63e307b1f105a7d34e49254"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:58.789232Z","signature_b64":"Sorko/FqFc2yxxavjcY6WGplnX67WJYVEQQaAwoHQMrqZ+nMg4yhQJ0Huo00qTmSpjmuaCT0XDkej4ut1FjPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04b83013350059822d008d00c335f72e23d76cc198fa19b992b58655f31f8d11","last_reissued_at":"2026-07-05T09:06:58.788742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:58.788742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty in Language Models: Assessment through Rank-Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Edgar Dobriban, Hamed Hassani, Insup Lee, Matteo Sesia, Mengxin Yu, Osbert Bastani, Shuo Li, Xinmeng Huang","submitted_at":"2024-04-04T02:31:05Z","abstract_excerpt":"Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures ($e.g.$, semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges ($e.g.$, $[0,\\infty)$ or $[0,1]$). In this work, we add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03163","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/2404.03163/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":"2404.03163","created_at":"2026-07-05T09:06:58.788798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03163v2","created_at":"2026-07-05T09:06:58.788798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03163","created_at":"2026-07-05T09:06:58.788798+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS4DAEZVABMY","created_at":"2026-07-05T09:06:58.788798+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS4DAEZVABMYELIA","created_at":"2026-07-05T09:06:58.788798+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS4DAEZV","created_at":"2026-07-05T09:06:58.788798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30814","citing_title":"When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY","json":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY.json","graph_json":"https://pith.science/api/pith-number/AS4DAEZVABMYELIARUAMGNPXFY/graph.json","events_json":"https://pith.science/api/pith-number/AS4DAEZVABMYELIARUAMGNPXFY/events.json","paper":"https://pith.science/paper/AS4DAEZV"},"agent_actions":{"view_html":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY","download_json":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY.json","view_paper":"https://pith.science/paper/AS4DAEZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03163&json=true","fetch_graph":"https://pith.science/api/pith-number/AS4DAEZVABMYELIARUAMGNPXFY/graph.json","fetch_events":"https://pith.science/api/pith-number/AS4DAEZVABMYELIARUAMGNPXFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY/action/storage_attestation","attest_author":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY/action/author_attestation","sign_citation":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY/action/citation_signature","submit_replication":"https://pith.science/pith/AS4DAEZVABMYELIARUAMGNPXFY/action/replication_record"}},"created_at":"2026-07-05T09:06:58.788798+00:00","updated_at":"2026-07-05T09:06:58.788798+00:00"}