{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CUCEF6CC5K75LESMB3CEHDNJ42","short_pith_number":"pith:CUCEF6CC","schema_version":"1.0","canonical_sha256":"150442f842eabfd5924c0ec4438da9e6ada822f3df263d8361af4f0c20d03669","source":{"kind":"arxiv","id":"2310.19208","version":2},"attestation_state":"computed","paper":{"title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Muhammad Khalifa, Xin Liu","submitted_at":"2023-10-30T00:30:34Z","abstract_excerpt":"A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as it plays a vital role in detecting and mitigating hallucinations of LMs as well as building more trustworthy models. However, standard calibration techniques may not be suited for LM calibration. For instance, post-processing methods such as temperature scaling do not reorder the candidate generations. On the other hand, training-based methods require fine-tuning the entire model, which is impractical for LMs of larg"},"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":"2310.19208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T00:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"69367d783bb9be357338d97519962e32ec40c0a953ce952b432c0687d01ac621","abstract_canon_sha256":"c428d9757702eeabd5cfc9d3ba909ce52b33b01239e45c200195d37872d3a46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:25.747600Z","signature_b64":"RzMVGaW4FUXykgukrrKZLGFJUjYeRcjgiA5LEw1baEu5unSxzQIpb+dzalStnD2x5nhXFuRdAkf5y6h/3ZjKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150442f842eabfd5924c0ec4438da9e6ada822f3df263d8361af4f0c20d03669","last_reissued_at":"2026-07-05T07:55:25.747077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:25.747077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Muhammad Khalifa, Xin Liu","submitted_at":"2023-10-30T00:30:34Z","abstract_excerpt":"A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as it plays a vital role in detecting and mitigating hallucinations of LMs as well as building more trustworthy models. However, standard calibration techniques may not be suited for LM calibration. For instance, post-processing methods such as temperature scaling do not reorder the candidate generations. On the other hand, training-based methods require fine-tuning the entire model, which is impractical for LMs of larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19208","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/2310.19208/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":"2310.19208","created_at":"2026-07-05T07:55:25.747152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19208v2","created_at":"2026-07-05T07:55:25.747152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19208","created_at":"2026-07-05T07:55:25.747152+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUCEF6CC5K75","created_at":"2026-07-05T07:55:25.747152+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUCEF6CC5K75LESM","created_at":"2026-07-05T07:55:25.747152+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUCEF6CC","created_at":"2026-07-05T07:55:25.747152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11954","citing_title":"Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42","json":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42.json","graph_json":"https://pith.science/api/pith-number/CUCEF6CC5K75LESMB3CEHDNJ42/graph.json","events_json":"https://pith.science/api/pith-number/CUCEF6CC5K75LESMB3CEHDNJ42/events.json","paper":"https://pith.science/paper/CUCEF6CC"},"agent_actions":{"view_html":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42","download_json":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42.json","view_paper":"https://pith.science/paper/CUCEF6CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19208&json=true","fetch_graph":"https://pith.science/api/pith-number/CUCEF6CC5K75LESMB3CEHDNJ42/graph.json","fetch_events":"https://pith.science/api/pith-number/CUCEF6CC5K75LESMB3CEHDNJ42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42/action/storage_attestation","attest_author":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42/action/author_attestation","sign_citation":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42/action/citation_signature","submit_replication":"https://pith.science/pith/CUCEF6CC5K75LESMB3CEHDNJ42/action/replication_record"}},"created_at":"2026-07-05T07:55:25.747152+00:00","updated_at":"2026-07-05T07:55:25.747152+00:00"}