{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CUCEF6CC5K75LESMB3CEHDNJ42","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":"c428d9757702eeabd5cfc9d3ba909ce52b33b01239e45c200195d37872d3a46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T00:30:34Z","title_canon_sha256":"69367d783bb9be357338d97519962e32ec40c0a953ce952b432c0687d01ac621"},"schema_version":"1.0","source":{"id":"2310.19208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19208","created_at":"2026-07-05T07:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19208v2","created_at":"2026-07-05T07:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19208","created_at":"2026-07-05T07:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"CUCEF6CC5K75","created_at":"2026-07-05T07:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"CUCEF6CC5K75LESM","created_at":"2026-07-05T07:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"CUCEF6CC","created_at":"2026-07-05T07:55:25Z"}],"graph_snapshots":[{"event_id":"sha256:b8826632006630c44a10773565e7150f5859a71f788025ee952b841775197c4a","target":"graph","created_at":"2026-07-05T07:55:25Z","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/2310.19208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lu Wang, Muhammad Khalifa, Xin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T00:30:34Z","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19208","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":"sha256:26d3ce3e2b7842a0dc7016d9e8a7373e91f85a799a0a831a880ec1a2b0ee8cf7","target":"record","created_at":"2026-07-05T07:55:25Z","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":"c428d9757702eeabd5cfc9d3ba909ce52b33b01239e45c200195d37872d3a46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T00:30:34Z","title_canon_sha256":"69367d783bb9be357338d97519962e32ec40c0a953ce952b432c0687d01ac621"},"schema_version":"1.0","source":{"id":"2310.19208","kind":"arxiv","version":2}},"canonical_sha256":"150442f842eabfd5924c0ec4438da9e6ada822f3df263d8361af4f0c20d03669","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"150442f842eabfd5924c0ec4438da9e6ada822f3df263d8361af4f0c20d03669","first_computed_at":"2026-07-05T07:55:25.747077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:25.747077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RzMVGaW4FUXykgukrrKZLGFJUjYeRcjgiA5LEw1baEu5unSxzQIpb+dzalStnD2x5nhXFuRdAkf5y6h/3ZjKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:25.747600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26d3ce3e2b7842a0dc7016d9e8a7373e91f85a799a0a831a880ec1a2b0ee8cf7","sha256:b8826632006630c44a10773565e7150f5859a71f788025ee952b841775197c4a"],"state_sha256":"3eb7b9dacc85607a5615a82bca06fc3fab65876c434902181e21b60758b95f53"}