{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TRYRDK33R4QB45QMKSP4Q7ZQC5","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":"fb2801a284a96c6c31fb863b590c1feb704d577724f5a9b48205fb5e15724c1b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-03T05:52:28Z","title_canon_sha256":"eae27b73c4bdf710b153314c94883d569f15c210ee3351caefd55b44267faf0d"},"schema_version":"1.0","source":{"id":"2402.02047","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02047","created_at":"2026-07-05T08:57:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02047v4","created_at":"2026-07-05T08:57:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02047","created_at":"2026-07-05T08:57:35Z"},{"alias_kind":"pith_short_12","alias_value":"TRYRDK33R4QB","created_at":"2026-07-05T08:57:35Z"},{"alias_kind":"pith_short_16","alias_value":"TRYRDK33R4QB45QM","created_at":"2026-07-05T08:57:35Z"},{"alias_kind":"pith_short_8","alias_value":"TRYRDK33","created_at":"2026-07-05T08:57:35Z"}],"graph_snapshots":[{"event_id":"sha256:2f0481fd080306568f387d441d866dca4bfd90e7ebb528b3a85c17dd5fc07045","target":"graph","created_at":"2026-07-05T08:57:35Z","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/2402.02047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models are widely used, but can also often be wrong. Users would benefit from a reliable indication of whether a given output from a given model should be trusted, so a rational decision can be made whether to use the output or not. For example, outputs can be associated with a confidence measure; if this confidence measure is strongly associated with likelihood of correctness, then the model is said to be well-calibrated.\n  A well-calibrated confidence measure can serve as a basis for rational, graduated decision-making on how much review and care is needed when using generat","authors_text":"Amin Alipour, Claudio Spiess, David Gros, Kunal Suresh Pai, Md Rafiqul Islam Rabin, Michael Pradel, Prem Devanbu, Susmit Jha, Toufique Ahmed","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-03T05:52:28Z","title":"Calibration and Correctness of Language Models for Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02047","kind":"arxiv","version":4},"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:dec4bf74742ffd814b66d00cd9c68af457f217cfe34cc5f4e097be6f6eccbb3b","target":"record","created_at":"2026-07-05T08:57:35Z","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":"fb2801a284a96c6c31fb863b590c1feb704d577724f5a9b48205fb5e15724c1b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-03T05:52:28Z","title_canon_sha256":"eae27b73c4bdf710b153314c94883d569f15c210ee3351caefd55b44267faf0d"},"schema_version":"1.0","source":{"id":"2402.02047","kind":"arxiv","version":4}},"canonical_sha256":"9c7111ab7b8f201e760c549fc87f301753ac2d4665bb5d2047142a3648d09f32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c7111ab7b8f201e760c549fc87f301753ac2d4665bb5d2047142a3648d09f32","first_computed_at":"2026-07-05T08:57:35.868239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:35.868239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6cLveCeetgqDgGWc+q3roUGesgDbKahkb+3IQ7VGs9nPYwperikRP8+AMASPM6SuOxldVD+gjyuxGFUm3oXHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:35.868754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02047","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dec4bf74742ffd814b66d00cd9c68af457f217cfe34cc5f4e097be6f6eccbb3b","sha256:2f0481fd080306568f387d441d866dca4bfd90e7ebb528b3a85c17dd5fc07045"],"state_sha256":"bfaa0291c6ac634894e353bc1e6a55a7ac0ca3e75d215347054ce379b821de42"}