{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TRYRDK33R4QB45QMKSP4Q7ZQC5","short_pith_number":"pith:TRYRDK33","schema_version":"1.0","canonical_sha256":"9c7111ab7b8f201e760c549fc87f301753ac2d4665bb5d2047142a3648d09f32","source":{"kind":"arxiv","id":"2402.02047","version":4},"attestation_state":"computed","paper":{"title":"Calibration and Correctness of Language Models for Code","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Amin Alipour, Claudio Spiess, David Gros, Kunal Suresh Pai, Md Rafiqul Islam Rabin, Michael Pradel, Prem Devanbu, Susmit Jha, Toufique Ahmed","submitted_at":"2024-02-03T05:52:28Z","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"},"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":"2402.02047","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-03T05:52:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eae27b73c4bdf710b153314c94883d569f15c210ee3351caefd55b44267faf0d","abstract_canon_sha256":"fb2801a284a96c6c31fb863b590c1feb704d577724f5a9b48205fb5e15724c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:35.868754Z","signature_b64":"6cLveCeetgqDgGWc+q3roUGesgDbKahkb+3IQ7VGs9nPYwperikRP8+AMASPM6SuOxldVD+gjyuxGFUm3oXHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c7111ab7b8f201e760c549fc87f301753ac2d4665bb5d2047142a3648d09f32","last_reissued_at":"2026-07-05T08:57:35.868239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:35.868239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration and Correctness of Language Models for Code","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Amin Alipour, Claudio Spiess, David Gros, Kunal Suresh Pai, Md Rafiqul Islam Rabin, Michael Pradel, Prem Devanbu, Susmit Jha, Toufique Ahmed","submitted_at":"2024-02-03T05:52:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02047","kind":"arxiv","version":4},"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/2402.02047/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":"2402.02047","created_at":"2026-07-05T08:57:35.868302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02047v4","created_at":"2026-07-05T08:57:35.868302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02047","created_at":"2026-07-05T08:57:35.868302+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRYRDK33R4QB","created_at":"2026-07-05T08:57:35.868302+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRYRDK33R4QB45QM","created_at":"2026-07-05T08:57:35.868302+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRYRDK33","created_at":"2026-07-05T08:57:35.868302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28500","citing_title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10656","citing_title":"Precision or Peril: A PoC of Python Code Quality from Quantized Large Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19369","citing_title":"When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5","json":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5.json","graph_json":"https://pith.science/api/pith-number/TRYRDK33R4QB45QMKSP4Q7ZQC5/graph.json","events_json":"https://pith.science/api/pith-number/TRYRDK33R4QB45QMKSP4Q7ZQC5/events.json","paper":"https://pith.science/paper/TRYRDK33"},"agent_actions":{"view_html":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5","download_json":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5.json","view_paper":"https://pith.science/paper/TRYRDK33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02047&json=true","fetch_graph":"https://pith.science/api/pith-number/TRYRDK33R4QB45QMKSP4Q7ZQC5/graph.json","fetch_events":"https://pith.science/api/pith-number/TRYRDK33R4QB45QMKSP4Q7ZQC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5/action/storage_attestation","attest_author":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5/action/author_attestation","sign_citation":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5/action/citation_signature","submit_replication":"https://pith.science/pith/TRYRDK33R4QB45QMKSP4Q7ZQC5/action/replication_record"}},"created_at":"2026-07-05T08:57:35.868302+00:00","updated_at":"2026-07-05T08:57:35.868302+00:00"}