{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YTUU7EZTWFJAMGHUCPR5B6HY4N","short_pith_number":"pith:YTUU7EZT","schema_version":"1.0","canonical_sha256":"c4e94f9333b1520618f413e3d0f8f8e364265c59130f8463e048b89236757424","source":{"kind":"arxiv","id":"2404.19318","version":3},"attestation_state":"computed","paper":{"title":"Calibration of Large Language Models on Code Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Premkumar Devanbu, Toufique Ahmed, Yuvraj Virk","submitted_at":"2024-04-30T07:38:08Z","abstract_excerpt":"A brief, fluent, and relevant summary can be helpful during program comprehension; however, such a summary does require significant human effort to produce. Often, good summaries are unavailable in software projects, which makes maintenance more difficult. There has been a considerable body of research into automated AI-based methods, using Large Language models (LLMs), to generate summaries of code; there also has been quite a bit of work on ways to measure the performance of such summarization methods, with special attention paid to how closely these AI-generated summaries resemble a summary"},"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":"2404.19318","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-04-30T07:38:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"30b3bdb80e663a1620aa78dcd26b1d1da80fcf5330c4d6a439c2696f20c0c2d0","abstract_canon_sha256":"e35a03f8433ec8f3d5afd14c247b934ad3da971e587c28b4af9145826d6b2fbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:09.190467Z","signature_b64":"B1eHJV/ZBNRYr3NO89d5AaFdVw0iXwb+J/bZvkA58/MhRAyAtQrcPGZp8hM0mqtRN8NnwnsLNCIDXJPtb1gyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4e94f9333b1520618f413e3d0f8f8e364265c59130f8463e048b89236757424","last_reissued_at":"2026-07-05T11:13:09.189808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:09.189808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration of Large Language Models on Code Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Premkumar Devanbu, Toufique Ahmed, Yuvraj Virk","submitted_at":"2024-04-30T07:38:08Z","abstract_excerpt":"A brief, fluent, and relevant summary can be helpful during program comprehension; however, such a summary does require significant human effort to produce. Often, good summaries are unavailable in software projects, which makes maintenance more difficult. There has been a considerable body of research into automated AI-based methods, using Large Language models (LLMs), to generate summaries of code; there also has been quite a bit of work on ways to measure the performance of such summarization methods, with special attention paid to how closely these AI-generated summaries resemble a summary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19318","kind":"arxiv","version":3},"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/2404.19318/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":"2404.19318","created_at":"2026-07-05T11:13:09.189903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19318v3","created_at":"2026-07-05T11:13:09.189903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19318","created_at":"2026-07-05T11:13:09.189903+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTUU7EZTWFJA","created_at":"2026-07-05T11:13:09.189903+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTUU7EZTWFJAMGHU","created_at":"2026-07-05T11:13:09.189903+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTUU7EZT","created_at":"2026-07-05T11:13:09.189903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.13217","citing_title":"Sustainability via LLM Right-sizing","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N","json":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N.json","graph_json":"https://pith.science/api/pith-number/YTUU7EZTWFJAMGHUCPR5B6HY4N/graph.json","events_json":"https://pith.science/api/pith-number/YTUU7EZTWFJAMGHUCPR5B6HY4N/events.json","paper":"https://pith.science/paper/YTUU7EZT"},"agent_actions":{"view_html":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N","download_json":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N.json","view_paper":"https://pith.science/paper/YTUU7EZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19318&json=true","fetch_graph":"https://pith.science/api/pith-number/YTUU7EZTWFJAMGHUCPR5B6HY4N/graph.json","fetch_events":"https://pith.science/api/pith-number/YTUU7EZTWFJAMGHUCPR5B6HY4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N/action/storage_attestation","attest_author":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N/action/author_attestation","sign_citation":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N/action/citation_signature","submit_replication":"https://pith.science/pith/YTUU7EZTWFJAMGHUCPR5B6HY4N/action/replication_record"}},"created_at":"2026-07-05T11:13:09.189903+00:00","updated_at":"2026-07-05T11:13:09.189903+00:00"}