{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YK7ZWRE6U2TEJ6J5SAVZP7DSTW","short_pith_number":"pith:YK7ZWRE6","schema_version":"1.0","canonical_sha256":"c2bf9b449ea6a644f93d902b97fc729da840c10f0ea185c6dfce4c6b860728e6","source":{"kind":"arxiv","id":"2502.00519","version":2},"attestation_state":"computed","paper":{"title":"CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Kunal Pai, Premkumar Devanbu, Toufique Ahmed","submitted_at":"2025-02-01T18:45:32Z","abstract_excerpt":"One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate the set of edits to that function to implement the desired new operation; likewise, given a set of edits to a function, an agent might be asked to generate a changed description, of that function's new workings. Thus, there is an incentive to train a neural model for change-related tasks. Motivated by this, we offer a new, \"natural\", large dataset of coupled"},"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":"2502.00519","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-01T18:45:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1cdaaab30d450a6acb9e8f07510743663f580ec032a70c7602cd552ce19630e","abstract_canon_sha256":"eb4d66f39cf84d9870f6d140fbb9483ad0bc2b6ee7373c332cb777ab34838de0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:16.454004Z","signature_b64":"/xqY4fobItDU1a3PGHhzE7MWgq6rbtz50L5zG2zaT04FVYekKfTe5SAKFkE4Io+x7HkYSspF40J4CU39YBtuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2bf9b449ea6a644f93d902b97fc729da840c10f0ea185c6dfce4c6b860728e6","last_reissued_at":"2026-07-05T10:09:16.453599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:16.453599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Kunal Pai, Premkumar Devanbu, Toufique Ahmed","submitted_at":"2025-02-01T18:45:32Z","abstract_excerpt":"One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate the set of edits to that function to implement the desired new operation; likewise, given a set of edits to a function, an agent might be asked to generate a changed description, of that function's new workings. Thus, there is an incentive to train a neural model for change-related tasks. Motivated by this, we offer a new, \"natural\", large dataset of coupled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00519","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/2502.00519/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":"2502.00519","created_at":"2026-07-05T10:09:16.453652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00519v2","created_at":"2026-07-05T10:09:16.453652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00519","created_at":"2026-07-05T10:09:16.453652+00:00"},{"alias_kind":"pith_short_12","alias_value":"YK7ZWRE6U2TE","created_at":"2026-07-05T10:09:16.453652+00:00"},{"alias_kind":"pith_short_16","alias_value":"YK7ZWRE6U2TEJ6J5","created_at":"2026-07-05T10:09:16.453652+00:00"},{"alias_kind":"pith_short_8","alias_value":"YK7ZWRE6","created_at":"2026-07-05T10:09:16.453652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04255","citing_title":"HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW","json":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW.json","graph_json":"https://pith.science/api/pith-number/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/graph.json","events_json":"https://pith.science/api/pith-number/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/events.json","paper":"https://pith.science/paper/YK7ZWRE6"},"agent_actions":{"view_html":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW","download_json":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW.json","view_paper":"https://pith.science/paper/YK7ZWRE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00519&json=true","fetch_graph":"https://pith.science/api/pith-number/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/graph.json","fetch_events":"https://pith.science/api/pith-number/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/action/storage_attestation","attest_author":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/action/author_attestation","sign_citation":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/action/citation_signature","submit_replication":"https://pith.science/pith/YK7ZWRE6U2TEJ6J5SAVZP7DSTW/action/replication_record"}},"created_at":"2026-07-05T10:09:16.453652+00:00","updated_at":"2026-07-05T10:09:16.453652+00:00"}