{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5WNRELBYMDLFRP4XJMMZODRCYZ","short_pith_number":"pith:5WNRELBY","schema_version":"1.0","canonical_sha256":"ed9b122c3860d658bf974b19970e22c65a62757c7e9d36dab5ffe76e4a3a4a90","source":{"kind":"arxiv","id":"2007.06934","version":3},"attestation_state":"computed","paper":{"title":"CoreGen: Contextualized Code Representation Learning for Commit Message Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Cuiyun Gao, Lun Yiu Nie, Wai Lam, Yang Liu, Zenglin Xu, Zhicong Zhong","submitted_at":"2020-07-14T09:43:26Z","abstract_excerpt":"Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for the task. Several studies have been proposed to alleviate the challenge but none explicitly involves code contextual information during commit message generation. Specifically, existing research adopts static embedding for code tokens, which maps a token to the same vector regardless of its context. In this paper, we propose a novel Contextualized code repres"},"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":"2007.06934","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-07-14T09:43:26Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"a0e54790648c687540139d892e2b82eff4fefea94b65574a47a56a8809bed60d","abstract_canon_sha256":"b4afc7c914c281af5f91db45d163dc1eef4e9687ac422a3928cce5b8c3198508"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:39.926648Z","signature_b64":"38RmOZdBhG71m4XA7Iyx6PmiTZ4U1qeCsP2tjRwZ5mqsPzkW4X57lK8z215QX3tu580vxxfzMzSFU1/Y24lBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed9b122c3860d658bf974b19970e22c65a62757c7e9d36dab5ffe76e4a3a4a90","last_reissued_at":"2026-07-05T02:50:39.926084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:39.926084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoreGen: Contextualized Code Representation Learning for Commit Message Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Cuiyun Gao, Lun Yiu Nie, Wai Lam, Yang Liu, Zenglin Xu, Zhicong Zhong","submitted_at":"2020-07-14T09:43:26Z","abstract_excerpt":"Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for the task. Several studies have been proposed to alleviate the challenge but none explicitly involves code contextual information during commit message generation. Specifically, existing research adopts static embedding for code tokens, which maps a token to the same vector regardless of its context. In this paper, we propose a novel Contextualized code repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06934","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/2007.06934/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":"2007.06934","created_at":"2026-07-05T02:50:39.926149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06934v3","created_at":"2026-07-05T02:50:39.926149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06934","created_at":"2026-07-05T02:50:39.926149+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WNRELBYMDLF","created_at":"2026-07-05T02:50:39.926149+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WNRELBYMDLFRP4X","created_at":"2026-07-05T02:50:39.926149+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WNRELBY","created_at":"2026-07-05T02:50:39.926149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ","json":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ.json","graph_json":"https://pith.science/api/pith-number/5WNRELBYMDLFRP4XJMMZODRCYZ/graph.json","events_json":"https://pith.science/api/pith-number/5WNRELBYMDLFRP4XJMMZODRCYZ/events.json","paper":"https://pith.science/paper/5WNRELBY"},"agent_actions":{"view_html":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ","download_json":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ.json","view_paper":"https://pith.science/paper/5WNRELBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06934&json=true","fetch_graph":"https://pith.science/api/pith-number/5WNRELBYMDLFRP4XJMMZODRCYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5WNRELBYMDLFRP4XJMMZODRCYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ/action/storage_attestation","attest_author":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ/action/author_attestation","sign_citation":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ/action/citation_signature","submit_replication":"https://pith.science/pith/5WNRELBYMDLFRP4XJMMZODRCYZ/action/replication_record"}},"created_at":"2026-07-05T02:50:39.926149+00:00","updated_at":"2026-07-05T02:50:39.926149+00:00"}