{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:33EUTCKG47EDRYTQ4W4L7BR2K4","short_pith_number":"pith:33EUTCKG","schema_version":"1.0","canonical_sha256":"dec9498946e7c838e270e5b8bf863a5703ae5cb819d4948979e6311af3270606","source":{"kind":"arxiv","id":"2203.02700","version":3},"attestation_state":"computed","paper":{"title":"RACE: Retrieval-Augmented Commit Message Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Dongmei Zhang, Ensheng Shi, Hongbin Sun, Hongyu Zhang, Lun Du, Shi Han, Wei Tao, Yanlin Wang","submitted_at":"2022-03-05T10:55:15Z","abstract_excerpt":"Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could be repetitive or redundant. In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we als"},"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":"2203.02700","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-03-05T10:55:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c77aedc8f46d2cdf5b6195bd41f9cdfbb23d4956a0740a25de233f26e818ea39","abstract_canon_sha256":"d97fcff945f034633b17e4b1f55b728f9bd322f52ee9fa83c8b32420c381b214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:16.129977Z","signature_b64":"o6pnmLb6gMo+3T30vAjYHFezHapER1Dux1chEZB5w84c0nIILTZlDJo8Agq/LVOz4S/QMjxbNnFLsHQ03LQcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dec9498946e7c838e270e5b8bf863a5703ae5cb819d4948979e6311af3270606","last_reissued_at":"2026-07-05T05:09:16.129533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:16.129533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RACE: Retrieval-Augmented Commit Message Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Dongmei Zhang, Ensheng Shi, Hongbin Sun, Hongyu Zhang, Lun Du, Shi Han, Wei Tao, Yanlin Wang","submitted_at":"2022-03-05T10:55:15Z","abstract_excerpt":"Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could be repetitive or redundant. In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02700","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/2203.02700/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":"2203.02700","created_at":"2026-07-05T05:09:16.129589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02700v3","created_at":"2026-07-05T05:09:16.129589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02700","created_at":"2026-07-05T05:09:16.129589+00:00"},{"alias_kind":"pith_short_12","alias_value":"33EUTCKG47ED","created_at":"2026-07-05T05:09:16.129589+00:00"},{"alias_kind":"pith_short_16","alias_value":"33EUTCKG47EDRYTQ","created_at":"2026-07-05T05:09:16.129589+00:00"},{"alias_kind":"pith_short_8","alias_value":"33EUTCKG","created_at":"2026-07-05T05:09:16.129589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4","json":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4.json","graph_json":"https://pith.science/api/pith-number/33EUTCKG47EDRYTQ4W4L7BR2K4/graph.json","events_json":"https://pith.science/api/pith-number/33EUTCKG47EDRYTQ4W4L7BR2K4/events.json","paper":"https://pith.science/paper/33EUTCKG"},"agent_actions":{"view_html":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4","download_json":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4.json","view_paper":"https://pith.science/paper/33EUTCKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02700&json=true","fetch_graph":"https://pith.science/api/pith-number/33EUTCKG47EDRYTQ4W4L7BR2K4/graph.json","fetch_events":"https://pith.science/api/pith-number/33EUTCKG47EDRYTQ4W4L7BR2K4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4/action/storage_attestation","attest_author":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4/action/author_attestation","sign_citation":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4/action/citation_signature","submit_replication":"https://pith.science/pith/33EUTCKG47EDRYTQ4W4L7BR2K4/action/replication_record"}},"created_at":"2026-07-05T05:09:16.129589+00:00","updated_at":"2026-07-05T05:09:16.129589+00:00"}