{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5MRCQKRLGVM4DX5PTOA4L5AKU3","short_pith_number":"pith:5MRCQKRL","schema_version":"1.0","canonical_sha256":"eb22282a2b3559c1dfaf9b81c5f40aa6f12b1ba60c61272f8dbd44aaad4eb816","source":{"kind":"arxiv","id":"2305.18584","version":2},"attestation_state":"computed","paper":{"title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Greg Durrett, Isil Dillig, Jiayi Wei","submitted_at":"2023-05-29T19:57:36Z","abstract_excerpt":"Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code, overlooking the distinctive needs of editing existing code. In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same codebase. Our model, Coeditor, is a fine-tuned language model specifically designed for code editing tasks. We represent code changes using a line diff format and employ static analysis to form large customized m"},"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":"2305.18584","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-29T19:57:36Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"b9bdd6981be1f1d5a2dc7c6c999c3dc5a8ea5c0e5b9128c5e69920efeb843e54","abstract_canon_sha256":"040ba2e8c549fb84e76c380b0dc774a56545b6434dd74e55af7905e4397da474"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:43.435117Z","signature_b64":"kiFP2tE8cRPL/c0Jka7FeGH1R2Ad5o2srRyWHM8XMZgfK1LGKq7ka9Lop3TgvgagO3CNqv/6xTJ7qXtTYSqjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb22282a2b3559c1dfaf9b81c5f40aa6f12b1ba60c61272f8dbd44aaad4eb816","last_reissued_at":"2026-07-05T08:12:43.434638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:43.434638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Greg Durrett, Isil Dillig, Jiayi Wei","submitted_at":"2023-05-29T19:57:36Z","abstract_excerpt":"Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code, overlooking the distinctive needs of editing existing code. In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same codebase. Our model, Coeditor, is a fine-tuned language model specifically designed for code editing tasks. We represent code changes using a line diff format and employ static analysis to form large customized m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18584","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/2305.18584/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":"2305.18584","created_at":"2026-07-05T08:12:43.434697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18584v2","created_at":"2026-07-05T08:12:43.434697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18584","created_at":"2026-07-05T08:12:43.434697+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MRCQKRLGVM4","created_at":"2026-07-05T08:12:43.434697+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MRCQKRLGVM4DX5P","created_at":"2026-07-05T08:12:43.434697+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MRCQKRL","created_at":"2026-07-05T08:12:43.434697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04185","citing_title":"From Legal Text to Tech Specs: Generative AI's Interpretation of Consent in Privacy Law","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3","json":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3.json","graph_json":"https://pith.science/api/pith-number/5MRCQKRLGVM4DX5PTOA4L5AKU3/graph.json","events_json":"https://pith.science/api/pith-number/5MRCQKRLGVM4DX5PTOA4L5AKU3/events.json","paper":"https://pith.science/paper/5MRCQKRL"},"agent_actions":{"view_html":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3","download_json":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3.json","view_paper":"https://pith.science/paper/5MRCQKRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18584&json=true","fetch_graph":"https://pith.science/api/pith-number/5MRCQKRLGVM4DX5PTOA4L5AKU3/graph.json","fetch_events":"https://pith.science/api/pith-number/5MRCQKRLGVM4DX5PTOA4L5AKU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3/action/storage_attestation","attest_author":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3/action/author_attestation","sign_citation":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3/action/citation_signature","submit_replication":"https://pith.science/pith/5MRCQKRLGVM4DX5PTOA4L5AKU3/action/replication_record"}},"created_at":"2026-07-05T08:12:43.434697+00:00","updated_at":"2026-07-05T08:12:43.434697+00:00"}