{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P7CCTGJ4L2FLGCRBYFUVFDVXFE","short_pith_number":"pith:P7CCTGJ4","schema_version":"1.0","canonical_sha256":"7fc429993c5e8ab30a21c169528eb729318dce6e96da46ede77bc7b9df3b06fa","source":{"kind":"arxiv","id":"2306.06490","version":2},"attestation_state":"computed","paper":{"title":"Automated Code Editing with Search-Generate-Modify","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Baishakhi Ray, Changshu Liu, Pelin Cetin, Saikat Chakraborty, Yangruibo Ding, Yogesh Patodia","submitted_at":"2023-06-10T17:11:21Z","abstract_excerpt":"Code editing is essential in evolving software development. Many automated code editing tools have been proposed that leverage both Information Retrieval-based techniques and Machine Learning-based code generation and code editing models. Each technique comes with its own promises and perils, and they are often used together to complement their strengths and compensate for their weaknesses. This paper proposes a hybrid approach to better synthesize code edits by leveraging the power of code search, generation, and modification. Our key observation is that a patch obtained by search and retriev"},"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":"2306.06490","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-10T17:11:21Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"d5bcb010dd1ced3161cc00422dc3792c20c42993e7182804377013c41ad3cab6","abstract_canon_sha256":"12ee96e5bdd7a4645622c525619e7240e85de840e2bfac3a0d4b5d991918bd80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:12.290142Z","signature_b64":"vLwOuUmNKYanvX+q2Z/gQfreOTdCTjEGb6eG6h0dcvzk54CYaeqOxq4C4nyra6NAGHDPlGwfAnnrC73p52dIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fc429993c5e8ab30a21c169528eb729318dce6e96da46ede77bc7b9df3b06fa","last_reissued_at":"2026-07-05T07:49:12.289634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:12.289634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Code Editing with Search-Generate-Modify","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Baishakhi Ray, Changshu Liu, Pelin Cetin, Saikat Chakraborty, Yangruibo Ding, Yogesh Patodia","submitted_at":"2023-06-10T17:11:21Z","abstract_excerpt":"Code editing is essential in evolving software development. Many automated code editing tools have been proposed that leverage both Information Retrieval-based techniques and Machine Learning-based code generation and code editing models. Each technique comes with its own promises and perils, and they are often used together to complement their strengths and compensate for their weaknesses. This paper proposes a hybrid approach to better synthesize code edits by leveraging the power of code search, generation, and modification. Our key observation is that a patch obtained by search and retriev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06490","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/2306.06490/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":"2306.06490","created_at":"2026-07-05T07:49:12.289692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06490v2","created_at":"2026-07-05T07:49:12.289692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06490","created_at":"2026-07-05T07:49:12.289692+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7CCTGJ4L2FL","created_at":"2026-07-05T07:49:12.289692+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7CCTGJ4L2FLGCRB","created_at":"2026-07-05T07:49:12.289692+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7CCTGJ4","created_at":"2026-07-05T07:49:12.289692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":176,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE","json":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE.json","graph_json":"https://pith.science/api/pith-number/P7CCTGJ4L2FLGCRBYFUVFDVXFE/graph.json","events_json":"https://pith.science/api/pith-number/P7CCTGJ4L2FLGCRBYFUVFDVXFE/events.json","paper":"https://pith.science/paper/P7CCTGJ4"},"agent_actions":{"view_html":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE","download_json":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE.json","view_paper":"https://pith.science/paper/P7CCTGJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06490&json=true","fetch_graph":"https://pith.science/api/pith-number/P7CCTGJ4L2FLGCRBYFUVFDVXFE/graph.json","fetch_events":"https://pith.science/api/pith-number/P7CCTGJ4L2FLGCRBYFUVFDVXFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE/action/storage_attestation","attest_author":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE/action/author_attestation","sign_citation":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE/action/citation_signature","submit_replication":"https://pith.science/pith/P7CCTGJ4L2FLGCRBYFUVFDVXFE/action/replication_record"}},"created_at":"2026-07-05T07:49:12.289692+00:00","updated_at":"2026-07-05T07:49:12.289692+00:00"}