{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3P4MGOVKN4VUBTNN2CIWW2OK32","short_pith_number":"pith:3P4MGOVK","schema_version":"1.0","canonical_sha256":"dbf8c33aaa6f2b40cdadd0916b69cade8a02b3115e4e961994049b7d186927c0","source":{"kind":"arxiv","id":"2502.07067","version":1},"attestation_state":"computed","paper":{"title":"Repository-level Code Search with Neural Retrieval Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Luyu Gao, Siddharth Gandhi","submitted_at":"2025-02-10T21:59:01Z","abstract_excerpt":"This paper presents a multi-stage reranking system for repository-level code search, which leverages the vastly available commit histories of large open-source repositories to aid in bug fixing. We define the task of repository-level code search as retrieving the set of files from the current state of a code repository that are most relevant to addressing a user's question or bug. The proposed approach combines BM25-based retrieval over commit messages with neural reranking using CodeBERT to identify the most pertinent files. By learning patterns from diverse repositories and their commit hist"},"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":"2502.07067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-10T21:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"ed6c1c6ce3e083fb0cd7438d5759a59c5ffd756a901c8e3769469b2538f79770","abstract_canon_sha256":"5a264bfea865b25541f2f5280c57cb175107bdbed25ddbacd898ea76e1a9570d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:31.923685Z","signature_b64":"DuNSxthjaio6AMrw9pDus5KcxluzmaCAD4Hk7Sj0O8Pk3DyQkoSEbGbBIT+SSifzqTneLUuwpSRx2whgQJQKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbf8c33aaa6f2b40cdadd0916b69cade8a02b3115e4e961994049b7d186927c0","last_reissued_at":"2026-07-05T10:12:31.923253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:31.923253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repository-level Code Search with Neural Retrieval Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Luyu Gao, Siddharth Gandhi","submitted_at":"2025-02-10T21:59:01Z","abstract_excerpt":"This paper presents a multi-stage reranking system for repository-level code search, which leverages the vastly available commit histories of large open-source repositories to aid in bug fixing. We define the task of repository-level code search as retrieving the set of files from the current state of a code repository that are most relevant to addressing a user's question or bug. The proposed approach combines BM25-based retrieval over commit messages with neural reranking using CodeBERT to identify the most pertinent files. By learning patterns from diverse repositories and their commit hist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07067","kind":"arxiv","version":1},"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/2502.07067/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":"2502.07067","created_at":"2026-07-05T10:12:31.923311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07067v1","created_at":"2026-07-05T10:12:31.923311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07067","created_at":"2026-07-05T10:12:31.923311+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P4MGOVKN4VU","created_at":"2026-07-05T10:12:31.923311+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P4MGOVKN4VUBTNN","created_at":"2026-07-05T10:12:31.923311+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P4MGOVK","created_at":"2026-07-05T10:12:31.923311+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/3P4MGOVKN4VUBTNN2CIWW2OK32","json":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32.json","graph_json":"https://pith.science/api/pith-number/3P4MGOVKN4VUBTNN2CIWW2OK32/graph.json","events_json":"https://pith.science/api/pith-number/3P4MGOVKN4VUBTNN2CIWW2OK32/events.json","paper":"https://pith.science/paper/3P4MGOVK"},"agent_actions":{"view_html":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32","download_json":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32.json","view_paper":"https://pith.science/paper/3P4MGOVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07067&json=true","fetch_graph":"https://pith.science/api/pith-number/3P4MGOVKN4VUBTNN2CIWW2OK32/graph.json","fetch_events":"https://pith.science/api/pith-number/3P4MGOVKN4VUBTNN2CIWW2OK32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32/action/storage_attestation","attest_author":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32/action/author_attestation","sign_citation":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32/action/citation_signature","submit_replication":"https://pith.science/pith/3P4MGOVKN4VUBTNN2CIWW2OK32/action/replication_record"}},"created_at":"2026-07-05T10:12:31.923311+00:00","updated_at":"2026-07-05T10:12:31.923311+00:00"}