{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ER5YLLVYUQ4DMDNHRIWXHHQD4","short_pith_number":"pith:4ER5YLLV","schema_version":"1.0","canonical_sha256":"e123dc2d75c521c1b06d3c516b9cf01f1679d7b67c0de6b819db9e16e4c60651","source":{"kind":"arxiv","id":"2412.14764","version":1},"attestation_state":"computed","paper":{"title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bo Jiang, Chao Peng, Cuiyun Gao, Jingyi Ren, Pengfei Gao, Qinyun Wu, Ruida Hu, Xiangxin Meng, Xinchen Wang","submitted_at":"2024-12-19T11:48:01Z","abstract_excerpt":"In this work, we introduce CodeRepoQA, a large-scale benchmark specifically designed for evaluating repository-level question-answering capabilities in the field of software engineering. CodeRepoQA encompasses five programming languages and covers a wide range of scenarios, enabling comprehensive evaluation of language models. To construct this dataset, we crawl data from 30 well-known repositories in GitHub, the largest platform for hosting and collaborating on code, and carefully filter raw data. In total, CodeRepoQA is a multi-turn question-answering benchmark with 585,687 entries, covering"},"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":"2412.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-19T11:48:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49c04fac76b01cbb9bb8ee20844a6e2bb5fa381661bca4376b4c51c3b447520c","abstract_canon_sha256":"4351a58e6d1f727fe7caca04d302ef55151e56670badd776b226528e79c7fff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:52.313681Z","signature_b64":"rfaGPTjGmjsigsvgCJz8wDzFIZbH2vv6u5gmfNdFqfjtJc0v5694QOq+nw4GH9fAa5N45qdSxHnyJdOqK/gjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e123dc2d75c521c1b06d3c516b9cf01f1679d7b67c0de6b819db9e16e4c60651","last_reissued_at":"2026-07-05T09:51:52.313200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:52.313200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bo Jiang, Chao Peng, Cuiyun Gao, Jingyi Ren, Pengfei Gao, Qinyun Wu, Ruida Hu, Xiangxin Meng, Xinchen Wang","submitted_at":"2024-12-19T11:48:01Z","abstract_excerpt":"In this work, we introduce CodeRepoQA, a large-scale benchmark specifically designed for evaluating repository-level question-answering capabilities in the field of software engineering. CodeRepoQA encompasses five programming languages and covers a wide range of scenarios, enabling comprehensive evaluation of language models. To construct this dataset, we crawl data from 30 well-known repositories in GitHub, the largest platform for hosting and collaborating on code, and carefully filter raw data. In total, CodeRepoQA is a multi-turn question-answering benchmark with 585,687 entries, covering"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14764","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/2412.14764/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":"2412.14764","created_at":"2026-07-05T09:51:52.313257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14764v1","created_at":"2026-07-05T09:51:52.313257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14764","created_at":"2026-07-05T09:51:52.313257+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ER5YLLVYUQ4","created_at":"2026-07-05T09:51:52.313257+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ER5YLLVYUQ4DMDN","created_at":"2026-07-05T09:51:52.313257+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ER5YLLV","created_at":"2026-07-05T09:51:52.313257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17548","citing_title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17548","citing_title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14635","citing_title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16021","citing_title":"Neurosymbolic Repo-level Code Localization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4","json":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4.json","graph_json":"https://pith.science/api/pith-number/4ER5YLLVYUQ4DMDNHRIWXHHQD4/graph.json","events_json":"https://pith.science/api/pith-number/4ER5YLLVYUQ4DMDNHRIWXHHQD4/events.json","paper":"https://pith.science/paper/4ER5YLLV"},"agent_actions":{"view_html":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4","download_json":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4.json","view_paper":"https://pith.science/paper/4ER5YLLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14764&json=true","fetch_graph":"https://pith.science/api/pith-number/4ER5YLLVYUQ4DMDNHRIWXHHQD4/graph.json","fetch_events":"https://pith.science/api/pith-number/4ER5YLLVYUQ4DMDNHRIWXHHQD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4/action/storage_attestation","attest_author":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4/action/author_attestation","sign_citation":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4/action/citation_signature","submit_replication":"https://pith.science/pith/4ER5YLLVYUQ4DMDNHRIWXHHQD4/action/replication_record"}},"created_at":"2026-07-05T09:51:52.313257+00:00","updated_at":"2026-07-05T09:51:52.313257+00:00"}