{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WIAV6IZFYGXDZYUPVCTMBYPBAR","short_pith_number":"pith:WIAV6IZF","schema_version":"1.0","canonical_sha256":"b2015f2325c1ae3ce28fa8a6c0e1e1046a68065fb9e9522265e72ed3c9ec29e7","source":{"kind":"arxiv","id":"2501.03447","version":1},"attestation_state":"computed","paper":{"title":"CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chao Peng, Hang Zhu, Jialiang Chen, Jie Liu, Jierui Liu, Kaifa Zhao, Pengfei Gao, Ping Yang, Shuiguang Deng","submitted_at":"2025-01-07T00:24:07Z","abstract_excerpt":"Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into popular intelligent IDEs like JetBrains and Cursor. Current benchmarks for evaluating models' code comprehension capabilities primarily focus on code generation or completion, often neglecting QA, which is a crucial aspect of understanding code. Existing code QA benchmarks are derived from code comments with predefined patterns (e.g., CodeQA) or focus on specific"},"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":"2501.03447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-01-07T00:24:07Z","cross_cats_sorted":[],"title_canon_sha256":"1cd339028efb2d9ee22a6a621fcd1308159938e87e6e0d61730ca512228a8c2e","abstract_canon_sha256":"8259e9ebea6a76ba9f626adcd5b01c169900377f49af4005bec8c352661aba0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:54.951716Z","signature_b64":"VkHDvqDsAYp/56wWPBY3+Z4hkaXl8rHPG0W5rLgO/2ohRiyb91S2iZtwbOupReBN4j+gQJ6FkJDg+I2FIpV1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2015f2325c1ae3ce28fa8a6c0e1e1046a68065fb9e9522265e72ed3c9ec29e7","last_reissued_at":"2026-07-05T09:57:54.951241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:54.951241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chao Peng, Hang Zhu, Jialiang Chen, Jie Liu, Jierui Liu, Kaifa Zhao, Pengfei Gao, Ping Yang, Shuiguang Deng","submitted_at":"2025-01-07T00:24:07Z","abstract_excerpt":"Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into popular intelligent IDEs like JetBrains and Cursor. Current benchmarks for evaluating models' code comprehension capabilities primarily focus on code generation or completion, often neglecting QA, which is a crucial aspect of understanding code. Existing code QA benchmarks are derived from code comments with predefined patterns (e.g., CodeQA) or focus on specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03447","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/2501.03447/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":"2501.03447","created_at":"2026-07-05T09:57:54.951321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03447v1","created_at":"2026-07-05T09:57:54.951321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03447","created_at":"2026-07-05T09:57:54.951321+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIAV6IZFYGXD","created_at":"2026-07-05T09:57:54.951321+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIAV6IZFYGXDZYUP","created_at":"2026-07-05T09:57:54.951321+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIAV6IZF","created_at":"2026-07-05T09:57:54.951321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05238","citing_title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29372","citing_title":"On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14635","citing_title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26567","citing_title":"Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08366","citing_title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16021","citing_title":"Neurosymbolic Repo-level Code Localization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02421","citing_title":"AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR","json":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR.json","graph_json":"https://pith.science/api/pith-number/WIAV6IZFYGXDZYUPVCTMBYPBAR/graph.json","events_json":"https://pith.science/api/pith-number/WIAV6IZFYGXDZYUPVCTMBYPBAR/events.json","paper":"https://pith.science/paper/WIAV6IZF"},"agent_actions":{"view_html":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR","download_json":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR.json","view_paper":"https://pith.science/paper/WIAV6IZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03447&json=true","fetch_graph":"https://pith.science/api/pith-number/WIAV6IZFYGXDZYUPVCTMBYPBAR/graph.json","fetch_events":"https://pith.science/api/pith-number/WIAV6IZFYGXDZYUPVCTMBYPBAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR/action/storage_attestation","attest_author":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR/action/author_attestation","sign_citation":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR/action/citation_signature","submit_replication":"https://pith.science/pith/WIAV6IZFYGXDZYUPVCTMBYPBAR/action/replication_record"}},"created_at":"2026-07-05T09:57:54.951321+00:00","updated_at":"2026-07-05T09:57:54.951321+00:00"}