{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B5P7V2ZP2ZD57JNNC7V374JRYX","short_pith_number":"pith:B5P7V2ZP","schema_version":"1.0","canonical_sha256":"0f5ffaeb2fd647dfa5ad17ebbff131c5d579c10e1f5f4f48455d33ad14afca01","source":{"kind":"arxiv","id":"2506.11066","version":3},"attestation_state":"computed","paper":{"title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenyang Lyu, Derui Zhu, Fakhri Karray, Fengyu Cai, Haonan Li, Heinz Koeppl, Jiahui Geng, Liangwei Chen, Qing Li, Shaobo Cui, Walter Pretschner","submitted_at":"2025-05-31T13:00:17Z","abstract_excerpt":"Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance while neglecting critical dimensions of software quality. Motivated by this gap, we introduce CoQuIR, the first large-scale, multilingual benchmark specifically designed to evaluate quality-aware code retrieval across four key dimensions: correctness, efficiency, security, and maintainability. CoQuIR provides fine-grained quality annotations for 42,725 queries and 134,907 code snippets in 11 programming languages, an"},"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":"2506.11066","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-31T13:00:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69dc525efd534e1b4f0699ad700564d097783d5afbff676d6b98a20b5c99ee29","abstract_canon_sha256":"8d4fa3e529567d61f6f17fa47f4ba72e071d626f4c509468a08997e612c78d03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:45.595366Z","signature_b64":"T0qeXf3bAgB1Xjt8QubiZzp2nNuvE/zD9Wv0VuLr1nfJmv3VIgIu/oDsElonTsohiU4Apqld9fGB+ytjqUZyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5ffaeb2fd647dfa5ad17ebbff131c5d579c10e1f5f4f48455d33ad14afca01","last_reissued_at":"2026-06-08T01:03:45.594343Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:45.594343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenyang Lyu, Derui Zhu, Fakhri Karray, Fengyu Cai, Haonan Li, Heinz Koeppl, Jiahui Geng, Liangwei Chen, Qing Li, Shaobo Cui, Walter Pretschner","submitted_at":"2025-05-31T13:00:17Z","abstract_excerpt":"Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance while neglecting critical dimensions of software quality. Motivated by this gap, we introduce CoQuIR, the first large-scale, multilingual benchmark specifically designed to evaluate quality-aware code retrieval across four key dimensions: correctness, efficiency, security, and maintainability. CoQuIR provides fine-grained quality annotations for 42,725 queries and 134,907 code snippets in 11 programming languages, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11066","kind":"arxiv","version":3},"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/2506.11066/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":"2506.11066","created_at":"2026-06-08T01:03:45.594480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11066v3","created_at":"2026-06-08T01:03:45.594480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11066","created_at":"2026-06-08T01:03:45.594480+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5P7V2ZP2ZD5","created_at":"2026-06-08T01:03:45.594480+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5P7V2ZP2ZD57JNN","created_at":"2026-06-08T01:03:45.594480+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5P7V2ZP","created_at":"2026-06-08T01:03:45.594480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15663","citing_title":"CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX","json":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX.json","graph_json":"https://pith.science/api/pith-number/B5P7V2ZP2ZD57JNNC7V374JRYX/graph.json","events_json":"https://pith.science/api/pith-number/B5P7V2ZP2ZD57JNNC7V374JRYX/events.json","paper":"https://pith.science/paper/B5P7V2ZP"},"agent_actions":{"view_html":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX","download_json":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX.json","view_paper":"https://pith.science/paper/B5P7V2ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11066&json=true","fetch_graph":"https://pith.science/api/pith-number/B5P7V2ZP2ZD57JNNC7V374JRYX/graph.json","fetch_events":"https://pith.science/api/pith-number/B5P7V2ZP2ZD57JNNC7V374JRYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX/action/storage_attestation","attest_author":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX/action/author_attestation","sign_citation":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX/action/citation_signature","submit_replication":"https://pith.science/pith/B5P7V2ZP2ZD57JNNC7V374JRYX/action/replication_record"}},"created_at":"2026-06-08T01:03:45.594480+00:00","updated_at":"2026-06-08T01:03:45.594480+00:00"}