{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKRP6J24IE5AQXMWTHZUL2EWJR","short_pith_number":"pith:MKRP6J24","schema_version":"1.0","canonical_sha256":"62a2ff275c413a085d9699f345e8964c6516bcfab1b47c5adf00b05f6798e816","source":{"kind":"arxiv","id":"2506.20081","version":2},"attestation_state":"computed","paper":{"title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie","submitted_at":"2025-06-25T01:44:28Z","abstract_excerpt":"Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework th"},"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":"2506.20081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T01:44:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f68a8628b608c290a942caf219756eb9ab0ccd2d5975b69e0a49b67ac40bf8e3","abstract_canon_sha256":"db9597ed9b6f89ad2212465a63372e8aa36a2af82df61a738153520ed4883e78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:31.798240Z","signature_b64":"yFBLNdbwkGOGukW4nj9CRJFBSP6EYwShYL0/e4lvEFSI408ldgZN2zbR8+8KwO9iFf1Cv5XggEPxjaSDyVQBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62a2ff275c413a085d9699f345e8964c6516bcfab1b47c5adf00b05f6798e816","last_reissued_at":"2026-07-05T11:27:31.797705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:31.797705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie","submitted_at":"2025-06-25T01:44:28Z","abstract_excerpt":"Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20081","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/2506.20081/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":"2506.20081","created_at":"2026-07-05T11:27:31.797774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20081v2","created_at":"2026-07-05T11:27:31.797774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20081","created_at":"2026-07-05T11:27:31.797774+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKRP6J24IE5A","created_at":"2026-07-05T11:27:31.797774+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKRP6J24IE5AQXMW","created_at":"2026-07-05T11:27:31.797774+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKRP6J24","created_at":"2026-07-05T11:27:31.797774+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/MKRP6J24IE5AQXMWTHZUL2EWJR","json":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR.json","graph_json":"https://pith.science/api/pith-number/MKRP6J24IE5AQXMWTHZUL2EWJR/graph.json","events_json":"https://pith.science/api/pith-number/MKRP6J24IE5AQXMWTHZUL2EWJR/events.json","paper":"https://pith.science/paper/MKRP6J24"},"agent_actions":{"view_html":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR","download_json":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR.json","view_paper":"https://pith.science/paper/MKRP6J24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20081&json=true","fetch_graph":"https://pith.science/api/pith-number/MKRP6J24IE5AQXMWTHZUL2EWJR/graph.json","fetch_events":"https://pith.science/api/pith-number/MKRP6J24IE5AQXMWTHZUL2EWJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR/action/storage_attestation","attest_author":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR/action/author_attestation","sign_citation":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR/action/citation_signature","submit_replication":"https://pith.science/pith/MKRP6J24IE5AQXMWTHZUL2EWJR/action/replication_record"}},"created_at":"2026-07-05T11:27:31.797774+00:00","updated_at":"2026-07-05T11:27:31.797774+00:00"}