{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKRP6J24IE5AQXMWTHZUL2EWJR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db9597ed9b6f89ad2212465a63372e8aa36a2af82df61a738153520ed4883e78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T01:44:28Z","title_canon_sha256":"f68a8628b608c290a942caf219756eb9ab0ccd2d5975b69e0a49b67ac40bf8e3"},"schema_version":"1.0","source":{"id":"2506.20081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20081","created_at":"2026-07-05T11:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20081v2","created_at":"2026-07-05T11:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20081","created_at":"2026-07-05T11:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"MKRP6J24IE5A","created_at":"2026-07-05T11:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"MKRP6J24IE5AQXMW","created_at":"2026-07-05T11:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"MKRP6J24","created_at":"2026-07-05T11:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:98c937d133ab0c0ac37b61e7d595419da635f93a65787ea0ac9b5b9328903bc3","target":"graph","created_at":"2026-07-05T11:27:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T01:44:28Z","title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20081","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3a6eaddd3bf271a424e294efcf99aa14020c8bfefa0528beb4fc7de94abda086","target":"record","created_at":"2026-07-05T11:27:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db9597ed9b6f89ad2212465a63372e8aa36a2af82df61a738153520ed4883e78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T01:44:28Z","title_canon_sha256":"f68a8628b608c290a942caf219756eb9ab0ccd2d5975b69e0a49b67ac40bf8e3"},"schema_version":"1.0","source":{"id":"2506.20081","kind":"arxiv","version":2}},"canonical_sha256":"62a2ff275c413a085d9699f345e8964c6516bcfab1b47c5adf00b05f6798e816","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62a2ff275c413a085d9699f345e8964c6516bcfab1b47c5adf00b05f6798e816","first_computed_at":"2026-07-05T11:27:31.797705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:31.797705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yFBLNdbwkGOGukW4nj9CRJFBSP6EYwShYL0/e4lvEFSI408ldgZN2zbR8+8KwO9iFf1Cv5XggEPxjaSDyVQBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:31.798240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a6eaddd3bf271a424e294efcf99aa14020c8bfefa0528beb4fc7de94abda086","sha256:98c937d133ab0c0ac37b61e7d595419da635f93a65787ea0ac9b5b9328903bc3"],"state_sha256":"1a4d905f4549d179e48a46fc0f116ccf43135a58456efcc61a6d2a85f53c75f7"}