{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BIEOVCJDJHNOZ4UB63OXYTZ7PM","short_pith_number":"pith:BIEOVCJD","schema_version":"1.0","canonical_sha256":"0a08ea892349daecf281f6dd7c4f3f7b3ca937e575c79b9f25da88f52c460d12","source":{"kind":"arxiv","id":"2406.06025","version":1},"attestation_state":"computed","paper":{"title":"RepoQA: Evaluating Long Context Code Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Jia Le Tian, Jiawei Liu, Jun Yang, Lingming Zhang, Vijay Daita, Yifeng Ding, Yuhan Katherine Wang, Yuxiang Wei","submitted_at":"2024-06-10T05:15:30Z","abstract_excerpt":"Recent advances have been improving the context windows of Large Language Models (LLMs). To quantify the real long-context capabilities of LLMs, evaluators such as the popular Needle in a Haystack have been developed to test LLMs over a large chunk of raw texts. While effective, current evaluations overlook the insight of how LLMs work with long-context code, i.e., repositories. To this end, we initiate the RepoQA benchmark to evaluate LLMs on long-context code understanding. Traditional needle testers ask LLMs to directly retrieve the answer from the context without necessary deep understandi"},"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":"2406.06025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-10T05:15:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8dd603c2f0cd3f38ba26f09fb2a68ba0c03b967ef4890c2dd11cb2b2677646b1","abstract_canon_sha256":"0e56b9a56c0a5cf757780bb0b1eefb895bf4aef8cbdb5b75aa3d22e49bdab025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:36.704213Z","signature_b64":"SnrdBwlZXa2U3PQd6QI+dX64VWUO/Auff4Ba47yUSEdymIpX4sC5is0RH6O/s9Lx4n5cNdaHst1KqGUtvyixBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a08ea892349daecf281f6dd7c4f3f7b3ca937e575c79b9f25da88f52c460d12","last_reissued_at":"2026-07-05T08:29:36.703728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:36.703728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoQA: Evaluating Long Context Code Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Jia Le Tian, Jiawei Liu, Jun Yang, Lingming Zhang, Vijay Daita, Yifeng Ding, Yuhan Katherine Wang, Yuxiang Wei","submitted_at":"2024-06-10T05:15:30Z","abstract_excerpt":"Recent advances have been improving the context windows of Large Language Models (LLMs). To quantify the real long-context capabilities of LLMs, evaluators such as the popular Needle in a Haystack have been developed to test LLMs over a large chunk of raw texts. While effective, current evaluations overlook the insight of how LLMs work with long-context code, i.e., repositories. To this end, we initiate the RepoQA benchmark to evaluate LLMs on long-context code understanding. Traditional needle testers ask LLMs to directly retrieve the answer from the context without necessary deep understandi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06025","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/2406.06025/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":"2406.06025","created_at":"2026-07-05T08:29:36.703785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06025v1","created_at":"2026-07-05T08:29:36.703785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06025","created_at":"2026-07-05T08:29:36.703785+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIEOVCJDJHNO","created_at":"2026-07-05T08:29:36.703785+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIEOVCJDJHNOZ4UB","created_at":"2026-07-05T08:29:36.703785+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIEOVCJD","created_at":"2026-07-05T08:29:36.703785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08284","citing_title":"Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2503.14281","citing_title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26692","citing_title":"Kimi Linear: An Expressive, Efficient Attention Architecture","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07019","citing_title":"LensVLM: Selective Context Expansion for Compressed Visual Representation of Text","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM","json":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM.json","graph_json":"https://pith.science/api/pith-number/BIEOVCJDJHNOZ4UB63OXYTZ7PM/graph.json","events_json":"https://pith.science/api/pith-number/BIEOVCJDJHNOZ4UB63OXYTZ7PM/events.json","paper":"https://pith.science/paper/BIEOVCJD"},"agent_actions":{"view_html":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM","download_json":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM.json","view_paper":"https://pith.science/paper/BIEOVCJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06025&json=true","fetch_graph":"https://pith.science/api/pith-number/BIEOVCJDJHNOZ4UB63OXYTZ7PM/graph.json","fetch_events":"https://pith.science/api/pith-number/BIEOVCJDJHNOZ4UB63OXYTZ7PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM/action/storage_attestation","attest_author":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM/action/author_attestation","sign_citation":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM/action/citation_signature","submit_replication":"https://pith.science/pith/BIEOVCJDJHNOZ4UB63OXYTZ7PM/action/replication_record"}},"created_at":"2026-07-05T08:29:36.703785+00:00","updated_at":"2026-07-05T08:29:36.703785+00:00"}