{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KXKXSW6QMMRCLCE5ACS2SMWUSL","short_pith_number":"pith:KXKXSW6Q","schema_version":"1.0","canonical_sha256":"55d5795bd0632225889d00a5a932d492db831f1f12f470d32d99da2549107427","source":{"kind":"arxiv","id":"2401.04621","version":3},"attestation_state":"computed","paper":{"title":"DebugBench: Evaluating Debugging Capability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Haotian Hui, Maosong Sun, Runchu Tian, Weichuan Liu, Xin Cong, Yankai Lin, Yesai Wu, Yining Ye, Yinxu Pan, Yujia Qin, Zhiyuan Liu","submitted_at":"2024-01-09T15:46:38Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we coll"},"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":"2401.04621","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-09T15:46:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4811fa6ce5d5620032edf26dfc9fee63a27984df427eb4662569b626ee660ad7","abstract_canon_sha256":"af71da4e606047ade0f2aa99f33231aa8be3494171037132ea84eda2ae962b06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:04.739959Z","signature_b64":"IYJC5yQVGgSL0EtR61Wkmr5UDX2Jpf8eW2rlEitHvspKvr+B25rNaqxlUDXYRrcgyVcmkMyBh98XfmXWA9/MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d5795bd0632225889d00a5a932d492db831f1f12f470d32d99da2549107427","last_reissued_at":"2026-07-05T08:28:04.739514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:04.739514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DebugBench: Evaluating Debugging Capability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Haotian Hui, Maosong Sun, Runchu Tian, Weichuan Liu, Xin Cong, Yankai Lin, Yesai Wu, Yining Ye, Yinxu Pan, Yujia Qin, Zhiyuan Liu","submitted_at":"2024-01-09T15:46:38Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we coll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04621","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/2401.04621/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":"2401.04621","created_at":"2026-07-05T08:28:04.739572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04621v3","created_at":"2026-07-05T08:28:04.739572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04621","created_at":"2026-07-05T08:28:04.739572+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXKXSW6QMMRC","created_at":"2026-07-05T08:28:04.739572+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXKXSW6QMMRCLCE5","created_at":"2026-07-05T08:28:04.739572+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXKXSW6Q","created_at":"2026-07-05T08:28:04.739572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11755","citing_title":"Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31511","citing_title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01055","citing_title":"Towards Agentic Runtime Healing","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00642","citing_title":"ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14503","citing_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL","json":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL.json","graph_json":"https://pith.science/api/pith-number/KXKXSW6QMMRCLCE5ACS2SMWUSL/graph.json","events_json":"https://pith.science/api/pith-number/KXKXSW6QMMRCLCE5ACS2SMWUSL/events.json","paper":"https://pith.science/paper/KXKXSW6Q"},"agent_actions":{"view_html":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL","download_json":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL.json","view_paper":"https://pith.science/paper/KXKXSW6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04621&json=true","fetch_graph":"https://pith.science/api/pith-number/KXKXSW6QMMRCLCE5ACS2SMWUSL/graph.json","fetch_events":"https://pith.science/api/pith-number/KXKXSW6QMMRCLCE5ACS2SMWUSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL/action/storage_attestation","attest_author":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL/action/author_attestation","sign_citation":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL/action/citation_signature","submit_replication":"https://pith.science/pith/KXKXSW6QMMRCLCE5ACS2SMWUSL/action/replication_record"}},"created_at":"2026-07-05T08:28:04.739572+00:00","updated_at":"2026-07-05T08:28:04.739572+00:00"}