{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JY3PWM45RG3LQPVE4JCKNU7LHD","short_pith_number":"pith:JY3PWM45","schema_version":"1.0","canonical_sha256":"4e36fb339d89b6b83ea4e244a6d3eb38deb0e484bc807e3d8992d21462dd736a","source":{"kind":"arxiv","id":"2510.20521","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models for Fault Localization: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anquan Jie, Boyang Yang, Hongwei Li, Jianjun Huang, Rongqun Hu, Weiwei Gong, Yingjian Xiao","submitted_at":"2025-10-23T13:04:22Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong performance on code-related tasks, particularly in automated program repair. However, repair effectiveness often depends on accurate upstream fault localization, while the statement-level fault localization capability of LLMs remains insufficiently evaluated. This paper presents a systematic empirical study of LLMs for statement-level fault localization. We evaluate four representative LLMs, including two open-weight models, Qwen2.5-Coder-32B-Instruct and DeepSeek-V3, and two closed-source models, GPT-4.1 mini and Gemini-2.5-Flash, on Human"},"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":"2510.20521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-10-23T13:04:22Z","cross_cats_sorted":[],"title_canon_sha256":"64ef35e9722f055df031ebbfe48a9e998e633a34ebc869486001c64fe352ffd6","abstract_canon_sha256":"8ea245bffc9bbc862952f230cdc6c7a91d88da3e273b48ad691f52338df265ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e36fb339d89b6b83ea4e244a6d3eb38deb0e484bc807e3d8992d21462dd736a","last_reissued_at":"2026-07-30T01:19:14.671923Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:14.671923Z"},"graph_snapshot":{"paper":{"title":"Large Language Models for Fault Localization: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anquan Jie, Boyang Yang, Hongwei Li, Jianjun Huang, Rongqun Hu, Weiwei Gong, Yingjian Xiao","submitted_at":"2025-10-23T13:04:22Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong performance on code-related tasks, particularly in automated program repair. However, repair effectiveness often depends on accurate upstream fault localization, while the statement-level fault localization capability of LLMs remains insufficiently evaluated. This paper presents a systematic empirical study of LLMs for statement-level fault localization. We evaluate four representative LLMs, including two open-weight models, Qwen2.5-Coder-32B-Instruct and DeepSeek-V3, and two closed-source models, GPT-4.1 mini and Gemini-2.5-Flash, on Human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20521","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/2510.20521/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":"2510.20521","created_at":"2026-07-30T01:19:14.677023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.20521v2","created_at":"2026-07-30T01:19:14.677023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20521","created_at":"2026-07-30T01:19:14.677023+00:00"},{"alias_kind":"pith_short_12","alias_value":"JY3PWM45RG3L","created_at":"2026-07-30T01:19:14.677023+00:00"},{"alias_kind":"pith_short_16","alias_value":"JY3PWM45RG3LQPVE","created_at":"2026-07-30T01:19:14.677023+00:00"},{"alias_kind":"pith_short_8","alias_value":"JY3PWM45","created_at":"2026-07-30T01:19:14.677023+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/JY3PWM45RG3LQPVE4JCKNU7LHD","json":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD.json","graph_json":"https://pith.science/api/pith-number/JY3PWM45RG3LQPVE4JCKNU7LHD/graph.json","events_json":"https://pith.science/api/pith-number/JY3PWM45RG3LQPVE4JCKNU7LHD/events.json","paper":"https://pith.science/paper/JY3PWM45"},"agent_actions":{"view_html":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD","download_json":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD.json","view_paper":"https://pith.science/paper/JY3PWM45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.20521&json=true","fetch_graph":"https://pith.science/api/pith-number/JY3PWM45RG3LQPVE4JCKNU7LHD/graph.json","fetch_events":"https://pith.science/api/pith-number/JY3PWM45RG3LQPVE4JCKNU7LHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD/action/storage_attestation","attest_author":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD/action/author_attestation","sign_citation":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD/action/citation_signature","submit_replication":"https://pith.science/pith/JY3PWM45RG3LQPVE4JCKNU7LHD/action/replication_record"}},"created_at":"2026-07-30T01:19:14.677023+00:00","updated_at":"2026-07-30T01:19:14.677023+00:00"}