{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XH2ZPKFTGVNHDOAS75WLTV57DT","short_pith_number":"pith:XH2ZPKFT","schema_version":"1.0","canonical_sha256":"b9f597a8b3355a71b812ff6cb9d7bf1cd1e3dbf4388bf4861e76d1a8fb99f2f0","source":{"kind":"arxiv","id":"2409.13642","version":2},"attestation_state":"computed","paper":{"title":"A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Jae Kim, Md Nakhla Rafi, Shaowei Wang, Tse-Hsun Chen","submitted_at":"2024-09-20T16:47:34Z","abstract_excerpt":"Identifying and resolving software faults remains a challenging and resource-intensive process. Traditional fault localization techniques, such as Spectrum-Based Fault Localization (SBFL), leverage statistical analysis of test coverage but often suffer from limited accuracy. While learning-based approaches improve fault localization, they demand extensive training datasets and high computational resources. Recent advances in Large Language Models (LLMs) offer new opportunities by enhancing code understanding and reasoning. However, existing LLM-based fault localization techniques face signific"},"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":"2409.13642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T16:47:34Z","cross_cats_sorted":[],"title_canon_sha256":"f60b4e11f1ea7ef7f7d029e9211d60150d176334ba19f2744dd22430d88a0911","abstract_canon_sha256":"2e917657eca3cf0929dfc0fc8b1ad6febe73256d84692d2a56b3441410e522a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:10.168877Z","signature_b64":"c2Jy+s5TWt0R2zPDkn3uW0LkXi6nUo8jO1gPC+8Dn07JKYpiEl9uPsxfu9tE8c0594gSDcwk0Bx1n0XJT5PGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f597a8b3355a71b812ff6cb9d7bf1cd1e3dbf4388bf4861e76d1a8fb99f2f0","last_reissued_at":"2026-07-05T10:34:10.168355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:10.168355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Jae Kim, Md Nakhla Rafi, Shaowei Wang, Tse-Hsun Chen","submitted_at":"2024-09-20T16:47:34Z","abstract_excerpt":"Identifying and resolving software faults remains a challenging and resource-intensive process. Traditional fault localization techniques, such as Spectrum-Based Fault Localization (SBFL), leverage statistical analysis of test coverage but often suffer from limited accuracy. While learning-based approaches improve fault localization, they demand extensive training datasets and high computational resources. Recent advances in Large Language Models (LLMs) offer new opportunities by enhancing code understanding and reasoning. However, existing LLM-based fault localization techniques face signific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13642","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/2409.13642/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":"2409.13642","created_at":"2026-07-05T10:34:10.168426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13642v2","created_at":"2026-07-05T10:34:10.168426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13642","created_at":"2026-07-05T10:34:10.168426+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH2ZPKFTGVNH","created_at":"2026-07-05T10:34:10.168426+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH2ZPKFTGVNHDOAS","created_at":"2026-07-05T10:34:10.168426+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH2ZPKFT","created_at":"2026-07-05T10:34:10.168426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23414","citing_title":"When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00253","citing_title":"Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13491","citing_title":"SieveFL: Hierarchical Runtime-Aware Pruning for Scalable LLM-Based Fault Localization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT","json":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT.json","graph_json":"https://pith.science/api/pith-number/XH2ZPKFTGVNHDOAS75WLTV57DT/graph.json","events_json":"https://pith.science/api/pith-number/XH2ZPKFTGVNHDOAS75WLTV57DT/events.json","paper":"https://pith.science/paper/XH2ZPKFT"},"agent_actions":{"view_html":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT","download_json":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT.json","view_paper":"https://pith.science/paper/XH2ZPKFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13642&json=true","fetch_graph":"https://pith.science/api/pith-number/XH2ZPKFTGVNHDOAS75WLTV57DT/graph.json","fetch_events":"https://pith.science/api/pith-number/XH2ZPKFTGVNHDOAS75WLTV57DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT/action/storage_attestation","attest_author":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT/action/author_attestation","sign_citation":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT/action/citation_signature","submit_replication":"https://pith.science/pith/XH2ZPKFTGVNHDOAS75WLTV57DT/action/replication_record"}},"created_at":"2026-07-05T10:34:10.168426+00:00","updated_at":"2026-07-05T10:34:10.168426+00:00"}