{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAOCMQOSMNJ2I62DWTA233D5HR","short_pith_number":"pith:FAOCMQOS","schema_version":"1.0","canonical_sha256":"281c2641d26353a47b43b4c1adec7d3c52d5ab7876cffddf1266d40d5d01ae36","source":{"kind":"arxiv","id":"2502.13966","version":2},"attestation_state":"computed","paper":{"title":"Where's the Bug? Attention Probing for Scalable Fault Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Aaditya Naik, Adam Stein, Arthur Wayne, Eric Wong, Mayur Naik","submitted_at":"2025-02-19T18:59:32Z","abstract_excerpt":"Ensuring code correctness remains a challenging problem even as large language models (LLMs) become increasingly capable at code-related tasks. While LLM-based program repair systems can propose bug fixes using only a user's bug report, their effectiveness is fundamentally limited by their ability to perform fault localization (FL), a challenging problem for both humans and LLMs. Existing FL approaches rely on executable test cases, require training on costly and often noisy line-level annotations, or demand resource-intensive LLMs. In this paper, we present Bug Attention Probe (BAP), a method"},"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":"2502.13966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-19T18:59:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"efe45f4f6852e8ad5a2a2083b6b0799546e2c594474de3296d8fecd16c5b0ccb","abstract_canon_sha256":"c8efa4a7ad92c271e2ad7d164641955ba0cd32492dd1f62085d78b9d32c5035c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:18.599473Z","signature_b64":"hX4uQgZIv+1RKZr6+JrOjHBDbJMkTuqwrefBwQ6nUEye3BNGITsVTMqApHm2kJNtp5/24/eFAHBAipctPnbOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281c2641d26353a47b43b4c1adec7d3c52d5ab7876cffddf1266d40d5d01ae36","last_reissued_at":"2026-07-05T10:17:18.598911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:18.598911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where's the Bug? Attention Probing for Scalable Fault Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Aaditya Naik, Adam Stein, Arthur Wayne, Eric Wong, Mayur Naik","submitted_at":"2025-02-19T18:59:32Z","abstract_excerpt":"Ensuring code correctness remains a challenging problem even as large language models (LLMs) become increasingly capable at code-related tasks. While LLM-based program repair systems can propose bug fixes using only a user's bug report, their effectiveness is fundamentally limited by their ability to perform fault localization (FL), a challenging problem for both humans and LLMs. Existing FL approaches rely on executable test cases, require training on costly and often noisy line-level annotations, or demand resource-intensive LLMs. In this paper, we present Bug Attention Probe (BAP), a method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13966","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/2502.13966/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":"2502.13966","created_at":"2026-07-05T10:17:18.598977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13966v2","created_at":"2026-07-05T10:17:18.598977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13966","created_at":"2026-07-05T10:17:18.598977+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAOCMQOSMNJ2","created_at":"2026-07-05T10:17:18.598977+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAOCMQOSMNJ2I62D","created_at":"2026-07-05T10:17:18.598977+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAOCMQOS","created_at":"2026-07-05T10:17:18.598977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03852","citing_title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR","json":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR.json","graph_json":"https://pith.science/api/pith-number/FAOCMQOSMNJ2I62DWTA233D5HR/graph.json","events_json":"https://pith.science/api/pith-number/FAOCMQOSMNJ2I62DWTA233D5HR/events.json","paper":"https://pith.science/paper/FAOCMQOS"},"agent_actions":{"view_html":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR","download_json":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR.json","view_paper":"https://pith.science/paper/FAOCMQOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13966&json=true","fetch_graph":"https://pith.science/api/pith-number/FAOCMQOSMNJ2I62DWTA233D5HR/graph.json","fetch_events":"https://pith.science/api/pith-number/FAOCMQOSMNJ2I62DWTA233D5HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR/action/storage_attestation","attest_author":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR/action/author_attestation","sign_citation":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR/action/citation_signature","submit_replication":"https://pith.science/pith/FAOCMQOSMNJ2I62DWTA233D5HR/action/replication_record"}},"created_at":"2026-07-05T10:17:18.598977+00:00","updated_at":"2026-07-05T10:17:18.598977+00:00"}