{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHZNAHZWIH64VQAVKZ7X5KDCE6","short_pith_number":"pith:AHZNAHZW","schema_version":"1.0","canonical_sha256":"01f2d01f3641fdcac015567f7ea862278f433b67e436f32ded75a3fe653549f2","source":{"kind":"arxiv","id":"2506.03396","version":1},"attestation_state":"computed","paper":{"title":"Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Gunel Jahangirova, Jinhan Kim, Nargiz Humbatova, Paolo Tonella, Shin Yoo","submitted_at":"2025-06-03T21:08:33Z","abstract_excerpt":"Numerous Fault Localisation (FL) and repair techniques have been proposed to address faults in Deep Learning (DL) models. However, their effectiveness in practical applications remains uncertain due to the reliance on pre-defined rules. This paper presents a comprehensive evaluation of state-of-the-art FL and repair techniques, examining their advantages and limitations. Moreover, we introduce a novel approach that harnesses the power of Large Language Models (LLMs) in localising and repairing DL faults. Our evaluation, conducted on a carefully designed benchmark, reveals the strengths and wea"},"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":"2506.03396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-03T21:08:33Z","cross_cats_sorted":[],"title_canon_sha256":"92e641fc5dcc69310bae2199031e5c92a73dac43373f5b1ea3f10d7a3a37595c","abstract_canon_sha256":"132fe94b30565f97e03e286a73c13dd604ec36efae66d7df35e4533232964a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:26.852562Z","signature_b64":"o1nmiCAt1t9OSG6siaGR8PT35uH9ICnpiIyZ0Ytc5DI0iBRC0rb/BCdLaQ7fxVw7AzToPTsJVZJd9XKxQ/pQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f2d01f3641fdcac015567f7ea862278f433b67e436f32ded75a3fe653549f2","last_reissued_at":"2026-07-05T11:15:26.852099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:26.852099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Gunel Jahangirova, Jinhan Kim, Nargiz Humbatova, Paolo Tonella, Shin Yoo","submitted_at":"2025-06-03T21:08:33Z","abstract_excerpt":"Numerous Fault Localisation (FL) and repair techniques have been proposed to address faults in Deep Learning (DL) models. However, their effectiveness in practical applications remains uncertain due to the reliance on pre-defined rules. This paper presents a comprehensive evaluation of state-of-the-art FL and repair techniques, examining their advantages and limitations. Moreover, we introduce a novel approach that harnesses the power of Large Language Models (LLMs) in localising and repairing DL faults. Our evaluation, conducted on a carefully designed benchmark, reveals the strengths and wea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03396","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/2506.03396/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":"2506.03396","created_at":"2026-07-05T11:15:26.852154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03396v1","created_at":"2026-07-05T11:15:26.852154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03396","created_at":"2026-07-05T11:15:26.852154+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHZNAHZWIH64","created_at":"2026-07-05T11:15:26.852154+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHZNAHZWIH64VQAV","created_at":"2026-07-05T11:15:26.852154+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHZNAHZW","created_at":"2026-07-05T11:15:26.852154+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/AHZNAHZWIH64VQAVKZ7X5KDCE6","json":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6.json","graph_json":"https://pith.science/api/pith-number/AHZNAHZWIH64VQAVKZ7X5KDCE6/graph.json","events_json":"https://pith.science/api/pith-number/AHZNAHZWIH64VQAVKZ7X5KDCE6/events.json","paper":"https://pith.science/paper/AHZNAHZW"},"agent_actions":{"view_html":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6","download_json":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6.json","view_paper":"https://pith.science/paper/AHZNAHZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03396&json=true","fetch_graph":"https://pith.science/api/pith-number/AHZNAHZWIH64VQAVKZ7X5KDCE6/graph.json","fetch_events":"https://pith.science/api/pith-number/AHZNAHZWIH64VQAVKZ7X5KDCE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6/action/storage_attestation","attest_author":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6/action/author_attestation","sign_citation":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6/action/citation_signature","submit_replication":"https://pith.science/pith/AHZNAHZWIH64VQAVKZ7X5KDCE6/action/replication_record"}},"created_at":"2026-07-05T11:15:26.852154+00:00","updated_at":"2026-07-05T11:15:26.852154+00:00"}