{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQK5HOTEYX3M6QTZAVAP5USEZW","short_pith_number":"pith:XQK5HOTE","schema_version":"1.0","canonical_sha256":"bc15d3ba64c5f6cf42790540fed244cdbad3b30c003f965d6630c07090920e52","source":{"kind":"arxiv","id":"2412.11304","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Study of Fault Localisation Techniques for Deep Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Gunel Jahangirova, Jinhan Kim, Nargiz Humbatova, Paolo Tonella, Shin Yoo","submitted_at":"2024-12-15T20:47:03Z","abstract_excerpt":"With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mut"},"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":"2412.11304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-15T20:47:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73a0aa3ec767371e36986ecaa0b07b271863f932740f354845e951365087b898","abstract_canon_sha256":"ab75649a028a70f7b50711d2740a616bd1369a0588dbcf90665aa1e1ae569a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:09.241283Z","signature_b64":"RrASYWMUe9BRXnrLAxRugtnNbqGOv0hz2ff/6lvpRpzz0K2LEdaAOIL1jknuDIQnpx6kAr8BNis1MaqUJc52Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc15d3ba64c5f6cf42790540fed244cdbad3b30c003f965d6630c07090920e52","last_reissued_at":"2026-07-05T09:50:09.240732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:09.240732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Fault Localisation Techniques for Deep Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Gunel Jahangirova, Jinhan Kim, Nargiz Humbatova, Paolo Tonella, Shin Yoo","submitted_at":"2024-12-15T20:47:03Z","abstract_excerpt":"With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11304","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/2412.11304/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":"2412.11304","created_at":"2026-07-05T09:50:09.240796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11304v2","created_at":"2026-07-05T09:50:09.240796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11304","created_at":"2026-07-05T09:50:09.240796+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQK5HOTEYX3M","created_at":"2026-07-05T09:50:09.240796+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQK5HOTEYX3M6QTZ","created_at":"2026-07-05T09:50:09.240796+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQK5HOTE","created_at":"2026-07-05T09:50:09.240796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03396","citing_title":"Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW","json":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW.json","graph_json":"https://pith.science/api/pith-number/XQK5HOTEYX3M6QTZAVAP5USEZW/graph.json","events_json":"https://pith.science/api/pith-number/XQK5HOTEYX3M6QTZAVAP5USEZW/events.json","paper":"https://pith.science/paper/XQK5HOTE"},"agent_actions":{"view_html":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW","download_json":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW.json","view_paper":"https://pith.science/paper/XQK5HOTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11304&json=true","fetch_graph":"https://pith.science/api/pith-number/XQK5HOTEYX3M6QTZAVAP5USEZW/graph.json","fetch_events":"https://pith.science/api/pith-number/XQK5HOTEYX3M6QTZAVAP5USEZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW/action/storage_attestation","attest_author":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW/action/author_attestation","sign_citation":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW/action/citation_signature","submit_replication":"https://pith.science/pith/XQK5HOTEYX3M6QTZAVAP5USEZW/action/replication_record"}},"created_at":"2026-07-05T09:50:09.240796+00:00","updated_at":"2026-07-05T09:50:09.240796+00:00"}