{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BAO4R3NV5GQEDYJ4QQZAPEGUS3","short_pith_number":"pith:BAO4R3NV","schema_version":"1.0","canonical_sha256":"081dc8edb5e9a041e13c84320790d496e21b92ede6d14035719f204d722a5ec4","source":{"kind":"arxiv","id":"2307.08947","version":1},"attestation_state":"computed","paper":{"title":"An Effective Data-Driven Approach for Localizing Deep Learning Faults","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Breno Dantas Cruz, Hridesh Rajan, Mohammad Wardat, Wei Le","submitted_at":"2023-07-18T03:28:39Z","abstract_excerpt":"Deep Learning (DL) applications are being used to solve problems in critical domains (e.g., autonomous driving or medical diagnosis systems). Thus, developers need to debug their systems to ensure that the expected behavior is delivered. However, it is hard and expensive to debug DNNs. When the failure symptoms or unsatisfied accuracies are reported after training, we lose the traceability as to which part of the DNN program is responsible for the failure. Even worse, sometimes, a deep learning program has different types of bugs. To address the challenges of debugging DNN models, we propose a"},"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":"2307.08947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-07-18T03:28:39Z","cross_cats_sorted":[],"title_canon_sha256":"dbda1a844c9524bdc700921f7f11a3577dfbc7cadac0bd87ca87ffbfc802f393","abstract_canon_sha256":"350da3af5281d683487756e1ea652e274f7fb78109ed29a474542de792bba1e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:36.595378Z","signature_b64":"kFsze27Cr//FoJzC7nV76/qkOJ5r3fcVRhbJN3D512GHVJRgr1zBauZMx/LzjqVF5plE5lICBNqxUXZ8dBj1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081dc8edb5e9a041e13c84320790d496e21b92ede6d14035719f204d722a5ec4","last_reissued_at":"2026-07-05T06:31:36.594840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:36.594840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Effective Data-Driven Approach for Localizing Deep Learning Faults","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Breno Dantas Cruz, Hridesh Rajan, Mohammad Wardat, Wei Le","submitted_at":"2023-07-18T03:28:39Z","abstract_excerpt":"Deep Learning (DL) applications are being used to solve problems in critical domains (e.g., autonomous driving or medical diagnosis systems). Thus, developers need to debug their systems to ensure that the expected behavior is delivered. However, it is hard and expensive to debug DNNs. When the failure symptoms or unsatisfied accuracies are reported after training, we lose the traceability as to which part of the DNN program is responsible for the failure. Even worse, sometimes, a deep learning program has different types of bugs. To address the challenges of debugging DNN models, we propose a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08947","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/2307.08947/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":"2307.08947","created_at":"2026-07-05T06:31:36.594909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08947v1","created_at":"2026-07-05T06:31:36.594909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08947","created_at":"2026-07-05T06:31:36.594909+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAO4R3NV5GQE","created_at":"2026-07-05T06:31:36.594909+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAO4R3NV5GQEDYJ4","created_at":"2026-07-05T06:31:36.594909+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAO4R3NV","created_at":"2026-07-05T06:31:36.594909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28118","citing_title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3","json":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3.json","graph_json":"https://pith.science/api/pith-number/BAO4R3NV5GQEDYJ4QQZAPEGUS3/graph.json","events_json":"https://pith.science/api/pith-number/BAO4R3NV5GQEDYJ4QQZAPEGUS3/events.json","paper":"https://pith.science/paper/BAO4R3NV"},"agent_actions":{"view_html":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3","download_json":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3.json","view_paper":"https://pith.science/paper/BAO4R3NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08947&json=true","fetch_graph":"https://pith.science/api/pith-number/BAO4R3NV5GQEDYJ4QQZAPEGUS3/graph.json","fetch_events":"https://pith.science/api/pith-number/BAO4R3NV5GQEDYJ4QQZAPEGUS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3/action/storage_attestation","attest_author":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3/action/author_attestation","sign_citation":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3/action/citation_signature","submit_replication":"https://pith.science/pith/BAO4R3NV5GQEDYJ4QQZAPEGUS3/action/replication_record"}},"created_at":"2026-07-05T06:31:36.594909+00:00","updated_at":"2026-07-05T06:31:36.594909+00:00"}