{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2UIPNRHG3ROIPF4IEKP6J32MEH","short_pith_number":"pith:2UIPNRHG","schema_version":"1.0","canonical_sha256":"d510f6c4e6dc5c879788229fe4ef4c21dba3d66bbac21d0ed85f1d46a41e14be","source":{"kind":"arxiv","id":"1909.02190","version":2},"attestation_state":"computed","paper":{"title":"Detecting Deep Neural Network Defects with Data Flow Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huanlin Xu, Hui Xu, Jiazhen Gu, Michael Lyu, Xin Wang, Yangfan Zhou","submitted_at":"2019-09-05T02:56:33Z","abstract_excerpt":"Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks. However, it is very hard to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects. This paper aims at addressing this challenging problem. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We develop DeepMorph (DNN Tomography) to analyze the root cause, which can guide a DNN developer to improve the model."},"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":"1909.02190","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T02:56:33Z","cross_cats_sorted":["eess.SP","stat.ML"],"title_canon_sha256":"d0f241fa8b3914686d4206a2f541577bd463c0f9cc316cca843d9c756c6ff303","abstract_canon_sha256":"eeb1d67b216cbc419d14cde11dba8ff1963b6ebf7d25ed9f54282502dbbc977e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:07.616417Z","signature_b64":"TWpaHt+gdB83C5N0RwhfxojBwY7H/kJ7t16ALwSrg5Vh3nVm7y/XDQqAzGQyf996pIT2Gl1rF1JFUKWCp9B9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d510f6c4e6dc5c879788229fe4ef4c21dba3d66bbac21d0ed85f1d46a41e14be","last_reissued_at":"2026-07-05T00:08:07.615905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:07.615905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Deep Neural Network Defects with Data Flow Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huanlin Xu, Hui Xu, Jiazhen Gu, Michael Lyu, Xin Wang, Yangfan Zhou","submitted_at":"2019-09-05T02:56:33Z","abstract_excerpt":"Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks. However, it is very hard to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects. This paper aims at addressing this challenging problem. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We develop DeepMorph (DNN Tomography) to analyze the root cause, which can guide a DNN developer to improve the model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02190","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/1909.02190/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":"1909.02190","created_at":"2026-07-05T00:08:07.615963+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02190v2","created_at":"2026-07-05T00:08:07.615963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02190","created_at":"2026-07-05T00:08:07.615963+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UIPNRHG3ROI","created_at":"2026-07-05T00:08:07.615963+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UIPNRHG3ROIPF4I","created_at":"2026-07-05T00:08:07.615963+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UIPNRHG","created_at":"2026-07-05T00:08:07.615963+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/2UIPNRHG3ROIPF4IEKP6J32MEH","json":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH.json","graph_json":"https://pith.science/api/pith-number/2UIPNRHG3ROIPF4IEKP6J32MEH/graph.json","events_json":"https://pith.science/api/pith-number/2UIPNRHG3ROIPF4IEKP6J32MEH/events.json","paper":"https://pith.science/paper/2UIPNRHG"},"agent_actions":{"view_html":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH","download_json":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH.json","view_paper":"https://pith.science/paper/2UIPNRHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02190&json=true","fetch_graph":"https://pith.science/api/pith-number/2UIPNRHG3ROIPF4IEKP6J32MEH/graph.json","fetch_events":"https://pith.science/api/pith-number/2UIPNRHG3ROIPF4IEKP6J32MEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH/action/storage_attestation","attest_author":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH/action/author_attestation","sign_citation":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH/action/citation_signature","submit_replication":"https://pith.science/pith/2UIPNRHG3ROIPF4IEKP6J32MEH/action/replication_record"}},"created_at":"2026-07-05T00:08:07.615963+00:00","updated_at":"2026-07-05T00:08:07.615963+00:00"}