{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XHCUEUIH5HAV7CXS2O2KBQHD4G","short_pith_number":"pith:XHCUEUIH","schema_version":"1.0","canonical_sha256":"b9c5425107e9c15f8af2d3b4a0c0e3e1a46d46a8a910e88fefcf82495d27e989","source":{"kind":"arxiv","id":"1903.08789","version":1},"attestation_state":"computed","paper":{"title":"Interpreting Neural Networks Using Flip Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dianne P. O'Leary, Roozbeh Yousefzadeh","submitted_at":"2019-03-21T01:03:42Z","abstract_excerpt":"Neural networks have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Here, we introduce a novel technique, interpreting a trained neural network by investigating its flip points. A flip point is any point that lies on the boundary between two output classes: e.g. for a neural network with a binary yes/no output, a flip point is any input that generates equal scores for \"yes\" and \"no\". The flip point closest to a given input is of particular importance, and this point is the solution to a well-posed optimization problem"},"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":"1903.08789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T01:03:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"605d895f7f8c44b7c4d825d84eae43a658c15dcc324b56d1320eaf329a545891","abstract_canon_sha256":"cfb5179c3a0ec10ed7ac14a8018ff301ffaef9094567f73f43a67832f281ebac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:43.928944Z","signature_b64":"5D2im7DSYFCWv9IkNcj8I/v5PeNL4Wo+bzwJ7ykpSMD5wGBirC51ZfubmgUdTAmZY0qr6UchNfeunBjPNTX9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c5425107e9c15f8af2d3b4a0c0e3e1a46d46a8a910e88fefcf82495d27e989","last_reissued_at":"2026-05-17T23:50:43.928376Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:43.928376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting Neural Networks Using Flip Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dianne P. O'Leary, Roozbeh Yousefzadeh","submitted_at":"2019-03-21T01:03:42Z","abstract_excerpt":"Neural networks have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Here, we introduce a novel technique, interpreting a trained neural network by investigating its flip points. A flip point is any point that lies on the boundary between two output classes: e.g. for a neural network with a binary yes/no output, a flip point is any input that generates equal scores for \"yes\" and \"no\". The flip point closest to a given input is of particular importance, and this point is the solution to a well-posed optimization problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08789","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":""},"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":"1903.08789","created_at":"2026-05-17T23:50:43.928474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08789v1","created_at":"2026-05-17T23:50:43.928474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08789","created_at":"2026-05-17T23:50:43.928474+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHCUEUIH5HAV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHCUEUIH5HAV7CXS","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHCUEUIH","created_at":"2026-05-18T12:33:33.725879+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/XHCUEUIH5HAV7CXS2O2KBQHD4G","json":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G.json","graph_json":"https://pith.science/api/pith-number/XHCUEUIH5HAV7CXS2O2KBQHD4G/graph.json","events_json":"https://pith.science/api/pith-number/XHCUEUIH5HAV7CXS2O2KBQHD4G/events.json","paper":"https://pith.science/paper/XHCUEUIH"},"agent_actions":{"view_html":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G","download_json":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G.json","view_paper":"https://pith.science/paper/XHCUEUIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08789&json=true","fetch_graph":"https://pith.science/api/pith-number/XHCUEUIH5HAV7CXS2O2KBQHD4G/graph.json","fetch_events":"https://pith.science/api/pith-number/XHCUEUIH5HAV7CXS2O2KBQHD4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G/action/storage_attestation","attest_author":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G/action/author_attestation","sign_citation":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G/action/citation_signature","submit_replication":"https://pith.science/pith/XHCUEUIH5HAV7CXS2O2KBQHD4G/action/replication_record"}},"created_at":"2026-05-17T23:50:43.928474+00:00","updated_at":"2026-05-17T23:50:43.928474+00:00"}