{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MS7GKKGD5BGJVGUP5KXKHTUNXM","short_pith_number":"pith:MS7GKKGD","schema_version":"1.0","canonical_sha256":"64be6528c3e84c9a9a8feaaea3ce8dbb22cb22249efcca0077813ab477afae41","source":{"kind":"arxiv","id":"1906.01150","version":1},"attestation_state":"computed","paper":{"title":"Breaking Inter-Layer Co-Adaptation by Classifier Anonymization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guoqing Liu, Ikuro Sato, Kohta Ishikawa, Masayuki Tanaka","submitted_at":"2019-06-04T01:33:35Z","abstract_excerpt":"This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimi"},"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":"1906.01150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T01:33:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"19d440aebc7984559eccc16448ad9482fb0bc863ab8a1448869052853ff0d48e","abstract_canon_sha256":"9d12915ea6c3635756665cfc811ccb6f5f35e6599895a8cd1da843cd641a413a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.715695Z","signature_b64":"btDRluFpuzeDMZ44nBjjtPJIeexttB3To8gpfRsSyLkcrkWpPyO5ivNnXDSqQYE2Zvrv8nBnjaZGEhYHkgk1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64be6528c3e84c9a9a8feaaea3ce8dbb22cb22249efcca0077813ab477afae41","last_reissued_at":"2026-05-17T23:44:17.715008Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.715008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Inter-Layer Co-Adaptation by Classifier Anonymization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guoqing Liu, Ikuro Sato, Kohta Ishikawa, Masayuki Tanaka","submitted_at":"2019-06-04T01:33:35Z","abstract_excerpt":"This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01150","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":"1906.01150","created_at":"2026-05-17T23:44:17.715119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01150v1","created_at":"2026-05-17T23:44:17.715119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01150","created_at":"2026-05-17T23:44:17.715119+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS7GKKGD5BGJ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS7GKKGD5BGJVGUP","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS7GKKGD","created_at":"2026-05-18T12:33:24.271573+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/MS7GKKGD5BGJVGUP5KXKHTUNXM","json":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM.json","graph_json":"https://pith.science/api/pith-number/MS7GKKGD5BGJVGUP5KXKHTUNXM/graph.json","events_json":"https://pith.science/api/pith-number/MS7GKKGD5BGJVGUP5KXKHTUNXM/events.json","paper":"https://pith.science/paper/MS7GKKGD"},"agent_actions":{"view_html":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM","download_json":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM.json","view_paper":"https://pith.science/paper/MS7GKKGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01150&json=true","fetch_graph":"https://pith.science/api/pith-number/MS7GKKGD5BGJVGUP5KXKHTUNXM/graph.json","fetch_events":"https://pith.science/api/pith-number/MS7GKKGD5BGJVGUP5KXKHTUNXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM/action/storage_attestation","attest_author":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM/action/author_attestation","sign_citation":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM/action/citation_signature","submit_replication":"https://pith.science/pith/MS7GKKGD5BGJVGUP5KXKHTUNXM/action/replication_record"}},"created_at":"2026-05-17T23:44:17.715119+00:00","updated_at":"2026-05-17T23:44:17.715119+00:00"}