{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AJL4NL4JJ65TBJOCLLYKL6RMOL","short_pith_number":"pith:AJL4NL4J","schema_version":"1.0","canonical_sha256":"0257c6af894fbb30a5c25af0a5fa2c72c6714e810f5bcef90da55c8dad103693","source":{"kind":"arxiv","id":"1812.08468","version":5},"attestation_state":"computed","paper":{"title":"One-Class Feature Learning Using Intra-Class Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Patrick Schlachter, Yiwen Liao","submitted_at":"2018-12-20T10:32:46Z","abstract_excerpt":"This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature extractors. In contrast, the proposed method realizes feature learning by splitting the given normal class into typical and atypical normal samples. By introducing closeness loss and dispersion loss, an intra-class joint training procedure between the two subsets after splitting "},"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":"1812.08468","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-20T10:32:46Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"28cbcc3ae3947848c6310612b3fb893d105a7467f6d2330ec52249cfcc9324bb","abstract_canon_sha256":"7581c9ddfc32de1ff6abdc00e70943b849149a707f6f4bdd4620706b9fe686d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:42.635372Z","signature_b64":"IWvWn+NaVzdT576JYiTfvlsjst7fn/NvXX5kfD/MRlQvfoTWtirh2eCCvI/YXG2yF+TD1BZ04tWIUs24BXSdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0257c6af894fbb30a5c25af0a5fa2c72c6714e810f5bcef90da55c8dad103693","last_reissued_at":"2026-07-05T00:20:42.634933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:42.634933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Class Feature Learning Using Intra-Class Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Patrick Schlachter, Yiwen Liao","submitted_at":"2018-12-20T10:32:46Z","abstract_excerpt":"This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature extractors. In contrast, the proposed method realizes feature learning by splitting the given normal class into typical and atypical normal samples. By introducing closeness loss and dispersion loss, an intra-class joint training procedure between the two subsets after splitting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08468","kind":"arxiv","version":5},"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/1812.08468/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":"1812.08468","created_at":"2026-07-05T00:20:42.634987+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08468v5","created_at":"2026-07-05T00:20:42.634987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08468","created_at":"2026-07-05T00:20:42.634987+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJL4NL4JJ65T","created_at":"2026-07-05T00:20:42.634987+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJL4NL4JJ65TBJOC","created_at":"2026-07-05T00:20:42.634987+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJL4NL4J","created_at":"2026-07-05T00:20:42.634987+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/AJL4NL4JJ65TBJOCLLYKL6RMOL","json":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL.json","graph_json":"https://pith.science/api/pith-number/AJL4NL4JJ65TBJOCLLYKL6RMOL/graph.json","events_json":"https://pith.science/api/pith-number/AJL4NL4JJ65TBJOCLLYKL6RMOL/events.json","paper":"https://pith.science/paper/AJL4NL4J"},"agent_actions":{"view_html":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL","download_json":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL.json","view_paper":"https://pith.science/paper/AJL4NL4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/AJL4NL4JJ65TBJOCLLYKL6RMOL/graph.json","fetch_events":"https://pith.science/api/pith-number/AJL4NL4JJ65TBJOCLLYKL6RMOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL/action/storage_attestation","attest_author":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL/action/author_attestation","sign_citation":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL/action/citation_signature","submit_replication":"https://pith.science/pith/AJL4NL4JJ65TBJOCLLYKL6RMOL/action/replication_record"}},"created_at":"2026-07-05T00:20:42.634987+00:00","updated_at":"2026-07-05T00:20:42.634987+00:00"}