{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BJSXIV5MP3QBBPBQ4PHGSPQ4YE","short_pith_number":"pith:BJSXIV5M","schema_version":"1.0","canonical_sha256":"0a657457ac7ee010bc30e3ce693e1cc115a6ae05edee0130e4684a9bf80a0cea","source":{"kind":"arxiv","id":"2207.02158","version":1},"attestation_state":"computed","paper":{"title":"Class-Specific Semantic Reconstruction for Open Set Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongzhi Huang, Ming-Ming Cheng, Qinghua Hu, Yu Wang","submitted_at":"2022-07-05T16:25:34Z","abstract_excerpt":"Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existing methods basing on auto-encoder (AE) and prototype learning show great potential in handling this challenging task. In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning. Specifically, CSSR replaces prototype points with manifolds represented by class-specific AEs. Unlike conventional prototype-based methods, CSSR models"},"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":"2207.02158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-05T16:25:34Z","cross_cats_sorted":[],"title_canon_sha256":"e6def8aea76d53840cf05eb6c822bdddf856040b38b3dbcae5d9311c681eb4a9","abstract_canon_sha256":"fce0b556d227e3e8d099651084d488efbc646f419b5bb654c822aa3f0bca89c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:47.888415Z","signature_b64":"bfUGjZEHpWfgJA+MxYHMwWOlJ+6et82dCAQfz7SJBuiJahmYOc4BQDNQVJQpYRCG4A7nsJAZirtD5FxTPO/EAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a657457ac7ee010bc30e3ce693e1cc115a6ae05edee0130e4684a9bf80a0cea","last_reissued_at":"2026-07-05T04:37:47.887981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:47.887981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Specific Semantic Reconstruction for Open Set Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongzhi Huang, Ming-Ming Cheng, Qinghua Hu, Yu Wang","submitted_at":"2022-07-05T16:25:34Z","abstract_excerpt":"Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existing methods basing on auto-encoder (AE) and prototype learning show great potential in handling this challenging task. In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning. Specifically, CSSR replaces prototype points with manifolds represented by class-specific AEs. Unlike conventional prototype-based methods, CSSR models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02158","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/2207.02158/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":"2207.02158","created_at":"2026-07-05T04:37:47.888039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02158v1","created_at":"2026-07-05T04:37:47.888039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02158","created_at":"2026-07-05T04:37:47.888039+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJSXIV5MP3QB","created_at":"2026-07-05T04:37:47.888039+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJSXIV5MP3QBBPBQ","created_at":"2026-07-05T04:37:47.888039+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJSXIV5M","created_at":"2026-07-05T04:37:47.888039+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/BJSXIV5MP3QBBPBQ4PHGSPQ4YE","json":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE.json","graph_json":"https://pith.science/api/pith-number/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/graph.json","events_json":"https://pith.science/api/pith-number/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/events.json","paper":"https://pith.science/paper/BJSXIV5M"},"agent_actions":{"view_html":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE","download_json":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE.json","view_paper":"https://pith.science/paper/BJSXIV5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02158&json=true","fetch_graph":"https://pith.science/api/pith-number/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/graph.json","fetch_events":"https://pith.science/api/pith-number/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/action/storage_attestation","attest_author":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/action/author_attestation","sign_citation":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/action/citation_signature","submit_replication":"https://pith.science/pith/BJSXIV5MP3QBBPBQ4PHGSPQ4YE/action/replication_record"}},"created_at":"2026-07-05T04:37:47.888039+00:00","updated_at":"2026-07-05T04:37:47.888039+00:00"}