{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GQY2IQKAXPYF22X3W52BBHPSIL","short_pith_number":"pith:GQY2IQKA","schema_version":"1.0","canonical_sha256":"3431a44140bbf05d6afbb774109df242c76c269086cc5e2f017333060b4252aa","source":{"kind":"arxiv","id":"2311.13355","version":2},"attestation_state":"computed","paper":{"title":"Unified Classification and Rejection: A One-versus-All Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Xu-Yao Zhang, Zhen Cheng","submitted_at":"2023-11-22T12:47:12Z","abstract_excerpt":"Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification while performs poorly in rejecting OOD inputs. To tackle this problem, numerous methods have been designed to perform open set recognition (OSR) or OOD rejection/detection tasks. Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes. In this paper, we attempt to buil"},"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":"2311.13355","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T12:47:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4027eb78d8c96560df97ac5e76676db082868fff1b3174333fd4200c407449f","abstract_canon_sha256":"8cfc832d57bc642a6d0b24072f162373859ffb29c8c79b0158d33765c639ebe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:44.855879Z","signature_b64":"tSSQsXq4HKtFiDJzHA6rmZs/nI27jET1BnwMDHcq9nkLPFxm+pokYEI0H/MJ+8+WjVlbD9Cg4p6cJ0w1x8n3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3431a44140bbf05d6afbb774109df242c76c269086cc5e2f017333060b4252aa","last_reissued_at":"2026-07-05T08:51:44.855428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:44.855428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Classification and Rejection: A One-versus-All Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Xu-Yao Zhang, Zhen Cheng","submitted_at":"2023-11-22T12:47:12Z","abstract_excerpt":"Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification while performs poorly in rejecting OOD inputs. To tackle this problem, numerous methods have been designed to perform open set recognition (OSR) or OOD rejection/detection tasks. Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes. In this paper, we attempt to buil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13355","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/2311.13355/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":"2311.13355","created_at":"2026-07-05T08:51:44.855486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13355v2","created_at":"2026-07-05T08:51:44.855486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13355","created_at":"2026-07-05T08:51:44.855486+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQY2IQKAXPYF","created_at":"2026-07-05T08:51:44.855486+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQY2IQKAXPYF22X3","created_at":"2026-07-05T08:51:44.855486+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQY2IQKA","created_at":"2026-07-05T08:51:44.855486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20490","citing_title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20490","citing_title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20490","citing_title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL","json":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL.json","graph_json":"https://pith.science/api/pith-number/GQY2IQKAXPYF22X3W52BBHPSIL/graph.json","events_json":"https://pith.science/api/pith-number/GQY2IQKAXPYF22X3W52BBHPSIL/events.json","paper":"https://pith.science/paper/GQY2IQKA"},"agent_actions":{"view_html":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL","download_json":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL.json","view_paper":"https://pith.science/paper/GQY2IQKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13355&json=true","fetch_graph":"https://pith.science/api/pith-number/GQY2IQKAXPYF22X3W52BBHPSIL/graph.json","fetch_events":"https://pith.science/api/pith-number/GQY2IQKAXPYF22X3W52BBHPSIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL/action/storage_attestation","attest_author":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL/action/author_attestation","sign_citation":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL/action/citation_signature","submit_replication":"https://pith.science/pith/GQY2IQKAXPYF22X3W52BBHPSIL/action/replication_record"}},"created_at":"2026-07-05T08:51:44.855486+00:00","updated_at":"2026-07-05T08:51:44.855486+00:00"}