{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2B4SD6WXRPXRYBKEQULAWM5ZW7","short_pith_number":"pith:2B4SD6WX","schema_version":"1.0","canonical_sha256":"d07921fad78bef1c054485160b33b9b7d1c968b1511afc987c016a6f07664995","source":{"kind":"arxiv","id":"2302.04002","version":1},"attestation_state":"computed","paper":{"title":"The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Di Luan, Jun Cen, Qifeng Chen, Shaojie Shen, Shiwei Zhang, Yingya Zhang, Yixuan Pei","submitted_at":"2023-02-08T11:34:04Z","abstract_excerpt":"Open-set Recognition (OSR) aims to identify test samples whose classes are not seen during the training process. Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications. The UOSR draws little attention since it is proposed, but we find sometimes it is even more practical than OSR in the real world applications, as evaluation results of known but wrongly classified samples are also wrong like unknown samples. In this paper, we deeply analyze the U"},"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":"2302.04002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-08T11:34:04Z","cross_cats_sorted":[],"title_canon_sha256":"97a3766554017c2494b6dbe530a122878ba935ccdbc3513779b4e1b3c80cfb40","abstract_canon_sha256":"9d8cb07b04813eca77c5f88be0c0b307ff467c9211c30209649770f38c89518c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:00.174912Z","signature_b64":"BxwiKcg6X/YZKZcZ2AZB5m0zBVwuZtq1EVraC7cVA3+OxWrYKYudeHXpfsxUbIXhtWn2VQe3CRYQ7n0UW3noCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d07921fad78bef1c054485160b33b9b7d1c968b1511afc987c016a6f07664995","last_reissued_at":"2026-07-05T05:40:00.174430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:00.174430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Di Luan, Jun Cen, Qifeng Chen, Shaojie Shen, Shiwei Zhang, Yingya Zhang, Yixuan Pei","submitted_at":"2023-02-08T11:34:04Z","abstract_excerpt":"Open-set Recognition (OSR) aims to identify test samples whose classes are not seen during the training process. Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications. The UOSR draws little attention since it is proposed, but we find sometimes it is even more practical than OSR in the real world applications, as evaluation results of known but wrongly classified samples are also wrong like unknown samples. In this paper, we deeply analyze the U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04002","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/2302.04002/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":"2302.04002","created_at":"2026-07-05T05:40:00.174489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04002v1","created_at":"2026-07-05T05:40:00.174489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04002","created_at":"2026-07-05T05:40:00.174489+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B4SD6WXRPXR","created_at":"2026-07-05T05:40:00.174489+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B4SD6WXRPXRYBKE","created_at":"2026-07-05T05:40:00.174489+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B4SD6WX","created_at":"2026-07-05T05:40:00.174489+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":9,"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":9,"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":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7","json":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7.json","graph_json":"https://pith.science/api/pith-number/2B4SD6WXRPXRYBKEQULAWM5ZW7/graph.json","events_json":"https://pith.science/api/pith-number/2B4SD6WXRPXRYBKEQULAWM5ZW7/events.json","paper":"https://pith.science/paper/2B4SD6WX"},"agent_actions":{"view_html":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7","download_json":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7.json","view_paper":"https://pith.science/paper/2B4SD6WX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04002&json=true","fetch_graph":"https://pith.science/api/pith-number/2B4SD6WXRPXRYBKEQULAWM5ZW7/graph.json","fetch_events":"https://pith.science/api/pith-number/2B4SD6WXRPXRYBKEQULAWM5ZW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7/action/storage_attestation","attest_author":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7/action/author_attestation","sign_citation":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7/action/citation_signature","submit_replication":"https://pith.science/pith/2B4SD6WXRPXRYBKEQULAWM5ZW7/action/replication_record"}},"created_at":"2026-07-05T05:40:00.174489+00:00","updated_at":"2026-07-05T05:40:00.174489+00:00"}