{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VECLU4FIMYNDPYIEEMK3TZNTG","short_pith_number":"pith:3VECLU4F","schema_version":"1.0","canonical_sha256":"dd4825d3854330d1bf082118adcf2d99aee15792e3039e321d75941a29b78e00","source":{"kind":"arxiv","id":"2402.15374","version":4},"attestation_state":"computed","paper":{"title":"Outlier detection by ensembling uncertainty with negative objectness","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anja Deli\\'c, Matej Grci\\'c, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2024-02-23T15:19:37Z","abstract_excerpt":"Outlier detection is an essential capability in safety-critical applications of supervised visual recognition. Most of the existing methods deliver best results by encouraging standard closed-set models to produce low-confidence predictions in negative training data. However, that approach conflates prediction uncertainty with recognition of the negative class. We therefore reconsider direct prediction of K+1 logits that correspond to K groundtruth classes and one outlier class. This setup allows us to formulate a novel anomaly score as an ensemble of in-distribution uncertainty and the poster"},"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":"2402.15374","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-23T15:19:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9bdca4c3fb18bd03c24ae5cf1f205c8df4b1ebf0aa25ca93c3a6676eb3bfa45","abstract_canon_sha256":"a8e0f691edacc4bcc86dd8a16294fe224bf05fdf053ce9f8b4597a694f1fbb12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:32.940716Z","signature_b64":"u1I3RbEA7DtC+I5zNu1qLK/37Vp+waVgKhLcMCicMHHOWUYf9v/cLBy1H9N+MYJ2/E/XR+/HP2M46LK6CtXdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd4825d3854330d1bf082118adcf2d99aee15792e3039e321d75941a29b78e00","last_reissued_at":"2026-07-05T09:04:32.940347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:32.940347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Outlier detection by ensembling uncertainty with negative objectness","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anja Deli\\'c, Matej Grci\\'c, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2024-02-23T15:19:37Z","abstract_excerpt":"Outlier detection is an essential capability in safety-critical applications of supervised visual recognition. Most of the existing methods deliver best results by encouraging standard closed-set models to produce low-confidence predictions in negative training data. However, that approach conflates prediction uncertainty with recognition of the negative class. We therefore reconsider direct prediction of K+1 logits that correspond to K groundtruth classes and one outlier class. This setup allows us to formulate a novel anomaly score as an ensemble of in-distribution uncertainty and the poster"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15374","kind":"arxiv","version":4},"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/2402.15374/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":"2402.15374","created_at":"2026-07-05T09:04:32.940404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15374v4","created_at":"2026-07-05T09:04:32.940404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15374","created_at":"2026-07-05T09:04:32.940404+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VECLU4FIMYN","created_at":"2026-07-05T09:04:32.940404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VECLU4FIMYNDPYI","created_at":"2026-07-05T09:04:32.940404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VECLU4F","created_at":"2026-07-05T09:04:32.940404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.12776","citing_title":"Randomized PCA Forest for Unsupervised Outlier Detection","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG","json":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG.json","graph_json":"https://pith.science/api/pith-number/3VECLU4FIMYNDPYIEEMK3TZNTG/graph.json","events_json":"https://pith.science/api/pith-number/3VECLU4FIMYNDPYIEEMK3TZNTG/events.json","paper":"https://pith.science/paper/3VECLU4F"},"agent_actions":{"view_html":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG","download_json":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG.json","view_paper":"https://pith.science/paper/3VECLU4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15374&json=true","fetch_graph":"https://pith.science/api/pith-number/3VECLU4FIMYNDPYIEEMK3TZNTG/graph.json","fetch_events":"https://pith.science/api/pith-number/3VECLU4FIMYNDPYIEEMK3TZNTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG/action/storage_attestation","attest_author":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG/action/author_attestation","sign_citation":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG/action/citation_signature","submit_replication":"https://pith.science/pith/3VECLU4FIMYNDPYIEEMK3TZNTG/action/replication_record"}},"created_at":"2026-07-05T09:04:32.940404+00:00","updated_at":"2026-07-05T09:04:32.940404+00:00"}