{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V33FNGCGJ3AJ3Q6JBEKEVZ75KM","short_pith_number":"pith:V33FNGCG","schema_version":"1.0","canonical_sha256":"aef65698464ec09dc3c909144ae7fd5320c0f5ebfeca190faf07d310f27b97fd","source":{"kind":"arxiv","id":"2403.20078","version":1},"attestation_state":"computed","paper":{"title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Feng Liu, Feng Zheng, Hong Chen, Tongliang Liu, Xue Jiang, Zhen Fang","submitted_at":"2024-03-29T09:19:52Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims at identifying samples from unknown classes, playing a crucial role in trustworthy models against errors on unexpected inputs. Extensive research has been dedicated to exploring OOD detection in the vision modality. Vision-language models (VLMs) can leverage both textual and visual information for various multi-modal applications, whereas few OOD detection methods take into account information from the text modality. In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extens"},"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":"2403.20078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T09:19:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f1906b1ac45bd9f29686d3eaac2bb10c139896518bd6d8707780ebb4ee16c11","abstract_canon_sha256":"7c2be84146a224688d04f083936c2618223e4f768d00b9b6db18472f5a64ae74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:13.187174Z","signature_b64":"SOfPWglsgopKcPfvGhPfArVB6O+Z9a2VNCwO2FrtCtaIGcQRlpq3Gz/bHVToZnI4oT2Eqq8Z7RndK3kJhm5ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef65698464ec09dc3c909144ae7fd5320c0f5ebfeca190faf07d310f27b97fd","last_reissued_at":"2026-07-05T08:02:13.186672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:13.186672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Feng Liu, Feng Zheng, Hong Chen, Tongliang Liu, Xue Jiang, Zhen Fang","submitted_at":"2024-03-29T09:19:52Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims at identifying samples from unknown classes, playing a crucial role in trustworthy models against errors on unexpected inputs. Extensive research has been dedicated to exploring OOD detection in the vision modality. Vision-language models (VLMs) can leverage both textual and visual information for various multi-modal applications, whereas few OOD detection methods take into account information from the text modality. In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20078","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/2403.20078/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":"2403.20078","created_at":"2026-07-05T08:02:13.186734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20078v1","created_at":"2026-07-05T08:02:13.186734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20078","created_at":"2026-07-05T08:02:13.186734+00:00"},{"alias_kind":"pith_short_12","alias_value":"V33FNGCGJ3AJ","created_at":"2026-07-05T08:02:13.186734+00:00"},{"alias_kind":"pith_short_16","alias_value":"V33FNGCGJ3AJ3Q6J","created_at":"2026-07-05T08:02:13.186734+00:00"},{"alias_kind":"pith_short_8","alias_value":"V33FNGCG","created_at":"2026-07-05T08:02:13.186734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25758","citing_title":"Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22537","citing_title":"NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23797","citing_title":"Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM","json":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM.json","graph_json":"https://pith.science/api/pith-number/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/graph.json","events_json":"https://pith.science/api/pith-number/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/events.json","paper":"https://pith.science/paper/V33FNGCG"},"agent_actions":{"view_html":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM","download_json":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM.json","view_paper":"https://pith.science/paper/V33FNGCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20078&json=true","fetch_graph":"https://pith.science/api/pith-number/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/graph.json","fetch_events":"https://pith.science/api/pith-number/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/action/storage_attestation","attest_author":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/action/author_attestation","sign_citation":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/action/citation_signature","submit_replication":"https://pith.science/pith/V33FNGCGJ3AJ3Q6JBEKEVZ75KM/action/replication_record"}},"created_at":"2026-07-05T08:02:13.186734+00:00","updated_at":"2026-07-05T08:02:13.186734+00:00"}