{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XNMLVLOQBAHCUY5KBEVQ2XFMZ","short_pith_number":"pith:5XNMLVLO","schema_version":"1.0","canonical_sha256":"eddac5d56e804071531d5049586ae5664fe57a9078efd2547ccfb312f7be4156","source":{"kind":"arxiv","id":"2408.15566","version":1},"attestation_state":"computed","paper":{"title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinglun Li, Kaixun Jiang, Lingyi Hong, Pinxue Guo, Weifeng Ge, Wenqiang Zhang, Xinyu Zhou, Zhaoyu Chen","submitted_at":"2024-08-28T06:37:59Z","abstract_excerpt":"Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose \\textbf{TagOOD}, a novel approach for OOD detection that leverages vision-language rep"},"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":"2408.15566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T06:37:59Z","cross_cats_sorted":[],"title_canon_sha256":"73824c8dd727ce39f3a1a554d83b171e04f82dc062c61b831318716a13aafb52","abstract_canon_sha256":"ff8d0dc10f083e4869123a0fcd104b14f1eb0cd6520aa2c82f08298b88d5d773"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:13.872813Z","signature_b64":"Qt1nEP5IYzUL3TwxaoK5/C0nH895odDKsIw2H9/4NEJraaKLsjjxrJ6Gsj7rGnZ95FRsRqd7LraZTxcKmE8uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eddac5d56e804071531d5049586ae5664fe57a9078efd2547ccfb312f7be4156","last_reissued_at":"2026-07-05T09:00:13.871627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:13.871627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinglun Li, Kaixun Jiang, Lingyi Hong, Pinxue Guo, Weifeng Ge, Wenqiang Zhang, Xinyu Zhou, Zhaoyu Chen","submitted_at":"2024-08-28T06:37:59Z","abstract_excerpt":"Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose \\textbf{TagOOD}, a novel approach for OOD detection that leverages vision-language rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15566","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/2408.15566/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":"2408.15566","created_at":"2026-07-05T09:00:13.872414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15566v1","created_at":"2026-07-05T09:00:13.872414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15566","created_at":"2026-07-05T09:00:13.872414+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XNMLVLOQBAH","created_at":"2026-07-05T09:00:13.872414+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XNMLVLOQBAHCUY5","created_at":"2026-07-05T09:00:13.872414+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XNMLVLO","created_at":"2026-07-05T09:00:13.872414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10225","citing_title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ","json":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ.json","graph_json":"https://pith.science/api/pith-number/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/graph.json","events_json":"https://pith.science/api/pith-number/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/events.json","paper":"https://pith.science/paper/5XNMLVLO"},"agent_actions":{"view_html":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ","download_json":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ.json","view_paper":"https://pith.science/paper/5XNMLVLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15566&json=true","fetch_graph":"https://pith.science/api/pith-number/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/action/storage_attestation","attest_author":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/action/author_attestation","sign_citation":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/action/citation_signature","submit_replication":"https://pith.science/pith/5XNMLVLOQBAHCUY5KBEVQ2XFMZ/action/replication_record"}},"created_at":"2026-07-05T09:00:13.872414+00:00","updated_at":"2026-07-05T09:00:13.872414+00:00"}