{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CFMNPQMQ4HSN7WRXFDSYVWH5K3","short_pith_number":"pith:CFMNPQMQ","schema_version":"1.0","canonical_sha256":"1158d7c190e1e4dfda3728e58ad8fd56d3dfa8a8aaec5a160bb53d07b822bec7","source":{"kind":"arxiv","id":"2412.05292","version":1},"attestation_state":"computed","paper":{"title":"TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiankang Chen, Ruixuan Wang, Tong Zhang, Wei-Shi Zheng","submitted_at":"2024-11-22T14:40:25Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (`anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluati"},"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":"2412.05292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T14:40:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20edd190934b2a9899fb1e0d1c08ac46a9462b7b7c7600aaf4438e24ac2c7322","abstract_canon_sha256":"8bf0d55e26fb2b3f8233f48b5638fd5d36fa64ecc292ad2fa43aaedcdc7eccb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:00.888498Z","signature_b64":"PHpl6V/0ymt+RFJ/PRwTzou5j3uQf7kKWdStUfQmZyArB0+ziT9s4nJk0N0McEb6MgxzQScHl0AIVVct/E3VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1158d7c190e1e4dfda3728e58ad8fd56d3dfa8a8aaec5a160bb53d07b822bec7","last_reissued_at":"2026-07-05T09:46:00.888025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:00.888025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiankang Chen, Ruixuan Wang, Tong Zhang, Wei-Shi Zheng","submitted_at":"2024-11-22T14:40:25Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (`anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05292","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/2412.05292/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":"2412.05292","created_at":"2026-07-05T09:46:00.888083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05292v1","created_at":"2026-07-05T09:46:00.888083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05292","created_at":"2026-07-05T09:46:00.888083+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFMNPQMQ4HSN","created_at":"2026-07-05T09:46:00.888083+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFMNPQMQ4HSN7WRX","created_at":"2026-07-05T09:46:00.888083+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFMNPQMQ","created_at":"2026-07-05T09:46:00.888083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3","json":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3.json","graph_json":"https://pith.science/api/pith-number/CFMNPQMQ4HSN7WRXFDSYVWH5K3/graph.json","events_json":"https://pith.science/api/pith-number/CFMNPQMQ4HSN7WRXFDSYVWH5K3/events.json","paper":"https://pith.science/paper/CFMNPQMQ"},"agent_actions":{"view_html":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3","download_json":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3.json","view_paper":"https://pith.science/paper/CFMNPQMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05292&json=true","fetch_graph":"https://pith.science/api/pith-number/CFMNPQMQ4HSN7WRXFDSYVWH5K3/graph.json","fetch_events":"https://pith.science/api/pith-number/CFMNPQMQ4HSN7WRXFDSYVWH5K3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3/action/storage_attestation","attest_author":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3/action/author_attestation","sign_citation":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3/action/citation_signature","submit_replication":"https://pith.science/pith/CFMNPQMQ4HSN7WRXFDSYVWH5K3/action/replication_record"}},"created_at":"2026-07-05T09:46:00.888083+00:00","updated_at":"2026-07-05T09:46:00.888083+00:00"}