{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGV6INVE5HBB3J55RPIMTAISDZ","short_pith_number":"pith:JGV6INVE","schema_version":"1.0","canonical_sha256":"49abe436a4e9c21da7bd8bd0c981121e606830207fa76090784909109562cc08","source":{"kind":"arxiv","id":"2503.06442","version":2},"attestation_state":"computed","paper":{"title":"OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Haiqi Zhang, Hao Tang, Jing Qin, Yu Liu, Zechao Li","submitted_at":"2025-03-09T04:47:19Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications. While zero-shot OOD detection, which requires no training on in-distribution (ID) data, has become feasible with the emergence of vision-language models like CLIP, existing methods primarily focus on semantic matching and fail to fully capture distributional discrepancies. To address these limitations, we propose OT-DETECTOR, a novel framework that employs Optimal Transport (OT) to quantify both semantic and distributional discrepancies between test samp"},"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":"2503.06442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T04:47:19Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7ce36aa3d863196b7ccb406abd8602710c5b3145ef9aaf5d5e8d39782d525d94","abstract_canon_sha256":"e175e4e0f36e6fd430787b0a418c2cc9f7a7b4e7a173b69f82982c01f0432ca7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:41.360037Z","signature_b64":"+YzIirFh9sSItiW7UHalF7zYlibXoCCXUuwiQHYbTJEQm3bE8bqyvabqYrs3b9UhfHsdPIox0F8p3GflhXFuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49abe436a4e9c21da7bd8bd0c981121e606830207fa76090784909109562cc08","last_reissued_at":"2026-07-05T11:05:41.359491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:41.359491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Haiqi Zhang, Hao Tang, Jing Qin, Yu Liu, Zechao Li","submitted_at":"2025-03-09T04:47:19Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications. While zero-shot OOD detection, which requires no training on in-distribution (ID) data, has become feasible with the emergence of vision-language models like CLIP, existing methods primarily focus on semantic matching and fail to fully capture distributional discrepancies. To address these limitations, we propose OT-DETECTOR, a novel framework that employs Optimal Transport (OT) to quantify both semantic and distributional discrepancies between test samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06442","kind":"arxiv","version":2},"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/2503.06442/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":"2503.06442","created_at":"2026-07-05T11:05:41.359561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06442v2","created_at":"2026-07-05T11:05:41.359561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06442","created_at":"2026-07-05T11:05:41.359561+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGV6INVE5HBB","created_at":"2026-07-05T11:05:41.359561+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGV6INVE5HBB3J55","created_at":"2026-07-05T11:05:41.359561+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGV6INVE","created_at":"2026-07-05T11:05:41.359561+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/JGV6INVE5HBB3J55RPIMTAISDZ","json":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ.json","graph_json":"https://pith.science/api/pith-number/JGV6INVE5HBB3J55RPIMTAISDZ/graph.json","events_json":"https://pith.science/api/pith-number/JGV6INVE5HBB3J55RPIMTAISDZ/events.json","paper":"https://pith.science/paper/JGV6INVE"},"agent_actions":{"view_html":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ","download_json":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ.json","view_paper":"https://pith.science/paper/JGV6INVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06442&json=true","fetch_graph":"https://pith.science/api/pith-number/JGV6INVE5HBB3J55RPIMTAISDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JGV6INVE5HBB3J55RPIMTAISDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ/action/storage_attestation","attest_author":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ/action/author_attestation","sign_citation":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ/action/citation_signature","submit_replication":"https://pith.science/pith/JGV6INVE5HBB3J55RPIMTAISDZ/action/replication_record"}},"created_at":"2026-07-05T11:05:41.359561+00:00","updated_at":"2026-07-05T11:05:41.359561+00:00"}