{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FP34M7S6BVK7AXGIYOEPBESM25","short_pith_number":"pith:FP34M7S6","schema_version":"1.0","canonical_sha256":"2bf7c67e5e0d55f05cc8c388f0924cd749c5783014e6a905da4af40afa350852","source":{"kind":"arxiv","id":"2310.08027","version":1},"attestation_state":"computed","paper":{"title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Hao Lang, Kaisheng Zeng, Yi Dai, Yongbin Li","submitted_at":"2023-10-12T04:14:28Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently neglects the rich contextual information of ID classes. Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. Indiscriminately using such knowledge causes catastrophic damage to OOD detection due to LLMs' hallucinations, as is observed by our analysis. In this paper, we propose to"},"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":"2310.08027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T04:14:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6afad4517726f69fbf76466473d4d1170f92fa70a6a08ef4f1485ee301e0e547","abstract_canon_sha256":"83a7a924b3257398be8ee923a2eba6e57d0712cf9590984ea652aa1f95d8a2b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:59.673353Z","signature_b64":"2BMg22hEf7ELmzZgDTcvANQU76XMEfbZVZ7py0BzdbKxu4/F16VfGJ7vQbeqLBY4Nssio5Ci4Z8pKXNC9FfPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf7c67e5e0d55f05cc8c388f0924cd749c5783014e6a905da4af40afa350852","last_reissued_at":"2026-07-05T06:59:59.672885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:59.672885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Hao Lang, Kaisheng Zeng, Yi Dai, Yongbin Li","submitted_at":"2023-10-12T04:14:28Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently neglects the rich contextual information of ID classes. Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. Indiscriminately using such knowledge causes catastrophic damage to OOD detection due to LLMs' hallucinations, as is observed by our analysis. In this paper, we propose to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08027","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/2310.08027/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":"2310.08027","created_at":"2026-07-05T06:59:59.672943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08027v1","created_at":"2026-07-05T06:59:59.672943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08027","created_at":"2026-07-05T06:59:59.672943+00:00"},{"alias_kind":"pith_short_12","alias_value":"FP34M7S6BVK7","created_at":"2026-07-05T06:59:59.672943+00:00"},{"alias_kind":"pith_short_16","alias_value":"FP34M7S6BVK7AXGI","created_at":"2026-07-05T06:59:59.672943+00:00"},{"alias_kind":"pith_short_8","alias_value":"FP34M7S6","created_at":"2026-07-05T06:59:59.672943+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/FP34M7S6BVK7AXGIYOEPBESM25","json":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25.json","graph_json":"https://pith.science/api/pith-number/FP34M7S6BVK7AXGIYOEPBESM25/graph.json","events_json":"https://pith.science/api/pith-number/FP34M7S6BVK7AXGIYOEPBESM25/events.json","paper":"https://pith.science/paper/FP34M7S6"},"agent_actions":{"view_html":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25","download_json":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25.json","view_paper":"https://pith.science/paper/FP34M7S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08027&json=true","fetch_graph":"https://pith.science/api/pith-number/FP34M7S6BVK7AXGIYOEPBESM25/graph.json","fetch_events":"https://pith.science/api/pith-number/FP34M7S6BVK7AXGIYOEPBESM25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25/action/storage_attestation","attest_author":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25/action/author_attestation","sign_citation":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25/action/citation_signature","submit_replication":"https://pith.science/pith/FP34M7S6BVK7AXGIYOEPBESM25/action/replication_record"}},"created_at":"2026-07-05T06:59:59.672943+00:00","updated_at":"2026-07-05T06:59:59.672943+00:00"}