{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TX4RYWHSTY2GPQZMEVAGM34KDI","short_pith_number":"pith:TX4RYWHS","schema_version":"1.0","canonical_sha256":"9df91c58f29e3467c32c2540666f8a1a16e3c96b37935a406e64066fc76886af","source":{"kind":"arxiv","id":"2405.17419","version":2},"attestation_state":"computed","paper":{"title":"MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eleni Chatzi, Hao Dong, Olga Fink, Yue Zhao","submitted_at":"2024-05-27T17:59:02Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes an"},"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":"2405.17419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:59:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a20e71105b735911fd7cfb7cb99eb4be7dfeda5f7402e987a2b7a5e1fca3fe6e","abstract_canon_sha256":"2396491328db75caa67b92a694c0e3b099f3e65f661b692356ec7433502139c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:27.029091Z","signature_b64":"TQrFYnA9hyM6hws0ttCnGg6lWZvHFEaYfNmmGhYzmjh4Ji+KPQ4x1EW62xZu+zbP+FNg0EItiiedPuo5lqP/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df91c58f29e3467c32c2540666f8a1a16e3c96b37935a406e64066fc76886af","last_reissued_at":"2026-07-05T09:26:27.028592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:27.028592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eleni Chatzi, Hao Dong, Olga Fink, Yue Zhao","submitted_at":"2024-05-27T17:59:02Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17419","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/2405.17419/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":"2405.17419","created_at":"2026-07-05T09:26:27.028652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17419v2","created_at":"2026-07-05T09:26:27.028652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17419","created_at":"2026-07-05T09:26:27.028652+00:00"},{"alias_kind":"pith_short_12","alias_value":"TX4RYWHSTY2G","created_at":"2026-07-05T09:26:27.028652+00:00"},{"alias_kind":"pith_short_16","alias_value":"TX4RYWHSTY2GPQZM","created_at":"2026-07-05T09:26:27.028652+00:00"},{"alias_kind":"pith_short_8","alias_value":"TX4RYWHS","created_at":"2026-07-05T09:26:27.028652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11465","citing_title":"RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI","json":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI.json","graph_json":"https://pith.science/api/pith-number/TX4RYWHSTY2GPQZMEVAGM34KDI/graph.json","events_json":"https://pith.science/api/pith-number/TX4RYWHSTY2GPQZMEVAGM34KDI/events.json","paper":"https://pith.science/paper/TX4RYWHS"},"agent_actions":{"view_html":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI","download_json":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI.json","view_paper":"https://pith.science/paper/TX4RYWHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17419&json=true","fetch_graph":"https://pith.science/api/pith-number/TX4RYWHSTY2GPQZMEVAGM34KDI/graph.json","fetch_events":"https://pith.science/api/pith-number/TX4RYWHSTY2GPQZMEVAGM34KDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI/action/storage_attestation","attest_author":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI/action/author_attestation","sign_citation":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI/action/citation_signature","submit_replication":"https://pith.science/pith/TX4RYWHSTY2GPQZMEVAGM34KDI/action/replication_record"}},"created_at":"2026-07-05T09:26:27.028652+00:00","updated_at":"2026-07-05T09:26:27.028652+00:00"}