{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HP2RI6YEKLBSCPZM2Z2APHLSYY","short_pith_number":"pith:HP2RI6YE","schema_version":"1.0","canonical_sha256":"3bf5147b0452c3213f2cd674079d72c62e3ea9a4b0773d67613ce950064f5407","source":{"kind":"arxiv","id":"2304.04521","version":4},"attestation_state":"computed","paper":{"title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atsuyuki Miyai, Go Irie, Kiyoharu Aizawa, Qing Yu","submitted_at":"2023-04-10T11:35:42Z","abstract_excerpt":"Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global 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":"2304.04521","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"00661f2e51d2d77a2792d152889d4d9aed8e84ecfe68264a8ba164893454ee8b","abstract_canon_sha256":"e248e4d6ca276ffa725d5cb250ec8d85f123e3bc08f7d5194bd3c11c4634c181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:22.654416Z","signature_b64":"8Pvf2dZeiplxl8hNf+dagMb6TdrXmdOuKOBM49oxyplmVLpceFDIBBZkVZ5BTrf/cAC237X8pF9GXgnAWYyjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf5147b0452c3213f2cd674079d72c62e3ea9a4b0773d67613ce950064f5407","last_reissued_at":"2026-07-05T10:03:22.653883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:22.653883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atsuyuki Miyai, Go Irie, Kiyoharu Aizawa, Qing Yu","submitted_at":"2023-04-10T11:35:42Z","abstract_excerpt":"Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04521","kind":"arxiv","version":4},"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/2304.04521/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":"2304.04521","created_at":"2026-07-05T10:03:22.653945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04521v4","created_at":"2026-07-05T10:03:22.653945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04521","created_at":"2026-07-05T10:03:22.653945+00:00"},{"alias_kind":"pith_short_12","alias_value":"HP2RI6YEKLBS","created_at":"2026-07-05T10:03:22.653945+00:00"},{"alias_kind":"pith_short_16","alias_value":"HP2RI6YEKLBSCPZM","created_at":"2026-07-05T10:03:22.653945+00:00"},{"alias_kind":"pith_short_8","alias_value":"HP2RI6YE","created_at":"2026-07-05T10:03:22.653945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22537","citing_title":"NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21546","citing_title":"Component-Based Out-of-Distribution Detection","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY","json":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY.json","graph_json":"https://pith.science/api/pith-number/HP2RI6YEKLBSCPZM2Z2APHLSYY/graph.json","events_json":"https://pith.science/api/pith-number/HP2RI6YEKLBSCPZM2Z2APHLSYY/events.json","paper":"https://pith.science/paper/HP2RI6YE"},"agent_actions":{"view_html":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY","download_json":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY.json","view_paper":"https://pith.science/paper/HP2RI6YE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04521&json=true","fetch_graph":"https://pith.science/api/pith-number/HP2RI6YEKLBSCPZM2Z2APHLSYY/graph.json","fetch_events":"https://pith.science/api/pith-number/HP2RI6YEKLBSCPZM2Z2APHLSYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY/action/storage_attestation","attest_author":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY/action/author_attestation","sign_citation":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY/action/citation_signature","submit_replication":"https://pith.science/pith/HP2RI6YEKLBSCPZM2Z2APHLSYY/action/replication_record"}},"created_at":"2026-07-05T10:03:22.653945+00:00","updated_at":"2026-07-05T10:03:22.653945+00:00"}