{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RHYZR5JDGW7WGQX4AFDXP3EKFK","short_pith_number":"pith:RHYZR5JD","schema_version":"1.0","canonical_sha256":"89f198f52335bf6342fc014777ec8a2aa187fd384ff409d3be50d6d5eec49468","source":{"kind":"arxiv","id":"2409.05162","version":1},"attestation_state":"computed","paper":{"title":"Can OOD Object Detectors Learn from Foundation Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Liu, Shizhen Zhao, Xiaojuan Qi, Xin Wen, Yingxian Chen","submitted_at":"2024-09-08T17:28:22Z","abstract_excerpt":"Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, such as Stable Diffusion, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples, thereby enhancing OOD object detection. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models to automatically extract meaningful OOD data from text-to-image generative models. This offers the model access to open-world knowledge "},"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":"2409.05162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-08T17:28:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9cb6cc743e39d664d2d5572d3554b991748b2c6fac0509c4675eafd4c6fcf43","abstract_canon_sha256":"2e4661099f5ab2759b2c07e0d3c0ae6d248944ba8e29bcbe572701797dfb7d01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:44.839109Z","signature_b64":"/AOiHQdPoO/ruamuxyWjyFDe/HKjQTdIy8qV+chfJKpQVNt5WJysPoLaucrRK70HsM1ChhKQNR1EJywUMhkcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f198f52335bf6342fc014777ec8a2aa187fd384ff409d3be50d6d5eec49468","last_reissued_at":"2026-07-05T09:04:44.838754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:44.838754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can OOD Object Detectors Learn from Foundation Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Liu, Shizhen Zhao, Xiaojuan Qi, Xin Wen, Yingxian Chen","submitted_at":"2024-09-08T17:28:22Z","abstract_excerpt":"Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, such as Stable Diffusion, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples, thereby enhancing OOD object detection. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models to automatically extract meaningful OOD data from text-to-image generative models. This offers the model access to open-world knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05162","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/2409.05162/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":"2409.05162","created_at":"2026-07-05T09:04:44.838808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05162v1","created_at":"2026-07-05T09:04:44.838808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05162","created_at":"2026-07-05T09:04:44.838808+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHYZR5JDGW7W","created_at":"2026-07-05T09:04:44.838808+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHYZR5JDGW7WGQX4","created_at":"2026-07-05T09:04:44.838808+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHYZR5JD","created_at":"2026-07-05T09:04:44.838808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23751","citing_title":"Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK","json":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK.json","graph_json":"https://pith.science/api/pith-number/RHYZR5JDGW7WGQX4AFDXP3EKFK/graph.json","events_json":"https://pith.science/api/pith-number/RHYZR5JDGW7WGQX4AFDXP3EKFK/events.json","paper":"https://pith.science/paper/RHYZR5JD"},"agent_actions":{"view_html":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK","download_json":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK.json","view_paper":"https://pith.science/paper/RHYZR5JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05162&json=true","fetch_graph":"https://pith.science/api/pith-number/RHYZR5JDGW7WGQX4AFDXP3EKFK/graph.json","fetch_events":"https://pith.science/api/pith-number/RHYZR5JDGW7WGQX4AFDXP3EKFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK/action/storage_attestation","attest_author":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK/action/author_attestation","sign_citation":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK/action/citation_signature","submit_replication":"https://pith.science/pith/RHYZR5JDGW7WGQX4AFDXP3EKFK/action/replication_record"}},"created_at":"2026-07-05T09:04:44.838808+00:00","updated_at":"2026-07-05T09:04:44.838808+00:00"}