{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HEZ54SIAMBY2R7WBAC736473FS","short_pith_number":"pith:HEZ54SIA","schema_version":"1.0","canonical_sha256":"3933de49006071a8fec100bfbf73fb2ca1aa181f9bf4b7d1a9b06a8ce38062f7","source":{"kind":"arxiv","id":"2311.01373","version":3},"attestation_state":"computed","paper":{"title":"Recognize Any Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wen, Chuofan Ma, Haosen Yang, Xiatian Zhu, Yi Jiang, Zehuan Yuan","submitted_at":"2023-11-02T16:31:49Z","abstract_excerpt":"Understanding the semantics of individual regions or patches of unconstrained images, such as open-world object detection, remains a critical yet challenging task in computer vision. Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an extensive collection of region-label pairs or aligning the outputs of a detection model with image-level representations of region proposals. Despite notable progress, these approaches are plagued by c"},"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":"2311.01373","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T16:31:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bf1a9bf0a5ed822a43c569bb5e779a703a7569dba52e2d8c86294566fa2bfa9","abstract_canon_sha256":"d31fb6f19a41c6a878d4bb60d8a61201a272e04d0e35e29c81c7500d6d398c5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:19.116900Z","signature_b64":"MX3Q9uNVDyG2vmdIpDqGbhLgsJA0QnLhdetuGjrCg6sEDnkp6szv9CBkFGl05L4vpPV/EYAQ24bS0U2ygMYpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3933de49006071a8fec100bfbf73fb2ca1aa181f9bf4b7d1a9b06a8ce38062f7","last_reissued_at":"2026-07-05T10:51:19.116396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:19.116396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recognize Any Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wen, Chuofan Ma, Haosen Yang, Xiatian Zhu, Yi Jiang, Zehuan Yuan","submitted_at":"2023-11-02T16:31:49Z","abstract_excerpt":"Understanding the semantics of individual regions or patches of unconstrained images, such as open-world object detection, remains a critical yet challenging task in computer vision. Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an extensive collection of region-label pairs or aligning the outputs of a detection model with image-level representations of region proposals. Despite notable progress, these approaches are plagued by c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01373","kind":"arxiv","version":3},"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/2311.01373/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":"2311.01373","created_at":"2026-07-05T10:51:19.116457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01373v3","created_at":"2026-07-05T10:51:19.116457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01373","created_at":"2026-07-05T10:51:19.116457+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEZ54SIAMBY2","created_at":"2026-07-05T10:51:19.116457+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEZ54SIAMBY2R7WB","created_at":"2026-07-05T10:51:19.116457+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEZ54SIA","created_at":"2026-07-05T10:51:19.116457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.13805","citing_title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS","json":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS.json","graph_json":"https://pith.science/api/pith-number/HEZ54SIAMBY2R7WBAC736473FS/graph.json","events_json":"https://pith.science/api/pith-number/HEZ54SIAMBY2R7WBAC736473FS/events.json","paper":"https://pith.science/paper/HEZ54SIA"},"agent_actions":{"view_html":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS","download_json":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS.json","view_paper":"https://pith.science/paper/HEZ54SIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01373&json=true","fetch_graph":"https://pith.science/api/pith-number/HEZ54SIAMBY2R7WBAC736473FS/graph.json","fetch_events":"https://pith.science/api/pith-number/HEZ54SIAMBY2R7WBAC736473FS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS/action/storage_attestation","attest_author":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS/action/author_attestation","sign_citation":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS/action/citation_signature","submit_replication":"https://pith.science/pith/HEZ54SIAMBY2R7WBAC736473FS/action/replication_record"}},"created_at":"2026-07-05T10:51:19.116457+00:00","updated_at":"2026-07-05T10:51:19.116457+00:00"}