{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SLYTJ3D4YDIYLIBT66HYIR3AXR","short_pith_number":"pith:SLYTJ3D4","schema_version":"1.0","canonical_sha256":"92f134ec7cc0d185a033f78f844760bc6b7269ad136f676d431b9ff0f9faf038","source":{"kind":"arxiv","id":"2407.16696","version":1},"attestation_state":"computed","paper":{"title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junfeng Wu, Junyi Li, Song Bai, Weizhi Zhao, Xiang Bai","submitted_at":"2024-07-23T17:58:26Z","abstract_excerpt":"We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling PartGLEE to recognize a rich variety of parts. We conduct compr"},"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":"2407.16696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T17:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"ee84ce06127aa0dc97259e3c755db3603cbdfe083f1defd833c20faa924027d8","abstract_canon_sha256":"0a7a70a83c2c0e4065917e54df86e84edb6561ade71de85ba991144d766e5145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:37.023039Z","signature_b64":"qS6L4b7FwosVjHmQC+NKiDOqGvloUCwaNLQqa4TNDIyPmZ5M4VLIYm0IDqj4IHZMmH1eSr4Oc2pP3h3NFlL8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92f134ec7cc0d185a033f78f844760bc6b7269ad136f676d431b9ff0f9faf038","last_reissued_at":"2026-07-05T08:47:37.022563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:37.022563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junfeng Wu, Junyi Li, Song Bai, Weizhi Zhao, Xiang Bai","submitted_at":"2024-07-23T17:58:26Z","abstract_excerpt":"We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling PartGLEE to recognize a rich variety of parts. We conduct compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16696","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/2407.16696/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":"2407.16696","created_at":"2026-07-05T08:47:37.022621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16696v1","created_at":"2026-07-05T08:47:37.022621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16696","created_at":"2026-07-05T08:47:37.022621+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLYTJ3D4YDIY","created_at":"2026-07-05T08:47:37.022621+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLYTJ3D4YDIYLIBT","created_at":"2026-07-05T08:47:37.022621+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLYTJ3D4","created_at":"2026-07-05T08:47:37.022621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09688","citing_title":"Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR","json":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR.json","graph_json":"https://pith.science/api/pith-number/SLYTJ3D4YDIYLIBT66HYIR3AXR/graph.json","events_json":"https://pith.science/api/pith-number/SLYTJ3D4YDIYLIBT66HYIR3AXR/events.json","paper":"https://pith.science/paper/SLYTJ3D4"},"agent_actions":{"view_html":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR","download_json":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR.json","view_paper":"https://pith.science/paper/SLYTJ3D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16696&json=true","fetch_graph":"https://pith.science/api/pith-number/SLYTJ3D4YDIYLIBT66HYIR3AXR/graph.json","fetch_events":"https://pith.science/api/pith-number/SLYTJ3D4YDIYLIBT66HYIR3AXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR/action/storage_attestation","attest_author":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR/action/author_attestation","sign_citation":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR/action/citation_signature","submit_replication":"https://pith.science/pith/SLYTJ3D4YDIYLIBT66HYIR3AXR/action/replication_record"}},"created_at":"2026-07-05T08:47:37.022621+00:00","updated_at":"2026-07-05T08:47:37.022621+00:00"}