{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:42JVJQLSXQAEK5UETCPQXJPNQ6","short_pith_number":"pith:42JVJQLS","schema_version":"1.0","canonical_sha256":"e69354c172bc00457684989f0ba5ed8790fb524beb5e122f5ae4919d5d34c009","source":{"kind":"arxiv","id":"2506.19331","version":1},"attestation_state":"computed","paper":{"title":"Segment Any 3D-Part in a Scene from a Sentence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Hongyu Wu, Pengwan Yang, Yuki M. Asano","submitted_at":"2025-06-24T05:51:22Z","abstract_excerpt":"This paper aims to achieve the segmentation of any 3D part in a scene based on natural language descriptions, extending beyond traditional object-level 3D scene understanding and addressing both data and methodological challenges. Due to the expensive acquisition and annotation burden, existing datasets and methods are predominantly limited to object-level comprehension. To overcome the limitations of data and annotation availability, we introduce the 3D-PU dataset, the first large-scale 3D dataset with dense part annotations, created through an innovative and cost-effective method for constru"},"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":"2506.19331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T05:51:22Z","cross_cats_sorted":[],"title_canon_sha256":"6427b7a3b2f1ab7d5e65c5ae5a7734d26cfe60ffb7fef314f98782094df40887","abstract_canon_sha256":"c781cb3802f02a9c451e2a57e97b46d654600b3986943f143c08a3cd525268bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:13.520951Z","signature_b64":"F/A5kNk2Pf4yyPPLZb1UbE4B5BzNB3phQtw+ndQu17TMBiFo0IDxTyE4MYf2w6z3dbVrhNlIE2Ed3IkL3cxQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e69354c172bc00457684989f0ba5ed8790fb524beb5e122f5ae4919d5d34c009","last_reissued_at":"2026-07-05T11:26:13.520426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:13.520426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Any 3D-Part in a Scene from a Sentence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Hongyu Wu, Pengwan Yang, Yuki M. Asano","submitted_at":"2025-06-24T05:51:22Z","abstract_excerpt":"This paper aims to achieve the segmentation of any 3D part in a scene based on natural language descriptions, extending beyond traditional object-level 3D scene understanding and addressing both data and methodological challenges. Due to the expensive acquisition and annotation burden, existing datasets and methods are predominantly limited to object-level comprehension. To overcome the limitations of data and annotation availability, we introduce the 3D-PU dataset, the first large-scale 3D dataset with dense part annotations, created through an innovative and cost-effective method for constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19331","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/2506.19331/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":"2506.19331","created_at":"2026-07-05T11:26:13.520490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19331v1","created_at":"2026-07-05T11:26:13.520490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19331","created_at":"2026-07-05T11:26:13.520490+00:00"},{"alias_kind":"pith_short_12","alias_value":"42JVJQLSXQAE","created_at":"2026-07-05T11:26:13.520490+00:00"},{"alias_kind":"pith_short_16","alias_value":"42JVJQLSXQAEK5UE","created_at":"2026-07-05T11:26:13.520490+00:00"},{"alias_kind":"pith_short_8","alias_value":"42JVJQLS","created_at":"2026-07-05T11:26:13.520490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10981","citing_title":"ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6","json":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6.json","graph_json":"https://pith.science/api/pith-number/42JVJQLSXQAEK5UETCPQXJPNQ6/graph.json","events_json":"https://pith.science/api/pith-number/42JVJQLSXQAEK5UETCPQXJPNQ6/events.json","paper":"https://pith.science/paper/42JVJQLS"},"agent_actions":{"view_html":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6","download_json":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6.json","view_paper":"https://pith.science/paper/42JVJQLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19331&json=true","fetch_graph":"https://pith.science/api/pith-number/42JVJQLSXQAEK5UETCPQXJPNQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/42JVJQLSXQAEK5UETCPQXJPNQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6/action/storage_attestation","attest_author":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6/action/author_attestation","sign_citation":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6/action/citation_signature","submit_replication":"https://pith.science/pith/42JVJQLSXQAEK5UETCPQXJPNQ6/action/replication_record"}},"created_at":"2026-07-05T11:26:13.520490+00:00","updated_at":"2026-07-05T11:26:13.520490+00:00"}