{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSTBXQM2PS4KNBEJEN3TEFXKZH","short_pith_number":"pith:VSTBXQM2","schema_version":"1.0","canonical_sha256":"aca61bc19a7cb8a6848923773216eac9edb357e023e1387d22405178fbf2d61b","source":{"kind":"arxiv","id":"2408.10652","version":2},"attestation_state":"computed","paper":{"title":"Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabio Poiesi, Guofeng Mei, Luigi Riz, Yiming Wang","submitted_at":"2024-08-20T08:46:54Z","abstract_excerpt":"Most recent 3D instance segmentation methods are open vocabulary, offering a greater flexibility than closed-vocabulary methods. Yet, they are limited to reasoning within a specific set of concepts, \\ie the vocabulary, prompted by the user at test time. In essence, these models cannot reason in an open-ended fashion, i.e., answering \"List the objects in the scene.''. We introduce the first method to address 3D instance segmentation in a setting that is void of any vocabulary prior, namely a vocabulary-free setting. We leverage a large vision-language assistant and an open-vocabulary 2D instanc"},"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":"2408.10652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T08:46:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82a841d362ebedf658fe019e8e9187b62d44034b29bb6aa1e903b724ea6bbc0f","abstract_canon_sha256":"7989d39a6a1981d994908d7cc24820abf95c9a22d038ce36deffba50e933ac42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:35.130643Z","signature_b64":"7PaRxuSdteUt7IkjBBRt/ud2xZ6guVf7XOLZEA64Zm6ss71IrFubsCQEXhkBEY5T0L22YgDCEwim9uqWl21+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aca61bc19a7cb8a6848923773216eac9edb357e023e1387d22405178fbf2d61b","last_reissued_at":"2026-07-05T10:40:35.130158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:35.130158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabio Poiesi, Guofeng Mei, Luigi Riz, Yiming Wang","submitted_at":"2024-08-20T08:46:54Z","abstract_excerpt":"Most recent 3D instance segmentation methods are open vocabulary, offering a greater flexibility than closed-vocabulary methods. Yet, they are limited to reasoning within a specific set of concepts, \\ie the vocabulary, prompted by the user at test time. In essence, these models cannot reason in an open-ended fashion, i.e., answering \"List the objects in the scene.''. We introduce the first method to address 3D instance segmentation in a setting that is void of any vocabulary prior, namely a vocabulary-free setting. We leverage a large vision-language assistant and an open-vocabulary 2D instanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10652","kind":"arxiv","version":2},"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/2408.10652/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":"2408.10652","created_at":"2026-07-05T10:40:35.130216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10652v2","created_at":"2026-07-05T10:40:35.130216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10652","created_at":"2026-07-05T10:40:35.130216+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSTBXQM2PS4K","created_at":"2026-07-05T10:40:35.130216+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSTBXQM2PS4KNBEJ","created_at":"2026-07-05T10:40:35.130216+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSTBXQM2","created_at":"2026-07-05T10:40:35.130216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13629","citing_title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH","json":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH.json","graph_json":"https://pith.science/api/pith-number/VSTBXQM2PS4KNBEJEN3TEFXKZH/graph.json","events_json":"https://pith.science/api/pith-number/VSTBXQM2PS4KNBEJEN3TEFXKZH/events.json","paper":"https://pith.science/paper/VSTBXQM2"},"agent_actions":{"view_html":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH","download_json":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH.json","view_paper":"https://pith.science/paper/VSTBXQM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10652&json=true","fetch_graph":"https://pith.science/api/pith-number/VSTBXQM2PS4KNBEJEN3TEFXKZH/graph.json","fetch_events":"https://pith.science/api/pith-number/VSTBXQM2PS4KNBEJEN3TEFXKZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH/action/storage_attestation","attest_author":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH/action/author_attestation","sign_citation":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH/action/citation_signature","submit_replication":"https://pith.science/pith/VSTBXQM2PS4KNBEJEN3TEFXKZH/action/replication_record"}},"created_at":"2026-07-05T10:40:35.130216+00:00","updated_at":"2026-07-05T10:40:35.130216+00:00"}