{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QVN2ADESIC6X22MNIUN6BILOJF","short_pith_number":"pith:QVN2ADES","schema_version":"1.0","canonical_sha256":"855ba00c9240bd7d698d451be0a16e495ff8bb8e97ff7747e230afc2d717035f","source":{"kind":"arxiv","id":"2502.02548","version":2},"attestation_state":"computed","paper":{"title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Choy, Chunghyun Park, Jaesung Choe, Jan Kautz, Junha Lee, Minsu Cho, Yu-Chiang Frank Wang","submitted_at":"2025-02-04T18:18:50Z","abstract_excerpt":"We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated sc"},"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":"2502.02548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"720d04f2bcb9e11cb926942d2265fe4db042b3a04e588c5b10eae1f22b4c47f7","abstract_canon_sha256":"3655c3831a69b69f98fce4ac7c0d63dd67f4a0e445bee881bd8e6d34e104b335"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:13.896299Z","signature_b64":"W91+EKBRvrIGmQ5HJaOgSI6kZle7bYVlQKTvpeE1TiPUPQUyrq6LInhap2RzXiEEeY/WxMe5yZqDyAHjoFLMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"855ba00c9240bd7d698d451be0a16e495ff8bb8e97ff7747e230afc2d717035f","last_reissued_at":"2026-07-05T10:49:13.895797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:13.895797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Choy, Chunghyun Park, Jaesung Choe, Jan Kautz, Junha Lee, Minsu Cho, Yu-Chiang Frank Wang","submitted_at":"2025-02-04T18:18:50Z","abstract_excerpt":"We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02548","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/2502.02548/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":"2502.02548","created_at":"2026-07-05T10:49:13.895857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02548v2","created_at":"2026-07-05T10:49:13.895857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02548","created_at":"2026-07-05T10:49:13.895857+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVN2ADESIC6X","created_at":"2026-07-05T10:49:13.895857+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVN2ADESIC6X22MN","created_at":"2026-07-05T10:49:13.895857+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVN2ADES","created_at":"2026-07-05T10:49:13.895857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF","json":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF.json","graph_json":"https://pith.science/api/pith-number/QVN2ADESIC6X22MNIUN6BILOJF/graph.json","events_json":"https://pith.science/api/pith-number/QVN2ADESIC6X22MNIUN6BILOJF/events.json","paper":"https://pith.science/paper/QVN2ADES"},"agent_actions":{"view_html":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF","download_json":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF.json","view_paper":"https://pith.science/paper/QVN2ADES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02548&json=true","fetch_graph":"https://pith.science/api/pith-number/QVN2ADESIC6X22MNIUN6BILOJF/graph.json","fetch_events":"https://pith.science/api/pith-number/QVN2ADESIC6X22MNIUN6BILOJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF/action/storage_attestation","attest_author":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF/action/author_attestation","sign_citation":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF/action/citation_signature","submit_replication":"https://pith.science/pith/QVN2ADESIC6X22MNIUN6BILOJF/action/replication_record"}},"created_at":"2026-07-05T10:49:13.895857+00:00","updated_at":"2026-07-05T10:49:13.895857+00:00"}