{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVN2ADESIC6X22MNIUN6BILOJF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3655c3831a69b69f98fce4ac7c0d63dd67f4a0e445bee881bd8e6d34e104b335","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:18:50Z","title_canon_sha256":"720d04f2bcb9e11cb926942d2265fe4db042b3a04e588c5b10eae1f22b4c47f7"},"schema_version":"1.0","source":{"id":"2502.02548","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02548","created_at":"2026-07-05T10:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02548v2","created_at":"2026-07-05T10:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02548","created_at":"2026-07-05T10:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"QVN2ADESIC6X","created_at":"2026-07-05T10:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"QVN2ADESIC6X22MN","created_at":"2026-07-05T10:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"QVN2ADES","created_at":"2026-07-05T10:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:98f70b0e14d9de58a6fc0adffb280f0ff07be9579315067d0dcd29ca2b5b970c","target":"graph","created_at":"2026-07-05T10:49:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.02548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chris Choy, Chunghyun Park, Jaesung Choe, Jan Kautz, Junha Lee, Minsu Cho, Yu-Chiang Frank Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:18:50Z","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02548","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f87d4c5718067f7ee79cc081fd29b183ce6ada8a6744e490af6b5eefe40df75b","target":"record","created_at":"2026-07-05T10:49:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3655c3831a69b69f98fce4ac7c0d63dd67f4a0e445bee881bd8e6d34e104b335","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:18:50Z","title_canon_sha256":"720d04f2bcb9e11cb926942d2265fe4db042b3a04e588c5b10eae1f22b4c47f7"},"schema_version":"1.0","source":{"id":"2502.02548","kind":"arxiv","version":2}},"canonical_sha256":"855ba00c9240bd7d698d451be0a16e495ff8bb8e97ff7747e230afc2d717035f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"855ba00c9240bd7d698d451be0a16e495ff8bb8e97ff7747e230afc2d717035f","first_computed_at":"2026-07-05T10:49:13.895797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:13.895797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W91+EKBRvrIGmQ5HJaOgSI6kZle7bYVlQKTvpeE1TiPUPQUyrq6LInhap2RzXiEEeY/WxMe5yZqDyAHjoFLMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:13.896299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02548","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87d4c5718067f7ee79cc081fd29b183ce6ada8a6744e490af6b5eefe40df75b","sha256:98f70b0e14d9de58a6fc0adffb280f0ff07be9579315067d0dcd29ca2b5b970c"],"state_sha256":"d61f367e0ffeb59cb9913037e349b5f0639ac00f4a007df7ed74fe1b83d0f869"}