{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DA2HHSLEK75M4HBTT7WIPND2SH","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":"9a82d8574ac4a2f82ed654021d0880260c3a1ca801f7ed70de71dfef44d7ad0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T12:02:12Z","title_canon_sha256":"5c0e6dad37a25a13dcb828be566b54ef76ee831274a73afcd834fee550292b39"},"schema_version":"1.0","source":{"id":"2411.13243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13243","created_at":"2026-07-05T09:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13243v1","created_at":"2026-07-05T09:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13243","created_at":"2026-07-05T09:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"DA2HHSLEK75M","created_at":"2026-07-05T09:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"DA2HHSLEK75M4HBT","created_at":"2026-07-05T09:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"DA2HHSLE","created_at":"2026-07-05T09:38:07Z"}],"graph_snapshots":[{"event_id":"sha256:16267679a2cf1c58074e95db1147c609c83dbfcceecd73c883454f8f36057e48","target":"graph","created_at":"2026-07-05T09:38:07Z","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/2411.13243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevertheless, traditional techniques such as global feature alignment or vision-language model distillation tend to impose only approximate correspondence, struggling notably with delineating fine-grained segmentation boundaries. To address this gap, we propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. In our approach,","authors_text":"Jie Zhou, Jiwen Lu, Xumin Yu, Yanbo Wang, Ziyi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T12:02:12Z","title":"XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13243","kind":"arxiv","version":1},"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:b22d72e4a5cbfbc8e0db12e24e934508b053e064cea90578d2159198d2a9a759","target":"record","created_at":"2026-07-05T09:38:07Z","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":"9a82d8574ac4a2f82ed654021d0880260c3a1ca801f7ed70de71dfef44d7ad0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T12:02:12Z","title_canon_sha256":"5c0e6dad37a25a13dcb828be566b54ef76ee831274a73afcd834fee550292b39"},"schema_version":"1.0","source":{"id":"2411.13243","kind":"arxiv","version":1}},"canonical_sha256":"183473c96457face1c339fec87b47a91e6948dc33199732efdfcccebbeebb762","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"183473c96457face1c339fec87b47a91e6948dc33199732efdfcccebbeebb762","first_computed_at":"2026-07-05T09:38:07.262772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:07.262772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RYN/OovHWh7qFSIkV8Xd7Drip0ce8GSuaTz3Pw3lndsfBcHwY7mT0B3s4RyBeOdTuhiVqNhVUs7G4Llo9CVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:07.263191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b22d72e4a5cbfbc8e0db12e24e934508b053e064cea90578d2159198d2a9a759","sha256:16267679a2cf1c58074e95db1147c609c83dbfcceecd73c883454f8f36057e48"],"state_sha256":"8c5dd647c62c1ecf947d9b21cd57ae0a24052f5dc3782386769175529ccc7ed6"}