{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DA2HHSLEK75M4HBTT7WIPND2SH","short_pith_number":"pith:DA2HHSLE","schema_version":"1.0","canonical_sha256":"183473c96457face1c339fec87b47a91e6948dc33199732efdfcccebbeebb762","source":{"kind":"arxiv","id":"2411.13243","version":1},"attestation_state":"computed","paper":{"title":"XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Xumin Yu, Yanbo Wang, Ziyi Wang","submitted_at":"2024-11-20T12:02:12Z","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,"},"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":"2411.13243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T12:02:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c0e6dad37a25a13dcb828be566b54ef76ee831274a73afcd834fee550292b39","abstract_canon_sha256":"9a82d8574ac4a2f82ed654021d0880260c3a1ca801f7ed70de71dfef44d7ad0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:07.263191Z","signature_b64":"6RYN/OovHWh7qFSIkV8Xd7Drip0ce8GSuaTz3Pw3lndsfBcHwY7mT0B3s4RyBeOdTuhiVqNhVUs7G4Llo9CVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"183473c96457face1c339fec87b47a91e6948dc33199732efdfcccebbeebb762","last_reissued_at":"2026-07-05T09:38:07.262772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:07.262772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Xumin Yu, Yanbo Wang, Ziyi Wang","submitted_at":"2024-11-20T12:02:12Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13243","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/2411.13243/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":"2411.13243","created_at":"2026-07-05T09:38:07.262833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13243v1","created_at":"2026-07-05T09:38:07.262833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13243","created_at":"2026-07-05T09:38:07.262833+00:00"},{"alias_kind":"pith_short_12","alias_value":"DA2HHSLEK75M","created_at":"2026-07-05T09:38:07.262833+00:00"},{"alias_kind":"pith_short_16","alias_value":"DA2HHSLEK75M4HBT","created_at":"2026-07-05T09:38:07.262833+00:00"},{"alias_kind":"pith_short_8","alias_value":"DA2HHSLE","created_at":"2026-07-05T09:38:07.262833+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/DA2HHSLEK75M4HBTT7WIPND2SH","json":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH.json","graph_json":"https://pith.science/api/pith-number/DA2HHSLEK75M4HBTT7WIPND2SH/graph.json","events_json":"https://pith.science/api/pith-number/DA2HHSLEK75M4HBTT7WIPND2SH/events.json","paper":"https://pith.science/paper/DA2HHSLE"},"agent_actions":{"view_html":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH","download_json":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH.json","view_paper":"https://pith.science/paper/DA2HHSLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13243&json=true","fetch_graph":"https://pith.science/api/pith-number/DA2HHSLEK75M4HBTT7WIPND2SH/graph.json","fetch_events":"https://pith.science/api/pith-number/DA2HHSLEK75M4HBTT7WIPND2SH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH/action/storage_attestation","attest_author":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH/action/author_attestation","sign_citation":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH/action/citation_signature","submit_replication":"https://pith.science/pith/DA2HHSLEK75M4HBTT7WIPND2SH/action/replication_record"}},"created_at":"2026-07-05T09:38:07.262833+00:00","updated_at":"2026-07-05T09:38:07.262833+00:00"}