{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RNVICPCDJR5CF7TG2IEETIQ7MC","short_pith_number":"pith:RNVICPCD","schema_version":"1.0","canonical_sha256":"8b6a813c434c7a22fe66d20849a21f608c2ab2d454a8bf0d31225c7d2559036d","source":{"kind":"arxiv","id":"2507.02813","version":1},"attestation_state":"computed","paper":{"title":"LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangfu Liu, Fudong Wang, Hanyang Wang, Hao Li, Jiawei Chi, Minghui Yang, Yueqi Duan","submitted_at":"2025-07-03T17:21:23Z","abstract_excerpt":"Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangScene-X, to unify and generate 3D consistent multi-modality information for reconstruction and underst"},"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":"2507.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T17:21:23Z","cross_cats_sorted":[],"title_canon_sha256":"fc9a6fde7fe2116c0a2fdecafaad2fecddc6206b66ccafe7041739e200c3ce50","abstract_canon_sha256":"ce1ae6c4a3f7f0a4ecfe6caf65c9b84cc90f2378bd17e3e54383259f1085c368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:34.947768Z","signature_b64":"2O7DucsTTuw8ayxpzzhHdmohHcCgdWSTlBkWz6jyR9+fTZ3pBL0/wnZkJusDktmtA1hcI6bLdV6lwewLDth4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6a813c434c7a22fe66d20849a21f608c2ab2d454a8bf0d31225c7d2559036d","last_reissued_at":"2026-07-05T11:31:34.947267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:34.947267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangfu Liu, Fudong Wang, Hanyang Wang, Hao Li, Jiawei Chi, Minghui Yang, Yueqi Duan","submitted_at":"2025-07-03T17:21:23Z","abstract_excerpt":"Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangScene-X, to unify and generate 3D consistent multi-modality information for reconstruction and underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02813","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/2507.02813/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":"2507.02813","created_at":"2026-07-05T11:31:34.947342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02813v1","created_at":"2026-07-05T11:31:34.947342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02813","created_at":"2026-07-05T11:31:34.947342+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNVICPCDJR5C","created_at":"2026-07-05T11:31:34.947342+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNVICPCDJR5CF7TG","created_at":"2026-07-05T11:31:34.947342+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNVICPCD","created_at":"2026-07-05T11:31:34.947342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.17541","citing_title":"FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14706","citing_title":"NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC","json":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC.json","graph_json":"https://pith.science/api/pith-number/RNVICPCDJR5CF7TG2IEETIQ7MC/graph.json","events_json":"https://pith.science/api/pith-number/RNVICPCDJR5CF7TG2IEETIQ7MC/events.json","paper":"https://pith.science/paper/RNVICPCD"},"agent_actions":{"view_html":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC","download_json":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC.json","view_paper":"https://pith.science/paper/RNVICPCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02813&json=true","fetch_graph":"https://pith.science/api/pith-number/RNVICPCDJR5CF7TG2IEETIQ7MC/graph.json","fetch_events":"https://pith.science/api/pith-number/RNVICPCDJR5CF7TG2IEETIQ7MC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC/action/storage_attestation","attest_author":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC/action/author_attestation","sign_citation":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC/action/citation_signature","submit_replication":"https://pith.science/pith/RNVICPCDJR5CF7TG2IEETIQ7MC/action/replication_record"}},"created_at":"2026-07-05T11:31:34.947342+00:00","updated_at":"2026-07-05T11:31:34.947342+00:00"}