{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5HAB4FDGJ4IFQERUVFM35OZ5M","short_pith_number":"pith:Q5HAB4FD","schema_version":"1.0","canonical_sha256":"874e00f0a3327882c091a54acdf5d9eb2cf3bb8035029de568754c9fa8111d0f","source":{"kind":"arxiv","id":"2604.02546","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Ranran Huang, Weixun Luo, Ye Mao","submitted_at":"2026-04-02T21:54:43Z","abstract_excerpt":"Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a transformer-based encoder that learns unified scene representations from multi-view colored pointmaps, jointly modeling image appearance and geometry. For robust colored pointmap representation learning, we introduce novel cross-view geometric alignment and grounded view alignment to enforce cross-view geometry and semantic consistency. Extensive low-shot and task-sp"},"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":"2604.02546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T21:54:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e7b2725b085313e67ad467cb130d2440faf6fcff80a62f4295266aa13da9394","abstract_canon_sha256":"76c7a7276223ba593521b60036e845a975353789c9578533a095d71092ccc5af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:30.833253Z","signature_b64":"4HFUKZ9XZWejXikFkxaZGUa/Nv+1UYqxI7Ys5Ihzp+7osxPsGVfHy5jdUPY8F/oAxpLvg9l4exBuT7YFWir/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874e00f0a3327882c091a54acdf5d9eb2cf3bb8035029de568754c9fa8111d0f","last_reissued_at":"2026-06-29T01:14:30.832790Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:30.832790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Ranran Huang, Weixun Luo, Ye Mao","submitted_at":"2026-04-02T21:54:43Z","abstract_excerpt":"Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a transformer-based encoder that learns unified scene representations from multi-view colored pointmaps, jointly modeling image appearance and geometry. For robust colored pointmap representation learning, we introduce novel cross-view geometric alignment and grounded view alignment to enforce cross-view geometry and semantic consistency. Extensive low-shot and task-sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose UniScene3D, a transformer-based encoder that learns unified scene representations from multi-view colored pointmaps, jointly modeling image appearance and geometry. ... Extensive low-shot and task-specific fine-tuning evaluations on viewpoint grounding, scene retrieval, scene type classification, and 3D VQA demonstrate our state-of-the-art performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the introduced cross-view geometric alignment and grounded view alignment will successfully enforce cross-view geometry and semantic consistency, leading to more generalizable unified representations (assumed without detailed verification of failure modes or data requirements in the abstract).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UniScene3D learns unified 3D scene representations from colored pointmaps using contrastive CLIP pretraining plus cross-view geometric and grounded view alignments, achieving state-of-the-art results on viewpoint grounding, scene retrieval, classification, and 3D VQA.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b2c4a294ea30600cb92f0dee864ea52351c17d05a97586ced93c33ae320beede"},"source":{"id":"2604.02546","kind":"arxiv","version":2},"verdict":{"id":"7d850af7-33cf-4ef6-9e07-e700269ffec5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T21:16:08.511554Z","strongest_claim":"We propose UniScene3D, a transformer-based encoder that learns unified scene representations from multi-view colored pointmaps, jointly modeling image appearance and geometry. ... Extensive low-shot and task-specific fine-tuning evaluations on viewpoint grounding, scene retrieval, scene type classification, and 3D VQA demonstrate our state-of-the-art performance.","one_line_summary":"UniScene3D learns unified 3D scene representations from colored pointmaps using contrastive CLIP pretraining plus cross-view geometric and grounded view alignments, achieving state-of-the-art results on viewpoint grounding, scene retrieval, classification, and 3D VQA.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the introduced cross-view geometric alignment and grounded view alignment will successfully enforce cross-view geometry and semantic consistency, leading to more generalizable unified representations (assumed without detailed verification of failure modes or data requirements in the abstract).","pith_extraction_headline":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.02546/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":"2604.02546","created_at":"2026-06-29T01:14:30.832848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.02546v2","created_at":"2026-06-29T01:14:30.832848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02546","created_at":"2026-06-29T01:14:30.832848+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5HAB4FDGJ4I","created_at":"2026-06-29T01:14:30.832848+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5HAB4FDGJ4IFQER","created_at":"2026-06-29T01:14:30.832848+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5HAB4FD","created_at":"2026-06-29T01:14:30.832848+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/Q5HAB4FDGJ4IFQERUVFM35OZ5M","json":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M.json","graph_json":"https://pith.science/api/pith-number/Q5HAB4FDGJ4IFQERUVFM35OZ5M/graph.json","events_json":"https://pith.science/api/pith-number/Q5HAB4FDGJ4IFQERUVFM35OZ5M/events.json","paper":"https://pith.science/paper/Q5HAB4FD"},"agent_actions":{"view_html":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M","download_json":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M.json","view_paper":"https://pith.science/paper/Q5HAB4FD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.02546&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5HAB4FDGJ4IFQERUVFM35OZ5M/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5HAB4FDGJ4IFQERUVFM35OZ5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M/action/storage_attestation","attest_author":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M/action/author_attestation","sign_citation":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M/action/citation_signature","submit_replication":"https://pith.science/pith/Q5HAB4FDGJ4IFQERUVFM35OZ5M/action/replication_record"}},"created_at":"2026-06-29T01:14:30.832848+00:00","updated_at":"2026-06-29T01:14:30.832848+00:00"}