{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q5HAB4FDGJ4IFQERUVFM35OZ5M","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":"76c7a7276223ba593521b60036e845a975353789c9578533a095d71092ccc5af","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T21:54:43Z","title_canon_sha256":"3e7b2725b085313e67ad467cb130d2440faf6fcff80a62f4295266aa13da9394"},"schema_version":"1.0","source":{"id":"2604.02546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.02546","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.02546v2","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02546","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"Q5HAB4FDGJ4I","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"Q5HAB4FDGJ4IFQER","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"Q5HAB4FD","created_at":"2026-06-29T01:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:bf64f0a1930760a11677b24f7fa292546f01390fcda6982a93848265e393d90f","target":"graph","created_at":"2026-06-29T01:14:30Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations."}],"snapshot_sha256":"b2c4a294ea30600cb92f0dee864ea52351c17d05a97586ced93c33ae320beede"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.02546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Ranran Huang, Weixun Luo, Ye Mao","cross_cats":["cs.LG"],"headline":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T21:54:43Z","title":"Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.02546","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T21:16:08.511554Z","id":"7d850af7-33cf-4ef6-9e07-e700269ffec5","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Pretraining a transformer on multi-view colored pointmaps with language contrast produces unified 3D scene representations.","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.","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)."}},"verdict_id":"7d850af7-33cf-4ef6-9e07-e700269ffec5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f04570f0403b99cd39582de36ef3f70c4cfe6f7de2ddada6dcc777e37a93548","target":"record","created_at":"2026-06-29T01:14:30Z","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":"76c7a7276223ba593521b60036e845a975353789c9578533a095d71092ccc5af","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T21:54:43Z","title_canon_sha256":"3e7b2725b085313e67ad467cb130d2440faf6fcff80a62f4295266aa13da9394"},"schema_version":"1.0","source":{"id":"2604.02546","kind":"arxiv","version":2}},"canonical_sha256":"874e00f0a3327882c091a54acdf5d9eb2cf3bb8035029de568754c9fa8111d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874e00f0a3327882c091a54acdf5d9eb2cf3bb8035029de568754c9fa8111d0f","first_computed_at":"2026-06-29T01:14:30.832790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:30.832790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4HFUKZ9XZWejXikFkxaZGUa/Nv+1UYqxI7Ys5Ihzp+7osxPsGVfHy5jdUPY8F/oAxpLvg9l4exBuT7YFWir/Dg==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:30.833253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.02546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f04570f0403b99cd39582de36ef3f70c4cfe6f7de2ddada6dcc777e37a93548","sha256:bf64f0a1930760a11677b24f7fa292546f01390fcda6982a93848265e393d90f"],"state_sha256":"d5928fb42506a1d67c3c1d15898b987f6b3f3344b7caad28899e20ef0747eb68"}