{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UC3WDQVAJQQGRH5MLRJNFNZCED","short_pith_number":"pith:UC3WDQVA","schema_version":"1.0","canonical_sha256":"a0b761c2a04c20689fac5c52d2b72220d2c05aa529b8db50f4b6a7f2ddf23bea","source":{"kind":"arxiv","id":"2504.01901","version":1},"attestation_state":"computed","paper":{"title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Haoqiang Fan, Tiancai Wang, Xiangyu Zhang, Yucheng Zhao, Zhaoxiang Zhang","submitted_at":"2025-04-02T16:59:55Z","abstract_excerpt":"The rapid development of Large Multimodal Models (LMMs) for 2D images and videos has spurred efforts to adapt these models for interpreting 3D scenes. However, the absence of large-scale 3D vision-language datasets has posed a significant obstacle. To address this issue, typical approaches focus on injecting 3D awareness into 2D LMMs by designing 3D input-level scene representations. This work provides a new perspective. We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure. Specifically, it in"},"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":"2504.01901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T16:59:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"ab9cad00918d1590ea1d491615819c95f10e4e8c14477c6078bd50f5428cb104","abstract_canon_sha256":"4c9eeb31600d8bae882d8a79b62cef742fb7d7f7097796310cfcc45d28dfd3d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:31.527510Z","signature_b64":"LhkOOuBayRro6N294LWhuS7hiA452ZKdKImRSsHtE7tgaOWpExkysjw5+CqJ1BHkk3y74YSXpWTcfFwxmayaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0b761c2a04c20689fac5c52d2b72220d2c05aa529b8db50f4b6a7f2ddf23bea","last_reissued_at":"2026-07-05T10:43:31.527042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:31.527042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Haoqiang Fan, Tiancai Wang, Xiangyu Zhang, Yucheng Zhao, Zhaoxiang Zhang","submitted_at":"2025-04-02T16:59:55Z","abstract_excerpt":"The rapid development of Large Multimodal Models (LMMs) for 2D images and videos has spurred efforts to adapt these models for interpreting 3D scenes. However, the absence of large-scale 3D vision-language datasets has posed a significant obstacle. To address this issue, typical approaches focus on injecting 3D awareness into 2D LMMs by designing 3D input-level scene representations. This work provides a new perspective. We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure. Specifically, it in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01901","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/2504.01901/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":"2504.01901","created_at":"2026-07-05T10:43:31.527096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01901v1","created_at":"2026-07-05T10:43:31.527096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01901","created_at":"2026-07-05T10:43:31.527096+00:00"},{"alias_kind":"pith_short_12","alias_value":"UC3WDQVAJQQG","created_at":"2026-07-05T10:43:31.527096+00:00"},{"alias_kind":"pith_short_16","alias_value":"UC3WDQVAJQQGRH5M","created_at":"2026-07-05T10:43:31.527096+00:00"},{"alias_kind":"pith_short_8","alias_value":"UC3WDQVA","created_at":"2026-07-05T10:43:31.527096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19915","citing_title":"SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06891","citing_title":"Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06476","citing_title":"Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20279","citing_title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11991","citing_title":"VGR: Visual Grounded Reasoning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16567","citing_title":"POMA-3D: The Point Map Way to 3D Scene Understanding","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06037","citing_title":"Thinking with Geometry: Active Geometry Integration for Spatial Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09167","citing_title":"MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED","json":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED.json","graph_json":"https://pith.science/api/pith-number/UC3WDQVAJQQGRH5MLRJNFNZCED/graph.json","events_json":"https://pith.science/api/pith-number/UC3WDQVAJQQGRH5MLRJNFNZCED/events.json","paper":"https://pith.science/paper/UC3WDQVA"},"agent_actions":{"view_html":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED","download_json":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED.json","view_paper":"https://pith.science/paper/UC3WDQVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01901&json=true","fetch_graph":"https://pith.science/api/pith-number/UC3WDQVAJQQGRH5MLRJNFNZCED/graph.json","fetch_events":"https://pith.science/api/pith-number/UC3WDQVAJQQGRH5MLRJNFNZCED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED/action/storage_attestation","attest_author":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED/action/author_attestation","sign_citation":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED/action/citation_signature","submit_replication":"https://pith.science/pith/UC3WDQVAJQQGRH5MLRJNFNZCED/action/replication_record"}},"created_at":"2026-07-05T10:43:31.527096+00:00","updated_at":"2026-07-05T10:43:31.527096+00:00"}