{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y63LIZTGZSZG3ZW7XCAEFB7BIL","short_pith_number":"pith:Y63LIZTG","schema_version":"1.0","canonical_sha256":"c7b6b46666ccb26de6dfb8804287e142c46bc1f682cca4910788d97024fa1ac7","source":{"kind":"arxiv","id":"2504.20024","version":2},"attestation_state":"computed","paper":{"title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Celso de Melo, Jianwen Xie, Qihao Liu, Wufei Ma, Xingrui Wang, Yu-Cheng Chou","submitted_at":"2025-04-28T17:48:43Z","abstract_excerpt":"Despite recent advances on multi-modal models, 3D spatial reasoning remains a challenging task for state-of-the-art open-source and proprietary models. Recent studies explore data-driven approaches and achieve enhanced spatial reasoning performance by fine-tuning models on 3D-related visual question-answering data. However, these methods typically perform spatial reasoning in an implicit manner and often fail on questions that are trivial to humans, even with long chain-of-thought reasoning. In this work, we introduce SpatialReasoner, a novel large vision-language model (LVLM) that addresses 3"},"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":"2504.20024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T17:48:43Z","cross_cats_sorted":[],"title_canon_sha256":"14aaa7896466b1965c077fb96e8967677988ee01450b09f7fe1e86d784cadc48","abstract_canon_sha256":"551a0aef9d5bb6141bc996ce01155accbedd153105e8c7b313370e21ace0e24e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:06.594073Z","signature_b64":"4ckJE3zRb1A5G7KEb5V3Mnu+N2VcyeJeLrZBDVSax38g/Dh6folmzbdE/BclW5yPJJVSP2Dj8YTx7umJRjGnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7b6b46666ccb26de6dfb8804287e142c46bc1f682cca4910788d97024fa1ac7","last_reissued_at":"2026-07-05T11:19:06.593600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:06.593600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Celso de Melo, Jianwen Xie, Qihao Liu, Wufei Ma, Xingrui Wang, Yu-Cheng Chou","submitted_at":"2025-04-28T17:48:43Z","abstract_excerpt":"Despite recent advances on multi-modal models, 3D spatial reasoning remains a challenging task for state-of-the-art open-source and proprietary models. Recent studies explore data-driven approaches and achieve enhanced spatial reasoning performance by fine-tuning models on 3D-related visual question-answering data. However, these methods typically perform spatial reasoning in an implicit manner and often fail on questions that are trivial to humans, even with long chain-of-thought reasoning. In this work, we introduce SpatialReasoner, a novel large vision-language model (LVLM) that addresses 3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20024","kind":"arxiv","version":2},"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/2504.20024/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":"2504.20024","created_at":"2026-07-05T11:19:06.593661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20024v2","created_at":"2026-07-05T11:19:06.593661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20024","created_at":"2026-07-05T11:19:06.593661+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y63LIZTGZSZG","created_at":"2026-07-05T11:19:06.593661+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y63LIZTGZSZG3ZW7","created_at":"2026-07-05T11:19:06.593661+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y63LIZTG","created_at":"2026-07-05T11:19:06.593661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21190","citing_title":"SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23717","citing_title":"SpaCE: Rethinking Spatial Capacity and Generalization in Multi-Frame Multimodal Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17539","citing_title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11918","citing_title":"The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11683","citing_title":"Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09803","citing_title":"Echo-Memory: A Controlled Study of Memory in Action World Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08952","citing_title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00881","citing_title":"OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01462","citing_title":"An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23898","citing_title":"SPACENUM: Revisiting Spatial Numerical Understanding in VLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19710","citing_title":"PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22658","citing_title":"PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21190","citing_title":"SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL","json":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL.json","graph_json":"https://pith.science/api/pith-number/Y63LIZTGZSZG3ZW7XCAEFB7BIL/graph.json","events_json":"https://pith.science/api/pith-number/Y63LIZTGZSZG3ZW7XCAEFB7BIL/events.json","paper":"https://pith.science/paper/Y63LIZTG"},"agent_actions":{"view_html":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL","download_json":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL.json","view_paper":"https://pith.science/paper/Y63LIZTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20024&json=true","fetch_graph":"https://pith.science/api/pith-number/Y63LIZTGZSZG3ZW7XCAEFB7BIL/graph.json","fetch_events":"https://pith.science/api/pith-number/Y63LIZTGZSZG3ZW7XCAEFB7BIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL/action/storage_attestation","attest_author":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL/action/author_attestation","sign_citation":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL/action/citation_signature","submit_replication":"https://pith.science/pith/Y63LIZTGZSZG3ZW7XCAEFB7BIL/action/replication_record"}},"created_at":"2026-07-05T11:19:06.593661+00:00","updated_at":"2026-07-05T11:19:06.593661+00:00"}