{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PC3MW3L36ZWUQLJLNWCSXNYQRF","short_pith_number":"pith:PC3MW3L3","schema_version":"1.0","canonical_sha256":"78b6cb6d7bf66d482d2b6d852bb7108963b2d55d7f69c6f5587d8b358d770c2a","source":{"kind":"arxiv","id":"2406.13642","version":7},"attestation_state":"computed","paper":{"title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Hao Dong, Iaroslav Ponomarenko, Jianhao Yuan, Wankou Yang, Wenxiao Cai, Xiaoqi Li","submitted_at":"2024-06-19T15:41:30Z","abstract_excerpt":"Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for better spatial understanding by feeding both RGB and depth images. Additionally, we have constructed the SpatialQA dataset, which involves multi-level depth-related questions to train VLMs for depth understanding. Finally, we present SpatialBench to comprehensively evaluate VLMs' capabilities in spatial understanding at different levels. Extensive experiments on"},"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":"2406.13642","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T15:41:30Z","cross_cats_sorted":[],"title_canon_sha256":"ed31ddd54f86be24138b400cfb461a7385ad3f35b625ec6afcd8e95fe26100ae","abstract_canon_sha256":"77aabd5312d4961b69baf09458655c6377847ca570adb53c190283e065168967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:08.477332Z","signature_b64":"7gwQ1SpUEWcFzHlqdaA5bGmOpUtn7Z3+rtJoVTAaShtfjqfdzLtPXyNLShk4cvvfScCbavEBef3RLetnn2f9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78b6cb6d7bf66d482d2b6d852bb7108963b2d55d7f69c6f5587d8b358d770c2a","last_reissued_at":"2026-07-05T10:34:08.476764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:08.476764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Hao Dong, Iaroslav Ponomarenko, Jianhao Yuan, Wankou Yang, Wenxiao Cai, Xiaoqi Li","submitted_at":"2024-06-19T15:41:30Z","abstract_excerpt":"Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for better spatial understanding by feeding both RGB and depth images. Additionally, we have constructed the SpatialQA dataset, which involves multi-level depth-related questions to train VLMs for depth understanding. Finally, we present SpatialBench to comprehensively evaluate VLMs' capabilities in spatial understanding at different levels. Extensive experiments on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13642","kind":"arxiv","version":7},"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/2406.13642/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":"2406.13642","created_at":"2026-07-05T10:34:08.476826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13642v7","created_at":"2026-07-05T10:34:08.476826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13642","created_at":"2026-07-05T10:34:08.476826+00:00"},{"alias_kind":"pith_short_12","alias_value":"PC3MW3L36ZWU","created_at":"2026-07-05T10:34:08.476826+00:00"},{"alias_kind":"pith_short_16","alias_value":"PC3MW3L36ZWUQLJL","created_at":"2026-07-05T10:34:08.476826+00:00"},{"alias_kind":"pith_short_8","alias_value":"PC3MW3L3","created_at":"2026-07-05T10:34:08.476826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01784","citing_title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05445","citing_title":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31257","citing_title":"Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30561","citing_title":"VLM3: Vision Language Models Are Native 3D Learners","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05997","citing_title":"4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13998","citing_title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06754","citing_title":"SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10588","citing_title":"Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05997","citing_title":"4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20012","citing_title":"EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07592","citing_title":"Spatio-Temporal Grounding of Large Language Models from Perception Streams","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF","json":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF.json","graph_json":"https://pith.science/api/pith-number/PC3MW3L36ZWUQLJLNWCSXNYQRF/graph.json","events_json":"https://pith.science/api/pith-number/PC3MW3L36ZWUQLJLNWCSXNYQRF/events.json","paper":"https://pith.science/paper/PC3MW3L3"},"agent_actions":{"view_html":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF","download_json":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF.json","view_paper":"https://pith.science/paper/PC3MW3L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13642&json=true","fetch_graph":"https://pith.science/api/pith-number/PC3MW3L36ZWUQLJLNWCSXNYQRF/graph.json","fetch_events":"https://pith.science/api/pith-number/PC3MW3L36ZWUQLJLNWCSXNYQRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF/action/storage_attestation","attest_author":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF/action/author_attestation","sign_citation":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF/action/citation_signature","submit_replication":"https://pith.science/pith/PC3MW3L36ZWUQLJLNWCSXNYQRF/action/replication_record"}},"created_at":"2026-07-05T10:34:08.476826+00:00","updated_at":"2026-07-05T10:34:08.476826+00:00"}