{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ROOSSE422SZAP5GWVR3AWAGFD","short_pith_number":"pith:3ROOSSE4","schema_version":"1.0","canonical_sha256":"dc5ce9489cd6a5903fa6b563b0580628ed30c44abd129b97aca2434c2886a250","source":{"kind":"arxiv","id":"2503.23765","version":6},"attestation_state":"computed","paper":{"title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Tao Lin, Wenxiao Cai, Xiangrui Liu, Yiming Zhang, Yun Li, Zheng Liu","submitted_at":"2025-03-31T06:30:35Z","abstract_excerpt":"The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their ability to perform precise and quantitative spatial-temporal understanding in real-world applications remains largely unexamined, leading to uncertain prospects. To evaluate models' Spatial-Temporal Intelligence, we introduce STI-Bench, a benchmark designed to evaluate MLLMs' spatial-temporal understanding through challenging tasks such as estimating and predic"},"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":"2503.23765","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T06:30:35Z","cross_cats_sorted":[],"title_canon_sha256":"11d93dbd86402db0c3dc1e28feeb33e1284d1ddbeca9c00f2ac406ee1477a19e","abstract_canon_sha256":"32ef3fae17a85a807e779885992c6a089a0881e419fb544544e16b3bf0885a22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:28.358445Z","signature_b64":"iA6sYVOZoDB2mdyNZUKMOMJ69u+v+msG+JBgPWXQe3cGmmRNYSxXqVHUKwoHaGrZrRyr5vNQufIbwems9HIGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc5ce9489cd6a5903fa6b563b0580628ed30c44abd129b97aca2434c2886a250","last_reissued_at":"2026-07-05T11:38:28.357968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:28.357968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Tao Lin, Wenxiao Cai, Xiangrui Liu, Yiming Zhang, Yun Li, Zheng Liu","submitted_at":"2025-03-31T06:30:35Z","abstract_excerpt":"The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their ability to perform precise and quantitative spatial-temporal understanding in real-world applications remains largely unexamined, leading to uncertain prospects. To evaluate models' Spatial-Temporal Intelligence, we introduce STI-Bench, a benchmark designed to evaluate MLLMs' spatial-temporal understanding through challenging tasks such as estimating and predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23765","kind":"arxiv","version":6},"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/2503.23765/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":"2503.23765","created_at":"2026-07-05T11:38:28.358028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23765v6","created_at":"2026-07-05T11:38:28.358028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23765","created_at":"2026-07-05T11:38:28.358028+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ROOSSE422SZ","created_at":"2026-07-05T11:38:28.358028+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ROOSSE422SZAP5G","created_at":"2026-07-05T11:38:28.358028+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ROOSSE4","created_at":"2026-07-05T11:38:28.358028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11683","citing_title":"Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05677","citing_title":"LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27318","citing_title":"Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30231","citing_title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28049","citing_title":"AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10719","citing_title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21625","citing_title":"Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20165","citing_title":"CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21471","citing_title":"SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03944","citing_title":"SCP: Spatial Causal Prediction in Video","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01805","citing_title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27437","citing_title":"SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10106","citing_title":"ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09712","citing_title":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD","json":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD.json","graph_json":"https://pith.science/api/pith-number/3ROOSSE422SZAP5GWVR3AWAGFD/graph.json","events_json":"https://pith.science/api/pith-number/3ROOSSE422SZAP5GWVR3AWAGFD/events.json","paper":"https://pith.science/paper/3ROOSSE4"},"agent_actions":{"view_html":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD","download_json":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD.json","view_paper":"https://pith.science/paper/3ROOSSE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23765&json=true","fetch_graph":"https://pith.science/api/pith-number/3ROOSSE422SZAP5GWVR3AWAGFD/graph.json","fetch_events":"https://pith.science/api/pith-number/3ROOSSE422SZAP5GWVR3AWAGFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD/action/storage_attestation","attest_author":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD/action/author_attestation","sign_citation":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD/action/citation_signature","submit_replication":"https://pith.science/pith/3ROOSSE422SZAP5GWVR3AWAGFD/action/replication_record"}},"created_at":"2026-07-05T11:38:28.358028+00:00","updated_at":"2026-07-05T11:38:28.358028+00:00"}