{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3ROOSSE422SZAP5GWVR3AWAGFD","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":"32ef3fae17a85a807e779885992c6a089a0881e419fb544544e16b3bf0885a22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T06:30:35Z","title_canon_sha256":"11d93dbd86402db0c3dc1e28feeb33e1284d1ddbeca9c00f2ac406ee1477a19e"},"schema_version":"1.0","source":{"id":"2503.23765","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23765","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23765v6","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23765","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"3ROOSSE422SZ","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"3ROOSSE422SZAP5G","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"3ROOSSE4","created_at":"2026-07-05T11:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:4d240de9a48ce51f785e106861e2f894539d58299995eaab3089415376194f8b","target":"graph","created_at":"2026-07-05T11:38:28Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.23765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Zhao, Tao Lin, Wenxiao Cai, Xiangrui Liu, Yiming Zhang, Yun Li, Zheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T06:30:35Z","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23765","kind":"arxiv","version":6},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1d8c767629d001b47f2a5aba007f95e727501071f3982eaa44363f72a0d18e4","target":"record","created_at":"2026-07-05T11:38:28Z","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":"32ef3fae17a85a807e779885992c6a089a0881e419fb544544e16b3bf0885a22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T06:30:35Z","title_canon_sha256":"11d93dbd86402db0c3dc1e28feeb33e1284d1ddbeca9c00f2ac406ee1477a19e"},"schema_version":"1.0","source":{"id":"2503.23765","kind":"arxiv","version":6}},"canonical_sha256":"dc5ce9489cd6a5903fa6b563b0580628ed30c44abd129b97aca2434c2886a250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc5ce9489cd6a5903fa6b563b0580628ed30c44abd129b97aca2434c2886a250","first_computed_at":"2026-07-05T11:38:28.357968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:28.357968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iA6sYVOZoDB2mdyNZUKMOMJ69u+v+msG+JBgPWXQe3cGmmRNYSxXqVHUKwoHaGrZrRyr5vNQufIbwems9HIGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:28.358445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23765","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1d8c767629d001b47f2a5aba007f95e727501071f3982eaa44363f72a0d18e4","sha256:4d240de9a48ce51f785e106861e2f894539d58299995eaab3089415376194f8b"],"state_sha256":"760076598cbd7fc7da4857831abd754caab05a0250029d3c1590edd257df0f63"}