{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4I32KD7BCKRB5ZDAQS4KBVMAC3","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":"db7f0aa41d78084ffe58d91aa0b2824fcd4d3f180e77b72e7aefadc946c950cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T07:30:57Z","title_canon_sha256":"010b9085aab50152e39ce3f217bbf5af265bcd9111daa28cf72785b8dd66edfb"},"schema_version":"1.0","source":{"id":"2505.17572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17572","created_at":"2026-07-05T11:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17572v1","created_at":"2026-07-05T11:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17572","created_at":"2026-07-05T11:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"4I32KD7BCKRB","created_at":"2026-07-05T11:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"4I32KD7BCKRB5ZDA","created_at":"2026-07-05T11:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"4I32KD7B","created_at":"2026-07-05T11:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:da7ba5e7892651c719937c5ef5c5833579ea15da0e1404eabb440af3929d84f2","target":"graph","created_at":"2026-07-05T11:08:28Z","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/2505.17572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown emerging potential in spatiotemporal reasoning, making them promising candidates for building urban agents that support diverse urban downstream applications. Despite these benefits, existing studies primarily focus on evaluating urban LLM agent on outcome-level metrics (e.g., prediction accuracy, traffic efficiency), offering limited insight into their underlying reasoning processes. As a result, the strengths and limitations of urban LLM agents in spatiotemporal reasoning remain poorly understood. To this end, we introduce USTBench, the first benchmark","authors_text":"Hao Liu, Siqi Lai, Yansong Ning, Zhixi Chen, Zirui Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T07:30:57Z","title":"USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17572","kind":"arxiv","version":1},"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":"sha256:34d40672b686c06585ad2d2a03f0bbca9b350d11102ed0b983a2e3baf471fe73","target":"record","created_at":"2026-07-05T11:08:28Z","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":"db7f0aa41d78084ffe58d91aa0b2824fcd4d3f180e77b72e7aefadc946c950cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T07:30:57Z","title_canon_sha256":"010b9085aab50152e39ce3f217bbf5af265bcd9111daa28cf72785b8dd66edfb"},"schema_version":"1.0","source":{"id":"2505.17572","kind":"arxiv","version":1}},"canonical_sha256":"e237a50fe112a21ee46084b8a0d58016e0f3abcf3167d16e3b9d2ff92e3174ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e237a50fe112a21ee46084b8a0d58016e0f3abcf3167d16e3b9d2ff92e3174ad","first_computed_at":"2026-07-05T11:08:28.343067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:28.343067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F390jb3bB41piM0/gHztBPzNKBq/pybOKOi7wgDNJi1Z1AUuR2nj6I+vTq4SO7ZDH4ZGFIzS25Tc7FzjAxJpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:28.343693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34d40672b686c06585ad2d2a03f0bbca9b350d11102ed0b983a2e3baf471fe73","sha256:da7ba5e7892651c719937c5ef5c5833579ea15da0e1404eabb440af3929d84f2"],"state_sha256":"3bb11b46d472903c7d6bc8fa2f5e168b1f6c72d26dc2022c1070cbb17e8b3515"}