{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GSQB4NTGO2GMIUDMDE2FSW2TH3","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":"9dbb16a463d727f5ae716886e7be82ee99b4e969a0f8f27d8b9c90871d02d5f6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T02:25:07Z","title_canon_sha256":"c3bb9f6b88cce57915bcd826b6609073e69ee1b8eaaa5f2892875aeb80bb031c"},"schema_version":"1.0","source":{"id":"2406.13945","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13945","created_at":"2026-07-05T11:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13945v3","created_at":"2026-07-05T11:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13945","created_at":"2026-07-05T11:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"GSQB4NTGO2GM","created_at":"2026-07-05T11:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"GSQB4NTGO2GMIUDM","created_at":"2026-07-05T11:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"GSQB4NTG","created_at":"2026-07-05T11:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:562c6ca26a0528ef926380dde41c16ba6413849021fab69c333a10e388f84e8f","target":"graph","created_at":"2026-07-05T11:13:10Z","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/2406.13945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) continue to advance and gain widespread use, establishing systematic and reliable evaluation methodologies for LLMs and vision-language models (VLMs) has become essential to ensure their real-world effectiveness and reliability. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dy","authors_text":"Jie Feng, Junbo Yan, Jun Zhang, Siqi Guo, Tianhui Liu, Tianjian Ouyang, Xin Zhang, Yong Li, Yuwei Du","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T02:25:07Z","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13945","kind":"arxiv","version":3},"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":"sha256:15e45ae14ed2d6613783eccbaa180a9f2872c5813494bd8ea2e8a6affec1a4d5","target":"record","created_at":"2026-07-05T11:13:10Z","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":"9dbb16a463d727f5ae716886e7be82ee99b4e969a0f8f27d8b9c90871d02d5f6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T02:25:07Z","title_canon_sha256":"c3bb9f6b88cce57915bcd826b6609073e69ee1b8eaaa5f2892875aeb80bb031c"},"schema_version":"1.0","source":{"id":"2406.13945","kind":"arxiv","version":3}},"canonical_sha256":"34a01e3666768cc4506c1934595b533ef5ccbc1aaf389f197eacd49352b8af5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34a01e3666768cc4506c1934595b533ef5ccbc1aaf389f197eacd49352b8af5e","first_computed_at":"2026-07-05T11:13:10.764345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:10.764345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJ6HJuJDktIiJETz8jkpdk7Y8GjV1+B6q6JkVkWQEXHUtaHUB4RKkDgv3zTf0j3cE0yyPl8BWbVJ0tgOD8+XBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:10.764910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13945","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15e45ae14ed2d6613783eccbaa180a9f2872c5813494bd8ea2e8a6affec1a4d5","sha256:562c6ca26a0528ef926380dde41c16ba6413849021fab69c333a10e388f84e8f"],"state_sha256":"538ec3eab3965225a66bdc9006abfc04fc77cbb14c2292839574813ae5521b37"}