{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GSQB4NTGO2GMIUDMDE2FSW2TH3","short_pith_number":"pith:GSQB4NTG","schema_version":"1.0","canonical_sha256":"34a01e3666768cc4506c1934595b533ef5ccbc1aaf389f197eacd49352b8af5e","source":{"kind":"arxiv","id":"2406.13945","version":3},"attestation_state":"computed","paper":{"title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jie Feng, Junbo Yan, Jun Zhang, Siqi Guo, Tianhui Liu, Tianjian Ouyang, Xin Zhang, Yong Li, Yuwei Du","submitted_at":"2024-06-20T02:25:07Z","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"},"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":"2406.13945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T02:25:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c3bb9f6b88cce57915bcd826b6609073e69ee1b8eaaa5f2892875aeb80bb031c","abstract_canon_sha256":"9dbb16a463d727f5ae716886e7be82ee99b4e969a0f8f27d8b9c90871d02d5f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:10.764910Z","signature_b64":"EJ6HJuJDktIiJETz8jkpdk7Y8GjV1+B6q6JkVkWQEXHUtaHUB4RKkDgv3zTf0j3cE0yyPl8BWbVJ0tgOD8+XBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34a01e3666768cc4506c1934595b533ef5ccbc1aaf389f197eacd49352b8af5e","last_reissued_at":"2026-07-05T11:13:10.764345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:10.764345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jie Feng, Junbo Yan, Jun Zhang, Siqi Guo, Tianhui Liu, Tianjian Ouyang, Xin Zhang, Yong Li, Yuwei Du","submitted_at":"2024-06-20T02:25:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13945","kind":"arxiv","version":3},"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/2406.13945/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":"2406.13945","created_at":"2026-07-05T11:13:10.764410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13945v3","created_at":"2026-07-05T11:13:10.764410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13945","created_at":"2026-07-05T11:13:10.764410+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSQB4NTGO2GM","created_at":"2026-07-05T11:13:10.764410+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSQB4NTGO2GMIUDM","created_at":"2026-07-05T11:13:10.764410+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSQB4NTG","created_at":"2026-07-05T11:13:10.764410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27650","citing_title":"GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3","json":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3.json","graph_json":"https://pith.science/api/pith-number/GSQB4NTGO2GMIUDMDE2FSW2TH3/graph.json","events_json":"https://pith.science/api/pith-number/GSQB4NTGO2GMIUDMDE2FSW2TH3/events.json","paper":"https://pith.science/paper/GSQB4NTG"},"agent_actions":{"view_html":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3","download_json":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3.json","view_paper":"https://pith.science/paper/GSQB4NTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13945&json=true","fetch_graph":"https://pith.science/api/pith-number/GSQB4NTGO2GMIUDMDE2FSW2TH3/graph.json","fetch_events":"https://pith.science/api/pith-number/GSQB4NTGO2GMIUDMDE2FSW2TH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3/action/storage_attestation","attest_author":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3/action/author_attestation","sign_citation":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3/action/citation_signature","submit_replication":"https://pith.science/pith/GSQB4NTGO2GMIUDMDE2FSW2TH3/action/replication_record"}},"created_at":"2026-07-05T11:13:10.764410+00:00","updated_at":"2026-07-05T11:13:10.764410+00:00"}