{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B7MNYUT7LLQHKJIIELI22IFQUV","short_pith_number":"pith:B7MNYUT7","schema_version":"1.0","canonical_sha256":"0fd8dc527f5ae075250822d1ad20b0a553d4a19f761888900bfdc4f69dcd8a6a","source":{"kind":"arxiv","id":"2602.22638","version":2},"attestation_state":"computed","paper":{"title":"MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Chen, Chao Wang, Chuan Qin, Hengshu Zhu, Jingshuai Zhang, Kaikui Liu, Longfei Xu, Xiangxiang Chu, Zhiheng Song","submitted_at":"2026-02-26T05:39:38Z","abstract_excerpt":"Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries c"},"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":"2602.22638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T05:39:38Z","cross_cats_sorted":[],"title_canon_sha256":"a9fe81272bf35b8c0a1d4527481e481d9712e6526055cfda323053b5d31d3da1","abstract_canon_sha256":"c84b0b28b0533ed642677c2e0810a7b98600d11c914c9ac7f6684cb29fdbbe58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:31.672220Z","signature_b64":"n3Lupr5OJr9FhSoomQuVIzAvOltJgEUZ/Bb+vPpRRcjPN3Mna9LFXbkRRvPxWNkl7Gcir4ph2wGtdf5xLkCSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd8dc527f5ae075250822d1ad20b0a553d4a19f761888900bfdc4f69dcd8a6a","last_reissued_at":"2026-06-11T01:09:31.671112Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:31.671112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Chen, Chao Wang, Chuan Qin, Hengshu Zhu, Jingshuai Zhang, Kaikui Liu, Longfei Xu, Xiangxiang Chu, Zhiheng Song","submitted_at":"2026-02-26T05:39:38Z","abstract_excerpt":"Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22638","kind":"arxiv","version":2},"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/2602.22638/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":"2602.22638","created_at":"2026-06-11T01:09:31.671249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22638v2","created_at":"2026-06-11T01:09:31.671249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22638","created_at":"2026-06-11T01:09:31.671249+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7MNYUT7LLQH","created_at":"2026-06-11T01:09:31.671249+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7MNYUT7LLQHKJII","created_at":"2026-06-11T01:09:31.671249+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7MNYUT7","created_at":"2026-06-11T01:09:31.671249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.22355","citing_title":"TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10782","citing_title":"TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV","json":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV.json","graph_json":"https://pith.science/api/pith-number/B7MNYUT7LLQHKJIIELI22IFQUV/graph.json","events_json":"https://pith.science/api/pith-number/B7MNYUT7LLQHKJIIELI22IFQUV/events.json","paper":"https://pith.science/paper/B7MNYUT7"},"agent_actions":{"view_html":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV","download_json":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV.json","view_paper":"https://pith.science/paper/B7MNYUT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22638&json=true","fetch_graph":"https://pith.science/api/pith-number/B7MNYUT7LLQHKJIIELI22IFQUV/graph.json","fetch_events":"https://pith.science/api/pith-number/B7MNYUT7LLQHKJIIELI22IFQUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV/action/storage_attestation","attest_author":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV/action/author_attestation","sign_citation":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV/action/citation_signature","submit_replication":"https://pith.science/pith/B7MNYUT7LLQHKJIIELI22IFQUV/action/replication_record"}},"created_at":"2026-06-11T01:09:31.671249+00:00","updated_at":"2026-06-11T01:09:31.671249+00:00"}