{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SHPQ2LCE5WE25SO4CSCCPZZ6VG","short_pith_number":"pith:SHPQ2LCE","schema_version":"1.0","canonical_sha256":"91df0d2c44ed89aec9dc148427e73ea9886c3fe64b4ff4bb2862acddf8e0ff93","source":{"kind":"arxiv","id":"2606.18803","version":1},"attestation_state":"computed","paper":{"title":"ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Hao Liu, Kai Wan, Li Ma, Tengfei Lyu, Xu Liu, Zihao Lu, Zirui Yuan","submitted_at":"2026-06-17T08:15:07Z","abstract_excerpt":"Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user profiles. However, scaling such profiling to a live, millisecond-latency dispatcher faces three intertwined constraints rarely addressed together: on a platf"},"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":"2606.18803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T08:15:07Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"3fa9d2465a7b73fb76bd9b85a997661f3bc7bbb175710c79ffd54fee75a7dd3e","abstract_canon_sha256":"6bd005abf1136d172da29c433b317b9e8d82c6033803e1d8fa211875b1c1b9f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:47.942649Z","signature_b64":"H0Ja05KjRDHNeqsBjwFYy0noeKZjuKg0pPc6Rnvfg16u0NBZR3EyLqzyaoggOWY9L9JwrSiQlOFtsOFuDC3jCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91df0d2c44ed89aec9dc148427e73ea9886c3fe64b4ff4bb2862acddf8e0ff93","last_reissued_at":"2026-06-19T16:11:47.942290Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:47.942290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Hao Liu, Kai Wan, Li Ma, Tengfei Lyu, Xu Liu, Zihao Lu, Zirui Yuan","submitted_at":"2026-06-17T08:15:07Z","abstract_excerpt":"Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user profiles. However, scaling such profiling to a live, millisecond-latency dispatcher faces three intertwined constraints rarely addressed together: on a platf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18803","kind":"arxiv","version":1},"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/2606.18803/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":"2606.18803","created_at":"2026-06-19T16:11:47.942362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18803v1","created_at":"2026-06-19T16:11:47.942362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18803","created_at":"2026-06-19T16:11:47.942362+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHPQ2LCE5WE2","created_at":"2026-06-19T16:11:47.942362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHPQ2LCE5WE25SO4","created_at":"2026-06-19T16:11:47.942362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHPQ2LCE","created_at":"2026-06-19T16:11:47.942362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG","json":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG.json","graph_json":"https://pith.science/api/pith-number/SHPQ2LCE5WE25SO4CSCCPZZ6VG/graph.json","events_json":"https://pith.science/api/pith-number/SHPQ2LCE5WE25SO4CSCCPZZ6VG/events.json","paper":"https://pith.science/paper/SHPQ2LCE"},"agent_actions":{"view_html":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG","download_json":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG.json","view_paper":"https://pith.science/paper/SHPQ2LCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18803&json=true","fetch_graph":"https://pith.science/api/pith-number/SHPQ2LCE5WE25SO4CSCCPZZ6VG/graph.json","fetch_events":"https://pith.science/api/pith-number/SHPQ2LCE5WE25SO4CSCCPZZ6VG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG/action/storage_attestation","attest_author":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG/action/author_attestation","sign_citation":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG/action/citation_signature","submit_replication":"https://pith.science/pith/SHPQ2LCE5WE25SO4CSCCPZZ6VG/action/replication_record"}},"created_at":"2026-06-19T16:11:47.942362+00:00","updated_at":"2026-06-19T16:11:47.942362+00:00"}