{"paper":{"title":"Intelligent Truck Matching in Full Truckload Shipments using Ping2Hex approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Machine learning with H3 hexagonal GPS indexing matches trucks to shipments more accurately when vehicle IDs are missing.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ankit Singh Chauhan, Aravind Manoj, Dinesh Rajkumar, Jose Mathew, Mohit Goel, Srinivas Kumar Ramdas","submitted_at":"2026-05-08T13:40:53Z","abstract_excerpt":"Accurate truck-to-shipment matching using GPS data is foundational for full truckload supply chain visibility, enabling real-time tracking and accurate estimated time of arrival (ETA) predictions. However, missing or corrupted vehicle identifiers prevent traditional matching approaches, leaving shipments without visibility. This paper presents Intelligent Truck Matching (ITM) 2.0, a machine learning system that addresses this critical gap by formulating matching as a probabilistic ranking problem. Our approach leverages Uber H3 hexagonal spatial indexing to discretize GPS pings into route simi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through rigorous evaluation including offline model selection (SVM, XGBoost, LightGBM), comprehensive ablation studies, and production shadow testing, ITM 2.0 achieves 26 percentage point precision improvement in North America and 14 points in Europe, while doubling coverage.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That historical matched shipment data provides a sufficiently clean and representative training signal, and that H3 discretization combined with temporal features can reliably distinguish correct matches despite geocoding errors up to 1 km and multiple candidate trucks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ITM 2.0 uses Uber H3 hexagons on GPS data plus temporal features with LightGBM ranking and threshold post-processing to match trucks to full truckload shipments, delivering 26 percentage point precision gains in North America and doubled coverage.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Machine learning with H3 hexagonal GPS indexing matches trucks to shipments more accurately when vehicle IDs are missing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8baaa1aa6df09b6d809fb382a66441debf830575e5ca1d946096941ab7813993"},"source":{"id":"2605.07733","kind":"arxiv","version":2},"verdict":{"id":"14b588cd-2c4f-43ca-8330-62d747d7b3c0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T03:24:53.805355Z","strongest_claim":"Through rigorous evaluation including offline model selection (SVM, XGBoost, LightGBM), comprehensive ablation studies, and production shadow testing, ITM 2.0 achieves 26 percentage point precision improvement in North America and 14 points in Europe, while doubling coverage.","one_line_summary":"ITM 2.0 uses Uber H3 hexagons on GPS data plus temporal features with LightGBM ranking and threshold post-processing to match trucks to full truckload shipments, delivering 26 percentage point precision gains in North America and doubled coverage.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That historical matched shipment data provides a sufficiently clean and representative training signal, and that H3 discretization combined with temporal features can reliably distinguish correct matches despite geocoding errors up to 1 km and multiple candidate trucks.","pith_extraction_headline":"Machine learning with H3 hexagonal GPS indexing matches trucks to shipments more accurately when vehicle IDs are missing."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07733/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:22:02.812425Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:35:43.439153Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.407986Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:34:13.532053Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3fee6912f65fe712b2f84eea2a679ba48c79bc1a754818dbf12a29f309de8a34"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f16f1eaf052c3cc0f2adb1dde25058ec833d53db3c95105269dd9c4d9999ebe3"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}