{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VTE45LMTHXKT45R6WCJC2E4FJE","short_pith_number":"pith:VTE45LMT","schema_version":"1.0","canonical_sha256":"acc9cead933dd53e763eb0922d1385491ba77d64a73e90f25a4ba192352dc8d6","source":{"kind":"arxiv","id":"2606.13604","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Haochen Wu, Shiguang Xie, Yi Hou","submitted_at":"2026-06-11T17:21:20Z","abstract_excerpt":"Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeo"},"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":"2606.13604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:21:20Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"23d8fcf5f9d4e776f9f373dbf18cb1b3b17596b2551e9f853d876f0e09070d73","abstract_canon_sha256":"9460a211193487e8cc2b815ca019db42b984466b6ca1c7e6b005a32c6c57d43c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:12.621342Z","signature_b64":"PV12zcvPMIVFwpN6+N7IpUUJsXYFULCNrnc/JTnW7/EtrNbaTZRZQ/6tG1ylEJnqkRxAALusrNEQ2HEK8UW0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc9cead933dd53e763eb0922d1385491ba77d64a73e90f25a4ba192352dc8d6","last_reissued_at":"2026-06-12T01:10:12.620586Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:12.620586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Haochen Wu, Shiguang Xie, Yi Hou","submitted_at":"2026-06-11T17:21:20Z","abstract_excerpt":"Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13604","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/2606.13604/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":"2606.13604","created_at":"2026-06-12T01:10:12.620708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13604v1","created_at":"2026-06-12T01:10:12.620708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13604","created_at":"2026-06-12T01:10:12.620708+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTE45LMTHXKT","created_at":"2026-06-12T01:10:12.620708+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTE45LMTHXKT45R6","created_at":"2026-06-12T01:10:12.620708+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTE45LMT","created_at":"2026-06-12T01:10:12.620708+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/VTE45LMTHXKT45R6WCJC2E4FJE","json":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE.json","graph_json":"https://pith.science/api/pith-number/VTE45LMTHXKT45R6WCJC2E4FJE/graph.json","events_json":"https://pith.science/api/pith-number/VTE45LMTHXKT45R6WCJC2E4FJE/events.json","paper":"https://pith.science/paper/VTE45LMT"},"agent_actions":{"view_html":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE","download_json":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE.json","view_paper":"https://pith.science/paper/VTE45LMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13604&json=true","fetch_graph":"https://pith.science/api/pith-number/VTE45LMTHXKT45R6WCJC2E4FJE/graph.json","fetch_events":"https://pith.science/api/pith-number/VTE45LMTHXKT45R6WCJC2E4FJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE/action/storage_attestation","attest_author":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE/action/author_attestation","sign_citation":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE/action/citation_signature","submit_replication":"https://pith.science/pith/VTE45LMTHXKT45R6WCJC2E4FJE/action/replication_record"}},"created_at":"2026-06-12T01:10:12.620708+00:00","updated_at":"2026-06-12T01:10:12.620708+00:00"}