{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTE45LMTHXKT45R6WCJC2E4FJE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9460a211193487e8cc2b815ca019db42b984466b6ca1c7e6b005a32c6c57d43c","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:21:20Z","title_canon_sha256":"23d8fcf5f9d4e776f9f373dbf18cb1b3b17596b2551e9f853d876f0e09070d73"},"schema_version":"1.0","source":{"id":"2606.13604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13604","created_at":"2026-06-12T01:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13604v1","created_at":"2026-06-12T01:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13604","created_at":"2026-06-12T01:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"VTE45LMTHXKT","created_at":"2026-06-12T01:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"VTE45LMTHXKT45R6","created_at":"2026-06-12T01:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"VTE45LMT","created_at":"2026-06-12T01:10:12Z"}],"graph_snapshots":[{"event_id":"sha256:e787d473fae8eab77f45bfd806519aeb367c1a786d8e12fd87a2a8422e4ec45d","target":"graph","created_at":"2026-06-12T01:10:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.13604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haochen Wu, Shiguang Xie, Yi Hou","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:21:20Z","title":"Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13604","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bcc80deee6791a12dcf93f845d2b669f8912624b367ec76069dddc7402b87613","target":"record","created_at":"2026-06-12T01:10:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9460a211193487e8cc2b815ca019db42b984466b6ca1c7e6b005a32c6c57d43c","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:21:20Z","title_canon_sha256":"23d8fcf5f9d4e776f9f373dbf18cb1b3b17596b2551e9f853d876f0e09070d73"},"schema_version":"1.0","source":{"id":"2606.13604","kind":"arxiv","version":1}},"canonical_sha256":"acc9cead933dd53e763eb0922d1385491ba77d64a73e90f25a4ba192352dc8d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc9cead933dd53e763eb0922d1385491ba77d64a73e90f25a4ba192352dc8d6","first_computed_at":"2026-06-12T01:10:12.620586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:12.620586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PV12zcvPMIVFwpN6+N7IpUUJsXYFULCNrnc/JTnW7/EtrNbaTZRZQ/6tG1ylEJnqkRxAALusrNEQ2HEK8UW0CA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:12.621342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcc80deee6791a12dcf93f845d2b669f8912624b367ec76069dddc7402b87613","sha256:e787d473fae8eab77f45bfd806519aeb367c1a786d8e12fd87a2a8422e4ec45d"],"state_sha256":"190a11c5de72ec83d6be4f891cd214bcb64ce83012bae1123d9cd6fa1f3e79fc"}