{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K4V6ZRKOVFJSFFJMRB7KRQT3IH","short_pith_number":"pith:K4V6ZRKO","schema_version":"1.0","canonical_sha256":"572becc54ea95322952c887ea8c27b41d2924ae7b624c1d60bb21879695a6942","source":{"kind":"arxiv","id":"2606.23978","version":1},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning for Warehouse SLAM Throughput Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ken Meszaros, Kevin Tan, Mouhacine Benosman, Rajat Kumar, Tina Dongxu Li, Trevor Dardik","submitted_at":"2026-06-22T22:10:06Z","abstract_excerpt":"We present an offline reinforcement learning (RL) framework for optimizing SLAM throughput control in a warehouse fulfillment environment. SLAM (Scan/Label/Apply/Manifest) throughput directly influences system congestion and operational efficiency. Our RL-based control approach dynamically recommends SLAM throughput settings that adaptively balance throughput maximization with downstream stability through intelligent adjustment of throttling behavior. We include a history-informed state representation, action space abstraction for delayed-impact control, and a reward function that captures bot"},"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":"2606.23978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T22:10:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7fa867b90aa46e2e3baaeea3d6d2ade600539c181e8524c1250a02bf9a373770","abstract_canon_sha256":"db672fec6c5bcabecdb34bceca0dc71143dba94959b7d0aa50359e8618dc3a30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:32.164611Z","signature_b64":"XQ6zDAiPxMejOJ6Qfpu6DwUca7yZtO3wl1JNsH3Er4fDUe5UyIDlZWtlSuG/WQ7NatDiDk4ZxAmikopPvLTSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572becc54ea95322952c887ea8c27b41d2924ae7b624c1d60bb21879695a6942","last_reissued_at":"2026-06-24T00:14:32.164206Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:32.164206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Warehouse SLAM Throughput Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ken Meszaros, Kevin Tan, Mouhacine Benosman, Rajat Kumar, Tina Dongxu Li, Trevor Dardik","submitted_at":"2026-06-22T22:10:06Z","abstract_excerpt":"We present an offline reinforcement learning (RL) framework for optimizing SLAM throughput control in a warehouse fulfillment environment. SLAM (Scan/Label/Apply/Manifest) throughput directly influences system congestion and operational efficiency. Our RL-based control approach dynamically recommends SLAM throughput settings that adaptively balance throughput maximization with downstream stability through intelligent adjustment of throttling behavior. We include a history-informed state representation, action space abstraction for delayed-impact control, and a reward function that captures bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23978","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/2606.23978/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":"2606.23978","created_at":"2026-06-24T00:14:32.164263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23978v1","created_at":"2026-06-24T00:14:32.164263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23978","created_at":"2026-06-24T00:14:32.164263+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4V6ZRKOVFJS","created_at":"2026-06-24T00:14:32.164263+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4V6ZRKOVFJSFFJM","created_at":"2026-06-24T00:14:32.164263+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4V6ZRKO","created_at":"2026-06-24T00:14:32.164263+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/K4V6ZRKOVFJSFFJMRB7KRQT3IH","json":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH.json","graph_json":"https://pith.science/api/pith-number/K4V6ZRKOVFJSFFJMRB7KRQT3IH/graph.json","events_json":"https://pith.science/api/pith-number/K4V6ZRKOVFJSFFJMRB7KRQT3IH/events.json","paper":"https://pith.science/paper/K4V6ZRKO"},"agent_actions":{"view_html":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH","download_json":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH.json","view_paper":"https://pith.science/paper/K4V6ZRKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23978&json=true","fetch_graph":"https://pith.science/api/pith-number/K4V6ZRKOVFJSFFJMRB7KRQT3IH/graph.json","fetch_events":"https://pith.science/api/pith-number/K4V6ZRKOVFJSFFJMRB7KRQT3IH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH/action/storage_attestation","attest_author":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH/action/author_attestation","sign_citation":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH/action/citation_signature","submit_replication":"https://pith.science/pith/K4V6ZRKOVFJSFFJMRB7KRQT3IH/action/replication_record"}},"created_at":"2026-06-24T00:14:32.164263+00:00","updated_at":"2026-06-24T00:14:32.164263+00:00"}