{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NDYGYQU2UIBU4NCCVIH4D54Z4N","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":"306ba9c4cca332d74bdc8207e48abe2593c6ff2b9e0f8585ade20f3f9affbc82","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T13:40:08Z","title_canon_sha256":"a194220685f97df6e61f7e9d66296482c4875162262b0b456f721b27cf751ffb"},"schema_version":"1.0","source":{"id":"2501.08109","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08109","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08109v4","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08109","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"NDYGYQU2UIBU","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"NDYGYQU2UIBU4NCC","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"NDYGYQU2","created_at":"2026-07-05T11:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:9fcfcd5327229fc2428600575d24750b737288ec00232df35beb6112d440f41d","target":"graph","created_at":"2026-07-05T11:18:17Z","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/2501.08109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel reinforcement learning algorithm for inventory management of newly launched products with no historical demand information. The algorithm follows the classic Dyna-$Q$ structure, balancing the model-free and model-based approaches, while accelerating the training process of Dyna-$Q$ and mitigating the model discrepancy generated by the model-based feedback. Based on the idea of transfer learning, warm-start information from the demand data of existing similar products can be incorporated into the algorithm to further stabilize the early-stage training and reduc","authors_text":"Longxiao Liu, Wenjie Huang, Xinye Qu","cross_cats":["cs.AI","cs.CE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T13:40:08Z","title":"Data-driven inventory management for new products: An adjusted Dyna-$Q$ approach with transfer learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08109","kind":"arxiv","version":4},"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":"sha256:44c3b5d7f06a18f0094eab85da75274925dbd04f44589c03f3802aef1d253094","target":"record","created_at":"2026-07-05T11:18:17Z","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":"306ba9c4cca332d74bdc8207e48abe2593c6ff2b9e0f8585ade20f3f9affbc82","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T13:40:08Z","title_canon_sha256":"a194220685f97df6e61f7e9d66296482c4875162262b0b456f721b27cf751ffb"},"schema_version":"1.0","source":{"id":"2501.08109","kind":"arxiv","version":4}},"canonical_sha256":"68f06c429aa2034e3442aa0fc1f799e35fee8046f784fc72b18dad72255d4cb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f06c429aa2034e3442aa0fc1f799e35fee8046f784fc72b18dad72255d4cb1","first_computed_at":"2026-07-05T11:18:17.046072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:17.046072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60ROyOBcQ3Rsv2/Ey9WIYz79qo89Z42Dj0hzM7mbdyRqTEDmEQoJJJHIYumFtW6vdCfqHpll/BDqiPcv+JhWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:17.046786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08109","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c3b5d7f06a18f0094eab85da75274925dbd04f44589c03f3802aef1d253094","sha256:9fcfcd5327229fc2428600575d24750b737288ec00232df35beb6112d440f41d"],"state_sha256":"4db7f2ea2730362f54ad98784bdb1072fec64b6abbc4abdef2c1b9001c90565b"}