{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q27G5PCTIXQPRD5GHVNDAWULRT","short_pith_number":"pith:Q27G5PCT","canonical_record":{"source":{"id":"2308.01649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T09:31:45Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1991189d461ea9950df1572c5c243ca3879aba7f594c3a4852ac52ead375e1c1","abstract_canon_sha256":"8726700ae7697d656b40c860abef51d027310e5a10323521fbba0a26c77add82"},"schema_version":"1.0"},"canonical_sha256":"86be6ebc5345e0f88fa63d5a305a8b8ce2f621ffd679f987120ed7c85d5c73c2","source":{"kind":"arxiv","id":"2308.01649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01649","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01649v1","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01649","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q27G5PCTIXQP","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q27G5PCTIXQPRD5G","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q27G5PCT","created_at":"2026-07-05T06:37:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q27G5PCTIXQPRD5GHVNDAWULRT","target":"record","payload":{"canonical_record":{"source":{"id":"2308.01649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T09:31:45Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1991189d461ea9950df1572c5c243ca3879aba7f594c3a4852ac52ead375e1c1","abstract_canon_sha256":"8726700ae7697d656b40c860abef51d027310e5a10323521fbba0a26c77add82"},"schema_version":"1.0"},"canonical_sha256":"86be6ebc5345e0f88fa63d5a305a8b8ce2f621ffd679f987120ed7c85d5c73c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:21.471937Z","signature_b64":"4owLPzGPC25mWPCjOgu6oFdpgd4qANzZlis61LgIGB1FXZUEyjfuzdZC5xMNzxBiAPKAt8fQTYnPPjWqoSdNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86be6ebc5345e0f88fa63d5a305a8b8ce2f621ffd679f987120ed7c85d5c73c2","last_reissued_at":"2026-07-05T06:37:21.471437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:21.471437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.01649","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ego5fgKeTCqpH4hj3sG0+W1V3H+KDccByWPdmRsPtUN+QjR6bs0NN2emHkmdbdXgV9NX7GtpZEErmn7epin4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:31.477007Z"},"content_sha256":"b538a25a0b34492386da827040c16dd700b66d25d32743357339f5d355bedd1a","schema_version":"1.0","event_id":"sha256:b538a25a0b34492386da827040c16dd700b66d25d32743357339f5d355bedd1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q27G5PCTIXQPRD5GHVNDAWULRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MARLIM: Multi-Agent Reinforcement Learning for Inventory Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Antoine Bertoncello, Elie Kadoche, R\\'emi Leluc, S\\'ebastien Gourv\\'enec","submitted_at":"2023-08-03T09:31:45Z","abstract_excerpt":"Maintaining a balance between the supply and demand of products by optimizing replenishment decisions is one of the most important challenges in the supply chain industry. This paper presents a novel reinforcement learning framework called MARLIM, to address the inventory management problem for a single-echelon multi-products supply chain with stochastic demands and lead-times. Within this context, controllers are developed through single or multiple agents in a cooperative setting. Numerical experiments on real data demonstrate the benefits of reinforcement learning methods over traditional b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01649","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/2308.01649/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9MhTkfWJp/3XEfbUhF+snyijgDuNz8HQ6axS/ni8EhHPoHQH38KzT8bKVj3iIOhddkt+pKVwXUc+nkRnV4rzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:31.477490Z"},"content_sha256":"54467d6ec2f864dfc7ef7d387890bd845f16ae2a5eb2a3b0cd88621a924a5554","schema_version":"1.0","event_id":"sha256:54467d6ec2f864dfc7ef7d387890bd845f16ae2a5eb2a3b0cd88621a924a5554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/bundle.json","state_url":"https://pith.science/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:53:31Z","links":{"resolver":"https://pith.science/pith/Q27G5PCTIXQPRD5GHVNDAWULRT","bundle":"https://pith.science/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/bundle.json","state":"https://pith.science/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q27G5PCTIXQPRD5GHVNDAWULRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q27G5PCTIXQPRD5GHVNDAWULRT","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":"8726700ae7697d656b40c860abef51d027310e5a10323521fbba0a26c77add82","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T09:31:45Z","title_canon_sha256":"1991189d461ea9950df1572c5c243ca3879aba7f594c3a4852ac52ead375e1c1"},"schema_version":"1.0","source":{"id":"2308.01649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01649","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01649v1","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01649","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q27G5PCTIXQP","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q27G5PCTIXQPRD5G","created_at":"2026-07-05T06:37:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q27G5PCT","created_at":"2026-07-05T06:37:21Z"}],"graph_snapshots":[{"event_id":"sha256:54467d6ec2f864dfc7ef7d387890bd845f16ae2a5eb2a3b0cd88621a924a5554","target":"graph","created_at":"2026-07-05T06:37:21Z","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/2308.01649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maintaining a balance between the supply and demand of products by optimizing replenishment decisions is one of the most important challenges in the supply chain industry. This paper presents a novel reinforcement learning framework called MARLIM, to address the inventory management problem for a single-echelon multi-products supply chain with stochastic demands and lead-times. Within this context, controllers are developed through single or multiple agents in a cooperative setting. Numerical experiments on real data demonstrate the benefits of reinforcement learning methods over traditional b","authors_text":"Antoine Bertoncello, Elie Kadoche, R\\'emi Leluc, S\\'ebastien Gourv\\'enec","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T09:31:45Z","title":"MARLIM: Multi-Agent Reinforcement Learning for Inventory Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01649","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:b538a25a0b34492386da827040c16dd700b66d25d32743357339f5d355bedd1a","target":"record","created_at":"2026-07-05T06:37:21Z","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":"8726700ae7697d656b40c860abef51d027310e5a10323521fbba0a26c77add82","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T09:31:45Z","title_canon_sha256":"1991189d461ea9950df1572c5c243ca3879aba7f594c3a4852ac52ead375e1c1"},"schema_version":"1.0","source":{"id":"2308.01649","kind":"arxiv","version":1}},"canonical_sha256":"86be6ebc5345e0f88fa63d5a305a8b8ce2f621ffd679f987120ed7c85d5c73c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86be6ebc5345e0f88fa63d5a305a8b8ce2f621ffd679f987120ed7c85d5c73c2","first_computed_at":"2026-07-05T06:37:21.471437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:21.471437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4owLPzGPC25mWPCjOgu6oFdpgd4qANzZlis61LgIGB1FXZUEyjfuzdZC5xMNzxBiAPKAt8fQTYnPPjWqoSdNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:21.471937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b538a25a0b34492386da827040c16dd700b66d25d32743357339f5d355bedd1a","sha256:54467d6ec2f864dfc7ef7d387890bd845f16ae2a5eb2a3b0cd88621a924a5554"],"state_sha256":"7512d542627788e7d724b591032eb9aa6662af7d663b0954de956da6d97f9992"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n6NIYNapxMzN27nvPxewu44UhPS9cAGI9LyzvWjZdllLLy+aZP9p1YrTvQeTPG3IEkgJanKEAK0QRyUq1bx6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:53:31.480782Z","bundle_sha256":"57a3142aab83952fbe2e5c35fb1109fd1a295b3d8767c0a7aaa87eda2a0af43a"}}