{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QCMMR3VMR3EBVVEXEBWFNOVPD","short_pith_number":"pith:5QCMMR3V","schema_version":"1.0","canonical_sha256":"ec04c64775647640d6a4b90362b5d578e46e726852055f24334fdf4c0ab0d19b","source":{"kind":"arxiv","id":"2302.00521","version":2},"attestation_state":"computed","paper":{"title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Arnu Pretorius, Asad Jeewa, Claude Formanek, Jonathan Shock","submitted_at":"2023-02-01T15:41:27Z","abstract_excerpt":"Being able to harness the power of large datasets for developing cooperative multi-agent controllers promises to unlock enormous value for real-world applications. Many important industrial systems are multi-agent in nature and are difficult to model using bespoke simulators. However, in industry, distributed processes can often be recorded during operation, and large quantities of demonstrative data stored. Offline multi-agent reinforcement learning (MARL) provides a promising paradigm for building effective decentralised controllers from such datasets. However, offline MARL is still in its i"},"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":"2302.00521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T15:41:27Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"a48eb75bdd89e8b6ae1436e3bbcf786cdf1e822bc538670387866ee546c25f6c","abstract_canon_sha256":"7b34c8d29a9b00658a436be40d174102d9b69529dee8d319e7ce50c785a453e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:33.979871Z","signature_b64":"mJG4USBDfPzpT0I3td2XwekEr25hk6oBHxn9Ljk7ftSchqZ2pcWkxioGHvl+nd625vypf/G/fw2Wav1LQK6nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec04c64775647640d6a4b90362b5d578e46e726852055f24334fdf4c0ab0d19b","last_reissued_at":"2026-07-05T06:53:33.979374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:33.979374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Arnu Pretorius, Asad Jeewa, Claude Formanek, Jonathan Shock","submitted_at":"2023-02-01T15:41:27Z","abstract_excerpt":"Being able to harness the power of large datasets for developing cooperative multi-agent controllers promises to unlock enormous value for real-world applications. Many important industrial systems are multi-agent in nature and are difficult to model using bespoke simulators. However, in industry, distributed processes can often be recorded during operation, and large quantities of demonstrative data stored. Offline multi-agent reinforcement learning (MARL) provides a promising paradigm for building effective decentralised controllers from such datasets. However, offline MARL is still in its i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00521","kind":"arxiv","version":2},"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/2302.00521/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":"2302.00521","created_at":"2026-07-05T06:53:33.979431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00521v2","created_at":"2026-07-05T06:53:33.979431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00521","created_at":"2026-07-05T06:53:33.979431+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QCMMR3VMR3E","created_at":"2026-07-05T06:53:33.979431+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QCMMR3VMR3EBVVE","created_at":"2026-07-05T06:53:33.979431+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QCMMR3V","created_at":"2026-07-05T06:53:33.979431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02496","citing_title":"Controllable Sim Agents with Behavior Latents","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12200","citing_title":"Implicit Neural Representations of Individual Behavior","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD","json":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD.json","graph_json":"https://pith.science/api/pith-number/5QCMMR3VMR3EBVVEXEBWFNOVPD/graph.json","events_json":"https://pith.science/api/pith-number/5QCMMR3VMR3EBVVEXEBWFNOVPD/events.json","paper":"https://pith.science/paper/5QCMMR3V"},"agent_actions":{"view_html":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD","download_json":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD.json","view_paper":"https://pith.science/paper/5QCMMR3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00521&json=true","fetch_graph":"https://pith.science/api/pith-number/5QCMMR3VMR3EBVVEXEBWFNOVPD/graph.json","fetch_events":"https://pith.science/api/pith-number/5QCMMR3VMR3EBVVEXEBWFNOVPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD/action/storage_attestation","attest_author":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD/action/author_attestation","sign_citation":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD/action/citation_signature","submit_replication":"https://pith.science/pith/5QCMMR3VMR3EBVVEXEBWFNOVPD/action/replication_record"}},"created_at":"2026-07-05T06:53:33.979431+00:00","updated_at":"2026-07-05T06:53:33.979431+00:00"}