{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DEM7HG2ULU5SA35O6BGLGXIYXO","short_pith_number":"pith:DEM7HG2U","canonical_record":{"source":{"id":"2305.17198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T18:43:16Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"a4d4e1af9b1086ee8ad4c8f4b43a4e648823d3b3e667fa368291d5dd886f6cc8","abstract_canon_sha256":"3a6482b1e929aea5ef95a165b5948276ae119902ed13aeb5b4eb9a090c6cd248"},"schema_version":"1.0"},"canonical_sha256":"1919f39b545d3b206faef04cb35d18bbb489a77c60dc390e0c0cebed5ad32506","source":{"kind":"arxiv","id":"2305.17198","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17198","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17198v2","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17198","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_12","alias_value":"DEM7HG2ULU5S","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_16","alias_value":"DEM7HG2ULU5SA35O","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_8","alias_value":"DEM7HG2U","created_at":"2026-07-05T07:34:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DEM7HG2ULU5SA35O6BGLGXIYXO","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T18:43:16Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"a4d4e1af9b1086ee8ad4c8f4b43a4e648823d3b3e667fa368291d5dd886f6cc8","abstract_canon_sha256":"3a6482b1e929aea5ef95a165b5948276ae119902ed13aeb5b4eb9a090c6cd248"},"schema_version":"1.0"},"canonical_sha256":"1919f39b545d3b206faef04cb35d18bbb489a77c60dc390e0c0cebed5ad32506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:48.345349Z","signature_b64":"2IgzY1JYqCBnyl27GY3x30hUyeYNVCi1CP5pZzXsQtGNK7y60rK4HZ/FkcxtJ+zxNtMDmhbF9fVXlQs51npRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1919f39b545d3b206faef04cb35d18bbb489a77c60dc390e0c0cebed5ad32506","last_reissued_at":"2026-07-05T07:34:48.344845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:48.344845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17198","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:34:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTShD4RXtxije8BVl7M+KO8juGZ0bZiiIYCwguWq+pepRa439yB/QWnd7d/57VoMGntyxyn4Y6ks5tV2VyT7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:32:40.929060Z"},"content_sha256":"949eaecea3e42107c24f3728a474fc68645062ac2cc3d388b3851d70a55c184e","schema_version":"1.0","event_id":"sha256:949eaecea3e42107c24f3728a474fc68645062ac2cc3d388b3851d70a55c184e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DEM7HG2ULU5SA35O6BGLGXIYXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Derek Nowrouzezahrai, Jakob Foerster, Paul Barde","submitted_at":"2023-05-26T18:43:16Z","abstract_excerpt":"Training multiple agents to coordinate is an essential problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinforcement Learning (MARL) methods are online and thus impractical for real-world applications in which collecting new interactions is costly or dangerous. While these algorithms should leverage offline data when available, doing so gives rise to what we call the offline coordination problem. Specifically, we identify and formalize the strategy agreement (SA) and the strategy fine-tuning (SFT) coordination challenges, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17198","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/2305.17198/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":"2026-07-05T07:34:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a5YTcH1A/fp2UMAHXL+PaWfO3Elnv6B4GJay3e+apUfiGL2Uc4kp69jr/UPry4sRIRI8Ae9BlSWpY1lArSyPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:32:40.929967Z"},"content_sha256":"114bce73e45bd8f5c2cbd620b0051cafbcd42bc9dcee25d00cb27068b665186d","schema_version":"1.0","event_id":"sha256:114bce73e45bd8f5c2cbd620b0051cafbcd42bc9dcee25d00cb27068b665186d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/bundle.json","state_url":"https://pith.science/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/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":"2026-08-11T03:32:40Z","links":{"resolver":"https://pith.science/pith/DEM7HG2ULU5SA35O6BGLGXIYXO","bundle":"https://pith.science/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/bundle.json","state":"https://pith.science/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEM7HG2ULU5SA35O6BGLGXIYXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DEM7HG2ULU5SA35O6BGLGXIYXO","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":"3a6482b1e929aea5ef95a165b5948276ae119902ed13aeb5b4eb9a090c6cd248","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T18:43:16Z","title_canon_sha256":"a4d4e1af9b1086ee8ad4c8f4b43a4e648823d3b3e667fa368291d5dd886f6cc8"},"schema_version":"1.0","source":{"id":"2305.17198","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17198","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17198v2","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17198","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_12","alias_value":"DEM7HG2ULU5S","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_16","alias_value":"DEM7HG2ULU5SA35O","created_at":"2026-07-05T07:34:48Z"},{"alias_kind":"pith_short_8","alias_value":"DEM7HG2U","created_at":"2026-07-05T07:34:48Z"}],"graph_snapshots":[{"event_id":"sha256:114bce73e45bd8f5c2cbd620b0051cafbcd42bc9dcee25d00cb27068b665186d","target":"graph","created_at":"2026-07-05T07:34:48Z","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/2305.17198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training multiple agents to coordinate is an essential problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinforcement Learning (MARL) methods are online and thus impractical for real-world applications in which collecting new interactions is costly or dangerous. While these algorithms should leverage offline data when available, doing so gives rise to what we call the offline coordination problem. Specifically, we identify and formalize the strategy agreement (SA) and the strategy fine-tuning (SFT) coordination challenges, t","authors_text":"Amy Zhang, Derek Nowrouzezahrai, Jakob Foerster, Paul Barde","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T18:43:16Z","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17198","kind":"arxiv","version":2},"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":"sha256:949eaecea3e42107c24f3728a474fc68645062ac2cc3d388b3851d70a55c184e","target":"record","created_at":"2026-07-05T07:34:48Z","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":"3a6482b1e929aea5ef95a165b5948276ae119902ed13aeb5b4eb9a090c6cd248","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T18:43:16Z","title_canon_sha256":"a4d4e1af9b1086ee8ad4c8f4b43a4e648823d3b3e667fa368291d5dd886f6cc8"},"schema_version":"1.0","source":{"id":"2305.17198","kind":"arxiv","version":2}},"canonical_sha256":"1919f39b545d3b206faef04cb35d18bbb489a77c60dc390e0c0cebed5ad32506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1919f39b545d3b206faef04cb35d18bbb489a77c60dc390e0c0cebed5ad32506","first_computed_at":"2026-07-05T07:34:48.344845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:48.344845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2IgzY1JYqCBnyl27GY3x30hUyeYNVCi1CP5pZzXsQtGNK7y60rK4HZ/FkcxtJ+zxNtMDmhbF9fVXlQs51npRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:48.345349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17198","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:949eaecea3e42107c24f3728a474fc68645062ac2cc3d388b3851d70a55c184e","sha256:114bce73e45bd8f5c2cbd620b0051cafbcd42bc9dcee25d00cb27068b665186d"],"state_sha256":"6ba7e2be3ecb851d6be216e9f640e2132892e208724e5adeb1ad89919aee1a00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JKeN24wUwimlOM5nCXmzsDwPVljgwJBMI09kq+MbFFwbmKBxszRJB0N1MJKg2nwe6N2teQ0o0GwU01RzmTetAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:32:40.936959Z","bundle_sha256":"f967cc5df74c7a92d4b7d226f3e61d902cb4f5cd701081ea337a5cf541b19176"}}