{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DT3MD2SSR4KZAWS6LGEDFQTFKI","short_pith_number":"pith:DT3MD2SS","canonical_record":{"source":{"id":"2112.02845","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T08:11:05Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8c7c87536ac7e7faf599d34331b9e8bf7ff69dc2c9319b4e3725ed6948654d68","abstract_canon_sha256":"117c7fdf29c4ef493137b11586a48e05fe1749ee173b0ffaad8c94264d2697e8"},"schema_version":"1.0"},"canonical_sha256":"1cf6c1ea528f15905a5e598832c265521828b48f6621b664de4511afd529dcc6","source":{"kind":"arxiv","id":"2112.02845","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02845","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02845v3","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02845","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"DT3MD2SSR4KZ","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"DT3MD2SSR4KZAWS6","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"DT3MD2SS","created_at":"2026-07-05T04:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DT3MD2SSR4KZAWS6LGEDFQTFKI","target":"record","payload":{"canonical_record":{"source":{"id":"2112.02845","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T08:11:05Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8c7c87536ac7e7faf599d34331b9e8bf7ff69dc2c9319b4e3725ed6948654d68","abstract_canon_sha256":"117c7fdf29c4ef493137b11586a48e05fe1749ee173b0ffaad8c94264d2697e8"},"schema_version":"1.0"},"canonical_sha256":"1cf6c1ea528f15905a5e598832c265521828b48f6621b664de4511afd529dcc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:39.875479Z","signature_b64":"uV+bqNyRSSK2zLOSpvUzunyJ4y0THL0ouo9j5S4iJDRd0SNk+5J8pExNw1T4Dv6YFTFFHg7uNNehByPlGP7WCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf6c1ea528f15905a5e598832c265521828b48f6621b664de4511afd529dcc6","last_reissued_at":"2026-07-05T04:30:39.875059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:39.875059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.02845","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkcW4Do1+5HZnu7LIERRFVt3aN6HOjQY/fAYRtZdoG75KcWWtLdb6UwzVZf+yfXQK5BFPkz7AN8/WAJZp6PGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:43:36.784262Z"},"content_sha256":"28977f6430f5282e3e1369a1c2b049a9e2e4eed70ecf2757629a7464cc698a65","schema_version":"1.0","event_id":"sha256:28977f6430f5282e3e1369a1c2b049a9e2e4eed70ecf2757629a7464cc698a65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DT3MD2SSR4KZAWS6LGEDFQTFKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo Xu, Chenyang Le, Haifeng Zhang, Jun Wang, Linghui Meng, Muning Wen, Weinan Zhang, Xiyun Li, Yaodong Yang, Ying Wen","submitted_at":"2021-12-06T08:11:05Z","abstract_excerpt":"Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also desirable for multi-agent reinforcement learning (MARL) tasks, given the increased interactions among agents and with the enviroment. Yet, in MARL, the paradigm of offline pre-training with online fine-tuning has not been studied, nor datasets or benchmarks for offline MARL research are available. In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Deci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02845","kind":"arxiv","version":3},"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/2112.02845/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":"2026-07-05T04:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJjrV24ec1fDP6RsKBJslpoOTyNOBGTsAYObU2Nh3pCvG87UJKskCHDec57nOy/whcAlQB4q/3aeoaD+0DvdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:43:36.784660Z"},"content_sha256":"5866db31136b78df6199ad7571fa2daaf1502f0b6a50f3c5727463828687b69c","schema_version":"1.0","event_id":"sha256:5866db31136b78df6199ad7571fa2daaf1502f0b6a50f3c5727463828687b69c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/bundle.json","state_url":"https://pith.science/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/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":"2026-07-05T15:43:36Z","links":{"resolver":"https://pith.science/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI","bundle":"https://pith.science/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/bundle.json","state":"https://pith.science/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DT3MD2SSR4KZAWS6LGEDFQTFKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DT3MD2SSR4KZAWS6LGEDFQTFKI","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":"117c7fdf29c4ef493137b11586a48e05fe1749ee173b0ffaad8c94264d2697e8","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T08:11:05Z","title_canon_sha256":"8c7c87536ac7e7faf599d34331b9e8bf7ff69dc2c9319b4e3725ed6948654d68"},"schema_version":"1.0","source":{"id":"2112.02845","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02845","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02845v3","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02845","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"DT3MD2SSR4KZ","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"DT3MD2SSR4KZAWS6","created_at":"2026-07-05T04:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"DT3MD2SS","created_at":"2026-07-05T04:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:5866db31136b78df6199ad7571fa2daaf1502f0b6a50f3c5727463828687b69c","target":"graph","created_at":"2026-07-05T04:30:39Z","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/2112.02845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also desirable for multi-agent reinforcement learning (MARL) tasks, given the increased interactions among agents and with the enviroment. Yet, in MARL, the paradigm of offline pre-training with online fine-tuning has not been studied, nor datasets or benchmarks for offline MARL research are available. In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Deci","authors_text":"Bo Xu, Chenyang Le, Haifeng Zhang, Jun Wang, Linghui Meng, Muning Wen, Weinan Zhang, Xiyun Li, Yaodong Yang, Ying Wen","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T08:11:05Z","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02845","kind":"arxiv","version":3},"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":"sha256:28977f6430f5282e3e1369a1c2b049a9e2e4eed70ecf2757629a7464cc698a65","target":"record","created_at":"2026-07-05T04:30:39Z","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":"117c7fdf29c4ef493137b11586a48e05fe1749ee173b0ffaad8c94264d2697e8","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T08:11:05Z","title_canon_sha256":"8c7c87536ac7e7faf599d34331b9e8bf7ff69dc2c9319b4e3725ed6948654d68"},"schema_version":"1.0","source":{"id":"2112.02845","kind":"arxiv","version":3}},"canonical_sha256":"1cf6c1ea528f15905a5e598832c265521828b48f6621b664de4511afd529dcc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cf6c1ea528f15905a5e598832c265521828b48f6621b664de4511afd529dcc6","first_computed_at":"2026-07-05T04:30:39.875059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:39.875059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uV+bqNyRSSK2zLOSpvUzunyJ4y0THL0ouo9j5S4iJDRd0SNk+5J8pExNw1T4Dv6YFTFFHg7uNNehByPlGP7WCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:39.875479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02845","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28977f6430f5282e3e1369a1c2b049a9e2e4eed70ecf2757629a7464cc698a65","sha256:5866db31136b78df6199ad7571fa2daaf1502f0b6a50f3c5727463828687b69c"],"state_sha256":"9dbe8a43c8b81154a693acf175d3ea7eb4ef1beed16dee95c952ac237ee9f60e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"No6rVQFm0MAPzwiCWTB4cT7BoMclmE7p9qEH3F9wKHrLfumwT36rutiKpbrGJteytSOgIWP5Wf9mfE6aH9PBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:43:36.786670Z","bundle_sha256":"c23b072aa8d2818e42bfd4fc508a602d77b6dcd7bcd6c37fcfc867562942f33a"}}