{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NLFBT3HI37VWH2WNAO4QZW7XZ5","short_pith_number":"pith:NLFBT3HI","canonical_record":{"source":{"id":"2412.07639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T16:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60f8df61efec4f5ee4fb7aaa59b8ee396884b540405658ccc6c19a63caee5aa3","abstract_canon_sha256":"48c8cf82a58bdcecb4526ddeb14085720d823bc9a541d1844c858c3dc9d7c271"},"schema_version":"1.0"},"canonical_sha256":"6aca19ece8dfeb63eacd03b90cdbf7cf5194a6b147713c4fe0d7b202a4914f3b","source":{"kind":"arxiv","id":"2412.07639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07639","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07639v2","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07639","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"NLFBT3HI37VW","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"NLFBT3HI37VWH2WN","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"NLFBT3HI","created_at":"2026-07-05T09:50:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NLFBT3HI37VWH2WNAO4QZW7XZ5","target":"record","payload":{"canonical_record":{"source":{"id":"2412.07639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T16:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60f8df61efec4f5ee4fb7aaa59b8ee396884b540405658ccc6c19a63caee5aa3","abstract_canon_sha256":"48c8cf82a58bdcecb4526ddeb14085720d823bc9a541d1844c858c3dc9d7c271"},"schema_version":"1.0"},"canonical_sha256":"6aca19ece8dfeb63eacd03b90cdbf7cf5194a6b147713c4fe0d7b202a4914f3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:55.249584Z","signature_b64":"2p+AEA5Q3rJ3rRHgNdg4bBoISfK8tiiM4mK8Ov7JxXKL85YLqOjNqxHLOQgKrLTdxQuJC51YLDqkdh27wM8oAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aca19ece8dfeb63eacd03b90cdbf7cf5194a6b147713c4fe0d7b202a4914f3b","last_reissued_at":"2026-07-05T09:50:55.249073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:55.249073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.07639","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":"2026-07-05T09:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QuhHxalF46qxgXdtRqY8Cop25/5wboAiXbMQvZHX379QcYfgU2v+QUtK1VRuYxLW2zwanwOIGoi4LJnR0bNPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:11:59.615735Z"},"content_sha256":"ff876c45f2d576185762dd2a8e3f3c54142cb985fb140f0107e72107cf9727b9","schema_version":"1.0","event_id":"sha256:ff876c45f2d576185762dd2a8e3f3c54142cb985fb140f0107e72107cf9727b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NLFBT3HI37VWH2WNAO4QZW7XZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chao Yu, Donghui Li, Qian Lin, Xiawei Wu, Xuetao Ding, Yile Liang, Zongkai Liu","submitted_at":"2024-12-10T16:19:08Z","abstract_excerpt":"Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, multi-agent setting involves a large joint state-action space and coupled behaviors of multiple agents, which bring extra complexity to offline policy optimization. In this work, we revisit the existing offline MARL methods and show that in certain scenarios they can be problematic, leading to uncoordinated behaviors and out-of-distribution (OOD) joint actions. To address these issues, we propose a new offline MARL al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07639","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/2412.07639/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":"2026-07-05T09:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fg7lUGejP37OJvU3PwWlTXWtH5LFjrZbgt5Va/1E2Hn83LzsJeSS3g7UBOgmTncA2qjBGtjdJDfNkD64qIBFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:11:59.616749Z"},"content_sha256":"5080c51d66ef10e98a35b48599bff6f174da0759a45fb8ad1f28bc7c6a70494a","schema_version":"1.0","event_id":"sha256:5080c51d66ef10e98a35b48599bff6f174da0759a45fb8ad1f28bc7c6a70494a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/bundle.json","state_url":"https://pith.science/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/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":"2026-08-06T03:11:59Z","links":{"resolver":"https://pith.science/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5","bundle":"https://pith.science/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/bundle.json","state":"https://pith.science/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLFBT3HI37VWH2WNAO4QZW7XZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NLFBT3HI37VWH2WNAO4QZW7XZ5","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":"48c8cf82a58bdcecb4526ddeb14085720d823bc9a541d1844c858c3dc9d7c271","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T16:19:08Z","title_canon_sha256":"60f8df61efec4f5ee4fb7aaa59b8ee396884b540405658ccc6c19a63caee5aa3"},"schema_version":"1.0","source":{"id":"2412.07639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07639","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07639v2","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07639","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"NLFBT3HI37VW","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"NLFBT3HI37VWH2WN","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"NLFBT3HI","created_at":"2026-07-05T09:50:55Z"}],"graph_snapshots":[{"event_id":"sha256:5080c51d66ef10e98a35b48599bff6f174da0759a45fb8ad1f28bc7c6a70494a","target":"graph","created_at":"2026-07-05T09:50:55Z","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/2412.07639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, multi-agent setting involves a large joint state-action space and coupled behaviors of multiple agents, which bring extra complexity to offline policy optimization. In this work, we revisit the existing offline MARL methods and show that in certain scenarios they can be problematic, leading to uncoordinated behaviors and out-of-distribution (OOD) joint actions. To address these issues, we propose a new offline MARL al","authors_text":"Chao Yu, Donghui Li, Qian Lin, Xiawei Wu, Xuetao Ding, Yile Liang, Zongkai Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T16:19:08Z","title":"Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07639","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:ff876c45f2d576185762dd2a8e3f3c54142cb985fb140f0107e72107cf9727b9","target":"record","created_at":"2026-07-05T09:50:55Z","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":"48c8cf82a58bdcecb4526ddeb14085720d823bc9a541d1844c858c3dc9d7c271","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T16:19:08Z","title_canon_sha256":"60f8df61efec4f5ee4fb7aaa59b8ee396884b540405658ccc6c19a63caee5aa3"},"schema_version":"1.0","source":{"id":"2412.07639","kind":"arxiv","version":2}},"canonical_sha256":"6aca19ece8dfeb63eacd03b90cdbf7cf5194a6b147713c4fe0d7b202a4914f3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aca19ece8dfeb63eacd03b90cdbf7cf5194a6b147713c4fe0d7b202a4914f3b","first_computed_at":"2026-07-05T09:50:55.249073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:55.249073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2p+AEA5Q3rJ3rRHgNdg4bBoISfK8tiiM4mK8Ov7JxXKL85YLqOjNqxHLOQgKrLTdxQuJC51YLDqkdh27wM8oAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:55.249584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff876c45f2d576185762dd2a8e3f3c54142cb985fb140f0107e72107cf9727b9","sha256:5080c51d66ef10e98a35b48599bff6f174da0759a45fb8ad1f28bc7c6a70494a"],"state_sha256":"ffd56952a6ad1ca612913dca33190910243d7c08621607a2d1a0aa71cfbabb54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e42jF5n5CHyFP+fR7GyursnmLU3aIM/5vNdYTMQEm2i4wR7TEdpEWSF39rgK/YAg3A29utIwFzagHabpkbvUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:11:59.623457Z","bundle_sha256":"8638ec77c71eeec3a86781e05364d7ab8ede0ac8f76d36a62234b56b00c96613"}}