{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3BXX347UIAB7GXF22PJGKEMH4L","short_pith_number":"pith:3BXX347U","canonical_record":{"source":{"id":"2311.02194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T18:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4467b28f3de03136893acf2d6f377846e52e9874f5d81af27705dcbcd6f9320e","abstract_canon_sha256":"2928c29725d7be0ff430864493c3a612bbbcae406b4f9eab6875d08d2b1641ee"},"schema_version":"1.0"},"canonical_sha256":"d86f7df3f44003f35cbad3d2651187e2cb858632f9c0206f3d13febb257e6a38","source":{"kind":"arxiv","id":"2311.02194","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02194","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02194v1","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02194","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"3BXX347UIAB7","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"3BXX347UIAB7GXF2","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"3BXX347U","created_at":"2026-07-05T07:09:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3BXX347UIAB7GXF22PJGKEMH4L","target":"record","payload":{"canonical_record":{"source":{"id":"2311.02194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T18:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4467b28f3de03136893acf2d6f377846e52e9874f5d81af27705dcbcd6f9320e","abstract_canon_sha256":"2928c29725d7be0ff430864493c3a612bbbcae406b4f9eab6875d08d2b1641ee"},"schema_version":"1.0"},"canonical_sha256":"d86f7df3f44003f35cbad3d2651187e2cb858632f9c0206f3d13febb257e6a38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:06.770814Z","signature_b64":"hfgiKg3UOSTwzG+5K8tiB0fk+W/3E4vynLB6AN3uLU9ap/0yeLJPtAO4tP4UernDN1GpMPfBOln5gq7Q/nevAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d86f7df3f44003f35cbad3d2651187e2cb858632f9c0206f3d13febb257e6a38","last_reissued_at":"2026-07-05T07:09:06.770411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:06.770411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.02194","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":"2026-07-05T07:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqNrV4a/Jp9aLrcaAtmbXY9rlkJcTWAABFhelXEI7KbgvMgxbUSCGHZFK+/qmiYCDjiQvjQaZIdZtCOoQwZ0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:09:32.130834Z"},"content_sha256":"07fb42ffa06c4edeeaee0340f6e5e7c816e452332f95538feab77f07dffb89d6","schema_version":"1.0","event_id":"sha256:07fb42ffa06c4edeeaee0340f6e5e7c816e452332f95538feab77f07dffb89d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3BXX347UIAB7GXF22PJGKEMH4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daiki E. Matsunaga, Jaeseok Yoon, Jongmin Lee, Kee-Eung Kim, Pieter Abbeel, Stefanos Leonardos","submitted_at":"2023-11-03T18:56:48Z","abstract_excerpt":"One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is often addressed by avoiding out-of-distribution (OOD) actions during policy improvement as their presence can lead to substantial performance degradation. This challenge is amplified in the offline Multi-Agent RL (MARL) setting since the joint action space grows exponentially with the number of agents. To avoid this curse of dimensionality, existing MARL methods adopt either value decomposition methods or fully decent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02194","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/2311.02194/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":"2026-07-05T07:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+fo8wjQos5OJd903ifunJLC1vrAjV2ecHqq8bG6lPE6Q6jbKoKO9GidCqcn6CsWNkOeBTMMbpPSsRFejq2ECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:09:32.131370Z"},"content_sha256":"ffd33f1e07a555e5466ad953927e48bf3617821f536c27f17a74b942fb650b57","schema_version":"1.0","event_id":"sha256:ffd33f1e07a555e5466ad953927e48bf3617821f536c27f17a74b942fb650b57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BXX347UIAB7GXF22PJGKEMH4L/bundle.json","state_url":"https://pith.science/pith/3BXX347UIAB7GXF22PJGKEMH4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BXX347UIAB7GXF22PJGKEMH4L/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":"2026-08-18T16:09:32Z","links":{"resolver":"https://pith.science/pith/3BXX347UIAB7GXF22PJGKEMH4L","bundle":"https://pith.science/pith/3BXX347UIAB7GXF22PJGKEMH4L/bundle.json","state":"https://pith.science/pith/3BXX347UIAB7GXF22PJGKEMH4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BXX347UIAB7GXF22PJGKEMH4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3BXX347UIAB7GXF22PJGKEMH4L","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":"2928c29725d7be0ff430864493c3a612bbbcae406b4f9eab6875d08d2b1641ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T18:56:48Z","title_canon_sha256":"4467b28f3de03136893acf2d6f377846e52e9874f5d81af27705dcbcd6f9320e"},"schema_version":"1.0","source":{"id":"2311.02194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02194","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02194v1","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02194","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"3BXX347UIAB7","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"3BXX347UIAB7GXF2","created_at":"2026-07-05T07:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"3BXX347U","created_at":"2026-07-05T07:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:ffd33f1e07a555e5466ad953927e48bf3617821f536c27f17a74b942fb650b57","target":"graph","created_at":"2026-07-05T07:09:06Z","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/2311.02194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is often addressed by avoiding out-of-distribution (OOD) actions during policy improvement as their presence can lead to substantial performance degradation. This challenge is amplified in the offline Multi-Agent RL (MARL) setting since the joint action space grows exponentially with the number of agents. To avoid this curse of dimensionality, existing MARL methods adopt either value decomposition methods or fully decent","authors_text":"Daiki E. Matsunaga, Jaeseok Yoon, Jongmin Lee, Kee-Eung Kim, Pieter Abbeel, Stefanos Leonardos","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T18:56:48Z","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02194","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":"sha256:07fb42ffa06c4edeeaee0340f6e5e7c816e452332f95538feab77f07dffb89d6","target":"record","created_at":"2026-07-05T07:09:06Z","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":"2928c29725d7be0ff430864493c3a612bbbcae406b4f9eab6875d08d2b1641ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T18:56:48Z","title_canon_sha256":"4467b28f3de03136893acf2d6f377846e52e9874f5d81af27705dcbcd6f9320e"},"schema_version":"1.0","source":{"id":"2311.02194","kind":"arxiv","version":1}},"canonical_sha256":"d86f7df3f44003f35cbad3d2651187e2cb858632f9c0206f3d13febb257e6a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d86f7df3f44003f35cbad3d2651187e2cb858632f9c0206f3d13febb257e6a38","first_computed_at":"2026-07-05T07:09:06.770411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:06.770411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hfgiKg3UOSTwzG+5K8tiB0fk+W/3E4vynLB6AN3uLU9ap/0yeLJPtAO4tP4UernDN1GpMPfBOln5gq7Q/nevAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:06.770814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07fb42ffa06c4edeeaee0340f6e5e7c816e452332f95538feab77f07dffb89d6","sha256:ffd33f1e07a555e5466ad953927e48bf3617821f536c27f17a74b942fb650b57"],"state_sha256":"12028584a95a9d179b6639dc7f4d1b6c7a4e36b2e03311aa7c5431328b41590b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCiaR6Jd/kZvOnlj6eTVYoWcjzn/Ar0c9bm3+yEDGI6eDgWr8bxis3FZv+4z4TubMDpMxD5BNdnbTLyTIN8dDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:09:32.136076Z","bundle_sha256":"81d91d0dcd11fd463a0d1c2a0de22cd0defc2baf411662d6e7522ee990f35029"}}