{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FPAYENCJCUQKJ5LIOEBXQLOIOC","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":"a17d57024e559e959cf0b5583efa0d4aa0c37165447e66696a6cc68de35cc562","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-17T22:25:15Z","title_canon_sha256":"b9f4c71fe04000a1b6ece991aa5c105fbbc688f62aa7c919d72166d7be1156e7"},"schema_version":"1.0","source":{"id":"2503.14555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14555","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14555v1","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14555","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"FPAYENCJCUQK","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"FPAYENCJCUQKJ5LI","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"FPAYENCJ","created_at":"2026-07-05T10:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:8675ee48381bbe31b1d24f01b165092092f71bdc45223309038e6f996dd70d27","target":"graph","created_at":"2026-07-05T10:34:19Z","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/2503.14555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting than the one they have been trained on, and struggle to successfully cooperate with unfamiliar collaborators. This is particularly visible in the Hanabi benchmark, a popular 2-to-5 player cooperative card-game which requires complex reasoning and precise assistance to other agents. Current MARL agents for Hanabi can only learn one specific game-setting (e.g., 2-player games), and play with the same","authors_text":"Arjun V Sudhakar, Hadi Nekoei, Janarthanan Rajendran, Mathieu Reymond, Miao Liu, Sarath Chandar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-17T22:25:15Z","title":"A Generalist Hanabi Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14555","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":"sha256:345ccb5c7a42f6f4295d24fe2ba2c055ed84462ff02de40aa4ab718634999e06","target":"record","created_at":"2026-07-05T10:34:19Z","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":"a17d57024e559e959cf0b5583efa0d4aa0c37165447e66696a6cc68de35cc562","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-17T22:25:15Z","title_canon_sha256":"b9f4c71fe04000a1b6ece991aa5c105fbbc688f62aa7c919d72166d7be1156e7"},"schema_version":"1.0","source":{"id":"2503.14555","kind":"arxiv","version":1}},"canonical_sha256":"2bc18234491520a4f5687103782dc870bfa38ae19de24c7533aafe7b17a558cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc18234491520a4f5687103782dc870bfa38ae19de24c7533aafe7b17a558cb","first_computed_at":"2026-07-05T10:34:19.822896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:19.822896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B+JWDKKtZgjvdA6xNKZi6MqIlfxyMHv8Q7FS9jjefY+cCkkYo4QqJRu8rRujThzT6P85eMUH85Ewmjr3g/DFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:19.823406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:345ccb5c7a42f6f4295d24fe2ba2c055ed84462ff02de40aa4ab718634999e06","sha256:8675ee48381bbe31b1d24f01b165092092f71bdc45223309038e6f996dd70d27"],"state_sha256":"b48722e5ada4169efc044acc0c97db72614dfd65b2a6b368a0b1ecc163dd80ba"}