{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FPAYENCJCUQKJ5LIOEBXQLOIOC","short_pith_number":"pith:FPAYENCJ","canonical_record":{"source":{"id":"2503.14555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-17T22:25:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9f4c71fe04000a1b6ece991aa5c105fbbc688f62aa7c919d72166d7be1156e7","abstract_canon_sha256":"a17d57024e559e959cf0b5583efa0d4aa0c37165447e66696a6cc68de35cc562"},"schema_version":"1.0"},"canonical_sha256":"2bc18234491520a4f5687103782dc870bfa38ae19de24c7533aafe7b17a558cb","source":{"kind":"arxiv","id":"2503.14555","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FPAYENCJCUQKJ5LIOEBXQLOIOC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-17T22:25:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9f4c71fe04000a1b6ece991aa5c105fbbc688f62aa7c919d72166d7be1156e7","abstract_canon_sha256":"a17d57024e559e959cf0b5583efa0d4aa0c37165447e66696a6cc68de35cc562"},"schema_version":"1.0"},"canonical_sha256":"2bc18234491520a4f5687103782dc870bfa38ae19de24c7533aafe7b17a558cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:19.823406Z","signature_b64":"B+JWDKKtZgjvdA6xNKZi6MqIlfxyMHv8Q7FS9jjefY+cCkkYo4QqJRu8rRujThzT6P85eMUH85Ewmjr3g/DFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bc18234491520a4f5687103782dc870bfa38ae19de24c7533aafe7b17a558cb","last_reissued_at":"2026-07-05T10:34:19.822896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:19.822896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14555","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":"2026-07-05T10:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHG+faGI5ahGOO4Tcw7U3p57/d3Ci+26Lqt9CeOlcZnBnWHbMIzPoQ38FxZz6aZIaD7QPHeO9t3ljP46BE9wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:12:01.651848Z"},"content_sha256":"345ccb5c7a42f6f4295d24fe2ba2c055ed84462ff02de40aa4ab718634999e06","schema_version":"1.0","event_id":"sha256:345ccb5c7a42f6f4295d24fe2ba2c055ed84462ff02de40aa4ab718634999e06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FPAYENCJCUQKJ5LIOEBXQLOIOC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Generalist Hanabi Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Arjun V Sudhakar, Hadi Nekoei, Janarthanan Rajendran, Mathieu Reymond, Miao Liu, Sarath Chandar","submitted_at":"2025-03-17T22:25:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14555","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/2503.14555/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":"2026-07-05T10:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHTM6zLdX6Dsy32U/FqZhI3DySytwTyx0QVV+uMDppog+A4hLwlMwZPQ+YZD1i7Lv5CVQ3E8shfoVza3XOeqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:12:01.652222Z"},"content_sha256":"8675ee48381bbe31b1d24f01b165092092f71bdc45223309038e6f996dd70d27","schema_version":"1.0","event_id":"sha256:8675ee48381bbe31b1d24f01b165092092f71bdc45223309038e6f996dd70d27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/bundle.json","state_url":"https://pith.science/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/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":"2026-07-09T04:12:01Z","links":{"resolver":"https://pith.science/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC","bundle":"https://pith.science/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/bundle.json","state":"https://pith.science/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPAYENCJCUQKJ5LIOEBXQLOIOC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"daxXSncOxArLkAMrssB/++UcHOjhoc8fiVb5SDvASQhi9j9i0cbi+6V1ltcKCnlPN40YZwiuRocNBRxeMVVQDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:12:01.654205Z","bundle_sha256":"edab262730563b4d96a33157395d7637e10b59510b9e0632f15528daa21496ca"}}