{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YKFMNSXKVEACS4IXBXS4IV3IOA","short_pith_number":"pith:YKFMNSXK","canonical_record":{"source":{"id":"2004.13291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7e4ea0ff55937a3e36bacee4e4d7f77b0e505f5aa2d425affc7937d73ccb9bbf","abstract_canon_sha256":"9977192745bada0223a310bd68744eb98f13877a36c9af755902718f5f5a62da"},"schema_version":"1.0"},"canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","source":{"kind":"arxiv","id":"2004.13291","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13291","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13291v1","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13291","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"YKFMNSXKVEAC","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_16","alias_value":"YKFMNSXKVEACS4IX","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_8","alias_value":"YKFMNSXK","created_at":"2026-07-05T00:58:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YKFMNSXKVEACS4IXBXS4IV3IOA","target":"record","payload":{"canonical_record":{"source":{"id":"2004.13291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7e4ea0ff55937a3e36bacee4e4d7f77b0e505f5aa2d425affc7937d73ccb9bbf","abstract_canon_sha256":"9977192745bada0223a310bd68744eb98f13877a36c9af755902718f5f5a62da"},"schema_version":"1.0"},"canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:57.638766Z","signature_b64":"m2T6TGz2EoLbdECQFG69gSL9bLNd0P+y3vSqACzXCNLRgSRqPS1EPv19xBziOc8aJGtUt51HOSufgMU6hn52Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","last_reissued_at":"2026-07-05T00:58:57.638263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:57.638263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.13291","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":"2026-07-05T00:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TF2hxfB4tf4Jbzb5Q12BkaJacVvhN2H8XXJrxYnRQDnhUVUWJuEPzZkPSeOqQjadq9E4ORRuuue0nl1KVvWtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:14:07.825830Z"},"content_sha256":"d14f11364155086344eac664b4b784d9ce9fca6e840d5c3bd020b673ff0e5aa6","schema_version":"1.0","event_id":"sha256:d14f11364155086344eac664b4b784d9ce9fca6e840d5c3bd020b673ff0e5aa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YKFMNSXKVEACS4IXBXS4IV3IOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Andy Nealen, Julian Togelius, Rodrigo Canaan, Stefan Menzel, Xianbo Gao, Youjin Chung","submitted_at":"2020-04-28T04:24:44Z","abstract_excerpt":"Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13291","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/2004.13291/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":"2026-07-05T00:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d7KyXGbdA+s8tybbE6DK9fDfkZhXM8LpZmN9/7EVagf9UY0DJUBLBgrQkfHGtrjA2xU0SZY6GN1Df1SLEZMaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:14:07.826208Z"},"content_sha256":"2dd7f39bdc8784a63976f48ebb9742a4380199f320a298b861f47801351d9518","schema_version":"1.0","event_id":"sha256:2dd7f39bdc8784a63976f48ebb9742a4380199f320a298b861f47801351d9518"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/bundle.json","state_url":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/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":"2026-08-13T10:14:07Z","links":{"resolver":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA","bundle":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/bundle.json","state":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YKFMNSXKVEACS4IXBXS4IV3IOA","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":"9977192745bada0223a310bd68744eb98f13877a36c9af755902718f5f5a62da","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","title_canon_sha256":"7e4ea0ff55937a3e36bacee4e4d7f77b0e505f5aa2d425affc7937d73ccb9bbf"},"schema_version":"1.0","source":{"id":"2004.13291","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13291","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13291v1","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13291","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"YKFMNSXKVEAC","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_16","alias_value":"YKFMNSXKVEACS4IX","created_at":"2026-07-05T00:58:57Z"},{"alias_kind":"pith_short_8","alias_value":"YKFMNSXK","created_at":"2026-07-05T00:58:57Z"}],"graph_snapshots":[{"event_id":"sha256:2dd7f39bdc8784a63976f48ebb9742a4380199f320a298b861f47801351d9518","target":"graph","created_at":"2026-07-05T00:58:57Z","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/2004.13291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training a","authors_text":"Andy Nealen, Julian Togelius, Rodrigo Canaan, Stefan Menzel, Xianbo Gao, Youjin Chung","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","title":"Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13291","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:d14f11364155086344eac664b4b784d9ce9fca6e840d5c3bd020b673ff0e5aa6","target":"record","created_at":"2026-07-05T00:58:57Z","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":"9977192745bada0223a310bd68744eb98f13877a36c9af755902718f5f5a62da","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","title_canon_sha256":"7e4ea0ff55937a3e36bacee4e4d7f77b0e505f5aa2d425affc7937d73ccb9bbf"},"schema_version":"1.0","source":{"id":"2004.13291","kind":"arxiv","version":1}},"canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","first_computed_at":"2026-07-05T00:58:57.638263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:57.638263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m2T6TGz2EoLbdECQFG69gSL9bLNd0P+y3vSqACzXCNLRgSRqPS1EPv19xBziOc8aJGtUt51HOSufgMU6hn52Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:57.638766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13291","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d14f11364155086344eac664b4b784d9ce9fca6e840d5c3bd020b673ff0e5aa6","sha256:2dd7f39bdc8784a63976f48ebb9742a4380199f320a298b861f47801351d9518"],"state_sha256":"ce59fdfcd3b359ac2de94fe1860ddbbc518428a1f934072fa197b6ce35828cbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjT7kZNRQQkjtVB9uCog1v0q7NYSf28YcbTG5/vCrPKX8M9z12gMmHTegPvImZBytT15QGdnoW2bxsXtdl8PCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T10:14:07.829071Z","bundle_sha256":"af07755485257b7bfc6ae2b29075aabaa159a878350b6459141f4a20101f5389"}}