{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ESWUNZE7OHLKM7DJUJXQL6B6QD","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":"e0b50c9a6e439833c7ccd335083538758622792853b57d8b9037f3f1ad8ac0d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-01-22T20:56:42Z","title_canon_sha256":"7bdfd4ae1217c651276a02038d7dc478b84481a111d483c6ceb4fd207bd5e739"},"schema_version":"1.0","source":{"id":"2101.09328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09328","created_at":"2026-07-05T02:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09328v1","created_at":"2026-07-05T02:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09328","created_at":"2026-07-05T02:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"ESWUNZE7OHLK","created_at":"2026-07-05T02:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"ESWUNZE7OHLKM7DJ","created_at":"2026-07-05T02:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"ESWUNZE7","created_at":"2026-07-05T02:09:17Z"}],"graph_snapshots":[{"event_id":"sha256:79559d051aff01928620b7c41f1f0056d6a1ddf416ad2a60974339bd0dc7bcfe","target":"graph","created_at":"2026-07-05T02:09:17Z","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/2101.09328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The partially observable card game Hanabi has recently been proposed as a new AI challenge problem due to its dependence on implicit communication conventions and apparent necessity of theory of mind reasoning for efficient play. In this work, we propose a mechanism for imbuing Reinforcement Learning agents with a theory of mind to discover efficient cooperative strategies in Hanabi. The primary contributions of this work are threefold: First, a formal definition of a computationally tractable mechanism for computing hand probabilities in Hanabi. Second, an extension to conventional Deep Reinf","authors_text":"Andrew Fuchs, Doug Lange, Michael Walton, Theresa Chadwick","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-01-22T20:56:42Z","title":"Theory of Mind for Deep Reinforcement Learning in Hanabi"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09328","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:ec66597904231c86182d63288500b533b248a9e5cae844e87b56637cac2753b4","target":"record","created_at":"2026-07-05T02:09:17Z","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":"e0b50c9a6e439833c7ccd335083538758622792853b57d8b9037f3f1ad8ac0d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-01-22T20:56:42Z","title_canon_sha256":"7bdfd4ae1217c651276a02038d7dc478b84481a111d483c6ceb4fd207bd5e739"},"schema_version":"1.0","source":{"id":"2101.09328","kind":"arxiv","version":1}},"canonical_sha256":"24ad46e49f71d6a67c69a26f05f83e80c9edc51b4596182533045ca7753bf469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24ad46e49f71d6a67c69a26f05f83e80c9edc51b4596182533045ca7753bf469","first_computed_at":"2026-07-05T02:09:17.714967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:09:17.714967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BpVYlsDPs8rcuisBQrVv1pT049v2GD9k/3MSd4lVAOgLKGElVNDxWCmKpqvhaZkJoN/GScga7y3yw0tMEnGgCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:09:17.715338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec66597904231c86182d63288500b533b248a9e5cae844e87b56637cac2753b4","sha256:79559d051aff01928620b7c41f1f0056d6a1ddf416ad2a60974339bd0dc7bcfe"],"state_sha256":"6637dd96e6a199fd03ec2cdabf2ccafc732216e15508eb5d5f9bb257bde62b1d"}