{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VQDWMVXFJ6SLEGPEA2YXDMISJQ","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":"f3e52c3f732a32e8c135360a462519a53fc09ee600138fac2c43a4a9f0296957","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T00:33:28Z","title_canon_sha256":"538296858868080589c74bea083ae6d13e880be512870b8fc6f09d374f0c9050"},"schema_version":"1.0","source":{"id":"2605.20577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20577","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20577v1","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20577","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"VQDWMVXFJ6SL","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"VQDWMVXFJ6SLEGPE","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"VQDWMVXF","created_at":"2026-05-21T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:50b9be5dfc2e639c6a722ca54c4f6d98ae1adc144d22744158840ce4d4b036e5","target":"graph","created_at":"2026-05-21T01:04:43Z","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/2605.20577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of challenges that mirror complex real-world decision-making problems in reinforcement learning. While prior research has heavily relied on supervised learning from human play logs to pre-train the policy, algorithms capable of learning \\textit{tabula rasa} (from scratch) offer greater potential for general applicability, as evidenced by the AlphaZero lineage. To facilitate such research, we introduce \\textbf{Mahjax}, a ful","authors_text":"Eason Yu, Keigo Habara, Masashi Sugiyama, Shinri Okano, Soichiro Nishimori, Sotetsu Koyamada","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T00:33:28Z","title":"Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20577","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":"sha256:6748f3a47fac2c5fa6032e57374119c328b714c59be7ae695aa1d2645a1fd8b7","target":"record","created_at":"2026-05-21T01:04:43Z","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":"f3e52c3f732a32e8c135360a462519a53fc09ee600138fac2c43a4a9f0296957","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T00:33:28Z","title_canon_sha256":"538296858868080589c74bea083ae6d13e880be512870b8fc6f09d374f0c9050"},"schema_version":"1.0","source":{"id":"2605.20577","kind":"arxiv","version":1}},"canonical_sha256":"ac076656e54fa4b219e406b171b1124c0f44f69316b0b96db33c1daed48098f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac076656e54fa4b219e406b171b1124c0f44f69316b0b96db33c1daed48098f0","first_computed_at":"2026-05-21T01:04:43.174822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:43.174822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjbxL7KT2zK9vIgmeADFxmlnQM+auk8hJZN7JTBDilJr3BRIff1TdfWarvINONz3n5M8k5oAJ9YbjLQs2EiSDQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:43.175353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6748f3a47fac2c5fa6032e57374119c328b714c59be7ae695aa1d2645a1fd8b7","sha256:50b9be5dfc2e639c6a722ca54c4f6d98ae1adc144d22744158840ce4d4b036e5"],"state_sha256":"05fb2feb2584e7f0dbd75360dd633feeed375f2a6f5efbf0fc81c9322e417be4"}