{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQDWMVXFJ6SLEGPEA2YXDMISJQ","short_pith_number":"pith:VQDWMVXF","schema_version":"1.0","canonical_sha256":"ac076656e54fa4b219e406b171b1124c0f44f69316b0b96db33c1daed48098f0","source":{"kind":"arxiv","id":"2605.20577","version":1},"attestation_state":"computed","paper":{"title":"Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Eason Yu, Keigo Habara, Masashi Sugiyama, Shinri Okano, Soichiro Nishimori, Sotetsu Koyamada","submitted_at":"2026-05-20T00:33:28Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T00:33:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"538296858868080589c74bea083ae6d13e880be512870b8fc6f09d374f0c9050","abstract_canon_sha256":"f3e52c3f732a32e8c135360a462519a53fc09ee600138fac2c43a4a9f0296957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:43.175353Z","signature_b64":"YjbxL7KT2zK9vIgmeADFxmlnQM+auk8hJZN7JTBDilJr3BRIff1TdfWarvINONz3n5M8k5oAJ9YbjLQs2EiSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac076656e54fa4b219e406b171b1124c0f44f69316b0b96db33c1daed48098f0","last_reissued_at":"2026-05-21T01:04:43.174822Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:43.174822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Eason Yu, Keigo Habara, Masashi Sugiyama, Shinri Okano, Soichiro Nishimori, Sotetsu Koyamada","submitted_at":"2026-05-20T00:33:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20577","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/2605.20577/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20577","created_at":"2026-05-21T01:04:43.174898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20577v1","created_at":"2026-05-21T01:04:43.174898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20577","created_at":"2026-05-21T01:04:43.174898+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQDWMVXFJ6SL","created_at":"2026-05-21T01:04:43.174898+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQDWMVXFJ6SLEGPE","created_at":"2026-05-21T01:04:43.174898+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQDWMVXF","created_at":"2026-05-21T01:04:43.174898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ","json":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ.json","graph_json":"https://pith.science/api/pith-number/VQDWMVXFJ6SLEGPEA2YXDMISJQ/graph.json","events_json":"https://pith.science/api/pith-number/VQDWMVXFJ6SLEGPEA2YXDMISJQ/events.json","paper":"https://pith.science/paper/VQDWMVXF"},"agent_actions":{"view_html":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ","download_json":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ.json","view_paper":"https://pith.science/paper/VQDWMVXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20577&json=true","fetch_graph":"https://pith.science/api/pith-number/VQDWMVXFJ6SLEGPEA2YXDMISJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VQDWMVXFJ6SLEGPEA2YXDMISJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ/action/storage_attestation","attest_author":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ/action/author_attestation","sign_citation":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ/action/citation_signature","submit_replication":"https://pith.science/pith/VQDWMVXFJ6SLEGPEA2YXDMISJQ/action/replication_record"}},"created_at":"2026-05-21T01:04:43.174898+00:00","updated_at":"2026-05-21T01:04:43.174898+00:00"}