{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VF3MFVXOQQA3UVEJGQJQMUSN5R","short_pith_number":"pith:VF3MFVXO","schema_version":"1.0","canonical_sha256":"a976c2d6ee8401ba5489341306524dec6a308159e486abd69f2e703f03871ebf","source":{"kind":"arxiv","id":"2106.06135","version":1},"attestation_state":"computed","paper":{"title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daochen Zha, Ji Liu, Jingru Xie, Sheng Zhang, Wenye Ma, Xia Hu, Xiangru Lian","submitted_at":"2021-06-11T02:45:51Z","abstract_excerpt":"Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on s"},"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":"2106.06135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-11T02:45:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fa4a5314f4f3d62ba98c333a8ca204755d9305c56d5cae29ba9134556bb720f","abstract_canon_sha256":"99fcff9a41ff9d2f33afe5233191b44ac110ac082572354107c322c312c440a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:26.560971Z","signature_b64":"lEvP6kWjKX5SsN/UOCV3xKmSFpJ9H1LJNAXLhxvGAVPUpNwbbJxgu0gZ+y3B585DMRNm4kqtiqmQlVnUXYvuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a976c2d6ee8401ba5489341306524dec6a308159e486abd69f2e703f03871ebf","last_reissued_at":"2026-07-05T02:48:26.560555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:26.560555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daochen Zha, Ji Liu, Jingru Xie, Sheng Zhang, Wenye Ma, Xia Hu, Xiangru Lian","submitted_at":"2021-06-11T02:45:51Z","abstract_excerpt":"Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06135","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/2106.06135/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":"2106.06135","created_at":"2026-07-05T02:48:26.560617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06135v1","created_at":"2026-07-05T02:48:26.560617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06135","created_at":"2026-07-05T02:48:26.560617+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF3MFVXOQQA3","created_at":"2026-07-05T02:48:26.560617+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF3MFVXOQQA3UVEJ","created_at":"2026-07-05T02:48:26.560617+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF3MFVXO","created_at":"2026-07-05T02:48:26.560617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12801","citing_title":"Mastering Da Vinci Code: A Comparative Study of Transformer, LLM, and PPO-based Agents","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R","json":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R.json","graph_json":"https://pith.science/api/pith-number/VF3MFVXOQQA3UVEJGQJQMUSN5R/graph.json","events_json":"https://pith.science/api/pith-number/VF3MFVXOQQA3UVEJGQJQMUSN5R/events.json","paper":"https://pith.science/paper/VF3MFVXO"},"agent_actions":{"view_html":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R","download_json":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R.json","view_paper":"https://pith.science/paper/VF3MFVXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06135&json=true","fetch_graph":"https://pith.science/api/pith-number/VF3MFVXOQQA3UVEJGQJQMUSN5R/graph.json","fetch_events":"https://pith.science/api/pith-number/VF3MFVXOQQA3UVEJGQJQMUSN5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R/action/storage_attestation","attest_author":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R/action/author_attestation","sign_citation":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R/action/citation_signature","submit_replication":"https://pith.science/pith/VF3MFVXOQQA3UVEJGQJQMUSN5R/action/replication_record"}},"created_at":"2026-07-05T02:48:26.560617+00:00","updated_at":"2026-07-05T02:48:26.560617+00:00"}