{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TUCT2YAZJS3FMJTIFYWZ35CDQ3","short_pith_number":"pith:TUCT2YAZ","canonical_record":{"source":{"id":"1808.10442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2ef0fe1be1709e8897a91009e52d26760ce6ba5251c32cd8605c006d62cb3940","abstract_canon_sha256":"6c88d29881c34282bab7d30b84d3da469ac20d01e4665f7f225784778e15966f"},"schema_version":"1.0"},"canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","source":{"kind":"arxiv","id":"1808.10442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10442","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10442v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10442","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"TUCT2YAZJS3F","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TUCT2YAZJS3FMJTI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TUCT2YAZ","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TUCT2YAZJS3FMJTIFYWZ35CDQ3","target":"record","payload":{"canonical_record":{"source":{"id":"1808.10442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2ef0fe1be1709e8897a91009e52d26760ce6ba5251c32cd8605c006d62cb3940","abstract_canon_sha256":"6c88d29881c34282bab7d30b84d3da469ac20d01e4665f7f225784778e15966f"},"schema_version":"1.0"},"canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:45.631343Z","signature_b64":"mIHX+M2NE+qyqMRVmOaQZU5kOAKlDKcRGdHbwp8WZI8qlbsJ6PeahuyKiTrP3GWWWoWjsKXwoL9e6GVVHeD4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","last_reissued_at":"2026-05-18T00:06:45.630827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:45.630827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.10442","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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7vHKM/e435By+SO2Lf1DCOet/16uHIHhg2hliWhDWYHWm6ZZSNkKiGKM20iL7spMx0+WzEmKQ200M82eg8TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:30:43.280994Z"},"content_sha256":"5ca9bbf9e543c2d3df4e3135d3c69ed49014cae9b9f9640d636c870490e70431","schema_version":"1.0","event_id":"sha256:5ca9bbf9e543c2d3df4e3135d3c69ed49014cae9b9f9640d636c870490e70431"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TUCT2YAZJS3FMJTIFYWZ35CDQ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Henry Charlesworth","submitted_at":"2018-08-30T11:26:59Z","abstract_excerpt":"We introduce a new virtual environment for simulating a card game known as \"Big 2\". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed \"Proximal Policy Optimization\" algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10442","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":""},"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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RfVWgn57+2zeywigXUdpLi89Goc5oBBpSeIujqhmoZVyEP+xiclTwLyqDCx2zSxlIi5+No6mzoeQ3BMORJ9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:30:43.281352Z"},"content_sha256":"81aad2228a5ef4c17d81ec87019cb59ba8cd3ad8bc065252c8816315b8b0dd1c","schema_version":"1.0","event_id":"sha256:81aad2228a5ef4c17d81ec87019cb59ba8cd3ad8bc065252c8816315b8b0dd1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/bundle.json","state_url":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/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":"2026-07-01T07:30:43Z","links":{"resolver":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3","bundle":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/bundle.json","state":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TUCT2YAZJS3FMJTIFYWZ35CDQ3","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":"6c88d29881c34282bab7d30b84d3da469ac20d01e4665f7f225784778e15966f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","title_canon_sha256":"2ef0fe1be1709e8897a91009e52d26760ce6ba5251c32cd8605c006d62cb3940"},"schema_version":"1.0","source":{"id":"1808.10442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10442","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10442v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10442","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"TUCT2YAZJS3F","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TUCT2YAZJS3FMJTI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TUCT2YAZ","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:81aad2228a5ef4c17d81ec87019cb59ba8cd3ad8bc065252c8816315b8b0dd1c","target":"graph","created_at":"2026-05-18T00:06:45Z","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"},"paper":{"abstract_excerpt":"We introduce a new virtual environment for simulating a card game known as \"Big 2\". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed \"Proximal Policy Optimization\" algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after on","authors_text":"Henry Charlesworth","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10442","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":"sha256:5ca9bbf9e543c2d3df4e3135d3c69ed49014cae9b9f9640d636c870490e70431","target":"record","created_at":"2026-05-18T00:06:45Z","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":"6c88d29881c34282bab7d30b84d3da469ac20d01e4665f7f225784778e15966f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","title_canon_sha256":"2ef0fe1be1709e8897a91009e52d26760ce6ba5251c32cd8605c006d62cb3940"},"schema_version":"1.0","source":{"id":"1808.10442","kind":"arxiv","version":1}},"canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","first_computed_at":"2026-05-18T00:06:45.630827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:45.630827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mIHX+M2NE+qyqMRVmOaQZU5kOAKlDKcRGdHbwp8WZI8qlbsJ6PeahuyKiTrP3GWWWoWjsKXwoL9e6GVVHeD4DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:45.631343Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ca9bbf9e543c2d3df4e3135d3c69ed49014cae9b9f9640d636c870490e70431","sha256:81aad2228a5ef4c17d81ec87019cb59ba8cd3ad8bc065252c8816315b8b0dd1c"],"state_sha256":"a5fe4578f96d01a2d4123190c56b0faff51450e50d56659aec4867155bfd95e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yr/gOG7ol2qZRm+q+MB+TkJAl5EqBfh3BvRvRMCZPn+icGtWSHm5IUBydmpD95uHbKbGdtkz7uz0b6aVxv+XAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T07:30:43.283489Z","bundle_sha256":"f574205fe970208b54c11893401eefde4ab9b587fcccd7f9a87a4531b06b36c0"}}