{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:6CJSNUEZGO5D2SRPNVZCLFGP7Y","short_pith_number":"pith:6CJSNUEZ","schema_version":"1.0","canonical_sha256":"f09326d09933ba3d4a2f6d722594cffe08b7f2bd75a77085be4094f2d8034dc2","source":{"kind":"arxiv","id":"1207.1411","version":1},"attestation_state":"computed","paper":{"title":"Bayes' Bluff: Opponent Modelling in Poker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Bryce Larson, Carmelo Piccione, Chris Rayner, Darse Billings, Finnegan Southey, Michael P. Bowling, Neil Burch","submitted_at":"2012-07-04T16:22:47Z","abstract_excerpt":"Poker is a challenging problem for artificial intelligence, with non-deterministic dynamics, partial observability, and the added difficulty of unknown adversaries. Modelling all of the uncertainties in this domain is not an easy task. In this paper we present a Bayesian probabilistic model for a broad class of poker games, separating the uncertainty in the game dynamics from the uncertainty of the opponent's strategy. We then describe approaches to two key subproblems: (i) inferring a posterior over opponent strategies given a prior distribution and observations of their play, and (ii) playin"},"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":"1207.1411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-07-04T16:22:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4a6ccdbbdd2301c37dbf6f02d3808ff775b663cf2ff8b5fbff6ab5c766d106c","abstract_canon_sha256":"8d29b1140bb4c3a363f72ad94dcbf71dc53ca4a3f707a9009d6e2f15dc22e976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:51:37.194808Z","signature_b64":"9TD+AqwXY38svl6+ZMtpMpDu+fG3yNK/Ci2b9jfHz1Ecrajy3DQzDyqOqBnCaZx9OTijEpi4EmQ1GERE3ByYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f09326d09933ba3d4a2f6d722594cffe08b7f2bd75a77085be4094f2d8034dc2","last_reissued_at":"2026-05-18T03:51:37.194246Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:51:37.194246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayes' Bluff: Opponent Modelling in Poker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Bryce Larson, Carmelo Piccione, Chris Rayner, Darse Billings, Finnegan Southey, Michael P. Bowling, Neil Burch","submitted_at":"2012-07-04T16:22:47Z","abstract_excerpt":"Poker is a challenging problem for artificial intelligence, with non-deterministic dynamics, partial observability, and the added difficulty of unknown adversaries. Modelling all of the uncertainties in this domain is not an easy task. In this paper we present a Bayesian probabilistic model for a broad class of poker games, separating the uncertainty in the game dynamics from the uncertainty of the opponent's strategy. We then describe approaches to two key subproblems: (i) inferring a posterior over opponent strategies given a prior distribution and observations of their play, and (ii) playin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.1411","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1207.1411","created_at":"2026-05-18T03:51:37.194325+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.1411v1","created_at":"2026-05-18T03:51:37.194325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.1411","created_at":"2026-05-18T03:51:37.194325+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CJSNUEZGO5D","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CJSNUEZGO5D2SRP","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CJSNUEZ","created_at":"2026-05-18T12:26:56.085431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.19235","citing_title":"GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09150","citing_title":"AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04979","citing_title":"On-line Learning in Tree MDPs by Treating Policies as Bandit Arms","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y","json":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y.json","graph_json":"https://pith.science/api/pith-number/6CJSNUEZGO5D2SRPNVZCLFGP7Y/graph.json","events_json":"https://pith.science/api/pith-number/6CJSNUEZGO5D2SRPNVZCLFGP7Y/events.json","paper":"https://pith.science/paper/6CJSNUEZ"},"agent_actions":{"view_html":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y","download_json":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y.json","view_paper":"https://pith.science/paper/6CJSNUEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.1411&json=true","fetch_graph":"https://pith.science/api/pith-number/6CJSNUEZGO5D2SRPNVZCLFGP7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/6CJSNUEZGO5D2SRPNVZCLFGP7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y/action/storage_attestation","attest_author":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y/action/author_attestation","sign_citation":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y/action/citation_signature","submit_replication":"https://pith.science/pith/6CJSNUEZGO5D2SRPNVZCLFGP7Y/action/replication_record"}},"created_at":"2026-05-18T03:51:37.194325+00:00","updated_at":"2026-05-18T03:51:37.194325+00:00"}