{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:67A5KBTOSNJF6CEUNIYSTCFTMB","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":"b89e30226e41962194fb35943df289d47a0586c8f6d38ea91979a50d6d54aee2","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T14:33:31Z","title_canon_sha256":"64900ef4b49bcda177fc7fa8a476933c183453ee42291735147b83c08ba356f5"},"schema_version":"1.0","source":{"id":"2006.04635","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04635","created_at":"2026-07-05T03:45:07Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04635v4","created_at":"2026-07-05T03:45:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04635","created_at":"2026-07-05T03:45:07Z"},{"alias_kind":"pith_short_12","alias_value":"67A5KBTOSNJF","created_at":"2026-07-05T03:45:07Z"},{"alias_kind":"pith_short_16","alias_value":"67A5KBTOSNJF6CEU","created_at":"2026-07-05T03:45:07Z"},{"alias_kind":"pith_short_8","alias_value":"67A5KBTO","created_at":"2026-07-05T03:45:07Z"}],"graph_snapshots":[{"event_id":"sha256:a9df0945ff634f84405a5d51166d3b449f85230576e842b29501db3737fa5215","target":"graph","created_at":"2026-07-05T03:45:07Z","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/2006.04635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and principled application of RL methods. However real-world settings are many-agent, and agent interactions are complex mixtures of common-interest and competitive aspects. We consider Diplomacy, a 7-player board game designed to accentuate dilemmas resulting from many-agent interactions. It also features a large combinatorial action space and simultaneous moves, which ","authors_text":"Andrea Tacchetti, Ian Gemp, J\\'anos Kram\\'ar, Julien P\\'erolat, Marc Lanctot, Nicolas Porcel, Richard Everett, Roman Werpachowski, Satinder Singh, Thomas Anthony, Thomas C. Hudson, Thore Graepel, Tom Eccles, Yoram Bachrach","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T14:33:31Z","title":"Learning to Play No-Press Diplomacy with Best Response Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04635","kind":"arxiv","version":4},"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":"sha256:70a80892f154f471f7700979992af5d69c1d56e88ee14e48fbc707e785fbeb94","target":"record","created_at":"2026-07-05T03:45:07Z","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":"b89e30226e41962194fb35943df289d47a0586c8f6d38ea91979a50d6d54aee2","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T14:33:31Z","title_canon_sha256":"64900ef4b49bcda177fc7fa8a476933c183453ee42291735147b83c08ba356f5"},"schema_version":"1.0","source":{"id":"2006.04635","kind":"arxiv","version":4}},"canonical_sha256":"f7c1d5066e93525f08946a312988b3606d4c3dbac9f7e669aceef7a580c9bde0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7c1d5066e93525f08946a312988b3606d4c3dbac9f7e669aceef7a580c9bde0","first_computed_at":"2026-07-05T03:45:07.622657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:07.622657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2EXZNro9Rayy1LOWnDWyoPI+zU0/0UReksBRRd58RvmVnpkssOxVVphVeXAfeqrwQfWEoCGZiJwfFI9bRppwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:07.623159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.04635","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70a80892f154f471f7700979992af5d69c1d56e88ee14e48fbc707e785fbeb94","sha256:a9df0945ff634f84405a5d51166d3b449f85230576e842b29501db3737fa5215"],"state_sha256":"a4a2e5aca301592d3ae6fdf78f74e26d7a860a43028b1252faf7afa153315a5e"}