{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GU2NAXJR6ECTV53KOJ3ZMUNXYW","short_pith_number":"pith:GU2NAXJR","canonical_record":{"source":{"id":"2210.05492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"5c2167f5a089d5d2b81fdbde2b537968f6f09bf44de1b6579135bf49b3e1cdd3","abstract_canon_sha256":"954d96ae1552a5d73b60885552e2addd775f4b33756ebdb5ef300dc3c51e7482"},"schema_version":"1.0"},"canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","source":{"kind":"arxiv","id":"2210.05492","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05492","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05492v1","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05492","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"GU2NAXJR6ECT","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"GU2NAXJR6ECTV53K","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"GU2NAXJR","created_at":"2026-07-05T05:05:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GU2NAXJR6ECTV53KOJ3ZMUNXYW","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"5c2167f5a089d5d2b81fdbde2b537968f6f09bf44de1b6579135bf49b3e1cdd3","abstract_canon_sha256":"954d96ae1552a5d73b60885552e2addd775f4b33756ebdb5ef300dc3c51e7482"},"schema_version":"1.0"},"canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:17.211828Z","signature_b64":"28dUD2wwu6Z1UAvbl3fBqfHo4fOesbrXtsgbPMukw9CSldDWiq7PvvKUOl7b/+cajYCXjlZV0zx6OED3gnlOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","last_reissued_at":"2026-07-05T05:05:17.211090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:17.211090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05492","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":"2026-07-05T05:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ukz5Fhjgi85lSbH1Irev2IJV17Bp5wtEXwJhLJy153gFfk4pramwn4izgTYiaMLu91BpS/XavdmKMIvn24EXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:30:58.978038Z"},"content_sha256":"6ba1d7e544439d82573296f82baddb1fa0eb4ef6a80b35a445e18860f0eb190e","schema_version":"1.0","event_id":"sha256:6ba1d7e544439d82573296f82baddb1fa0eb4ef6a80b35a445e18860f0eb190e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GU2NAXJR6ECTV53KOJ3ZMUNXYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Adam Lerer, Alexander H Miller, Anton Bakhtin, Athul Paul Jacob, David J Wu, Gabriele Farina, Jonathan Gray, Noam Brown","submitted_at":"2022-10-11T14:47:35Z","abstract_excerpt":"No-press Diplomacy is a complex strategy game involving both cooperation and competition that has served as a benchmark for multi-agent AI research. While self-play reinforcement learning has resulted in numerous successes in purely adversarial games like chess, Go, and poker, self-play alone is insufficient for achieving optimal performance in domains involving cooperation with humans. We address this shortcoming by first introducing a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We prove that this is a no-regret lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05492","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/2210.05492/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJnUFKDR2x8oQd4czSs+z1fZRgjJozgJrsYy+czW+a+39LwLZfwwonWyHSGCxc+SEN/JrAly2UfbZLEDFwpgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:30:58.978566Z"},"content_sha256":"ef62ff94d2910165b891b7b5db4f560b5aaf99e1c984c9561c93757bf420a3e1","schema_version":"1.0","event_id":"sha256:ef62ff94d2910165b891b7b5db4f560b5aaf99e1c984c9561c93757bf420a3e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/bundle.json","state_url":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/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":"2026-08-09T14:30:58Z","links":{"resolver":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW","bundle":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/bundle.json","state":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GU2NAXJR6ECTV53KOJ3ZMUNXYW","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":"954d96ae1552a5d73b60885552e2addd775f4b33756ebdb5ef300dc3c51e7482","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","title_canon_sha256":"5c2167f5a089d5d2b81fdbde2b537968f6f09bf44de1b6579135bf49b3e1cdd3"},"schema_version":"1.0","source":{"id":"2210.05492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05492","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05492v1","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05492","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"GU2NAXJR6ECT","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"GU2NAXJR6ECTV53K","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"GU2NAXJR","created_at":"2026-07-05T05:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:ef62ff94d2910165b891b7b5db4f560b5aaf99e1c984c9561c93757bf420a3e1","target":"graph","created_at":"2026-07-05T05:05:17Z","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/2210.05492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"No-press Diplomacy is a complex strategy game involving both cooperation and competition that has served as a benchmark for multi-agent AI research. While self-play reinforcement learning has resulted in numerous successes in purely adversarial games like chess, Go, and poker, self-play alone is insufficient for achieving optimal performance in domains involving cooperation with humans. We address this shortcoming by first introducing a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We prove that this is a no-regret lear","authors_text":"Adam Lerer, Alexander H Miller, Anton Bakhtin, Athul Paul Jacob, David J Wu, Gabriele Farina, Jonathan Gray, Noam Brown","cross_cats":["cs.AI","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05492","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":"sha256:6ba1d7e544439d82573296f82baddb1fa0eb4ef6a80b35a445e18860f0eb190e","target":"record","created_at":"2026-07-05T05:05:17Z","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":"954d96ae1552a5d73b60885552e2addd775f4b33756ebdb5ef300dc3c51e7482","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","title_canon_sha256":"5c2167f5a089d5d2b81fdbde2b537968f6f09bf44de1b6579135bf49b3e1cdd3"},"schema_version":"1.0","source":{"id":"2210.05492","kind":"arxiv","version":1}},"canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","first_computed_at":"2026-07-05T05:05:17.211090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:17.211090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"28dUD2wwu6Z1UAvbl3fBqfHo4fOesbrXtsgbPMukw9CSldDWiq7PvvKUOl7b/+cajYCXjlZV0zx6OED3gnlOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:17.211828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ba1d7e544439d82573296f82baddb1fa0eb4ef6a80b35a445e18860f0eb190e","sha256:ef62ff94d2910165b891b7b5db4f560b5aaf99e1c984c9561c93757bf420a3e1"],"state_sha256":"4dd2ae8d3e4ea492dd18762baee0fba584a63796584fcd172562e86570b1cec9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAylXpsDJd6kVTHVlZhGGh+uf5vIlZh7llXe5mCm29CnZelWLPLHgCNGwYuWIjNr9mpmDpjLhDzOxsEvry/NBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:30:58.982235Z","bundle_sha256":"53757b288477b0c9403dfbcb839e07a63543cf2431267b215a8075136e367101"}}