{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:6NYJNFNQ53MRNUN3WWRIFWXLFN","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":"79a729833c175185a778aa2feb6abfd5504f11c422190bb40216a24e80be2b8e","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2012-07-03T22:30:34Z","title_canon_sha256":"8a4269b51f1ad99bec648ff786cad0fe54f679b8e268548dcbfc53b0d8516436"},"schema_version":"1.0","source":{"id":"1207.0852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.0852","created_at":"2026-05-18T03:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"1207.0852v1","created_at":"2026-05-18T03:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.0852","created_at":"2026-05-18T03:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"6NYJNFNQ53MR","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"6NYJNFNQ53MRNUN3","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"6NYJNFNQ","created_at":"2026-05-18T12:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:d3d5ecbb85396cdcc41ad439be711ea32635c639d288dd79594e303b8d0c940a","target":"graph","created_at":"2026-05-18T03:51:48Z","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":"This paper introduces a novel framework for modeling interacting humans in a multi-stage game. This \"iterated semi network-form game\" framework has the following desirable characteristics: (1) Bounded rational players, (2) strategic players (i.e., players account for one another's reward functions when predicting one another's behavior), and (3) computational tractability even on real-world systems. We achieve these benefits by combining concepts from game theory and reinforcement learning. To be precise, we extend the bounded rational \"level-K reasoning\" model to apply to games over multiple ","authors_text":"Brendan Tracey, David H. Wolpert, James Bono, Ritchie Lee, Russell Bent, Scott Backhaus","cross_cats":["cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2012-07-03T22:30:34Z","title":"Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate The Future"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.0852","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":"sha256:641b1ca24e38f914148f7e39ddc6fbc04f3820e8804670f08c9651de913cedf3","target":"record","created_at":"2026-05-18T03:51:48Z","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":"79a729833c175185a778aa2feb6abfd5504f11c422190bb40216a24e80be2b8e","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2012-07-03T22:30:34Z","title_canon_sha256":"8a4269b51f1ad99bec648ff786cad0fe54f679b8e268548dcbfc53b0d8516436"},"schema_version":"1.0","source":{"id":"1207.0852","kind":"arxiv","version":1}},"canonical_sha256":"f3709695b0eed916d1bbb5a282daeb2b505ba32aa258e6fbc27e43df25f7b456","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3709695b0eed916d1bbb5a282daeb2b505ba32aa258e6fbc27e43df25f7b456","first_computed_at":"2026-05-18T03:51:48.210389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:51:48.210389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5+mjVzSm4UJ+vdFuug6W6OIBy2sCdTWSOfZTA3rkzr2Vv1cbNRDTNn4NX7HnHmMvNWk3eEnQF9s8/HaGqz6ECA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:51:48.211125Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.0852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:641b1ca24e38f914148f7e39ddc6fbc04f3820e8804670f08c9651de913cedf3","sha256:d3d5ecbb85396cdcc41ad439be711ea32635c639d288dd79594e303b8d0c940a"],"state_sha256":"643b21c774eb6d3724cd7bfbe353ed5b4b5e94375a1ddd6079b6320d67468bdb"}