{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:6NYJNFNQ53MRNUN3WWRIFWXLFN","short_pith_number":"pith:6NYJNFNQ","schema_version":"1.0","canonical_sha256":"f3709695b0eed916d1bbb5a282daeb2b505ba32aa258e6fbc27e43df25f7b456","source":{"kind":"arxiv","id":"1207.0852","version":1},"attestation_state":"computed","paper":{"title":"Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate The Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.MA","authors_text":"Brendan Tracey, David H. Wolpert, James Bono, Ritchie Lee, Russell Bent, Scott Backhaus","submitted_at":"2012-07-03T22:30:34Z","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 "},"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":"1207.0852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2012-07-03T22:30:34Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"8a4269b51f1ad99bec648ff786cad0fe54f679b8e268548dcbfc53b0d8516436","abstract_canon_sha256":"79a729833c175185a778aa2feb6abfd5504f11c422190bb40216a24e80be2b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:51:48.211125Z","signature_b64":"5+mjVzSm4UJ+vdFuug6W6OIBy2sCdTWSOfZTA3rkzr2Vv1cbNRDTNn4NX7HnHmMvNWk3eEnQF9s8/HaGqz6ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3709695b0eed916d1bbb5a282daeb2b505ba32aa258e6fbc27e43df25f7b456","last_reissued_at":"2026-05-18T03:51:48.210389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:51:48.210389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate The Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.MA","authors_text":"Brendan Tracey, David H. Wolpert, James Bono, Ritchie Lee, Russell Bent, Scott Backhaus","submitted_at":"2012-07-03T22:30:34Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.0852","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":"1207.0852","created_at":"2026-05-18T03:51:48.210522+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.0852v1","created_at":"2026-05-18T03:51:48.210522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.0852","created_at":"2026-05-18T03:51:48.210522+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NYJNFNQ53MR","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NYJNFNQ53MRNUN3","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NYJNFNQ","created_at":"2026-05-18T12:26:56.085431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN","json":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN.json","graph_json":"https://pith.science/api/pith-number/6NYJNFNQ53MRNUN3WWRIFWXLFN/graph.json","events_json":"https://pith.science/api/pith-number/6NYJNFNQ53MRNUN3WWRIFWXLFN/events.json","paper":"https://pith.science/paper/6NYJNFNQ"},"agent_actions":{"view_html":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN","download_json":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN.json","view_paper":"https://pith.science/paper/6NYJNFNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.0852&json=true","fetch_graph":"https://pith.science/api/pith-number/6NYJNFNQ53MRNUN3WWRIFWXLFN/graph.json","fetch_events":"https://pith.science/api/pith-number/6NYJNFNQ53MRNUN3WWRIFWXLFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN/action/storage_attestation","attest_author":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN/action/author_attestation","sign_citation":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN/action/citation_signature","submit_replication":"https://pith.science/pith/6NYJNFNQ53MRNUN3WWRIFWXLFN/action/replication_record"}},"created_at":"2026-05-18T03:51:48.210522+00:00","updated_at":"2026-05-18T03:51:48.210522+00:00"}