{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YS6TM4ETDMCKDZRL5OHYPXQXJW","short_pith_number":"pith:YS6TM4ET","schema_version":"1.0","canonical_sha256":"c4bd3670931b04a1e62beb8f87de174d8f31bc956f2277beb4f44fe163aedda9","source":{"kind":"arxiv","id":"2202.13252","version":3},"attestation_state":"computed","paper":{"title":"The Quest for a Common Model of the Intelligent Decision Maker","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Richard S. Sutton","submitted_at":"2022-02-26T23:40:42Z","abstract_excerpt":"The premise of the Multi-disciplinary Conference on Reinforcement Learning and Decision Making is that multiple disciplines share an interest in goal-directed decision making over time. The idea of this paper is to sharpen and deepen this premise by proposing a perspective on the decision maker that is substantive and widely held across psychology, artificial intelligence, economics, control theory, and neuroscience, which I call the \"common model of the intelligent agent\". The common model does not include anything specific to any organism, world, or application domain. The common model does "},"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":"2202.13252","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-26T23:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d2eb549b798f792a319e55c00f57e19a2d7f86b562ed8a01cce63f7f7d4ecfd","abstract_canon_sha256":"d7183892cf8f7044b7b72cdb437ffd31430ff170a02ffc56e821802f677c9585"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:12.319038Z","signature_b64":"+l5jfrEP7t6w8kdo4yPCWuorH2nt+JhRM2t5CmZc6tF749kJiWPVO4CUNR8dHEx36eahktrqKpiodfsxL5rMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bd3670931b04a1e62beb8f87de174d8f31bc956f2277beb4f44fe163aedda9","last_reissued_at":"2026-07-05T04:29:12.318429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:12.318429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Quest for a Common Model of the Intelligent Decision Maker","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Richard S. Sutton","submitted_at":"2022-02-26T23:40:42Z","abstract_excerpt":"The premise of the Multi-disciplinary Conference on Reinforcement Learning and Decision Making is that multiple disciplines share an interest in goal-directed decision making over time. The idea of this paper is to sharpen and deepen this premise by proposing a perspective on the decision maker that is substantive and widely held across psychology, artificial intelligence, economics, control theory, and neuroscience, which I call the \"common model of the intelligent agent\". The common model does not include anything specific to any organism, world, or application domain. The common model does "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13252","kind":"arxiv","version":3},"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/2202.13252/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.13252","created_at":"2026-07-05T04:29:12.318518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13252v3","created_at":"2026-07-05T04:29:12.318518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13252","created_at":"2026-07-05T04:29:12.318518+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS6TM4ETDMCK","created_at":"2026-07-05T04:29:12.318518+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS6TM4ETDMCKDZRL","created_at":"2026-07-05T04:29:12.318518+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS6TM4ET","created_at":"2026-07-05T04:29:12.318518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.01844","citing_title":"Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW","json":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW.json","graph_json":"https://pith.science/api/pith-number/YS6TM4ETDMCKDZRL5OHYPXQXJW/graph.json","events_json":"https://pith.science/api/pith-number/YS6TM4ETDMCKDZRL5OHYPXQXJW/events.json","paper":"https://pith.science/paper/YS6TM4ET"},"agent_actions":{"view_html":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW","download_json":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW.json","view_paper":"https://pith.science/paper/YS6TM4ET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13252&json=true","fetch_graph":"https://pith.science/api/pith-number/YS6TM4ETDMCKDZRL5OHYPXQXJW/graph.json","fetch_events":"https://pith.science/api/pith-number/YS6TM4ETDMCKDZRL5OHYPXQXJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW/action/storage_attestation","attest_author":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW/action/author_attestation","sign_citation":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW/action/citation_signature","submit_replication":"https://pith.science/pith/YS6TM4ETDMCKDZRL5OHYPXQXJW/action/replication_record"}},"created_at":"2026-07-05T04:29:12.318518+00:00","updated_at":"2026-07-05T04:29:12.318518+00:00"}