{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I6YWZSA6AU6TCNBC5KJ4PWDQWU","short_pith_number":"pith:I6YWZSA6","schema_version":"1.0","canonical_sha256":"47b16cc81e053d313422ea93c7d870b5219d5652112b5163c4c1323f48bde347","source":{"kind":"arxiv","id":"2603.08956","version":6},"attestation_state":"computed","paper":{"title":"A Survey of Reinforcement Learning For Economics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-fin.EC"],"primary_cat":"econ.GN","authors_text":"Pranjal Rawat","submitted_at":"2026-03-09T21:43:10Z","abstract_excerpt":"This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably \"small\" problems or our ability to convert \"big\" problems into smaller ones. While this reduction has been sufficient for many classical applications, a growing class of economic models resists such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming, extending tractability to problems with high-dimensional states, continuous actions, and st"},"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":"2603.08956","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.GN","submitted_at":"2026-03-09T21:43:10Z","cross_cats_sorted":["cs.LG","q-fin.EC"],"title_canon_sha256":"661d1d73b83982a4c525ff9f049a28bef16239212886db3100cc23954ef97691","abstract_canon_sha256":"67e242e9f7c163c7fb8485d4d147f98f6beb52b15a1524e046b55845d766aea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:30.408875Z","signature_b64":"6XQpONQuu2TUDNiq804xcFDnY101qoVf3GsLbJmWt9Ef15JOP0SxV3xwjYqnyEkDnk5huGfSRgby6n7nOQ7HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47b16cc81e053d313422ea93c7d870b5219d5652112b5163c4c1323f48bde347","last_reissued_at":"2026-07-28T01:23:30.407765Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:30.407765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Reinforcement Learning For Economics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-fin.EC"],"primary_cat":"econ.GN","authors_text":"Pranjal Rawat","submitted_at":"2026-03-09T21:43:10Z","abstract_excerpt":"This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably \"small\" problems or our ability to convert \"big\" problems into smaller ones. While this reduction has been sufficient for many classical applications, a growing class of economic models resists such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming, extending tractability to problems with high-dimensional states, continuous actions, and st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08956","kind":"arxiv","version":6},"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/2603.08956/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":"2603.08956","created_at":"2026-07-28T01:23:30.408339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.08956v6","created_at":"2026-07-28T01:23:30.408339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08956","created_at":"2026-07-28T01:23:30.408339+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6YWZSA6AU6T","created_at":"2026-07-28T01:23:30.408339+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6YWZSA6AU6TCNBC","created_at":"2026-07-28T01:23:30.408339+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6YWZSA6","created_at":"2026-07-28T01:23:30.408339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.06621","citing_title":"The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligence","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU","json":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU.json","graph_json":"https://pith.science/api/pith-number/I6YWZSA6AU6TCNBC5KJ4PWDQWU/graph.json","events_json":"https://pith.science/api/pith-number/I6YWZSA6AU6TCNBC5KJ4PWDQWU/events.json","paper":"https://pith.science/paper/I6YWZSA6"},"agent_actions":{"view_html":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU","download_json":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU.json","view_paper":"https://pith.science/paper/I6YWZSA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.08956&json=true","fetch_graph":"https://pith.science/api/pith-number/I6YWZSA6AU6TCNBC5KJ4PWDQWU/graph.json","fetch_events":"https://pith.science/api/pith-number/I6YWZSA6AU6TCNBC5KJ4PWDQWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU/action/storage_attestation","attest_author":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU/action/author_attestation","sign_citation":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU/action/citation_signature","submit_replication":"https://pith.science/pith/I6YWZSA6AU6TCNBC5KJ4PWDQWU/action/replication_record"}},"created_at":"2026-07-28T01:23:30.408339+00:00","updated_at":"2026-07-28T01:23:30.408339+00:00"}