{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3ZC5F5F7772TN7TWTA3DW57AH2","short_pith_number":"pith:3ZC5F5F7","schema_version":"1.0","canonical_sha256":"de45d2f4bffff536fe7698363b77e03eb8cdda0291df4fa0afb6a6ea0b28c020","source":{"kind":"arxiv","id":"2004.13332","version":1},"attestation_state":"computed","paper":{"title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.EC","stat.ML"],"primary_cat":"econ.GN","authors_text":"Alexander Trott, David C. Parkes, Melvin Gruesbeck, Nikhil Naik, Richard Socher, Stephan Zheng, Sunil Srinivasa","submitted_at":"2020-04-28T06:57:18Z","abstract_excerpt":"Tackling real-world socio-economic challenges requires designing and testing economic policies. However, this is hard in practice, due to a lack of appropriate (micro-level) economic data and limited opportunity to experiment. In this work, we train social planners that discover tax policies in dynamic economies that can effectively trade-off economic equality and productivity. We propose a two-level deep reinforcement learning approach to learn dynamic tax policies, based on economic simulations in which both agents and a government learn and adapt. Our data-driven approach does not make use "},"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":"2004.13332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.GN","submitted_at":"2020-04-28T06:57:18Z","cross_cats_sorted":["cs.LG","q-fin.EC","stat.ML"],"title_canon_sha256":"8753af1ea42ca0cf7509bf2baac29174e090ccb2f37499cbbe28bc8ea4de3f1c","abstract_canon_sha256":"ca2a0e3de84e71cd0dfe28f8eeed7f8326037bd9751a20f2bba6f833fe9d772e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:58.154109Z","signature_b64":"NVoE0PvzAU2MNkbU/MPrAflrra/2+wcW9BhUsTdLtovEmcVuH6UetW0tprkdV/F00otm0BimzlJ8z86OR30mBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de45d2f4bffff536fe7698363b77e03eb8cdda0291df4fa0afb6a6ea0b28c020","last_reissued_at":"2026-07-05T00:58:58.153592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:58.153592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.EC","stat.ML"],"primary_cat":"econ.GN","authors_text":"Alexander Trott, David C. Parkes, Melvin Gruesbeck, Nikhil Naik, Richard Socher, Stephan Zheng, Sunil Srinivasa","submitted_at":"2020-04-28T06:57:18Z","abstract_excerpt":"Tackling real-world socio-economic challenges requires designing and testing economic policies. However, this is hard in practice, due to a lack of appropriate (micro-level) economic data and limited opportunity to experiment. In this work, we train social planners that discover tax policies in dynamic economies that can effectively trade-off economic equality and productivity. We propose a two-level deep reinforcement learning approach to learn dynamic tax policies, based on economic simulations in which both agents and a government learn and adapt. Our data-driven approach does not make use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13332","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/2004.13332/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":"2004.13332","created_at":"2026-07-05T00:58:58.153652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13332v1","created_at":"2026-07-05T00:58:58.153652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13332","created_at":"2026-07-05T00:58:58.153652+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZC5F5F7772T","created_at":"2026-07-05T00:58:58.153652+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZC5F5F7772TN7TW","created_at":"2026-07-05T00:58:58.153652+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZC5F5F7","created_at":"2026-07-05T00:58:58.153652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06744","citing_title":"Learn to Match: Two-Sided Matching with Temporally Extended Feedback","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03237","citing_title":"Solipsistic Superintelligence is Unlikely to be Cooperative","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22827","citing_title":"Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2","json":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2.json","graph_json":"https://pith.science/api/pith-number/3ZC5F5F7772TN7TWTA3DW57AH2/graph.json","events_json":"https://pith.science/api/pith-number/3ZC5F5F7772TN7TWTA3DW57AH2/events.json","paper":"https://pith.science/paper/3ZC5F5F7"},"agent_actions":{"view_html":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2","download_json":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2.json","view_paper":"https://pith.science/paper/3ZC5F5F7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13332&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZC5F5F7772TN7TWTA3DW57AH2/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZC5F5F7772TN7TWTA3DW57AH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2/action/storage_attestation","attest_author":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2/action/author_attestation","sign_citation":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2/action/citation_signature","submit_replication":"https://pith.science/pith/3ZC5F5F7772TN7TWTA3DW57AH2/action/replication_record"}},"created_at":"2026-07-05T00:58:58.153652+00:00","updated_at":"2026-07-05T00:58:58.153652+00:00"}