{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IVFEEZGS2YT7X67XIHLFKGEHRB","short_pith_number":"pith:IVFEEZGS","schema_version":"1.0","canonical_sha256":"454a4264d2d627fbfbf741d655188788661f299c8daa4bc5b18363cae868ae64","source":{"kind":"arxiv","id":"2011.06158","version":3},"attestation_state":"computed","paper":{"title":"Mostly Harmless Machine Learning: Learning Optimal Instruments in Linear IV Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Daniel L. Chen, Greg Lewis, Jiafeng Chen","submitted_at":"2020-11-12T01:55:11Z","abstract_excerpt":"We offer straightforward theoretical results that justify incorporating machine learning in the standard linear instrumental variable setting. The key idea is to use machine learning, combined with sample-splitting, to predict the treatment variable from the instrument and any exogenous covariates, and then use this predicted treatment and the covariates as technical instruments to recover the coefficients in the second-stage. This allows the researcher to extract non-linear co-variation between the treatment and instrument that may dramatically improve estimation precision and robustness by b"},"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":"2011.06158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2020-11-12T01:55:11Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"5198864ee4bb122ab2ea3a9b0b725f70576c8a26308acb7fa373cf4973377edb","abstract_canon_sha256":"f500fd619b6ccb77a5e1489666949f851b65684c6606d8827f5a57e3fcde35d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:41.956972Z","signature_b64":"Z5ZfQARxvEmmbw2muj8wE8IVYZxLG0xJTCmq7q9gKIrhDvOBRuzsdDcsEIzJw8Cz1TpK8pqql/FPq1d0Cv7EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454a4264d2d627fbfbf741d655188788661f299c8daa4bc5b18363cae868ae64","last_reissued_at":"2026-07-05T02:50:41.956603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:41.956603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mostly Harmless Machine Learning: Learning Optimal Instruments in Linear IV Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Daniel L. Chen, Greg Lewis, Jiafeng Chen","submitted_at":"2020-11-12T01:55:11Z","abstract_excerpt":"We offer straightforward theoretical results that justify incorporating machine learning in the standard linear instrumental variable setting. The key idea is to use machine learning, combined with sample-splitting, to predict the treatment variable from the instrument and any exogenous covariates, and then use this predicted treatment and the covariates as technical instruments to recover the coefficients in the second-stage. This allows the researcher to extract non-linear co-variation between the treatment and instrument that may dramatically improve estimation precision and robustness by b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06158","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/2011.06158/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":"2011.06158","created_at":"2026-07-05T02:50:41.956661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06158v3","created_at":"2026-07-05T02:50:41.956661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06158","created_at":"2026-07-05T02:50:41.956661+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVFEEZGS2YT7","created_at":"2026-07-05T02:50:41.956661+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVFEEZGS2YT7X67X","created_at":"2026-07-05T02:50:41.956661+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVFEEZGS","created_at":"2026-07-05T02:50:41.956661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13422","citing_title":"Machine learning the first stage in 2SLS: Practical guidance from bias decomposition and simulation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB","json":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB.json","graph_json":"https://pith.science/api/pith-number/IVFEEZGS2YT7X67XIHLFKGEHRB/graph.json","events_json":"https://pith.science/api/pith-number/IVFEEZGS2YT7X67XIHLFKGEHRB/events.json","paper":"https://pith.science/paper/IVFEEZGS"},"agent_actions":{"view_html":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB","download_json":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB.json","view_paper":"https://pith.science/paper/IVFEEZGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06158&json=true","fetch_graph":"https://pith.science/api/pith-number/IVFEEZGS2YT7X67XIHLFKGEHRB/graph.json","fetch_events":"https://pith.science/api/pith-number/IVFEEZGS2YT7X67XIHLFKGEHRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB/action/storage_attestation","attest_author":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB/action/author_attestation","sign_citation":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB/action/citation_signature","submit_replication":"https://pith.science/pith/IVFEEZGS2YT7X67XIHLFKGEHRB/action/replication_record"}},"created_at":"2026-07-05T02:50:41.956661+00:00","updated_at":"2026-07-05T02:50:41.956661+00:00"}