{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5NFKQOL7R3TAAHLKPLBHM3JTJE","short_pith_number":"pith:5NFKQOL7","schema_version":"1.0","canonical_sha256":"eb4aa8397f8ee6001d6a7ac2766d334905467b0dfa8b34c0d2e9982800a54eb1","source":{"kind":"arxiv","id":"1809.09953","version":3},"attestation_state":"computed","paper":{"title":"Deep Neural Networks for Estimation and Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Max H. Farrell, Sanjog Misra, Tengyuan Liang","submitted_at":"2018-09-26T13:04:23Z","abstract_excerpt":"We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets. Our new rates are sufficiently fast (in some cases minimax optimal) to allow us to establish valid second-step inference after first-step estimation with deep learning, a result also new to the literature. Our estimation rates and semiparametric inference results handle the current standard architecture: fully connected feedforward neural networks (multi-layer perceptrons), with the now-common rectified linear unit activation function and a depth ex"},"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":"1809.09953","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2018-09-26T13:04:23Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"49045ef8c1e7f9b2455e74435d566d3c495296e25f1518ac44364ea6e78e3d26","abstract_canon_sha256":"15650d6ccd70910ae3e4320ba14ca576bb341866352aba6183926bb7858a1672"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:42.614103Z","signature_b64":"LwTO/1yq+0SBsM9ueVL5gPt6WjiZhVz18i8sBjGSsT4Cstef1/Cfjb/RPYJpGVsOGMSqrR5zDIg3yHIswvPuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4aa8397f8ee6001d6a7ac2766d334905467b0dfa8b34c0d2e9982800a54eb1","last_reissued_at":"2026-07-05T02:07:42.613654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:42.613654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks for Estimation and Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Max H. Farrell, Sanjog Misra, Tengyuan Liang","submitted_at":"2018-09-26T13:04:23Z","abstract_excerpt":"We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets. Our new rates are sufficiently fast (in some cases minimax optimal) to allow us to establish valid second-step inference after first-step estimation with deep learning, a result also new to the literature. Our estimation rates and semiparametric inference results handle the current standard architecture: fully connected feedforward neural networks (multi-layer perceptrons), with the now-common rectified linear unit activation function and a depth ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09953","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/1809.09953/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":"1809.09953","created_at":"2026-07-05T02:07:42.613721+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09953v3","created_at":"2026-07-05T02:07:42.613721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09953","created_at":"2026-07-05T02:07:42.613721+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NFKQOL7R3TA","created_at":"2026-07-05T02:07:42.613721+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NFKQOL7R3TAAHLK","created_at":"2026-07-05T02:07:42.613721+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NFKQOL7","created_at":"2026-07-05T02:07:42.613721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02210","citing_title":"Using Wasserstein Generative Adversarial Networks for the Design of Monte Carlo Simulations","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE","json":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE.json","graph_json":"https://pith.science/api/pith-number/5NFKQOL7R3TAAHLKPLBHM3JTJE/graph.json","events_json":"https://pith.science/api/pith-number/5NFKQOL7R3TAAHLKPLBHM3JTJE/events.json","paper":"https://pith.science/paper/5NFKQOL7"},"agent_actions":{"view_html":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE","download_json":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE.json","view_paper":"https://pith.science/paper/5NFKQOL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09953&json=true","fetch_graph":"https://pith.science/api/pith-number/5NFKQOL7R3TAAHLKPLBHM3JTJE/graph.json","fetch_events":"https://pith.science/api/pith-number/5NFKQOL7R3TAAHLKPLBHM3JTJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE/action/storage_attestation","attest_author":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE/action/author_attestation","sign_citation":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE/action/citation_signature","submit_replication":"https://pith.science/pith/5NFKQOL7R3TAAHLKPLBHM3JTJE/action/replication_record"}},"created_at":"2026-07-05T02:07:42.613721+00:00","updated_at":"2026-07-05T02:07:42.613721+00:00"}