{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FU3ELYKBSZ6U3HZBCGGKX3N2ZH","short_pith_number":"pith:FU3ELYKB","schema_version":"1.0","canonical_sha256":"2d3645e141967d4d9f21118cabedbac9e5d552edbba3c8b7f0a7554dc29c7d43","source":{"kind":"arxiv","id":"2405.08276","version":1},"attestation_state":"computed","paper":{"title":"Scalable Subsampling Inference for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Dimitris N. Politis, Kejin Wu","submitted_at":"2024-05-14T02:11:38Z","abstract_excerpt":"Deep neural networks (DNN) has received increasing attention in machine learning applications in the last several years. Recently, a non-asymptotic error bound has been developed to measure the performance of the fully connected DNN estimator with ReLU activation functions for estimating regression models. The paper at hand gives a small improvement on the current error bound based on the latest results on the approximation ability of DNN. More importantly, however, a non-random subsampling technique--scalable subsampling--is applied to construct a `subagged' DNN estimator. Under regularity co"},"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":"2405.08276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-14T02:11:38Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"b9da730d5e2c6ebdd7a6649741054c1dd70bf43a9361f5b63d31415d5c2a040f","abstract_canon_sha256":"2ecc3fbfd9a80d5e87d704da728ec0004a245374250ea99a0507c13d4c0a37e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:58.054665Z","signature_b64":"HG1lxlVaS8/BJofK1szkegbFbDI/GfBXwUonSWrBoqCCqu7n+SgJRuY7oAql8q5pwrgOSeI77x2/rQ20TzqJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3645e141967d4d9f21118cabedbac9e5d552edbba3c8b7f0a7554dc29c7d43","last_reissued_at":"2026-07-05T08:18:58.054200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:58.054200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Subsampling Inference for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Dimitris N. Politis, Kejin Wu","submitted_at":"2024-05-14T02:11:38Z","abstract_excerpt":"Deep neural networks (DNN) has received increasing attention in machine learning applications in the last several years. Recently, a non-asymptotic error bound has been developed to measure the performance of the fully connected DNN estimator with ReLU activation functions for estimating regression models. The paper at hand gives a small improvement on the current error bound based on the latest results on the approximation ability of DNN. More importantly, however, a non-random subsampling technique--scalable subsampling--is applied to construct a `subagged' DNN estimator. Under regularity co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08276","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/2405.08276/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":"2405.08276","created_at":"2026-07-05T08:18:58.054256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08276v1","created_at":"2026-07-05T08:18:58.054256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08276","created_at":"2026-07-05T08:18:58.054256+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU3ELYKBSZ6U","created_at":"2026-07-05T08:18:58.054256+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU3ELYKBSZ6U3HZB","created_at":"2026-07-05T08:18:58.054256+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU3ELYKB","created_at":"2026-07-05T08:18:58.054256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01325","citing_title":"Fusion Sampling Validation in Data Partitioning for Machine Learning","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH","json":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH.json","graph_json":"https://pith.science/api/pith-number/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/graph.json","events_json":"https://pith.science/api/pith-number/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/events.json","paper":"https://pith.science/paper/FU3ELYKB"},"agent_actions":{"view_html":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH","download_json":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH.json","view_paper":"https://pith.science/paper/FU3ELYKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08276&json=true","fetch_graph":"https://pith.science/api/pith-number/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/graph.json","fetch_events":"https://pith.science/api/pith-number/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/action/storage_attestation","attest_author":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/action/author_attestation","sign_citation":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/action/citation_signature","submit_replication":"https://pith.science/pith/FU3ELYKBSZ6U3HZBCGGKX3N2ZH/action/replication_record"}},"created_at":"2026-07-05T08:18:58.054256+00:00","updated_at":"2026-07-05T08:18:58.054256+00:00"}