{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:52NKXIGFARBDITXTQAT57QLXEH","short_pith_number":"pith:52NKXIGF","canonical_record":{"source":{"id":"2311.14609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-24T17:04:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ada92a62f56834a5f46e46695b0479626cf1767071a1c410c168e6b06bffa872","abstract_canon_sha256":"607f25cbd986d4f7421a806aab7250a0e9bb5fab5a3d1c0260e78db1a2e499d3"},"schema_version":"1.0"},"canonical_sha256":"ee9aaba0c50442344ef38027dfc17721d4f499f2d7469e681fbe6bae68a05969","source":{"kind":"arxiv","id":"2311.14609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14609","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14609v1","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14609","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"52NKXIGFARBD","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"52NKXIGFARBDITXT","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"52NKXIGF","created_at":"2026-07-05T07:16:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:52NKXIGFARBDITXTQAT57QLXEH","target":"record","payload":{"canonical_record":{"source":{"id":"2311.14609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-24T17:04:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ada92a62f56834a5f46e46695b0479626cf1767071a1c410c168e6b06bffa872","abstract_canon_sha256":"607f25cbd986d4f7421a806aab7250a0e9bb5fab5a3d1c0260e78db1a2e499d3"},"schema_version":"1.0"},"canonical_sha256":"ee9aaba0c50442344ef38027dfc17721d4f499f2d7469e681fbe6bae68a05969","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:21.765454Z","signature_b64":"2XXD5q9WEWbG/FKvz0Ost4uCGzSEqMr0q98XDVEq2IikI1KxKW06HYrGHNbYzuYBGt6RWYN7/BtuTKEVSVrWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee9aaba0c50442344ef38027dfc17721d4f499f2d7469e681fbe6bae68a05969","last_reissued_at":"2026-07-05T07:16:21.764923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:21.764923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.14609","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HzOT9uNk2hFCbKpJ95dgenSbkTerJtFVu8hqjquaTDGJKKNRig+2qI0Kdn8ahelpDm0GKSWRXRuJ0YErWlFCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:49:15.256868Z"},"content_sha256":"38acd55466165d393157ffaf4d94cbe4083f653167d90c7e9e2808d7cff9611a","schema_version":"1.0","event_id":"sha256:38acd55466165d393157ffaf4d94cbe4083f653167d90c7e9e2808d7cff9611a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:52NKXIGFARBDITXTQAT57QLXEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Kohler, Selina Drews","submitted_at":"2023-11-24T17:04:21Z","abstract_excerpt":"Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L_2$ risk are universally consistent and achieve good rates of convergence. In this paper, we show that the regularization term is not necessary to obtain similar results. In the case of a suitably chosen initialization of the network, a suitable number of gradient descent steps, and a suitable step size we show that an estimate without a regularization term is universally consistent for bounded predictor variables. Additionally, we show that if "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14609","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/2311.14609/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+2nDdFSu1njbB4UBX6cgJksrs/I7M3U5haDEltV3cnaTqjOHx+RWYmyxDTbiK6lJnQBh4A2ZZVzmt6VEKAzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:49:15.257271Z"},"content_sha256":"e3b0a0c0d24d9ba375b28c306db1e1996f35dbe92975cb11f3e319b53c6277aa","schema_version":"1.0","event_id":"sha256:e3b0a0c0d24d9ba375b28c306db1e1996f35dbe92975cb11f3e319b53c6277aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52NKXIGFARBDITXTQAT57QLXEH/bundle.json","state_url":"https://pith.science/pith/52NKXIGFARBDITXTQAT57QLXEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52NKXIGFARBDITXTQAT57QLXEH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T00:49:15Z","links":{"resolver":"https://pith.science/pith/52NKXIGFARBDITXTQAT57QLXEH","bundle":"https://pith.science/pith/52NKXIGFARBDITXTQAT57QLXEH/bundle.json","state":"https://pith.science/pith/52NKXIGFARBDITXTQAT57QLXEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52NKXIGFARBDITXTQAT57QLXEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:52NKXIGFARBDITXTQAT57QLXEH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"607f25cbd986d4f7421a806aab7250a0e9bb5fab5a3d1c0260e78db1a2e499d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-24T17:04:21Z","title_canon_sha256":"ada92a62f56834a5f46e46695b0479626cf1767071a1c410c168e6b06bffa872"},"schema_version":"1.0","source":{"id":"2311.14609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14609","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14609v1","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14609","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"52NKXIGFARBD","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"52NKXIGFARBDITXT","created_at":"2026-07-05T07:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"52NKXIGF","created_at":"2026-07-05T07:16:21Z"}],"graph_snapshots":[{"event_id":"sha256:e3b0a0c0d24d9ba375b28c306db1e1996f35dbe92975cb11f3e319b53c6277aa","target":"graph","created_at":"2026-07-05T07:16:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.14609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L_2$ risk are universally consistent and achieve good rates of convergence. In this paper, we show that the regularization term is not necessary to obtain similar results. In the case of a suitably chosen initialization of the network, a suitable number of gradient descent steps, and a suitable step size we show that an estimate without a regularization term is universally consistent for bounded predictor variables. Additionally, we show that if ","authors_text":"Michael Kohler, Selina Drews","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-24T17:04:21Z","title":"Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14609","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38acd55466165d393157ffaf4d94cbe4083f653167d90c7e9e2808d7cff9611a","target":"record","created_at":"2026-07-05T07:16:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"607f25cbd986d4f7421a806aab7250a0e9bb5fab5a3d1c0260e78db1a2e499d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-24T17:04:21Z","title_canon_sha256":"ada92a62f56834a5f46e46695b0479626cf1767071a1c410c168e6b06bffa872"},"schema_version":"1.0","source":{"id":"2311.14609","kind":"arxiv","version":1}},"canonical_sha256":"ee9aaba0c50442344ef38027dfc17721d4f499f2d7469e681fbe6bae68a05969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee9aaba0c50442344ef38027dfc17721d4f499f2d7469e681fbe6bae68a05969","first_computed_at":"2026-07-05T07:16:21.764923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:21.764923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2XXD5q9WEWbG/FKvz0Ost4uCGzSEqMr0q98XDVEq2IikI1KxKW06HYrGHNbYzuYBGt6RWYN7/BtuTKEVSVrWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:21.765454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38acd55466165d393157ffaf4d94cbe4083f653167d90c7e9e2808d7cff9611a","sha256:e3b0a0c0d24d9ba375b28c306db1e1996f35dbe92975cb11f3e319b53c6277aa"],"state_sha256":"744a60a599cbc7db406a89a5c69a5f7fc8affdbf8f0b9661e792ce33c0d26336"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClP7N+XQZbTPuLri5w9K4Z47SA46IpkMDZ1kEtbONH+4xWfrUVxKSe5OHXu7JO20LwBw4TgLHteXlfnmWioeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T00:49:15.260809Z","bundle_sha256":"6a3d212d936ff7e7bd7bbccd779c9bfdd3f7fcbadcffb09e188db7d0442dbee5"}}