{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FB4S7V7UFPEXJ2O6ZN4IKJLA2N","short_pith_number":"pith:FB4S7V7U","canonical_record":{"source":{"id":"1809.03090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-10T02:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b2d6baf3577fcaebbb66010625a286c22d6223aaff4b24e22edd1da281d4a0f","abstract_canon_sha256":"dc021b07a93c64de58075cdc2ddc1b99f0689d1d16c8c1eac2ef5b0da3e8126e"},"schema_version":"1.0"},"canonical_sha256":"28792fd7f42bc974e9decb78852560d3661991772814480de4297030591e748d","source":{"kind":"arxiv","id":"1809.03090","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03090","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03090v2","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03090","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"FB4S7V7UFPEX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FB4S7V7UFPEXJ2O6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FB4S7V7U","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FB4S7V7UFPEXJ2O6ZN4IKJLA2N","target":"record","payload":{"canonical_record":{"source":{"id":"1809.03090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-10T02:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b2d6baf3577fcaebbb66010625a286c22d6223aaff4b24e22edd1da281d4a0f","abstract_canon_sha256":"dc021b07a93c64de58075cdc2ddc1b99f0689d1d16c8c1eac2ef5b0da3e8126e"},"schema_version":"1.0"},"canonical_sha256":"28792fd7f42bc974e9decb78852560d3661991772814480de4297030591e748d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:27.693893Z","signature_b64":"Wz82If5ZlUmdI1M4oCP25uNoNARBCRlgmQ+mzsGxvFEz0gnU8+HQY2zKET410wCRaH5IPYAQE6tRN85Z5n9fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28792fd7f42bc974e9decb78852560d3661991772814480de4297030591e748d","last_reissued_at":"2026-05-18T00:05:27.693419Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:27.693419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.03090","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqxKuTXr/fRa1YkFQD1iUzIWQOJsy5CCjgcKm0zE5AOWRTlzrBkMbSNR0402tMhyQIiDNs+iJdidH05k73nFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:46:50.459514Z"},"content_sha256":"2b5266925b2e9b7fdbdda0348c95b5c6ee32d09fa391bdfc27e3cf280d37c381","schema_version":"1.0","event_id":"sha256:2b5266925b2e9b7fdbdda0348c95b5c6ee32d09fa391bdfc27e3cf280d37c381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FB4S7V7UFPEXJ2O6ZN4IKJLA2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximation and Estimation for High-Dimensional Deep Learning Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew R. Barron, Jason M. Klusowski","submitted_at":"2018-09-10T02:21:40Z","abstract_excerpt":"It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this? The best available bounds on their metric entropy and associated complexity measures are essentially linear in the number of parameters, which is inadequate to explain this phenomenon. Here we examine the statistical risk (mean squared predictive error) of multi-layer networks with $\\ell^1$-type controls on their parameters and with ramp activation functions ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03090","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xi5yyzhM0YyVh/YobUABs3twxMFJJgeJKRhEkrMxVALeCt4nqMn7+ZE+cTvYQLREufiJ+fvYCW9IrOfjGt1WBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:46:50.460066Z"},"content_sha256":"133a5a536357fc97d842ff9ee4a680e0a6986f8b1e4bb498a03b7f6ad9521917","schema_version":"1.0","event_id":"sha256:133a5a536357fc97d842ff9ee4a680e0a6986f8b1e4bb498a03b7f6ad9521917"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/bundle.json","state_url":"https://pith.science/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/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":"2026-06-07T20:46:50Z","links":{"resolver":"https://pith.science/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N","bundle":"https://pith.science/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/bundle.json","state":"https://pith.science/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FB4S7V7UFPEXJ2O6ZN4IKJLA2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FB4S7V7UFPEXJ2O6ZN4IKJLA2N","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":"dc021b07a93c64de58075cdc2ddc1b99f0689d1d16c8c1eac2ef5b0da3e8126e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-10T02:21:40Z","title_canon_sha256":"4b2d6baf3577fcaebbb66010625a286c22d6223aaff4b24e22edd1da281d4a0f"},"schema_version":"1.0","source":{"id":"1809.03090","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03090","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03090v2","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03090","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"FB4S7V7UFPEX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FB4S7V7UFPEXJ2O6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FB4S7V7U","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:133a5a536357fc97d842ff9ee4a680e0a6986f8b1e4bb498a03b7f6ad9521917","target":"graph","created_at":"2026-05-18T00:05:27Z","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"},"paper":{"abstract_excerpt":"It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this? The best available bounds on their metric entropy and associated complexity measures are essentially linear in the number of parameters, which is inadequate to explain this phenomenon. Here we examine the statistical risk (mean squared predictive error) of multi-layer networks with $\\ell^1$-type controls on their parameters and with ramp activation functions (","authors_text":"Andrew R. Barron, Jason M. Klusowski","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-10T02:21:40Z","title":"Approximation and Estimation for High-Dimensional Deep Learning Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03090","kind":"arxiv","version":2},"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":"sha256:2b5266925b2e9b7fdbdda0348c95b5c6ee32d09fa391bdfc27e3cf280d37c381","target":"record","created_at":"2026-05-18T00:05:27Z","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":"dc021b07a93c64de58075cdc2ddc1b99f0689d1d16c8c1eac2ef5b0da3e8126e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-10T02:21:40Z","title_canon_sha256":"4b2d6baf3577fcaebbb66010625a286c22d6223aaff4b24e22edd1da281d4a0f"},"schema_version":"1.0","source":{"id":"1809.03090","kind":"arxiv","version":2}},"canonical_sha256":"28792fd7f42bc974e9decb78852560d3661991772814480de4297030591e748d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28792fd7f42bc974e9decb78852560d3661991772814480de4297030591e748d","first_computed_at":"2026-05-18T00:05:27.693419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:27.693419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wz82If5ZlUmdI1M4oCP25uNoNARBCRlgmQ+mzsGxvFEz0gnU8+HQY2zKET410wCRaH5IPYAQE6tRN85Z5n9fCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:27.693893Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03090","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b5266925b2e9b7fdbdda0348c95b5c6ee32d09fa391bdfc27e3cf280d37c381","sha256:133a5a536357fc97d842ff9ee4a680e0a6986f8b1e4bb498a03b7f6ad9521917"],"state_sha256":"f00ce7b601a69e14081551480d34261291a396bd42d26c25ff3864e546bc3290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XaPnfui9j9b1sVjO7Onaaa2W68xhT58wtxDXB55iGvAfanfqEyDJ+PJavMyil/8/QGCM/mm8yBAU+CDYyl1xAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T20:46:50.463338Z","bundle_sha256":"2114f2f617f0f3b4ca95941d5d13861bbd949f0397ba996983b89e73437b16f7"}}