{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XM6DTJRUNBNJPWQR3DEV7GRSHY","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":"79b54fb7bc902d83f09bb15d2d7880fa7c26d4d81f73a84f9d56ad18445621b8","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:27Z","title_canon_sha256":"d425fe1bafc61e1eb3233e8e561f01f816091e5b1c223d301e2512a74e0008bf"},"schema_version":"1.0","source":{"id":"1901.02220","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02220","created_at":"2026-07-05T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02220v4","created_at":"2026-07-05T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02220","created_at":"2026-07-05T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"XM6DTJRUNBNJ","created_at":"2026-07-05T02:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"XM6DTJRUNBNJPWQR","created_at":"2026-07-05T02:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"XM6DTJRU","created_at":"2026-07-05T02:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:6d8946a2d6677699ae50d587596a3163dd24720e60c25f4f8faaf70947342931","target":"graph","created_at":"2026-07-05T02:22:20Z","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/1901.02220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper develops fundamental limits of deep neural network learning by characterizing what is possible if no constraints are imposed on the learning algorithm and on the amount of training data. Concretely, we consider Kolmogorov-optimal approximation through deep neural networks with the guiding theme being a relation between the complexity of the function (class) to be approximated and the complexity of the approximating network in terms of connectivity and memory requirements for storing the network topology and the associated quantized weights. The theory we develop establishes that dee","authors_text":"Dennis Elbr\\\"achter, Dmytro Perekrestenko, Helmut B\\\"olcskei, Philipp Grohs","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:27Z","title":"Deep Neural Network Approximation Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02220","kind":"arxiv","version":4},"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":"sha256:7c2a24f476b0db865c27b0c7df2f47c668343a65c32fa405d66a0dbac4b97192","target":"record","created_at":"2026-07-05T02:22:20Z","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":"79b54fb7bc902d83f09bb15d2d7880fa7c26d4d81f73a84f9d56ad18445621b8","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:27Z","title_canon_sha256":"d425fe1bafc61e1eb3233e8e561f01f816091e5b1c223d301e2512a74e0008bf"},"schema_version":"1.0","source":{"id":"1901.02220","kind":"arxiv","version":4}},"canonical_sha256":"bb3c39a634685a97da11d8c95f9a323e016f8b2179ac14495a8c1ae3334503b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb3c39a634685a97da11d8c95f9a323e016f8b2179ac14495a8c1ae3334503b3","first_computed_at":"2026-07-05T02:22:20.567438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:20.567438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"14G3tci2XDAgOIiy/8H2R9DKCzB+RdJ+ozi1eXq50Uid/4YsR7WhTAyNGwNpcZwvIAdvCocRXA2JkSopTCpRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:20.567899Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02220","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c2a24f476b0db865c27b0c7df2f47c668343a65c32fa405d66a0dbac4b97192","sha256:6d8946a2d6677699ae50d587596a3163dd24720e60c25f4f8faaf70947342931"],"state_sha256":"b1ecce5e3576d987d8e65e3c831d4d0f5e9724f49608efab9ae416cc268d6b6c"}