{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DQLDGWFARMDWZPVJVHARNYM52R","short_pith_number":"pith:DQLDGWFA","schema_version":"1.0","canonical_sha256":"1c163358a08b076cbea9a9c116e19dd46d913b9c85f36833aa869604bc5f05be","source":{"kind":"arxiv","id":"1912.06732","version":2},"attestation_state":"computed","paper":{"title":"On the approximation of rough functions with deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Deep Ray, Siddhartha Mishra, Tim De Ryck","submitted_at":"2019-12-13T22:48:36Z","abstract_excerpt":"Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables the transfer of several desirable properties of the ENO procedure to deep neural networks, including its high-order accuracy at approximating Lipschitz functions. Numerical tests for the resulting neural networks show excellent performance for approximating solutions of nonlinear conservation laws and at data compression."},"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":"1912.06732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2019-12-13T22:48:36Z","cross_cats_sorted":["cs.LG","cs.NA","stat.ML"],"title_canon_sha256":"14df8cb300b1ff14c3d0c3cd5fa6cfd1666aefa405f3b20136654a2165fae3f6","abstract_canon_sha256":"fd4316c76ca40f7ad454bf5a39f4b75135726fbde63ac12453dcc7a360996ac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:16.058552Z","signature_b64":"UUuRmCKfnhH+yX2ErDN0fQM21Qj/vSHu6RXvIIpMKp7uo3fd4s4ppcMLKPjaoQd9MhS7xcV0ID4nLkwWqmgzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c163358a08b076cbea9a9c116e19dd46d913b9c85f36833aa869604bc5f05be","last_reissued_at":"2026-07-05T01:41:16.058142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:16.058142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the approximation of rough functions with deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Deep Ray, Siddhartha Mishra, Tim De Ryck","submitted_at":"2019-12-13T22:48:36Z","abstract_excerpt":"Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables the transfer of several desirable properties of the ENO procedure to deep neural networks, including its high-order accuracy at approximating Lipschitz functions. Numerical tests for the resulting neural networks show excellent performance for approximating solutions of nonlinear conservation laws and at data compression."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06732","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.06732/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":"1912.06732","created_at":"2026-07-05T01:41:16.058203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06732v2","created_at":"2026-07-05T01:41:16.058203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06732","created_at":"2026-07-05T01:41:16.058203+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQLDGWFARMDW","created_at":"2026-07-05T01:41:16.058203+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQLDGWFARMDWZPVJ","created_at":"2026-07-05T01:41:16.058203+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQLDGWFA","created_at":"2026-07-05T01:41:16.058203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R","json":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R.json","graph_json":"https://pith.science/api/pith-number/DQLDGWFARMDWZPVJVHARNYM52R/graph.json","events_json":"https://pith.science/api/pith-number/DQLDGWFARMDWZPVJVHARNYM52R/events.json","paper":"https://pith.science/paper/DQLDGWFA"},"agent_actions":{"view_html":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R","download_json":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R.json","view_paper":"https://pith.science/paper/DQLDGWFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06732&json=true","fetch_graph":"https://pith.science/api/pith-number/DQLDGWFARMDWZPVJVHARNYM52R/graph.json","fetch_events":"https://pith.science/api/pith-number/DQLDGWFARMDWZPVJVHARNYM52R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R/action/storage_attestation","attest_author":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R/action/author_attestation","sign_citation":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R/action/citation_signature","submit_replication":"https://pith.science/pith/DQLDGWFARMDWZPVJVHARNYM52R/action/replication_record"}},"created_at":"2026-07-05T01:41:16.058203+00:00","updated_at":"2026-07-05T01:41:16.058203+00:00"}