{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4JUULF6ZDQV2QQSUG7ITO2ORMH","short_pith_number":"pith:4JUULF6Z","schema_version":"1.0","canonical_sha256":"e2694597d91c2ba8425437d13769d161eb68cdb4f217ad744ef6a6b5983a5503","source":{"kind":"arxiv","id":"1702.08882","version":7},"attestation_state":"computed","paper":{"title":"Deep Semi-Random Features for Nonlinear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xie, Kenji Kawaguchi, Le Song, Vikas Verma","submitted_at":"2017-02-28T17:47:34Z","abstract_excerpt":"We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the model classes contain an arbitrarily good function as the width increases (universality), and despite non-convexity, we can find such a good function (optimization theory) that generalizes to unseen new data (generalization bound). For deep models, with no unrealistic assumptions,"},"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":"1702.08882","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T17:47:34Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"6e15ebb38a9c93da9fc8c609cb743ce3a5ec38516321d5f45fccab339d8580fd","abstract_canon_sha256":"5dcbc784ecc89bd991af545d660b31b491907b323a7cc66e23a63de4682c1eb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:05.488732Z","signature_b64":"Bo7e+bW3Ko/pU3K52mKG6l75q0MssTFC3eHD0uWerNQa4nEc2sXIU96AzM9cMGALyf13F0PV3JJ+8f5v0I3rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2694597d91c2ba8425437d13769d161eb68cdb4f217ad744ef6a6b5983a5503","last_reissued_at":"2026-05-18T00:30:05.488234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:05.488234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Semi-Random Features for Nonlinear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xie, Kenji Kawaguchi, Le Song, Vikas Verma","submitted_at":"2017-02-28T17:47:34Z","abstract_excerpt":"We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the model classes contain an arbitrarily good function as the width increases (universality), and despite non-convexity, we can find such a good function (optimization theory) that generalizes to unseen new data (generalization bound). For deep models, with no unrealistic assumptions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08882","kind":"arxiv","version":7},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1702.08882","created_at":"2026-05-18T00:30:05.488311+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08882v7","created_at":"2026-05-18T00:30:05.488311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08882","created_at":"2026-05-18T00:30:05.488311+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JUULF6ZDQV2","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JUULF6ZDQV2QQSU","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JUULF6Z","created_at":"2026-05-18T12:31:00.734936+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/4JUULF6ZDQV2QQSUG7ITO2ORMH","json":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH.json","graph_json":"https://pith.science/api/pith-number/4JUULF6ZDQV2QQSUG7ITO2ORMH/graph.json","events_json":"https://pith.science/api/pith-number/4JUULF6ZDQV2QQSUG7ITO2ORMH/events.json","paper":"https://pith.science/paper/4JUULF6Z"},"agent_actions":{"view_html":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH","download_json":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH.json","view_paper":"https://pith.science/paper/4JUULF6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08882&json=true","fetch_graph":"https://pith.science/api/pith-number/4JUULF6ZDQV2QQSUG7ITO2ORMH/graph.json","fetch_events":"https://pith.science/api/pith-number/4JUULF6ZDQV2QQSUG7ITO2ORMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH/action/storage_attestation","attest_author":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH/action/author_attestation","sign_citation":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH/action/citation_signature","submit_replication":"https://pith.science/pith/4JUULF6ZDQV2QQSUG7ITO2ORMH/action/replication_record"}},"created_at":"2026-05-18T00:30:05.488311+00:00","updated_at":"2026-05-18T00:30:05.488311+00:00"}