{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UF2NKNWMX7NE46T5BB6ENGNNFB","short_pith_number":"pith:UF2NKNWM","schema_version":"1.0","canonical_sha256":"a174d536ccbfda4e7a7d087c4699ad28451faf5d06548b17a70f4e5afd1a9790","source":{"kind":"arxiv","id":"1712.05440","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"George Philipp, Jaime G. Carbonell","submitted_at":"2017-12-14T20:31:29Z","abstract_excerpt":"Automatically determining the optimal size of a neural network for a given task without prior information currently requires an expensive global search and training many networks from scratch. In this paper, we address the problem of automatically finding a good network size during a single training cycle. We introduce *nonparametric neural networks*, a non-probabilistic framework for conducting optimization over all possible network sizes and prove its soundness when network growth is limited via an L_p penalty. We train networks under this framework by continuously adding new units while eli"},"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":"1712.05440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T20:31:29Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"fc73db334fe9d36dbd86b79f142376094df9ee1fe01c4cdc1b4d101aeec7a1f5","abstract_canon_sha256":"ba0c143e0d93735cce6b1ceba36dc2f6862c5b928ee456e7dc888f62bb3a2e9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:56.458512Z","signature_b64":"5NV/PBa65Rb70e+Y/lhXgWZxIqlR0676zBTg5o3L1UGnWx7HYawRmGz/MDfDL20zMgOan2lPmAyPSJ+sRMTfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a174d536ccbfda4e7a7d087c4699ad28451faf5d06548b17a70f4e5afd1a9790","last_reissued_at":"2026-05-18T00:27:56.457849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:56.457849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"George Philipp, Jaime G. Carbonell","submitted_at":"2017-12-14T20:31:29Z","abstract_excerpt":"Automatically determining the optimal size of a neural network for a given task without prior information currently requires an expensive global search and training many networks from scratch. In this paper, we address the problem of automatically finding a good network size during a single training cycle. We introduce *nonparametric neural networks*, a non-probabilistic framework for conducting optimization over all possible network sizes and prove its soundness when network growth is limited via an L_p penalty. We train networks under this framework by continuously adding new units while eli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05440","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":""},"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":"1712.05440","created_at":"2026-05-18T00:27:56.457950+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.05440v1","created_at":"2026-05-18T00:27:56.457950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05440","created_at":"2026-05-18T00:27:56.457950+00:00"},{"alias_kind":"pith_short_12","alias_value":"UF2NKNWMX7NE","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UF2NKNWMX7NE46T5","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UF2NKNWM","created_at":"2026-05-18T12:31:46.661854+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/UF2NKNWMX7NE46T5BB6ENGNNFB","json":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB.json","graph_json":"https://pith.science/api/pith-number/UF2NKNWMX7NE46T5BB6ENGNNFB/graph.json","events_json":"https://pith.science/api/pith-number/UF2NKNWMX7NE46T5BB6ENGNNFB/events.json","paper":"https://pith.science/paper/UF2NKNWM"},"agent_actions":{"view_html":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB","download_json":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB.json","view_paper":"https://pith.science/paper/UF2NKNWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.05440&json=true","fetch_graph":"https://pith.science/api/pith-number/UF2NKNWMX7NE46T5BB6ENGNNFB/graph.json","fetch_events":"https://pith.science/api/pith-number/UF2NKNWMX7NE46T5BB6ENGNNFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB/action/storage_attestation","attest_author":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB/action/author_attestation","sign_citation":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB/action/citation_signature","submit_replication":"https://pith.science/pith/UF2NKNWMX7NE46T5BB6ENGNNFB/action/replication_record"}},"created_at":"2026-05-18T00:27:56.457950+00:00","updated_at":"2026-05-18T00:27:56.457950+00:00"}