{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WDARDB43M5SUUILXTX53BCKENE","short_pith_number":"pith:WDARDB43","schema_version":"1.0","canonical_sha256":"b0c111879b67654a21779dfbb089446901c71f9f5b9df26bd7a50cc0b352a7c0","source":{"kind":"arxiv","id":"1901.07114","version":2},"attestation_state":"computed","paper":{"title":"Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Tengyuan Liang, Xialiang Dou","submitted_at":"2019-01-21T23:15:16Z","abstract_excerpt":"Consider the problem: given the data pair $(\\mathbf{x}, \\mathbf{y})$ drawn from a population with $f_*(x) = \\mathbf{E}[\\mathbf{y} | \\mathbf{x} = x]$, specify a neural network model and run gradient flow on the weights over time until reaching any stationarity. How does $f_t$, the function computed by the neural network at time $t$, relate to $f_*$, in terms of approximation and representation? What are the provable benefits of the adaptive representation by neural networks compared to the pre-specified fixed basis representation in the classical nonparametric literature? We answer the above qu"},"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":"1901.07114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-21T23:15:16Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"106ee99b616269bb4f1e3c5ebd7d073b004dd173ff882d3a2861259ee25c90c4","abstract_canon_sha256":"a8cd252cca5735c89fe88c80d4469690de14ff00f86e2de4a4795aee28de1765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:45.401048Z","signature_b64":"0VOlxDLdSSGlCmWo4wmp8iAnHPlKkeESTigBUxmruqLnVkJuHOxAnAbYI3m/Nsu8Msv62aT9mvRE22XXhpFTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c111879b67654a21779dfbb089446901c71f9f5b9df26bd7a50cc0b352a7c0","last_reissued_at":"2026-07-05T01:21:45.400570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:45.400570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Tengyuan Liang, Xialiang Dou","submitted_at":"2019-01-21T23:15:16Z","abstract_excerpt":"Consider the problem: given the data pair $(\\mathbf{x}, \\mathbf{y})$ drawn from a population with $f_*(x) = \\mathbf{E}[\\mathbf{y} | \\mathbf{x} = x]$, specify a neural network model and run gradient flow on the weights over time until reaching any stationarity. How does $f_t$, the function computed by the neural network at time $t$, relate to $f_*$, in terms of approximation and representation? What are the provable benefits of the adaptive representation by neural networks compared to the pre-specified fixed basis representation in the classical nonparametric literature? We answer the above qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07114","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/1901.07114/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":"1901.07114","created_at":"2026-07-05T01:21:45.400621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07114v2","created_at":"2026-07-05T01:21:45.400621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07114","created_at":"2026-07-05T01:21:45.400621+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDARDB43M5SU","created_at":"2026-07-05T01:21:45.400621+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDARDB43M5SUUILX","created_at":"2026-07-05T01:21:45.400621+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDARDB43","created_at":"2026-07-05T01:21:45.400621+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/WDARDB43M5SUUILXTX53BCKENE","json":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE.json","graph_json":"https://pith.science/api/pith-number/WDARDB43M5SUUILXTX53BCKENE/graph.json","events_json":"https://pith.science/api/pith-number/WDARDB43M5SUUILXTX53BCKENE/events.json","paper":"https://pith.science/paper/WDARDB43"},"agent_actions":{"view_html":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE","download_json":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE.json","view_paper":"https://pith.science/paper/WDARDB43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07114&json=true","fetch_graph":"https://pith.science/api/pith-number/WDARDB43M5SUUILXTX53BCKENE/graph.json","fetch_events":"https://pith.science/api/pith-number/WDARDB43M5SUUILXTX53BCKENE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE/action/storage_attestation","attest_author":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE/action/author_attestation","sign_citation":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE/action/citation_signature","submit_replication":"https://pith.science/pith/WDARDB43M5SUUILXTX53BCKENE/action/replication_record"}},"created_at":"2026-07-05T01:21:45.400621+00:00","updated_at":"2026-07-05T01:21:45.400621+00:00"}