{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TYAMIY6P3HEJGPRZYKB5Z6ZBJL","short_pith_number":"pith:TYAMIY6P","schema_version":"1.0","canonical_sha256":"9e00c463cfd9c8933e39c283dcfb214ac77b528d7de9b0c870d8dc63edcca731","source":{"kind":"arxiv","id":"2507.04779","version":2},"attestation_state":"computed","paper":{"title":"Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Chien-Ming Chi","submitted_at":"2025-07-07T08:55:28Z","abstract_excerpt":"We propose o1Neuro, a new neural network model built on sparse indicator activation neurons, with two key statistical properties. (1) Constructive universal approximation: At the population level, a deep o1Neuro can approximate any measurable function of $\\boldsymbol{X}$, while a shallow o1Neuro suffices for additive models with two-way interaction components, including XOR and univariate terms, assuming $\\boldsymbol{X} \\in [0,1]^p$ has bounded density. Combined with prior work showing that a single-hidden-layer non-sparse network is a universal approximator, this highlights a trade-off betwee"},"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":"2507.04779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-07T08:55:28Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"6ef11bb384d4f3827ee4699d2fb424c0ef8196f9ed8fa072e30b3d9d48787499","abstract_canon_sha256":"fdc78c565b815d80966341355186f9482abae8ca631700a259fc8ea252352745"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:45.263093Z","signature_b64":"towceLwR+cUBLu2a9wzxqIKy1KmL5mDkdlCezRgZQJotA/vrkIqcuOgmgJz/xWJhV2o7IGubZJJilmcG7u07Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e00c463cfd9c8933e39c283dcfb214ac77b528d7de9b0c870d8dc63edcca731","last_reissued_at":"2026-07-05T12:09:45.262461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:45.262461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Chien-Ming Chi","submitted_at":"2025-07-07T08:55:28Z","abstract_excerpt":"We propose o1Neuro, a new neural network model built on sparse indicator activation neurons, with two key statistical properties. (1) Constructive universal approximation: At the population level, a deep o1Neuro can approximate any measurable function of $\\boldsymbol{X}$, while a shallow o1Neuro suffices for additive models with two-way interaction components, including XOR and univariate terms, assuming $\\boldsymbol{X} \\in [0,1]^p$ has bounded density. Combined with prior work showing that a single-hidden-layer non-sparse network is a universal approximator, this highlights a trade-off betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04779","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/2507.04779/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":"2507.04779","created_at":"2026-07-05T12:09:45.262535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04779v2","created_at":"2026-07-05T12:09:45.262535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04779","created_at":"2026-07-05T12:09:45.262535+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYAMIY6P3HEJ","created_at":"2026-07-05T12:09:45.262535+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYAMIY6P3HEJGPRZ","created_at":"2026-07-05T12:09:45.262535+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYAMIY6P","created_at":"2026-07-05T12:09:45.262535+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/TYAMIY6P3HEJGPRZYKB5Z6ZBJL","json":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL.json","graph_json":"https://pith.science/api/pith-number/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/graph.json","events_json":"https://pith.science/api/pith-number/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/events.json","paper":"https://pith.science/paper/TYAMIY6P"},"agent_actions":{"view_html":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL","download_json":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL.json","view_paper":"https://pith.science/paper/TYAMIY6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04779&json=true","fetch_graph":"https://pith.science/api/pith-number/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/graph.json","fetch_events":"https://pith.science/api/pith-number/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/action/storage_attestation","attest_author":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/action/author_attestation","sign_citation":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/action/citation_signature","submit_replication":"https://pith.science/pith/TYAMIY6P3HEJGPRZYKB5Z6ZBJL/action/replication_record"}},"created_at":"2026-07-05T12:09:45.262535+00:00","updated_at":"2026-07-05T12:09:45.262535+00:00"}