{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RZ5PZCITN7HQI75FTIMIMFFEAY","short_pith_number":"pith:RZ5PZCIT","schema_version":"1.0","canonical_sha256":"8e7afc89136fcf047fa59a188614a406118fa029249c7f2b989c2b21919724fe","source":{"kind":"arxiv","id":"2112.09181","version":2},"attestation_state":"computed","paper":{"title":"Approximation of functions with one-bit neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.NA","math.IT","math.NA"],"primary_cat":"cs.LG","authors_text":"C. Sinan G\\\"unt\\\"urk, Weilin Li","submitted_at":"2021-12-16T20:10:56Z","abstract_excerpt":"The celebrated universal approximation theorems for neural networks roughly state that any reasonable function can be arbitrarily well-approximated by a network whose parameters are appropriately chosen real numbers. This paper examines the approximation capabilities of one-bit neural networks -- those whose nonzero parameters are $\\pm a$ for some fixed $a\\not=0$. One of our main theorems shows that for any $f\\in C^s([0,1]^d)$ with $\\|f\\|_\\infty<1$ and error $\\varepsilon$, there is a $f_{NN}$ such that $|f(\\boldsymbol{x})-f_{NN}(\\boldsymbol{x})|\\leq \\varepsilon$ for all $\\boldsymbol{x}$ away f"},"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":"2112.09181","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T20:10:56Z","cross_cats_sorted":["cs.IT","cs.NA","math.IT","math.NA"],"title_canon_sha256":"c16828f8aaf25f3c5b5879bff64bc7b95e47b1739fb227682afeba2e9246006d","abstract_canon_sha256":"24ae6ca19b4af16656bc56bf0963137da5bce16eef811bc7a250f44ef5831d23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:39.054399Z","signature_b64":"BPrAZBFf14A1EnL4fkQpmOwR9oyKZUVxqVJETjlCa3Ofos6Xp0mc376+Zrx5BWaT2oTFKr/6PdommXVLAyhABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e7afc89136fcf047fa59a188614a406118fa029249c7f2b989c2b21919724fe","last_reissued_at":"2026-07-05T05:51:39.053885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:39.053885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation of functions with one-bit neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.NA","math.IT","math.NA"],"primary_cat":"cs.LG","authors_text":"C. Sinan G\\\"unt\\\"urk, Weilin Li","submitted_at":"2021-12-16T20:10:56Z","abstract_excerpt":"The celebrated universal approximation theorems for neural networks roughly state that any reasonable function can be arbitrarily well-approximated by a network whose parameters are appropriately chosen real numbers. This paper examines the approximation capabilities of one-bit neural networks -- those whose nonzero parameters are $\\pm a$ for some fixed $a\\not=0$. One of our main theorems shows that for any $f\\in C^s([0,1]^d)$ with $\\|f\\|_\\infty<1$ and error $\\varepsilon$, there is a $f_{NN}$ such that $|f(\\boldsymbol{x})-f_{NN}(\\boldsymbol{x})|\\leq \\varepsilon$ for all $\\boldsymbol{x}$ away f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09181","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/2112.09181/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":"2112.09181","created_at":"2026-07-05T05:51:39.053954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.09181v2","created_at":"2026-07-05T05:51:39.053954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09181","created_at":"2026-07-05T05:51:39.053954+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ5PZCITN7HQ","created_at":"2026-07-05T05:51:39.053954+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ5PZCITN7HQI75F","created_at":"2026-07-05T05:51:39.053954+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ5PZCIT","created_at":"2026-07-05T05:51:39.053954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06781","citing_title":"On Explicit Super-Expressive Approximation for Neural Networks","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY","json":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY.json","graph_json":"https://pith.science/api/pith-number/RZ5PZCITN7HQI75FTIMIMFFEAY/graph.json","events_json":"https://pith.science/api/pith-number/RZ5PZCITN7HQI75FTIMIMFFEAY/events.json","paper":"https://pith.science/paper/RZ5PZCIT"},"agent_actions":{"view_html":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY","download_json":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY.json","view_paper":"https://pith.science/paper/RZ5PZCIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.09181&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ5PZCITN7HQI75FTIMIMFFEAY/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ5PZCITN7HQI75FTIMIMFFEAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY/action/storage_attestation","attest_author":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY/action/author_attestation","sign_citation":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY/action/citation_signature","submit_replication":"https://pith.science/pith/RZ5PZCITN7HQI75FTIMIMFFEAY/action/replication_record"}},"created_at":"2026-07-05T05:51:39.053954+00:00","updated_at":"2026-07-05T05:51:39.053954+00:00"}