{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F7WLUO2OCOHNUKGG7DIYHVVF2M","short_pith_number":"pith:F7WLUO2O","schema_version":"1.0","canonical_sha256":"2fecba3b4e138eda28c6f8d183d6a5d32f986a9a8a975a7e3657f13608709674","source":{"kind":"arxiv","id":"2001.06931","version":2},"attestation_state":"computed","paper":{"title":"Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shun-ichi Amari","submitted_at":"2020-01-20T01:09:53Z","abstract_excerpt":"It is known that any target function is realized in a sufficiently small neighborhood of any randomly connected deep network, provided the width (the number of neurons in a layer) is sufficiently large. There are sophisticated theories and discussions concerning this striking fact, but rigorous theories are very complicated. We give an elementary geometrical proof by using a simple model for the purpose of elucidating its structure. We show that high-dimensional geometry plays a magical role: When we project a high-dimensional sphere of radius 1 to a low-dimensional subspace, the uniform distr"},"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":"2001.06931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-20T01:09:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ade3548eec529af57e97944a86da93420d0abe38bcab914025c367d7bb0aa244","abstract_canon_sha256":"39986b93d6c89124582495d02b82d07215644ae88da9a2a5f4fb01fc11629096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:01.460225Z","signature_b64":"ov9MfEK1gfbkL4Gp0KR4gMoknzqsQI/krf/gkb2+lV39B61aAEx3dMuzQu6LLS3eo0YVHHBQP1iSYqoSalQKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fecba3b4e138eda28c6f8d183d6a5d32f986a9a8a975a7e3657f13608709674","last_reissued_at":"2026-07-05T00:49:01.459848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:01.459848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shun-ichi Amari","submitted_at":"2020-01-20T01:09:53Z","abstract_excerpt":"It is known that any target function is realized in a sufficiently small neighborhood of any randomly connected deep network, provided the width (the number of neurons in a layer) is sufficiently large. There are sophisticated theories and discussions concerning this striking fact, but rigorous theories are very complicated. We give an elementary geometrical proof by using a simple model for the purpose of elucidating its structure. We show that high-dimensional geometry plays a magical role: When we project a high-dimensional sphere of radius 1 to a low-dimensional subspace, the uniform distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06931","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/2001.06931/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":"2001.06931","created_at":"2026-07-05T00:49:01.459913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.06931v2","created_at":"2026-07-05T00:49:01.459913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06931","created_at":"2026-07-05T00:49:01.459913+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7WLUO2OCOHN","created_at":"2026-07-05T00:49:01.459913+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7WLUO2OCOHNUKGG","created_at":"2026-07-05T00:49:01.459913+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7WLUO2O","created_at":"2026-07-05T00:49:01.459913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10200","citing_title":"Dynamic Reinforcement Learning for Actors","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M","json":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M.json","graph_json":"https://pith.science/api/pith-number/F7WLUO2OCOHNUKGG7DIYHVVF2M/graph.json","events_json":"https://pith.science/api/pith-number/F7WLUO2OCOHNUKGG7DIYHVVF2M/events.json","paper":"https://pith.science/paper/F7WLUO2O"},"agent_actions":{"view_html":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M","download_json":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M.json","view_paper":"https://pith.science/paper/F7WLUO2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.06931&json=true","fetch_graph":"https://pith.science/api/pith-number/F7WLUO2OCOHNUKGG7DIYHVVF2M/graph.json","fetch_events":"https://pith.science/api/pith-number/F7WLUO2OCOHNUKGG7DIYHVVF2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M/action/storage_attestation","attest_author":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M/action/author_attestation","sign_citation":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M/action/citation_signature","submit_replication":"https://pith.science/pith/F7WLUO2OCOHNUKGG7DIYHVVF2M/action/replication_record"}},"created_at":"2026-07-05T00:49:01.459913+00:00","updated_at":"2026-07-05T00:49:01.459913+00:00"}