{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:F7RUVTRPD74UILQYMSC3KS7SXB","short_pith_number":"pith:F7RUVTRP","canonical_record":{"source":{"id":"1710.11278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T00:26:56Z","cross_cats_sorted":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"title_canon_sha256":"bc2b9772aa1a27ab4ba4230e024cad1a6be2373db87a6ee2ae604b1f2846b618","abstract_canon_sha256":"4f98bb4dc492ff73584fdcd62bb3461006bea5b764088cf0e1d064638a2319b2"},"schema_version":"1.0"},"canonical_sha256":"2fe34ace2f1ff9442e186485b54bf2b855efb27ff1046f2c85b6292b526616f0","source":{"kind":"arxiv","id":"1710.11278","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11278","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11278v2","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11278","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"F7RUVTRPD74U","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F7RUVTRPD74UILQY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F7RUVTRP","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:F7RUVTRPD74UILQYMSC3KS7SXB","target":"record","payload":{"canonical_record":{"source":{"id":"1710.11278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T00:26:56Z","cross_cats_sorted":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"title_canon_sha256":"bc2b9772aa1a27ab4ba4230e024cad1a6be2373db87a6ee2ae604b1f2846b618","abstract_canon_sha256":"4f98bb4dc492ff73584fdcd62bb3461006bea5b764088cf0e1d064638a2319b2"},"schema_version":"1.0"},"canonical_sha256":"2fe34ace2f1ff9442e186485b54bf2b855efb27ff1046f2c85b6292b526616f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:34.566561Z","signature_b64":"W6/BE+Bkc0ve4+mglbLVFGPLNziEG/pJZv7neq5ykpMWy7yZM5yVTR0YAXEnuCsR31X3d8/LfJyu+Wj2okI5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe34ace2f1ff9442e186485b54bf2b855efb27ff1046f2c85b6292b526616f0","last_reissued_at":"2026-05-18T00:21:34.565831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:34.565831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.11278","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6ATR/M+oyyy7wAyufwRrxnEt4mrOkWOeKl7KonrOOctE8sHsMpfaqQO9POS9plsMQdgV+9Qgb3V5EBuhccJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:22:41.545520Z"},"content_sha256":"20a65c006ed5fd4bfa5096ce328e995cfe26495e8188e783ed5f59b05f70e620","schema_version":"1.0","event_id":"sha256:20a65c006ed5fd4bfa5096ce328e995cfe26495e8188e783ed5f59b05f70e620"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:F7RUVTRPD74UILQYMSC3KS7SXB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Boris Hanin, Mark Sellke","submitted_at":"2017-10-31T00:26:56Z","abstract_excerpt":"This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\\geq 1,$ what is the minimal width $w$ so that neural nets with ReLU activations, input dimension $d_{in}$, hidden layer widths at most $w,$ and arbitrary depth can approximate any continuous, real-valued function of $d_{in}$ variables arbitrarily well? It turns out that this minimal width is exactly equal to $d_{in}+1.$ That is, if all the hidden layer widths are bounded by $d_{in}$, then even in the infinite depth limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11278","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjfM/oFuTuhfuPxFKVhybdECX0aVSeDHTY27W33Au0wYvxO0zPwHLI3KnOIIVyap49ubwfQyTGOrnPJ85h0hAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:22:41.545872Z"},"content_sha256":"9252e42545ad054345ffc862227a1743687ee89a8e9226014d5bb077382fc6d8","schema_version":"1.0","event_id":"sha256:9252e42545ad054345ffc862227a1743687ee89a8e9226014d5bb077382fc6d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7RUVTRPD74UILQYMSC3KS7SXB/bundle.json","state_url":"https://pith.science/pith/F7RUVTRPD74UILQYMSC3KS7SXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7RUVTRPD74UILQYMSC3KS7SXB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T10:22:41Z","links":{"resolver":"https://pith.science/pith/F7RUVTRPD74UILQYMSC3KS7SXB","bundle":"https://pith.science/pith/F7RUVTRPD74UILQYMSC3KS7SXB/bundle.json","state":"https://pith.science/pith/F7RUVTRPD74UILQYMSC3KS7SXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7RUVTRPD74UILQYMSC3KS7SXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F7RUVTRPD74UILQYMSC3KS7SXB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4f98bb4dc492ff73584fdcd62bb3461006bea5b764088cf0e1d064638a2319b2","cross_cats_sorted":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T00:26:56Z","title_canon_sha256":"bc2b9772aa1a27ab4ba4230e024cad1a6be2373db87a6ee2ae604b1f2846b618"},"schema_version":"1.0","source":{"id":"1710.11278","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11278","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11278v2","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11278","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"F7RUVTRPD74U","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F7RUVTRPD74UILQY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F7RUVTRP","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:9252e42545ad054345ffc862227a1743687ee89a8e9226014d5bb077382fc6d8","target":"graph","created_at":"2026-05-18T00:21:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\\geq 1,$ what is the minimal width $w$ so that neural nets with ReLU activations, input dimension $d_{in}$, hidden layer widths at most $w,$ and arbitrary depth can approximate any continuous, real-valued function of $d_{in}$ variables arbitrarily well? It turns out that this minimal width is exactly equal to $d_{in}+1.$ That is, if all the hidden layer widths are bounded by $d_{in}$, then even in the infinite depth limit","authors_text":"Boris Hanin, Mark Sellke","cross_cats":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T00:26:56Z","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11278","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:20a65c006ed5fd4bfa5096ce328e995cfe26495e8188e783ed5f59b05f70e620","target":"record","created_at":"2026-05-18T00:21:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4f98bb4dc492ff73584fdcd62bb3461006bea5b764088cf0e1d064638a2319b2","cross_cats_sorted":["cs.CC","cs.LG","math.CO","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T00:26:56Z","title_canon_sha256":"bc2b9772aa1a27ab4ba4230e024cad1a6be2373db87a6ee2ae604b1f2846b618"},"schema_version":"1.0","source":{"id":"1710.11278","kind":"arxiv","version":2}},"canonical_sha256":"2fe34ace2f1ff9442e186485b54bf2b855efb27ff1046f2c85b6292b526616f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fe34ace2f1ff9442e186485b54bf2b855efb27ff1046f2c85b6292b526616f0","first_computed_at":"2026-05-18T00:21:34.565831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:34.565831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W6/BE+Bkc0ve4+mglbLVFGPLNziEG/pJZv7neq5ykpMWy7yZM5yVTR0YAXEnuCsR31X3d8/LfJyu+Wj2okI5Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:34.566561Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.11278","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20a65c006ed5fd4bfa5096ce328e995cfe26495e8188e783ed5f59b05f70e620","sha256:9252e42545ad054345ffc862227a1743687ee89a8e9226014d5bb077382fc6d8"],"state_sha256":"08ccea88d907b7ea75daf762d8196c9b81fbaf643fa002cb8e191c59054eba04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMOCXscbAvEMjvYundm2Q0gHfGpHYT6Ju538HFiMvLiHABikg2neHb6qR+W2uWz8Yyn0VvxX30z16Ly3hthIAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:22:41.547948Z","bundle_sha256":"451a1df6f50176055b1f90c63b1f89aa08529fce369e66f1c053adb9855012b0"}}