{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SWUGSK5OYPDVU3AHKL6FTMQVMI","short_pith_number":"pith:SWUGSK5O","canonical_record":{"source":{"id":"1803.01206","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-03T17:37:57Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"80480eb810dbd1adb37ffc0c825f08d84b8449b450e2fa92f98fe851f5dffa9b","abstract_canon_sha256":"3dec5f6ffab43601fc47e1b6cfd6db74bfb366cc8ae9f16d6e6367ec93fb85c7"},"schema_version":"1.0"},"canonical_sha256":"95a8692baec3c75a6c0752fc59b2156235a19dde1d9c603394455e7728c063fd","source":{"kind":"arxiv","id":"1803.01206","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01206","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01206v2","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01206","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"SWUGSK5OYPDV","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SWUGSK5OYPDVU3AH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SWUGSK5O","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SWUGSK5OYPDVU3AHKL6FTMQVMI","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01206","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-03T17:37:57Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"80480eb810dbd1adb37ffc0c825f08d84b8449b450e2fa92f98fe851f5dffa9b","abstract_canon_sha256":"3dec5f6ffab43601fc47e1b6cfd6db74bfb366cc8ae9f16d6e6367ec93fb85c7"},"schema_version":"1.0"},"canonical_sha256":"95a8692baec3c75a6c0752fc59b2156235a19dde1d9c603394455e7728c063fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:10.337855Z","signature_b64":"qzZBOQ8lOhleffTpwtBRTffoFifBH/mXpAuM3khvgw9+bJAWysenu+xHhOK0rcTG4ob9+KW0Nq2IN8AY0d9MAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a8692baec3c75a6c0752fc59b2156235a19dde1d9c603394455e7728c063fd","last_reissued_at":"2026-05-18T00:13:10.337101Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:10.337101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01206","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":"2026-05-18T00:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y8AxcMYv2pwGR97EZ3ds+gQpUuZKegzcV+pCXoYRab/RdLdYgpVxc81Y2zJb6Cw6u5/k5p9THSMyzL7ENNxFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:55:03.205710Z"},"content_sha256":"5a410fb1e95e771382c838f3c519b0f7c8a70433e8d0cd2a6366e154a4c55da1","schema_version":"1.0","event_id":"sha256:5a410fb1e95e771382c838f3c519b0f7c8a70433e8d0cd2a6366e154a4c55da1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SWUGSK5OYPDVU3AHKL6FTMQVMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Simon S. Du","submitted_at":"2018-03-03T17:37:57Z","abstract_excerpt":"We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \\ge \\sqrt{2n}$, over-parametrization enables local search algorithms to find a \\emph{globally} optimal solution for general smooth and convex loss functions. Further, despite that the number of parameters may exceed the sample size, using theory of Rademacher complexity, we show with weight decay, the solution also generalizes well if the data is sampled from a regular distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01206","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":"2026-05-18T00:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fH2XqtlGeo8VlR/YDw8G0N2ulGIKgZaqw23ZABHCvVao8MK65fcOHRck2Ala0VMN9Kh0MGgqnYehiYTw+oxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:55:03.206402Z"},"content_sha256":"22bce3bd98836f028be9af5bf4517bad0503e92bf18e347cc9e172397618fb1b","schema_version":"1.0","event_id":"sha256:22bce3bd98836f028be9af5bf4517bad0503e92bf18e347cc9e172397618fb1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/bundle.json","state_url":"https://pith.science/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/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":"2026-05-26T12:55:03Z","links":{"resolver":"https://pith.science/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI","bundle":"https://pith.science/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/bundle.json","state":"https://pith.science/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWUGSK5OYPDVU3AHKL6FTMQVMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SWUGSK5OYPDVU3AHKL6FTMQVMI","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":"3dec5f6ffab43601fc47e1b6cfd6db74bfb366cc8ae9f16d6e6367ec93fb85c7","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-03T17:37:57Z","title_canon_sha256":"80480eb810dbd1adb37ffc0c825f08d84b8449b450e2fa92f98fe851f5dffa9b"},"schema_version":"1.0","source":{"id":"1803.01206","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01206","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01206v2","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01206","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"SWUGSK5OYPDV","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SWUGSK5OYPDVU3AH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SWUGSK5O","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:22bce3bd98836f028be9af5bf4517bad0503e92bf18e347cc9e172397618fb1b","target":"graph","created_at":"2026-05-18T00:13:10Z","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":"We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \\ge \\sqrt{2n}$, over-parametrization enables local search algorithms to find a \\emph{globally} optimal solution for general smooth and convex loss functions. Further, despite that the number of parameters may exceed the sample size, using theory of Rademacher complexity, we show with weight decay, the solution also generalizes well if the data is sampled from a regular distr","authors_text":"Jason D. Lee, Simon S. Du","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-03T17:37:57Z","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01206","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":"sha256:5a410fb1e95e771382c838f3c519b0f7c8a70433e8d0cd2a6366e154a4c55da1","target":"record","created_at":"2026-05-18T00:13:10Z","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":"3dec5f6ffab43601fc47e1b6cfd6db74bfb366cc8ae9f16d6e6367ec93fb85c7","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-03T17:37:57Z","title_canon_sha256":"80480eb810dbd1adb37ffc0c825f08d84b8449b450e2fa92f98fe851f5dffa9b"},"schema_version":"1.0","source":{"id":"1803.01206","kind":"arxiv","version":2}},"canonical_sha256":"95a8692baec3c75a6c0752fc59b2156235a19dde1d9c603394455e7728c063fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95a8692baec3c75a6c0752fc59b2156235a19dde1d9c603394455e7728c063fd","first_computed_at":"2026-05-18T00:13:10.337101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:10.337101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzZBOQ8lOhleffTpwtBRTffoFifBH/mXpAuM3khvgw9+bJAWysenu+xHhOK0rcTG4ob9+KW0Nq2IN8AY0d9MAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:10.337855Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01206","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a410fb1e95e771382c838f3c519b0f7c8a70433e8d0cd2a6366e154a4c55da1","sha256:22bce3bd98836f028be9af5bf4517bad0503e92bf18e347cc9e172397618fb1b"],"state_sha256":"a4fef246a4318354da50b28af3537ccc4702f46d6b9b5cdb4ab1d2a5845a8a8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Biqt3qMzs4wieaBAlF8TTtcmbzvBDR69a6wMuI+93d582uu83Zsvr/VzOUifVKIJSC81F9nrc4KFCe6WWctKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:55:03.210325Z","bundle_sha256":"d85882f97da37cdc944b7768b7b4ab63ddbdae686333d497435f11624933ebe6"}}