{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UVPP7V2OF4K4PZ3FPQ7A4EDVGT","short_pith_number":"pith:UVPP7V2O","canonical_record":{"source":{"id":"1706.03175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T02:56:39Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"e172e11458234b2cb454961209995b97c7fcc96cc53ad3413e3dbaca1ff823fc","abstract_canon_sha256":"fe79dbe610002bc4b59aa877477a2c827b92f2100a788087e053a6a884ee565b"},"schema_version":"1.0"},"canonical_sha256":"a55effd74e2f15c7e7657c3e0e107534e9853d07c6f35d65f638d8d760311ff1","source":{"kind":"arxiv","id":"1706.03175","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03175","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03175v1","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03175","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"UVPP7V2OF4K4","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UVPP7V2OF4K4PZ3F","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UVPP7V2O","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UVPP7V2OF4K4PZ3FPQ7A4EDVGT","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T02:56:39Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"e172e11458234b2cb454961209995b97c7fcc96cc53ad3413e3dbaca1ff823fc","abstract_canon_sha256":"fe79dbe610002bc4b59aa877477a2c827b92f2100a788087e053a6a884ee565b"},"schema_version":"1.0"},"canonical_sha256":"a55effd74e2f15c7e7657c3e0e107534e9853d07c6f35d65f638d8d760311ff1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:38.280410Z","signature_b64":"S525Dwj+3N7C+B/dhMswsHreM2LbjQavrFCaQar9ttsiP+9F2FesYFWERiTUYVjArtrnoCCqxWDQCJdzuJ76AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a55effd74e2f15c7e7657c3e0e107534e9853d07c6f35d65f638d8d760311ff1","last_reissued_at":"2026-05-18T00:42:38.279891Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:38.279891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03175","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dN7XiqxwYshnHdMHkLJ2nZjAdyXo9SkkMu1d9gDnLMaRl/aa83gynZtJxVJYb5yYS329gx+GiDzqfttcgTDNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:27:05.693085Z"},"content_sha256":"4fe670bcc61b58333987a33b5678ae4b886562ccf7f1e1fc6590f73b51939d67","schema_version":"1.0","event_id":"sha256:4fe670bcc61b58333987a33b5678ae4b886562ccf7f1e1fc6590f73b51939d67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UVPP7V2OF4K4PZ3FPQ7A4EDVGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recovery Guarantees for One-hidden-layer Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Inderjit S. Dhillon, Kai Zhong, Peter L. Bartlett, Prateek Jain, Zhao Song","submitted_at":"2017-06-10T02:56:39Z","abstract_excerpt":"In this paper, we consider regression problems with one-hidden-layer neural networks (1NNs). We distill some properties of activation functions that lead to $\\mathit{local~strong~convexity}$ in the neighborhood of the ground-truth parameters for the 1NN squared-loss objective. Most popular nonlinear activation functions satisfy the distilled properties, including rectified linear units (ReLUs), leaky ReLUs, squared ReLUs and sigmoids. For activation functions that are also smooth, we show $\\mathit{local~linear~convergence}$ guarantees of gradient descent under a resampling rule. For homogeneou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03175","kind":"arxiv","version":1},"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":"2026-05-18T00:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bvKZHks85UhPWtoMHXFbEQMJ7tvqJK0tM50cK0IhDaPIEQJTSkGvVZ5+Ba4C6hybu0Vcx8P6iaS1zinTF9NLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:27:05.693441Z"},"content_sha256":"b67d445ce1274315a33fd354c861bf9ef60f4f2f0d3cc7701361ad5b13e4d93e","schema_version":"1.0","event_id":"sha256:b67d445ce1274315a33fd354c861bf9ef60f4f2f0d3cc7701361ad5b13e4d93e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/bundle.json","state_url":"https://pith.science/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/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":"2026-06-01T09:27:05Z","links":{"resolver":"https://pith.science/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT","bundle":"https://pith.science/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/bundle.json","state":"https://pith.science/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVPP7V2OF4K4PZ3FPQ7A4EDVGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UVPP7V2OF4K4PZ3FPQ7A4EDVGT","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":"fe79dbe610002bc4b59aa877477a2c827b92f2100a788087e053a6a884ee565b","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T02:56:39Z","title_canon_sha256":"e172e11458234b2cb454961209995b97c7fcc96cc53ad3413e3dbaca1ff823fc"},"schema_version":"1.0","source":{"id":"1706.03175","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03175","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03175v1","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03175","created_at":"2026-05-18T00:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"UVPP7V2OF4K4","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UVPP7V2OF4K4PZ3F","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UVPP7V2O","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:b67d445ce1274315a33fd354c861bf9ef60f4f2f0d3cc7701361ad5b13e4d93e","target":"graph","created_at":"2026-05-18T00:42:38Z","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":"In this paper, we consider regression problems with one-hidden-layer neural networks (1NNs). We distill some properties of activation functions that lead to $\\mathit{local~strong~convexity}$ in the neighborhood of the ground-truth parameters for the 1NN squared-loss objective. Most popular nonlinear activation functions satisfy the distilled properties, including rectified linear units (ReLUs), leaky ReLUs, squared ReLUs and sigmoids. For activation functions that are also smooth, we show $\\mathit{local~linear~convergence}$ guarantees of gradient descent under a resampling rule. For homogeneou","authors_text":"Inderjit S. Dhillon, Kai Zhong, Peter L. Bartlett, Prateek Jain, Zhao Song","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T02:56:39Z","title":"Recovery Guarantees for One-hidden-layer Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03175","kind":"arxiv","version":1},"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":"sha256:4fe670bcc61b58333987a33b5678ae4b886562ccf7f1e1fc6590f73b51939d67","target":"record","created_at":"2026-05-18T00:42:38Z","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":"fe79dbe610002bc4b59aa877477a2c827b92f2100a788087e053a6a884ee565b","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T02:56:39Z","title_canon_sha256":"e172e11458234b2cb454961209995b97c7fcc96cc53ad3413e3dbaca1ff823fc"},"schema_version":"1.0","source":{"id":"1706.03175","kind":"arxiv","version":1}},"canonical_sha256":"a55effd74e2f15c7e7657c3e0e107534e9853d07c6f35d65f638d8d760311ff1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a55effd74e2f15c7e7657c3e0e107534e9853d07c6f35d65f638d8d760311ff1","first_computed_at":"2026-05-18T00:42:38.279891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:38.279891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S525Dwj+3N7C+B/dhMswsHreM2LbjQavrFCaQar9ttsiP+9F2FesYFWERiTUYVjArtrnoCCqxWDQCJdzuJ76AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:38.280410Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03175","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fe670bcc61b58333987a33b5678ae4b886562ccf7f1e1fc6590f73b51939d67","sha256:b67d445ce1274315a33fd354c861bf9ef60f4f2f0d3cc7701361ad5b13e4d93e"],"state_sha256":"f10f76c8b0d310078c3bbe611cc4143dd10060cec58e1029c5a0848ca10a6d96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdNzcXGKcWrA2SwWuM0gx1m4zT2+qKnar+uyQbXV2MpjZQd5z1Cvx2o+cN0Acg/rPLdRIPlJDMTT7NLySVViDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:27:05.695473Z","bundle_sha256":"86b4ea06eab5b6c873dc5f99241e7f3cb4463ebc9dbc5c05b04fe701848d8493"}}