{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:DV6W4YMMKKPV4A3D6T5J22PQZM","short_pith_number":"pith:DV6W4YMM","canonical_record":{"source":{"id":"1511.07948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","cross_cats_sorted":[],"title_canon_sha256":"f6be6a8dbeaa733e4265689cc076e8a39b7f1be0b87e1e897830c43dd584ef61","abstract_canon_sha256":"84f835a97d1cd9dd314d66d1d38b7b12922e3d572b39424b96e19a2722a52be2"},"schema_version":"1.0"},"canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","source":{"kind":"arxiv","id":"1511.07948","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07948","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07948v1","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07948","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"pith_short_12","alias_value":"DV6W4YMMKKPV","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DV6W4YMMKKPV4A3D","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DV6W4YMM","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:DV6W4YMMKKPV4A3D6T5J22PQZM","target":"record","payload":{"canonical_record":{"source":{"id":"1511.07948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","cross_cats_sorted":[],"title_canon_sha256":"f6be6a8dbeaa733e4265689cc076e8a39b7f1be0b87e1e897830c43dd584ef61","abstract_canon_sha256":"84f835a97d1cd9dd314d66d1d38b7b12922e3d572b39424b96e19a2722a52be2"},"schema_version":"1.0"},"canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:02.131666Z","signature_b64":"seAfd7/ABxKsrOJB3q75UTy1gfw12dVn7pDccfNAZFQ/L3L7zZ8VJsw8K2aYC3lMyQ2LId1KT5UoBU45jsn6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","last_reissued_at":"2026-05-18T01:26:02.131025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:02.131025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.07948","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":"2026-05-18T01:26:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/T5go2xVFpjZpqBrQqjpqDGm5YcNGAN1WhpGTjO4kPekFNu3gmzeTsycMp5xbRSId4JfzJx/zN3tE2w7TFPWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:29:46.855114Z"},"content_sha256":"77aaffcffd7d8203d072120ecbabb220358ef2e2f8942f45cec219ad043a479b","schema_version":"1.0","event_id":"sha256:77aaffcffd7d8203d072120ecbabb220358ef2e2f8942f45cec219ad043a479b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:DV6W4YMMKKPV4A3D6T5J22PQZM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Halfspaces and Neural Networks with Random Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Martin J. Wainwright, Michael I. Jordan, Yuchen Zhang","submitted_at":"2015-11-25T04:41:20Z","abstract_excerpt":"We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve arbitrarily small excess risk $\\epsilon>0$. The time complexity is polynomial in the input dimension $d$ and the sample size $n$, but exponential in the quantity $(L/\\epsilon^2)\\log(L/\\epsilon)$. These algorithms run multiple rounds of random initialization followed by arbitrary optimization steps. We further show that if the data is separable by some neural netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07948","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":"2026-05-18T01:26:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yuVu7cTva8mThqR4R85/eEHzMdD7WPSnZzpk3b/Dn/GgSjk0mdOGtViyajA5mRTU75Tyztm+6BcKIapAF3cQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:29:46.855826Z"},"content_sha256":"910ebe7a6664e712b06bf629c64881699c906a6008e715bb9d19d68cb210893e","schema_version":"1.0","event_id":"sha256:910ebe7a6664e712b06bf629c64881699c906a6008e715bb9d19d68cb210893e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/bundle.json","state_url":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/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":"2026-05-31T20:29:46Z","links":{"resolver":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM","bundle":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/bundle.json","state":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:DV6W4YMMKKPV4A3D6T5J22PQZM","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":"84f835a97d1cd9dd314d66d1d38b7b12922e3d572b39424b96e19a2722a52be2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","title_canon_sha256":"f6be6a8dbeaa733e4265689cc076e8a39b7f1be0b87e1e897830c43dd584ef61"},"schema_version":"1.0","source":{"id":"1511.07948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07948","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07948v1","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07948","created_at":"2026-05-18T01:26:02Z"},{"alias_kind":"pith_short_12","alias_value":"DV6W4YMMKKPV","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DV6W4YMMKKPV4A3D","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DV6W4YMM","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:910ebe7a6664e712b06bf629c64881699c906a6008e715bb9d19d68cb210893e","target":"graph","created_at":"2026-05-18T01:26:02Z","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 study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve arbitrarily small excess risk $\\epsilon>0$. The time complexity is polynomial in the input dimension $d$ and the sample size $n$, but exponential in the quantity $(L/\\epsilon^2)\\log(L/\\epsilon)$. These algorithms run multiple rounds of random initialization followed by arbitrary optimization steps. We further show that if the data is separable by some neural netwo","authors_text":"Jason D. Lee, Martin J. Wainwright, Michael I. Jordan, Yuchen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","title":"Learning Halfspaces and Neural Networks with Random Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07948","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":"sha256:77aaffcffd7d8203d072120ecbabb220358ef2e2f8942f45cec219ad043a479b","target":"record","created_at":"2026-05-18T01:26:02Z","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":"84f835a97d1cd9dd314d66d1d38b7b12922e3d572b39424b96e19a2722a52be2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","title_canon_sha256":"f6be6a8dbeaa733e4265689cc076e8a39b7f1be0b87e1e897830c43dd584ef61"},"schema_version":"1.0","source":{"id":"1511.07948","kind":"arxiv","version":1}},"canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","first_computed_at":"2026-05-18T01:26:02.131025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:02.131025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"seAfd7/ABxKsrOJB3q75UTy1gfw12dVn7pDccfNAZFQ/L3L7zZ8VJsw8K2aYC3lMyQ2LId1KT5UoBU45jsn6Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:02.131666Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.07948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77aaffcffd7d8203d072120ecbabb220358ef2e2f8942f45cec219ad043a479b","sha256:910ebe7a6664e712b06bf629c64881699c906a6008e715bb9d19d68cb210893e"],"state_sha256":"491a01be8ee1347ba24b6b94273f237b2084abf9af7a9d25a68ae8f33fd8b7cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZ5dFjo1JvaOJb3yMde2Pn7AhakFe4UmgVvQuKo7HdUBwWr9MlbZlnlxNPmGPx4563vU08T8lAdYtZDcRwiQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:29:46.860576Z","bundle_sha256":"ef270bf5b5023673948d690987374befba8c1676f9b84ae02a4e27c4d3b36c9a"}}