{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7VZKJMTEWEHDS4IUL6E35ZLW7P","short_pith_number":"pith:7VZKJMTE","canonical_record":{"source":{"id":"1705.04591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:06:46Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"6a453c3e650d6acecf4522f0616578cc0bca3b8dbec5ac0da89f51ba5a74930c","abstract_canon_sha256":"b87a319b2695bd78e16a8b52b8aacd9c37a6ad4e991028f0945071dc114b182f"},"schema_version":"1.0"},"canonical_sha256":"fd72a4b264b10e3971145f89bee576fbc9ae470366889dc320462d1de4aa5da6","source":{"kind":"arxiv","id":"1705.04591","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04591","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04591v2","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04591","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"7VZKJMTEWEHD","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7VZKJMTEWEHDS4IU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7VZKJMTE","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7VZKJMTEWEHDS4IUL6E35ZLW7P","target":"record","payload":{"canonical_record":{"source":{"id":"1705.04591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:06:46Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"6a453c3e650d6acecf4522f0616578cc0bca3b8dbec5ac0da89f51ba5a74930c","abstract_canon_sha256":"b87a319b2695bd78e16a8b52b8aacd9c37a6ad4e991028f0945071dc114b182f"},"schema_version":"1.0"},"canonical_sha256":"fd72a4b264b10e3971145f89bee576fbc9ae470366889dc320462d1de4aa5da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:45.926714Z","signature_b64":"m4YNNvcQhQ3l7OiPsmwC+ieVZEaf71sXpGZgjRX6dSbzvMlurtu40K5FA4smAIvo2ZojT/cPbNSgpg+/YOhgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd72a4b264b10e3971145f89bee576fbc9ae470366889dc320462d1de4aa5da6","last_reissued_at":"2026-05-18T00:38:45.926139Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:45.926139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.04591","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":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHBcysTYhj8thkjpZcVVP1I4Xv9ZdFQ20XThEcgAPHaIRjfKoIb2aavdEH8LHdUsXz+9Y8nZr6tjGWFxEp7JCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:20:45.829005Z"},"content_sha256":"90d60b652de531bb9843bbc83d6a075100a246f5424ab8c5c3754bad381f1699","schema_version":"1.0","event_id":"sha256:90d60b652de531bb9843bbc83d6a075100a246f5424ab8c5c3754bad381f1699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7VZKJMTEWEHDS4IUL6E35ZLW7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning ReLUs via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahdi Soltanolkotabi","submitted_at":"2017-05-10T22:06:46Z","abstract_excerpt":"In this paper we study the problem of learning Rectified Linear Units (ReLUs) which are functions of the form $max(0,<w,x>)$ with $w$ denoting the weight vector. We study this problem in the high-dimensional regime where the number of observations are fewer than the dimension of the weight vector. We assume that the weight vector belongs to some closed set (convex or nonconvex) which captures known side-information about its structure. We focus on the realizable model where the inputs are chosen i.i.d.~from a Gaussian distribution and the labels are generated according to a planted weight vect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04591","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":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JI3o9jW6sQ3s6SuW6fgcx0RNC5VKc0JJNGrfs1loi1rzXuv342j//+SvRVnz4lg0gsOz9t9SIZgMfxPt8QK0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:20:45.829457Z"},"content_sha256":"b49314124a5541f7580fdb7c4bf4d4cb638387159686e040c671b8e0119306df","schema_version":"1.0","event_id":"sha256:b49314124a5541f7580fdb7c4bf4d4cb638387159686e040c671b8e0119306df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/bundle.json","state_url":"https://pith.science/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/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":"2026-05-27T02:20:45Z","links":{"resolver":"https://pith.science/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P","bundle":"https://pith.science/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/bundle.json","state":"https://pith.science/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VZKJMTEWEHDS4IUL6E35ZLW7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7VZKJMTEWEHDS4IUL6E35ZLW7P","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":"b87a319b2695bd78e16a8b52b8aacd9c37a6ad4e991028f0945071dc114b182f","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:06:46Z","title_canon_sha256":"6a453c3e650d6acecf4522f0616578cc0bca3b8dbec5ac0da89f51ba5a74930c"},"schema_version":"1.0","source":{"id":"1705.04591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04591","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04591v2","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04591","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"7VZKJMTEWEHD","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7VZKJMTEWEHDS4IU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7VZKJMTE","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b49314124a5541f7580fdb7c4bf4d4cb638387159686e040c671b8e0119306df","target":"graph","created_at":"2026-05-18T00:38:45Z","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 study the problem of learning Rectified Linear Units (ReLUs) which are functions of the form $max(0,<w,x>)$ with $w$ denoting the weight vector. We study this problem in the high-dimensional regime where the number of observations are fewer than the dimension of the weight vector. We assume that the weight vector belongs to some closed set (convex or nonconvex) which captures known side-information about its structure. We focus on the realizable model where the inputs are chosen i.i.d.~from a Gaussian distribution and the labels are generated according to a planted weight vect","authors_text":"Mahdi Soltanolkotabi","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:06:46Z","title":"Learning ReLUs via Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04591","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":"sha256:90d60b652de531bb9843bbc83d6a075100a246f5424ab8c5c3754bad381f1699","target":"record","created_at":"2026-05-18T00:38:45Z","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":"b87a319b2695bd78e16a8b52b8aacd9c37a6ad4e991028f0945071dc114b182f","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:06:46Z","title_canon_sha256":"6a453c3e650d6acecf4522f0616578cc0bca3b8dbec5ac0da89f51ba5a74930c"},"schema_version":"1.0","source":{"id":"1705.04591","kind":"arxiv","version":2}},"canonical_sha256":"fd72a4b264b10e3971145f89bee576fbc9ae470366889dc320462d1de4aa5da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd72a4b264b10e3971145f89bee576fbc9ae470366889dc320462d1de4aa5da6","first_computed_at":"2026-05-18T00:38:45.926139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:45.926139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m4YNNvcQhQ3l7OiPsmwC+ieVZEaf71sXpGZgjRX6dSbzvMlurtu40K5FA4smAIvo2ZojT/cPbNSgpg+/YOhgCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:45.926714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.04591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90d60b652de531bb9843bbc83d6a075100a246f5424ab8c5c3754bad381f1699","sha256:b49314124a5541f7580fdb7c4bf4d4cb638387159686e040c671b8e0119306df"],"state_sha256":"e33e92b68729935dd776045a06bf40098ace25a501a91a6250d3c86ac06a096b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2kKdi6L79tYfakr/GM5BRPJL6vncJ040YKPJY/7zoldrsilLH3x0MKt8KvVOWGMpFwB1A37rrwYVNEsHH9QAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:20:45.832964Z","bundle_sha256":"1c552665c4bac559a72818ec8ce439ca84ae3c492296cf4630932ddae70d8ce3"}}