{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7T772CUYU7UTN4BNUCBYGZKEPO","short_pith_number":"pith:7T772CUY","canonical_record":{"source":{"id":"1809.04481","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T14:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"73e20f7c03beabbf452a4f06a14e531e97867b78c1de9de3a775abc8c82881f0","abstract_canon_sha256":"6a2e23de1f84803dd6763fd6296dcd0757e207f2a64b8bb368d95708a5b5607a"},"schema_version":"1.0"},"canonical_sha256":"fcfffd0a98a7e936f02da0838365447b9cd5bcd6ab4d8163ba7a058ed32dd16b","source":{"kind":"arxiv","id":"1809.04481","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04481","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04481v3","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04481","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"7T772CUYU7UT","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7T772CUYU7UTN4BN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7T772CUY","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7T772CUYU7UTN4BNUCBYGZKEPO","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04481","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T14:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"73e20f7c03beabbf452a4f06a14e531e97867b78c1de9de3a775abc8c82881f0","abstract_canon_sha256":"6a2e23de1f84803dd6763fd6296dcd0757e207f2a64b8bb368d95708a5b5607a"},"schema_version":"1.0"},"canonical_sha256":"fcfffd0a98a7e936f02da0838365447b9cd5bcd6ab4d8163ba7a058ed32dd16b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:47.237750Z","signature_b64":"6vt96ATt0+lecBd72cShjpQgrZgg4crC18DLWxL5h26U+3rbMCq7nYy0c0Jx2Z6Shjf5QM5236rHNeVof5x0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcfffd0a98a7e936f02da0838365447b9cd5bcd6ab4d8163ba7a058ed32dd16b","last_reissued_at":"2026-05-17T23:56:47.237326Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:47.237326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04481","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLkfyFeKHve1B2mxNm6vQev0MLn+gwCbh6w/Psm5qTr9dmQEiiG7PbRQMVal/RlxS+dQ26BLDeZw2ZY+SdrBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:41:12.427451Z"},"content_sha256":"b84e6eec4d3cf62df2bbdd77c5f751267a172ffcbe03b73c2b4fec3ec51a8bbe","schema_version":"1.0","event_id":"sha256:b84e6eec4d3cf62df2bbdd77c5f751267a172ffcbe03b73c2b4fec3ec51a8bbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7T772CUYU7UTN4BNUCBYGZKEPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"But How Does It Work in Theory? Linear SVM with Random Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Anna Gilbert, Yitong Sun","submitted_at":"2018-09-12T14:29:05Z","abstract_excerpt":"We prove that, under low noise assumptions, the support vector machine with $N\\ll m$ random features (RFSVM) can achieve the learning rate faster than $O(1/\\sqrt{m})$ on a training set with $m$ samples when an optimized feature map is used. Our work extends the previous fast rate analysis of random features method from least square loss to 0-1 loss. We also show that the reweighted feature selection method, which approximates the optimized feature map, helps improve the performance of RFSVM in experiments on a synthetic data set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04481","kind":"arxiv","version":3},"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":"2026-05-17T23:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fax78bcL4ajQZ/F861kSpWahliRRrNOPHFuu4IuehE7Q4iUWjSvqhov0kGTd4x1s4fmn6F2eDB8nqP+EUji2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:41:12.427797Z"},"content_sha256":"dff052cec5304c039c64949f886c61c938f5c46ad159d0dc3e87cb19d8a8daf7","schema_version":"1.0","event_id":"sha256:dff052cec5304c039c64949f886c61c938f5c46ad159d0dc3e87cb19d8a8daf7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7T772CUYU7UTN4BNUCBYGZKEPO/bundle.json","state_url":"https://pith.science/pith/7T772CUYU7UTN4BNUCBYGZKEPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7T772CUYU7UTN4BNUCBYGZKEPO/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":"2026-06-01T14:41:12Z","links":{"resolver":"https://pith.science/pith/7T772CUYU7UTN4BNUCBYGZKEPO","bundle":"https://pith.science/pith/7T772CUYU7UTN4BNUCBYGZKEPO/bundle.json","state":"https://pith.science/pith/7T772CUYU7UTN4BNUCBYGZKEPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7T772CUYU7UTN4BNUCBYGZKEPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7T772CUYU7UTN4BNUCBYGZKEPO","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":"6a2e23de1f84803dd6763fd6296dcd0757e207f2a64b8bb368d95708a5b5607a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T14:29:05Z","title_canon_sha256":"73e20f7c03beabbf452a4f06a14e531e97867b78c1de9de3a775abc8c82881f0"},"schema_version":"1.0","source":{"id":"1809.04481","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04481","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04481v3","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04481","created_at":"2026-05-17T23:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"7T772CUYU7UT","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7T772CUYU7UTN4BN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7T772CUY","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:dff052cec5304c039c64949f886c61c938f5c46ad159d0dc3e87cb19d8a8daf7","target":"graph","created_at":"2026-05-17T23:56:47Z","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 prove that, under low noise assumptions, the support vector machine with $N\\ll m$ random features (RFSVM) can achieve the learning rate faster than $O(1/\\sqrt{m})$ on a training set with $m$ samples when an optimized feature map is used. Our work extends the previous fast rate analysis of random features method from least square loss to 0-1 loss. We also show that the reweighted feature selection method, which approximates the optimized feature map, helps improve the performance of RFSVM in experiments on a synthetic data set.","authors_text":"Ambuj Tewari, Anna Gilbert, Yitong Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T14:29:05Z","title":"But How Does It Work in Theory? Linear SVM with Random Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04481","kind":"arxiv","version":3},"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:b84e6eec4d3cf62df2bbdd77c5f751267a172ffcbe03b73c2b4fec3ec51a8bbe","target":"record","created_at":"2026-05-17T23:56:47Z","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":"6a2e23de1f84803dd6763fd6296dcd0757e207f2a64b8bb368d95708a5b5607a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T14:29:05Z","title_canon_sha256":"73e20f7c03beabbf452a4f06a14e531e97867b78c1de9de3a775abc8c82881f0"},"schema_version":"1.0","source":{"id":"1809.04481","kind":"arxiv","version":3}},"canonical_sha256":"fcfffd0a98a7e936f02da0838365447b9cd5bcd6ab4d8163ba7a058ed32dd16b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcfffd0a98a7e936f02da0838365447b9cd5bcd6ab4d8163ba7a058ed32dd16b","first_computed_at":"2026-05-17T23:56:47.237326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:47.237326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vt96ATt0+lecBd72cShjpQgrZgg4crC18DLWxL5h26U+3rbMCq7nYy0c0Jx2Z6Shjf5QM5236rHNeVof5x0AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:47.237750Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04481","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b84e6eec4d3cf62df2bbdd77c5f751267a172ffcbe03b73c2b4fec3ec51a8bbe","sha256:dff052cec5304c039c64949f886c61c938f5c46ad159d0dc3e87cb19d8a8daf7"],"state_sha256":"c477098a2e7fb2a6a36aee82fa957203277e0c65333c2eabd8a0c1b0f65c0ac9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvQsJElJ2Nt6J1y7bVO6CRLag01q7jc0F/1a8iZPFNtbdmnP12R/M3OAmtuxJ1YQG5BuEN6wlKhsGqWi4DEtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T14:41:12.429892Z","bundle_sha256":"dec21bd5818874347e9a40f14be62e06b2004155f6234a12f6e49832858893f3"}}