{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MVKMTWSKBTNE3YDXHK3CANQ56Q","short_pith_number":"pith:MVKMTWSK","canonical_record":{"source":{"id":"1811.00155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T23:24:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a2306c2dbf9df336c33a55f5535283a8a5be2e6ed149257e789ecb35e2524bd2","abstract_canon_sha256":"9160e4c294a83e02c8bd84de97b755b3ea7d7488f4c9613e66b352c1a4f73879"},"schema_version":"1.0"},"canonical_sha256":"6554c9da4a0cda4de0773ab620361df40cfac0434c7aacddad7bfb7efaf03aee","source":{"kind":"arxiv","id":"1811.00155","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00155","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00155v2","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00155","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"MVKMTWSKBTNE","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MVKMTWSKBTNE3YDX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MVKMTWSK","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MVKMTWSKBTNE3YDXHK3CANQ56Q","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T23:24:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a2306c2dbf9df336c33a55f5535283a8a5be2e6ed149257e789ecb35e2524bd2","abstract_canon_sha256":"9160e4c294a83e02c8bd84de97b755b3ea7d7488f4c9613e66b352c1a4f73879"},"schema_version":"1.0"},"canonical_sha256":"6554c9da4a0cda4de0773ab620361df40cfac0434c7aacddad7bfb7efaf03aee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:48.774236Z","signature_b64":"Ktp/GO/88TtaMvYVOUzEUbCNfefYcyxLKpPBBFjJrx7wFzUSgGk4nbnSOV868wqxOjTg227PBmAu7U7uxYZoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6554c9da4a0cda4de0773ab620361df40cfac0434c7aacddad7bfb7efaf03aee","last_reissued_at":"2026-05-17T23:50:48.773723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:48.773723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00155","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":"2026-05-17T23:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cM6PNaOM4/sZAEAW7TDzhiPe71RQuyTOnhlW/VM04HlylBGxE7x1f0QCUdWCuYUzMtKlVERPEI5cukWv61CNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:14:45.430386Z"},"content_sha256":"c8b37bacd7e02712e045c6eaae5672f2f7b0c1a1b7a65b66062a1e90cbbf20d4","schema_version":"1.0","event_id":"sha256:c8b37bacd7e02712e045c6eaae5672f2f7b0c1a1b7a65b66062a1e90cbbf20d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MVKMTWSKBTNE3YDXHK3CANQ56Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avner May, Christopher R\\'e, Jian Zhang, Tri Dao","submitted_at":"2018-10-31T23:24:51Z","abstract_excerpt":"We investigate how to train kernel approximation methods that generalize well under a memory budget. Building on recent theoretical work, we define a measure of kernel approximation error which we find to be more predictive of the empirical generalization performance of kernel approximation methods than conventional metrics. An important consequence of this definition is that a kernel approximation matrix must be high rank to attain close approximation. Because storing a high-rank approximation is memory intensive, we propose using a low-precision quantization of random Fourier features (LP-RF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00155","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":"2026-05-17T23:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9oNzGbFjw/Jy5ycsbKovsgNAgeBLJo85wD81lrQ4n46gPSLovSBkqns3ykMS6LZITcQSxLh+sFrBY0k9oDiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:14:45.431263Z"},"content_sha256":"ad12d4f278b62218ba9be36f3b77e203c920a0ea36018ba32e1b5627eafba505","schema_version":"1.0","event_id":"sha256:ad12d4f278b62218ba9be36f3b77e203c920a0ea36018ba32e1b5627eafba505"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/bundle.json","state_url":"https://pith.science/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/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":"2026-06-10T12:14:45Z","links":{"resolver":"https://pith.science/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q","bundle":"https://pith.science/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/bundle.json","state":"https://pith.science/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVKMTWSKBTNE3YDXHK3CANQ56Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MVKMTWSKBTNE3YDXHK3CANQ56Q","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":"9160e4c294a83e02c8bd84de97b755b3ea7d7488f4c9613e66b352c1a4f73879","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T23:24:51Z","title_canon_sha256":"a2306c2dbf9df336c33a55f5535283a8a5be2e6ed149257e789ecb35e2524bd2"},"schema_version":"1.0","source":{"id":"1811.00155","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00155","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00155v2","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00155","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"MVKMTWSKBTNE","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MVKMTWSKBTNE3YDX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MVKMTWSK","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:ad12d4f278b62218ba9be36f3b77e203c920a0ea36018ba32e1b5627eafba505","target":"graph","created_at":"2026-05-17T23:50:48Z","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 investigate how to train kernel approximation methods that generalize well under a memory budget. Building on recent theoretical work, we define a measure of kernel approximation error which we find to be more predictive of the empirical generalization performance of kernel approximation methods than conventional metrics. An important consequence of this definition is that a kernel approximation matrix must be high rank to attain close approximation. Because storing a high-rank approximation is memory intensive, we propose using a low-precision quantization of random Fourier features (LP-RF","authors_text":"Avner May, Christopher R\\'e, Jian Zhang, Tri Dao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T23:24:51Z","title":"Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00155","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:c8b37bacd7e02712e045c6eaae5672f2f7b0c1a1b7a65b66062a1e90cbbf20d4","target":"record","created_at":"2026-05-17T23:50:48Z","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":"9160e4c294a83e02c8bd84de97b755b3ea7d7488f4c9613e66b352c1a4f73879","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T23:24:51Z","title_canon_sha256":"a2306c2dbf9df336c33a55f5535283a8a5be2e6ed149257e789ecb35e2524bd2"},"schema_version":"1.0","source":{"id":"1811.00155","kind":"arxiv","version":2}},"canonical_sha256":"6554c9da4a0cda4de0773ab620361df40cfac0434c7aacddad7bfb7efaf03aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6554c9da4a0cda4de0773ab620361df40cfac0434c7aacddad7bfb7efaf03aee","first_computed_at":"2026-05-17T23:50:48.773723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:48.773723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ktp/GO/88TtaMvYVOUzEUbCNfefYcyxLKpPBBFjJrx7wFzUSgGk4nbnSOV868wqxOjTg227PBmAu7U7uxYZoBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:48.774236Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00155","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b37bacd7e02712e045c6eaae5672f2f7b0c1a1b7a65b66062a1e90cbbf20d4","sha256:ad12d4f278b62218ba9be36f3b77e203c920a0ea36018ba32e1b5627eafba505"],"state_sha256":"57044cc6313027012b5255f4d8512705ffcc2f111654984242b3c8230e02edf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hf5wfZeeT3cVzy/YYb7G1nQUeCb4bgeIgwt/tvEQW61/hYWgaXAHBhlJ1nuG0MJwEegV1zi2FB9wlv4gHlAiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:14:45.436498Z","bundle_sha256":"2e75d37ac8223312b47ad65716147e5b454b6ce52aa05e4c4c07d237349edfac"}}