{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2ZJ45EHQII2JBHEIKCY7D7E3SO","short_pith_number":"pith:2ZJ45EHQ","canonical_record":{"source":{"id":"1706.04892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-15T14:33:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b96d8545016599a276003720ae1f30b23e562344214de6811ccb7e38f7f259d5","abstract_canon_sha256":"034a3a783e20b9a369c1c848293c249be3b7ffd3e4a341b6fdf1adb7503ccd1b"},"schema_version":"1.0"},"canonical_sha256":"d653ce90f04234909c8850b1f1fc9b93ad7312aec2fb034d4011a83d9730e955","source":{"kind":"arxiv","id":"1706.04892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04892","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04892v1","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04892","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"pith_short_12","alias_value":"2ZJ45EHQII2J","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2ZJ45EHQII2JBHEI","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2ZJ45EHQ","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2ZJ45EHQII2JBHEIKCY7D7E3SO","target":"record","payload":{"canonical_record":{"source":{"id":"1706.04892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-15T14:33:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b96d8545016599a276003720ae1f30b23e562344214de6811ccb7e38f7f259d5","abstract_canon_sha256":"034a3a783e20b9a369c1c848293c249be3b7ffd3e4a341b6fdf1adb7503ccd1b"},"schema_version":"1.0"},"canonical_sha256":"d653ce90f04234909c8850b1f1fc9b93ad7312aec2fb034d4011a83d9730e955","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:18.629126Z","signature_b64":"u8kQ+GQzAh+WH/5xYtmusKwjsC4l6jQa9nKVENOEuYWyI2wErfXtkN1mLzTOk8H+nnI8pc+5ZfcdLjul+QRHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d653ce90f04234909c8850b1f1fc9b93ad7312aec2fb034d4011a83d9730e955","last_reissued_at":"2026-05-18T00:42:18.628496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:18.628496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.04892","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":"2026-05-18T00:42:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8a86hUT6c56Y3jb0RlLQaFijICP7eu4ivUeEpedQmn1jdrY3WwBemqYqr9gsPtdHSCmE37WPBfYENgZUQU8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:00:03.454638Z"},"content_sha256":"14ab2d1421986c20b7d1bfe745c4faaca1ab74aadef254478734dc1fcd129ed4","schema_version":"1.0","event_id":"sha256:14ab2d1421986c20b7d1bfe745c4faaca1ab74aadef254478734dc1fcd129ed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2ZJ45EHQII2JBHEIKCY7D7E3SO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Second-Order Kernel Online Convex Optimization with Adaptive Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Daniele Calandriello, Michal Valko","submitted_at":"2017-06-15T14:33:08Z","abstract_excerpt":"Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO methods such as functional gradient descent require only $\\mathcal{O}(t)$ time and space per iteration, and, when the only information on the losses is their convexity, achieve a minimax optimal $\\mathcal{O}(\\sqrt{T})$ regret. Nonetheless, many common losses in kernel problems, such as squared loss, logistic loss, and squared hinge loss posses stronger curvature that can be exploited. In this case, second-order KOCO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04892","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":"2026-05-18T00:42:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZXOpUHdYHmXHMGt1BbHcyQ5S/JZotpsjzfPdbgraOX7xL+nq0ahC/QpGFElNnl2r2OdzOVFUOONk9QFVCa2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:00:03.454987Z"},"content_sha256":"28c1aac696c2998799bc368e824fecf2eb237607cdb61d251055e8d33ca0bb41","schema_version":"1.0","event_id":"sha256:28c1aac696c2998799bc368e824fecf2eb237607cdb61d251055e8d33ca0bb41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/bundle.json","state_url":"https://pith.science/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/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":"2026-07-07T06:00:03Z","links":{"resolver":"https://pith.science/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO","bundle":"https://pith.science/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/bundle.json","state":"https://pith.science/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZJ45EHQII2JBHEIKCY7D7E3SO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2ZJ45EHQII2JBHEIKCY7D7E3SO","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":"034a3a783e20b9a369c1c848293c249be3b7ffd3e4a341b6fdf1adb7503ccd1b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-15T14:33:08Z","title_canon_sha256":"b96d8545016599a276003720ae1f30b23e562344214de6811ccb7e38f7f259d5"},"schema_version":"1.0","source":{"id":"1706.04892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04892","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04892v1","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04892","created_at":"2026-05-18T00:42:18Z"},{"alias_kind":"pith_short_12","alias_value":"2ZJ45EHQII2J","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2ZJ45EHQII2JBHEI","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2ZJ45EHQ","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:28c1aac696c2998799bc368e824fecf2eb237607cdb61d251055e8d33ca0bb41","target":"graph","created_at":"2026-05-18T00:42:18Z","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":"Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO methods such as functional gradient descent require only $\\mathcal{O}(t)$ time and space per iteration, and, when the only information on the losses is their convexity, achieve a minimax optimal $\\mathcal{O}(\\sqrt{T})$ regret. Nonetheless, many common losses in kernel problems, such as squared loss, logistic loss, and squared hinge loss posses stronger curvature that can be exploited. In this case, second-order KOCO","authors_text":"Alessandro Lazaric, Daniele Calandriello, Michal Valko","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-15T14:33:08Z","title":"Second-Order Kernel Online Convex Optimization with Adaptive Sketching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04892","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":"sha256:14ab2d1421986c20b7d1bfe745c4faaca1ab74aadef254478734dc1fcd129ed4","target":"record","created_at":"2026-05-18T00:42:18Z","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":"034a3a783e20b9a369c1c848293c249be3b7ffd3e4a341b6fdf1adb7503ccd1b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-15T14:33:08Z","title_canon_sha256":"b96d8545016599a276003720ae1f30b23e562344214de6811ccb7e38f7f259d5"},"schema_version":"1.0","source":{"id":"1706.04892","kind":"arxiv","version":1}},"canonical_sha256":"d653ce90f04234909c8850b1f1fc9b93ad7312aec2fb034d4011a83d9730e955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d653ce90f04234909c8850b1f1fc9b93ad7312aec2fb034d4011a83d9730e955","first_computed_at":"2026-05-18T00:42:18.628496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:18.628496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u8kQ+GQzAh+WH/5xYtmusKwjsC4l6jQa9nKVENOEuYWyI2wErfXtkN1mLzTOk8H+nnI8pc+5ZfcdLjul+QRHBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:18.629126Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14ab2d1421986c20b7d1bfe745c4faaca1ab74aadef254478734dc1fcd129ed4","sha256:28c1aac696c2998799bc368e824fecf2eb237607cdb61d251055e8d33ca0bb41"],"state_sha256":"e93e81fca8dbfc1607eeaf4bb17dbae6cd411a7431707d8833fbca34b0904a05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6KeiLfgHE5b1AkE3kxynpD0ir2o89SwTXVyOjbENl32UxZudatvXM/38CmA0Zqou9AJEhLv/9PVB0+DdH7JAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:00:03.456889Z","bundle_sha256":"de7a36eb65ff998824840b965eb6a513f0ca5f199c1b1022ee4046d98ca60648"}}