{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R3475O6FHUKABTDPRXR2LLMMPU","short_pith_number":"pith:R3475O6F","canonical_record":{"source":{"id":"1902.07528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T11:58:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"669a0589169ca71a7bb433228a41f06b364ed6fed2c07e66659369cd7d96080a","abstract_canon_sha256":"cec95c3a24a0f5cd675f19f80b8f1f421ba84a9807c2f27264296d84fd4a9829"},"schema_version":"1.0"},"canonical_sha256":"8ef9febbc53d1400cc6f8de3a5ad8c7d0b5170ab4bad836f7b5c181d6179e4d1","source":{"kind":"arxiv","id":"1902.07528","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07528","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07528v1","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07528","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"pith_short_12","alias_value":"R3475O6FHUKA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R3475O6FHUKABTDP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R3475O6F","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R3475O6FHUKABTDPRXR2LLMMPU","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T11:58:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"669a0589169ca71a7bb433228a41f06b364ed6fed2c07e66659369cd7d96080a","abstract_canon_sha256":"cec95c3a24a0f5cd675f19f80b8f1f421ba84a9807c2f27264296d84fd4a9829"},"schema_version":"1.0"},"canonical_sha256":"8ef9febbc53d1400cc6f8de3a5ad8c7d0b5170ab4bad836f7b5c181d6179e4d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:07.553757Z","signature_b64":"Z8v9NfRtNDqm15UcOxrze3chjs1VR5LPa4NRDA9d3fKgce5r/X6TpV7aPV7YlsM3C+Z/xPudWiJkwhi9t+8IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef9febbc53d1400cc6f8de3a5ad8c7d0b5170ab4bad836f7b5c181d6179e4d1","last_reissued_at":"2026-05-17T23:53:07.553055Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:07.553055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07528","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":"2026-05-17T23:53:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxrqCAgBz8WyiE3yfmwP/q5g9WuA0/GuEtOFU5vluO7tZmV7IrnK7NhxHhE31Inm/0WMZA5v+JExaeGAfu+DAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:49:38.309778Z"},"content_sha256":"fe32696df06e3a62eb9e82b1133a9a445f1f25f2ddbe6761b77d35915c6c15c6","schema_version":"1.0","event_id":"sha256:fe32696df06e3a62eb9e82b1133a9a445f1f25f2ddbe6761b77d35915c6c15c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R3475O6FHUKABTDPRXR2LLMMPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive scale-invariant online algorithms for learning linear models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manfred K. Warmuth, Micha{\\l} Kempka, Wojciech Kot{\\l}owski","submitted_at":"2019-02-20T11:58:05Z","abstract_excerpt":"We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this framework, such as Online Gradient Descent (OGD), have parameters (learning rates), which ideally should be tuned based on the scales of the features and the optimal comparator, but these quantities only become available at the end of the learning process. In this paper, we resolve the tuning problem by proposing online algorithms making predictions which are inva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07528","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":"2026-05-17T23:53:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLoO1o2KJpH6ni+KHnNRl2bxJwXVGnt4b/hDPVYwijkeh5BdweZ3f8lihlxY3YoR/oi+RRZV1IWgb5PXoId+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:49:38.310467Z"},"content_sha256":"59889a4025aba057a988d24650e5ac8f7c4b41cf7496b3d411bf80bb326f4d0a","schema_version":"1.0","event_id":"sha256:59889a4025aba057a988d24650e5ac8f7c4b41cf7496b3d411bf80bb326f4d0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3475O6FHUKABTDPRXR2LLMMPU/bundle.json","state_url":"https://pith.science/pith/R3475O6FHUKABTDPRXR2LLMMPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3475O6FHUKABTDPRXR2LLMMPU/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":"2026-06-11T23:49:38Z","links":{"resolver":"https://pith.science/pith/R3475O6FHUKABTDPRXR2LLMMPU","bundle":"https://pith.science/pith/R3475O6FHUKABTDPRXR2LLMMPU/bundle.json","state":"https://pith.science/pith/R3475O6FHUKABTDPRXR2LLMMPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3475O6FHUKABTDPRXR2LLMMPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R3475O6FHUKABTDPRXR2LLMMPU","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":"cec95c3a24a0f5cd675f19f80b8f1f421ba84a9807c2f27264296d84fd4a9829","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T11:58:05Z","title_canon_sha256":"669a0589169ca71a7bb433228a41f06b364ed6fed2c07e66659369cd7d96080a"},"schema_version":"1.0","source":{"id":"1902.07528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07528","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07528v1","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07528","created_at":"2026-05-17T23:53:07Z"},{"alias_kind":"pith_short_12","alias_value":"R3475O6FHUKA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R3475O6FHUKABTDP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R3475O6F","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:59889a4025aba057a988d24650e5ac8f7c4b41cf7496b3d411bf80bb326f4d0a","target":"graph","created_at":"2026-05-17T23:53:07Z","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 consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this framework, such as Online Gradient Descent (OGD), have parameters (learning rates), which ideally should be tuned based on the scales of the features and the optimal comparator, but these quantities only become available at the end of the learning process. In this paper, we resolve the tuning problem by proposing online algorithms making predictions which are inva","authors_text":"Manfred K. Warmuth, Micha{\\l} Kempka, Wojciech Kot{\\l}owski","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T11:58:05Z","title":"Adaptive scale-invariant online algorithms for learning linear models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07528","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:fe32696df06e3a62eb9e82b1133a9a445f1f25f2ddbe6761b77d35915c6c15c6","target":"record","created_at":"2026-05-17T23:53:07Z","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":"cec95c3a24a0f5cd675f19f80b8f1f421ba84a9807c2f27264296d84fd4a9829","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T11:58:05Z","title_canon_sha256":"669a0589169ca71a7bb433228a41f06b364ed6fed2c07e66659369cd7d96080a"},"schema_version":"1.0","source":{"id":"1902.07528","kind":"arxiv","version":1}},"canonical_sha256":"8ef9febbc53d1400cc6f8de3a5ad8c7d0b5170ab4bad836f7b5c181d6179e4d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ef9febbc53d1400cc6f8de3a5ad8c7d0b5170ab4bad836f7b5c181d6179e4d1","first_computed_at":"2026-05-17T23:53:07.553055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:07.553055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z8v9NfRtNDqm15UcOxrze3chjs1VR5LPa4NRDA9d3fKgce5r/X6TpV7aPV7YlsM3C+Z/xPudWiJkwhi9t+8IBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:07.553757Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe32696df06e3a62eb9e82b1133a9a445f1f25f2ddbe6761b77d35915c6c15c6","sha256:59889a4025aba057a988d24650e5ac8f7c4b41cf7496b3d411bf80bb326f4d0a"],"state_sha256":"ab4aed6bcad0f4a2ae638e3f0801e4902bda6e551939178b7c883cbd5a24cabf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seRHXhtcHxCmbcm4eJnAlQMyRWVtVYBRAtEK0mW7ynAdkmhLe4GihnGu7xcvGV5Vm98cTkdbJTVD72XaZfgwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T23:49:38.314093Z","bundle_sha256":"7ba529201e75594ffb4fe9bacab73672d4d427688fc4a0b1144e973efdc6898b"}}