{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HE2PWC3RLHO7Y3RCJKZU36CYS4","short_pith_number":"pith:HE2PWC3R","canonical_record":{"source":{"id":"1907.07751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T20:51:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e723adc73cee544802b0526ee3258f5f40af775200bfd76504a8e491e002454a","abstract_canon_sha256":"f3eee8ee8669d38660c8b7fd73c2814e8a4adf2029c115c5d3a579a975178d51"},"schema_version":"1.0"},"canonical_sha256":"3934fb0b7159ddfc6e224ab34df8589716a035439a075007bad83083d5a7d29a","source":{"kind":"arxiv","id":"1907.07751","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07751","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07751v2","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07751","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"HE2PWC3RLHO7","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"HE2PWC3RLHO7Y3RC","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"HE2PWC3R","created_at":"2026-07-05T00:25:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HE2PWC3RLHO7Y3RCJKZU36CYS4","target":"record","payload":{"canonical_record":{"source":{"id":"1907.07751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T20:51:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e723adc73cee544802b0526ee3258f5f40af775200bfd76504a8e491e002454a","abstract_canon_sha256":"f3eee8ee8669d38660c8b7fd73c2814e8a4adf2029c115c5d3a579a975178d51"},"schema_version":"1.0"},"canonical_sha256":"3934fb0b7159ddfc6e224ab34df8589716a035439a075007bad83083d5a7d29a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:55.736717Z","signature_b64":"Si47RIxQ6bc+rVV/5pOA6+ryseLBPnAjd7Vr0vuFXfa8gvfNYYViMS6/lflXYSCSzaT4sUN9kM30mw/X/OYsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3934fb0b7159ddfc6e224ab34df8589716a035439a075007bad83083d5a7d29a","last_reissued_at":"2026-07-05T00:25:55.736213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:55.736213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.07751","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":"2026-07-05T00:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F0syaM+FP5oHkqebRg/wUMg8/gBkrYFqIlxcMSM/iqQ+QHqcIr/8b8LCjtfWcC33QaRLkgRQMatqm6zLy9MRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:10:10.465895Z"},"content_sha256":"564d0f8fb3b0dbac430719efd5eedab7e4d781a4e9243a9e1d9ab2d5b0fd8403","schema_version":"1.0","event_id":"sha256:564d0f8fb3b0dbac430719efd5eedab7e4d781a4e9243a9e1d9ab2d5b0fd8403"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HE2PWC3RLHO7Y3RCJKZU36CYS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-descent for Online, Continual Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam White, Andrew Jacobsen, Cameron Linke, Martha White, Matthew Schlegel, Thomas Degris","submitted_at":"2019-07-17T20:51:58Z","abstract_excerpt":"This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update---a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the step-size parameters to minimize prediction error. These meta-descent strategies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07751","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1907.07751/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P14unPQK5byEqxQkEiHdKKqIkvl1I0EtfkuWxLfSeZ1XbcPdq+YjnclWwV1rIfocSbsoF8c0WrUPNtuOYTWjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:10:10.466620Z"},"content_sha256":"965fe862cb29c7c3cb76819df464ea295a83530766ba7c6ea379e6b626652015","schema_version":"1.0","event_id":"sha256:965fe862cb29c7c3cb76819df464ea295a83530766ba7c6ea379e6b626652015"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/bundle.json","state_url":"https://pith.science/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/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":"2026-08-10T22:10:10Z","links":{"resolver":"https://pith.science/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4","bundle":"https://pith.science/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/bundle.json","state":"https://pith.science/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HE2PWC3RLHO7Y3RCJKZU36CYS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HE2PWC3RLHO7Y3RCJKZU36CYS4","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":"f3eee8ee8669d38660c8b7fd73c2814e8a4adf2029c115c5d3a579a975178d51","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T20:51:58Z","title_canon_sha256":"e723adc73cee544802b0526ee3258f5f40af775200bfd76504a8e491e002454a"},"schema_version":"1.0","source":{"id":"1907.07751","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07751","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07751v2","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07751","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"HE2PWC3RLHO7","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"HE2PWC3RLHO7Y3RC","created_at":"2026-07-05T00:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"HE2PWC3R","created_at":"2026-07-05T00:25:55Z"}],"graph_snapshots":[{"event_id":"sha256:965fe862cb29c7c3cb76819df464ea295a83530766ba7c6ea379e6b626652015","target":"graph","created_at":"2026-07-05T00:25:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.07751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update---a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the step-size parameters to minimize prediction error. These meta-descent strategies","authors_text":"Adam White, Andrew Jacobsen, Cameron Linke, Martha White, Matthew Schlegel, Thomas Degris","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T20:51:58Z","title":"Meta-descent for Online, Continual Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07751","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":"sha256:564d0f8fb3b0dbac430719efd5eedab7e4d781a4e9243a9e1d9ab2d5b0fd8403","target":"record","created_at":"2026-07-05T00:25:55Z","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":"f3eee8ee8669d38660c8b7fd73c2814e8a4adf2029c115c5d3a579a975178d51","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T20:51:58Z","title_canon_sha256":"e723adc73cee544802b0526ee3258f5f40af775200bfd76504a8e491e002454a"},"schema_version":"1.0","source":{"id":"1907.07751","kind":"arxiv","version":2}},"canonical_sha256":"3934fb0b7159ddfc6e224ab34df8589716a035439a075007bad83083d5a7d29a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3934fb0b7159ddfc6e224ab34df8589716a035439a075007bad83083d5a7d29a","first_computed_at":"2026-07-05T00:25:55.736213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:55.736213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Si47RIxQ6bc+rVV/5pOA6+ryseLBPnAjd7Vr0vuFXfa8gvfNYYViMS6/lflXYSCSzaT4sUN9kM30mw/X/OYsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:55.736717Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.07751","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:564d0f8fb3b0dbac430719efd5eedab7e4d781a4e9243a9e1d9ab2d5b0fd8403","sha256:965fe862cb29c7c3cb76819df464ea295a83530766ba7c6ea379e6b626652015"],"state_sha256":"8dbb43f6a20b092f58536d11346c88c31c29d6c8fbce2b21ce709edefdac05fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXQOgfhJCmU2ZxlmjyQ1VPlSXIHl5lqFWVs+9SbMjgmh8QkFSmpdX5A9kB6w7VKrO8kgkNcrhPUXgQOZx4TkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:10:10.471959Z","bundle_sha256":"f220aeafa75c161d08537b2851fec5722102d8529e9156cdd4553bf454835b9c"}}