{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2VJULYVOGQMM6BDFZ4WH6AX4UX","short_pith_number":"pith:2VJULYVO","canonical_record":{"source":{"id":"1903.04666","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-12T00:03:44Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"c16cdb7e0480951022b8deff37237efab55201342cbb2834aa29493bcb1e1c89","abstract_canon_sha256":"129ff7ad13e1e7d394aa6a40511238824236428681af054d0000d02f85714827"},"schema_version":"1.0"},"canonical_sha256":"d55345e2ae3418cf0465cf2c7f02fca5ccdaddf0c0150fd452c7deca20182ecd","source":{"kind":"arxiv","id":"1903.04666","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04666","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04666v3","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04666","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"pith_short_12","alias_value":"2VJULYVOGQMM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2VJULYVOGQMM6BDF","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2VJULYVO","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2VJULYVOGQMM6BDFZ4WH6AX4UX","target":"record","payload":{"canonical_record":{"source":{"id":"1903.04666","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-12T00:03:44Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"c16cdb7e0480951022b8deff37237efab55201342cbb2834aa29493bcb1e1c89","abstract_canon_sha256":"129ff7ad13e1e7d394aa6a40511238824236428681af054d0000d02f85714827"},"schema_version":"1.0"},"canonical_sha256":"d55345e2ae3418cf0465cf2c7f02fca5ccdaddf0c0150fd452c7deca20182ecd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:54.979839Z","signature_b64":"VcYcGZrXcDJsWoAWMagO3AiVthSaKG7rCyPt9WAbL52vyTx7vEnSpOVR1OWgRkTKVoa/dDMdRxjtXMGbPxV6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d55345e2ae3418cf0465cf2c7f02fca5ccdaddf0c0150fd452c7deca20182ecd","last_reissued_at":"2026-05-17T23:44:54.979248Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:54.979248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.04666","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":"2026-05-17T23:44:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4PAy6mJFzOyEUWfTQTbP7CXagXY3V8Yk6NEmp4810XlMW81mzN/Wd6YrdnjiZ/POLf8gf63U0m0KtLRVI4wXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:41:00.095662Z"},"content_sha256":"4071df4360a32ced0920f7574e03eaabdfb37ba2b7b0abf47ba61f3928634390","schema_version":"1.0","event_id":"sha256:4071df4360a32ced0920f7574e03eaabdfb37ba2b7b0abf47ba61f3928634390"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2VJULYVOGQMM6BDFZ4WH6AX4UX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"math.OC","authors_text":"Anuradha M. Annaswamy, Joseph E. Gaudio, Michael A. Bolender, Travis E. Gibson","submitted_at":"2019-03-12T00:03:44Z","abstract_excerpt":"Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent methods unstable or weakens their convergence guarantees. Inspired by methods employed in adaptive control, this paper proposes new algorithms for the case when time-varying features are present, and demonstrates provable performance guarantees. In particular, we develop a unified variational perspective within a continuous time algorithm. This variational p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04666","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":"2026-05-17T23:44:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fItKgTFADleCAyvEpNpShTb8UvCS2N47taW+eTZ4I+lWohB4EqMt/lqPc4Tfpoq1e/miEGSnXSVBmd5gdVynBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:41:00.096105Z"},"content_sha256":"32213a649dc01b2a2a64f51537f0f9b3ecfa208509b4b6e3aaf3ab9ac0a8bfde","schema_version":"1.0","event_id":"sha256:32213a649dc01b2a2a64f51537f0f9b3ecfa208509b4b6e3aaf3ab9ac0a8bfde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/bundle.json","state_url":"https://pith.science/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/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":"2026-06-04T02:41:00Z","links":{"resolver":"https://pith.science/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX","bundle":"https://pith.science/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/bundle.json","state":"https://pith.science/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VJULYVOGQMM6BDFZ4WH6AX4UX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2VJULYVOGQMM6BDFZ4WH6AX4UX","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":"129ff7ad13e1e7d394aa6a40511238824236428681af054d0000d02f85714827","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-12T00:03:44Z","title_canon_sha256":"c16cdb7e0480951022b8deff37237efab55201342cbb2834aa29493bcb1e1c89"},"schema_version":"1.0","source":{"id":"1903.04666","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04666","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04666v3","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04666","created_at":"2026-05-17T23:44:54Z"},{"alias_kind":"pith_short_12","alias_value":"2VJULYVOGQMM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2VJULYVOGQMM6BDF","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2VJULYVO","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:32213a649dc01b2a2a64f51537f0f9b3ecfa208509b4b6e3aaf3ab9ac0a8bfde","target":"graph","created_at":"2026-05-17T23:44:54Z","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":"Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent methods unstable or weakens their convergence guarantees. Inspired by methods employed in adaptive control, this paper proposes new algorithms for the case when time-varying features are present, and demonstrates provable performance guarantees. In particular, we develop a unified variational perspective within a continuous time algorithm. This variational p","authors_text":"Anuradha M. Annaswamy, Joseph E. Gaudio, Michael A. Bolender, Travis E. Gibson","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-12T00:03:44Z","title":"Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04666","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":"sha256:4071df4360a32ced0920f7574e03eaabdfb37ba2b7b0abf47ba61f3928634390","target":"record","created_at":"2026-05-17T23:44:54Z","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":"129ff7ad13e1e7d394aa6a40511238824236428681af054d0000d02f85714827","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-12T00:03:44Z","title_canon_sha256":"c16cdb7e0480951022b8deff37237efab55201342cbb2834aa29493bcb1e1c89"},"schema_version":"1.0","source":{"id":"1903.04666","kind":"arxiv","version":3}},"canonical_sha256":"d55345e2ae3418cf0465cf2c7f02fca5ccdaddf0c0150fd452c7deca20182ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d55345e2ae3418cf0465cf2c7f02fca5ccdaddf0c0150fd452c7deca20182ecd","first_computed_at":"2026-05-17T23:44:54.979248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:54.979248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VcYcGZrXcDJsWoAWMagO3AiVthSaKG7rCyPt9WAbL52vyTx7vEnSpOVR1OWgRkTKVoa/dDMdRxjtXMGbPxV6CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:54.979839Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.04666","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4071df4360a32ced0920f7574e03eaabdfb37ba2b7b0abf47ba61f3928634390","sha256:32213a649dc01b2a2a64f51537f0f9b3ecfa208509b4b6e3aaf3ab9ac0a8bfde"],"state_sha256":"75665b74e107cf4320906c16702be5800df2c213d0e28be0d5a4643ce89bd4ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3K54LNf2qiSMxpEEWvENrVed1EcYPfOPkR+x/Vgf2YQchIgwO76ZSK5y6vMqs0iVWg0weN/23zM8EmIpv0PrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T02:41:00.099824Z","bundle_sha256":"d2bdcf2083e8cfe75fd7b2ebf1f26c7803c634b084801a6cc3780f3f15215349"}}