{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:WTGETPM2ZKEQ3EFSDZLW6BRMT2","short_pith_number":"pith:WTGETPM2","canonical_record":{"source":{"id":"1302.6937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-27T17:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"83d733cea1e9dafda19dc026c5e7dbf4ba8bbd8d06a4da1bc84aacec47adc262","abstract_canon_sha256":"1bff92582b42b8ab1a4b220bb4035e28ef0a56656594dbe0ab040d3d0be410f8"},"schema_version":"1.0"},"canonical_sha256":"b4cc49bd9aca890d90b21e576f062c9e9f863ee284ab993d1eb958965ec25ed1","source":{"kind":"arxiv","id":"1302.6937","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1302.6937","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"1302.6937v2","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.6937","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"WTGETPM2ZKEQ","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"WTGETPM2ZKEQ3EFS","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"WTGETPM2","created_at":"2026-05-18T12:28:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:WTGETPM2ZKEQ3EFSDZLW6BRMT2","target":"record","payload":{"canonical_record":{"source":{"id":"1302.6937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-27T17:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"83d733cea1e9dafda19dc026c5e7dbf4ba8bbd8d06a4da1bc84aacec47adc262","abstract_canon_sha256":"1bff92582b42b8ab1a4b220bb4035e28ef0a56656594dbe0ab040d3d0be410f8"},"schema_version":"1.0"},"canonical_sha256":"b4cc49bd9aca890d90b21e576f062c9e9f863ee284ab993d1eb958965ec25ed1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:03.527664Z","signature_b64":"cBo9dtMARO11puAn4fMJflOQa1i8a3B6hnxrh+7hIAlv545zFJYedBk3GRRLjW+vy1J7x/SudRlynwgo0mKeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4cc49bd9aca890d90b21e576f062c9e9f863ee284ab993d1eb958965ec25ed1","last_reissued_at":"2026-05-18T02:50:03.526873Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:03.526873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1302.6937","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":"2026-05-18T02:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jUBazdqbObfPi6AMlk2GuSCAbHjttxQqLkiZ1VYlkqp/quAsfeAg/3fnMXXnpqO8n6IAckQTlKj8+XtU30JOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:11:10.145484Z"},"content_sha256":"1fcb6dd06d1c37d1278b6116999cbfd9842801c604bf485550a1e8308edb0500","schema_version":"1.0","event_id":"sha256:1fcb6dd06d1c37d1278b6116999cbfd9842801c604bf485550a1e8308edb0500"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:WTGETPM2ZKEQ3EFSDZLW6BRMT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Convex Optimization Against Adversaries with Memory and Application to Statistical Arbitrage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elad Hazan, Oren Anava, Shie Mannor","submitted_at":"2013-02-27T17:46:43Z","abstract_excerpt":"The framework of online learning with memory naturally captures learning problems with temporal constraints, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obtaining optimal regret bounds for both convex and strongly convex losses. The second algorithm attains the optimal regret bounds and applies more broadly to convex losses without requiring Lipschitz co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.6937","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":"2026-05-18T02:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UPnzKOY32kdIf/F7Vz4HYvJKnuczufPHz9hgprsk+1+Osfw1uqUvVLEBGruZzHchbgkWLg3AaCdv3iGB2k/RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:11:10.145838Z"},"content_sha256":"3a54ad0386b059916eb0769c90ccde74cd2bbd4b5c47a14bef32c38d458cedf8","schema_version":"1.0","event_id":"sha256:3a54ad0386b059916eb0769c90ccde74cd2bbd4b5c47a14bef32c38d458cedf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/bundle.json","state_url":"https://pith.science/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/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":"2026-05-31T05:11:10Z","links":{"resolver":"https://pith.science/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2","bundle":"https://pith.science/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/bundle.json","state":"https://pith.science/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTGETPM2ZKEQ3EFSDZLW6BRMT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:WTGETPM2ZKEQ3EFSDZLW6BRMT2","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":"1bff92582b42b8ab1a4b220bb4035e28ef0a56656594dbe0ab040d3d0be410f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-27T17:46:43Z","title_canon_sha256":"83d733cea1e9dafda19dc026c5e7dbf4ba8bbd8d06a4da1bc84aacec47adc262"},"schema_version":"1.0","source":{"id":"1302.6937","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1302.6937","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"1302.6937v2","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.6937","created_at":"2026-05-18T02:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"WTGETPM2ZKEQ","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"WTGETPM2ZKEQ3EFS","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"WTGETPM2","created_at":"2026-05-18T12:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:3a54ad0386b059916eb0769c90ccde74cd2bbd4b5c47a14bef32c38d458cedf8","target":"graph","created_at":"2026-05-18T02:50:03Z","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":"The framework of online learning with memory naturally captures learning problems with temporal constraints, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obtaining optimal regret bounds for both convex and strongly convex losses. The second algorithm attains the optimal regret bounds and applies more broadly to convex losses without requiring Lipschitz co","authors_text":"Elad Hazan, Oren Anava, Shie Mannor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-27T17:46:43Z","title":"Online Convex Optimization Against Adversaries with Memory and Application to Statistical Arbitrage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.6937","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":"sha256:1fcb6dd06d1c37d1278b6116999cbfd9842801c604bf485550a1e8308edb0500","target":"record","created_at":"2026-05-18T02:50:03Z","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":"1bff92582b42b8ab1a4b220bb4035e28ef0a56656594dbe0ab040d3d0be410f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-27T17:46:43Z","title_canon_sha256":"83d733cea1e9dafda19dc026c5e7dbf4ba8bbd8d06a4da1bc84aacec47adc262"},"schema_version":"1.0","source":{"id":"1302.6937","kind":"arxiv","version":2}},"canonical_sha256":"b4cc49bd9aca890d90b21e576f062c9e9f863ee284ab993d1eb958965ec25ed1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4cc49bd9aca890d90b21e576f062c9e9f863ee284ab993d1eb958965ec25ed1","first_computed_at":"2026-05-18T02:50:03.526873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:50:03.526873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cBo9dtMARO11puAn4fMJflOQa1i8a3B6hnxrh+7hIAlv545zFJYedBk3GRRLjW+vy1J7x/SudRlynwgo0mKeBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:50:03.527664Z","signed_message":"canonical_sha256_bytes"},"source_id":"1302.6937","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fcb6dd06d1c37d1278b6116999cbfd9842801c604bf485550a1e8308edb0500","sha256:3a54ad0386b059916eb0769c90ccde74cd2bbd4b5c47a14bef32c38d458cedf8"],"state_sha256":"0b28994a417077c552b3480c599f52c2c423f7907b884f04e5789bdbaa124564"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hzqC0keohNnuYkmDieLbX8KkWG4VzQqXDku1tGhwxoY9oUsNATe0PDGHcG4/PmoEONT+SUzOe3HAxzh0rfo0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:11:10.148168Z","bundle_sha256":"ae39f9b6c7f68911573cef051aab9f88bb9a21414364e1c77c70d08a6b57f535"}}