{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7LMCWZCFFNBPU5KZEI7OZXEPEF","short_pith_number":"pith:7LMCWZCF","schema_version":"1.0","canonical_sha256":"fad82b64452b42fa7559223eecdc8f21793c53f5ea708174add40151cf5e526b","source":{"kind":"arxiv","id":"2204.04964","version":2},"attestation_state":"computed","paper":{"title":"Projection-free Online Learning with Arbitrary Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yao, Lijun Zhang, Wei-Wei Tu, Yibo Wang, Yuanyu Wan","submitted_at":"2022-04-11T09:26:24Z","abstract_excerpt":"Projection-free online learning, which eschews the projection operation via less expensive computations such as linear optimization (LO), has received much interest recently due to its efficiency in handling high-dimensional problems with complex constraints. However, previous studies assume that any queried gradient is revealed immediately, which may not hold in practice and limits their applications. To address this limitation, we generalize the online Frank-Wolfe (OFW) algorithm and the online smooth projection-free (OSPF) algorithm, which are state-of-the-art LO-based projection-free onlin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.04964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T09:26:24Z","cross_cats_sorted":[],"title_canon_sha256":"420ba8714fb39cc844f78f64285346ba753d595f41663a731735a049d6b4389e","abstract_canon_sha256":"ee9cbed92f8b8921875f1cbf89b095e5860a57b0a88a29c3fc3679abae550f1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:55.021927Z","signature_b64":"wtNglWbsZIcxsGd/NexuZdvpZwYRRYE5plCFzxd+DdcYCk/WH9wwOElu6qPGQIMBmAD/o0bSeKzrCSlHejVvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad82b64452b42fa7559223eecdc8f21793c53f5ea708174add40151cf5e526b","last_reissued_at":"2026-07-05T06:11:55.021507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:55.021507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projection-free Online Learning with Arbitrary Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yao, Lijun Zhang, Wei-Wei Tu, Yibo Wang, Yuanyu Wan","submitted_at":"2022-04-11T09:26:24Z","abstract_excerpt":"Projection-free online learning, which eschews the projection operation via less expensive computations such as linear optimization (LO), has received much interest recently due to its efficiency in handling high-dimensional problems with complex constraints. However, previous studies assume that any queried gradient is revealed immediately, which may not hold in practice and limits their applications. To address this limitation, we generalize the online Frank-Wolfe (OFW) algorithm and the online smooth projection-free (OSPF) algorithm, which are state-of-the-art LO-based projection-free onlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04964","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/2204.04964/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.04964","created_at":"2026-07-05T06:11:55.021562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04964v2","created_at":"2026-07-05T06:11:55.021562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04964","created_at":"2026-07-05T06:11:55.021562+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LMCWZCFFNBP","created_at":"2026-07-05T06:11:55.021562+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LMCWZCFFNBPU5KZ","created_at":"2026-07-05T06:11:55.021562+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LMCWZCF","created_at":"2026-07-05T06:11:55.021562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11711","citing_title":"Capacity-Constrained Online Convex Optimization with Delayed Feedback","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF","json":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF.json","graph_json":"https://pith.science/api/pith-number/7LMCWZCFFNBPU5KZEI7OZXEPEF/graph.json","events_json":"https://pith.science/api/pith-number/7LMCWZCFFNBPU5KZEI7OZXEPEF/events.json","paper":"https://pith.science/paper/7LMCWZCF"},"agent_actions":{"view_html":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF","download_json":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF.json","view_paper":"https://pith.science/paper/7LMCWZCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04964&json=true","fetch_graph":"https://pith.science/api/pith-number/7LMCWZCFFNBPU5KZEI7OZXEPEF/graph.json","fetch_events":"https://pith.science/api/pith-number/7LMCWZCFFNBPU5KZEI7OZXEPEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF/action/storage_attestation","attest_author":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF/action/author_attestation","sign_citation":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF/action/citation_signature","submit_replication":"https://pith.science/pith/7LMCWZCFFNBPU5KZEI7OZXEPEF/action/replication_record"}},"created_at":"2026-07-05T06:11:55.021562+00:00","updated_at":"2026-07-05T06:11:55.021562+00:00"}