{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RM5NF244SWKIOKHSB5W2PGFQMW","short_pith_number":"pith:RM5NF244","schema_version":"1.0","canonical_sha256":"8b3ad2eb9c95948728f20f6da798b065b3c31a2a0df05b44c54313c6cea78a25","source":{"kind":"arxiv","id":"2408.09074","version":2},"attestation_state":"computed","paper":{"title":"Gradient-Variation Online Learning under Generalized Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Peng Zhao, Yan-Feng Xie, Zhi-Hua Zhou","submitted_at":"2024-08-17T02:22:08Z","abstract_excerpt":"Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic optimization, hence receiving increased attention. Existing results often require the smoothness condition by imposing a fixed bound on gradient Lipschitzness, which may be unrealistic in practice. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. In this paper, we sy"},"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":"2408.09074","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-17T02:22:08Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"25142785d36731d14e300cf1fa6c73845d98b2849952f25060a3324c278a4058","abstract_canon_sha256":"42ca472b84220f2f62a5fcfa49d5dbc1d602f1cad60e28406552c19a934edbe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:20.343927Z","signature_b64":"Rp/YpPlnUEHp1aPKSFPNgGhm1BOKUUvjuU3SlJMUxAs7FPaLryeRURL3kxPxzUCQKtIUnxLSoWaIBBEuTzQtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3ad2eb9c95948728f20f6da798b065b3c31a2a0df05b44c54313c6cea78a25","last_reissued_at":"2026-07-05T09:30:20.343418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:20.343418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-Variation Online Learning under Generalized Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Peng Zhao, Yan-Feng Xie, Zhi-Hua Zhou","submitted_at":"2024-08-17T02:22:08Z","abstract_excerpt":"Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic optimization, hence receiving increased attention. Existing results often require the smoothness condition by imposing a fixed bound on gradient Lipschitzness, which may be unrealistic in practice. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. In this paper, we sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09074","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/2408.09074/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":"2408.09074","created_at":"2026-07-05T09:30:20.343491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09074v2","created_at":"2026-07-05T09:30:20.343491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09074","created_at":"2026-07-05T09:30:20.343491+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM5NF244SWKI","created_at":"2026-07-05T09:30:20.343491+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM5NF244SWKIOKHS","created_at":"2026-07-05T09:30:20.343491+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM5NF244","created_at":"2026-07-05T09:30:20.343491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11773","citing_title":"Toward a Unified Theory of Gradient Descent under Generalized Smoothness","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW","json":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW.json","graph_json":"https://pith.science/api/pith-number/RM5NF244SWKIOKHSB5W2PGFQMW/graph.json","events_json":"https://pith.science/api/pith-number/RM5NF244SWKIOKHSB5W2PGFQMW/events.json","paper":"https://pith.science/paper/RM5NF244"},"agent_actions":{"view_html":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW","download_json":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW.json","view_paper":"https://pith.science/paper/RM5NF244","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09074&json=true","fetch_graph":"https://pith.science/api/pith-number/RM5NF244SWKIOKHSB5W2PGFQMW/graph.json","fetch_events":"https://pith.science/api/pith-number/RM5NF244SWKIOKHSB5W2PGFQMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW/action/storage_attestation","attest_author":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW/action/author_attestation","sign_citation":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW/action/citation_signature","submit_replication":"https://pith.science/pith/RM5NF244SWKIOKHSB5W2PGFQMW/action/replication_record"}},"created_at":"2026-07-05T09:30:20.343491+00:00","updated_at":"2026-07-05T09:30:20.343491+00:00"}