{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RX6CXGW5K6ATBMCKDSI4TEXKNF","short_pith_number":"pith:RX6CXGW5","schema_version":"1.0","canonical_sha256":"8dfc2b9add578130b04a1c91c992ea6956b09b6e5c77723363186e08d957abbe","source":{"kind":"arxiv","id":"2606.06043","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chansoo Kim, Jongyeong Lee, Junya Honda, Shinji Ito","submitted_at":"2026-06-04T11:36:08Z","abstract_excerpt":"Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-selection probabilities, obtained by solving convex optimization, have achieved improved best-of-both-worlds (BOBW) guarantees in various bandit problems. In contrast, BOBW guarantees for its computationally efficient alternative, follow-the-perturbed-leader (FTPL), remain relatively limited since its optimization-free nature ironically makes the design of adaptive, "},"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":"2606.06043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-04T11:36:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6abdec21813145d1d66d403e956ef48db776b49c08dc0d553a69e52a022bb08c","abstract_canon_sha256":"28411f780a40bc54e1525b931fc42749cdf1a1110fdd22bdbd10430d13155898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:31.389233Z","signature_b64":"nSElHhiILGBSKx8uXED40694pSA2MfZb5aMOFYIqf8sUvqBpiKvCSygcJ828+8+23RrBV+3hDyUqKvBZQJ6AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dfc2b9add578130b04a1c91c992ea6956b09b6e5c77723363186e08d957abbe","last_reissued_at":"2026-06-05T01:15:31.388840Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:31.388840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chansoo Kim, Jongyeong Lee, Junya Honda, Shinji Ito","submitted_at":"2026-06-04T11:36:08Z","abstract_excerpt":"Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-selection probabilities, obtained by solving convex optimization, have achieved improved best-of-both-worlds (BOBW) guarantees in various bandit problems. In contrast, BOBW guarantees for its computationally efficient alternative, follow-the-perturbed-leader (FTPL), remain relatively limited since its optimization-free nature ironically makes the design of adaptive, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06043","kind":"arxiv","version":1},"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/2606.06043/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":"2606.06043","created_at":"2026-06-05T01:15:31.388895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06043v1","created_at":"2026-06-05T01:15:31.388895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06043","created_at":"2026-06-05T01:15:31.388895+00:00"},{"alias_kind":"pith_short_12","alias_value":"RX6CXGW5K6AT","created_at":"2026-06-05T01:15:31.388895+00:00"},{"alias_kind":"pith_short_16","alias_value":"RX6CXGW5K6ATBMCK","created_at":"2026-06-05T01:15:31.388895+00:00"},{"alias_kind":"pith_short_8","alias_value":"RX6CXGW5","created_at":"2026-06-05T01:15:31.388895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF","json":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF.json","graph_json":"https://pith.science/api/pith-number/RX6CXGW5K6ATBMCKDSI4TEXKNF/graph.json","events_json":"https://pith.science/api/pith-number/RX6CXGW5K6ATBMCKDSI4TEXKNF/events.json","paper":"https://pith.science/paper/RX6CXGW5"},"agent_actions":{"view_html":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF","download_json":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF.json","view_paper":"https://pith.science/paper/RX6CXGW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06043&json=true","fetch_graph":"https://pith.science/api/pith-number/RX6CXGW5K6ATBMCKDSI4TEXKNF/graph.json","fetch_events":"https://pith.science/api/pith-number/RX6CXGW5K6ATBMCKDSI4TEXKNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF/action/storage_attestation","attest_author":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF/action/author_attestation","sign_citation":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF/action/citation_signature","submit_replication":"https://pith.science/pith/RX6CXGW5K6ATBMCKDSI4TEXKNF/action/replication_record"}},"created_at":"2026-06-05T01:15:31.388895+00:00","updated_at":"2026-06-05T01:15:31.388895+00:00"}