{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SEBQQAX3FXZE7VIHZ6NS2E6G6M","short_pith_number":"pith:SEBQQAX3","canonical_record":{"source":{"id":"2604.20024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T22:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"8609ea4fe477c0a106d96b015674d2788da8f9a91c718b65e03d90e3c582cc41","abstract_canon_sha256":"28fbd29e9c43e8bc3b68d17370c681c00d00a0903a94b8c7739ab1f1cab08b1a"},"schema_version":"1.0"},"canonical_sha256":"91030802fb2df24fd507cf9b2d13c6f33c699c3be5695287f4b89dbfa283896d","source":{"kind":"arxiv","id":"2604.20024","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20024","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20024v2","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20024","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"SEBQQAX3FXZE","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"SEBQQAX3FXZE7VIH","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"SEBQQAX3","created_at":"2026-06-10T01:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SEBQQAX3FXZE7VIHZ6NS2E6G6M","target":"record","payload":{"canonical_record":{"source":{"id":"2604.20024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T22:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"8609ea4fe477c0a106d96b015674d2788da8f9a91c718b65e03d90e3c582cc41","abstract_canon_sha256":"28fbd29e9c43e8bc3b68d17370c681c00d00a0903a94b8c7739ab1f1cab08b1a"},"schema_version":"1.0"},"canonical_sha256":"91030802fb2df24fd507cf9b2d13c6f33c699c3be5695287f4b89dbfa283896d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:01.456042Z","signature_b64":"ew2ZqpgaaDWumv99f2iVVfah31QK4uUEYDJ8he+ONDjA8x2SQweudOvfLfUAem60+A1WTz3NlJgzJHRSRRveCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91030802fb2df24fd507cf9b2d13c6f33c699c3be5695287f4b89dbfa283896d","last_reissued_at":"2026-06-10T01:10:01.455132Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:01.455132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.20024","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":"2026-06-10T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIU4ZfxJTsI9sOXxRHdr21XCrPGbwMPVvmnkwS8vYnXsaRpybD3DuVoTqN/NcgZ5iTZosQH6+JwoR1nVpDjICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:13.627417Z"},"content_sha256":"9a77fcc195c92a4b96b4b4877db56edd8f2b63700ebee2073a577c0a7b8927f5","schema_version":"1.0","event_id":"sha256:9a77fcc195c92a4b96b4b4877db56edd8f2b63700ebee2073a577c0a7b8927f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SEBQQAX3FXZE7VIHZ6NS2E6G6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Replicable Bandits with UCB based Exploration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arindam Banerjee, Karan Singh, Rohan Deb, Udaya Ghai","submitted_at":"2026-04-21T22:04:35Z","abstract_excerpt":"We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is $\\rho$-replicable if two executions using shared internal randomness but independent reward realizations produce the same action sequence with probability at least $1-\\rho$. Prior approaches to this problem are elimination-based and, in linear bandits with infinitely many actions, rely on discretization, leading to suboptimal dependence on the dimension $d$ and $\\rho$. We develop optimistic alternatives for both settings. For stoc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RepLinUCB attains regret Õ((d + d³/ρ)√T), improving the best prior guarantee by a factor of O(d/ρ) while satisfying ρ-replicability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The analysis assumes stochastic rewards with sub-Gaussian tails and that the shared randomness can be perfectly synchronized across independent executions; if either fails the replicability or regret guarantees may not hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f38262320cb54f52c392ebf9025cd5949e0f0ea1bfaf748c7a35b948a40ad69c"},"source":{"id":"2604.20024","kind":"arxiv","version":2},"verdict":{"id":"de014cb4-2041-4aad-86af-2a1928a0d52f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T02:19:44.675840Z","strongest_claim":"RepLinUCB attains regret Õ((d + d³/ρ)√T), improving the best prior guarantee by a factor of O(d/ρ) while satisfying ρ-replicability.","one_line_summary":"RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The analysis assumes stochastic rewards with sub-Gaussian tails and that the shared randomness can be perfectly synchronized across independent executions; if either fails the replicability or regret guarantees may not hold.","pith_extraction_headline":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20024/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T15:38:32.209516Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:24:11.609145Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"436bb5a31d27d91b53d22015aceb1f71e683abf93330e4339e0b2f92efbf0d79"},"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":"de014cb4-2041-4aad-86af-2a1928a0d52f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7Y0ZRsv19Qe0jZrn1jVFdRn+CHW0vJ0quZkGZNeG+ixXsma+5c6zkdKt98egCGrPOJ7xOQndDhe0d0ZxNYFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:13.628247Z"},"content_sha256":"b098ba9d5e5b82f9b0b805dad9b821cbcd580e5ff98bfeb5df538a10a2c550a8","schema_version":"1.0","event_id":"sha256:b098ba9d5e5b82f9b0b805dad9b821cbcd580e5ff98bfeb5df538a10a2c550a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/bundle.json","state_url":"https://pith.science/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/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":"2026-08-04T05:49:13Z","links":{"resolver":"https://pith.science/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M","bundle":"https://pith.science/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/bundle.json","state":"https://pith.science/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SEBQQAX3FXZE7VIHZ6NS2E6G6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SEBQQAX3FXZE7VIHZ6NS2E6G6M","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":"28fbd29e9c43e8bc3b68d17370c681c00d00a0903a94b8c7739ab1f1cab08b1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T22:04:35Z","title_canon_sha256":"8609ea4fe477c0a106d96b015674d2788da8f9a91c718b65e03d90e3c582cc41"},"schema_version":"1.0","source":{"id":"2604.20024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20024","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20024v2","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20024","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"SEBQQAX3FXZE","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"SEBQQAX3FXZE7VIH","created_at":"2026-06-10T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"SEBQQAX3","created_at":"2026-06-10T01:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:b098ba9d5e5b82f9b0b805dad9b821cbcd580e5ff98bfeb5df538a10a2c550a8","target":"graph","created_at":"2026-06-10T01:10:01Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"RepLinUCB attains regret Õ((d + d³/ρ)√T), improving the best prior guarantee by a factor of O(d/ρ) while satisfying ρ-replicability."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The analysis assumes stochastic rewards with sub-Gaussian tails and that the shared randomness can be perfectly synchronized across independent executions; if either fails the replicability or regret guarantees may not hold."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability."}],"snapshot_sha256":"f38262320cb54f52c392ebf9025cd5949e0f0ea1bfaf748c7a35b948a40ad69c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T15:38:32.209516Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T02:24:11.609145Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.20024/integrity.json","findings":[],"snapshot_sha256":"436bb5a31d27d91b53d22015aceb1f71e683abf93330e4339e0b2f92efbf0d79","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is $\\rho$-replicable if two executions using shared internal randomness but independent reward realizations produce the same action sequence with probability at least $1-\\rho$. Prior approaches to this problem are elimination-based and, in linear bandits with infinitely many actions, rely on discretization, leading to suboptimal dependence on the dimension $d$ and $\\rho$. We develop optimistic alternatives for both settings. For stoc","authors_text":"Arindam Banerjee, Karan Singh, Rohan Deb, Udaya Ghai","cross_cats":[],"headline":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T22:04:35Z","title":"Replicable Bandits with UCB based Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.20024","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T02:19:44.675840Z","id":"de014cb4-2041-4aad-86af-2a1928a0d52f","model_set":{"reader":"grok-4.3"},"one_line_summary":"RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Replicable optimistic UCB algorithms for linear bandits attain Õ((d + d³/ρ)√T) regret while matching actions across runs with high probability.","strongest_claim":"RepLinUCB attains regret Õ((d + d³/ρ)√T), improving the best prior guarantee by a factor of O(d/ρ) while satisfying ρ-replicability.","weakest_assumption":"The analysis assumes stochastic rewards with sub-Gaussian tails and that the shared randomness can be perfectly synchronized across independent executions; if either fails the replicability or regret guarantees may not hold."}},"verdict_id":"de014cb4-2041-4aad-86af-2a1928a0d52f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9a77fcc195c92a4b96b4b4877db56edd8f2b63700ebee2073a577c0a7b8927f5","target":"record","created_at":"2026-06-10T01:10:01Z","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":"28fbd29e9c43e8bc3b68d17370c681c00d00a0903a94b8c7739ab1f1cab08b1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T22:04:35Z","title_canon_sha256":"8609ea4fe477c0a106d96b015674d2788da8f9a91c718b65e03d90e3c582cc41"},"schema_version":"1.0","source":{"id":"2604.20024","kind":"arxiv","version":2}},"canonical_sha256":"91030802fb2df24fd507cf9b2d13c6f33c699c3be5695287f4b89dbfa283896d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91030802fb2df24fd507cf9b2d13c6f33c699c3be5695287f4b89dbfa283896d","first_computed_at":"2026-06-10T01:10:01.455132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:01.455132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ew2ZqpgaaDWumv99f2iVVfah31QK4uUEYDJ8he+ONDjA8x2SQweudOvfLfUAem60+A1WTz3NlJgzJHRSRRveCw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:01.456042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.20024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a77fcc195c92a4b96b4b4877db56edd8f2b63700ebee2073a577c0a7b8927f5","sha256:b098ba9d5e5b82f9b0b805dad9b821cbcd580e5ff98bfeb5df538a10a2c550a8"],"state_sha256":"736b3b3e4f94723b4bb1b7dfced0b7cb26f31ee84f9178d0e71f3591c08fd475"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9OpVOWz9duYAxH+/UnxNtUKBJmOejMXGpQajlRSDIp5GqrtWbTyzwNbMQfs/k6ix4EJfkPSk8WiCyPK9C0DxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:49:13.634741Z","bundle_sha256":"b10243c535f74b0da3ab97366e862de3baf90d11fd6dffcc2439286b18dd26ea"}}