{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KPUXKEOQYKHHWH5NMF5ITT76XA","short_pith_number":"pith:KPUXKEOQ","canonical_record":{"source":{"id":"2008.03959","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b4ef5eeaf69968f7998ba412cf214dab90f3ebb8b39c72318063a7ab2e9aa39","abstract_canon_sha256":"5adcd8f3ab99ee5c2e0ffb02ba501fb420a2edd8415c41dcf00e6fe95ecd3447"},"schema_version":"1.0"},"canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","source":{"kind":"arxiv","id":"2008.03959","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03959","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03959v4","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03959","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"KPUXKEOQYKHH","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"KPUXKEOQYKHHWH5N","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"KPUXKEOQ","created_at":"2026-07-05T03:13:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KPUXKEOQYKHHWH5NMF5ITT76XA","target":"record","payload":{"canonical_record":{"source":{"id":"2008.03959","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b4ef5eeaf69968f7998ba412cf214dab90f3ebb8b39c72318063a7ab2e9aa39","abstract_canon_sha256":"5adcd8f3ab99ee5c2e0ffb02ba501fb420a2edd8415c41dcf00e6fe95ecd3447"},"schema_version":"1.0"},"canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:22.739726Z","signature_b64":"DH4wkkA0ldrA8TWdDVt36DufZ7nVt1dV8axZMr3ZANcrTDe0yNhsHPLHq/gkOixgDbVAvtAF/rpHhBFMDrobDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","last_reissued_at":"2026-07-05T03:13:22.739282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:22.739282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.03959","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubfsRenwLizsZVab0wqya3EuJfav1nBPFYewD1PWX5J+OlvooesX5PZOyYllZWf/XDveHMpGwE1Ixc96agXUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:20:49.752908Z"},"content_sha256":"ecf7d4819a3f6da80bb07ea3a8654282b6588a505b3f80efbddeaac62dbf26fd","schema_version":"1.0","event_id":"sha256:ecf7d4819a3f6da80bb07ea3a8654282b6588a505b3f80efbddeaac62dbf26fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KPUXKEOQYKHHWH5NMF5ITT76XA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lenient Regret for Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Merlis, Shie Mannor","submitted_at":"2020-08-10T08:30:52Z","abstract_excerpt":"We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03959","kind":"arxiv","version":4},"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/2008.03959/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QIX537MNKcr2BHgrh6ApyvtVPeM9otIcR5YFZchkq9mwBlHGMb+46kjtt4G7d7v4CmgsQsXQVVJil/E4OpbwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:20:49.834984Z"},"content_sha256":"9a3edc4c45b9cff146b5128147e0e929e1c523e863d8ead8c2140c748474dada","schema_version":"1.0","event_id":"sha256:9a3edc4c45b9cff146b5128147e0e929e1c523e863d8ead8c2140c748474dada"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/bundle.json","state_url":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/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":"2026-08-12T15:20:49Z","links":{"resolver":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA","bundle":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/bundle.json","state":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KPUXKEOQYKHHWH5NMF5ITT76XA","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":"5adcd8f3ab99ee5c2e0ffb02ba501fb420a2edd8415c41dcf00e6fe95ecd3447","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","title_canon_sha256":"8b4ef5eeaf69968f7998ba412cf214dab90f3ebb8b39c72318063a7ab2e9aa39"},"schema_version":"1.0","source":{"id":"2008.03959","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03959","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03959v4","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03959","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"KPUXKEOQYKHH","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"KPUXKEOQYKHHWH5N","created_at":"2026-07-05T03:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"KPUXKEOQ","created_at":"2026-07-05T03:13:22Z"}],"graph_snapshots":[{"event_id":"sha256:9a3edc4c45b9cff146b5128147e0e929e1c523e863d8ead8c2140c748474dada","target":"graph","created_at":"2026-07-05T03:13:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.03959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus o","authors_text":"Nadav Merlis, Shie Mannor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","title":"Lenient Regret for Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03959","kind":"arxiv","version":4},"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:ecf7d4819a3f6da80bb07ea3a8654282b6588a505b3f80efbddeaac62dbf26fd","target":"record","created_at":"2026-07-05T03:13:22Z","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":"5adcd8f3ab99ee5c2e0ffb02ba501fb420a2edd8415c41dcf00e6fe95ecd3447","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","title_canon_sha256":"8b4ef5eeaf69968f7998ba412cf214dab90f3ebb8b39c72318063a7ab2e9aa39"},"schema_version":"1.0","source":{"id":"2008.03959","kind":"arxiv","version":4}},"canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","first_computed_at":"2026-07-05T03:13:22.739282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:22.739282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DH4wkkA0ldrA8TWdDVt36DufZ7nVt1dV8axZMr3ZANcrTDe0yNhsHPLHq/gkOixgDbVAvtAF/rpHhBFMDrobDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:22.739726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03959","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecf7d4819a3f6da80bb07ea3a8654282b6588a505b3f80efbddeaac62dbf26fd","sha256:9a3edc4c45b9cff146b5128147e0e929e1c523e863d8ead8c2140c748474dada"],"state_sha256":"388e1d51c0e3f4bb468a742fdeb3bcc1132c5e39017533fa576505b295a7f680"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JyBSGn85JvF9qHmyMGUx7SWyJbys0LdZ020qSB1RCwr9trASBF/UbIMYkU+5vJ12vz59q5wDy/0iGPD6y7hDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:20:49.856890Z","bundle_sha256":"bb5fcbac4547d913863e40d80bb6e134e5bcde27a536463331b6383eed305fff"}}