{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:WYTMOWVLW3CLB63XOWRYBWXIAV","short_pith_number":"pith:WYTMOWVL","canonical_record":{"source":{"id":"1205.2874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-13T15:11:00Z","cross_cats_sorted":[],"title_canon_sha256":"5618c053cb01e1d350195da429e41006a8199acc2e2c1e35169525aabcce2fcf","abstract_canon_sha256":"5be3ee9c6d344e1d99c0a6fa171c861f4b1c299981a116eb7a83ebed2fb79ed6"},"schema_version":"1.0"},"canonical_sha256":"b626c75aabb6c4b0fb7775a380dae8054a68e4ef60bce8e8b8ba19cd319e71ad","source":{"kind":"arxiv","id":"1205.2874","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2874","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2874v3","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2874","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"WYTMOWVLW3CL","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WYTMOWVLW3CLB63X","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WYTMOWVL","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:WYTMOWVLW3CLB63XOWRYBWXIAV","target":"record","payload":{"canonical_record":{"source":{"id":"1205.2874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-13T15:11:00Z","cross_cats_sorted":[],"title_canon_sha256":"5618c053cb01e1d350195da429e41006a8199acc2e2c1e35169525aabcce2fcf","abstract_canon_sha256":"5be3ee9c6d344e1d99c0a6fa171c861f4b1c299981a116eb7a83ebed2fb79ed6"},"schema_version":"1.0"},"canonical_sha256":"b626c75aabb6c4b0fb7775a380dae8054a68e4ef60bce8e8b8ba19cd319e71ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:00.722436Z","signature_b64":"ZAURwj/8hig9kN/qygQKguCXR3CGZghMvhDL9K0SOQxAo8btGpfM1SpnAUA9lEAH4HNFLNBmkppOSq83gdZWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b626c75aabb6c4b0fb7775a380dae8054a68e4ef60bce8e8b8ba19cd319e71ad","last_reissued_at":"2026-05-18T03:52:00.721712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:00.721712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1205.2874","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFLP0tEOVRFJStHYDwHLoFN8pD2rAEhVA6QVrUc4ADxSOhvKRXHUmjEWxXFnsJDXqN8CtLoira2svRgO0JRGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:14:05.589191Z"},"content_sha256":"eeb577d0f01e344fbe74941dd28f9dc01283eb19da62971c6869225f4185a751","schema_version":"1.0","event_id":"sha256:eeb577d0f01e344fbe74941dd28f9dc01283eb19da62971c6869225f4185a751"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:WYTMOWVLW3CLB63XOWRYBWXIAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Exploration and Exploitation in Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ohad Shamir, Orly Avner, Shie Mannor","submitted_at":"2012-05-13T15:11:00Z","abstract_excerpt":"We consider a multi-armed bandit problem where the decision maker can explore and exploit different arms at every round. The exploited arm adds to the decision maker's cumulative reward (without necessarily observing the reward) while the explored arm reveals its value. We devise algorithms for this setup and show that the dependence on the number of arms, k, can be much better than the standard square root of k dependence, depending on the behavior of the arms' reward sequences. For the important case of piecewise stationary stochastic bandits, we show a significant improvement over existing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2874","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T03:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3f3DWhUIuNf+4skCrMx+MQ/1IESi4DyhB5R7yWiqRNiyJO7Z3zJWOPJD7Hw7bQ0ZtMdK2HGfFGducNsvdUFyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:14:05.589862Z"},"content_sha256":"f6ebdfd93a9883c48a3ec0fefc5d006cdc6ad8c715895992043c3a17c30781b8","schema_version":"1.0","event_id":"sha256:f6ebdfd93a9883c48a3ec0fefc5d006cdc6ad8c715895992043c3a17c30781b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/bundle.json","state_url":"https://pith.science/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/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":"2026-05-31T03:14:05Z","links":{"resolver":"https://pith.science/pith/WYTMOWVLW3CLB63XOWRYBWXIAV","bundle":"https://pith.science/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/bundle.json","state":"https://pith.science/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYTMOWVLW3CLB63XOWRYBWXIAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WYTMOWVLW3CLB63XOWRYBWXIAV","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":"5be3ee9c6d344e1d99c0a6fa171c861f4b1c299981a116eb7a83ebed2fb79ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-13T15:11:00Z","title_canon_sha256":"5618c053cb01e1d350195da429e41006a8199acc2e2c1e35169525aabcce2fcf"},"schema_version":"1.0","source":{"id":"1205.2874","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2874","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2874v3","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2874","created_at":"2026-05-18T03:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"WYTMOWVLW3CL","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WYTMOWVLW3CLB63X","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WYTMOWVL","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:f6ebdfd93a9883c48a3ec0fefc5d006cdc6ad8c715895992043c3a17c30781b8","target":"graph","created_at":"2026-05-18T03:52:00Z","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"},"paper":{"abstract_excerpt":"We consider a multi-armed bandit problem where the decision maker can explore and exploit different arms at every round. The exploited arm adds to the decision maker's cumulative reward (without necessarily observing the reward) while the explored arm reveals its value. We devise algorithms for this setup and show that the dependence on the number of arms, k, can be much better than the standard square root of k dependence, depending on the behavior of the arms' reward sequences. For the important case of piecewise stationary stochastic bandits, we show a significant improvement over existing ","authors_text":"Ohad Shamir, Orly Avner, Shie Mannor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-13T15:11:00Z","title":"Decoupling Exploration and Exploitation in Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2874","kind":"arxiv","version":3},"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:eeb577d0f01e344fbe74941dd28f9dc01283eb19da62971c6869225f4185a751","target":"record","created_at":"2026-05-18T03:52:00Z","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":"5be3ee9c6d344e1d99c0a6fa171c861f4b1c299981a116eb7a83ebed2fb79ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-13T15:11:00Z","title_canon_sha256":"5618c053cb01e1d350195da429e41006a8199acc2e2c1e35169525aabcce2fcf"},"schema_version":"1.0","source":{"id":"1205.2874","kind":"arxiv","version":3}},"canonical_sha256":"b626c75aabb6c4b0fb7775a380dae8054a68e4ef60bce8e8b8ba19cd319e71ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b626c75aabb6c4b0fb7775a380dae8054a68e4ef60bce8e8b8ba19cd319e71ad","first_computed_at":"2026-05-18T03:52:00.721712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:00.721712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZAURwj/8hig9kN/qygQKguCXR3CGZghMvhDL9K0SOQxAo8btGpfM1SpnAUA9lEAH4HNFLNBmkppOSq83gdZWBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:00.722436Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.2874","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb577d0f01e344fbe74941dd28f9dc01283eb19da62971c6869225f4185a751","sha256:f6ebdfd93a9883c48a3ec0fefc5d006cdc6ad8c715895992043c3a17c30781b8"],"state_sha256":"3a338dccccd25d4271e58b0c7d50f94e5002bd0afdef347c91a60241dbf5f4af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uvnPDawMONyyhPAIlq1uNTeqxeHZd1ea7O7CCJrf1Mzc32PrrJXeNV/IRdu6OL2gDhaOCogI9AY/LIBgZrqLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:14:05.593170Z","bundle_sha256":"2f1a0084fb6fe64caff837948548f570f956e8126ac5a8a5250ba71b0877279a"}}