{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HPYMTG564G2PXA2F4B4XFXYL2J","short_pith_number":"pith:HPYMTG56","canonical_record":{"source":{"id":"1812.00856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:01:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12aead6cdc38fc71e4f22d9ffe6394c70fefd59ea960975a649600258afae96c","abstract_canon_sha256":"045f2dfefb8767467d2f206f177ee285c6181fe11812f959edf9f120e23bde35"},"schema_version":"1.0"},"canonical_sha256":"3bf0c99bbee1b4fb8345e07972df0bd248fa70ba91634972a5ee493f644c1c30","source":{"kind":"arxiv","id":"1812.00856","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00856","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00856v1","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00856","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"HPYMTG564G2P","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HPYMTG564G2PXA2F","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HPYMTG56","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HPYMTG564G2PXA2F4B4XFXYL2J","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:01:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12aead6cdc38fc71e4f22d9ffe6394c70fefd59ea960975a649600258afae96c","abstract_canon_sha256":"045f2dfefb8767467d2f206f177ee285c6181fe11812f959edf9f120e23bde35"},"schema_version":"1.0"},"canonical_sha256":"3bf0c99bbee1b4fb8345e07972df0bd248fa70ba91634972a5ee493f644c1c30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:18.791780Z","signature_b64":"lTcUr9Fsb8HrcHAbLwM+WI7XW+EA5jj2om8+Y8AkGhHNKd8+qJS8l5oR4fMW99kqjtBpPT9YF93eFmXoY6S+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf0c99bbee1b4fb8345e07972df0bd248fa70ba91634972a5ee493f644c1c30","last_reissued_at":"2026-05-17T23:59:18.791361Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:18.791361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00856","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3j6SzyzaBQrxPcw50JDpNkJTaOTOWrdIqHraF9AXMHGjzrz24PjgDtHDSs3I57wjLRZok9tBbzeFSAvFf55yAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:31:16.646854Z"},"content_sha256":"4a0cf813b2874dd9f9ed215ed34e9a3644bf61273991a4604516d7b44cd814c9","schema_version":"1.0","event_id":"sha256:4a0cf813b2874dd9f9ed215ed34e9a3644bf61273991a4604516d7b44cd814c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HPYMTG564G2PXA2F4B4XFXYL2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thompson Sampling for Noncompliant Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Stirn, Tony Jebara","submitted_at":"2018-12-03T16:01:43Z","abstract_excerpt":"Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains. Traditional Thompson sampling, however, assumes perfect compliance, where an agent's chosen action is treated as the implemented action. This article introduces a stochastic noncompliance model that relaxes this assumption. We prove that any noncompliance in a 2-armed Bernoulli bandit increases existing regret bounds. With our noncompliance model, we derive Thompson sampling variants that explicitly handle both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00856","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":""},"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":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7N3ad/jQUavM0jhStzfa4QT1ptWSkWNPN8bMkbj4FmunuPTBtN3THG2bvMo6mfRQdW9pJEfPmLCvgI3M1yktCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:31:16.647560Z"},"content_sha256":"ff702f37962a2423592c123864233da99e10f377fc9cf19583ee9233d8c5917c","schema_version":"1.0","event_id":"sha256:ff702f37962a2423592c123864233da99e10f377fc9cf19583ee9233d8c5917c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPYMTG564G2PXA2F4B4XFXYL2J/bundle.json","state_url":"https://pith.science/pith/HPYMTG564G2PXA2F4B4XFXYL2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPYMTG564G2PXA2F4B4XFXYL2J/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":"2026-06-05T20:31:16Z","links":{"resolver":"https://pith.science/pith/HPYMTG564G2PXA2F4B4XFXYL2J","bundle":"https://pith.science/pith/HPYMTG564G2PXA2F4B4XFXYL2J/bundle.json","state":"https://pith.science/pith/HPYMTG564G2PXA2F4B4XFXYL2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPYMTG564G2PXA2F4B4XFXYL2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HPYMTG564G2PXA2F4B4XFXYL2J","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":"045f2dfefb8767467d2f206f177ee285c6181fe11812f959edf9f120e23bde35","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:01:43Z","title_canon_sha256":"12aead6cdc38fc71e4f22d9ffe6394c70fefd59ea960975a649600258afae96c"},"schema_version":"1.0","source":{"id":"1812.00856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00856","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00856v1","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00856","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"HPYMTG564G2P","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HPYMTG564G2PXA2F","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HPYMTG56","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:ff702f37962a2423592c123864233da99e10f377fc9cf19583ee9233d8c5917c","target":"graph","created_at":"2026-05-17T23:59:18Z","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":"Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains. Traditional Thompson sampling, however, assumes perfect compliance, where an agent's chosen action is treated as the implemented action. This article introduces a stochastic noncompliance model that relaxes this assumption. We prove that any noncompliance in a 2-armed Bernoulli bandit increases existing regret bounds. With our noncompliance model, we derive Thompson sampling variants that explicitly handle both","authors_text":"Andrew Stirn, Tony Jebara","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:01:43Z","title":"Thompson Sampling for Noncompliant Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00856","kind":"arxiv","version":1},"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":"sha256:4a0cf813b2874dd9f9ed215ed34e9a3644bf61273991a4604516d7b44cd814c9","target":"record","created_at":"2026-05-17T23:59:18Z","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":"045f2dfefb8767467d2f206f177ee285c6181fe11812f959edf9f120e23bde35","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:01:43Z","title_canon_sha256":"12aead6cdc38fc71e4f22d9ffe6394c70fefd59ea960975a649600258afae96c"},"schema_version":"1.0","source":{"id":"1812.00856","kind":"arxiv","version":1}},"canonical_sha256":"3bf0c99bbee1b4fb8345e07972df0bd248fa70ba91634972a5ee493f644c1c30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bf0c99bbee1b4fb8345e07972df0bd248fa70ba91634972a5ee493f644c1c30","first_computed_at":"2026-05-17T23:59:18.791361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:18.791361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lTcUr9Fsb8HrcHAbLwM+WI7XW+EA5jj2om8+Y8AkGhHNKd8+qJS8l5oR4fMW99kqjtBpPT9YF93eFmXoY6S+Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:18.791780Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0cf813b2874dd9f9ed215ed34e9a3644bf61273991a4604516d7b44cd814c9","sha256:ff702f37962a2423592c123864233da99e10f377fc9cf19583ee9233d8c5917c"],"state_sha256":"914f93fe271c98c49b25688b3ae460fa7f6475a6ade27ed3bd5a87c73649cea7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnjhSm93n7lAe41ZTBZDrmpi0VUBLLNYRItDq2Zwr+K1LCKcDosPU+Uxnh1j7kuNfs/VYwKAEKcoXqmB52BcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:31:16.651756Z","bundle_sha256":"aad7d5da954ee1b601e7f3633bf96eb747d585c835fa2d254eb800857dee7a95"}}