{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IWL5DAQK3OUFMQA67KXYUXAV2L","short_pith_number":"pith:IWL5DAQK","canonical_record":{"source":{"id":"2302.03319","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T08:49:12Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"039c1d96922a5ba59e5347a4372062b27d45d397ca8f0b7d9962fcd3189f6001","abstract_canon_sha256":"786d8923146a0dc4ea2b8fc6d98d8f84728119c320f580ea6c067848c63de589"},"schema_version":"1.0"},"canonical_sha256":"4597d1820adba856401efaaf8a5c15d2ed91d894fa64d1acae07c80fd9bd4662","source":{"kind":"arxiv","id":"2302.03319","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03319","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03319v4","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03319","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"IWL5DAQK3OUF","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"IWL5DAQK3OUFMQA6","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"IWL5DAQK","created_at":"2026-07-05T06:11:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IWL5DAQK3OUFMQA67KXYUXAV2L","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03319","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T08:49:12Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"039c1d96922a5ba59e5347a4372062b27d45d397ca8f0b7d9962fcd3189f6001","abstract_canon_sha256":"786d8923146a0dc4ea2b8fc6d98d8f84728119c320f580ea6c067848c63de589"},"schema_version":"1.0"},"canonical_sha256":"4597d1820adba856401efaaf8a5c15d2ed91d894fa64d1acae07c80fd9bd4662","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:03.199260Z","signature_b64":"WxXDtmpl8x7GztwLgcoWzn8cZuCI/8yrgapW99bCjym3ZciN1T9AbYcCRmtqRB/qTVcDSLLJcf/nDIUdKvFHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4597d1820adba856401efaaf8a5c15d2ed91d894fa64d1acae07c80fd9bd4662","last_reissued_at":"2026-07-05T06:11:03.198865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:03.198865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03319","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":"2026-07-05T06:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sQqNqS55kvVYqV+nqApvFfLl3fEBDJQrdBxjyNox2vpCe5PZbEfYkILJIeWbKkhDleC+IWLPaNyaDkMAWxAkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:53:45.295314Z"},"content_sha256":"5ee55387244f814a82abd806c4c5b11fff547866ad202b580d00ce3a67bc3033","schema_version":"1.0","event_id":"sha256:5ee55387244f814a82abd806c4c5b11fff547866ad202b580d00ce3a67bc3033"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IWL5DAQK3OUFMQA67KXYUXAV2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Botao Hao, Rahul Jain, Tor Lattimore, Zheng Wen","submitted_at":"2023-02-07T08:49:12Z","abstract_excerpt":"We investigate the extent to which offline demonstration data can improve online learning. It is natural to expect some improvement, but the question is how, and by how much? We show that the degree of improvement must depend on the quality of the demonstration data. To generate portable insights, we focus on Thompson sampling (TS) applied to a multi-armed bandit as a prototypical online learning algorithm and model. The demonstration data is generated by an expert with a given competence level, a notion we introduce. We propose an informed TS algorithm that utilizes the demonstration data in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03319","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/2302.03319/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":"2026-07-05T06:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2aWQ5tclrWqyY6QWSCuQRKyI9fXbrYPdsUnw5xB1eLzlpBqw8+93z3WTCMgacnT5LAo4XW7vaCX/VC06qYwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:53:45.295915Z"},"content_sha256":"feabbe96f5a326fe1a892ce2fb6304cfd52edf698120ba299af67f1970113a1e","schema_version":"1.0","event_id":"sha256:feabbe96f5a326fe1a892ce2fb6304cfd52edf698120ba299af67f1970113a1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/bundle.json","state_url":"https://pith.science/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/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":"2026-08-12T17:53:45Z","links":{"resolver":"https://pith.science/pith/IWL5DAQK3OUFMQA67KXYUXAV2L","bundle":"https://pith.science/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/bundle.json","state":"https://pith.science/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWL5DAQK3OUFMQA67KXYUXAV2L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IWL5DAQK3OUFMQA67KXYUXAV2L","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":"786d8923146a0dc4ea2b8fc6d98d8f84728119c320f580ea6c067848c63de589","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T08:49:12Z","title_canon_sha256":"039c1d96922a5ba59e5347a4372062b27d45d397ca8f0b7d9962fcd3189f6001"},"schema_version":"1.0","source":{"id":"2302.03319","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03319","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03319v4","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03319","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"IWL5DAQK3OUF","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"IWL5DAQK3OUFMQA6","created_at":"2026-07-05T06:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"IWL5DAQK","created_at":"2026-07-05T06:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:feabbe96f5a326fe1a892ce2fb6304cfd52edf698120ba299af67f1970113a1e","target":"graph","created_at":"2026-07-05T06:11:03Z","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/2302.03319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the extent to which offline demonstration data can improve online learning. It is natural to expect some improvement, but the question is how, and by how much? We show that the degree of improvement must depend on the quality of the demonstration data. To generate portable insights, we focus on Thompson sampling (TS) applied to a multi-armed bandit as a prototypical online learning algorithm and model. The demonstration data is generated by an expert with a given competence level, a notion we introduce. We propose an informed TS algorithm that utilizes the demonstration data in ","authors_text":"Benjamin Van Roy, Botao Hao, Rahul Jain, Tor Lattimore, Zheng Wen","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T08:49:12Z","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03319","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":"sha256:5ee55387244f814a82abd806c4c5b11fff547866ad202b580d00ce3a67bc3033","target":"record","created_at":"2026-07-05T06:11:03Z","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":"786d8923146a0dc4ea2b8fc6d98d8f84728119c320f580ea6c067848c63de589","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T08:49:12Z","title_canon_sha256":"039c1d96922a5ba59e5347a4372062b27d45d397ca8f0b7d9962fcd3189f6001"},"schema_version":"1.0","source":{"id":"2302.03319","kind":"arxiv","version":4}},"canonical_sha256":"4597d1820adba856401efaaf8a5c15d2ed91d894fa64d1acae07c80fd9bd4662","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4597d1820adba856401efaaf8a5c15d2ed91d894fa64d1acae07c80fd9bd4662","first_computed_at":"2026-07-05T06:11:03.198865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:03.198865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WxXDtmpl8x7GztwLgcoWzn8cZuCI/8yrgapW99bCjym3ZciN1T9AbYcCRmtqRB/qTVcDSLLJcf/nDIUdKvFHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:03.199260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03319","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ee55387244f814a82abd806c4c5b11fff547866ad202b580d00ce3a67bc3033","sha256:feabbe96f5a326fe1a892ce2fb6304cfd52edf698120ba299af67f1970113a1e"],"state_sha256":"9f380cc33603ee5a7dda98853cb041872dce591b30014c82284a62366ef5a61e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WNltFLFfUgaDJnmC8q92M9JnTPqV0otazHLgQBDdICYw4FEEBUDqRCOn5le/NLAmCdiIYhKUr6TGe+feNrpbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T17:53:45.300989Z","bundle_sha256":"6c2b1cb88033ae1a178c68afa3e0bf279ab29faa860874fbb04fc2458ff80f4b"}}