{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BONWTCAUBMQRFVD5PKDP5KXKGL","short_pith_number":"pith:BONWTCAU","schema_version":"1.0","canonical_sha256":"0b9b6988140b2112d47d7a86feaaea32fdf38818218baced35b72ebea7a8cb27","source":{"kind":"arxiv","id":"2210.00025","version":4},"attestation_state":"computed","paper":{"title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christina Lee Yu, Lily Xu, Milind Tambe, Sean R. Sinclair, Siddhartha Banerjee","submitted_at":"2022-09-30T18:03:31Z","abstract_excerpt":"Most real-world deployments of bandit algorithms exist somewhere in between the offline and online set-up, where some historical data is available upfront and additional data is collected dynamically online. How best to incorporate historical data to \"warm start\" bandit algorithms is an open question: naively initializing reward estimates using all historical samples can suffer from spurious data and imbalanced data coverage, leading to data inefficiency (amount of historical data used) - particularly for continuous action spaces. To address these challenges, we propose ArtificialReplay, a met"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.00025","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T18:03:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a895e4c6be6ad7a11e22b4385776c65ac2c23f98f15a7e22905f22663b7dc2da","abstract_canon_sha256":"eb702a4eeab6cdbca5a89f3062d36d86f0a4abb593f20a0bfa2d94c74852b967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:35.746462Z","signature_b64":"MjfvSbmgDSel2YEsYFd8qDZ+d+2aUz/ESR613HzZuNNSzzxeyQsIIS6e4tRg9Pt2sFYwqUKNmuPRYBckrpPoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b9b6988140b2112d47d7a86feaaea32fdf38818218baced35b72ebea7a8cb27","last_reissued_at":"2026-07-05T10:34:35.745453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:35.745453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christina Lee Yu, Lily Xu, Milind Tambe, Sean R. Sinclair, Siddhartha Banerjee","submitted_at":"2022-09-30T18:03:31Z","abstract_excerpt":"Most real-world deployments of bandit algorithms exist somewhere in between the offline and online set-up, where some historical data is available upfront and additional data is collected dynamically online. How best to incorporate historical data to \"warm start\" bandit algorithms is an open question: naively initializing reward estimates using all historical samples can suffer from spurious data and imbalanced data coverage, leading to data inefficiency (amount of historical data used) - particularly for continuous action spaces. To address these challenges, we propose ArtificialReplay, a met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00025","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/2210.00025/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.00025","created_at":"2026-07-05T10:34:35.745577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00025v4","created_at":"2026-07-05T10:34:35.745577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00025","created_at":"2026-07-05T10:34:35.745577+00:00"},{"alias_kind":"pith_short_12","alias_value":"BONWTCAUBMQR","created_at":"2026-07-05T10:34:35.745577+00:00"},{"alias_kind":"pith_short_16","alias_value":"BONWTCAUBMQRFVD5","created_at":"2026-07-05T10:34:35.745577+00:00"},{"alias_kind":"pith_short_8","alias_value":"BONWTCAU","created_at":"2026-07-05T10:34:35.745577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.16658","citing_title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10289","citing_title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10289","citing_title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL","json":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL.json","graph_json":"https://pith.science/api/pith-number/BONWTCAUBMQRFVD5PKDP5KXKGL/graph.json","events_json":"https://pith.science/api/pith-number/BONWTCAUBMQRFVD5PKDP5KXKGL/events.json","paper":"https://pith.science/paper/BONWTCAU"},"agent_actions":{"view_html":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL","download_json":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL.json","view_paper":"https://pith.science/paper/BONWTCAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00025&json=true","fetch_graph":"https://pith.science/api/pith-number/BONWTCAUBMQRFVD5PKDP5KXKGL/graph.json","fetch_events":"https://pith.science/api/pith-number/BONWTCAUBMQRFVD5PKDP5KXKGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL/action/storage_attestation","attest_author":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL/action/author_attestation","sign_citation":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL/action/citation_signature","submit_replication":"https://pith.science/pith/BONWTCAUBMQRFVD5PKDP5KXKGL/action/replication_record"}},"created_at":"2026-07-05T10:34:35.745577+00:00","updated_at":"2026-07-05T10:34:35.745577+00:00"}