{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZM52GTA7DMJN7KIEACLIM2Q573","short_pith_number":"pith:ZM52GTA7","schema_version":"1.0","canonical_sha256":"cb3ba34c1f1b12dfa9040096866a1dfec2bc7a4107aae6ef9c4c84f3862d36b7","source":{"kind":"arxiv","id":"2107.09912","version":2},"attestation_state":"computed","paper":{"title":"Design of Experiments for Stochastic Contextual Linear Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Zanette, Emma Brunskill, Jonathan Lee, Kefan Dong","submitted_at":"2021-07-21T07:25:37Z","abstract_excerpt":"In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy these algorithms, especially when the dataset is collected in a distributed fashion or when a human in the loop is needed to implement a different policy. Exploring with a single non-reactive policy is beneficial in such cases. Assuming some batch contexts are available, we design a single stochastic policy to collect a good dataset from which a near-optimal po"},"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":"2107.09912","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T07:25:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e1e9b8a08a868efe1226dcfdd25abbc78381dc0e1678bb4907f48fd257aff94","abstract_canon_sha256":"0cae7286a4c08e317197105655c10588211d921e524cfd80a8d88805a900fd66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:10.550348Z","signature_b64":"N6Vlp6mbvPeJzfOmenw19dXie1zW69va/KjD3gr3i407EEt6haUzRuV+iZxBCvJ4qdbag4fWrTykQkg3iUx/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb3ba34c1f1b12dfa9040096866a1dfec2bc7a4107aae6ef9c4c84f3862d36b7","last_reissued_at":"2026-07-05T03:00:10.549833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:10.549833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design of Experiments for Stochastic Contextual Linear Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Zanette, Emma Brunskill, Jonathan Lee, Kefan Dong","submitted_at":"2021-07-21T07:25:37Z","abstract_excerpt":"In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy these algorithms, especially when the dataset is collected in a distributed fashion or when a human in the loop is needed to implement a different policy. Exploring with a single non-reactive policy is beneficial in such cases. Assuming some batch contexts are available, we design a single stochastic policy to collect a good dataset from which a near-optimal po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09912","kind":"arxiv","version":2},"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/2107.09912/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":"2107.09912","created_at":"2026-07-05T03:00:10.549907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.09912v2","created_at":"2026-07-05T03:00:10.549907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09912","created_at":"2026-07-05T03:00:10.549907+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZM52GTA7DMJN","created_at":"2026-07-05T03:00:10.549907+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZM52GTA7DMJN7KIE","created_at":"2026-07-05T03:00:10.549907+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZM52GTA7","created_at":"2026-07-05T03:00:10.549907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17515","citing_title":"Anytime-valid Optimal Policy Identification","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15108","citing_title":"Logging Policy Design for Off-Policy Evaluation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15108","citing_title":"Logging Policy Design for Off-Policy Evaluation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573","json":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573.json","graph_json":"https://pith.science/api/pith-number/ZM52GTA7DMJN7KIEACLIM2Q573/graph.json","events_json":"https://pith.science/api/pith-number/ZM52GTA7DMJN7KIEACLIM2Q573/events.json","paper":"https://pith.science/paper/ZM52GTA7"},"agent_actions":{"view_html":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573","download_json":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573.json","view_paper":"https://pith.science/paper/ZM52GTA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.09912&json=true","fetch_graph":"https://pith.science/api/pith-number/ZM52GTA7DMJN7KIEACLIM2Q573/graph.json","fetch_events":"https://pith.science/api/pith-number/ZM52GTA7DMJN7KIEACLIM2Q573/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573/action/storage_attestation","attest_author":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573/action/author_attestation","sign_citation":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573/action/citation_signature","submit_replication":"https://pith.science/pith/ZM52GTA7DMJN7KIEACLIM2Q573/action/replication_record"}},"created_at":"2026-07-05T03:00:10.549907+00:00","updated_at":"2026-07-05T03:00:10.549907+00:00"}