{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:336IZTKHSHMI6RY47NFAPILA5W","short_pith_number":"pith:336IZTKH","schema_version":"1.0","canonical_sha256":"defc8ccd4791d88f471cfb4a07a160edbce957b9298d8fa3f70466b1428b75e5","source":{"kind":"arxiv","id":"2202.05100","version":3},"attestation_state":"computed","paper":{"title":"Adaptively Exploiting d-Separators with Causal Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Blair Bilodeau, Daniel M. Roy, Linbo Wang","submitted_at":"2022-02-10T15:39:07Z","abstract_excerpt":"Multi-armed bandit problems provide a framework to identify the optimal intervention over a sequence of repeated experiments. Without additional assumptions, minimax optimal performance (measured by cumulative regret) is well-understood. With access to additional observed variables that d-separate the intervention from the outcome (i.e., they are a d-separator), recent \"causal bandit\" algorithms provably incur less regret. However, in practice it is desirable to be agnostic to whether observed variables are a d-separator. Ideally, an algorithm should be adaptive; that is, perform nearly as wel"},"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":"2202.05100","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-02-10T15:39:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fcca405a23cbf56cbcd8458448290dfa9af18de44fce2fa097408f5b5a7c90ad","abstract_canon_sha256":"d43244baecf3edb6f658000c3f33128eae6d7a8f7096c62c626509e5226b19d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:54.247548Z","signature_b64":"Da2oRSTxg3IjS0ScQI6EPzwC6p1A5AKdQmpU5Bvq6eKunxEmyLpXrL9ONvjYKL30MlfwpYMR4vrG3UaEI4prDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"defc8ccd4791d88f471cfb4a07a160edbce957b9298d8fa3f70466b1428b75e5","last_reissued_at":"2026-07-05T05:10:54.247105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:54.247105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptively Exploiting d-Separators with Causal Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Blair Bilodeau, Daniel M. Roy, Linbo Wang","submitted_at":"2022-02-10T15:39:07Z","abstract_excerpt":"Multi-armed bandit problems provide a framework to identify the optimal intervention over a sequence of repeated experiments. Without additional assumptions, minimax optimal performance (measured by cumulative regret) is well-understood. With access to additional observed variables that d-separate the intervention from the outcome (i.e., they are a d-separator), recent \"causal bandit\" algorithms provably incur less regret. However, in practice it is desirable to be agnostic to whether observed variables are a d-separator. Ideally, an algorithm should be adaptive; that is, perform nearly as wel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05100","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.05100/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":"2202.05100","created_at":"2026-07-05T05:10:54.247175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05100v3","created_at":"2026-07-05T05:10:54.247175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05100","created_at":"2026-07-05T05:10:54.247175+00:00"},{"alias_kind":"pith_short_12","alias_value":"336IZTKHSHMI","created_at":"2026-07-05T05:10:54.247175+00:00"},{"alias_kind":"pith_short_16","alias_value":"336IZTKHSHMI6RY4","created_at":"2026-07-05T05:10:54.247175+00:00"},{"alias_kind":"pith_short_8","alias_value":"336IZTKH","created_at":"2026-07-05T05:10:54.247175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04296","citing_title":"Using causal abstractions to accelerate decision-making in complex bandit problems","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W","json":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W.json","graph_json":"https://pith.science/api/pith-number/336IZTKHSHMI6RY47NFAPILA5W/graph.json","events_json":"https://pith.science/api/pith-number/336IZTKHSHMI6RY47NFAPILA5W/events.json","paper":"https://pith.science/paper/336IZTKH"},"agent_actions":{"view_html":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W","download_json":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W.json","view_paper":"https://pith.science/paper/336IZTKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05100&json=true","fetch_graph":"https://pith.science/api/pith-number/336IZTKHSHMI6RY47NFAPILA5W/graph.json","fetch_events":"https://pith.science/api/pith-number/336IZTKHSHMI6RY47NFAPILA5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W/action/storage_attestation","attest_author":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W/action/author_attestation","sign_citation":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W/action/citation_signature","submit_replication":"https://pith.science/pith/336IZTKHSHMI6RY47NFAPILA5W/action/replication_record"}},"created_at":"2026-07-05T05:10:54.247175+00:00","updated_at":"2026-07-05T05:10:54.247175+00:00"}