{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5UCP7E3IBGGHHSXPWPJ46ZHSTH","short_pith_number":"pith:5UCP7E3I","schema_version":"1.0","canonical_sha256":"ed04ff9368098c73caefb3d3cf64f299f97b4e8e9c0d2faa8cf938235fdac0a0","source":{"kind":"arxiv","id":"2206.02326","version":2},"attestation_state":"computed","paper":{"title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Tengyu Ma","submitted_at":"2022-06-06T02:56:10Z","abstract_excerpt":"Past research on interactive decision making problems (bandits, reinforcement learning, etc.) mostly focuses on the minimax regret that measures the algorithm's performance on the hardest instance. However, an ideal algorithm should adapt to the complexity of a particular problem instance and incur smaller regrets on easy instances than worst-case instances. In this paper, we design the first asymptotic instance-optimal algorithm for general interactive decision making problems with finite number of decisions under mild conditions. On every instance $f$, our algorithm outperforms all consisten"},"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":"2206.02326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T02:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"8e827e34e6d50ca6bed094f8a901f1a0662f9598ca1529db4a926bc51757534b","abstract_canon_sha256":"50213ab0de7d08be1969cc6dd50a8276a8dbc9d8572159cad5c23797930aa809"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:34.501333Z","signature_b64":"Y7LKqGfkl6jHkX9k+YT4bvpkkFQt6x9rfoU+JIlJTomwkLLCWswTnjeAyAg2ZEbTnUIc61yOfTjB8OUE9u5AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed04ff9368098c73caefb3d3cf64f299f97b4e8e9c0d2faa8cf938235fdac0a0","last_reissued_at":"2026-07-05T06:19:34.500859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:34.500859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Tengyu Ma","submitted_at":"2022-06-06T02:56:10Z","abstract_excerpt":"Past research on interactive decision making problems (bandits, reinforcement learning, etc.) mostly focuses on the minimax regret that measures the algorithm's performance on the hardest instance. However, an ideal algorithm should adapt to the complexity of a particular problem instance and incur smaller regrets on easy instances than worst-case instances. In this paper, we design the first asymptotic instance-optimal algorithm for general interactive decision making problems with finite number of decisions under mild conditions. On every instance $f$, our algorithm outperforms all consisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02326","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/2206.02326/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":"2206.02326","created_at":"2026-07-05T06:19:34.500919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02326v2","created_at":"2026-07-05T06:19:34.500919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02326","created_at":"2026-07-05T06:19:34.500919+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UCP7E3IBGGH","created_at":"2026-07-05T06:19:34.500919+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UCP7E3IBGGHHSXP","created_at":"2026-07-05T06:19:34.500919+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UCP7E3I","created_at":"2026-07-05T06:19:34.500919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH","json":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH.json","graph_json":"https://pith.science/api/pith-number/5UCP7E3IBGGHHSXPWPJ46ZHSTH/graph.json","events_json":"https://pith.science/api/pith-number/5UCP7E3IBGGHHSXPWPJ46ZHSTH/events.json","paper":"https://pith.science/paper/5UCP7E3I"},"agent_actions":{"view_html":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH","download_json":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH.json","view_paper":"https://pith.science/paper/5UCP7E3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02326&json=true","fetch_graph":"https://pith.science/api/pith-number/5UCP7E3IBGGHHSXPWPJ46ZHSTH/graph.json","fetch_events":"https://pith.science/api/pith-number/5UCP7E3IBGGHHSXPWPJ46ZHSTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH/action/storage_attestation","attest_author":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH/action/author_attestation","sign_citation":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH/action/citation_signature","submit_replication":"https://pith.science/pith/5UCP7E3IBGGHHSXPWPJ46ZHSTH/action/replication_record"}},"created_at":"2026-07-05T06:19:34.500919+00:00","updated_at":"2026-07-05T06:19:34.500919+00:00"}