{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GW3KVPPJECFJ2XCGN7WN635MUR","short_pith_number":"pith:GW3KVPPJ","schema_version":"1.0","canonical_sha256":"35b6aabde9208a9d5c466fecdf6faca4577e1e75c30e384f315fe8d7a3739636","source":{"kind":"arxiv","id":"2303.07154","version":3},"attestation_state":"computed","paper":{"title":"Differential Good Arm Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shou-De Lin, Tzu-Hsien Tsai, Yun-Da Tsai","submitted_at":"2023-03-13T14:28:21Z","abstract_excerpt":"This paper targets a variant of the stochastic multi-armed bandit problem called good arm identification (GAI). GAI is a pure-exploration bandit problem with the goal to output as many good arms using as few samples as possible, where a good arm is defined as an arm whose expected reward is greater than a given threshold. In this work, we propose DGAI - a differentiable good arm identification algorithm to improve the sample complexity of the state-of-the-art HDoC algorithm in a data-driven fashion. We also showed that the DGAI can further boost the performance of a general multi-arm bandit (M"},"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":"2303.07154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T14:28:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2a95d25f290489dc42df5f4117fcb4ee09ec472944b6798e15a1fbf9eeb2139","abstract_canon_sha256":"a3264f3df8cefa3531c3e93b8da135e071a9235764130b9443ac738a26298f04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:45.680329Z","signature_b64":"FXkWide+tKqR77ukFa9o5ecoXf4RJeuadf6twPO1k0l5xOUDwH/X0kPFKAnFuRx3rH8HSRJPgH05lFT+xfN6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b6aabde9208a9d5c466fecdf6faca4577e1e75c30e384f315fe8d7a3739636","last_reissued_at":"2026-07-05T07:45:45.679836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:45.679836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Good Arm Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shou-De Lin, Tzu-Hsien Tsai, Yun-Da Tsai","submitted_at":"2023-03-13T14:28:21Z","abstract_excerpt":"This paper targets a variant of the stochastic multi-armed bandit problem called good arm identification (GAI). GAI is a pure-exploration bandit problem with the goal to output as many good arms using as few samples as possible, where a good arm is defined as an arm whose expected reward is greater than a given threshold. In this work, we propose DGAI - a differentiable good arm identification algorithm to improve the sample complexity of the state-of-the-art HDoC algorithm in a data-driven fashion. We also showed that the DGAI can further boost the performance of a general multi-arm bandit (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07154","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/2303.07154/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":"2303.07154","created_at":"2026-07-05T07:45:45.679892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07154v3","created_at":"2026-07-05T07:45:45.679892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07154","created_at":"2026-07-05T07:45:45.679892+00:00"},{"alias_kind":"pith_short_12","alias_value":"GW3KVPPJECFJ","created_at":"2026-07-05T07:45:45.679892+00:00"},{"alias_kind":"pith_short_16","alias_value":"GW3KVPPJECFJ2XCG","created_at":"2026-07-05T07:45:45.679892+00:00"},{"alias_kind":"pith_short_8","alias_value":"GW3KVPPJ","created_at":"2026-07-05T07:45:45.679892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03062","citing_title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR","json":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR.json","graph_json":"https://pith.science/api/pith-number/GW3KVPPJECFJ2XCGN7WN635MUR/graph.json","events_json":"https://pith.science/api/pith-number/GW3KVPPJECFJ2XCGN7WN635MUR/events.json","paper":"https://pith.science/paper/GW3KVPPJ"},"agent_actions":{"view_html":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR","download_json":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR.json","view_paper":"https://pith.science/paper/GW3KVPPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07154&json=true","fetch_graph":"https://pith.science/api/pith-number/GW3KVPPJECFJ2XCGN7WN635MUR/graph.json","fetch_events":"https://pith.science/api/pith-number/GW3KVPPJECFJ2XCGN7WN635MUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR/action/storage_attestation","attest_author":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR/action/author_attestation","sign_citation":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR/action/citation_signature","submit_replication":"https://pith.science/pith/GW3KVPPJECFJ2XCGN7WN635MUR/action/replication_record"}},"created_at":"2026-07-05T07:45:45.679892+00:00","updated_at":"2026-07-05T07:45:45.679892+00:00"}