{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QHLTGS3KFXUPQCWSA6F65NYKQD","short_pith_number":"pith:QHLTGS3K","schema_version":"1.0","canonical_sha256":"81d7334b6a2de8f80ad2078beeb70a80cdc63533ecb2dbb20c362acdb01e07a2","source":{"kind":"arxiv","id":"1603.09050","version":1},"attestation_state":"computed","paper":{"title":"Robustness of Bayesian Pool-based Active Learning Against Prior Misspecification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nan Ye, Nguyen Viet Cuong, Wee Sun Lee","submitted_at":"2016-03-30T06:21:42Z","abstract_excerpt":"We study the robustness of active learning (AL) algorithms against prior misspecification: whether an algorithm achieves similar performance using a perturbed prior as compared to using the true prior. In both the average and worst cases of the maximum coverage setting, we prove that all $\\alpha$-approximate algorithms are robust (i.e., near $\\alpha$-approximate) if the utility is Lipschitz continuous in the prior. We further show that robustness may not be achieved if the utility is non-Lipschitz. This suggests we should use a Lipschitz utility for AL if robustness is required. For the minimu"},"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":"1603.09050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-30T06:21:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"56cbcd5773ecd1135f48e4f3f5fe04949871ee48960713c3746bd608f4e52ed7","abstract_canon_sha256":"080817ee47cf18421ca843e0aa9e3da8ff5755f01f107d45073d6d19182a69b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:03.876189Z","signature_b64":"Nu7USpr7PYbWI3hZ4Xv7XjoCLCHnOF+vnppzbO+CPXy3k0NeKMwTKVdCKSWd4eh32tio1LgekARb6ek0S+L2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81d7334b6a2de8f80ad2078beeb70a80cdc63533ecb2dbb20c362acdb01e07a2","last_reissued_at":"2026-05-18T01:18:03.875521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:03.875521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of Bayesian Pool-based Active Learning Against Prior Misspecification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nan Ye, Nguyen Viet Cuong, Wee Sun Lee","submitted_at":"2016-03-30T06:21:42Z","abstract_excerpt":"We study the robustness of active learning (AL) algorithms against prior misspecification: whether an algorithm achieves similar performance using a perturbed prior as compared to using the true prior. In both the average and worst cases of the maximum coverage setting, we prove that all $\\alpha$-approximate algorithms are robust (i.e., near $\\alpha$-approximate) if the utility is Lipschitz continuous in the prior. We further show that robustness may not be achieved if the utility is non-Lipschitz. This suggests we should use a Lipschitz utility for AL if robustness is required. For the minimu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09050","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1603.09050","created_at":"2026-05-18T01:18:03.875633+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.09050v1","created_at":"2026-05-18T01:18:03.875633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09050","created_at":"2026-05-18T01:18:03.875633+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHLTGS3KFXUP","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHLTGS3KFXUPQCWS","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHLTGS3K","created_at":"2026-05-18T12:30:39.010887+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/QHLTGS3KFXUPQCWSA6F65NYKQD","json":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD.json","graph_json":"https://pith.science/api/pith-number/QHLTGS3KFXUPQCWSA6F65NYKQD/graph.json","events_json":"https://pith.science/api/pith-number/QHLTGS3KFXUPQCWSA6F65NYKQD/events.json","paper":"https://pith.science/paper/QHLTGS3K"},"agent_actions":{"view_html":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD","download_json":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD.json","view_paper":"https://pith.science/paper/QHLTGS3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.09050&json=true","fetch_graph":"https://pith.science/api/pith-number/QHLTGS3KFXUPQCWSA6F65NYKQD/graph.json","fetch_events":"https://pith.science/api/pith-number/QHLTGS3KFXUPQCWSA6F65NYKQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD/action/storage_attestation","attest_author":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD/action/author_attestation","sign_citation":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD/action/citation_signature","submit_replication":"https://pith.science/pith/QHLTGS3KFXUPQCWSA6F65NYKQD/action/replication_record"}},"created_at":"2026-05-18T01:18:03.875633+00:00","updated_at":"2026-05-18T01:18:03.875633+00:00"}