{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UODT2DJGZGC4FJT5QBGJFNDNI7","short_pith_number":"pith:UODT2DJG","schema_version":"1.0","canonical_sha256":"a3873d0d26c985c2a67d804c92b46d47fc9bbde7d0d84375801ee11a7647d51a","source":{"kind":"arxiv","id":"2104.02822","version":3},"attestation_state":"computed","paper":{"title":"Low-Regret Active learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Lucas Liebenwein","submitted_at":"2021-04-06T22:53:45Z","abstract_excerpt":"We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i.e., active learning). By formulating the active learning problem as the prediction with sleeping experts problem, we provide a regret minimization framework for identifying relevant data with respect to any given definition of informativeness. Motivated by the successes of ensembles in active learning, we define regret with respect to an omnipotent algorithm that has access to an infinity large ensemble. At the core of our work is an efficient algorithm for sleeping experts t"},"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":"2104.02822","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T22:53:45Z","cross_cats_sorted":[],"title_canon_sha256":"1894fd72f35b75c6ff41a127a6d1346c38d1f73c21c5bfd14130d499dad267e9","abstract_canon_sha256":"663f959fd786637eb71ca8e98b320d6303c6dfa63955a3a3f7c0d04374245c9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:21.872614Z","signature_b64":"VimlwWqd8G1i8bMjQj3bx6zp6oti/p6mD3FKXUHrlZOzWi82DEC8YLWxyRxgrivm5Ka9nwVQ8MRucFiFWvl7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3873d0d26c985c2a67d804c92b46d47fc9bbde7d0d84375801ee11a7647d51a","last_reissued_at":"2026-07-05T03:59:21.872130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:21.872130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Regret Active learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Lucas Liebenwein","submitted_at":"2021-04-06T22:53:45Z","abstract_excerpt":"We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i.e., active learning). By formulating the active learning problem as the prediction with sleeping experts problem, we provide a regret minimization framework for identifying relevant data with respect to any given definition of informativeness. Motivated by the successes of ensembles in active learning, we define regret with respect to an omnipotent algorithm that has access to an infinity large ensemble. At the core of our work is an efficient algorithm for sleeping experts t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02822","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/2104.02822/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":"2104.02822","created_at":"2026-07-05T03:59:21.872189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02822v3","created_at":"2026-07-05T03:59:21.872189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02822","created_at":"2026-07-05T03:59:21.872189+00:00"},{"alias_kind":"pith_short_12","alias_value":"UODT2DJGZGC4","created_at":"2026-07-05T03:59:21.872189+00:00"},{"alias_kind":"pith_short_16","alias_value":"UODT2DJGZGC4FJT5","created_at":"2026-07-05T03:59:21.872189+00:00"},{"alias_kind":"pith_short_8","alias_value":"UODT2DJG","created_at":"2026-07-05T03:59:21.872189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10654","citing_title":"Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7","json":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7.json","graph_json":"https://pith.science/api/pith-number/UODT2DJGZGC4FJT5QBGJFNDNI7/graph.json","events_json":"https://pith.science/api/pith-number/UODT2DJGZGC4FJT5QBGJFNDNI7/events.json","paper":"https://pith.science/paper/UODT2DJG"},"agent_actions":{"view_html":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7","download_json":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7.json","view_paper":"https://pith.science/paper/UODT2DJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02822&json=true","fetch_graph":"https://pith.science/api/pith-number/UODT2DJGZGC4FJT5QBGJFNDNI7/graph.json","fetch_events":"https://pith.science/api/pith-number/UODT2DJGZGC4FJT5QBGJFNDNI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7/action/storage_attestation","attest_author":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7/action/author_attestation","sign_citation":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7/action/citation_signature","submit_replication":"https://pith.science/pith/UODT2DJGZGC4FJT5QBGJFNDNI7/action/replication_record"}},"created_at":"2026-07-05T03:59:21.872189+00:00","updated_at":"2026-07-05T03:59:21.872189+00:00"}