{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UBMYD5TLCAM7JRMWVC6IO6CTNL","short_pith_number":"pith:UBMYD5TL","schema_version":"1.0","canonical_sha256":"a05981f66b1019f4c596a8bc8778536ac3722872b1b6ccb7b59961c1d4231437","source":{"kind":"arxiv","id":"2210.00423","version":3},"attestation_state":"computed","paper":{"title":"Improved Algorithms for Neural Active Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arindam Banerjee, Hanghang Tong, Jingrui He, Yikun Ban, Yuheng Zhang","submitted_at":"2022-10-02T05:03:38Z","abstract_excerpt":"We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. In particular, we introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for $k$-class classification problems with the performance guarantee, utilizes the full feedback, and updates paramet"},"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":"2210.00423","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T05:03:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b62b7157bb01c670f61fb29e89edc787dcd803f4cba8e75a2b07565021bf5259","abstract_canon_sha256":"e214c6710a96230f18c5222fbb77dc0c8fece4831d92890d28873cb1d1f06287"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:18.774386Z","signature_b64":"F241Oil3IWivI22Pqg/KRdCR+wgbwXeRsVRuueFmzD0s+hr77eyzVbhCr+L0l9FNoRH7dmumZNyzD7GP/b9sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a05981f66b1019f4c596a8bc8778536ac3722872b1b6ccb7b59961c1d4231437","last_reissued_at":"2026-07-05T05:33:18.773893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:18.773893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Algorithms for Neural Active Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arindam Banerjee, Hanghang Tong, Jingrui He, Yikun Ban, Yuheng Zhang","submitted_at":"2022-10-02T05:03:38Z","abstract_excerpt":"We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. In particular, we introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for $k$-class classification problems with the performance guarantee, utilizes the full feedback, and updates paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00423","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/2210.00423/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":"2210.00423","created_at":"2026-07-05T05:33:18.773953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00423v3","created_at":"2026-07-05T05:33:18.773953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00423","created_at":"2026-07-05T05:33:18.773953+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBMYD5TLCAM7","created_at":"2026-07-05T05:33:18.773953+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBMYD5TLCAM7JRMW","created_at":"2026-07-05T05:33:18.773953+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBMYD5TL","created_at":"2026-07-05T05:33:18.773953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07101","citing_title":"Constrained Online Decision-Making: A Unified Framework","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL","json":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL.json","graph_json":"https://pith.science/api/pith-number/UBMYD5TLCAM7JRMWVC6IO6CTNL/graph.json","events_json":"https://pith.science/api/pith-number/UBMYD5TLCAM7JRMWVC6IO6CTNL/events.json","paper":"https://pith.science/paper/UBMYD5TL"},"agent_actions":{"view_html":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL","download_json":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL.json","view_paper":"https://pith.science/paper/UBMYD5TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00423&json=true","fetch_graph":"https://pith.science/api/pith-number/UBMYD5TLCAM7JRMWVC6IO6CTNL/graph.json","fetch_events":"https://pith.science/api/pith-number/UBMYD5TLCAM7JRMWVC6IO6CTNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL/action/storage_attestation","attest_author":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL/action/author_attestation","sign_citation":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL/action/citation_signature","submit_replication":"https://pith.science/pith/UBMYD5TLCAM7JRMWVC6IO6CTNL/action/replication_record"}},"created_at":"2026-07-05T05:33:18.773953+00:00","updated_at":"2026-07-05T05:33:18.773953+00:00"}