{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UNMMCMX5BMOOT4VIXGHMIZRDPO","short_pith_number":"pith:UNMMCMX5","schema_version":"1.0","canonical_sha256":"a358c132fd0b1ce9f2a8b98ec466237b844e69a129af65623d67efc0f9ce985f","source":{"kind":"arxiv","id":"1909.12473","version":2},"attestation_state":"computed","paper":{"title":"Noisy Batch Active Learning with Deterministic Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anit Kumar Sahu, Gaurav Gupta, Wan-Yi Lin","submitted_at":"2019-09-27T02:33:30Z","abstract_excerpt":"We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More importantly, we incorporate model uncertainty into the sampling probability to compensate for poor estimation of the importance scores when the training data is too small to build a meaningful model. Experiments on benchmark image classification datasets (MNIST, SVHN, CIFAR10, and EMNIST) show improvement over existing active learning strategies. We introduce "},"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":"1909.12473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-27T02:33:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37d65edc8786ffedd89bf0b19d4acbfea4ed0900912538de0f364f653913d9df","abstract_canon_sha256":"4d061edd9f3cd2383b0dc154af9d1db0ee1094d6a462b64b8be241799d479327"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:29.068373Z","signature_b64":"mnCL367lsJxdSTRFrjHdXZPAV/GmbPXvWi6uePnUfbwU2iVYHfM2s7LwrcbFiO7FyYiPQ4AfeX3gV+zBAeBIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a358c132fd0b1ce9f2a8b98ec466237b844e69a129af65623d67efc0f9ce985f","last_reissued_at":"2026-07-05T01:47:29.067992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:29.067992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noisy Batch Active Learning with Deterministic Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anit Kumar Sahu, Gaurav Gupta, Wan-Yi Lin","submitted_at":"2019-09-27T02:33:30Z","abstract_excerpt":"We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More importantly, we incorporate model uncertainty into the sampling probability to compensate for poor estimation of the importance scores when the training data is too small to build a meaningful model. Experiments on benchmark image classification datasets (MNIST, SVHN, CIFAR10, and EMNIST) show improvement over existing active learning strategies. We introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12473","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/1909.12473/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":"1909.12473","created_at":"2026-07-05T01:47:29.068052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12473v2","created_at":"2026-07-05T01:47:29.068052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12473","created_at":"2026-07-05T01:47:29.068052+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNMMCMX5BMOO","created_at":"2026-07-05T01:47:29.068052+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNMMCMX5BMOOT4VI","created_at":"2026-07-05T01:47:29.068052+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNMMCMX5","created_at":"2026-07-05T01:47:29.068052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08718","citing_title":"Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO","json":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO.json","graph_json":"https://pith.science/api/pith-number/UNMMCMX5BMOOT4VIXGHMIZRDPO/graph.json","events_json":"https://pith.science/api/pith-number/UNMMCMX5BMOOT4VIXGHMIZRDPO/events.json","paper":"https://pith.science/paper/UNMMCMX5"},"agent_actions":{"view_html":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO","download_json":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO.json","view_paper":"https://pith.science/paper/UNMMCMX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12473&json=true","fetch_graph":"https://pith.science/api/pith-number/UNMMCMX5BMOOT4VIXGHMIZRDPO/graph.json","fetch_events":"https://pith.science/api/pith-number/UNMMCMX5BMOOT4VIXGHMIZRDPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO/action/storage_attestation","attest_author":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO/action/author_attestation","sign_citation":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO/action/citation_signature","submit_replication":"https://pith.science/pith/UNMMCMX5BMOOT4VIXGHMIZRDPO/action/replication_record"}},"created_at":"2026-07-05T01:47:29.068052+00:00","updated_at":"2026-07-05T01:47:29.068052+00:00"}