{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3XRI2OMEDS7U77W4TNUOXCOVDQ","short_pith_number":"pith:3XRI2OME","schema_version":"1.0","canonical_sha256":"dde28d39841cbf4ffedc9b68eb89d51c07f4fdc093c25f50f6626a9303448d22","source":{"kind":"arxiv","id":"1703.02910","version":1},"attestation_state":"computed","paper":{"title":"Deep Bayesian Active Learning with Image Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Riashat Islam, Yarin Gal, Zoubin Ghahramani","submitted_at":"2017-03-08T16:53:57Z","abstract_excerpt":"Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine rec"},"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":"1703.02910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-08T16:53:57Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"66d32adad7da2b66aad12ab8aef2d956a0e7c571e1798f30d086cb6c9b8f45fd","abstract_canon_sha256":"10ea8e7066207eba4f744d05015d69056cd6a871b79b5ff3b6d9e2fcc3f9beb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.333494Z","signature_b64":"NFUfjHCPUTSdYl+bIhOW7Om+xVBXOHiKlCIoY8+EVzEex8TRANAB82oxRyz8x8IGQ2EpO8BtqLiVdkHR7nJlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dde28d39841cbf4ffedc9b68eb89d51c07f4fdc093c25f50f6626a9303448d22","last_reissued_at":"2026-05-18T00:49:05.333062Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.333062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Bayesian Active Learning with Image Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Riashat Islam, Yarin Gal, Zoubin Ghahramani","submitted_at":"2017-03-08T16:53:57Z","abstract_excerpt":"Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02910","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":"1703.02910","created_at":"2026-05-18T00:49:05.333122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02910v1","created_at":"2026-05-18T00:49:05.333122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02910","created_at":"2026-05-18T00:49:05.333122+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XRI2OMEDS7U","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XRI2OMEDS7U77W4","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XRI2OME","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10718","citing_title":"Active Learning Solution on Distributed Edge Computing","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06347","citing_title":"Discriminative Active Learning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08977","citing_title":"Testing the Assumptions of Active Learning for Translation Tasks with Few Samples","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ","json":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ.json","graph_json":"https://pith.science/api/pith-number/3XRI2OMEDS7U77W4TNUOXCOVDQ/graph.json","events_json":"https://pith.science/api/pith-number/3XRI2OMEDS7U77W4TNUOXCOVDQ/events.json","paper":"https://pith.science/paper/3XRI2OME"},"agent_actions":{"view_html":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ","download_json":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ.json","view_paper":"https://pith.science/paper/3XRI2OME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02910&json=true","fetch_graph":"https://pith.science/api/pith-number/3XRI2OMEDS7U77W4TNUOXCOVDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3XRI2OMEDS7U77W4TNUOXCOVDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ/action/storage_attestation","attest_author":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ/action/author_attestation","sign_citation":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ/action/citation_signature","submit_replication":"https://pith.science/pith/3XRI2OMEDS7U77W4TNUOXCOVDQ/action/replication_record"}},"created_at":"2026-05-18T00:49:05.333122+00:00","updated_at":"2026-05-18T00:49:05.333122+00:00"}