{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6LVO4G2ZQBHC52RTZXZVC22QUU","short_pith_number":"pith:6LVO4G2Z","schema_version":"1.0","canonical_sha256":"f2eaee1b59804e2eea33cdf3516b50a529aa8c27e06243325e61f277c09b779f","source":{"kind":"arxiv","id":"1808.05697","version":3},"attestation_state":"computed","paper":{"title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Zachary C. Lipton","submitted_at":"2018-08-16T22:46:40Z","abstract_excerpt":"Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, an active learner has no opportunity to compare models and acquisition functions. This pap"},"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":"1808.05697","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-16T22:46:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"23a6276158848f835cabdb33008f7b78ca0a41e440c490acd90cd101bc84131d","abstract_canon_sha256":"2baa15dbd3347d73244d05e0638299ed425170328d8d6ef744035c62ae039a88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:04.542777Z","signature_b64":"fK5HJtnHOIEPsx/hbSjscdqqLngf7du8i2/RRgcEFQIafQnUAY0nVfc72TV7xP7lSAbK6+01r5lIkvJawmu4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2eaee1b59804e2eea33cdf3516b50a529aa8c27e06243325e61f277c09b779f","last_reissued_at":"2026-05-18T00:05:04.542002Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:04.542002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Zachary C. Lipton","submitted_at":"2018-08-16T22:46:40Z","abstract_excerpt":"Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, an active learner has no opportunity to compare models and acquisition functions. This pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05697","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":""},"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":"1808.05697","created_at":"2026-05-18T00:05:04.542119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05697v3","created_at":"2026-05-18T00:05:04.542119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05697","created_at":"2026-05-18T00:05:04.542119+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LVO4G2ZQBHC","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LVO4G2ZQBHC52RT","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LVO4G2Z","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06162","citing_title":"Modeling the Uncertainty in Electronic Health Records: a Bayesian Deep Learning Approach","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU","json":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU.json","graph_json":"https://pith.science/api/pith-number/6LVO4G2ZQBHC52RTZXZVC22QUU/graph.json","events_json":"https://pith.science/api/pith-number/6LVO4G2ZQBHC52RTZXZVC22QUU/events.json","paper":"https://pith.science/paper/6LVO4G2Z"},"agent_actions":{"view_html":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU","download_json":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU.json","view_paper":"https://pith.science/paper/6LVO4G2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05697&json=true","fetch_graph":"https://pith.science/api/pith-number/6LVO4G2ZQBHC52RTZXZVC22QUU/graph.json","fetch_events":"https://pith.science/api/pith-number/6LVO4G2ZQBHC52RTZXZVC22QUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU/action/storage_attestation","attest_author":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU/action/author_attestation","sign_citation":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU/action/citation_signature","submit_replication":"https://pith.science/pith/6LVO4G2ZQBHC52RTZXZVC22QUU/action/replication_record"}},"created_at":"2026-05-18T00:05:04.542119+00:00","updated_at":"2026-05-18T00:05:04.542119+00:00"}