{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TYE6MLPD6JZKYXVFP6QYH2A4JB","short_pith_number":"pith:TYE6MLPD","schema_version":"1.0","canonical_sha256":"9e09e62de3f272ac5ea57fa183e81c485f576d6ad7749c49d230227f950db00f","source":{"kind":"arxiv","id":"2111.03837","version":3},"attestation_state":"computed","paper":{"title":"Focusing on Potential Named Entities During Active Label Acquisition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Osman Berk Sapci, Oznur Tastan, Reyyan Yeniterzi","submitted_at":"2021-11-06T09:04:16Z","abstract_excerpt":"Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive performances in NER, many domain-specific NER applications still call for a substantial amount of labeled data. Active learning (AL), a general framework for the label acquisition problem, has been used for NER tasks to minimize the annotation cost without sacrificing model performance. However, the heavily imbalanced class distribution of tokens introduces"},"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":"2111.03837","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-06T09:04:16Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7dfef4ef27020171b826f6f149d4e0145ff15a2a0d55f4d5a91f562f6dbc29e3","abstract_canon_sha256":"86a862607d9c45b5a18035c7711adf38cf66a4066e60a280b1247febbb6da2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:33.847113Z","signature_b64":"OUhyvggLPTLR9IXjHpxzVefnP+MAY1OWxC7l2mk6gu1gDQrcxjtxEOpxNSAFbWk8KSkxiMgF21HuXfAWYEPDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e09e62de3f272ac5ea57fa183e81c485f576d6ad7749c49d230227f950db00f","last_reissued_at":"2026-07-05T06:20:33.846676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:33.846676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focusing on Potential Named Entities During Active Label Acquisition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Osman Berk Sapci, Oznur Tastan, Reyyan Yeniterzi","submitted_at":"2021-11-06T09:04:16Z","abstract_excerpt":"Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive performances in NER, many domain-specific NER applications still call for a substantial amount of labeled data. Active learning (AL), a general framework for the label acquisition problem, has been used for NER tasks to minimize the annotation cost without sacrificing model performance. However, the heavily imbalanced class distribution of tokens introduces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03837","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/2111.03837/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":"2111.03837","created_at":"2026-07-05T06:20:33.846737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03837v3","created_at":"2026-07-05T06:20:33.846737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03837","created_at":"2026-07-05T06:20:33.846737+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYE6MLPD6JZK","created_at":"2026-07-05T06:20:33.846737+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYE6MLPD6JZKYXVF","created_at":"2026-07-05T06:20:33.846737+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYE6MLPD","created_at":"2026-07-05T06:20:33.846737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB","json":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB.json","graph_json":"https://pith.science/api/pith-number/TYE6MLPD6JZKYXVFP6QYH2A4JB/graph.json","events_json":"https://pith.science/api/pith-number/TYE6MLPD6JZKYXVFP6QYH2A4JB/events.json","paper":"https://pith.science/paper/TYE6MLPD"},"agent_actions":{"view_html":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB","download_json":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB.json","view_paper":"https://pith.science/paper/TYE6MLPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03837&json=true","fetch_graph":"https://pith.science/api/pith-number/TYE6MLPD6JZKYXVFP6QYH2A4JB/graph.json","fetch_events":"https://pith.science/api/pith-number/TYE6MLPD6JZKYXVFP6QYH2A4JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB/action/storage_attestation","attest_author":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB/action/author_attestation","sign_citation":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB/action/citation_signature","submit_replication":"https://pith.science/pith/TYE6MLPD6JZKYXVFP6QYH2A4JB/action/replication_record"}},"created_at":"2026-07-05T06:20:33.846737+00:00","updated_at":"2026-07-05T06:20:33.846737+00:00"}