{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IFFV3TPLU6F7HLZ3XNWD3W77MA","short_pith_number":"pith:IFFV3TPL","schema_version":"1.0","canonical_sha256":"414b5dcdeba78bf3af3bbb6c3ddbff602a586c48a473a9640ef4abfab1f5c45f","source":{"kind":"arxiv","id":"2112.11914","version":1},"attestation_state":"computed","paper":{"title":"Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DL","authors_text":"Bela Gipp, Felix Hamborg, Franziska Weeber, Karsten Donnay","submitted_at":"2021-12-15T13:14:58Z","abstract_excerpt":"Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents. To highlight our research direction's potential, we evaluate the approach on "},"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":"2112.11914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-15T13:14:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"799e4854372e68bb91f71801978992ae48090e4827df117f6dab24acc2bcd068","abstract_canon_sha256":"e6af68655970a4e0ed71522c97b9969d5f52876a1ee6b3f741ac561b6c8e70bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:13.034347Z","signature_b64":"70srzRdf0sicY3kUuVt91XsWCILDq7XpE3h1LJJpWrqaUO2injSmLMCFRiQTv5szJf96Q/mteecRBlbJkZGkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414b5dcdeba78bf3af3bbb6c3ddbff602a586c48a473a9640ef4abfab1f5c45f","last_reissued_at":"2026-07-05T03:43:13.033940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:13.033940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DL","authors_text":"Bela Gipp, Felix Hamborg, Franziska Weeber, Karsten Donnay","submitted_at":"2021-12-15T13:14:58Z","abstract_excerpt":"Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents. To highlight our research direction's potential, we evaluate the approach on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11914","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.11914/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":"2112.11914","created_at":"2026-07-05T03:43:13.033996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11914v1","created_at":"2026-07-05T03:43:13.033996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11914","created_at":"2026-07-05T03:43:13.033996+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFFV3TPLU6F7","created_at":"2026-07-05T03:43:13.033996+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFFV3TPLU6F7HLZ3","created_at":"2026-07-05T03:43:13.033996+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFFV3TPL","created_at":"2026-07-05T03:43:13.033996+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/IFFV3TPLU6F7HLZ3XNWD3W77MA","json":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA.json","graph_json":"https://pith.science/api/pith-number/IFFV3TPLU6F7HLZ3XNWD3W77MA/graph.json","events_json":"https://pith.science/api/pith-number/IFFV3TPLU6F7HLZ3XNWD3W77MA/events.json","paper":"https://pith.science/paper/IFFV3TPL"},"agent_actions":{"view_html":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA","download_json":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA.json","view_paper":"https://pith.science/paper/IFFV3TPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11914&json=true","fetch_graph":"https://pith.science/api/pith-number/IFFV3TPLU6F7HLZ3XNWD3W77MA/graph.json","fetch_events":"https://pith.science/api/pith-number/IFFV3TPLU6F7HLZ3XNWD3W77MA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA/action/storage_attestation","attest_author":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA/action/author_attestation","sign_citation":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA/action/citation_signature","submit_replication":"https://pith.science/pith/IFFV3TPLU6F7HLZ3XNWD3W77MA/action/replication_record"}},"created_at":"2026-07-05T03:43:13.033996+00:00","updated_at":"2026-07-05T03:43:13.033996+00:00"}