{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M6BGLQW3DHEGKHDMFNELYQG4VA","short_pith_number":"pith:M6BGLQW3","schema_version":"1.0","canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","source":{"kind":"arxiv","id":"2011.00767","version":2},"attestation_state":"computed","paper":{"title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Antonios Anastasopoulos, Graham Neubig, Zaid Sheikh","submitted_at":"2020-11-02T06:24:58Z","abstract_excerpt":"Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL heuristics are generally designed on the principle of selecting uncertain yet representative training instances, where annotating these instances may reduce a large number of errors. However, in an empirical study across six typologically diverse languages (German, Swedish, Galician, North Sami, Persian, and Ukrainian), we found the surprising result that "},"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":"2011.00767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"547a47a6c159d27608c98c0618ba4de1f88b389edd724430d8ac5795c4c8aac0","abstract_canon_sha256":"e3905f2b99efad2c7dff4cf862104284aec520b4e8e09e90245798bbef13d97a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:22.758621Z","signature_b64":"8vVEVNc5YYW6J39Q67lGuKhfAbw+ky5duN+QAxD2oLierFXxSPle1n/3Re7FIcqtjacszx6SH/Zy0mXsuToqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","last_reissued_at":"2026-07-05T01:53:22.758123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:22.758123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Antonios Anastasopoulos, Graham Neubig, Zaid Sheikh","submitted_at":"2020-11-02T06:24:58Z","abstract_excerpt":"Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL heuristics are generally designed on the principle of selecting uncertain yet representative training instances, where annotating these instances may reduce a large number of errors. However, in an empirical study across six typologically diverse languages (German, Swedish, Galician, North Sami, Persian, and Ukrainian), we found the surprising result that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00767","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/2011.00767/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":"2011.00767","created_at":"2026-07-05T01:53:22.758181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.00767v2","created_at":"2026-07-05T01:53:22.758181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00767","created_at":"2026-07-05T01:53:22.758181+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6BGLQW3DHEG","created_at":"2026-07-05T01:53:22.758181+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6BGLQW3DHEGKHDM","created_at":"2026-07-05T01:53:22.758181+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6BGLQW3","created_at":"2026-07-05T01:53:22.758181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17715","citing_title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA","json":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA.json","graph_json":"https://pith.science/api/pith-number/M6BGLQW3DHEGKHDMFNELYQG4VA/graph.json","events_json":"https://pith.science/api/pith-number/M6BGLQW3DHEGKHDMFNELYQG4VA/events.json","paper":"https://pith.science/paper/M6BGLQW3"},"agent_actions":{"view_html":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA","download_json":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA.json","view_paper":"https://pith.science/paper/M6BGLQW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.00767&json=true","fetch_graph":"https://pith.science/api/pith-number/M6BGLQW3DHEGKHDMFNELYQG4VA/graph.json","fetch_events":"https://pith.science/api/pith-number/M6BGLQW3DHEGKHDMFNELYQG4VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/action/storage_attestation","attest_author":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/action/author_attestation","sign_citation":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/action/citation_signature","submit_replication":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/action/replication_record"}},"created_at":"2026-07-05T01:53:22.758181+00:00","updated_at":"2026-07-05T01:53:22.758181+00:00"}