{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:IGH3CFB4V7VKGT3S5HL3WHTZ5S","short_pith_number":"pith:IGH3CFB4","schema_version":"1.0","canonical_sha256":"418fb1143cafeaa34f72e9d7bb1e79eca20b378f83495e41d8beaaf493a38a6c","source":{"kind":"arxiv","id":"1104.2086","version":1},"attestation_state":"computed","paper":{"title":"A Universal Part-of-Speech Tagset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipanjan Das, Ryan McDonald, Slav Petrov","submitted_at":"2011-04-11T23:06:54Z","abstract_excerpt":"To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a mapping from 25 different treebank tagsets to this universal set. As a result, when combined with the original treebank data, this universal tagset and mapping produce a dataset consisting of common parts-of-speech for 22 different languages. We highlight the use of this resource via two experiments, including one that reports competitive accuracies for unsupervi"},"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":"1104.2086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2011-04-11T23:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"cd31fb47cd666b40a04ddd1cbec4fc004d68400c9830893ddf0f29a4258f5c0e","abstract_canon_sha256":"1df5c009d802ecda9f720902855da2b5f5d30f13baa97730797db8c2ccaf7832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:22:09.839686Z","signature_b64":"IGzUkMlgQ0KZKpPRHZwfbn+2B3u5fAht1KLux53jLs3VhgGPAvM7cmUPziQtE01Ohq5Q1lcQ2xuog8ijJe5PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"418fb1143cafeaa34f72e9d7bb1e79eca20b378f83495e41d8beaaf493a38a6c","last_reissued_at":"2026-05-18T02:22:09.839147Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:22:09.839147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Universal Part-of-Speech Tagset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipanjan Das, Ryan McDonald, Slav Petrov","submitted_at":"2011-04-11T23:06:54Z","abstract_excerpt":"To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a mapping from 25 different treebank tagsets to this universal set. As a result, when combined with the original treebank data, this universal tagset and mapping produce a dataset consisting of common parts-of-speech for 22 different languages. We highlight the use of this resource via two experiments, including one that reports competitive accuracies for unsupervi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1104.2086","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":"1104.2086","created_at":"2026-05-18T02:22:09.839233+00:00"},{"alias_kind":"arxiv_version","alias_value":"1104.2086v1","created_at":"2026-05-18T02:22:09.839233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1104.2086","created_at":"2026-05-18T02:22:09.839233+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGH3CFB4V7VK","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGH3CFB4V7VKGT3S","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGH3CFB4","created_at":"2026-05-18T12:26:30.835961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00570","citing_title":"Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S","json":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S.json","graph_json":"https://pith.science/api/pith-number/IGH3CFB4V7VKGT3S5HL3WHTZ5S/graph.json","events_json":"https://pith.science/api/pith-number/IGH3CFB4V7VKGT3S5HL3WHTZ5S/events.json","paper":"https://pith.science/paper/IGH3CFB4"},"agent_actions":{"view_html":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S","download_json":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S.json","view_paper":"https://pith.science/paper/IGH3CFB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1104.2086&json=true","fetch_graph":"https://pith.science/api/pith-number/IGH3CFB4V7VKGT3S5HL3WHTZ5S/graph.json","fetch_events":"https://pith.science/api/pith-number/IGH3CFB4V7VKGT3S5HL3WHTZ5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S/action/storage_attestation","attest_author":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S/action/author_attestation","sign_citation":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S/action/citation_signature","submit_replication":"https://pith.science/pith/IGH3CFB4V7VKGT3S5HL3WHTZ5S/action/replication_record"}},"created_at":"2026-05-18T02:22:09.839233+00:00","updated_at":"2026-05-18T02:22:09.839233+00:00"}