{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L7HFTOXU7FYOKSWXW6FZGCJ3DO","short_pith_number":"pith:L7HFTOXU","schema_version":"1.0","canonical_sha256":"5fce59baf4f970e54ad7b78b93093b1b92069e30fcb52da3da3cad33f4b663f3","source":{"kind":"arxiv","id":"1804.08228","version":1},"attestation_state":"computed","paper":{"title":"Parsing Tweets into Universal Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Nathan Schneider, Noah A. Smith, Wanxiang Che, Yijia Liu, Yi Zhu","submitted_at":"2018-04-23T02:38:20Z","abstract_excerpt":"We study the problem of analyzing tweets with Universal Dependencies. We extend the UD guidelines to cover special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies. Using the extended guidelines, we create a new tweet treebank for English (Tweebank v2) that is four times larger than the (unlabeled) Tweebank v1 introduced by Kong et al. (2014). We characterize the disagreements between our annotators and show that it is challenging to deliver consistent annotation due to ambiguity in understanding and explaining tweets. Nonetheless, using the ne"},"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":"1804.08228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T02:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"1e176c9180b91e2fa18e461de842aae210ddbb2ff49f396433f09bde7c86fc6f","abstract_canon_sha256":"231bb82aafb309085f651aeeb11f7599915efcda697233a51a81deab16fdd025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:49.142723Z","signature_b64":"B4p7ma4610yId9Ik55GWi97NE9a9OivC/V3LNXZbtD8UWxyJlPgRI1NnRGNjtrIrfYxpIPnumi7OT7O0J2quCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fce59baf4f970e54ad7b78b93093b1b92069e30fcb52da3da3cad33f4b663f3","last_reissued_at":"2026-05-18T00:17:49.142091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:49.142091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parsing Tweets into Universal Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Nathan Schneider, Noah A. Smith, Wanxiang Che, Yijia Liu, Yi Zhu","submitted_at":"2018-04-23T02:38:20Z","abstract_excerpt":"We study the problem of analyzing tweets with Universal Dependencies. We extend the UD guidelines to cover special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies. Using the extended guidelines, we create a new tweet treebank for English (Tweebank v2) that is four times larger than the (unlabeled) Tweebank v1 introduced by Kong et al. (2014). We characterize the disagreements between our annotators and show that it is challenging to deliver consistent annotation due to ambiguity in understanding and explaining tweets. Nonetheless, using the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08228","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":"1804.08228","created_at":"2026-05-18T00:17:49.142184+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08228v1","created_at":"2026-05-18T00:17:49.142184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08228","created_at":"2026-05-18T00:17:49.142184+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7HFTOXU7FYO","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7HFTOXU7FYOKSWX","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7HFTOXU","created_at":"2026-05-18T12:32:33.847187+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/L7HFTOXU7FYOKSWXW6FZGCJ3DO","json":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO.json","graph_json":"https://pith.science/api/pith-number/L7HFTOXU7FYOKSWXW6FZGCJ3DO/graph.json","events_json":"https://pith.science/api/pith-number/L7HFTOXU7FYOKSWXW6FZGCJ3DO/events.json","paper":"https://pith.science/paper/L7HFTOXU"},"agent_actions":{"view_html":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO","download_json":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO.json","view_paper":"https://pith.science/paper/L7HFTOXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08228&json=true","fetch_graph":"https://pith.science/api/pith-number/L7HFTOXU7FYOKSWXW6FZGCJ3DO/graph.json","fetch_events":"https://pith.science/api/pith-number/L7HFTOXU7FYOKSWXW6FZGCJ3DO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO/action/storage_attestation","attest_author":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO/action/author_attestation","sign_citation":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO/action/citation_signature","submit_replication":"https://pith.science/pith/L7HFTOXU7FYOKSWXW6FZGCJ3DO/action/replication_record"}},"created_at":"2026-05-18T00:17:49.142184+00:00","updated_at":"2026-05-18T00:17:49.142184+00:00"}