{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OANFHBHDFOOUJNPAPE7LECLN7W","short_pith_number":"pith:OANFHBHD","schema_version":"1.0","canonical_sha256":"701a5384e32b9d44b5e0793eb2096dfdb64cd8d0ad70f75c98c1426167d20e64","source":{"kind":"arxiv","id":"2003.07082","version":2},"attestation_state":"computed","paper":{"title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Jason Bolton, Peng Qi, Yuhao Zhang, Yuhui Zhang","submitted_at":"2020-03-16T09:05:53Z","abstract_excerpt":"We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Stanza on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves "},"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":"2003.07082","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-16T09:05:53Z","cross_cats_sorted":[],"title_canon_sha256":"bb0a03672fb6857f59484f43c9787b68cd65a728bb33174eaedf44866ba6eac6","abstract_canon_sha256":"05f108a57b683afed27549786f557cea3899eab0ea5886f90c51440b5ff23391"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:35.247422Z","signature_b64":"mu4CB4zaxk356/Sy1hbqbdhwz+hsRkq26alcy8RWeGmPCKGCevDLg9V0VdwPrtsSlWzUXSoS/+X6Vlgsqp1YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"701a5384e32b9d44b5e0793eb2096dfdb64cd8d0ad70f75c98c1426167d20e64","last_reissued_at":"2026-07-05T00:57:35.246971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:35.246971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Jason Bolton, Peng Qi, Yuhao Zhang, Yuhui Zhang","submitted_at":"2020-03-16T09:05:53Z","abstract_excerpt":"We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Stanza on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07082","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/2003.07082/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":"2003.07082","created_at":"2026-07-05T00:57:35.247036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.07082v2","created_at":"2026-07-05T00:57:35.247036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07082","created_at":"2026-07-05T00:57:35.247036+00:00"},{"alias_kind":"pith_short_12","alias_value":"OANFHBHDFOOU","created_at":"2026-07-05T00:57:35.247036+00:00"},{"alias_kind":"pith_short_16","alias_value":"OANFHBHDFOOUJNPA","created_at":"2026-07-05T00:57:35.247036+00:00"},{"alias_kind":"pith_short_8","alias_value":"OANFHBHD","created_at":"2026-07-05T00:57:35.247036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02953","citing_title":"Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15867","citing_title":"RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27673","citing_title":"The TEA Nets framework combines AI and cognitive network science to model targets, events and actors in text","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06625","citing_title":"Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13232","citing_title":"Evaluating the Evaluator: Problems with SemEval-2020 Task 1 for Lexical Semantic Change Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02052","citing_title":"Methods, Data, and Conceptual Change: Reflections from Two Quantitative Diachronic Case Studies","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W","json":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W.json","graph_json":"https://pith.science/api/pith-number/OANFHBHDFOOUJNPAPE7LECLN7W/graph.json","events_json":"https://pith.science/api/pith-number/OANFHBHDFOOUJNPAPE7LECLN7W/events.json","paper":"https://pith.science/paper/OANFHBHD"},"agent_actions":{"view_html":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W","download_json":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W.json","view_paper":"https://pith.science/paper/OANFHBHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.07082&json=true","fetch_graph":"https://pith.science/api/pith-number/OANFHBHDFOOUJNPAPE7LECLN7W/graph.json","fetch_events":"https://pith.science/api/pith-number/OANFHBHDFOOUJNPAPE7LECLN7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W/action/storage_attestation","attest_author":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W/action/author_attestation","sign_citation":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W/action/citation_signature","submit_replication":"https://pith.science/pith/OANFHBHDFOOUJNPAPE7LECLN7W/action/replication_record"}},"created_at":"2026-07-05T00:57:35.247036+00:00","updated_at":"2026-07-05T00:57:35.247036+00:00"}