{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WTUDJ2PXB2IQXRB53ZHZNJQTPL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"545ad01239942703ba239b16335aaa0c2f20e14b2ffb6ea5e187114acf0b2c18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-09T04:55:52Z","title_canon_sha256":"c000a51448bf185d444df6105ea8cc74afe33d4f7662905dbd39cbce0c2d18b5"},"schema_version":"1.0","source":{"id":"2101.03289","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.03289","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2101.03289v5","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03289","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"WTUDJ2PXB2IQ","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"WTUDJ2PXB2IQXRB5","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"WTUDJ2PX","created_at":"2026-07-05T03:22:45Z"}],"graph_snapshots":[{"event_id":"sha256:6d6acb4d3189d39a0deeb129bf2b52e6012cd339401681fec05f27d636c4728c","target":"graph","created_at":"2026-07-05T03:22:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.03289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependen","authors_text":"Amir Pouran Ben Veyseh, Minh Van Nguyen, Thien Huu Nguyen, Viet Dac Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-09T04:55:52Z","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03289","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8508464544f46ac36a0757ad7c08ddec32566370b7488ff12be1b9a20d239504","target":"record","created_at":"2026-07-05T03:22:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"545ad01239942703ba239b16335aaa0c2f20e14b2ffb6ea5e187114acf0b2c18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-09T04:55:52Z","title_canon_sha256":"c000a51448bf185d444df6105ea8cc74afe33d4f7662905dbd39cbce0c2d18b5"},"schema_version":"1.0","source":{"id":"2101.03289","kind":"arxiv","version":5}},"canonical_sha256":"b4e834e9f70e910bc43dde4f96a6137aff529ad7058551aed6f8fa34bced013c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e834e9f70e910bc43dde4f96a6137aff529ad7058551aed6f8fa34bced013c","first_computed_at":"2026-07-05T03:22:45.106690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:45.106690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UcrC0BkK0v9ln21PibhuhVBYbgDNuQztCc0Kl1vZP5eE53aAFXldb8Kse9lzN5BwsrL3BOo5NxylEhmVagiuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:45.107088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.03289","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8508464544f46ac36a0757ad7c08ddec32566370b7488ff12be1b9a20d239504","sha256:6d6acb4d3189d39a0deeb129bf2b52e6012cd339401681fec05f27d636c4728c"],"state_sha256":"c148c0cb4e22b39251c5a8ab7ac85ae087354c850e8394c9dadd4c2126fdae7a"}