{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:32SGCAAQLOXBBEJ6PE7RZ2ADQJ","short_pith_number":"pith:32SGCAAQ","schema_version":"1.0","canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","source":{"kind":"arxiv","id":"2505.20428","version":1},"attestation_state":"computed","paper":{"title":"The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angelina A. Aquino, Elsie Marie T. Or, Lester James V. Miranda","submitted_at":"2025-05-26T18:25:10Z","abstract_excerpt":"This paper presents UD-NewsCrawl, the largest Tagalog treebank to date, containing 15.6k trees manually annotated according to the Universal Dependencies framework. We detail our treebank development process, including data collection, pre-processing, manual annotation, and quality assurance procedures. We provide baseline evaluations using multiple transformer-based models to assess the performance of state-of-the-art dependency parsers on Tagalog. We also highlight challenges in the syntactic analysis of Tagalog given its distinctive grammatical properties, and discuss its implications for t"},"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":"2505.20428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:25:10Z","cross_cats_sorted":[],"title_canon_sha256":"a672ab727b44e451b9de52f36c37c392a14d4888586d2f701e22472cfdabaac4","abstract_canon_sha256":"97fa3282b906e9a67b9ce039f590910b786ec21a3eadc6642952b3f2318f0120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:12.408297Z","signature_b64":"j/h3R/4d//9xcQav/0T2zacdPi8NHIoJ4Ax8kUz6YQARC//La9Harmrhe1l3087r5OPdoVCCHc9fHlMaMhNgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","last_reissued_at":"2026-07-05T11:10:12.407723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:12.407723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angelina A. Aquino, Elsie Marie T. Or, Lester James V. Miranda","submitted_at":"2025-05-26T18:25:10Z","abstract_excerpt":"This paper presents UD-NewsCrawl, the largest Tagalog treebank to date, containing 15.6k trees manually annotated according to the Universal Dependencies framework. We detail our treebank development process, including data collection, pre-processing, manual annotation, and quality assurance procedures. We provide baseline evaluations using multiple transformer-based models to assess the performance of state-of-the-art dependency parsers on Tagalog. We also highlight challenges in the syntactic analysis of Tagalog given its distinctive grammatical properties, and discuss its implications for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20428","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20428/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":"2505.20428","created_at":"2026-07-05T11:10:12.407781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20428v1","created_at":"2026-07-05T11:10:12.407781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20428","created_at":"2026-07-05T11:10:12.407781+00:00"},{"alias_kind":"pith_short_12","alias_value":"32SGCAAQLOXB","created_at":"2026-07-05T11:10:12.407781+00:00"},{"alias_kind":"pith_short_16","alias_value":"32SGCAAQLOXBBEJ6","created_at":"2026-07-05T11:10:12.407781+00:00"},{"alias_kind":"pith_short_8","alias_value":"32SGCAAQ","created_at":"2026-07-05T11:10:12.407781+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/32SGCAAQLOXBBEJ6PE7RZ2ADQJ","json":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ.json","graph_json":"https://pith.science/api/pith-number/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/graph.json","events_json":"https://pith.science/api/pith-number/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/events.json","paper":"https://pith.science/paper/32SGCAAQ"},"agent_actions":{"view_html":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ","download_json":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ.json","view_paper":"https://pith.science/paper/32SGCAAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20428&json=true","fetch_graph":"https://pith.science/api/pith-number/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/action/storage_attestation","attest_author":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/action/author_attestation","sign_citation":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/action/citation_signature","submit_replication":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/action/replication_record"}},"created_at":"2026-07-05T11:10:12.407781+00:00","updated_at":"2026-07-05T11:10:12.407781+00:00"}