{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:32SGCAAQLOXBBEJ6PE7RZ2ADQJ","short_pith_number":"pith:32SGCAAQ","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"},"canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","source":{"kind":"arxiv","id":"2505.20428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20428","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20428v1","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20428","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"32SGCAAQLOXB","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"32SGCAAQLOXBBEJ6","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"32SGCAAQ","created_at":"2026-07-05T11:10:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:32SGCAAQLOXBBEJ6PE7RZ2ADQJ","target":"record","payload":{"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"},"canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","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"},"source_kind":"arxiv","source_id":"2505.20428","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E250/vsy9sudPJ2IDQ0rO6JD4pbfQg69Lgkhm7B57+Vm7EW1Z8drkuc3KbiBYzNLhVxh53OLVRHk1/cL1JH1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:52:47.508655Z"},"content_sha256":"e81802b0e49222b72b9bb87eef4668f2a55f36f4175fec750effb1b64d0cf249","schema_version":"1.0","event_id":"sha256:e81802b0e49222b72b9bb87eef4668f2a55f36f4175fec750effb1b64d0cf249"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:32SGCAAQLOXBBEJ6PE7RZ2ADQJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWkmVa3hhQC4DiZ1X03DsnAPQkKQDKgSRazSE89Pn5TobWDBD0i88woURZHsiK3/rXG1JIQr357d9ljYjxFGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:52:47.509153Z"},"content_sha256":"9f0f9912ec7d8e7d1bce465ec085aa5ed8cdb43a737960ee2f187abaab831cd6","schema_version":"1.0","event_id":"sha256:9f0f9912ec7d8e7d1bce465ec085aa5ed8cdb43a737960ee2f187abaab831cd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/bundle.json","state_url":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T03:52:47Z","links":{"resolver":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ","bundle":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/bundle.json","state":"https://pith.science/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32SGCAAQLOXBBEJ6PE7RZ2ADQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:32SGCAAQLOXBBEJ6PE7RZ2ADQJ","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":"97fa3282b906e9a67b9ce039f590910b786ec21a3eadc6642952b3f2318f0120","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:25:10Z","title_canon_sha256":"a672ab727b44e451b9de52f36c37c392a14d4888586d2f701e22472cfdabaac4"},"schema_version":"1.0","source":{"id":"2505.20428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20428","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20428v1","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20428","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"32SGCAAQLOXB","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"32SGCAAQLOXBBEJ6","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"32SGCAAQ","created_at":"2026-07-05T11:10:12Z"}],"graph_snapshots":[{"event_id":"sha256:9f0f9912ec7d8e7d1bce465ec085aa5ed8cdb43a737960ee2f187abaab831cd6","target":"graph","created_at":"2026-07-05T11:10:12Z","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/2505.20428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Angelina A. Aquino, Elsie Marie T. Or, Lester James V. Miranda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:25:10Z","title":"The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20428","kind":"arxiv","version":1},"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:e81802b0e49222b72b9bb87eef4668f2a55f36f4175fec750effb1b64d0cf249","target":"record","created_at":"2026-07-05T11:10:12Z","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":"97fa3282b906e9a67b9ce039f590910b786ec21a3eadc6642952b3f2318f0120","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:25:10Z","title_canon_sha256":"a672ab727b44e451b9de52f36c37c392a14d4888586d2f701e22472cfdabaac4"},"schema_version":"1.0","source":{"id":"2505.20428","kind":"arxiv","version":1}},"canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea46100105bae10913e793f1ce803827c9132fbddb36aebfd6fa72cf852ae8a","first_computed_at":"2026-07-05T11:10:12.407723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:12.407723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j/h3R/4d//9xcQav/0T2zacdPi8NHIoJ4Ax8kUz6YQARC//La9Harmrhe1l3087r5OPdoVCCHc9fHlMaMhNgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:12.408297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e81802b0e49222b72b9bb87eef4668f2a55f36f4175fec750effb1b64d0cf249","sha256:9f0f9912ec7d8e7d1bce465ec085aa5ed8cdb43a737960ee2f187abaab831cd6"],"state_sha256":"0ab3f00735d44dad379684d0851eaaacec29a6698cb54ffa3e555b5af1f16e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/IDMe9/jE+tGxh+8fNdyWcEF8mpHb1JZjE7yQMCmXAYzFvTDO7O5SmU+tZqPq0DmdDb/1SjQZmMtazA90+fCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:52:47.513839Z","bundle_sha256":"4b13c27e8a93ba047d04e8578f78bc65075f8ce89406c6b934e8f6cddc5cb7fa"}}