{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JEVEJ2CKLTDT5ILIVOXFUOD6KK","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":"a83cad48868a7ba620d923df4c207af00b62244a72e8e272ae721fe07d8728d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T09:36:51Z","title_canon_sha256":"4cdf15b574d90d82ea011e2d2b9ef6d1d19a15aa99ade7f67eb44d74e8ed49ae"},"schema_version":"1.0","source":{"id":"2403.16571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16571","created_at":"2026-07-05T08:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16571v1","created_at":"2026-07-05T08:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16571","created_at":"2026-07-05T08:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"JEVEJ2CKLTDT","created_at":"2026-07-05T08:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"JEVEJ2CKLTDT5ILI","created_at":"2026-07-05T08:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"JEVEJ2CK","created_at":"2026-07-05T08:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:b97b294ad7eb86e2abcd7c9f9b218b72d536f33a59d5c41efdea18eb9ce6d660","target":"graph","created_at":"2026-07-05T08:00:17Z","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/2403.16571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The introduction of large language models (LLMs) has advanced natural language processing (NLP), but their effectiveness is largely dependent on pre-training resources. This is especially evident in low-resource languages, such as Sinhala, which face two primary challenges: the lack of substantial training data and limited benchmarking datasets. In response, this study introduces NSINA, a comprehensive news corpus of over 500,000 articles from popular Sinhala news websites, along with three NLP tasks: news media identification, news category prediction, and news headline generation. The releas","authors_text":"Damith Premasiri, Hansi Hettiarachchi, Lasitha Uyangodage, Tharindu Ranasinghe","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T09:36:51Z","title":"NSINA: A News Corpus for Sinhala"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16571","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:af44b0385f28cf439c7a756bc004b07ca41f73ba8cac7a5e9ab256c66c3926c3","target":"record","created_at":"2026-07-05T08:00:17Z","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":"a83cad48868a7ba620d923df4c207af00b62244a72e8e272ae721fe07d8728d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T09:36:51Z","title_canon_sha256":"4cdf15b574d90d82ea011e2d2b9ef6d1d19a15aa99ade7f67eb44d74e8ed49ae"},"schema_version":"1.0","source":{"id":"2403.16571","kind":"arxiv","version":1}},"canonical_sha256":"492a44e84a5cc73ea168abae5a387e52bb3b72697d9299e503cb3f20584b12eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"492a44e84a5cc73ea168abae5a387e52bb3b72697d9299e503cb3f20584b12eb","first_computed_at":"2026-07-05T08:00:17.725255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:17.725255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11Xq1a5n8UB15N5/4IMCbfhBkLx9+Ne+fjwIB9jIxq3Uxn8UjaoIDsKrd2vx0VP8da3flw4oFBZI+i6srbn3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:17.725770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af44b0385f28cf439c7a756bc004b07ca41f73ba8cac7a5e9ab256c66c3926c3","sha256:b97b294ad7eb86e2abcd7c9f9b218b72d536f33a59d5c41efdea18eb9ce6d660"],"state_sha256":"d21411b10a6b7dc8fbbf3db70aec3f66790515ebb4985e4c83db1dc5ce925ebd"}