{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JEVEJ2CKLTDT5ILIVOXFUOD6KK","short_pith_number":"pith:JEVEJ2CK","schema_version":"1.0","canonical_sha256":"492a44e84a5cc73ea168abae5a387e52bb3b72697d9299e503cb3f20584b12eb","source":{"kind":"arxiv","id":"2403.16571","version":1},"attestation_state":"computed","paper":{"title":"NSINA: A News Corpus for Sinhala","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Damith Premasiri, Hansi Hettiarachchi, Lasitha Uyangodage, Tharindu Ranasinghe","submitted_at":"2024-03-25T09:36:51Z","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"},"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":"2403.16571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T09:36:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4cdf15b574d90d82ea011e2d2b9ef6d1d19a15aa99ade7f67eb44d74e8ed49ae","abstract_canon_sha256":"a83cad48868a7ba620d923df4c207af00b62244a72e8e272ae721fe07d8728d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:17.725770Z","signature_b64":"11Xq1a5n8UB15N5/4IMCbfhBkLx9+Ne+fjwIB9jIxq3Uxn8UjaoIDsKrd2vx0VP8da3flw4oFBZI+i6srbn3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"492a44e84a5cc73ea168abae5a387e52bb3b72697d9299e503cb3f20584b12eb","last_reissued_at":"2026-07-05T08:00:17.725255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:17.725255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NSINA: A News Corpus for Sinhala","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Damith Premasiri, Hansi Hettiarachchi, Lasitha Uyangodage, Tharindu Ranasinghe","submitted_at":"2024-03-25T09:36:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16571","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/2403.16571/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":"2403.16571","created_at":"2026-07-05T08:00:17.725321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16571v1","created_at":"2026-07-05T08:00:17.725321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16571","created_at":"2026-07-05T08:00:17.725321+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEVEJ2CKLTDT","created_at":"2026-07-05T08:00:17.725321+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEVEJ2CKLTDT5ILI","created_at":"2026-07-05T08:00:17.725321+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEVEJ2CK","created_at":"2026-07-05T08:00:17.725321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18633","citing_title":"Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK","json":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK.json","graph_json":"https://pith.science/api/pith-number/JEVEJ2CKLTDT5ILIVOXFUOD6KK/graph.json","events_json":"https://pith.science/api/pith-number/JEVEJ2CKLTDT5ILIVOXFUOD6KK/events.json","paper":"https://pith.science/paper/JEVEJ2CK"},"agent_actions":{"view_html":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK","download_json":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK.json","view_paper":"https://pith.science/paper/JEVEJ2CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16571&json=true","fetch_graph":"https://pith.science/api/pith-number/JEVEJ2CKLTDT5ILIVOXFUOD6KK/graph.json","fetch_events":"https://pith.science/api/pith-number/JEVEJ2CKLTDT5ILIVOXFUOD6KK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK/action/storage_attestation","attest_author":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK/action/author_attestation","sign_citation":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK/action/citation_signature","submit_replication":"https://pith.science/pith/JEVEJ2CKLTDT5ILIVOXFUOD6KK/action/replication_record"}},"created_at":"2026-07-05T08:00:17.725321+00:00","updated_at":"2026-07-05T08:00:17.725321+00:00"}