{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WRPY4NMEBPVVHRANWAGMZV7A62","short_pith_number":"pith:WRPY4NME","schema_version":"1.0","canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","source":{"kind":"arxiv","id":"2305.05858","version":1},"attestation_state":"computed","paper":{"title":"V\\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Rahul Aralikatte, Sumanth Doddapaneni, Ziling Cheng","submitted_at":"2023-05-10T03:07:17Z","abstract_excerpt":"We present V\\=arta, a large-scale multilingual dataset for headline generation in Indic languages. This dataset includes 41.8 million news articles in 14 different Indic languages (and English), which come from a variety of high-quality sources. To the best of our knowledge, this is the largest collection of curated articles for Indic languages currently available. We use the data collected in a series of experiments to answer important questions related to Indic NLP and multilinguality research in general. We show that the dataset is challenging even for state-of-the-art abstractive models an"},"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":"2305.05858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"155616cdd75fbb14e9d7b40ed3d8093259a6eb65ae9289e0ca26aeccf4dfdae2","abstract_canon_sha256":"3f254309a04969ee32eebd3b66eaf8425d7d130c7167c094a1fd03467e7fa439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:56.845067Z","signature_b64":"JUbhzSD48P3KaiGXwepospMc3yZqULym7pM0ZSITWMRruWsWCc6zQRfvmLMRWQInyLAG0TBiWv14l+W9rKBkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","last_reissued_at":"2026-07-05T06:08:56.844692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:56.844692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V\\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Rahul Aralikatte, Sumanth Doddapaneni, Ziling Cheng","submitted_at":"2023-05-10T03:07:17Z","abstract_excerpt":"We present V\\=arta, a large-scale multilingual dataset for headline generation in Indic languages. This dataset includes 41.8 million news articles in 14 different Indic languages (and English), which come from a variety of high-quality sources. To the best of our knowledge, this is the largest collection of curated articles for Indic languages currently available. We use the data collected in a series of experiments to answer important questions related to Indic NLP and multilinguality research in general. We show that the dataset is challenging even for state-of-the-art abstractive models an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05858","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/2305.05858/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":"2305.05858","created_at":"2026-07-05T06:08:56.844747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05858v1","created_at":"2026-07-05T06:08:56.844747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05858","created_at":"2026-07-05T06:08:56.844747+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRPY4NMEBPVV","created_at":"2026-07-05T06:08:56.844747+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRPY4NMEBPVVHRAN","created_at":"2026-07-05T06:08:56.844747+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRPY4NME","created_at":"2026-07-05T06:08:56.844747+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/WRPY4NMEBPVVHRANWAGMZV7A62","json":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62.json","graph_json":"https://pith.science/api/pith-number/WRPY4NMEBPVVHRANWAGMZV7A62/graph.json","events_json":"https://pith.science/api/pith-number/WRPY4NMEBPVVHRANWAGMZV7A62/events.json","paper":"https://pith.science/paper/WRPY4NME"},"agent_actions":{"view_html":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62","download_json":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62.json","view_paper":"https://pith.science/paper/WRPY4NME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05858&json=true","fetch_graph":"https://pith.science/api/pith-number/WRPY4NMEBPVVHRANWAGMZV7A62/graph.json","fetch_events":"https://pith.science/api/pith-number/WRPY4NMEBPVVHRANWAGMZV7A62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/action/storage_attestation","attest_author":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/action/author_attestation","sign_citation":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/action/citation_signature","submit_replication":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/action/replication_record"}},"created_at":"2026-07-05T06:08:56.844747+00:00","updated_at":"2026-07-05T06:08:56.844747+00:00"}