{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EYXIF2VDIU4FUSN5F2HSYF5LEM","short_pith_number":"pith:EYXIF2VD","schema_version":"1.0","canonical_sha256":"262e82eaa345385a49bd2e8f2c17ab2319933916a1033e7bb3e5bdc5c23903d3","source":{"kind":"arxiv","id":"2411.15734","version":2},"attestation_state":"computed","paper":{"title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bal Krishna Bal, Jinu Nyachhyon, Mridul Sharma, Prajwal Thapa","submitted_at":"2024-11-24T06:38:24Z","abstract_excerpt":"Transformer-based pre-trained language models have dominated the field of Natural Language Processing (NLP) for quite some time now. However, the Nepali language, spoken by approximately 32 million people worldwide, remains significantly underrepresented in this domain. This underrepresentation is primarily attributed to the scarcity of monolingual data corpora and limited available resources for the Nepali language. While existing efforts have predominantly concentrated on basic encoder-based models, there is a notable gap in the exploration of decoder-based architectures. To address this gap"},"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":"2411.15734","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T06:38:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c7cf41bf524aa1d98a3ffa3f44f23dada5547078052964a50f58b4d6a668f6b","abstract_canon_sha256":"86c3354a0658f9b977b78fd5cf29eabd0d7c8348634e0cf78f0a3bed0265e6a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:01.181573Z","signature_b64":"4EkdQTtVQNHqF+8F4FKTOxKp2haqEqfSkuJ8AjhEQtreizb5GPmCQthx6mo9J42mbHvLYwFyGx0slhd0bYAXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"262e82eaa345385a49bd2e8f2c17ab2319933916a1033e7bb3e5bdc5c23903d3","last_reissued_at":"2026-07-05T11:56:01.181174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:01.181174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bal Krishna Bal, Jinu Nyachhyon, Mridul Sharma, Prajwal Thapa","submitted_at":"2024-11-24T06:38:24Z","abstract_excerpt":"Transformer-based pre-trained language models have dominated the field of Natural Language Processing (NLP) for quite some time now. However, the Nepali language, spoken by approximately 32 million people worldwide, remains significantly underrepresented in this domain. This underrepresentation is primarily attributed to the scarcity of monolingual data corpora and limited available resources for the Nepali language. While existing efforts have predominantly concentrated on basic encoder-based models, there is a notable gap in the exploration of decoder-based architectures. To address this gap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15734","kind":"arxiv","version":2},"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/2411.15734/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":"2411.15734","created_at":"2026-07-05T11:56:01.181227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15734v2","created_at":"2026-07-05T11:56:01.181227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15734","created_at":"2026-07-05T11:56:01.181227+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYXIF2VDIU4F","created_at":"2026-07-05T11:56:01.181227+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYXIF2VDIU4FUSN5","created_at":"2026-07-05T11:56:01.181227+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYXIF2VD","created_at":"2026-07-05T11:56:01.181227+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/EYXIF2VDIU4FUSN5F2HSYF5LEM","json":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM.json","graph_json":"https://pith.science/api/pith-number/EYXIF2VDIU4FUSN5F2HSYF5LEM/graph.json","events_json":"https://pith.science/api/pith-number/EYXIF2VDIU4FUSN5F2HSYF5LEM/events.json","paper":"https://pith.science/paper/EYXIF2VD"},"agent_actions":{"view_html":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM","download_json":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM.json","view_paper":"https://pith.science/paper/EYXIF2VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15734&json=true","fetch_graph":"https://pith.science/api/pith-number/EYXIF2VDIU4FUSN5F2HSYF5LEM/graph.json","fetch_events":"https://pith.science/api/pith-number/EYXIF2VDIU4FUSN5F2HSYF5LEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM/action/storage_attestation","attest_author":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM/action/author_attestation","sign_citation":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM/action/citation_signature","submit_replication":"https://pith.science/pith/EYXIF2VDIU4FUSN5F2HSYF5LEM/action/replication_record"}},"created_at":"2026-07-05T11:56:01.181227+00:00","updated_at":"2026-07-05T11:56:01.181227+00:00"}