{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VI2CZS6QZXO2DRS32XNNXQ4C55","short_pith_number":"pith:VI2CZS6Q","schema_version":"1.0","canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","source":{"kind":"arxiv","id":"2503.18288","version":7},"attestation_state":"computed","paper":{"title":"TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Huang, Fan Gao, Nyima Tashi, Wenbin Wei, Xiangxiang Wang, Yadi Liu, Yongbin Yu, Yutong Liu","submitted_at":"2025-03-24T02:17:41Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in high-resource languages, yet progress in Tibetan remains severely constrained. While recent efforts have begun to address pre-training data scarcity for Tibetan, a more fundamental gap persists: no existing resource supports the complete LLM development pipeline, spanning pre-training, instruction tuning, safety alignment, preference optimization, and reasoning supervision. We introduce the Tibetan Foundation Dataset (TFD), the first structured, large-scale, and expert-curated dataset covering all key stages of Tibetan large lang"},"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":"2503.18288","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T02:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"5a74811d554500e16ad67a963af8af2e255d5ef401e3395fa4766bcc09f5a768","abstract_canon_sha256":"7d6d3880228e8b9ed48bbb6d7d7b77a17aabad1f9bbc494796b907ec0c028d1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:33.809405Z","signature_b64":"JaOb6mwaKkisqkGbLxRXccjG1PD2sv8Wr801uuD3hYIhVmwtYPKBqXTmpZYoTRcDUrDfH6+SzfnwkSj5AUr8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","last_reissued_at":"2026-05-27T01:05:33.808661Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:33.808661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Huang, Fan Gao, Nyima Tashi, Wenbin Wei, Xiangxiang Wang, Yadi Liu, Yongbin Yu, Yutong Liu","submitted_at":"2025-03-24T02:17:41Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in high-resource languages, yet progress in Tibetan remains severely constrained. While recent efforts have begun to address pre-training data scarcity for Tibetan, a more fundamental gap persists: no existing resource supports the complete LLM development pipeline, spanning pre-training, instruction tuning, safety alignment, preference optimization, and reasoning supervision. We introduce the Tibetan Foundation Dataset (TFD), the first structured, large-scale, and expert-curated dataset covering all key stages of Tibetan large lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18288","kind":"arxiv","version":7},"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/2503.18288/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":"2503.18288","created_at":"2026-05-27T01:05:33.808772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18288v7","created_at":"2026-05-27T01:05:33.808772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18288","created_at":"2026-05-27T01:05:33.808772+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI2CZS6QZXO2","created_at":"2026-05-27T01:05:33.808772+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI2CZS6QZXO2DRS3","created_at":"2026-05-27T01:05:33.808772+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI2CZS6Q","created_at":"2026-05-27T01:05:33.808772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2507.09205","citing_title":"From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02496","citing_title":"Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55","json":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55.json","graph_json":"https://pith.science/api/pith-number/VI2CZS6QZXO2DRS32XNNXQ4C55/graph.json","events_json":"https://pith.science/api/pith-number/VI2CZS6QZXO2DRS32XNNXQ4C55/events.json","paper":"https://pith.science/paper/VI2CZS6Q"},"agent_actions":{"view_html":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55","download_json":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55.json","view_paper":"https://pith.science/paper/VI2CZS6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18288&json=true","fetch_graph":"https://pith.science/api/pith-number/VI2CZS6QZXO2DRS32XNNXQ4C55/graph.json","fetch_events":"https://pith.science/api/pith-number/VI2CZS6QZXO2DRS32XNNXQ4C55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/action/storage_attestation","attest_author":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/action/author_attestation","sign_citation":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/action/citation_signature","submit_replication":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/action/replication_record"}},"created_at":"2026-05-27T01:05:33.808772+00:00","updated_at":"2026-05-27T01:05:33.808772+00:00"}