{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VI2CZS6QZXO2DRS32XNNXQ4C55","short_pith_number":"pith:VI2CZS6Q","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"},"canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","source":{"kind":"arxiv","id":"2503.18288","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18288","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18288v7","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18288","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"VI2CZS6QZXO2","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"VI2CZS6QZXO2DRS3","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"VI2CZS6Q","created_at":"2026-05-27T01:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VI2CZS6QZXO2DRS32XNNXQ4C55","target":"record","payload":{"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"},"canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","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"},"source_kind":"arxiv","source_id":"2503.18288","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Z4UHJ3Z8szADV94OuaF0ElFBz1isyVBEO2a19DFpX6/fRqeyoADea6jee+j0DCkTICARcKTK/oK3ornDGYiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:51:06.299072Z"},"content_sha256":"ddb18ec2145297974e875ea2567fa888a1bdc49380b37a017deff8d617b3f31a","schema_version":"1.0","event_id":"sha256:ddb18ec2145297974e875ea2567fa888a1bdc49380b37a017deff8d617b3f31a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VI2CZS6QZXO2DRS32XNNXQ4C55","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vySPi31HCR0iN4TS+AHF6hF5pO45+dlWZmUFtRE3NzYemMFQrUJHvjp9mwP6r94EDbq3gIoOW8NoM5UyUJBECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:51:06.299462Z"},"content_sha256":"95388ed4974a8fb24dc2bcca5283bde0c3f991f75449dd1e734c159ebefd0a37","schema_version":"1.0","event_id":"sha256:95388ed4974a8fb24dc2bcca5283bde0c3f991f75449dd1e734c159ebefd0a37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/bundle.json","state_url":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T00:51:06Z","links":{"resolver":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55","bundle":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/bundle.json","state":"https://pith.science/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VI2CZS6QZXO2DRS32XNNXQ4C55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VI2CZS6QZXO2DRS32XNNXQ4C55","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":"7d6d3880228e8b9ed48bbb6d7d7b77a17aabad1f9bbc494796b907ec0c028d1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T02:17:41Z","title_canon_sha256":"5a74811d554500e16ad67a963af8af2e255d5ef401e3395fa4766bcc09f5a768"},"schema_version":"1.0","source":{"id":"2503.18288","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18288","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18288v7","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18288","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"VI2CZS6QZXO2","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"VI2CZS6QZXO2DRS3","created_at":"2026-05-27T01:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"VI2CZS6Q","created_at":"2026-05-27T01:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:95388ed4974a8fb24dc2bcca5283bde0c3f991f75449dd1e734c159ebefd0a37","target":"graph","created_at":"2026-05-27T01:05:33Z","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/2503.18288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng Huang, Fan Gao, Nyima Tashi, Wenbin Wei, Xiangxiang Wang, Yadi Liu, Yongbin Yu, Yutong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T02:17:41Z","title":"TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18288","kind":"arxiv","version":7},"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:ddb18ec2145297974e875ea2567fa888a1bdc49380b37a017deff8d617b3f31a","target":"record","created_at":"2026-05-27T01:05:33Z","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":"7d6d3880228e8b9ed48bbb6d7d7b77a17aabad1f9bbc494796b907ec0c028d1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T02:17:41Z","title_canon_sha256":"5a74811d554500e16ad67a963af8af2e255d5ef401e3395fa4766bcc09f5a768"},"schema_version":"1.0","source":{"id":"2503.18288","kind":"arxiv","version":7}},"canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa342ccbd0cddda1c65bd5dadbc382ef79737b39522f664aa24ff48cd0044337","first_computed_at":"2026-05-27T01:05:33.808661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:33.808661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JaOb6mwaKkisqkGbLxRXccjG1PD2sv8Wr801uuD3hYIhVmwtYPKBqXTmpZYoTRcDUrDfH6+SzfnwkSj5AUr8Ag==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:33.809405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18288","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddb18ec2145297974e875ea2567fa888a1bdc49380b37a017deff8d617b3f31a","sha256:95388ed4974a8fb24dc2bcca5283bde0c3f991f75449dd1e734c159ebefd0a37"],"state_sha256":"efe2b123424d382e39476cdd631faaabece7706f5c3c1f9fddea25e631418cdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mH+CieSmaFtxq4Z6EPqIFWAqhQ8CoM5OpGz6RVjH9APjHN9DseZ6A981/hU4Wx+RVpy51I9LphdIfnI+pw+BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:51:06.301477Z","bundle_sha256":"ebf775a291dc7bb6f3ed7b0bb9fc3e9664dff2db5171c9903db1b1f5accbcb76"}}