{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C36TFWBC6J4IYJ47AKPTP5ZFXM","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":"4f4e8e5ebc15c7267153b111e7bb7bd39b8d7f64f07254cd8f5b22a87c9dcbb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T07:50:43Z","title_canon_sha256":"743aa2546ff1261cd5616df2201767c23a6bbbc939a16eaf160795ffb7e1bfe1"},"schema_version":"1.0","source":{"id":"2311.01049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01049","created_at":"2026-07-05T07:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01049v1","created_at":"2026-07-05T07:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01049","created_at":"2026-07-05T07:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"C36TFWBC6J4I","created_at":"2026-07-05T07:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"C36TFWBC6J4IYJ47","created_at":"2026-07-05T07:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"C36TFWBC","created_at":"2026-07-05T07:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:8a7d15c1f720a65b8e70f388e4a418d04530b1966845e580d12ff027017e658d","target":"graph","created_at":"2026-07-05T07:08:19Z","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/2311.01049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data is a cornerstone for fine-tuning large language models, yet acquiring suitable data remains challenging. Challenges encompassed data scarcity, linguistic diversity, and domain-specific content. This paper presents lessons learned while crawling and refining data tailored for fine-tuning Vietnamese language models. Crafting such a dataset, while accounting for linguistic intricacies and striking a balance between inclusivity and accuracy, demands meticulous planning. Our paper presents a multidimensional strategy including leveraging existing datasets in the English language and developing","authors_text":"Arthur Tang, Bao Nguyen, Quang Nhat Tran, Thanh Nguyen Ngoc, Thanh Pham, Thuy Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T07:50:43Z","title":"Multi-dimensional data refining strategy for effective fine-tuning LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01049","kind":"arxiv","version":1},"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":"sha256:25bb1c49f8fb5afe349bfe292cad932ddca45c677d519e940c0543f92788b9b3","target":"record","created_at":"2026-07-05T07:08:19Z","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":"4f4e8e5ebc15c7267153b111e7bb7bd39b8d7f64f07254cd8f5b22a87c9dcbb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T07:50:43Z","title_canon_sha256":"743aa2546ff1261cd5616df2201767c23a6bbbc939a16eaf160795ffb7e1bfe1"},"schema_version":"1.0","source":{"id":"2311.01049","kind":"arxiv","version":1}},"canonical_sha256":"16fd32d822f2788c279f029f37f725bb3a0c20b7498b70f144cb87b031ac2508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16fd32d822f2788c279f029f37f725bb3a0c20b7498b70f144cb87b031ac2508","first_computed_at":"2026-07-05T07:08:19.872144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:19.872144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZAsjOfRodyOk8NelpKgUW0XzSSU0xhcLVc6JqXrXJEVTN4841XpmiMeoPBhPCUpHC+gIBgCOixUt96FOQW1ZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:19.872560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25bb1c49f8fb5afe349bfe292cad932ddca45c677d519e940c0543f92788b9b3","sha256:8a7d15c1f720a65b8e70f388e4a418d04530b1966845e580d12ff027017e658d"],"state_sha256":"77da0ecd3e78a38c059a665c6c2ed6cc2516c33a56e7c96e91ebe90d1e6a0607"}