{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OKTLRQU2VBRV5BYURG5OYFCPOK","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":"f308fd570ad6cf8aad076f4e3869564071fd2d16c26d2fb682fe21683db9635a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T03:21:55Z","title_canon_sha256":"f57da477dadaf0725c7468750b585b6b2cc9bfed6e73e43a8858080acc49b961"},"schema_version":"1.0","source":{"id":"2405.03138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03138","created_at":"2026-07-05T08:42:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03138v2","created_at":"2026-07-05T08:42:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03138","created_at":"2026-07-05T08:42:03Z"},{"alias_kind":"pith_short_12","alias_value":"OKTLRQU2VBRV","created_at":"2026-07-05T08:42:03Z"},{"alias_kind":"pith_short_16","alias_value":"OKTLRQU2VBRV5BYU","created_at":"2026-07-05T08:42:03Z"},{"alias_kind":"pith_short_8","alias_value":"OKTLRQU2","created_at":"2026-07-05T08:42:03Z"}],"graph_snapshots":[{"event_id":"sha256:bf3ab6b799fcced8f737fbbefe72f4c0d148575f018f6d461c9bc665fc81bf3a","target":"graph","created_at":"2026-07-05T08:42:03Z","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/2405.03138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have rapidly evolved as the foundation of various natural language processing (NLP) applications. Despite their wide use cases, their understanding of culturally-related concepts and reasoning remains limited. Meantime, there is a significant need to enhance these models' cultural reasoning capabilities, especially concerning underrepresented regions. This paper introduces a novel pipeline for extracting high-quality, culturally-related instruction tuning datasets from vast unstructured corpora. We utilize a self-instruction generation pipeline to identify cultural","authors_text":"Bin Wang, Chengwei Wei, Geyu Lin, Nancy F. Chen, Zhengyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T03:21:55Z","title":"CRAFT: Extracting and Tuning Cultural Instructions from the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03138","kind":"arxiv","version":2},"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":"sha256:04aafeeb612956de6f3afd599650b86c7abdc2928b568153e393ed6e6b8b6a06","target":"record","created_at":"2026-07-05T08:42:03Z","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":"f308fd570ad6cf8aad076f4e3869564071fd2d16c26d2fb682fe21683db9635a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T03:21:55Z","title_canon_sha256":"f57da477dadaf0725c7468750b585b6b2cc9bfed6e73e43a8858080acc49b961"},"schema_version":"1.0","source":{"id":"2405.03138","kind":"arxiv","version":2}},"canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","first_computed_at":"2026-07-05T08:42:03.997019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:03.997019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLL/qw+8yG8Ota5eIbcgu9OTXzqBtAa3mDCxllmO0+aEpBZ/7qcfI+yL889WItI8YFVeO901eTLXZsQWWBw9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:03.997510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04aafeeb612956de6f3afd599650b86c7abdc2928b568153e393ed6e6b8b6a06","sha256:bf3ab6b799fcced8f737fbbefe72f4c0d148575f018f6d461c9bc665fc81bf3a"],"state_sha256":"1f5843bdf1f949da363f152bf7e80134d6cb64a11dda9c457d22278d153586f9"}