{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKTLRQU2VBRV5BYURG5OYFCPOK","short_pith_number":"pith:OKTLRQU2","schema_version":"1.0","canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","source":{"kind":"arxiv","id":"2405.03138","version":2},"attestation_state":"computed","paper":{"title":"CRAFT: Extracting and Tuning Cultural Instructions from the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chengwei Wei, Geyu Lin, Nancy F. Chen, Zhengyuan Liu","submitted_at":"2024-05-06T03:21:55Z","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"},"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":"2405.03138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T03:21:55Z","cross_cats_sorted":[],"title_canon_sha256":"f57da477dadaf0725c7468750b585b6b2cc9bfed6e73e43a8858080acc49b961","abstract_canon_sha256":"f308fd570ad6cf8aad076f4e3869564071fd2d16c26d2fb682fe21683db9635a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:03.997510Z","signature_b64":"lLL/qw+8yG8Ota5eIbcgu9OTXzqBtAa3mDCxllmO0+aEpBZ/7qcfI+yL889WItI8YFVeO901eTLXZsQWWBw9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","last_reissued_at":"2026-07-05T08:42:03.997019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:03.997019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRAFT: Extracting and Tuning Cultural Instructions from the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chengwei Wei, Geyu Lin, Nancy F. Chen, Zhengyuan Liu","submitted_at":"2024-05-06T03:21:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03138","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/2405.03138/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":"2405.03138","created_at":"2026-07-05T08:42:03.997076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03138v2","created_at":"2026-07-05T08:42:03.997076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03138","created_at":"2026-07-05T08:42:03.997076+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKTLRQU2VBRV","created_at":"2026-07-05T08:42:03.997076+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKTLRQU2VBRV5BYU","created_at":"2026-07-05T08:42:03.997076+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKTLRQU2","created_at":"2026-07-05T08:42:03.997076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14239","citing_title":"CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK","json":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK.json","graph_json":"https://pith.science/api/pith-number/OKTLRQU2VBRV5BYURG5OYFCPOK/graph.json","events_json":"https://pith.science/api/pith-number/OKTLRQU2VBRV5BYURG5OYFCPOK/events.json","paper":"https://pith.science/paper/OKTLRQU2"},"agent_actions":{"view_html":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK","download_json":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK.json","view_paper":"https://pith.science/paper/OKTLRQU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03138&json=true","fetch_graph":"https://pith.science/api/pith-number/OKTLRQU2VBRV5BYURG5OYFCPOK/graph.json","fetch_events":"https://pith.science/api/pith-number/OKTLRQU2VBRV5BYURG5OYFCPOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/action/storage_attestation","attest_author":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/action/author_attestation","sign_citation":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/action/citation_signature","submit_replication":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/action/replication_record"}},"created_at":"2026-07-05T08:42:03.997076+00:00","updated_at":"2026-07-05T08:42:03.997076+00:00"}