{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OKTLRQU2VBRV5BYURG5OYFCPOK","short_pith_number":"pith:OKTLRQU2","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"},"canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","source":{"kind":"arxiv","id":"2405.03138","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OKTLRQU2VBRV5BYURG5OYFCPOK","target":"record","payload":{"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"},"canonical_sha256":"72a6b8c29aa8635e871489baec144f72ac3ddce7a5300e03fd5e8263de8f6b12","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"},"source_kind":"arxiv","source_id":"2405.03138","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5g5Z2ssRLcxHO/YynxvYzJjvZf+qX7h6j2iiSy4gb8Y8sGaFNlNKDP2XlJjoLJneMee6J/PvF2gBEjUlRs6KDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:08:01.357026Z"},"content_sha256":"04aafeeb612956de6f3afd599650b86c7abdc2928b568153e393ed6e6b8b6a06","schema_version":"1.0","event_id":"sha256:04aafeeb612956de6f3afd599650b86c7abdc2928b568153e393ed6e6b8b6a06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OKTLRQU2VBRV5BYURG5OYFCPOK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5AZiS0gj0oJGO5xbxy1tq82vMRownEtwmEa4vUirRnQUQJ6hAuQhRtfnH/WQdvgOtDzsFvi/2LjF0yLy/e4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:08:01.357574Z"},"content_sha256":"bf3ab6b799fcced8f737fbbefe72f4c0d148575f018f6d461c9bc665fc81bf3a","schema_version":"1.0","event_id":"sha256:bf3ab6b799fcced8f737fbbefe72f4c0d148575f018f6d461c9bc665fc81bf3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/bundle.json","state_url":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/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":"2026-08-09T20:08:01Z","links":{"resolver":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK","bundle":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/bundle.json","state":"https://pith.science/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKTLRQU2VBRV5BYURG5OYFCPOK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5rGB/6koOPrt9OoMsbgSJvx3Ja9kpeKfJz3PYTYTHWTslQd+7djfX8P8GCscEtMVPm5hXT8ep/9T9gptd19+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:08:01.365777Z","bundle_sha256":"8caa19a6a69da71b47547af8fe4e935d86eb50022263cb3b80b58b3a70ca03e5"}}