{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IV37MAHEH7HS3H7SI5EM637DGD","short_pith_number":"pith:IV37MAHE","canonical_record":{"source":{"id":"2309.09400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T23:49:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5028988ebcf28c87c6b99c0393ab2183e3b7f35eff49522799fa6d1d805d315b","abstract_canon_sha256":"7a542cc37a3fc9e825a33272d0ac6ce7e075f5db7847a91a68f978915986adc6"},"schema_version":"1.0"},"canonical_sha256":"4577f600e43fcf2d9ff24748cf6fe330e9ebe083f657c73cc69b6fee3c599dc6","source":{"kind":"arxiv","id":"2309.09400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09400","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09400v1","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09400","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"IV37MAHEH7HS","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"IV37MAHEH7HS3H7S","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"IV37MAHE","created_at":"2026-07-05T06:51:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IV37MAHEH7HS3H7SI5EM637DGD","target":"record","payload":{"canonical_record":{"source":{"id":"2309.09400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T23:49:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5028988ebcf28c87c6b99c0393ab2183e3b7f35eff49522799fa6d1d805d315b","abstract_canon_sha256":"7a542cc37a3fc9e825a33272d0ac6ce7e075f5db7847a91a68f978915986adc6"},"schema_version":"1.0"},"canonical_sha256":"4577f600e43fcf2d9ff24748cf6fe330e9ebe083f657c73cc69b6fee3c599dc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:38.420749Z","signature_b64":"X51YJIJXoPXblJ21eyCpWgtHvIx7i6NKM/WAfTj7CEL074dfcH0mJapai9aMVdowytTtzt/DJ4l9FKD3oUEhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4577f600e43fcf2d9ff24748cf6fe330e9ebe083f657c73cc69b6fee3c599dc6","last_reissued_at":"2026-07-05T06:51:38.420251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:38.420251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.09400","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1hDv0TxazxU9UMUnGfjwvwroi2b44oJllTPtCWqmaGdB0OmD2RXc4ajB9iI/sJuFJMbpRfWH4qUvunLHY3lIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:55:43.891717Z"},"content_sha256":"b97b2d55d8462f9c36f0b4147feea2c147ee17becc64a856ffd86b6e77c562d8","schema_version":"1.0","event_id":"sha256:b97b2d55d8462f9c36f0b4147feea2c147ee17becc64a856ffd86b6e77c562d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IV37MAHEH7HS3H7SI5EM637DGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chien Van Nguyen, Franck Dernoncourt, Hieu Man, Nghia Trung Ngo, Ryan A. Rossi, Thien Huu Nguyen, Thuat Nguyen, Viet Dac Lai","submitted_at":"2023-09-17T23:49:10Z","abstract_excerpt":"The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs have been frequently made accessible to the public to foster deeper investigation and applications. However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09400","kind":"arxiv","version":1},"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/2309.09400/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":"2026-07-05T06:51:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVkp2xKMD5V1KZLkTrbcZT1PaeWqfdpuhBattG/wHniB4zNAxF3fqoTvrGatGXWA4Aw26cLsdDeaeSoCOjqeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:55:43.892203Z"},"content_sha256":"fd848663d395546c5a23e7598dbc680e7d437e1200ec0df1689e5c8296ec9051","schema_version":"1.0","event_id":"sha256:fd848663d395546c5a23e7598dbc680e7d437e1200ec0df1689e5c8296ec9051"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV37MAHEH7HS3H7SI5EM637DGD/bundle.json","state_url":"https://pith.science/pith/IV37MAHEH7HS3H7SI5EM637DGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV37MAHEH7HS3H7SI5EM637DGD/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":"2026-08-05T23:55:43Z","links":{"resolver":"https://pith.science/pith/IV37MAHEH7HS3H7SI5EM637DGD","bundle":"https://pith.science/pith/IV37MAHEH7HS3H7SI5EM637DGD/bundle.json","state":"https://pith.science/pith/IV37MAHEH7HS3H7SI5EM637DGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV37MAHEH7HS3H7SI5EM637DGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IV37MAHEH7HS3H7SI5EM637DGD","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":"7a542cc37a3fc9e825a33272d0ac6ce7e075f5db7847a91a68f978915986adc6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T23:49:10Z","title_canon_sha256":"5028988ebcf28c87c6b99c0393ab2183e3b7f35eff49522799fa6d1d805d315b"},"schema_version":"1.0","source":{"id":"2309.09400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09400","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09400v1","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09400","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"IV37MAHEH7HS","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"IV37MAHEH7HS3H7S","created_at":"2026-07-05T06:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"IV37MAHE","created_at":"2026-07-05T06:51:38Z"}],"graph_snapshots":[{"event_id":"sha256:fd848663d395546c5a23e7598dbc680e7d437e1200ec0df1689e5c8296ec9051","target":"graph","created_at":"2026-07-05T06:51:38Z","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/2309.09400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs have been frequently made accessible to the public to foster deeper investigation and applications. However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary l","authors_text":"Chien Van Nguyen, Franck Dernoncourt, Hieu Man, Nghia Trung Ngo, Ryan A. Rossi, Thien Huu Nguyen, Thuat Nguyen, Viet Dac Lai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T23:49:10Z","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09400","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:b97b2d55d8462f9c36f0b4147feea2c147ee17becc64a856ffd86b6e77c562d8","target":"record","created_at":"2026-07-05T06:51:38Z","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":"7a542cc37a3fc9e825a33272d0ac6ce7e075f5db7847a91a68f978915986adc6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T23:49:10Z","title_canon_sha256":"5028988ebcf28c87c6b99c0393ab2183e3b7f35eff49522799fa6d1d805d315b"},"schema_version":"1.0","source":{"id":"2309.09400","kind":"arxiv","version":1}},"canonical_sha256":"4577f600e43fcf2d9ff24748cf6fe330e9ebe083f657c73cc69b6fee3c599dc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4577f600e43fcf2d9ff24748cf6fe330e9ebe083f657c73cc69b6fee3c599dc6","first_computed_at":"2026-07-05T06:51:38.420251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:38.420251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X51YJIJXoPXblJ21eyCpWgtHvIx7i6NKM/WAfTj7CEL074dfcH0mJapai9aMVdowytTtzt/DJ4l9FKD3oUEhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:38.420749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b97b2d55d8462f9c36f0b4147feea2c147ee17becc64a856ffd86b6e77c562d8","sha256:fd848663d395546c5a23e7598dbc680e7d437e1200ec0df1689e5c8296ec9051"],"state_sha256":"1b2aea42435f3b1eebcf18288b2856c35db8ccadd4fc8c6c9b031eb98992eecb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n55zjEklERyCQXbVPlS9cuCzo3ov5aORzFs7SbjklLtYkJ55fvqh6Cf/Cf95uYcQ0hCT8zaSwVRONsvACROeBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:55:43.895583Z","bundle_sha256":"7a8e6290d19a0fbedef7b83f44070bd0cb2fdd3e042315152c07930f7dc57957"}}