{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HE742ZBLXNA2AJJGZ2LEEQIMPB","short_pith_number":"pith:HE742ZBL","canonical_record":{"source":{"id":"2410.20796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T07:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"43673825fec09df886c6473bd52cc5992347fe0c25ffc558829990de138d204c","abstract_canon_sha256":"5e1eb0405aeb493d4b7c0131749974f17cbfc088dab3531bab7d24e465888abe"},"schema_version":"1.0"},"canonical_sha256":"393fcd642bbb41a02526ce9642410c7869ab1c4c849af04d3bdb840d0216002f","source":{"kind":"arxiv","id":"2410.20796","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20796","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20796v1","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20796","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"HE742ZBLXNA2","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"HE742ZBLXNA2AJJG","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"HE742ZBL","created_at":"2026-07-05T09:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HE742ZBLXNA2AJJGZ2LEEQIMPB","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T07:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"43673825fec09df886c6473bd52cc5992347fe0c25ffc558829990de138d204c","abstract_canon_sha256":"5e1eb0405aeb493d4b7c0131749974f17cbfc088dab3531bab7d24e465888abe"},"schema_version":"1.0"},"canonical_sha256":"393fcd642bbb41a02526ce9642410c7869ab1c4c849af04d3bdb840d0216002f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:11.290311Z","signature_b64":"BngCF8WdfQD9SkH+McFZvGZDa90ZBM6u7Ve2gjecWkX+BJ2piapJesTVfWYKM+doT8b+L21CfUS6uunPgbw4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"393fcd642bbb41a02526ce9642410c7869ab1c4c849af04d3bdb840d0216002f","last_reissued_at":"2026-07-05T09:27:11.289849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:11.289849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20796","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":"2026-07-05T09:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D3RkDnYcBdSiBvKkgT8JHSJJxxff68KULl0yLtWiCOqUKrwMmg2MHTGDZ+kKcJ9qwzPmdS4DSDRaarZSrMiMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:40.532334Z"},"content_sha256":"9cff9718fb589be9129f3a2cff611b8c2d24cb6f6fdb9666063e4eb13fb4d43b","schema_version":"1.0","event_id":"sha256:9cff9718fb589be9129f3a2cff611b8c2d24cb6f6fdb9666063e4eb13fb4d43b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HE742ZBLXNA2AJJGZ2LEEQIMPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Riquelme, Duy Phung, Hannah Teufel, Jonathan Tow, Maksym Zhuravinskyi, Marco Bellagente, Michael Pieler, Nathan Cooper, Nikhil Pinnaparaju, Paulo Rocha, Reshinth Adithyan, Zaid Alyafeai","submitted_at":"2024-10-28T07:30:05Z","abstract_excerpt":"Recently published work on rephrasing natural text data for pre-training LLMs has shown promising results when combining the original dataset with the synthetically rephrased data. We build upon previous work by replicating existing results on C4 and extending them with our optimized rephrasing pipeline to the English, German, Italian, and Spanish Oscar subsets of CulturaX. Our pipeline leads to increased performance on standard evaluation benchmarks in both the mono- and multilingual setup. In addition, we provide a detailed study of our pipeline, investigating the choice of the base dataset "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20796","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/2410.20796/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":"2026-07-05T09:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HBHOErI0857BbZbm4EQNW2gIv3Ta3JwJqwRRUGY4DuHqcEZWnBEIP/2ha+7joUbmMniaMsSZgZn+pJkbgM3DBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:40.532709Z"},"content_sha256":"3ff9c5770d252f4eec715399d0e9e7d83fda77ca5db311bbb4529650843eaf75","schema_version":"1.0","event_id":"sha256:3ff9c5770d252f4eec715399d0e9e7d83fda77ca5db311bbb4529650843eaf75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/bundle.json","state_url":"https://pith.science/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/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":"2026-07-06T20:59:40Z","links":{"resolver":"https://pith.science/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB","bundle":"https://pith.science/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/bundle.json","state":"https://pith.science/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HE742ZBLXNA2AJJGZ2LEEQIMPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HE742ZBLXNA2AJJGZ2LEEQIMPB","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":"5e1eb0405aeb493d4b7c0131749974f17cbfc088dab3531bab7d24e465888abe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T07:30:05Z","title_canon_sha256":"43673825fec09df886c6473bd52cc5992347fe0c25ffc558829990de138d204c"},"schema_version":"1.0","source":{"id":"2410.20796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20796","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20796v1","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20796","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"HE742ZBLXNA2","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"HE742ZBLXNA2AJJG","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"HE742ZBL","created_at":"2026-07-05T09:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:3ff9c5770d252f4eec715399d0e9e7d83fda77ca5db311bbb4529650843eaf75","target":"graph","created_at":"2026-07-05T09:27:11Z","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/2410.20796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently published work on rephrasing natural text data for pre-training LLMs has shown promising results when combining the original dataset with the synthetically rephrased data. We build upon previous work by replicating existing results on C4 and extending them with our optimized rephrasing pipeline to the English, German, Italian, and Spanish Oscar subsets of CulturaX. Our pipeline leads to increased performance on standard evaluation benchmarks in both the mono- and multilingual setup. In addition, we provide a detailed study of our pipeline, investigating the choice of the base dataset ","authors_text":"Carlos Riquelme, Duy Phung, Hannah Teufel, Jonathan Tow, Maksym Zhuravinskyi, Marco Bellagente, Michael Pieler, Nathan Cooper, Nikhil Pinnaparaju, Paulo Rocha, Reshinth Adithyan, Zaid Alyafeai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T07:30:05Z","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20796","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":"sha256:9cff9718fb589be9129f3a2cff611b8c2d24cb6f6fdb9666063e4eb13fb4d43b","target":"record","created_at":"2026-07-05T09:27:11Z","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":"5e1eb0405aeb493d4b7c0131749974f17cbfc088dab3531bab7d24e465888abe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T07:30:05Z","title_canon_sha256":"43673825fec09df886c6473bd52cc5992347fe0c25ffc558829990de138d204c"},"schema_version":"1.0","source":{"id":"2410.20796","kind":"arxiv","version":1}},"canonical_sha256":"393fcd642bbb41a02526ce9642410c7869ab1c4c849af04d3bdb840d0216002f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"393fcd642bbb41a02526ce9642410c7869ab1c4c849af04d3bdb840d0216002f","first_computed_at":"2026-07-05T09:27:11.289849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:11.289849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BngCF8WdfQD9SkH+McFZvGZDa90ZBM6u7Ve2gjecWkX+BJ2piapJesTVfWYKM+doT8b+L21CfUS6uunPgbw4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:11.290311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cff9718fb589be9129f3a2cff611b8c2d24cb6f6fdb9666063e4eb13fb4d43b","sha256:3ff9c5770d252f4eec715399d0e9e7d83fda77ca5db311bbb4529650843eaf75"],"state_sha256":"80cd6750488cbbd7efc6e58dffff81bac72777cebcbac26a5bb6a3d3a3ad419f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFiFJJ0Q4XbFB0k6bFAQe6FRNj3H00RNbk7gKty2bc39zUMV3e0/HoaTeWZpAv/uBneJ9WP9tXUBacnPwqy/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:59:40.534707Z","bundle_sha256":"a19f7ecfe27e9b8054ead5ee7afc739b951c97b698d4476d3349baf9d0571879"}}