{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R3TB4SIMRLJABRCQMNKGP4N2WE","short_pith_number":"pith:R3TB4SIM","canonical_record":{"source":{"id":"2506.20920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T01:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"cdbbcfa019bb781512ddd45a3f61f6656425ef4583643150bb35767be6a605ea","abstract_canon_sha256":"91b46ea12280b413a971ce18b93fb1552a398ede374e43c40d06b9f8ba31cc95"},"schema_version":"1.0"},"canonical_sha256":"8ee61e490c8ad200c450635467f1bab1246039f11d1333d9a7f0be0d7a8e4f45","source":{"kind":"arxiv","id":"2506.20920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20920","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20920v1","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20920","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"R3TB4SIMRLJA","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"R3TB4SIMRLJABRCQ","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"R3TB4SIM","created_at":"2026-07-05T11:27:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R3TB4SIMRLJABRCQMNKGP4N2WE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T01:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"cdbbcfa019bb781512ddd45a3f61f6656425ef4583643150bb35767be6a605ea","abstract_canon_sha256":"91b46ea12280b413a971ce18b93fb1552a398ede374e43c40d06b9f8ba31cc95"},"schema_version":"1.0"},"canonical_sha256":"8ee61e490c8ad200c450635467f1bab1246039f11d1333d9a7f0be0d7a8e4f45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:36.161857Z","signature_b64":"6FV8E4d5XKGMEHyAJUVkUbe5SjGyyyMhUx6gfuQO5yrW5KWkVrU5LikNrf2J/cLXUhDOAKV8JCb+VhVWucaHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ee61e490c8ad200c450635467f1bab1246039f11d1333d9a7f0be0d7a8e4f45","last_reissued_at":"2026-07-05T11:27:36.161374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:36.161374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20920","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":"2026-07-05T11:27:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uoJhJ+ZRKmKGKezbUPWR2SZq3SPEuytUq9aMSvuI14bMfwfCv/BDULbvPc/r0QzbgkLPCcpCMTaOKQnktUSbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:19:51.585240Z"},"content_sha256":"b84183592fb014fd6e20b9870a32828282c78db216c32bbd4452df76ac12f68a","schema_version":"1.0","event_id":"sha256:b84183592fb014fd6e20b9870a32828282c78db216c32bbd4452df76ac12f68a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R3TB4SIMRLJABRCQMNKGP4N2WE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hossein Kargaran, Bettina Messmer, Colin Raffel, Guilherme Penedo, Hynek Kydl\\'i\\v{c}ek, Leandro Von Werra, Martin Jaggi, Negar Foroutan, Thomas Wolf, Vinko Sabol\\v{c}ec","submitted_at":"2025-06-26T01:01:47Z","abstract_excerpt":"Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-training datasets has seen substantial recent progress, training performant multilingual LLMs remains a challenge, in large part due to the inherent difficulty of tailoring filtering and deduplication pipelines to a large number of languages. In this work, we introduce a new pre-training dataset curation pipeline based on FineWeb that can be automatically adapted to support any language. We extensively ablate our pipeline "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20920","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/2506.20920/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":"2026-07-05T11:27:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXTuThGq4QcLs7kvSYf4D0nK5eoEyKOOM2HaoibGWMxmH2lEGiQf4kKAgMhn2TJrAMcWWMnDm5hNw6ocEJd0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:19:51.585748Z"},"content_sha256":"90194ad64d8f9d1aae042e672dc3b62f9251b674a78d798df52cdba72aac491f","schema_version":"1.0","event_id":"sha256:90194ad64d8f9d1aae042e672dc3b62f9251b674a78d798df52cdba72aac491f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/bundle.json","state_url":"https://pith.science/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/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":"2026-08-06T05:19:51Z","links":{"resolver":"https://pith.science/pith/R3TB4SIMRLJABRCQMNKGP4N2WE","bundle":"https://pith.science/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/bundle.json","state":"https://pith.science/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3TB4SIMRLJABRCQMNKGP4N2WE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R3TB4SIMRLJABRCQMNKGP4N2WE","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":"91b46ea12280b413a971ce18b93fb1552a398ede374e43c40d06b9f8ba31cc95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T01:01:47Z","title_canon_sha256":"cdbbcfa019bb781512ddd45a3f61f6656425ef4583643150bb35767be6a605ea"},"schema_version":"1.0","source":{"id":"2506.20920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20920","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20920v1","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20920","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"R3TB4SIMRLJA","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"R3TB4SIMRLJABRCQ","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"R3TB4SIM","created_at":"2026-07-05T11:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:90194ad64d8f9d1aae042e672dc3b62f9251b674a78d798df52cdba72aac491f","target":"graph","created_at":"2026-07-05T11:27:36Z","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/2506.20920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-training datasets has seen substantial recent progress, training performant multilingual LLMs remains a challenge, in large part due to the inherent difficulty of tailoring filtering and deduplication pipelines to a large number of languages. In this work, we introduce a new pre-training dataset curation pipeline based on FineWeb that can be automatically adapted to support any language. We extensively ablate our pipeline ","authors_text":"Amir Hossein Kargaran, Bettina Messmer, Colin Raffel, Guilherme Penedo, Hynek Kydl\\'i\\v{c}ek, Leandro Von Werra, Martin Jaggi, Negar Foroutan, Thomas Wolf, Vinko Sabol\\v{c}ec","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T01:01:47Z","title":"FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20920","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:b84183592fb014fd6e20b9870a32828282c78db216c32bbd4452df76ac12f68a","target":"record","created_at":"2026-07-05T11:27:36Z","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":"91b46ea12280b413a971ce18b93fb1552a398ede374e43c40d06b9f8ba31cc95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T01:01:47Z","title_canon_sha256":"cdbbcfa019bb781512ddd45a3f61f6656425ef4583643150bb35767be6a605ea"},"schema_version":"1.0","source":{"id":"2506.20920","kind":"arxiv","version":1}},"canonical_sha256":"8ee61e490c8ad200c450635467f1bab1246039f11d1333d9a7f0be0d7a8e4f45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ee61e490c8ad200c450635467f1bab1246039f11d1333d9a7f0be0d7a8e4f45","first_computed_at":"2026-07-05T11:27:36.161374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:36.161374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6FV8E4d5XKGMEHyAJUVkUbe5SjGyyyMhUx6gfuQO5yrW5KWkVrU5LikNrf2J/cLXUhDOAKV8JCb+VhVWucaHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:36.161857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b84183592fb014fd6e20b9870a32828282c78db216c32bbd4452df76ac12f68a","sha256:90194ad64d8f9d1aae042e672dc3b62f9251b674a78d798df52cdba72aac491f"],"state_sha256":"7dd4fb560f8b8ef787179a5945251bd3a8397da4c2f2837ec37259a0cc230d60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uyByD162kWHe3d/bVvus6XNI5MQ4Gex2u+5vj/9S2Gsxuj4l8ZYMozEjuT8wOxJvo3Vw4ujWtc+znL1Mu9T7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:19:51.590848Z","bundle_sha256":"9132dc8d3082536016c35118e4449dd38dd4a860e9aa2b754b2bd4dc5818e77a"}}