{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VHLBUSLBMJ346ZSG2RIIG5HCV6","short_pith_number":"pith:VHLBUSLB","canonical_record":{"source":{"id":"2410.08800","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:34:24Z","cross_cats_sorted":[],"title_canon_sha256":"1165b932aa3249e94f5ceccf4995c2af23010be714384d9b940cabeaa084d5dd","abstract_canon_sha256":"ed9f562e60e98cb66a4a43d203936f7fdc1b6b8d6164ce5ec19814d500e9ba6f"},"schema_version":"1.0"},"canonical_sha256":"a9d61a49616277cf6646d4508374e2af8152d71b686e715575ad422d8a636703","source":{"kind":"arxiv","id":"2410.08800","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08800","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08800v4","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08800","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"VHLBUSLBMJ34","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"VHLBUSLBMJ346ZSG","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"VHLBUSLB","created_at":"2026-07-05T11:49:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VHLBUSLBMJ346ZSG2RIIG5HCV6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08800","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:34:24Z","cross_cats_sorted":[],"title_canon_sha256":"1165b932aa3249e94f5ceccf4995c2af23010be714384d9b940cabeaa084d5dd","abstract_canon_sha256":"ed9f562e60e98cb66a4a43d203936f7fdc1b6b8d6164ce5ec19814d500e9ba6f"},"schema_version":"1.0"},"canonical_sha256":"a9d61a49616277cf6646d4508374e2af8152d71b686e715575ad422d8a636703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:47.638217Z","signature_b64":"QtUCSpuuN2u/sgJ+0/sdOtddrOP17Q6n1G+kUrV7vICZ3J9L2MceNONqrBsnVZtxLOu0VSNlm2r99+xrimDaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d61a49616277cf6646d4508374e2af8152d71b686e715575ad422d8a636703","last_reissued_at":"2026-07-05T11:49:47.637725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:47.637725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08800","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJHxrl664RtuDG0sjxT0nx2PH4r/BCs4Gw/Flf6VHXTFo+I8rUisRu0xCQeKxPx74h81rPoAJE6KiHtXdbgeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:22.841221Z"},"content_sha256":"66d7d524eaf0a3058a27205600a8085253b99cbfce01e7ae1dd6e7c80eaf850f","schema_version":"1.0","event_id":"sha256:66d7d524eaf0a3058a27205600a8085253b99cbfce01e7ae1dd6e7c80eaf850f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VHLBUSLBMJ346ZSG2RIIG5HCV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Processing for the OpenGPT-X Model Family","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Schwirjow, Anirban Bhowmick, Benny J\\\"org Stein, Dennis Wegener, Fabian K\\\"uch, Farzad Naderi, Georg Rehm, Hammam Abdelwahab, Joachim k\\\"ohler, Johannes Leveling, Lennard Helmer, Luzian Hahn, Malte Ostendorff, Mehdi Ali, Michael Fromm, Mohamad Saif Agy, Nicolas Flores-Herr, Nicolo' Brandizzi, Pavel Denisov, Pedro Ortiz Suarez, Qasid Saleem, Richard Rutmann","submitted_at":"2024-10-11T13:34:24Z","abstract_excerpt":"This paper presents a comprehensive overview of the data preparation pipeline developed for the OpenGPT-X project, a large-scale initiative aimed at creating open and high-performance multilingual large language models (LLMs). The project goal is to deliver models that cover all major European languages, with a particular focus on real-world applications within the European Union. We explain all data processing steps, starting with the data selection and requirement definition to the preparation of the final filtered data. We distinguish between curated data and web data, as each of these cate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08800","kind":"arxiv","version":4},"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/2410.08800/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":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yRi2+6cQ1apbMijuPFJ6zKMIwCAU3RKG3Vadk1Gco5a5xfcNK1xLTXTA4TtkspTOisXPd+0YY2540GZ3GOcJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:22.841613Z"},"content_sha256":"4bf02b55a6d7d81f1d1b64faf05d0376e27c33e6130d85a00f89c45e48f2528c","schema_version":"1.0","event_id":"sha256:4bf02b55a6d7d81f1d1b64faf05d0376e27c33e6130d85a00f89c45e48f2528c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/bundle.json","state_url":"https://pith.science/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/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":"2026-07-08T19:10:22Z","links":{"resolver":"https://pith.science/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6","bundle":"https://pith.science/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/bundle.json","state":"https://pith.science/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHLBUSLBMJ346ZSG2RIIG5HCV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHLBUSLBMJ346ZSG2RIIG5HCV6","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":"ed9f562e60e98cb66a4a43d203936f7fdc1b6b8d6164ce5ec19814d500e9ba6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:34:24Z","title_canon_sha256":"1165b932aa3249e94f5ceccf4995c2af23010be714384d9b940cabeaa084d5dd"},"schema_version":"1.0","source":{"id":"2410.08800","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08800","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08800v4","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08800","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"VHLBUSLBMJ34","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"VHLBUSLBMJ346ZSG","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"VHLBUSLB","created_at":"2026-07-05T11:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:4bf02b55a6d7d81f1d1b64faf05d0376e27c33e6130d85a00f89c45e48f2528c","target":"graph","created_at":"2026-07-05T11:49:47Z","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/2410.08800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comprehensive overview of the data preparation pipeline developed for the OpenGPT-X project, a large-scale initiative aimed at creating open and high-performance multilingual large language models (LLMs). The project goal is to deliver models that cover all major European languages, with a particular focus on real-world applications within the European Union. We explain all data processing steps, starting with the data selection and requirement definition to the preparation of the final filtered data. We distinguish between curated data and web data, as each of these cate","authors_text":"Alexander Schwirjow, Anirban Bhowmick, Benny J\\\"org Stein, Dennis Wegener, Fabian K\\\"uch, Farzad Naderi, Georg Rehm, Hammam Abdelwahab, Joachim k\\\"ohler, Johannes Leveling, Lennard Helmer, Luzian Hahn, Malte Ostendorff, Mehdi Ali, Michael Fromm, Mohamad Saif Agy, Nicolas Flores-Herr, Nicolo' Brandizzi, Pavel Denisov, Pedro Ortiz Suarez, Qasid Saleem, Richard Rutmann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:34:24Z","title":"Data Processing for the OpenGPT-X Model Family"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08800","kind":"arxiv","version":4},"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":"sha256:66d7d524eaf0a3058a27205600a8085253b99cbfce01e7ae1dd6e7c80eaf850f","target":"record","created_at":"2026-07-05T11:49:47Z","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":"ed9f562e60e98cb66a4a43d203936f7fdc1b6b8d6164ce5ec19814d500e9ba6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:34:24Z","title_canon_sha256":"1165b932aa3249e94f5ceccf4995c2af23010be714384d9b940cabeaa084d5dd"},"schema_version":"1.0","source":{"id":"2410.08800","kind":"arxiv","version":4}},"canonical_sha256":"a9d61a49616277cf6646d4508374e2af8152d71b686e715575ad422d8a636703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9d61a49616277cf6646d4508374e2af8152d71b686e715575ad422d8a636703","first_computed_at":"2026-07-05T11:49:47.637725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:47.637725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QtUCSpuuN2u/sgJ+0/sdOtddrOP17Q6n1G+kUrV7vICZ3J9L2MceNONqrBsnVZtxLOu0VSNlm2r99+xrimDaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:47.638217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08800","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d7d524eaf0a3058a27205600a8085253b99cbfce01e7ae1dd6e7c80eaf850f","sha256:4bf02b55a6d7d81f1d1b64faf05d0376e27c33e6130d85a00f89c45e48f2528c"],"state_sha256":"aa3e236ce73e93e4dfa2c0ffe4676631f40622f17110afafd6e18220bedadcbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dK/F1NImYZcNzsDbb6bm2Ff2Rt0eCkuUZABnwNNdK17I3Zop+3ee4oYYkINGpyuEBPdPes4sXUmBqfFpFUaWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:10:22.843814Z","bundle_sha256":"5a4b07ef82f58dd171572ff7008016d9426109b92f1b3eaff20615f1fe714e2c"}}