{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQUXHD4OXMMDA7MSQWPM6YJEEN","short_pith_number":"pith:VQUXHD4O","schema_version":"1.0","canonical_sha256":"ac29738f8ebb18307d92859ecf61242364083c2acf69477aaac8e95d67cfb703","source":{"kind":"arxiv","id":"2606.03773","version":1},"attestation_state":"computed","paper":{"title":"KletterMix: Climbing Toward High-Quality German Pretraining Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Goher Khan, Kristian Kersting, Maurice Kraus, Mehdi Ali, Michael Fromm, Ruben H\\\"arle, Sebastian Sztwiertnia","submitted_at":"2026-06-02T15:28:15Z","abstract_excerpt":"High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are often smaller, less carefully curated, weakly documented, and rarely validated through controlled training experiments. We introduce KletterMix, a high-quality German corpus for language model pretraining and annealing, designed as a reusable dataset artifact for the natural language processing and modeling community. KletterMix is built by translating a state-of-the-art English pretraining corpus into German while pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.03773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:28:15Z","cross_cats_sorted":[],"title_canon_sha256":"620a9dd87558776a762c0f6750779adc88de45e613c2a035acdca66aa1262c2d","abstract_canon_sha256":"b41b257932e9afecff23efd40eafc5f25f0dad2d1e6e163bf90b38fd3f878419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:02.089849Z","signature_b64":"CyTKefSV8RmdfzLssMwOAsqDdumVQDFrjqal3fCNGdZ68CxObWE4Pwr6I4rOFaRdVKu/9BXKDou7ERK9J7ieAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac29738f8ebb18307d92859ecf61242364083c2acf69477aaac8e95d67cfb703","last_reissued_at":"2026-06-03T02:06:02.089265Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:02.089265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KletterMix: Climbing Toward High-Quality German Pretraining Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Goher Khan, Kristian Kersting, Maurice Kraus, Mehdi Ali, Michael Fromm, Ruben H\\\"arle, Sebastian Sztwiertnia","submitted_at":"2026-06-02T15:28:15Z","abstract_excerpt":"High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are often smaller, less carefully curated, weakly documented, and rarely validated through controlled training experiments. We introduce KletterMix, a high-quality German corpus for language model pretraining and annealing, designed as a reusable dataset artifact for the natural language processing and modeling community. KletterMix is built by translating a state-of-the-art English pretraining corpus into German while pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03773","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/2606.03773/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.03773","created_at":"2026-06-03T02:06:02.089340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03773v1","created_at":"2026-06-03T02:06:02.089340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03773","created_at":"2026-06-03T02:06:02.089340+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQUXHD4OXMMD","created_at":"2026-06-03T02:06:02.089340+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQUXHD4OXMMDA7MS","created_at":"2026-06-03T02:06:02.089340+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQUXHD4O","created_at":"2026-06-03T02:06:02.089340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN","json":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN.json","graph_json":"https://pith.science/api/pith-number/VQUXHD4OXMMDA7MSQWPM6YJEEN/graph.json","events_json":"https://pith.science/api/pith-number/VQUXHD4OXMMDA7MSQWPM6YJEEN/events.json","paper":"https://pith.science/paper/VQUXHD4O"},"agent_actions":{"view_html":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN","download_json":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN.json","view_paper":"https://pith.science/paper/VQUXHD4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03773&json=true","fetch_graph":"https://pith.science/api/pith-number/VQUXHD4OXMMDA7MSQWPM6YJEEN/graph.json","fetch_events":"https://pith.science/api/pith-number/VQUXHD4OXMMDA7MSQWPM6YJEEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN/action/storage_attestation","attest_author":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN/action/author_attestation","sign_citation":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN/action/citation_signature","submit_replication":"https://pith.science/pith/VQUXHD4OXMMDA7MSQWPM6YJEEN/action/replication_record"}},"created_at":"2026-06-03T02:06:02.089340+00:00","updated_at":"2026-06-03T02:06:02.089340+00:00"}