{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VQUXHD4OXMMDA7MSQWPM6YJEEN","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":"b41b257932e9afecff23efd40eafc5f25f0dad2d1e6e163bf90b38fd3f878419","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:28:15Z","title_canon_sha256":"620a9dd87558776a762c0f6750779adc88de45e613c2a035acdca66aa1262c2d"},"schema_version":"1.0","source":{"id":"2606.03773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03773","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03773v1","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03773","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"VQUXHD4OXMMD","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"VQUXHD4OXMMDA7MS","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"VQUXHD4O","created_at":"2026-06-03T02:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:f93b891f99ed8cfd3447851f9eae80db3f9f68a7b327c062544127e98e965cff","target":"graph","created_at":"2026-06-03T02:06:02Z","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/2606.03773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abbas Goher Khan, Kristian Kersting, Maurice Kraus, Mehdi Ali, Michael Fromm, Ruben H\\\"arle, Sebastian Sztwiertnia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:28:15Z","title":"KletterMix: Climbing Toward High-Quality German Pretraining Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03773","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":"sha256:62ca3703ab811d7fa0c99f30222cd968c649b34bc7c88f2d9c962c1a0c1aaf8c","target":"record","created_at":"2026-06-03T02:06:02Z","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":"b41b257932e9afecff23efd40eafc5f25f0dad2d1e6e163bf90b38fd3f878419","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:28:15Z","title_canon_sha256":"620a9dd87558776a762c0f6750779adc88de45e613c2a035acdca66aa1262c2d"},"schema_version":"1.0","source":{"id":"2606.03773","kind":"arxiv","version":1}},"canonical_sha256":"ac29738f8ebb18307d92859ecf61242364083c2acf69477aaac8e95d67cfb703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac29738f8ebb18307d92859ecf61242364083c2acf69477aaac8e95d67cfb703","first_computed_at":"2026-06-03T02:06:02.089265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:02.089265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CyTKefSV8RmdfzLssMwOAsqDdumVQDFrjqal3fCNGdZ68CxObWE4Pwr6I4rOFaRdVKu/9BXKDou7ERK9J7ieAw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:02.089849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ca3703ab811d7fa0c99f30222cd968c649b34bc7c88f2d9c962c1a0c1aaf8c","sha256:f93b891f99ed8cfd3447851f9eae80db3f9f68a7b327c062544127e98e965cff"],"state_sha256":"e939cdb13c5e82c06700159669f74fa3dd116527dd039882ce360b03c62194f2"}