{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WXIEKTEGGHFHFIFW7S34HQUJRT","short_pith_number":"pith:WXIEKTEG","canonical_record":{"source":{"id":"2310.07321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T09:09:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f05aa1e0710fe4dd7e4fd8243085fc145df8da2f623b04704599974267b26c7c","abstract_canon_sha256":"3f8a737359e839d8a7455305ba76fe073810ec2f56607bdfeabc5389c1b48529"},"schema_version":"1.0"},"canonical_sha256":"b5d0454c8631ca72a0b6fcb7c3c2898cf07e5c9051d57dba31f8c9a1558bc4fa","source":{"kind":"arxiv","id":"2310.07321","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07321","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07321v2","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07321","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"WXIEKTEGGHFH","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"WXIEKTEGGHFHFIFW","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"WXIEKTEG","created_at":"2026-07-05T07:00:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WXIEKTEGGHFHFIFW7S34HQUJRT","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T09:09:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f05aa1e0710fe4dd7e4fd8243085fc145df8da2f623b04704599974267b26c7c","abstract_canon_sha256":"3f8a737359e839d8a7455305ba76fe073810ec2f56607bdfeabc5389c1b48529"},"schema_version":"1.0"},"canonical_sha256":"b5d0454c8631ca72a0b6fcb7c3c2898cf07e5c9051d57dba31f8c9a1558bc4fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:29.845938Z","signature_b64":"F9/M+PydPEWPkCoykT+yRybKPxEsIFSuXgytIexmjMZYRvs+d4ar0NgbF7xEGZQ8KuQQ/8EVGHToGbGhlQovAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d0454c8631ca72a0b6fcb7c3c2898cf07e5c9051d57dba31f8c9a1558bc4fa","last_reissued_at":"2026-07-05T07:00:29.845555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:29.845555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07321","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VV49/iz+vHxO9RCm7u/SX78ta11eK6w6NZoWM9st5RT89Dgwjaq8LqSyQAkmkejclCt83dRWkf4CTNHHuw+SDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:43:51.161059Z"},"content_sha256":"f3826df30eb6a10292066fe8e80e69b886f39538a4f3dc05671ac7ee1b6efcf1","schema_version":"1.0","event_id":"sha256:f3826df30eb6a10292066fe8e80e69b886f39538a4f3dc05671ac7ee1b6efcf1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WXIEKTEGGHFHFIFW7S34HQUJRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Impact of Cross-Domain Data on German Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmad Idrissi-Yaghir, Amin Dada, Aokun Chen, Cheng Peng, Christoph M. Friedrich, Constantin Marc Seibold, Daniel Truhn, Jan Egger, Jens Kleesiek, Jiang Bian, Jianning Li, Kaleb E Smith, Lars Heiliger, Xi Yang, Yonghui Wu","submitted_at":"2023-10-11T09:09:55Z","abstract_excerpt":"Traditionally, large language models have been either trained on general web crawls or domain-specific data. However, recent successes of generative large language models, have shed light on the benefits of cross-domain datasets. To examine the significance of prioritizing data diversity over quality, we present a German dataset comprising texts from five domains, along with another dataset aimed at containing high-quality data. Through training a series of models ranging between 122M and 750M parameters on both datasets, we conduct a comprehensive benchmark on multiple downstream tasks. Our f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07321","kind":"arxiv","version":2},"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/2310.07321/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":"2026-07-05T07:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHd3yrTfxPXByx3JX0YFYyc2DLPb0RVAmnpp7STl9bVU6BSWmu58oLECqc3Im1nhPZruGQHii+/auLYGMbW7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:43:51.161452Z"},"content_sha256":"2227ba16423ff3ea0282c6ace52bb090fcd282299fb0961dd354850019cc57cc","schema_version":"1.0","event_id":"sha256:2227ba16423ff3ea0282c6ace52bb090fcd282299fb0961dd354850019cc57cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/bundle.json","state_url":"https://pith.science/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/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":"2026-07-07T09:43:51Z","links":{"resolver":"https://pith.science/pith/WXIEKTEGGHFHFIFW7S34HQUJRT","bundle":"https://pith.science/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/bundle.json","state":"https://pith.science/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXIEKTEGGHFHFIFW7S34HQUJRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WXIEKTEGGHFHFIFW7S34HQUJRT","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":"3f8a737359e839d8a7455305ba76fe073810ec2f56607bdfeabc5389c1b48529","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T09:09:55Z","title_canon_sha256":"f05aa1e0710fe4dd7e4fd8243085fc145df8da2f623b04704599974267b26c7c"},"schema_version":"1.0","source":{"id":"2310.07321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07321","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07321v2","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07321","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"WXIEKTEGGHFH","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"WXIEKTEGGHFHFIFW","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"WXIEKTEG","created_at":"2026-07-05T07:00:29Z"}],"graph_snapshots":[{"event_id":"sha256:2227ba16423ff3ea0282c6ace52bb090fcd282299fb0961dd354850019cc57cc","target":"graph","created_at":"2026-07-05T07:00:29Z","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/2310.07321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditionally, large language models have been either trained on general web crawls or domain-specific data. However, recent successes of generative large language models, have shed light on the benefits of cross-domain datasets. To examine the significance of prioritizing data diversity over quality, we present a German dataset comprising texts from five domains, along with another dataset aimed at containing high-quality data. Through training a series of models ranging between 122M and 750M parameters on both datasets, we conduct a comprehensive benchmark on multiple downstream tasks. Our f","authors_text":"Ahmad Idrissi-Yaghir, Amin Dada, Aokun Chen, Cheng Peng, Christoph M. Friedrich, Constantin Marc Seibold, Daniel Truhn, Jan Egger, Jens Kleesiek, Jiang Bian, Jianning Li, Kaleb E Smith, Lars Heiliger, Xi Yang, Yonghui Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T09:09:55Z","title":"On the Impact of Cross-Domain Data on German Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07321","kind":"arxiv","version":2},"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:f3826df30eb6a10292066fe8e80e69b886f39538a4f3dc05671ac7ee1b6efcf1","target":"record","created_at":"2026-07-05T07:00:29Z","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":"3f8a737359e839d8a7455305ba76fe073810ec2f56607bdfeabc5389c1b48529","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T09:09:55Z","title_canon_sha256":"f05aa1e0710fe4dd7e4fd8243085fc145df8da2f623b04704599974267b26c7c"},"schema_version":"1.0","source":{"id":"2310.07321","kind":"arxiv","version":2}},"canonical_sha256":"b5d0454c8631ca72a0b6fcb7c3c2898cf07e5c9051d57dba31f8c9a1558bc4fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5d0454c8631ca72a0b6fcb7c3c2898cf07e5c9051d57dba31f8c9a1558bc4fa","first_computed_at":"2026-07-05T07:00:29.845555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:29.845555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F9/M+PydPEWPkCoykT+yRybKPxEsIFSuXgytIexmjMZYRvs+d4ar0NgbF7xEGZQ8KuQQ/8EVGHToGbGhlQovAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:29.845938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3826df30eb6a10292066fe8e80e69b886f39538a4f3dc05671ac7ee1b6efcf1","sha256:2227ba16423ff3ea0282c6ace52bb090fcd282299fb0961dd354850019cc57cc"],"state_sha256":"630fee76b8de845bf017e8e4d60133a0a3397b6caf9c03a183317015665b9998"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hzb9CbdhWfC75nCX9TY2y0gkk4e4osk0HBbYcBSfREfxbrdeg0iOMa+KAwEz06P5VlMCGrA3QmO2geERDpu8Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:43:51.164518Z","bundle_sha256":"b3f3a9b98d6781430b574559a3b43a138793c8ccbb24322cdd207964151b94ed"}}