{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FIJRYMAKUZ445YG7RBSSXBVXH3","short_pith_number":"pith:FIJRYMAK","canonical_record":{"source":{"id":"2509.05668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T10:12:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0ec803df574172a142045b94f9b6677be44cb5823409c8098ed476b1b07748b","abstract_canon_sha256":"fed92fdec03c12e92e5be34b9c006c79279392a9bf459f9b347189b24f923bba"},"schema_version":"1.0"},"canonical_sha256":"2a131c300aa679cee0df88652b86b73eded24c6bc3d11a1302d36752262a4021","source":{"kind":"arxiv","id":"2509.05668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05668","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05668v1","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05668","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"FIJRYMAKUZ44","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"FIJRYMAKUZ445YG7","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"FIJRYMAK","created_at":"2026-07-05T12:06:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FIJRYMAKUZ445YG7RBSSXBVXH3","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T10:12:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0ec803df574172a142045b94f9b6677be44cb5823409c8098ed476b1b07748b","abstract_canon_sha256":"fed92fdec03c12e92e5be34b9c006c79279392a9bf459f9b347189b24f923bba"},"schema_version":"1.0"},"canonical_sha256":"2a131c300aa679cee0df88652b86b73eded24c6bc3d11a1302d36752262a4021","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:22.100832Z","signature_b64":"KYl6q1EVqeCYAf6LnrDLI3cdze14Pc7nHm+WNnZT8nfREuyyW3ei7KmdveThIjoanRy0OCuymdPCGPpPZTpFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a131c300aa679cee0df88652b86b73eded24c6bc3d11a1302d36752262a4021","last_reissued_at":"2026-07-05T12:06:22.100322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:22.100322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05668","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":"2026-07-05T12:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XOPjqbSHynXz6jlND5edwclt2AZXOTRi++u8ZqVnkO+tuEGzRTDf54y8Z3YbpHuBjALd3Nhu0+kaOp1nOa69BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:57.768075Z"},"content_sha256":"8d21506a771c3e5541383f1f938127162f965465b6309fa6ed17d490c69ae598","schema_version":"1.0","event_id":"sha256:8d21506a771c3e5541383f1f938127162f965465b6309fa6ed17d490c69ae598"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FIJRYMAKUZ445YG7RBSSXBVXH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alice Zhang, Dmitry Gaynullin, Gokul Ramakrishnan, Hoi-Fong Mak, Jophin John, Michael Hoffmann, Nicolay J. Hammer, Stefan Schweter","submitted_at":"2025-09-06T10:12:52Z","abstract_excerpt":"We present Llama-GENBA-10B, a trilingual foundation model addressing English-centric bias in large language models. Built on Llama 3.1-8B and scaled to 10B parameters, Llama-GENBA-10B is continuously pretrained on 164B tokens (82B English, 82B German, and 80M Bavarian), balancing resources while preventing English dominance. Targeted at the German NLP community, the model also promotes Bavarian as a low-resource language. Development tackled four challenges: (1) curating a multilingual corpus despite Bavarian scarcity, (2) creating a unified tokenizer for English, German, and Bavarian, (3) opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05668","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/2509.05668/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":"2026-07-05T12:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/khYyqzN8X/AUh5iSWZhO6DD9O86jNSfohu03a/cdxXqVkB1mCpepts2zlIVYNpcD05A7bisqHWDae31qAWjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:57.768988Z"},"content_sha256":"d1ea5a87bef984ad2dfbcb71a81fe826fb9032c03c664ca3f66e4fb926690c19","schema_version":"1.0","event_id":"sha256:d1ea5a87bef984ad2dfbcb71a81fe826fb9032c03c664ca3f66e4fb926690c19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/bundle.json","state_url":"https://pith.science/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/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":"2026-08-04T10:22:57Z","links":{"resolver":"https://pith.science/pith/FIJRYMAKUZ445YG7RBSSXBVXH3","bundle":"https://pith.science/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/bundle.json","state":"https://pith.science/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIJRYMAKUZ445YG7RBSSXBVXH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIJRYMAKUZ445YG7RBSSXBVXH3","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":"fed92fdec03c12e92e5be34b9c006c79279392a9bf459f9b347189b24f923bba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T10:12:52Z","title_canon_sha256":"b0ec803df574172a142045b94f9b6677be44cb5823409c8098ed476b1b07748b"},"schema_version":"1.0","source":{"id":"2509.05668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05668","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05668v1","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05668","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"FIJRYMAKUZ44","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"FIJRYMAKUZ445YG7","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"FIJRYMAK","created_at":"2026-07-05T12:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:d1ea5a87bef984ad2dfbcb71a81fe826fb9032c03c664ca3f66e4fb926690c19","target":"graph","created_at":"2026-07-05T12:06:22Z","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/2509.05668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Llama-GENBA-10B, a trilingual foundation model addressing English-centric bias in large language models. Built on Llama 3.1-8B and scaled to 10B parameters, Llama-GENBA-10B is continuously pretrained on 164B tokens (82B English, 82B German, and 80M Bavarian), balancing resources while preventing English dominance. Targeted at the German NLP community, the model also promotes Bavarian as a low-resource language. Development tackled four challenges: (1) curating a multilingual corpus despite Bavarian scarcity, (2) creating a unified tokenizer for English, German, and Bavarian, (3) opt","authors_text":"Alice Zhang, Dmitry Gaynullin, Gokul Ramakrishnan, Hoi-Fong Mak, Jophin John, Michael Hoffmann, Nicolay J. Hammer, Stefan Schweter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T10:12:52Z","title":"Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05668","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":"sha256:8d21506a771c3e5541383f1f938127162f965465b6309fa6ed17d490c69ae598","target":"record","created_at":"2026-07-05T12:06:22Z","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":"fed92fdec03c12e92e5be34b9c006c79279392a9bf459f9b347189b24f923bba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T10:12:52Z","title_canon_sha256":"b0ec803df574172a142045b94f9b6677be44cb5823409c8098ed476b1b07748b"},"schema_version":"1.0","source":{"id":"2509.05668","kind":"arxiv","version":1}},"canonical_sha256":"2a131c300aa679cee0df88652b86b73eded24c6bc3d11a1302d36752262a4021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a131c300aa679cee0df88652b86b73eded24c6bc3d11a1302d36752262a4021","first_computed_at":"2026-07-05T12:06:22.100322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:22.100322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KYl6q1EVqeCYAf6LnrDLI3cdze14Pc7nHm+WNnZT8nfREuyyW3ei7KmdveThIjoanRy0OCuymdPCGPpPZTpFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:22.100832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d21506a771c3e5541383f1f938127162f965465b6309fa6ed17d490c69ae598","sha256:d1ea5a87bef984ad2dfbcb71a81fe826fb9032c03c664ca3f66e4fb926690c19"],"state_sha256":"f0cb868c10413760158ff8b07202c0c59956167a6f8d7abeef0f99a85de41b7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T5G8Jwb1uG+UueICAP3je2Hz/R/vMsztBB/mK54HwvNqrbHbPPQ9UKvRHI+THV4QOAdFnBr0HR4dXFrP+8aiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:22:57.775525Z","bundle_sha256":"70b5cf451ad059273259638b18cb61ff13218e3cdb0c0fdc2e39b94712c1c865"}}