{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q3MWKJEFUUQVADUW7XUAHPDHS3","short_pith_number":"pith:Q3MWKJEF","canonical_record":{"source":{"id":"2412.04092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T11:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"50855938bfea9094ef7ba7be46a41465e5bc66c46a7e614fb876d8862e229c5a","abstract_canon_sha256":"71010b29eb31f73ae5253901c0fdd3aaea4e46147f9059ef0f2248800f82cf09"},"schema_version":"1.0"},"canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","source":{"kind":"arxiv","id":"2412.04092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04092","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04092v1","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04092","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"Q3MWKJEFUUQV","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_16","alias_value":"Q3MWKJEFUUQVADUW","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_8","alias_value":"Q3MWKJEF","created_at":"2026-07-05T09:44:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q3MWKJEFUUQVADUW7XUAHPDHS3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T11:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"50855938bfea9094ef7ba7be46a41465e5bc66c46a7e614fb876d8862e229c5a","abstract_canon_sha256":"71010b29eb31f73ae5253901c0fdd3aaea4e46147f9059ef0f2248800f82cf09"},"schema_version":"1.0"},"canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:59.427031Z","signature_b64":"PzCVOj0cV7gmtAiQmWLZFTnq3mAnWdzz/3U15JqIuEfcMHPNfqn+vCvw0vTekF1snKn7Pdcr4/GGhngMOPJtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","last_reissued_at":"2026-07-05T09:44:59.426596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:59.426596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04092","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":"2026-07-05T09:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYoppCfqDsk6RZPhaVYNRnqVQrrrmocSm3tU5SqB8Avd7ObYfrV93qlQjlnuhoJ1Fxn4Yd+fADCP3vMgv7PyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:08.809217Z"},"content_sha256":"8d766600e1a262ebdf11146b9fa619da504e0620e929017f378c9d10c7e0b2a3","schema_version":"1.0","event_id":"sha256:8d766600e1a262ebdf11146b9fa619da504e0620e929017f378c9d10c7e0b2a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q3MWKJEFUUQVADUW7XUAHPDHS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GEITje 7B Ultra: A Conversational Model for Dutch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bram Vanroy","submitted_at":"2024-12-05T11:56:48Z","abstract_excerpt":"Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference align"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04092","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/2412.04092/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":"2026-07-05T09:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzQKFqs9whZNC25ghuOCJzJBCc3Y+2G8n74/JAdks9QKzOWwNKRg+xvXS7m2x5u2jrAlSg/irCmEj/kiF+EXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:08.809808Z"},"content_sha256":"3cc4a9d4ae19c1adb9e5aac568bb5da2ad12cd16f7d35f35c6b1b7552b2caad5","schema_version":"1.0","event_id":"sha256:3cc4a9d4ae19c1adb9e5aac568bb5da2ad12cd16f7d35f35c6b1b7552b2caad5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/bundle.json","state_url":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/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":"2026-08-09T03:00:08Z","links":{"resolver":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3","bundle":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/bundle.json","state":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3MWKJEFUUQVADUW7XUAHPDHS3","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":"71010b29eb31f73ae5253901c0fdd3aaea4e46147f9059ef0f2248800f82cf09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T11:56:48Z","title_canon_sha256":"50855938bfea9094ef7ba7be46a41465e5bc66c46a7e614fb876d8862e229c5a"},"schema_version":"1.0","source":{"id":"2412.04092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04092","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04092v1","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04092","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"Q3MWKJEFUUQV","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_16","alias_value":"Q3MWKJEFUUQVADUW","created_at":"2026-07-05T09:44:59Z"},{"alias_kind":"pith_short_8","alias_value":"Q3MWKJEF","created_at":"2026-07-05T09:44:59Z"}],"graph_snapshots":[{"event_id":"sha256:3cc4a9d4ae19c1adb9e5aac568bb5da2ad12cd16f7d35f35c6b1b7552b2caad5","target":"graph","created_at":"2026-07-05T09:44:59Z","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/2412.04092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference align","authors_text":"Bram Vanroy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T11:56:48Z","title":"GEITje 7B Ultra: A Conversational Model for Dutch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04092","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":"sha256:8d766600e1a262ebdf11146b9fa619da504e0620e929017f378c9d10c7e0b2a3","target":"record","created_at":"2026-07-05T09:44:59Z","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":"71010b29eb31f73ae5253901c0fdd3aaea4e46147f9059ef0f2248800f82cf09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T11:56:48Z","title_canon_sha256":"50855938bfea9094ef7ba7be46a41465e5bc66c46a7e614fb876d8862e229c5a"},"schema_version":"1.0","source":{"id":"2412.04092","kind":"arxiv","version":1}},"canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","first_computed_at":"2026-07-05T09:44:59.426596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:59.426596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PzCVOj0cV7gmtAiQmWLZFTnq3mAnWdzz/3U15JqIuEfcMHPNfqn+vCvw0vTekF1snKn7Pdcr4/GGhngMOPJtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:59.427031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d766600e1a262ebdf11146b9fa619da504e0620e929017f378c9d10c7e0b2a3","sha256:3cc4a9d4ae19c1adb9e5aac568bb5da2ad12cd16f7d35f35c6b1b7552b2caad5"],"state_sha256":"5281f279986510a89a48a884da43d5e9b69ba5348e71d3f001695488b82a5e43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ok5x/RPfu4qDMn+h45ZWpOX1pJCNio2kvrmMY8SrF2cqy4aqRlCamzkGZ+cTnbo42IrP1z2s1mWTt/5ZjadIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:00:08.813576Z","bundle_sha256":"e924823a9707bbe0effb309263246b50d8c6b6656099c466b57c028fee50c0dc"}}