{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3MWKJEFUUQVADUW7XUAHPDHS3","short_pith_number":"pith:Q3MWKJEF","schema_version":"1.0","canonical_sha256":"86d9652485a521500e96fde803bc6796df000f22df810f27cdf7e3e14053262e","source":{"kind":"arxiv","id":"2412.04092","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.04092","created_at":"2026-07-05T09:44:59.426649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04092v1","created_at":"2026-07-05T09:44:59.426649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04092","created_at":"2026-07-05T09:44:59.426649+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3MWKJEFUUQV","created_at":"2026-07-05T09:44:59.426649+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3MWKJEFUUQVADUW","created_at":"2026-07-05T09:44:59.426649+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3MWKJEF","created_at":"2026-07-05T09:44:59.426649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21203","citing_title":"When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3","json":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3.json","graph_json":"https://pith.science/api/pith-number/Q3MWKJEFUUQVADUW7XUAHPDHS3/graph.json","events_json":"https://pith.science/api/pith-number/Q3MWKJEFUUQVADUW7XUAHPDHS3/events.json","paper":"https://pith.science/paper/Q3MWKJEF"},"agent_actions":{"view_html":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3","download_json":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3.json","view_paper":"https://pith.science/paper/Q3MWKJEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04092&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3MWKJEFUUQVADUW7XUAHPDHS3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3MWKJEFUUQVADUW7XUAHPDHS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/action/storage_attestation","attest_author":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/action/author_attestation","sign_citation":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/action/citation_signature","submit_replication":"https://pith.science/pith/Q3MWKJEFUUQVADUW7XUAHPDHS3/action/replication_record"}},"created_at":"2026-07-05T09:44:59.426649+00:00","updated_at":"2026-07-05T09:44:59.426649+00:00"}