{"id":"W7082252827","doi":"10.48448/b0c9-0p64","title":"Enriching children’s stories with LLMs: Delivering multilingual data enrichment for children’s books at scale and across markets","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Metadata; Pipeline (software); Scale (ratio); Software deployment; Scalability; Quality (philosophy); Publishing; Linked data; Control (management)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001135741,0.0004767917,0.0004196448,0.0002145734,0.001019936,0.0004718547,0.003421665,0.000199326,0.00002996876],"category_scores_gemma":[0.0002657628,0.0004015942,0.0000394414,0.0004174996,0.0008290207,0.0004224371,0.004758805,0.0003064282,0.000004074523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001512188,"about_ca_system_score_gemma":0.000489651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006783738,"about_ca_topic_score_gemma":0.001225757,"domain_scores_codex":[0.9962993,0.00003492575,0.0003260146,0.001945697,0.0005301104,0.000863914],"domain_scores_gemma":[0.9973783,0.0001511911,0.0003159727,0.001778093,0.0001757058,0.0002007597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003570423,0.001152536,0.1476608,0.001916048,0.001348752,0.000116051,0.01645142,0.001910768,0.003872885,0.007402427,0.1366466,0.6811647],"study_design_scores_gemma":[0.0118133,0.001162817,0.07165976,0.00470601,0.0004534236,0.001561756,0.002289569,0.3472521,0.01475491,0.002385917,0.5322178,0.009742654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1197586,0.00855036,0.691277,0.003176013,0.003512821,0.00665816,0.002753453,0.002981441,0.1613321],"genre_scores_gemma":[0.3542389,0.0004096242,0.2964736,0.0008432815,0.001040812,0.0001392195,0.000747908,0.0001411422,0.3459655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6714221,"threshold_uncertainty_score":0.9998436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01564382290344489,"score_gpt":0.2788922544012628,"score_spread":0.2632484314978178,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}