{"id":"W4407684169","doi":"10.48550/arxiv.2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Sequence (biology); Binary number; Psychology; Computer science; Genetics; Mathematics; Biology; Arithmetic","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003037352,0.0003890162,0.0003208414,0.0002491859,0.0005421917,0.000182586,0.001744301,0.0002717678,0.00002829154],"category_scores_gemma":[0.00004513788,0.0003907657,0.0001704279,0.0005840178,0.0001146842,0.0003349642,0.001852278,0.000862103,0.00008529014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005654648,"about_ca_system_score_gemma":0.0004411897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009607227,"about_ca_topic_score_gemma":0.000004621858,"domain_scores_codex":[0.9972348,0.00008308153,0.0004436608,0.001325021,0.0004496144,0.0004638832],"domain_scores_gemma":[0.9978873,0.0001357584,0.0002815754,0.001435704,0.0001199297,0.0001397346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005264469,0.002027791,0.3055003,0.002273503,0.001003551,0.0002390851,0.008673216,0.01933897,0.005559825,0.3450296,0.30511,0.005191457],"study_design_scores_gemma":[0.001464008,0.0006740181,0.2308613,0.005868923,0.0002168793,0.00005582203,0.0004650988,0.5466546,0.004588713,0.1217087,0.08358672,0.003855241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3075095,0.0004135676,0.6398451,0.03793203,0.002429603,0.002306706,0.0002795711,0.001600139,0.00768381],"genre_scores_gemma":[0.937929,0.0001919024,0.05061993,0.006004049,0.0005898926,0.0007872935,0.0001410276,0.00004828244,0.003688622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6304195,"threshold_uncertainty_score":0.9998544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1358133988045544,"score_gpt":0.3089118984965303,"score_spread":0.1730984996919759,"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."}}