{"id":"W4385570357","doi":"10.18653/v1/2023.findings-acl.533","title":"Fixed Input Parameterization for Efficient Prompting","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Computer science; Inference; Task (project management); Parsing; Conversation; Fixed point; Overhead (engineering); Artificial intelligence; Property (philosophy); Theoretical computer science; Natural language processing; Programming language; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003768636,0.001781871,0.0014468,0.00055401,0.000879659,0.001731233,0.002973237,0.002343695,0.01518737],"category_scores_gemma":[0.03157652,0.0009077313,0.0009098597,0.0007439847,0.001787134,0.005832638,0.004221331,0.004835501,0.005216997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001114594,"about_ca_system_score_gemma":0.001810543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001331404,"about_ca_topic_score_gemma":0.001982087,"domain_scores_codex":[0.9963117,0.001880083,0.0002111957,0.0009221382,0.0004138096,0.0002610718],"domain_scores_gemma":[0.9884702,0.007629161,0.0003296927,0.002438561,0.0008506249,0.0002817549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002019468,0.0004740888,0.002822375,0.0009975989,0.00009580854,0.0007825626,0.002918364,0.1786299,0.05473718,0.1126733,0.02255262,0.6212967],"study_design_scores_gemma":[0.0001374342,0.0002016957,0.0003738211,0.00007958113,0.00003818446,0.0001830959,0.0003372621,0.819307,0.02396907,0.1388737,0.01643246,0.00006672362],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008183897,0.0001306611,0.9825362,0.000283876,0.00006831019,0.0001046114,0.0001776501,0.007283134,0.001231655],"genre_scores_gemma":[0.3682882,0.0001925771,0.6228871,0.0005883188,0.0001401449,0.0007314017,0.001084712,0.002013999,0.004073594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01518737,"threshold_uncertainty_score":0.05080688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0487086013721159,"score_gpt":0.2818651687223084,"score_spread":0.2331565673501925,"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."}}