{"id":"W4396828482","doi":"10.1145/3613904.3642462","title":"DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Undo; Computer science; Syntax; Interface (matter); Programming language; Reuse; Representation (politics); Code (set theory); Software; Human–computer interaction; Artificial intelligence; Operating system; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001735567,0.0001126981,0.0001047709,0.0001264905,0.00003261035,0.0003182138,0.0003674923,0.00002564192,0.0000496267],"category_scores_gemma":[0.000009069931,0.00008187399,0.00003178075,0.0003028782,0.000003427887,0.0007254446,0.0002243578,0.00009539937,0.0001492445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005717498,"about_ca_system_score_gemma":0.0000236052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134953,"about_ca_topic_score_gemma":0.0001818262,"domain_scores_codex":[0.9990336,0.00002560091,0.0001314598,0.0004146679,0.0001792804,0.0002153518],"domain_scores_gemma":[0.9994343,0.00004926398,0.00001273536,0.0004062923,0.00002499406,0.00007242742],"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":[0.00004927614,0.0001599096,0.0002649685,0.0001906329,0.0001617752,0.0003682525,0.06460266,0.1652887,0.007074587,0.4565526,0.004883036,0.3004036],"study_design_scores_gemma":[0.00006268227,0.00004003489,0.00003353157,0.0001114265,0.000003462505,0.00001345725,0.0000872294,0.9936064,0.002765422,0.0005596158,0.002582321,0.0001343547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03736861,0.0002290478,0.9268133,0.0008043441,0.0002601469,0.0001386263,0.000001415869,0.0006865892,0.03369792],"genre_scores_gemma":[0.9360222,0.000001496199,0.05947433,0.0002722415,0.00005004236,0.00001410249,0.000001085045,0.00001240814,0.004152095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8986536,"threshold_uncertainty_score":0.3338724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02170615330698138,"score_gpt":0.2853995418462698,"score_spread":0.2636933885392884,"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."}}