{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00162155,0.001318336,0.00052771,0.0006811441,0.0003697385,0.001811091,0.001585319,0.001143029,0.02988053],"category_scores_gemma":[0.009630896,0.0006500559,0.001025457,0.0003176175,0.0007078818,0.003645554,0.004238026,0.001442036,0.008053534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004310088,"about_ca_system_score_gemma":0.0006332374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00115309,"about_ca_topic_score_gemma":0.001995977,"domain_scores_codex":[0.9991303,0.0003249548,0.00006855646,0.0001816054,0.0002360037,0.00005859082],"domain_scores_gemma":[0.9953879,0.002992155,0.0001570412,0.001029914,0.000258832,0.0001742886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001879217,0.0007230095,0.007748431,0.002621659,0.0002582679,0.002408862,0.01493859,0.01641168,0.1532809,0.06390765,0.1728807,0.5629411],"study_design_scores_gemma":[0.0004264021,0.0009361216,0.005061524,0.0006116605,0.0001775292,0.002473928,0.001372293,0.2969672,0.09997138,0.06622766,0.5254035,0.0003709068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01607268,0.0001376003,0.8440153,0.0002891357,0.00009698966,0.0002628183,0.001802941,0.1296578,0.007664812],"genre_scores_gemma":[0.2725409,0.0003303006,0.6685518,0.000678308,0.00008760599,0.001407137,0.005804064,0.02825978,0.02234019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02988053,"threshold_uncertainty_score":0.09996033,"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."}}