{"id":"W7124303850","doi":"10.65109/kagr5160","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","year":2023,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Generalization; Task (project management); Inference; Principle of compositionality; sort; Suite; Task analysis","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004518845,0.0003003858,0.0003034873,0.0002533009,0.0005600962,0.0005448881,0.0008250613,0.0001649915,0.0004398169],"category_scores_gemma":[0.0001411215,0.0002851626,0.00009070439,0.001753076,0.0001527699,0.0003664172,0.0004331862,0.001171011,0.002593894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006536946,"about_ca_system_score_gemma":0.0001947255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004472513,"about_ca_topic_score_gemma":0.0002987857,"domain_scores_codex":[0.9968308,0.0003581913,0.0004320694,0.001052263,0.0007052376,0.0006214133],"domain_scores_gemma":[0.9980748,0.0005144627,0.0001863841,0.0008296494,0.00009581141,0.0002989335],"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":[0.0001143083,0.0005574574,0.147048,0.00005715647,0.0002884332,0.0001366076,0.02368986,0.145445,0.02949506,0.04483931,0.0002340147,0.6080948],"study_design_scores_gemma":[0.0004230558,0.0001811168,0.3013462,0.00005809874,0.00002592621,0.000004608683,0.0001635772,0.6964167,0.0004812855,0.0004685114,0.0001458654,0.0002849864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.598281,0.0000421404,0.389246,0.006760018,0.00008294958,0.0003653872,0.000005454806,0.001019402,0.004197648],"genre_scores_gemma":[0.9479504,0.0000268097,0.04976921,0.0002245458,0.0001969366,0.00007374989,0.0001256398,0.00003762656,0.001595102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6078098,"threshold_uncertainty_score":0.9999601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04760603091420795,"score_gpt":0.3014580807053827,"score_spread":0.2538520497911748,"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."}}