{"id":"W6901668656","doi":"10.60692/dv6n0-s9c31","title":"Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Software deployment; Quality (philosophy); Order (exchange); Key (lock); Work (physics); Point (geometry)","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":[0.005556622,0.001648269,0.001328484,0.0009283425,0.0006143291,0.001511361,0.002132351,0.00185031,0.001812112],"category_scores_gemma":[0.02210219,0.0007271231,0.0007619105,0.0006302696,0.0008382805,0.003941148,0.001956934,0.003116448,0.001728321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001183852,"about_ca_system_score_gemma":0.001420592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009884802,"about_ca_topic_score_gemma":0.0114676,"domain_scores_codex":[0.9977413,0.001304211,0.00007299393,0.0005237024,0.0001790941,0.0001786312],"domain_scores_gemma":[0.9858504,0.01055332,0.0004687627,0.001583185,0.0009902648,0.0005540507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001441926,0.001859363,0.01570991,0.0004315056,0.0003104401,0.0001705809,0.00147831,0.5397608,0.008515023,0.002972371,0.01330492,0.4140448],"study_design_scores_gemma":[0.00004393583,0.0001494279,0.000608143,0.00001089153,0.00002040692,0.00001926532,0.00006372631,0.9952984,0.001526888,0.001666433,0.000579024,0.00001344676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3410911,0.001947579,0.6320547,0.001870354,0.0002259905,0.0003780674,0.0007972386,0.01550379,0.006131212],"genre_scores_gemma":[0.8977744,0.0001868891,0.09628406,0.0005312756,0.00009464144,0.0001778025,0.001478712,0.0003722576,0.003099998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009884802,"threshold_uncertainty_score":0.02938658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468337336507025,"score_gpt":0.2190784673812446,"score_spread":0.1943950940161743,"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."}}