{"id":"W3014285644","doi":"10.48550/arxiv.2004.01735","title":"Unsupervised Domain Adaptation with Progressive Domain Augmentation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Domain (mathematical analysis); Computer science; Subspace topology; Exploit; Domain adaptation; Artificial intelligence; Adaptation (eye); Divergence (linguistics); Interpolation (computer graphics); Pattern recognition (psychology); Image (mathematics); Mathematics; Biology","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"],"consensus_categories":[],"category_scores_codex":[0.0002471604,0.0003970063,0.0003443426,0.0002618438,0.0002699931,0.0003169301,0.001210695,0.0002172624,0.00005410303],"category_scores_gemma":[0.00002187482,0.0004223362,0.0001461154,0.000923329,0.0001340867,0.0006982313,0.0006942485,0.0006278924,0.0001400001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002587716,"about_ca_system_score_gemma":0.000376792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004829605,"about_ca_topic_score_gemma":0.00002826083,"domain_scores_codex":[0.997447,0.00035756,0.0002650306,0.00130621,0.0002530832,0.0003711739],"domain_scores_gemma":[0.998206,0.00009493966,0.0004667315,0.0007391211,0.0002189418,0.0002743234],"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":[0.0003948944,0.0001755882,0.001965361,0.0001778947,0.0002905491,0.00160666,0.01280462,0.4386887,0.0003070625,0.5395071,0.0001696712,0.003911935],"study_design_scores_gemma":[0.003163412,0.0003496926,0.004210203,0.0002477687,0.00009174015,0.00001810031,0.005391822,0.8750631,0.0001115892,0.1088296,0.001476658,0.001046352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1279018,0.00004711236,0.8674359,0.0006464918,0.0002311199,0.0006180531,0.000008245426,0.0004410481,0.00267021],"genre_scores_gemma":[0.9235017,0.00002584963,0.0755877,0.0003463486,0.00007553904,0.000007191956,0.00009670659,0.00003115244,0.0003278165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7955999,"threshold_uncertainty_score":0.9998229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08486027176570617,"score_gpt":0.1941086992223512,"score_spread":0.109248427456645,"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."}}