{"id":"W3169425788","doi":"10.18653/v1/2021.repl4nlp-1.21","title":"Predicting the Success of Domain Adaptation in Text Similarity","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Exploit; Similarity (geometry); Domain (mathematical analysis); Adaptation (eye); Domain adaptation; Task (project management); Selection (genetic algorithm); Point (geometry); Artificial intelligence; Machine learning; Data mining; Psychology; Mathematics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001313526,0.0001688369,0.0002647756,0.0001409161,0.00009090423,0.0003047485,0.001154327,0.0001672725,0.00005878759],"category_scores_gemma":[0.0002211664,0.0001338098,0.0001069619,0.0004628634,0.00005893561,0.0002818883,0.001232213,0.0007401051,0.000003508453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005936836,"about_ca_system_score_gemma":0.0003078271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009288369,"about_ca_topic_score_gemma":0.001040667,"domain_scores_codex":[0.9979066,0.0004189398,0.000514105,0.0004853753,0.0004633717,0.0002116246],"domain_scores_gemma":[0.9983716,0.000367389,0.0003377813,0.0007162279,0.0001608568,0.00004615681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003028246,0.0003739695,0.1016092,0.0005368677,0.0001335362,0.00007966248,0.1008455,0.5548917,0.0006348671,0.1554388,0.0001501531,0.08527544],"study_design_scores_gemma":[0.0002956652,0.00001691438,0.08610523,0.0001964723,0.000006336486,0.000004398221,0.005237356,0.9015971,0.0002649804,0.005785988,0.0002768945,0.0002126883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1549735,0.0001973011,0.82862,0.001594935,0.0005046664,0.0002782677,0.000001851335,0.00009617078,0.01373336],"genre_scores_gemma":[0.9321064,0.00003214426,0.06733701,0.0002607956,0.0000399799,0.00002525637,0.0000136788,0.000008642905,0.0001760951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7771329,"threshold_uncertainty_score":0.5456607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03325727457945828,"score_gpt":0.2713782545948602,"score_spread":0.2381209800154019,"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."}}