{"id":"W4385612789","doi":"10.1145/3539618.3591925","title":"SIGIR 2023 Workshop on Retrieval Enhanced Machine Learning (REML @ SIGIR 2023)","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; ENCODE; Question answering; Context (archaeology); Robustness (evolution); Information retrieval","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006725989,0.0002382395,0.0002518606,0.0002512386,0.0002226632,0.0002100256,0.001040152,0.0001327667,0.0003265402],"category_scores_gemma":[0.0004098453,0.0002158804,0.0001118335,0.001568884,0.00002628367,0.0003321908,0.0005829094,0.0005575185,0.002861185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008116508,"about_ca_system_score_gemma":0.00007166995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008572889,"about_ca_topic_score_gemma":0.00005048989,"domain_scores_codex":[0.9975139,0.0001097767,0.0003643263,0.0007913233,0.0006123312,0.0006083296],"domain_scores_gemma":[0.9983965,0.0004790295,0.00009281799,0.0007985088,0.00007179377,0.0001613877],"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":[0.000147991,0.0002006925,0.0005188732,0.00009513211,0.0001444146,0.0003500527,0.002889359,0.2629527,0.04969187,0.05120977,0.04241078,0.5893884],"study_design_scores_gemma":[0.0004568565,0.0001092178,0.0002743698,0.00007167536,0.000004699204,0.000003924601,0.00009368214,0.9647765,0.009221117,0.001400842,0.02317604,0.000411075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05014895,0.0001514565,0.8641852,0.003337712,0.001487338,0.000289063,0.000002321495,0.001941739,0.07845619],"genre_scores_gemma":[0.6975615,0.000155703,0.01530215,0.0008642315,0.0003950519,0.00001456601,0.00001834405,0.00003938373,0.285649],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8488831,"threshold_uncertainty_score":0.9979152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03283412424060274,"score_gpt":0.2765557851906155,"score_spread":0.2437216609500127,"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."}}