{"id":"W4404782650","doi":"10.18653/v1/2024.emnlp-main.579","title":"MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung","keywords":"Granularity; Generalization; Computer science; Domain (mathematical analysis); Labrador Retriever; Mathematics; Medicine; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003849448,0.0019923,0.002316948,0.008174028,0.0008501881,0.001967653,0.002367752,0.001761817,0.003157591],"category_scores_gemma":[0.01102905,0.0005205763,0.001607206,0.004890125,0.001100798,0.004994338,0.004282049,0.001358167,0.003601641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008244982,"about_ca_system_score_gemma":0.001082466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00366089,"about_ca_topic_score_gemma":0.00564991,"domain_scores_codex":[0.9967855,0.000788248,0.0002594742,0.0009537389,0.000979535,0.0002334414],"domain_scores_gemma":[0.994531,0.002130946,0.0003517154,0.002120136,0.0006445349,0.0002217472],"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":[0.0009930447,0.0008058872,0.008760625,0.001292687,0.0004495943,0.0004127586,0.001006995,0.02800388,0.08326381,0.003971917,0.0259537,0.8450852],"study_design_scores_gemma":[0.0004433077,0.001552408,0.01423854,0.0001321773,0.0005932113,0.002489648,0.001153231,0.8193194,0.09422994,0.02365788,0.04187899,0.0003112771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2096211,0.0080451,0.6953347,0.0007303553,0.0002250578,0.0008842253,0.004082026,0.07341406,0.007663392],"genre_scores_gemma":[0.4657717,0.001488127,0.5111461,0.0006881702,0.0003115146,0.0004616155,0.01170432,0.002124534,0.00630394],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008174028,"threshold_uncertainty_score":0.02035809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04566579330471872,"score_gpt":0.2979242531118234,"score_spread":0.2522584598071047,"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."}}