{"id":"W2142018130","doi":"","title":"DalTREC 2006 QA System Jellyfish: Regular Expressions Mark-and-Match Approach to Question Answering","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Question answering; Rewriting; Computer science; Jellyfish; Robustness (evolution); Regular expression; Artificial intelligence; Architecture; Natural language processing; Information retrieval; Programming language","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":[0.0006515023,0.0002547745,0.0003069803,0.0001569055,0.0002284028,0.0003975679,0.0008796937,0.0001455853,0.00000896307],"category_scores_gemma":[0.00007443455,0.0002429478,0.00005164683,0.0004793357,0.00004795579,0.0004680197,0.0004555756,0.0002377255,0.00004990365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001172348,"about_ca_system_score_gemma":0.0001105016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005412513,"about_ca_topic_score_gemma":0.00001408072,"domain_scores_codex":[0.9976109,0.0001545537,0.0004393385,0.0008218911,0.0005111584,0.0004621074],"domain_scores_gemma":[0.9984661,0.00008087745,0.0001265688,0.0009185041,0.0002039426,0.0002040503],"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":[0.00007617781,0.0001822281,0.002904245,0.0004997601,0.00002713872,0.00004332857,0.00175315,0.004411596,0.04124119,0.9222208,0.001984434,0.02465594],"study_design_scores_gemma":[0.0009714282,0.0001739885,0.01279231,0.001154964,0.00004165874,0.0001793395,0.0005128304,0.9509105,0.01932043,0.005679738,0.006831346,0.001431464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013721,0.0002055887,0.8785027,0.0003429191,0.0002681627,0.0003638913,0.000006237237,0.0004529113,0.0184855],"genre_scores_gemma":[0.9194544,0.000007220272,0.07863701,0.0000605569,0.0001387452,0.00001792687,0.000006881503,0.00001603429,0.001661222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9464989,"threshold_uncertainty_score":0.9907125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02211898084258234,"score_gpt":0.2386022074487429,"score_spread":0.2164832266061605,"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."}}