{"id":"W4385571010","doi":"10.18653/v1/2023.acl-demo.57","title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Interoperability; STELLA (programming language); Natural language processing; Artificial intelligence; Training set; Information retrieval; Face (sociological concept); World Wide Web; Linguistics; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000899619,0.00006624957,0.00008750273,0.00005481208,0.00009820375,0.0001896609,0.0006573384,0.00002282731,0.000004296543],"category_scores_gemma":[0.0001102258,0.00005914977,0.00001258655,0.0001643081,0.00001888306,0.001288934,0.0008682028,0.00006291131,0.00001192655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001304381,"about_ca_system_score_gemma":0.00003379826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003273273,"about_ca_topic_score_gemma":0.00003847672,"domain_scores_codex":[0.9990451,0.00003515616,0.0001490556,0.000463568,0.0001034634,0.0002036528],"domain_scores_gemma":[0.9990466,0.0001213648,0.00001631135,0.0007297128,0.00003282064,0.00005315709],"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":[0.000009217179,0.00001989308,0.0008028484,0.000102142,0.00001821338,0.000003211983,0.0373196,0.005117398,0.00311205,0.0279324,0.001162952,0.9244001],"study_design_scores_gemma":[0.0001244791,0.00002250115,0.0002833318,0.00001063817,0.000001005813,0.000001365461,0.001824233,0.9943444,0.0002997756,0.001731922,0.001283468,0.00007294636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1403683,0.000008729215,0.8561562,0.002581815,0.0001370979,0.0001733094,0.00000422884,0.0003613319,0.0002089584],"genre_scores_gemma":[0.9048478,0.000007937841,0.09470241,0.0001237293,0.00004666632,0.00001595862,0.00001782621,0.000006502089,0.0002311881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9892269,"threshold_uncertainty_score":0.2412058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5397407610899357,"score_gpt":0.3876501314400893,"score_spread":0.1520906296498464,"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."}}