{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003119764,0.001502009,0.001471043,0.001993046,0.001506759,0.00290935,0.003250413,0.002539928,0.02926896],"category_scores_gemma":[0.008422912,0.0008645592,0.001359007,0.002151828,0.0008940072,0.007555256,0.007705802,0.002381523,0.02166714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006702298,"about_ca_system_score_gemma":0.001367529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006008429,"about_ca_topic_score_gemma":0.01160022,"domain_scores_codex":[0.9982974,0.0006120621,0.00009844692,0.0004705218,0.0003662452,0.0001552837],"domain_scores_gemma":[0.9977509,0.001182486,0.00004449562,0.0006872626,0.0001861045,0.0001486916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002076013,0.0003297969,0.001578409,0.0004064179,0.0002089922,0.0004111368,0.001060229,0.007001458,0.009173021,0.01625773,0.4090322,0.5524646],"study_design_scores_gemma":[0.0007047473,0.0003973615,0.001907873,0.0001868898,0.000176102,0.0007254737,0.001199125,0.5786635,0.03138105,0.07437218,0.3100746,0.0002110096],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01729388,0.002000154,0.4845376,0.002310641,0.0009281798,0.0003782498,0.009772996,0.4639393,0.01883898],"genre_scores_gemma":[0.1906146,0.001372535,0.6955846,0.002193152,0.0004125114,0.001148203,0.04982352,0.02977654,0.02907426],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02926896,"threshold_uncertainty_score":0.0979144,"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."}}