{"meta":{"query_hash":"2d56ba59d3cf","filters":{"venue":"Findings of the Association for Computational Linguistics: NAACL 2022"},"cohort_total":2,"direct_labels_cover":0,"predictions_cover":2,"exported":2,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/2d56ba59d3cf","api":"https://metacan.xera.ac/api/v1/cohort?venue=Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2022"},"results":[{"id":"W3206996280","doi":"10.18653/v1/2022.findings-naacl.184","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: NAACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Question answering; Computer science; Open domain; Task (project management); Language model; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Scale (ratio); Training set; Information retrieval; Resource (disambiguation); Natural language; Natural language understanding","score_opus":0.024946483409200453,"score_gpt":0.2847366473702726,"score_spread":0.25979016396107213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206996280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068358104,0.00003412822,0.9847167,0.0011068481,0.0019262165,0.0007326242,0.0043962738,0.000086558655,0.00016481653],"genre_scores_gemma":[0.6542889,0.0000011739432,0.34105587,0.00041362908,0.00050797884,0.00014450602,0.0018020875,0.00002928549,0.0017565537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979905,0.00006810661,0.00050169433,0.00039647013,0.00075004215,0.00029319385],"domain_scores_gemma":[0.9977671,0.00082714757,0.0006082441,0.000288816,0.00044907196,0.000059604026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014146791,0.00014307353,0.0002235931,0.00013874548,0.0006715293,0.00009700989,0.0010011601,0.000057813955,0.0000071266327],"category_scores_gemma":[0.0030261376,0.00015589404,0.0001669454,0.0003154786,0.00001291988,0.000109221364,0.0005358108,0.00020585288,0.0000012554669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021679149,0.000038670503,0.00089946575,0.00002668462,0.000042194824,1.0055779e-7,0.00093372125,0.864004,0.0001357318,0.11659237,0.016951872,0.00035348564],"study_design_scores_gemma":[0.00069178926,0.000056693294,0.00050956896,0.000016192565,0.000032062846,0.0000012139351,0.00003401504,0.8796859,0.00007783811,0.09314414,0.025600322,0.0001502648],"about_ca_topic_score_codex":0.000031861386,"about_ca_topic_score_gemma":0.000007763039,"teacher_disagreement_score":0.6474531,"about_ca_system_score_codex":0.0005716553,"about_ca_system_score_gemma":0.00054141,"threshold_uncertainty_score":0.63571745},"labels":[],"label_agreement":null},{"id":"W4287889735","doi":"10.18653/v1/2022.findings-naacl.151","title":"Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: NAACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Massachusetts Green High Performance Computing Center; Leukemia and Lymphoma Society of Canada; National Science Foundation","keywords":"Computer science; Energy consumption; Inference; Pace; Cloud computing; Transformer; Efficient energy use; Machine learning; Artificial intelligence; Risk analysis (engineering); Engineering","score_opus":0.03769841022498763,"score_gpt":0.29149186124092274,"score_spread":0.2537934510159351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287889735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043525607,0.0000808332,0.9853062,0.0035634085,0.003013422,0.00097071525,0.0019974427,0.00011189729,0.000603544],"genre_scores_gemma":[0.7491319,0.0000013941353,0.24559075,0.0005633378,0.00034517018,0.0004908889,0.0005457811,0.000038374987,0.003292366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997807,0.00014208787,0.0006344541,0.00049751514,0.00057206437,0.0003468265],"domain_scores_gemma":[0.9945863,0.0033869925,0.0006935187,0.00035266564,0.0009290152,0.000051494084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020831956,0.00016554055,0.00028869006,0.00022178497,0.0010759339,0.000096623764,0.00088139594,0.00007044457,0.000017617967],"category_scores_gemma":[0.006130092,0.00017766705,0.0003372334,0.00039630142,0.000018035855,0.00011460059,0.00036957714,0.00015819726,3.5112274e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007566023,0.000057400677,0.0001478751,0.000031869196,0.000107910106,1.8402208e-7,0.0036892083,0.3642886,0.00008077651,0.6192699,0.010217081,0.0020334926],"study_design_scores_gemma":[0.0008835406,0.00012652656,0.000069065754,0.000020222336,0.00004153758,0.0000017388137,0.0002668192,0.7034373,0.0001863669,0.25807005,0.03671907,0.0001777189],"about_ca_topic_score_codex":0.000043990764,"about_ca_topic_score_gemma":0.0000065157965,"teacher_disagreement_score":0.74477935,"about_ca_system_score_codex":0.0008206541,"about_ca_system_score_gemma":0.00037193808,"threshold_uncertainty_score":0.8275323},"labels":[],"label_agreement":null}]}