{"meta":{"query_hash":"65a47c5cc863","filters":{"venue":"2021 International Conference on Data Mining Workshops (ICDMW)"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"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/65a47c5cc863","api":"https://metacan.xera.ac/api/v1/cohort?venue=2021+International+Conference+on+Data+Mining+Workshops+%28ICDMW%29"},"results":[{"id":"W3203427563","doi":"10.1109/icdmw53433.2021.00085","title":"Determining Standard Occupational Classification Codes from Job Descriptions in Immigration Petitions","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Data Mining Workshops (ICDMW)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Becton Dickinson (Canada)","funders":"","keywords":"Computer science; Code (set theory); Task (project management); Variety (cybernetics); Quality (philosophy); Natural language processing; Machine learning; Artificial intelligence; Programming language; Engineering","score_opus":0.31506050833024407,"score_gpt":0.43601401014173113,"score_spread":0.12095350181148706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203427563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7273029,0.00017044513,0.0824304,0.029293576,0.005872314,0.00067247316,0.0060367654,0.00025213003,0.147969],"genre_scores_gemma":[0.978192,0.0004218781,0.012675734,0.0002997789,0.00072700833,0.000070002985,0.006057588,0.00002057477,0.0015354805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966445,0.00041789774,0.00068652607,0.00084468146,0.0010394767,0.0003669003],"domain_scores_gemma":[0.9971992,0.00081455644,0.0002560047,0.0007347053,0.0008547344,0.00014084819],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00087571185,0.0002136661,0.00024640246,0.00024656983,0.00059065013,0.00075472536,0.0011439703,0.00020532311,0.008497138],"category_scores_gemma":[0.0025093018,0.000257495,0.000068273526,0.0005895389,0.000351401,0.0013382483,0.0002696857,0.00038863355,0.00022932087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002508867,0.00042179046,0.15459882,0.0000067301735,0.0001539712,0.00012194967,0.014718037,0.00042983884,0.004389901,0.6442839,0.010768029,0.16985613],"study_design_scores_gemma":[0.001510942,0.00018755502,0.19761316,0.0030805045,0.00020081873,0.000018025012,0.21533236,0.35351244,0.002737569,0.039368514,0.18384868,0.0025894162],"about_ca_topic_score_codex":0.0012286062,"about_ca_topic_score_gemma":0.056699205,"teacher_disagreement_score":0.6049154,"about_ca_system_score_codex":0.0004603278,"about_ca_system_score_gemma":0.001239477,"threshold_uncertainty_score":0.9999877},"labels":[],"label_agreement":null},{"id":"W4205504967","doi":"10.1109/icdmw53433.2021.00084","title":"Detection of Similar Legal Cases on Personal Injury","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Data Mining Workshops (ICDMW)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Personal injury; Computer science; Plaintiff; Compensation (psychology); Similarity (geometry); Artificial intelligence; Deep learning; Variation (astronomy); Legal research; Feature (linguistics); Style (visual arts); Data science; Natural language processing; Information retrieval; Psychology; Law; Social psychology; Political science; Linguistics","score_opus":0.2099168421139607,"score_gpt":0.4157965502019689,"score_spread":0.20587970808800818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205504967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7660227,0.00015953278,0.0035049291,0.016783098,0.008053172,0.00041069434,0.0017721184,0.00015690172,0.20313686],"genre_scores_gemma":[0.9932322,0.00021354502,0.0007103154,0.00042399578,0.00086513255,0.000013031969,0.00035088827,0.000018858438,0.0041720388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971377,0.00028279424,0.00045615365,0.00068123126,0.0011081602,0.00033392545],"domain_scores_gemma":[0.9975883,0.0007569057,0.00023831666,0.0006027681,0.0006820873,0.00013166231],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075934833,0.00019982831,0.00024262916,0.00015744304,0.00036345152,0.00029862806,0.0011390022,0.00017848662,0.007586548],"category_scores_gemma":[0.0036612442,0.00021945933,0.0000929633,0.00040544636,0.0004273185,0.00065411517,0.0003460924,0.0003789177,0.00019130814],"study_design_candidate":"not_applicable","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":[0.00079803914,0.0008303061,0.0022424036,0.000021182854,0.00033366,0.00054059946,0.00909053,0.00017066406,0.013963619,0.3688583,0.015503077,0.5876476],"study_design_scores_gemma":[0.000811457,0.0011204539,0.0025306689,0.002622366,0.00021719198,0.00008758644,0.11827631,0.068587765,0.12070595,0.0048827967,0.677784,0.0023734465],"about_ca_topic_score_codex":0.0007395303,"about_ca_topic_score_gemma":0.0040586987,"teacher_disagreement_score":0.6622809,"about_ca_system_score_codex":0.00017716267,"about_ca_system_score_gemma":0.0006403852,"threshold_uncertainty_score":0.99332064},"labels":[],"label_agreement":null},{"id":"W4205619838","doi":"10.1109/icdmw53433.2021.00020","title":"Sentiment Analysis Using Part-of-Speech-Based Feature Extraction and Game-Theoretic Rough Sets","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Data Mining Workshops (ICDMW)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Computer science; Sentiment analysis; Artificial intelligence; Naive Bayes classifier; Rough set; Support vector machine; Ambiguity; Decision tree; Probabilistic logic; Feature extraction; Natural language processing; Data mining; Machine learning","score_opus":0.09865835572894807,"score_gpt":0.3584949497619248,"score_spread":0.25983659403297676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205619838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32059753,0.0012435239,0.65962404,0.01010428,0.0030178546,0.00029616387,0.00040242405,0.00012682258,0.0045873774],"genre_scores_gemma":[0.8834847,0.0002068978,0.11348807,0.0002492362,0.00018609883,0.0000062944714,0.0015007078,0.000015310248,0.00086264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972544,0.00018659484,0.00048301887,0.0010100085,0.000802998,0.00026299784],"domain_scores_gemma":[0.99752194,0.00027073798,0.00042267411,0.0012580348,0.00041464643,0.000111975976],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005598054,0.0002521297,0.00040173854,0.00042208337,0.00011708597,0.0006283873,0.0011518146,0.000119511,0.0012965387],"category_scores_gemma":[0.0001887398,0.00025515817,0.00015839619,0.0011558443,0.000086184096,0.00068137917,0.0006996375,0.00024656142,0.000012834861],"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":[0.00029205327,0.001421187,0.070458,0.00012470035,0.010062316,0.00094863516,0.0031053368,0.035093635,0.014654365,0.12694502,0.013219932,0.72367483],"study_design_scores_gemma":[0.00038893853,0.000025165402,0.0023561458,0.00027199826,0.00035001466,0.000015863,0.00037654085,0.9906396,0.0027899789,0.00018766931,0.002314735,0.00028332073],"about_ca_topic_score_codex":0.000015868103,"about_ca_topic_score_gemma":0.000028218288,"teacher_disagreement_score":0.955546,"about_ca_system_score_codex":0.000067402936,"about_ca_system_score_gemma":0.00018751097,"threshold_uncertainty_score":0.99999005},"labels":[],"label_agreement":null}]}