{"meta":{"query_hash":"5fe5dc47342b","filters":{"venue":"Web Intelligence"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"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/5fe5dc47342b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Web+Intelligence"},"results":[{"id":"W2344430697","doi":"10.3233/web-160335","title":"Accurate and efficient query clustering via top ranked search results","year":2016,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Science Foundation","keywords":"Computer science; Cluster analysis; Data mining; Information retrieval; DBSCAN; Search engine; Web search query; Metric (unit); Feature (linguistics); Hierarchical clustering; Similarity (geometry); Query expansion; Fuzzy clustering; CURE data clustering algorithm; Machine learning; Artificial intelligence","score_opus":0.031748576220429654,"score_gpt":0.27678550056573076,"score_spread":0.2450369243453011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344430697","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":[0.009742327,0.00007816423,0.98539495,0.0019237081,0.00040605754,0.0001586286,0.000010330515,0.00013535799,0.0021504774],"genre_scores_gemma":[0.98537993,0.0001881829,0.01296249,0.00014609328,0.00006803114,0.000007692499,0.0000017568545,0.000007108962,0.0012387325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855286,0.00005487432,0.0002641569,0.0005184874,0.00026623855,0.00034337165],"domain_scores_gemma":[0.9989797,0.00017561375,0.000053707936,0.00063409493,0.000056035267,0.00010085316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067326357,0.00012981091,0.00011474639,0.000117887044,0.00010561368,0.00023090276,0.00097090326,0.000033461463,0.000018540772],"category_scores_gemma":[0.00006952584,0.000088596906,0.000029151612,0.00029815861,0.00008799719,0.00047726763,0.0010678008,0.00007720977,0.00030548897],"study_design_candidate":"design_other","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":[0.00003959965,0.00004424366,0.00006725427,0.00002751387,0.000020915191,0.00004943514,0.0005395186,0.00068974495,0.0034748386,0.014146032,0.0005467886,0.98035413],"study_design_scores_gemma":[0.00032564744,0.00009694556,0.0007460406,0.00012891414,0.000004546774,0.000015972282,0.000053071777,0.97058696,0.01823302,0.00071232044,0.008773589,0.0003229947],"about_ca_topic_score_codex":0.00003442612,"about_ca_topic_score_gemma":0.000014148103,"teacher_disagreement_score":0.98003113,"about_ca_system_score_codex":0.00002792017,"about_ca_system_score_gemma":0.00002490845,"threshold_uncertainty_score":0.39265445},"labels":[],"label_agreement":null},{"id":"W2344499866","doi":"10.3233/web-160333","title":"Predicting political conflicts from polarized social media","year":2016,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","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":"Ontario Tech University","funders":"","keywords":"Politics; Social media; Political science; Political economy; Social psychology; Sociology; Psychology; Law","score_opus":0.04654038883628945,"score_gpt":0.28706160598265235,"score_spread":0.2405212171463629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344499866","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":[0.08372799,0.00011297773,0.90547496,0.0053386963,0.0010109668,0.000071656345,0.000020528723,0.0002596773,0.0039825416],"genre_scores_gemma":[0.99236846,0.000012325479,0.0066282735,0.0003468196,0.00049716013,0.000003864475,0.00000353019,0.0000074555333,0.00013212668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835783,0.00007649596,0.0003289826,0.00041607674,0.00039059037,0.00043002688],"domain_scores_gemma":[0.9985764,0.00076984864,0.00009517824,0.0003117791,0.00008429174,0.000162481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025599418,0.00013212804,0.00019481842,0.00009196259,0.00013976714,0.00013774174,0.0008270216,0.00008168365,0.00039559216],"category_scores_gemma":[0.00032722353,0.00009317232,0.00011403099,0.00024885705,0.00009803608,0.00031988966,0.00026606774,0.000096448835,0.00049360446],"study_design_candidate":"theoretical_or_conceptual","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":[0.00001057749,0.00005571169,0.018988807,0.0000025886268,0.000080566286,0.000015508891,0.0027646872,6.3083803e-7,0.036268603,0.8835447,0.00033042353,0.057937212],"study_design_scores_gemma":[0.0023281681,0.00023303441,0.06403479,0.00061914924,0.00020113641,0.000028142185,0.0027854322,0.2647696,0.4437988,0.17389834,0.04439107,0.0029122971],"about_ca_topic_score_codex":0.00007018844,"about_ca_topic_score_gemma":0.000021441103,"teacher_disagreement_score":0.90864044,"about_ca_system_score_codex":0.000045057037,"about_ca_system_score_gemma":0.00006073936,"threshold_uncertainty_score":0.63444513},"labels":[],"label_agreement":null},{"id":"W3089922444","doi":"10.3233/web-200445","title":"Document classification using convolutional neural networks with small window sizes and latent semantic analysis","year":2020,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Convolutional neural network; Word2vec; Artificial intelligence; Leverage (statistics); Latent semantic analysis; Pattern recognition (psychology); Sliding window protocol; Window (computing); Word (group theory); Robustness (evolution); Document classification; Mathematics","score_opus":0.07204337661805335,"score_gpt":0.2603511661477368,"score_spread":0.18830778952968344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089922444","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":[0.19313061,0.00019474556,0.80502623,0.0014098187,0.00005620223,0.00009787216,4.7587753e-7,0.000059063896,0.000024958543],"genre_scores_gemma":[0.9429002,0.000031072024,0.056578167,0.0004105616,0.00005941608,0.000004519499,0.000002041355,0.000004766351,0.000009300786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988459,0.0000520069,0.0002366251,0.00045616287,0.00020418699,0.00020513518],"domain_scores_gemma":[0.99937254,0.000066322675,0.000100218196,0.0002600797,0.000079332574,0.000121493176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013372353,0.00012409592,0.00016585957,0.00006825709,0.000099552875,0.00016020177,0.0003644627,0.000039300052,0.000015951615],"category_scores_gemma":[0.000017788216,0.000104965184,0.000047417565,0.0006160381,0.00006194754,0.00021113559,0.00015118916,0.00012867853,0.0000043632203],"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":[0.000011293008,0.000012185852,0.027418163,0.000012540051,0.00010151082,0.000009728071,0.00041167642,0.9457912,0.00063141785,0.0136132,0.0000027120195,0.011984391],"study_design_scores_gemma":[0.000047552156,0.000039944287,0.007951147,0.000011106913,0.00007040313,0.000008617808,0.00003957511,0.99132794,0.00017073497,0.00018533523,0.000018880648,0.00012873238],"about_ca_topic_score_codex":0.000055696644,"about_ca_topic_score_gemma":0.0000336514,"teacher_disagreement_score":0.7497695,"about_ca_system_score_codex":0.000036611516,"about_ca_system_score_gemma":0.000044341446,"threshold_uncertainty_score":0.4280356},"labels":[],"label_agreement":null},{"id":"W4381856443","doi":"10.3233/web-230036","title":"A bias study and an unbiased deep neural network for recommender systems","year":2023,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Recommender system; Debiasing; Computer science; Ranking (information retrieval); Learning to rank; Process (computing); Focus (optics); Machine learning; Information retrieval; Perspective (graphical); Rank (graph theory); Variety (cybernetics); Artificial intelligence; Data mining; Data science","score_opus":0.1399967181115029,"score_gpt":0.3486015167690462,"score_spread":0.2086047986575433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381856443","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":[0.051915757,0.0003211995,0.9413507,0.0006564369,0.0019923346,0.0019445012,0.0000065299228,0.0014302499,0.00038229456],"genre_scores_gemma":[0.9913679,0.000043335385,0.007580392,0.00018597605,0.0002470732,0.00039993314,0.0000054946595,0.000022024064,0.00014789685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804366,0.00025080284,0.00043749416,0.0006036929,0.00020133094,0.00046303213],"domain_scores_gemma":[0.998507,0.00040301628,0.00013209067,0.00071121624,0.00009889331,0.00014773641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014246074,0.00020555915,0.00028757387,0.00014818717,0.00023649771,0.00046120366,0.0008477677,0.00007228669,0.000003403726],"category_scores_gemma":[0.00004947398,0.0001778115,0.000056631252,0.0007161524,0.000026783506,0.00041754678,0.00026660677,0.00012497198,0.000020112482],"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":[0.00006658584,0.00074647553,0.0393607,0.00034155152,0.00024962376,0.000109852605,0.012746854,0.009383277,0.00019919724,0.13541047,0.054819442,0.746566],"study_design_scores_gemma":[0.00012253058,0.00074400473,0.0010882798,0.00003496252,0.000007863677,0.00001796484,0.0012840908,0.98528355,0.00012236233,0.003245003,0.0077621024,0.00028725603],"about_ca_topic_score_codex":0.00021876536,"about_ca_topic_score_gemma":0.00021441988,"teacher_disagreement_score":0.9759003,"about_ca_system_score_codex":0.000028257036,"about_ca_system_score_gemma":0.000025962876,"threshold_uncertainty_score":0.72509426},"labels":[],"label_agreement":null},{"id":"W4390831632","doi":"10.3233/web-230363","title":"Exploring ChatGPT for next-generation information retrieval: Opportunities and challenges","year":2024,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Information retrieval; Computer science; Data science","score_opus":0.8004622817749834,"score_gpt":0.4349030895662207,"score_spread":0.36555919220876265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390831632","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":[0.8451281,0.038111195,0.021400986,0.08405191,0.005981562,0.0018972933,0.000027804803,0.0005985118,0.0028026004],"genre_scores_gemma":[0.915803,0.08201058,0.0005749799,0.00042333588,0.0008052188,0.00013735438,0.000060592996,0.000014631001,0.00017025913],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990523,0.000017882108,0.00038123492,0.00018743186,0.00015897177,0.00020221845],"domain_scores_gemma":[0.99929005,0.00017810159,0.00004183581,0.00015053104,0.00022323834,0.00011623194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046672462,0.00011440397,0.00013322529,0.0002250812,0.00011485926,0.00013849109,0.000047024707,0.000076234974,0.000045569912],"category_scores_gemma":[0.000295812,0.00010558236,0.00004550735,0.00013905122,0.000057723748,0.0013654071,0.000016050266,0.00011831395,0.000067251625],"study_design_candidate":"design_other","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":[0.00004418271,0.000015201231,0.000024384863,0.0010866226,0.00001758271,0.0000019825934,0.0073155216,0.000010977017,0.0019188845,0.040244058,0.00040943924,0.9489112],"study_design_scores_gemma":[0.0000321314,0.0009515286,0.00018291283,0.0010344329,0.00010320334,0.00006786762,0.036915395,0.19116355,0.20818643,0.0040715807,0.5568943,0.00039665084],"about_ca_topic_score_codex":0.000029619943,"about_ca_topic_score_gemma":0.00001706128,"teacher_disagreement_score":0.9485145,"about_ca_system_score_codex":0.00007224246,"about_ca_system_score_gemma":0.00021354116,"threshold_uncertainty_score":0.43055236},"labels":[],"label_agreement":null},{"id":"W4390919039","doi":"10.3233/web-230413","title":"Web Intelligence: In search of a better connected world","year":2024,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Cognitive Science and Education Research","field":"Neuroscience","cited_by":0,"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 Regina","funders":"","keywords":"Web intelligence; World Wide Web; Social Semantic Web; Computer science; Web development; Diversity (politics); Heading (navigation); Web standards; Meaning (existential); Data science; The Internet; Sociology; Web service; Engineering; Psychology","score_opus":0.10716458187924208,"score_gpt":0.40371322572835633,"score_spread":0.2965486438491143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390919039","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":[0.9584912,0.00040848448,0.003511398,0.0046795863,0.0009666575,0.00057219743,0.00003938747,0.00014095992,0.031190122],"genre_scores_gemma":[0.9953272,0.00034446304,0.00017646202,0.00054798916,0.000083733394,0.000048297552,0.0000019847018,0.000017386026,0.003452522],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99718726,0.00024187085,0.00048619794,0.00073601335,0.0007454474,0.00060322974],"domain_scores_gemma":[0.9976932,0.001602805,0.000035656383,0.00034628512,0.00017056901,0.00015151635],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001018543,0.0001683897,0.0001989545,0.001226831,0.00008207808,0.00017457039,0.0007904433,0.000059078924,0.004381031],"category_scores_gemma":[0.0013520409,0.00014913308,0.00008801757,0.005260801,0.00067375693,0.0003401368,0.00020235992,0.00058559317,0.0020197101],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006714219,0.00033393837,0.0056928326,0.00024826813,0.000008561822,0.00017829477,0.0041805427,0.00022705107,0.6108991,0.04847753,0.0017454536,0.3279413],"study_design_scores_gemma":[0.000036623318,0.00009740923,0.0011441798,0.00033182526,0.0000035678643,0.000017526487,0.0012227996,0.06298392,0.9219096,0.005180974,0.0068382844,0.00023330457],"about_ca_topic_score_codex":0.000106998465,"about_ca_topic_score_gemma":0.0002782304,"teacher_disagreement_score":0.327708,"about_ca_system_score_codex":0.000092900285,"about_ca_system_score_gemma":0.0007251976,"threshold_uncertainty_score":0.99875736},"labels":[],"label_agreement":null}]}