{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":630,"total_is_capped":false,"direct_labels_cover":3,"predictions_cover":630,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"371cb4d87b7b","filters":{"topic":"Web Data Mining and Analysis"}},"results":[{"id":"W2913556077","doi":"","title":"Proceedings of the 25th International Conference on World Wide Web","year":2016,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":635,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université TÉLUQ","funders":"","keywords":"Computer science; World Wide Web; Track (disk drive); Social media; Consistency (knowledge bases); Personalization; Phishing; Data science; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.0271719921717674,"gpt":0.2464222719911995,"spread":0.2192502798194321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001092485,0.00004409397,0.00005521486,0.00006563845,0.00002444615,0.00005289393,0.001052359,0.000009419392,0.0001469665],"category_scores_gemma":[0.0000557365,0.00001935504,0.00003671341,0.0002120734,0.00003649,0.000223537,0.0002167281,0.00002936681,0.00004467749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001095667,"about_ca_system_score_gemma":0.00002765363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008111647,"about_ca_topic_score_gemma":0.00001810976,"domain_scores_codex":[0.9994785,0.000003864684,0.00009402289,0.0001508843,0.0002007171,0.0000719727],"domain_scores_gemma":[0.9996341,0.00002881054,0.00006041592,0.0001648582,0.00009054932,0.00002123664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001643425,0.0000206897,0.01311563,0.000001156561,0.00001555372,1.618894e-7,0.00004768137,3.216485e-7,0.009542132,0.9491502,0.02052411,0.007580735],"study_design_scores_gemma":[0.002666657,0.0002979051,0.1157865,0.001493259,0.00006402352,0.00001551105,0.0004010845,0.333118,0.3216697,0.04209876,0.1812377,0.001150932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1832229,0.000003929909,0.02780035,0.05151417,0.0005425395,0.00008312071,0.000017601,0.0001530804,0.7366623],"genre_scores_gemma":[0.9740925,0.00000366703,0.003468035,0.0003499244,0.0000217199,0.000001637431,1.613579e-7,0.000001412799,0.02206089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9070514,"threshold_uncertainty_score":0.1955562,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090018148","doi":"10.1109/dnsr.2004.1344743","title":"Weighted PageRank algorithm","year":2004,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":562,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"PageRank; Computer science; Ranking (information retrieval); HITS algorithm; Web page; Information retrieval; Popularity; Rank (graph theory); Categorization; Learning to rank; Data mining; World Wide Web; Theoretical computer science; Web search engine; Web navigation; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.008709172515255128,"gpt":0.218913923281581,"spread":0.2102047507663259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000899079,0.00005581107,0.00007120317,0.00006080675,0.00006176056,0.0001071522,0.0004866031,0.00002024639,0.00005142775],"category_scores_gemma":[0.000004948661,0.00004278959,0.00004137866,0.0003593387,0.00001202994,0.0002883483,0.00009991337,0.00004376933,0.0004336394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001256217,"about_ca_system_score_gemma":0.00002954387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001045815,"about_ca_topic_score_gemma":0.000004783566,"domain_scores_codex":[0.9994411,0.00000997688,0.00008495701,0.0002010692,0.0001287391,0.0001341938],"domain_scores_gemma":[0.9994974,0.00001225042,0.00001708419,0.0003951284,0.00002250296,0.00005561994],"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":[3.058484e-7,0.00007844203,0.00006879459,0.000001737197,0.00003902411,0.00006125593,0.0002724718,0.00004893569,0.0003763557,0.111152,0.00340635,0.8844943],"study_design_scores_gemma":[0.003274822,0.0002789974,0.003171297,0.00006332339,0.00006606142,0.0001394534,0.0001708953,0.6841376,0.04866382,0.1085356,0.1499604,0.001537769],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001426227,0.00003077181,0.9889924,0.001604834,0.00007576778,0.0000134436,0.000001440555,0.000211874,0.007643271],"genre_scores_gemma":[0.1102465,0.000009583431,0.8874591,0.0006738121,0.00005611983,0.000002099604,0.000006540493,0.000003162685,0.001543067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8829565,"threshold_uncertainty_score":0.5573702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137763598","doi":"10.1109/tkde.2004.58","title":"Efficient phrase-based document indexing for Web document clustering","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Document clustering; Computer science; Cluster analysis; Vector space model; Search engine indexing; Phrase; Information retrieval; Document classification; Data mining; tf–idf; Artificial intelligence; Term (time)","retraction":null,"screen_n_in":null,"score":{"opus":0.02028388213544066,"gpt":0.2679597706680517,"spread":0.247675888532611,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003419823,0.0002049949,0.0001926514,0.0002855363,0.0002133799,0.0002177284,0.0006802019,0.00005285157,0.000004958067],"category_scores_gemma":[0.000008043313,0.0002021405,0.0000673313,0.0003431034,0.00001614486,0.0003144251,0.00002518323,0.0001446296,0.00001762712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009411,"about_ca_system_score_gemma":0.00008974737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000186786,"about_ca_topic_score_gemma":0.00003339825,"domain_scores_codex":[0.9986981,0.00001259748,0.0002472124,0.0005792846,0.0001507878,0.0003120013],"domain_scores_gemma":[0.9987521,0.0001044905,0.00003679768,0.000934187,0.00003374653,0.0001387132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000821009,0.000105566,0.000001027519,0.00008869779,0.00005468107,0.000003846004,0.0002296668,0.9700858,0.001920419,0.0003200825,0.00003901521,0.027143],"study_design_scores_gemma":[0.001064808,0.00007637138,0.000009209919,0.0001740748,0.00005016522,0.00000569945,0.00001882931,0.9885849,0.006719325,0.00001931992,0.003021014,0.0002562322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007419664,0.0001950593,0.9911999,0.0001820255,0.0004795745,0.0001662769,0.0001075544,0.0002164863,0.00003342925],"genre_scores_gemma":[0.9234667,0.00001709425,0.07628253,0.00003994777,0.00005907203,0.00005234398,0.00003098117,0.00001778425,0.00003357515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.916047,"threshold_uncertainty_score":0.8243051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011539648","doi":"10.1145/2109205.2109208","title":"Crawling Ajax-Based Web Applications through Dynamic Analysis of User Interface State Changes","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Ajax; Computer science; JavaScript; Dynamic web page; World Wide Web; Crawling; Web application; Web page; Interactivity; Web modeling; Web-based simulation; Mashup; User interface; Web crawler; Web API; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0267733111547076,"gpt":0.2868866886135497,"spread":0.2601133774588421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003937336,0.0001496207,0.0002435559,0.000357037,0.0002515456,0.0000690322,0.001311889,0.00004386784,0.0001097341],"category_scores_gemma":[0.00001987428,0.0001108456,0.0002135999,0.002408314,0.00007903489,0.0003290434,0.0000249304,0.0001781208,0.0000632305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004088906,"about_ca_system_score_gemma":0.0000502446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008710477,"about_ca_topic_score_gemma":0.0004615335,"domain_scores_codex":[0.9988495,0.000112473,0.0002338683,0.0002819528,0.0002454665,0.0002767594],"domain_scores_gemma":[0.9975486,0.0004656563,0.0001367566,0.001715859,0.00007055285,0.00006250837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001243173,0.004959028,0.003488178,0.0002242699,0.01889284,0.000004833748,0.02166377,0.3667053,0.2402269,0.007056837,0.0009601653,0.3356936],"study_design_scores_gemma":[0.0005466907,0.0001294844,0.001532706,0.00007775737,0.00327341,0.000003599,0.0009233697,0.8850385,0.07740922,0.0007907507,0.02958413,0.0006903748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0369109,0.0001149363,0.9573905,0.00504158,0.00007379952,0.0001157792,0.0001617709,0.0001108385,0.00007986967],"genre_scores_gemma":[0.9774219,0.0001004875,0.02177444,0.0002742144,0.00001192809,0.00008473855,0.00001480533,0.00001100036,0.0003064921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.940511,"threshold_uncertainty_score":0.4520153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010463775","doi":"10.1145/860435.860449","title":"Query type classification for web document retrieval","year":2003,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":251,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Information retrieval; Relevance (law); Task (project management); Web query classification; Query expansion; Relevance feedback; Scheme (mathematics); Web search query; Search engine; Artificial intelligence; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.03861046735755231,"gpt":0.2879217894911348,"spread":0.2493113221335825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003338265,0.00004858532,0.00006387338,0.00004960551,0.00006091186,0.0001051554,0.0002540282,0.0000258572,0.00004177794],"category_scores_gemma":[0.0001248084,0.00003973177,0.00003599827,0.0003194123,0.000008698921,0.0002193293,0.00002349874,0.00002671303,0.00009368458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002064371,"about_ca_system_score_gemma":0.00007331016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003858082,"about_ca_topic_score_gemma":0.000002518878,"domain_scores_codex":[0.9994346,0.00002813094,0.0001080986,0.0002077866,0.0001068046,0.0001145488],"domain_scores_gemma":[0.9994306,0.00005386243,0.00003437648,0.0003739361,0.00006771275,0.00003952138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007075609,0.0000440543,0.0005698922,0.000007463869,0.00003127877,8.43243e-7,0.00007880638,0.00001305032,0.01031082,0.9390064,0.03770945,0.01222087],"study_design_scores_gemma":[0.0007068962,0.0002268221,0.001722912,0.00001364776,0.00004254855,0.000007660246,0.0001749799,0.1388918,0.02195096,0.01283771,0.8230037,0.0004203471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01637574,0.00006911166,0.9595601,0.001664273,0.0004043764,0.0001116194,0.000002605668,0.0001691941,0.02164299],"genre_scores_gemma":[0.8702459,0.0000125592,0.1234091,0.0002707849,0.0000316639,0.000003936542,0.00001109643,0.000003643421,0.006011302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9261687,"threshold_uncertainty_score":0.1620215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245995216","doi":"10.1007/978-3-642-45135-5","title":"Recommendation Systems in Software Engineering","year":2014,"lang":"en","type":"book","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":212,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; McGill University","funders":"","keywords":"Software engineering; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01132452895672102,"gpt":0.2009287867464777,"spread":0.1896042577897566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003256248,0.000140871,0.0002494678,0.0003091551,0.00001763159,0.000168691,0.0005784673,0.0001301804,0.00003941372],"category_scores_gemma":[0.00005894835,0.0001337585,0.00004989517,0.000123607,0.000003385104,0.0001907879,0.0001645223,0.0001791304,0.0001778406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001099619,"about_ca_system_score_gemma":0.00007074994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005410938,"about_ca_topic_score_gemma":0.0000167486,"domain_scores_codex":[0.9991339,0.00002163046,0.0002404588,0.0003380752,0.0001208433,0.0001451145],"domain_scores_gemma":[0.9992535,0.000125457,0.00008647245,0.000468044,0.00002615017,0.00004042521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001066899,0.00003613536,0.0002826994,0.0005520233,0.0001529256,0.00003101149,0.0002322473,0.009070585,0.000007781893,0.1367687,0.6299509,0.222914],"study_design_scores_gemma":[0.00005940085,0.000009926785,0.00002147178,0.0001496019,0.00000675377,0.000003560254,0.000001495162,0.2932914,0.00000154618,0.00007986328,0.7061692,0.0002057779],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000001773131,0.00005011196,0.9027479,0.00008237084,0.0004230272,0.00004886817,0.000006051477,0.0002311006,0.0964088],"genre_scores_gemma":[0.0003784299,0.00002324152,0.05825153,0.0001341916,0.0003381327,0.00001891366,0.0005237663,0.00002941713,0.9403024],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8444964,"threshold_uncertainty_score":0.5454515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158943277","doi":"10.1109/tvcg.2008.175","title":"VisGets: Coordinated Visualizations for Web-based Information Exploration and Discovery","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Web navigation; World Wide Web; RSS; Filter (signal processing); Exploratory search; Web search query; Visualization; Web page; Data visualization; Dimension (graph theory); Search engine; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02577688320399458,"gpt":0.2634437113893258,"spread":0.2376668281853312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001644853,0.0001875702,0.0001847845,0.0006240438,0.0007374207,0.0003983521,0.000167295,0.0000964278,0.000001879258],"category_scores_gemma":[0.000007522107,0.0001885577,0.00007468004,0.0009604464,0.00009435444,0.003066045,0.000004919257,0.00008117559,0.000002804671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001726563,"about_ca_system_score_gemma":0.0000763307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001265579,"about_ca_topic_score_gemma":0.00001152764,"domain_scores_codex":[0.9988745,0.00008211649,0.0003493518,0.000313157,0.0002104412,0.000170365],"domain_scores_gemma":[0.9991466,0.0001342081,0.0001303764,0.0002566809,0.0002354144,0.00009667095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009343941,0.000696774,0.0004547606,0.0002062915,0.0002033329,0.000003693342,0.004087307,0.01762727,0.000122022,0.9425414,0.002849618,0.03111406],"study_design_scores_gemma":[0.0009829935,0.0002377196,0.0002228577,0.00003417109,0.00003266855,0.000008900302,0.00003769128,0.9947575,0.0008262391,0.0003655516,0.002265791,0.0002278818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006522303,0.00001877434,0.9924024,0.0002154116,0.0002543762,0.0002478144,0.00005789291,0.0002695887,0.00001142226],"genre_scores_gemma":[0.9931772,0.0002900785,0.004908117,0.001292768,0.0000306066,0.00007793954,0.0001770545,0.00001340691,0.00003278214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9874943,"threshold_uncertainty_score":0.7689161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080132606","doi":"10.14778/1938545.1938547","title":"Automatic wrappers for large scale web extraction","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Noise (video); Scale (ratio); Noisy data; Extraction (chemistry); Data extraction; Data mining; Information extraction; Training set; Artificial intelligence; Machine learning; Information retrieval; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02415002081639386,"gpt":0.2448207655012949,"spread":0.2206707446849011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004121945,0.00009426787,0.000134771,0.00008097065,0.000130293,0.0000503766,0.0008487081,0.00003029341,0.00002556905],"category_scores_gemma":[0.00004494737,0.0000645535,0.0001346095,0.0002744832,0.00002162676,0.0003980818,0.0002116503,0.00005681924,0.00001135651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002894376,"about_ca_system_score_gemma":0.00002188755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001733837,"about_ca_topic_score_gemma":0.000002911289,"domain_scores_codex":[0.9991307,0.000003793631,0.0002048558,0.0002304081,0.0002151883,0.0002150059],"domain_scores_gemma":[0.9994513,0.00002002495,0.0001993546,0.0001863106,0.00009833239,0.00004472669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008868141,0.002929436,0.0420534,0.001262166,0.0008989658,0.000001503001,0.03905774,0.00001217746,0.3998624,0.2733877,0.08925852,0.1511873],"study_design_scores_gemma":[0.001972075,0.0003952651,0.0101086,0.0003335241,0.0002984758,0.00002913727,0.003211157,0.3443504,0.609665,0.01227753,0.01675934,0.000599567],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9398059,0.0001177666,0.03362151,0.002135886,0.0008084552,0.0009767832,0.00004161059,0.0004205003,0.02207159],"genre_scores_gemma":[0.9490006,0.000009229226,0.05049328,0.00008504764,0.00002995853,0.00005939276,7.845499e-7,0.000006423864,0.0003152729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3443382,"threshold_uncertainty_score":0.2632415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036101886","doi":"10.5430/air.v2n1p44","title":"Exploiting web scraping in a collaborative filtering- based approach to web advertising","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; World Wide Web; Web page; Scraper site; Copying; Web mining; Web development; Static web page; Web modeling; Web analytics; Web navigation; Information retrieval; Data Web; Web intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2115775441977723,"gpt":0.410260957608213,"spread":0.1986834134104407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00520404,0.0001764393,0.0002576608,0.001165748,0.0003995555,0.0005499252,0.001293414,0.00007991378,0.00003163405],"category_scores_gemma":[0.001246729,0.0001768634,0.00006322897,0.006046857,0.0001215943,0.001115225,0.0006332644,0.0004917544,0.0004028331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001897864,"about_ca_system_score_gemma":0.0003741456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00020629,"about_ca_topic_score_gemma":0.0001171318,"domain_scores_codex":[0.9960811,0.0006150031,0.0005048226,0.0006446879,0.0008897783,0.00126462],"domain_scores_gemma":[0.9979173,0.0006006444,0.00005931632,0.0007178503,0.0003481738,0.0003567284],"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":[0.0001127466,0.001593866,0.007679521,0.0001334525,0.00006523605,0.00006004244,0.02757188,0.0217459,0.2460181,0.1228254,0.001186128,0.5710077],"study_design_scores_gemma":[0.00004111667,0.00009157789,0.0001491857,0.0001988698,0.00000319539,0.000002955248,0.007366637,0.8940472,0.09546468,0.0009153081,0.001381031,0.000338229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1924749,0.0001937556,0.8006265,0.001074168,0.0001617072,0.0003460555,0.000009640809,0.0001235247,0.004989779],"genre_scores_gemma":[0.9295261,0.00001348185,0.07000553,0.0001225957,0.0001740355,0.00009555577,0.000006042329,0.00001584372,0.00004081642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8723013,"threshold_uncertainty_score":0.721228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400526908","doi":"10.1145/3626772.3657707","title":"Large Language Models can Accurately Predict Searcher Preferences","year":2024,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.07561307685075239,"gpt":0.3207369305742917,"spread":0.2451238537235393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003200866,0.00008944723,0.00009702956,0.0001116533,0.00005828142,0.0005570957,0.0007358876,0.00003676765,0.0001718715],"category_scores_gemma":[0.00001613957,0.00006214538,0.00005345224,0.0004843915,0.00001596071,0.0006751104,0.0002786712,0.0001256169,0.0001490013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470814,"about_ca_system_score_gemma":0.0001103241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002994609,"about_ca_topic_score_gemma":0.0002151692,"domain_scores_codex":[0.9989731,0.0000482016,0.0001119961,0.0003593554,0.0002504937,0.0002568678],"domain_scores_gemma":[0.999397,0.00006265953,0.00001142321,0.0004175103,0.00002476688,0.00008661122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004872898,0.0001839457,0.0008012776,0.0001751506,0.000476976,0.0004065568,0.03597824,0.001111217,0.00103047,0.5122191,0.1050792,0.3425329],"study_design_scores_gemma":[0.00005705704,0.00002488441,0.00008969205,0.00003233201,0.00001164063,0.000004743139,0.0005865586,0.9905349,0.0006388277,0.003013474,0.004879319,0.000126542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08019068,0.0009876853,0.8654788,0.002003569,0.0002196636,0.00007495302,0.0001114178,0.001083644,0.04984966],"genre_scores_gemma":[0.9854001,0.00002749171,0.005386545,0.0001538262,0.00006259403,0.000007306237,0.00002438249,0.000005658602,0.008932074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9894237,"threshold_uncertainty_score":0.5372086,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129546202","doi":"10.1109/tkde.2009.174","title":"An Efficient Concept-Based Mining Model for Enhancing Text Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sentence; Natural language processing; Phrase; Term (time); Similarity (geometry); Semantics (computer science); Cluster analysis; Artificial intelligence; Document clustering; Meaning (existential); Word (group theory); Measure (data warehouse); Information retrieval; Similarity measure; Semantic similarity; Data mining; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02779020595604768,"gpt":0.2810140212831417,"spread":0.253223815327094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000262825,0.0001803386,0.0001905087,0.0002198206,0.0002098036,0.0001705563,0.0007010057,0.00005614471,0.000001667858],"category_scores_gemma":[0.000006700024,0.0001856918,0.00004853342,0.0002611228,0.00001251327,0.0005065864,0.000007252913,0.0001152264,0.00000330278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276966,"about_ca_system_score_gemma":0.00005162087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000271801,"about_ca_topic_score_gemma":0.00002273831,"domain_scores_codex":[0.9988211,0.00001339826,0.0002198609,0.0005637287,0.0001004537,0.0002814317],"domain_scores_gemma":[0.9987236,0.0001122982,0.00003214907,0.0009533399,0.00003945975,0.0001391547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004530902,0.00008491378,1.779571e-7,0.00001585297,0.00001214752,9.798123e-7,0.0005523343,0.9268813,0.003856711,0.00005512716,0.00005228357,0.06848367],"study_design_scores_gemma":[0.0003545949,0.0001017748,0.000004968153,0.00007302899,0.00003392881,0.000002615989,0.00003324074,0.9921582,0.006827439,0.00000272018,0.0001835741,0.0002238726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003891453,0.000129599,0.9952431,0.0000561388,0.0001894916,0.00009320914,0.000130284,0.0002380028,0.00002869334],"genre_scores_gemma":[0.8403625,0.000004060427,0.1594156,0.00006946542,0.00004538479,0.000009794446,0.00004544479,0.00001179664,0.0000359766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8364711,"threshold_uncertainty_score":0.7572293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120376711","doi":"10.1145/634067.634291","title":"Integrating back, history and bookmarks in web browsers","year":2001,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Web browser; World Wide Web; Multimedia; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.01732150180113526,"gpt":0.215305818929065,"spread":0.1979843171279298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002069074,0.00006137975,0.00009066614,0.0001226342,0.00002092052,0.00004533554,0.0002732057,0.00002524976,0.0001624106],"category_scores_gemma":[0.00002909286,0.00005178228,0.0000198132,0.0001703731,0.00002503938,0.0003369368,0.0001158869,0.00008276415,0.00004421401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005919954,"about_ca_system_score_gemma":0.00004107308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003348204,"about_ca_topic_score_gemma":0.0007916166,"domain_scores_codex":[0.9994272,0.00002930045,0.0001161092,0.0002212505,0.00007608366,0.0001300578],"domain_scores_gemma":[0.9996372,0.00004257336,0.00002485482,0.000237249,0.00001136561,0.00004675774],"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":[0.00001084203,0.0001490027,0.1681948,0.00002761311,0.00005346857,0.0002067383,0.005841505,0.0000626899,0.005747657,0.06557222,0.1864992,0.5676342],"study_design_scores_gemma":[0.0005043945,0.00005093836,0.005507458,0.0000628287,0.000007216929,0.00004056994,0.0006297302,0.6685716,0.00008805223,0.0003367172,0.3238477,0.0003527951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2898365,0.001330704,0.1799231,0.00258998,0.0002919992,0.00008382578,0.000001070006,0.0002203546,0.5257224],"genre_scores_gemma":[0.8907401,0.0001192003,0.08847103,0.001228879,0.00003633545,0.000003308352,0.000003328873,0.000006040728,0.0193918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6685089,"threshold_uncertainty_score":0.211162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1828830618","doi":"","title":"World wide web site summarization","year":2004,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Automatic summarization; Computer science; World Wide Web; Web site; Directory; Web navigation; Information retrieval; Task (project management); Web page; Web mapping; Data Web; Web modeling; Web standards; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.009892234255779498,"gpt":0.2168120506008852,"spread":0.2069198163451057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009397601,0.00004954031,0.00005872083,0.0001212986,0.00005721351,0.0001361544,0.0003196994,0.00001251927,0.00003969246],"category_scores_gemma":[0.00002268989,0.00004166714,0.00002981723,0.0006953023,0.000009948622,0.0004012113,0.000106297,0.00003592948,0.0004014933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001741679,"about_ca_system_score_gemma":0.00003947302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001003454,"about_ca_topic_score_gemma":0.0006255341,"domain_scores_codex":[0.9994902,0.00001037479,0.0000884137,0.0001828939,0.0001179397,0.0001101751],"domain_scores_gemma":[0.99955,0.00002272918,0.00002400552,0.0003367605,0.00002303043,0.00004341523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003760959,0.0002261798,0.06480232,0.00001511774,0.00008673908,0.00006024457,0.001143464,0.0117585,0.007730507,0.8086139,0.03937544,0.06618384],"study_design_scores_gemma":[0.002619724,0.0001491031,0.03320723,0.0001396456,0.00008668091,0.00001827024,0.0001039227,0.5225384,0.02663892,0.03237659,0.3805858,0.001535706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01571997,0.00001568246,0.9574972,0.00299773,0.00008442302,0.0000187964,0.00000177266,0.0002204676,0.02344395],"genre_scores_gemma":[0.9045511,0.00000513148,0.0869271,0.001062038,0.00003504675,0.000001399119,0.00001927066,0.000003053608,0.007395877],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8888311,"threshold_uncertainty_score":0.5160518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2585438896","doi":"","title":"The data civilizer system","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.6414419922836844,"gpt":0.5044311967031525,"spread":0.1370107955805319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01486543,0.0002244579,0.0003606796,0.0002904342,0.004139095,0.009152149,0.04588917,0.00009965778,0.000006735707],"category_scores_gemma":[0.003496828,0.0001421178,0.00001844446,0.001222321,0.0007843953,0.002828222,0.02105016,0.0008378897,0.0008002319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009898134,"about_ca_system_score_gemma":0.0006784677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001244886,"about_ca_topic_score_gemma":0.0001892868,"domain_scores_codex":[0.9941769,0.001056758,0.0005586725,0.001625257,0.001777166,0.0008053111],"domain_scores_gemma":[0.9653193,0.0009541845,0.0004183412,0.03077381,0.002391115,0.000143205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001211329,0.00003257725,0.000392178,0.00006721194,0.0001124209,0.00004364416,0.00008714563,8.424748e-7,0.0001534632,0.7966109,0.1535977,0.0488898],"study_design_scores_gemma":[0.0004722072,0.0001255221,0.00189211,0.0008289244,0.000007493811,0.00003289042,0.003070116,0.7378812,0.00008442844,0.0004526723,0.2547271,0.0004253858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005776752,0.001722985,0.570177,0.03664406,0.00785681,0.003628636,0.01920058,0.001038225,0.3539549],"genre_scores_gemma":[0.9952725,0.00009849805,0.0005788262,0.0000165443,0.0003225112,0.00006067682,0.001108808,0.00001574625,0.002525951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9894957,"threshold_uncertainty_score":0.9999778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1485672862","doi":"","title":"BlogScope: a system for online analysis of high volume text streams","year":2007,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Blogosphere; Computer science; Ranking (information retrieval); Relevance (law); Information retrieval; Volume (thermodynamics); Set (abstract data type); Data stream mining; World Wide Web; Data mining; Data science; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.01347909899140815,"gpt":0.2599205676831217,"spread":0.2464414686917135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005910666,0.0001030227,0.0003933531,0.0005150837,0.00005257971,0.00005133733,0.0007319278,0.00004913893,0.00002888043],"category_scores_gemma":[0.00003715049,0.00008192335,0.0002355797,0.002133127,0.00002481172,0.000164167,0.0001296768,0.0000387949,0.00001226607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003085721,"about_ca_system_score_gemma":0.00003150712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079652,"about_ca_topic_score_gemma":0.0007277448,"domain_scores_codex":[0.9987894,0.00001981785,0.0003916688,0.0003477498,0.0002144251,0.0002369013],"domain_scores_gemma":[0.9987252,0.0001465629,0.0001539763,0.0007472652,0.0001444642,0.00008257186],"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":[0.00006391127,0.001265972,0.02967839,0.0002935708,0.01055621,0.0000496018,0.0007387627,0.01061249,0.002756321,0.1688699,0.008242382,0.7668725],"study_design_scores_gemma":[0.0004688052,0.0001538637,0.01768842,0.00003302663,0.001552384,0.000002953353,0.000494863,0.9726841,0.003337085,0.00004892947,0.003274124,0.0002614832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1587836,0.00003124011,0.8401632,0.0001380237,0.00005545859,0.00005397616,0.0001083711,0.0001001413,0.0005659792],"genre_scores_gemma":[0.8598476,0.000001607432,0.1383023,0.00004568805,0.00003074405,0.000002334709,0.0001156252,0.000004136717,0.001649951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9620716,"threshold_uncertainty_score":0.3340738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1563293148","doi":"10.1007/978-1-4471-0105-5_15","title":"How People Recognise Previously Seen Web Pages from Titles, URLs and Thumbnails","year":2002,"lang":"en","type":"book-chapter","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Thumbnail; Computer science; World Wide Web; Information retrieval; Web page; String (physics); Image (mathematics); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02709610252049598,"gpt":0.1978387770905628,"spread":0.1707426745700668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001521615,0.00034718,0.0005163423,0.0001548203,0.0000960699,0.0007831464,0.000872104,0.0002411073,0.000971973],"category_scores_gemma":[0.00002842458,0.0002851786,0.0001500193,0.00005792709,0.00004800743,0.0003721631,0.0004861508,0.000247762,0.0005888455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002114619,"about_ca_system_score_gemma":0.0000481508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001565059,"about_ca_topic_score_gemma":0.0004604209,"domain_scores_codex":[0.9983484,0.00002699018,0.0002269132,0.0008301818,0.0003113067,0.0002562452],"domain_scores_gemma":[0.9983681,0.0001528186,0.0001803839,0.001078854,0.00005780079,0.0001620807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002831052,0.00003986534,0.000273804,0.00007271078,0.0006058221,0.0001075262,0.0008090236,8.904216e-7,0.000056825,0.02764505,0.5470052,0.4233805],"study_design_scores_gemma":[0.0002696602,0.00006570285,0.0001015792,0.0002643575,0.0002490444,0.00001688775,0.0000203861,0.005906292,0.00003349403,0.007651484,0.9845965,0.0008246166],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00016747,0.005295055,0.01354469,0.003370475,0.0002353888,0.0002334725,0.0003326442,0.0004394226,0.9763814],"genre_scores_gemma":[0.002625221,0.005371347,0.01513384,0.0002478133,0.0002375637,0.000005445387,0.0001373832,0.00003607382,0.9762053],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4375913,"threshold_uncertainty_score":0.9999601,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1886218757","doi":"10.1109/icdm.2002.1183904","title":"Phrase-based document similarity based on an index graph model","year":2003,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Document clustering; Cluster analysis; Phrase; Vector space model; Information retrieval; Graph; Similarity (geometry); Matching (statistics); Set (abstract data type); Artificial intelligence; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02070779077958386,"gpt":0.2583232720134422,"spread":0.2376154812338583,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005378005,0.0001544104,0.0001522231,0.0002115309,0.0001373411,0.0002194085,0.0006669237,0.0000564513,0.0000974411],"category_scores_gemma":[0.00003817309,0.0001279786,0.00009917311,0.0005192706,0.00002774767,0.0003763963,0.00003444301,0.0001205855,0.00003016027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003101855,"about_ca_system_score_gemma":0.0001568981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007933179,"about_ca_topic_score_gemma":0.00004243707,"domain_scores_codex":[0.9985147,0.0001339715,0.0001739489,0.0005124386,0.0003977117,0.0002672716],"domain_scores_gemma":[0.998526,0.00004994873,0.00004931372,0.001150018,0.00004715626,0.0001775995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001392617,0.0006718919,0.004211195,0.000009728397,0.00002482146,0.00001956037,0.00007318374,0.9162505,0.000191354,0.06862238,0.003584889,0.006326613],"study_design_scores_gemma":[0.0004183367,0.00008131817,0.0001880376,0.000006694433,0.000009340277,2.673653e-7,0.000008631894,0.9930756,0.002131409,0.003432481,0.0004618049,0.0001860701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01164468,0.000003757931,0.9805255,0.0006824785,0.00004519683,0.0000523239,0.000006672587,0.0001875319,0.006851853],"genre_scores_gemma":[0.8798538,5.264528e-7,0.1161235,0.00378392,0.000008024847,0.000007676715,0.00001640824,0.000006015527,0.0002000788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8682092,"threshold_uncertainty_score":0.5218815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098181468","doi":"10.1109/hicss.2005.114","title":"Automatic Identification of Home Pages on the Web","year":2005,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Identification (biology); Computer science; World Wide Web; Web page; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0194470054804127,"gpt":0.2397336240570869,"spread":0.2202866185766742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003093511,0.00003352783,0.00005192084,0.0000501402,0.00003944083,0.00006416818,0.0005241342,0.00001023901,0.00008084311],"category_scores_gemma":[0.0000344179,0.00001903194,0.00002994045,0.0002245286,0.00001605515,0.0001548776,0.0000498969,0.00002567332,0.0002411444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005555415,"about_ca_system_score_gemma":0.00001170157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003431312,"about_ca_topic_score_gemma":0.000005000214,"domain_scores_codex":[0.9995347,0.00003070293,0.0001360361,0.000103605,0.0001380478,0.00005687379],"domain_scores_gemma":[0.9993101,0.00009853878,0.00006050748,0.0004992333,0.00001897817,0.00001267382],"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":[6.267809e-7,0.0001666455,0.0005696524,0.00001512718,0.00006199972,8.808793e-7,0.0009322108,0.0003756616,0.01994338,0.2995403,0.054846,0.6235476],"study_design_scores_gemma":[0.00004475365,0.00001398883,0.006254593,0.000009317861,0.00000748201,7.627531e-7,0.00005372372,0.9759462,0.01520925,0.0006531847,0.001753147,0.00005354499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8250338,0.00005437879,0.1315842,0.03397925,0.0001026221,0.00007726251,0.000005160579,0.0002502385,0.008913064],"genre_scores_gemma":[0.9940596,0.000009409766,0.004701045,0.0002008934,0.00001804403,0.000002370314,0.000001132992,0.000001244796,0.001006303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9755706,"threshold_uncertainty_score":0.3099504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070347268","doi":"10.1145/1753326.1753426","title":"A study of tabbed browsing among mozilla firefox users","year":2010,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"World Wide Web; Computer science; Web browser; Web page; Web navigation; Information retrieval; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.0144848797964874,"gpt":0.2481044691568604,"spread":0.233619589360373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002449405,0.00007565471,0.0001453948,0.0001052059,0.00006674891,0.00009214154,0.0006974889,0.0000296114,0.00003529979],"category_scores_gemma":[0.0000479925,0.00005924047,0.00004285459,0.000432542,0.00003337369,0.0003434802,0.0002365942,0.000109401,0.00001397203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003798848,"about_ca_system_score_gemma":0.00002106304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001190598,"about_ca_topic_score_gemma":0.001061999,"domain_scores_codex":[0.9991773,0.00002934494,0.0001806033,0.0002578062,0.0002128231,0.0001420621],"domain_scores_gemma":[0.999046,0.00004690935,0.00007464588,0.0007220114,0.000049269,0.00006113103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004740325,0.0009627513,0.9213678,0.00001224564,0.0002098824,0.00004520006,0.01061825,0.0002230512,0.02394735,0.002941152,0.002391538,0.0372761],"study_design_scores_gemma":[0.002055866,0.0006188047,0.7483239,0.00003717874,0.0001252491,0.00001634678,0.006838657,0.2223125,0.01688825,0.0003487615,0.001584249,0.0008501774],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875093,0.000002126679,0.009923414,0.00006077699,0.0001236573,0.00005019593,8.590255e-7,0.00008405049,0.002245588],"genre_scores_gemma":[0.9886848,4.072281e-7,0.01080966,0.00002771944,0.00002206688,0.00000230146,9.759068e-7,0.00000388746,0.0004481271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2220895,"threshold_uncertainty_score":0.2415756,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147293034","doi":"10.1145/2348283.2348327","title":"Mining query subtopics from search log data","year":2012,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Web search query; Information retrieval; Ranking (information retrieval); Cluster analysis; Web query classification; Search engine; Leverage (statistics); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1367392867182668,"gpt":0.3206255663048285,"spread":0.1838862795865617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004886962,0.00007124065,0.0001052564,0.00005678581,0.00007369423,0.0001532592,0.001929417,0.00003594319,0.0001326729],"category_scores_gemma":[0.00005302694,0.00005858377,0.00002269343,0.0002443005,0.00002048039,0.001259321,0.001504886,0.00007937849,0.0003047677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009377461,"about_ca_system_score_gemma":0.00003572897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007882718,"about_ca_topic_score_gemma":0.0000478118,"domain_scores_codex":[0.9990102,0.00005378101,0.0001227719,0.0003074046,0.0002146743,0.0002911486],"domain_scores_gemma":[0.9979225,0.0001411984,0.00002303352,0.001772405,0.00002044849,0.0001203962],"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":[0.000002996623,0.0002442116,0.4140649,0.00001215411,0.0002007542,0.00002431736,0.004012604,0.00003362962,0.001058189,0.0364116,0.1257444,0.4181902],"study_design_scores_gemma":[0.0004828057,0.00004302531,0.07371912,0.00004257861,0.00007926107,0.0000156773,0.001440312,0.7455769,0.004337328,0.0004752864,0.1729331,0.000854641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.142505,0.0003433448,0.8455454,0.001266314,0.00036902,0.00002561835,0.0000420132,0.0001864058,0.009716837],"genre_scores_gemma":[0.7638428,0.00001307817,0.2337232,0.0004026624,0.0003526883,7.284924e-7,0.0001855255,0.000004569391,0.001474831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7455432,"threshold_uncertainty_score":0.3917274,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107131706","doi":"10.1109/icdm.2006.64","title":"Enhancing Text Clustering Using Concept-based Mining Model","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Phrase; Sentence; Document clustering; Term (time); Semantics (computer science); Similarity (geometry); Natural language processing; Matching (statistics); Artificial intelligence; Similarity measure; Measure (data warehouse); Word (group theory); Information retrieval; Data mining; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02220185227204753,"gpt":0.2452552487338726,"spread":0.223053396461825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002650612,0.0001665911,0.0001968173,0.0001791413,0.0002327842,0.0004143846,0.0006000313,0.00005770642,0.000008028982],"category_scores_gemma":[0.00003236112,0.000169082,0.00007546115,0.0005237807,0.00003686682,0.0008077928,0.0002177562,0.0001013175,0.00001301231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006421212,"about_ca_system_score_gemma":0.00007187897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001098797,"about_ca_topic_score_gemma":0.000009324203,"domain_scores_codex":[0.9985927,0.000004598875,0.0002820373,0.0004687291,0.0002708287,0.0003811437],"domain_scores_gemma":[0.9994678,0.00002434367,0.0001457513,0.0001745945,0.0001186041,0.00006887153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001776958,0.0002021106,0.0083932,0.000219493,0.00007602124,0.00002750245,0.0060079,0.3411702,0.5899568,0.01583744,0.004719516,0.03337212],"study_design_scores_gemma":[0.0001752626,0.00001215116,0.00005254959,0.00007384234,0.00001685673,0.000006994339,0.0001076815,0.9693813,0.02955339,0.0002060807,0.0001996042,0.0002142969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2178031,0.00003780846,0.7789806,0.0001478699,0.00005275437,0.00003924304,0.000001307372,0.0002242336,0.002713092],"genre_scores_gemma":[0.6854144,2.633038e-7,0.314116,0.0001518211,0.00009571074,0.000003445618,0.000003213546,0.00001134613,0.0002037554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6282111,"threshold_uncertainty_score":0.6894965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056767790","doi":"10.1145/2508037.2508038","title":"Mining search and browse logs for web search","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Web search query; Terabyte; Web search engine; Search engine; Search analytics; Information retrieval; World Wide Web; Web crawler; Ranking (information retrieval); Web log analysis software; Transaction log; Metasearch engine; Database; Web page; Static web page; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.03611578898037965,"gpt":0.2776240375976158,"spread":0.2415082486172361,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002745188,0.000137511,0.0002272756,0.0006361915,0.0002834142,0.0002058446,0.0005865575,0.0001704199,0.00001584],"category_scores_gemma":[0.00003041056,0.0001190532,0.00004208523,0.000535499,0.0001362752,0.0002080798,0.0000480665,0.0001957759,0.0000423623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002192302,"about_ca_system_score_gemma":0.0000343606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004110911,"about_ca_topic_score_gemma":0.00003019524,"domain_scores_codex":[0.9987963,0.00003907269,0.0002463967,0.0004658998,0.000133699,0.0003186008],"domain_scores_gemma":[0.9988194,0.0002188879,0.00002968711,0.0007084787,0.0001325465,0.00009102903],"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":[0.000009283275,0.0001587365,0.001399669,0.0001902269,0.0002674001,0.000007528528,0.0008287375,0.0004811959,0.005615795,0.02734298,0.0006863026,0.9630122],"study_design_scores_gemma":[0.001415664,0.002123574,0.0004054016,0.0004854564,0.0001424257,0.0005513265,0.01345244,0.8992789,0.04083842,0.004940111,0.0351638,0.001202522],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1941389,0.0004939006,0.8011045,0.00351283,0.0001535422,0.0003286267,0.00001351212,0.0001998014,0.00005435816],"genre_scores_gemma":[0.9829599,0.0002333842,0.01575416,0.00003446011,0.00001884977,0.0001766349,0.00000270363,0.00001075551,0.000809184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9618096,"threshold_uncertainty_score":0.485485,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2287148974","doi":"10.1145/2888422.2888439","title":"Report on the SIGIR 2015 Workshop on Reproducibility, Inexplicability, and Generalizability of Results (RIGOR)","year":2016,"lang":"en","type":"article","venue":"ACM SIGIR Forum","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Università degli Studi di Padova","keywords":"Generalizability theory; Computer science; Presentation (obstetrics); Thursday; Information retrieval; Library science; Data science; Statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04259519423738254,"gpt":0.3006233049999692,"spread":0.2580281107625866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005688907,0.0002303333,0.0003563738,0.0000948482,0.0001641046,0.00008632347,0.001833374,0.0001002398,0.00001391268],"category_scores_gemma":[0.01669456,0.0001195423,0.0001371179,0.0005233134,0.0002956594,0.000311224,0.001604173,0.0001604857,0.00002898022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005641903,"about_ca_system_score_gemma":0.00007158014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001071751,"about_ca_topic_score_gemma":0.00004342706,"domain_scores_codex":[0.9960001,0.0002854286,0.0007569217,0.002041582,0.0005220588,0.0003939852],"domain_scores_gemma":[0.9848558,0.001966414,0.0003536961,0.01252153,0.0001779223,0.0001246765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006073102,0.00169714,0.1901527,0.00007912196,0.0003186968,0.0001051576,0.001250064,0.0001737375,0.01034418,0.05430614,0.3245273,0.4164384],"study_design_scores_gemma":[0.005299484,0.003164568,0.3087355,0.001043032,0.0002228294,0.0002348182,0.0005120747,0.005977084,0.1449754,0.3671139,0.159782,0.002939396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.849148,0.00007002734,0.004623293,0.143811,0.0002329134,0.000299111,0.00007167718,0.0001466699,0.001597285],"genre_scores_gemma":[0.9955367,0.00002904775,0.002626835,0.0007002136,0.00008035628,0.00002301538,0.00001066381,0.00001120439,0.0009819471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.413499,"threshold_uncertainty_score":0.9915882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W16404305","doi":"10.1097/01.prs.0000196262.13766.5c","title":"Proceedings of the 20th ACM conference on Hypertext and hypermedia","year":2009,"lang":"en","type":"article","venue":"ACM Conference on Hypertext","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Hypertext; Computer science; World Wide Web; Hypermedia; Presentation (obstetrics); Social media; Markup language; HTML; Multimedia; Web page; XML","retraction":null,"screen_n_in":null,"score":{"opus":0.05153949935545338,"gpt":0.2611461444505319,"spread":0.2096066450950785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003114501,0.0003647899,0.0005144836,0.0001784588,0.0002441256,0.0003526632,0.004239618,0.0001548568,0.00008467726],"category_scores_gemma":[0.001160995,0.0002458489,0.0001263344,0.0006122185,0.0002472151,0.0005011096,0.0007427784,0.0003527133,0.00009483803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002738431,"about_ca_system_score_gemma":0.0001983043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003706838,"about_ca_topic_score_gemma":0.000009964817,"domain_scores_codex":[0.9975799,0.00004860656,0.0003960335,0.000859509,0.0006377337,0.0004782698],"domain_scores_gemma":[0.9971231,0.0002140231,0.0002490106,0.001846355,0.0003267686,0.000240751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006723342,0.0005328376,0.00384689,0.00004599845,0.000108441,0.00001663431,0.002406659,0.00000513441,0.06466699,0.3999384,0.01682317,0.5115415],"study_design_scores_gemma":[0.008989932,0.009430676,0.4150101,0.0046055,0.000811359,0.0005732208,0.005578854,0.1380861,0.1121479,0.2631967,0.03477268,0.006797017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9353897,0.0001381692,0.0002841899,0.0302176,0.0003095303,0.0003095714,0.00003240467,0.0001752085,0.03314363],"genre_scores_gemma":[0.9925405,0.000226036,0.003239156,0.002890717,0.00007059478,0.00001174614,0.000004649832,0.00001264626,0.001003977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5047445,"threshold_uncertainty_score":0.9999994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2897050313","doi":"10.1145/3269206.3271728","title":"Personalizing Search Results Using Hierarchical RNN with Query-aware Attention","year":2018,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Personalization; Exploit; Information retrieval; Ranking (information retrieval); Search engine; Query expansion; Web search query; Personalized search; User information; Data mining; Quality (philosophy); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04730866175086899,"gpt":0.2962645276011868,"spread":0.2489558658503178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004555908,0.00009749857,0.0001152065,0.0001406813,0.0002805179,0.0002819615,0.0004842397,0.00003821704,0.00002493617],"category_scores_gemma":[0.00002516682,0.00007093581,0.00004690546,0.0005930249,0.0001149498,0.0005032354,0.000221084,0.000140209,0.00007933466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003205533,"about_ca_system_score_gemma":0.0000982456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005854162,"about_ca_topic_score_gemma":0.0001064766,"domain_scores_codex":[0.9986362,0.00008747328,0.000155237,0.0004554931,0.0003830338,0.0002825896],"domain_scores_gemma":[0.9991711,0.00005926506,0.00003903834,0.0004862302,0.0001423383,0.0001019758],"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":[0.001233468,0.001577581,0.1461506,0.0003125227,0.001776364,0.001031477,0.03726637,0.001949777,0.08352736,0.1949745,0.0445343,0.4856657],"study_design_scores_gemma":[0.00052364,0.0002321084,0.004181626,0.00009666451,0.0000212642,0.00006144096,0.0004051111,0.9916487,0.001259537,0.0001029226,0.001213482,0.0002534855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2668276,0.000006622179,0.7291903,0.001321394,0.00004849647,0.00003275914,0.000005935861,0.0001215289,0.002445333],"genre_scores_gemma":[0.8663108,0.000001193484,0.1322347,0.0001518209,0.0001775456,8.433261e-7,0.00001365563,0.000006189878,0.001103275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9896989,"threshold_uncertainty_score":0.2892678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1924960892","doi":"10.3127/ajis.v7i2.270","title":"Issues of Page Representation and Organisation in Web Browser's Revisitation Tools","year":2000,"lang":"en","type":"article","venue":"AJIS. Australasian journal of information systems/AJIS. Australian journal of information systems/Australian journal of information systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Representation (politics); World Wide Web; Computer science; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.02498188981610518,"gpt":0.2760008897835208,"spread":0.2510189999674157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01208184,0.0009404036,0.002866289,0.006311871,0.0003155693,0.00441742,0.002380728,0.0007275694,0.00009722515],"category_scores_gemma":[0.001117771,0.0008103133,0.0008300798,0.003025289,0.0002241075,0.08167165,0.0001007843,0.001570639,0.0001808519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008220735,"about_ca_system_score_gemma":0.001253167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842055,"about_ca_topic_score_gemma":0.000004315445,"domain_scores_codex":[0.9750916,0.001370379,0.01829006,0.0002443473,0.004096398,0.0009072062],"domain_scores_gemma":[0.9620155,0.0004120256,0.02850694,0.0009093567,0.007236162,0.0009200014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"qualitative","study_design_scores_codex":[0.003177678,0.000682477,0.04452636,0.01571291,0.004921926,0.0004903943,0.1609099,0.5140029,0.002982648,0.01800625,0.148788,0.08579855],"study_design_scores_gemma":[0.03575918,0.009601571,0.05580208,0.04106551,0.001920573,0.08386828,0.41642,0.02766682,0.006281618,0.0002643989,0.3161393,0.00521063],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8788094,0.001995434,0.09240542,0.00504024,0.01237693,0.00409717,0.000897135,0.0001884367,0.004189869],"genre_scores_gemma":[0.9933439,0.0007445985,0.004587596,0.00009303173,0.0006791595,0.00001291217,0.0001297016,0.00003246639,0.0003765886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4863361,"threshold_uncertainty_score":0.9994348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148387158","doi":"10.1145/1557914.1557947","title":"Individual and social behavior in tagging systems","year":2009,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Pairwise comparison; Reuse; Similarity (geometry); Metric (unit); Information retrieval; Tag system; Recommender system; World Wide Web; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02698872560099214,"gpt":0.2641396343212282,"spread":0.2371509087202361,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000182012,0.0000437595,0.00008222362,0.0000982053,0.00005455116,0.0002104471,0.0002354337,0.00002409631,0.000002126288],"category_scores_gemma":[0.000003562247,0.00003830098,0.00001359935,0.0001716214,0.000008595397,0.0002360515,0.00006329123,0.00004804806,0.000005292476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006726629,"about_ca_system_score_gemma":0.00001005228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007820634,"about_ca_topic_score_gemma":0.000008814982,"domain_scores_codex":[0.9995086,0.00002145218,0.00009300386,0.0001538777,0.0001090708,0.0001140235],"domain_scores_gemma":[0.9998389,0.0000115586,0.00002073698,0.0001011376,0.000007072937,0.00002061065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000002435696,0.000267001,0.06680293,0.00001525811,0.00002705303,0.0001530988,0.006716759,0.00004387744,0.001304787,0.2174672,0.006470977,0.7007287],"study_design_scores_gemma":[0.001078206,0.000256458,0.8926395,0.00004130662,0.00006578046,0.00006256284,0.001621049,0.09811787,0.0002640695,0.0004823629,0.004657537,0.000713328],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9663595,0.0000856889,0.02903034,0.001826687,0.00008741144,0.00006274474,0.00000460578,0.0001364989,0.002406503],"genre_scores_gemma":[0.9968836,0.000001268793,0.002725734,0.0002223863,0.00002911386,0.00000209646,0.000003283216,9.551472e-7,0.0001315577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8258365,"threshold_uncertainty_score":0.2029346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285540454","doi":"10.52458/978-93-91842-08-6-38","title":"Web Scraping Techniques and Applications: A Literature Review","year":2021,"lang":"en","type":"review","venue":"Soft Computing Research Society eBooks","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cégep de Chicoutimi; Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; World Wide Web; Web intelligence; Big data; Data science; Web mining; Web analytics; Web application; Analytics; Social media; Web standards; Web development; Web engineering; Web modeling; The Internet; Web page; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0854457235976239,"gpt":0.4236613379830667,"spread":0.3382156143854428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005636099,0.0004778932,0.001711047,0.0002721169,0.0009693469,0.001493235,0.002332933,0.000401508,0.000002560131],"category_scores_gemma":[0.0002678318,0.0004070455,0.001016715,0.002103393,0.0002898014,0.000158527,0.003452264,0.002303989,0.00001518285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691963,"about_ca_system_score_gemma":0.001127404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005702033,"about_ca_topic_score_gemma":5.556943e-7,"domain_scores_codex":[0.9949663,0.001028073,0.0007784807,0.00149605,0.0009389654,0.00079208],"domain_scores_gemma":[0.9953763,0.001521798,0.0003286768,0.00183605,0.0006976274,0.0002395755],"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":[4.546244e-8,0.00001290574,2.03901e-7,0.0458517,0.0001431128,0.0000301363,0.0001949213,1.914527e-8,4.180214e-7,0.001426457,0.013433,0.9389071],"study_design_scores_gemma":[0.00003414802,0.00001537174,1.712722e-8,0.2018708,0.000100301,0.0001573805,0.000018705,0.0005531427,8.731259e-7,0.0001396995,0.7968107,0.0002988942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.50666e-8,0.9748182,0.021992,0.0001707925,0.00002929275,0.001051031,0.00002552821,0.0004335192,0.001479612],"genre_scores_gemma":[2.127265e-7,0.9466663,0.05105902,0.0002523531,0.0005465426,0.0003032565,0.0001303793,0.00004354031,0.0009984055],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9386082,"threshold_uncertainty_score":0.9999977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169558036","doi":"10.1109/dnsr.2004.1344744","title":"The reconstruction of user sessions from a server log using improved time-oriented heuristics","year":2004,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"Computer science; Heuristics; Web log analysis software; Web mining; Web server; Personalization; Web page; Web modeling; Web service; Clickstream; Data Web; World Wide Web; Web navigation; Adaptation (eye); Information retrieval; Data mining; Static web page; Web API; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.01334641712887633,"gpt":0.2362877217104381,"spread":0.2229413045815618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001394157,0.00007154096,0.0001083265,0.00004031309,0.0001884496,0.00007424261,0.0003644151,0.00003797783,0.0000253195],"category_scores_gemma":[0.00007263842,0.00004580879,0.00005663206,0.0003435577,0.00005550013,0.0002542058,0.0001700941,0.00007052598,0.00001840334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002708291,"about_ca_system_score_gemma":0.00008691512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009378663,"about_ca_topic_score_gemma":0.00006745541,"domain_scores_codex":[0.9993039,0.0000359722,0.0002073047,0.0002029414,0.0001223887,0.0001274718],"domain_scores_gemma":[0.9991316,0.00008525747,0.0001129078,0.0005321513,0.00009474252,0.00004332765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009518638,0.0009269143,0.02570366,0.00004540853,0.00149859,0.00004069803,0.00373645,0.01477844,0.5443623,0.1247738,0.003950514,0.280088],"study_design_scores_gemma":[0.000996844,0.00007261782,0.003653369,0.0001292996,0.0001233997,0.00002667644,0.0004204421,0.9582254,0.02689674,0.007399347,0.001705248,0.0003506604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4416469,0.00001585058,0.5576363,0.0002272331,0.0001889874,0.00003088576,0.00001362158,0.00004956725,0.0001906942],"genre_scores_gemma":[0.7011146,0.00001071143,0.2981429,0.00007371541,0.00005607366,0.000001346285,0.00001329207,0.000006275779,0.000581141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9434469,"threshold_uncertainty_score":0.1868028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121415061","doi":"10.1109/iv.2006.108","title":"The Visual Exploration ofWeb Search Results Using HotMap","year":2006,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Information retrieval; Search engine; Relevance (law); Set (abstract data type); Representation (politics); Result set; World Wide Web; Web search query; Usability; Search analytics; Visual search; Web search engine; Human–computer interaction; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04998496559217664,"gpt":0.3085191218787094,"spread":0.2585341562865328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005498992,0.00005445264,0.00005396263,0.00005288069,0.0003257481,0.0004487406,0.0004219547,0.00001997235,0.00000242774],"category_scores_gemma":[0.00002586276,0.00003430892,0.0000322318,0.000414373,0.00002839154,0.0005877218,0.0001452988,0.00005413917,0.00006498668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001752504,"about_ca_system_score_gemma":0.00004309808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007233802,"about_ca_topic_score_gemma":0.0001391153,"domain_scores_codex":[0.9991392,0.00006787885,0.0001634802,0.0002093912,0.0002483316,0.0001717354],"domain_scores_gemma":[0.9994138,0.00009922279,0.00003486314,0.0003672791,0.00005968941,0.00002514642],"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":[0.00008808843,0.0004824391,0.002092901,0.00001762791,0.000137282,0.00006760365,0.002722217,0.04813847,0.04677812,0.3910393,0.1051989,0.4032371],"study_design_scores_gemma":[0.0001437695,0.00002412525,0.0004120232,0.000004634672,0.000004038687,0.000002234723,0.0001512734,0.9875846,0.005727764,0.0008308479,0.005031805,0.00008288389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05829673,0.00002946235,0.93405,0.002125709,0.000091036,0.00003522509,0.000002298189,0.0001066628,0.005262888],"genre_scores_gemma":[0.9633607,0.000006435266,0.03374698,0.00005775253,0.0001436466,0.00000145245,0.00001482099,0.000003432258,0.002664835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9394462,"threshold_uncertainty_score":0.4327216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1554796723","doi":"10.1007/3-540-46105-1_24","title":"Finding Similar Queries to Satisfy Searches Based on Query Traces","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Web query classification; Search engine; Web search query; Similarity (geometry); Query expansion; Task (project management); Spatial query; Disappointment; Query language; Sargable; Query optimization; Variety (cybernetics); Search-oriented architecture; Ranking (information retrieval); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03937416903002822,"gpt":0.2637484585050917,"spread":0.2243742894750635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001167484,0.0006014308,0.0006371252,0.001768657,0.0004615523,0.001100554,0.00379756,0.0002721098,0.00006721223],"category_scores_gemma":[0.0002873261,0.0005366949,0.0001871673,0.00119089,0.0005087567,0.0005768954,0.0009291545,0.0008277013,0.0001495621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002758415,"about_ca_system_score_gemma":0.000373732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004551803,"about_ca_topic_score_gemma":0.00008412842,"domain_scores_codex":[0.9952608,0.00007260671,0.0004866833,0.001916393,0.001461335,0.0008022112],"domain_scores_gemma":[0.9965404,0.0009385483,0.000198266,0.001872521,0.0001520444,0.0002982607],"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":[0.000008466676,0.0000522146,0.0002886976,0.00006116087,0.00002282662,0.0002205634,0.001491291,0.2256036,0.0001070367,0.007580612,0.0004731295,0.7640904],"study_design_scores_gemma":[0.0001609649,0.0003313388,0.0001726876,0.0008246358,0.00001162947,0.00001361267,5.346919e-7,0.982362,0.001455045,0.009603576,0.004202298,0.0008616436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001812926,0.000137525,0.9908921,0.004495827,0.0006106819,0.0002136499,0.00002073784,0.0001991289,0.003249054],"genre_scores_gemma":[0.2744487,0.00004246942,0.7155328,0.007958628,0.0006132125,0.00001931139,0.00001692334,0.00006438691,0.001303645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7632288,"threshold_uncertainty_score":0.9999364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806438009","doi":"10.1007/978-3-540-85902-4_35","title":"University of Waterloo at INEX2007: Adhoc and Link-the-Wiki Tracks","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Link (geometry); XML; Embedding; Track (disk drive); Context (archaeology); Point (geometry); Information retrieval; World Wide Web; Computer network; Artificial intelligence; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01357757496992636,"gpt":0.1988799585418461,"spread":0.1853023835719198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000529225,0.0003109271,0.0004480527,0.00040393,0.0004002328,0.0001233581,0.002795719,0.0002099353,0.00001826918],"category_scores_gemma":[0.00003395913,0.0002431972,0.0001217712,0.0004577551,0.001317802,0.0003515889,0.001895775,0.0004653116,0.00002209153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000107951,"about_ca_system_score_gemma":0.0002253806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001667934,"about_ca_topic_score_gemma":0.0003241635,"domain_scores_codex":[0.9976824,0.0000375174,0.000291274,0.00101745,0.0005963483,0.0003750154],"domain_scores_gemma":[0.9979166,0.0003336794,0.0002472558,0.0012323,0.0001458103,0.0001243725],"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":[0.0000110328,0.00002168343,0.0002709739,0.00003741709,0.00003926875,0.0001986697,0.005800331,0.007561986,0.0001525581,0.001436453,0.0003115128,0.9841581],"study_design_scores_gemma":[0.001107841,0.0005276566,0.00173326,0.0007771949,0.0001021623,0.0005765427,0.000003771647,0.9036919,0.002474292,0.01317039,0.07406417,0.001770835],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002962731,0.0008609173,0.992904,0.001401823,0.0003965991,0.0001401271,0.00001596574,0.00007098894,0.001246838],"genre_scores_gemma":[0.5828026,0.0021359,0.402157,0.001730227,0.000800528,0.000001215432,0.00003606976,0.00006082956,0.01027567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9823873,"threshold_uncertainty_score":0.9917295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1570003767","doi":"","title":"Predicting Future User Actions by Observing Unmodified Applications","year":2000,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; User interface; User modeling; Human–computer interaction; State space; Software; User interface design; State (computer science); Space (punctuation); Machine learning; Artificial intelligence; Distributed computing; Data mining; User experience design; Algorithm; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01742366038573868,"gpt":0.2458363644001544,"spread":0.2284127040144157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009159742,0.00007899159,0.00008043695,0.00004097855,0.0002991618,0.0001854528,0.0006656445,0.0000429607,0.0003795016],"category_scores_gemma":[0.000004011441,0.00006975391,0.00004746606,0.0005478923,0.00001181949,0.0004989006,0.00007212994,0.000100909,0.0002314444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001511112,"about_ca_system_score_gemma":0.00002042031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001225592,"about_ca_topic_score_gemma":0.00002781328,"domain_scores_codex":[0.9992369,0.00002148271,0.00013604,0.0002996668,0.0001358646,0.0001700622],"domain_scores_gemma":[0.9992069,0.00003747206,0.00003036392,0.0006220203,0.00002669108,0.00007652646],"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":[0.000002408618,0.000245131,0.01035876,0.00001510838,0.0001375638,0.000002408073,0.0008412896,0.001051849,0.00301354,0.03915663,0.1358749,0.8093004],"study_design_scores_gemma":[0.0001540038,0.00001235471,0.002079377,0.000007860154,0.00002679736,0.000006983413,0.0002773947,0.1233153,0.0006982228,0.0002458891,0.872946,0.000229787],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02610156,0.0001582013,0.9275281,0.004710194,0.00009673371,0.0001241312,0.00003135083,0.0008160647,0.04043365],"genre_scores_gemma":[0.7951894,0.0001731115,0.1441858,0.001674481,0.0008150789,0.0001643191,0.0001562655,0.00002282837,0.05761872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8090706,"threshold_uncertainty_score":0.4155276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W15738104","doi":"10.1145/2488388.2488459","title":"Imagen","year":2013,"lang":"es","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; JavaScript; HTML5; Session (web analytics); Web browser; Rich Internet application; World Wide Web; Client-side scripting; Snapshot (computer storage); Operating system; Web application; Multimedia; Web page; Web API; The Internet; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.01083153206537008,"gpt":0.2287507717079443,"spread":0.2179192396425742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001075273,0.00009784725,0.0001209663,0.00007315376,0.0000764355,0.001062736,0.000771845,0.00003563838,0.003242724],"category_scores_gemma":[0.00002478562,0.00007665391,0.00007321291,0.0003317301,0.00003347128,0.0007540586,0.0003387251,0.00006341564,0.02281177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007691461,"about_ca_system_score_gemma":0.00003051979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008154197,"about_ca_topic_score_gemma":0.000001820248,"domain_scores_codex":[0.9991319,0.00003494187,0.0001446069,0.000300164,0.0001601369,0.0002282916],"domain_scores_gemma":[0.9990836,0.00003708576,0.00003956318,0.0006608194,0.00007146878,0.0001074405],"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":[3.044697e-7,0.00008703656,0.006763571,0.00001963207,0.0001028707,0.00001184166,0.0002932627,0.000009789789,0.002284968,0.06579296,0.3930559,0.5315778],"study_design_scores_gemma":[0.0003573532,0.0001243558,0.07436608,0.00007338196,0.00008724649,0.00001761489,0.0002330022,0.6584652,0.004184486,0.003138218,0.2581039,0.0008490986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06958611,0.0005173559,0.5101651,0.0234556,0.000529278,0.0001798024,0.00001229461,0.0004255816,0.3951289],"genre_scores_gemma":[0.9265001,0.00003862672,0.04549109,0.0009001059,0.0001369241,0.00000589758,0.000004909972,0.000006007364,0.02691627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.856914,"threshold_uncertainty_score":0.9999743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2793625150","doi":"10.1002/asi.24048","title":"If these crawls could talk: Studying and documenting web archives provenance","year":2018,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"World Wide Web; Computer science; Transparency (behavior); Context (archaeology); Data science; Process (computing); Geography; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.009031874620079431,"gpt":0.2572771037646895,"spread":0.2482452291446101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002150562,0.00004981274,0.0001060115,0.0004601546,0.0004679193,0.0003866922,0.0007011126,0.00004008817,3.072747e-7],"category_scores_gemma":[0.001942466,0.0000319467,0.00002628307,0.001077252,0.0002343643,0.003329937,0.0002822742,0.0001082773,0.000001187654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005089272,"about_ca_system_score_gemma":0.0001522767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001262643,"about_ca_topic_score_gemma":0.000001134982,"domain_scores_codex":[0.9990699,0.00001534346,0.0003035967,0.00007754128,0.0003764717,0.0001571238],"domain_scores_gemma":[0.9981992,0.0001051685,0.0009151616,0.0001553424,0.0005981321,0.00002704936],"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":[0.00002127415,0.00006679184,0.1036576,0.00004514571,0.0001622434,7.037663e-7,0.01654205,0.00003798578,0.02249401,0.2451307,0.002368282,0.6094733],"study_design_scores_gemma":[0.004280523,0.001440921,0.06303629,0.0004357376,0.0001900799,0.0002829324,0.01127026,0.2957872,0.06294978,0.1122489,0.4473016,0.0007758298],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9213243,0.00008337849,0.0508798,0.02392402,0.0006254092,0.0002826922,0.000008878811,0.00006970823,0.002801787],"genre_scores_gemma":[0.9934469,0.00003329608,0.006200859,0.0001903683,0.00003443585,0.000002646181,1.394051e-7,9.521822e-7,0.00009036021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6086974,"threshold_uncertainty_score":0.3728882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034607275","doi":"10.1145/1046456.1046459","title":"Learning important models for web page blocks based on layout and content analysis","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Web page; Block (permutation group theory); Information retrieval; Partition (number theory); Page view; Static web page; Data mining; World Wide Web; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.07156513468895788,"gpt":0.263723749372729,"spread":0.1921586146837712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003536036,0.0002002775,0.0002997896,0.0004805945,0.0003528921,0.0003548443,0.0005988899,0.00006687111,0.00001193282],"category_scores_gemma":[0.0002069578,0.0001754638,0.0002084373,0.0008906577,0.00004138863,0.0007449358,0.0001484178,0.0001644543,0.00001490417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004178306,"about_ca_system_score_gemma":0.00007187721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006150408,"about_ca_topic_score_gemma":0.0000766659,"domain_scores_codex":[0.9983951,0.00005916821,0.0003922141,0.0005910995,0.0002661491,0.0002962322],"domain_scores_gemma":[0.9983237,0.0002316802,0.0001560139,0.001065966,0.0001071866,0.0001154421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003270999,0.0002920232,0.006642864,0.0000169159,0.0008355855,0.00004607904,0.003073836,0.9574893,0.01300381,0.008258896,0.005671036,0.004637022],"study_design_scores_gemma":[0.0008253599,0.0001712054,0.000175635,0.0000185297,0.0003128498,0.000001281562,0.0002350106,0.9943652,0.0007692239,0.001617438,0.001228807,0.0002794721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1240727,0.00003243297,0.851975,0.0234238,0.00005197617,0.000171194,0.00003146431,0.0001541,0.00008732],"genre_scores_gemma":[0.9279734,0.000009580306,0.06680482,0.004679256,0.00007397772,0.0001224311,0.0001640408,0.00001373546,0.0001587926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8039007,"threshold_uncertainty_score":0.7155205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004193186","doi":"10.1145/584931.584940","title":"A framework for web table mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Table (database); Web page; Information retrieval; World Wide Web; Web mining; Table of contents; Information extraction; Process (computing); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.04721870685743441,"gpt":0.2677927006460024,"spread":0.220573993788568,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001171398,0.00005669616,0.0000884178,0.00005366192,0.00009323288,0.000158507,0.0004950073,0.00003462961,0.0002314135],"category_scores_gemma":[0.0001072721,0.00004751666,0.00004533713,0.0003559986,0.000008941631,0.0002468905,0.00008864133,0.00003758592,0.0001229213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005876903,"about_ca_system_score_gemma":0.000008292463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006109663,"about_ca_topic_score_gemma":0.000002611293,"domain_scores_codex":[0.9993995,0.000008424297,0.00009312033,0.000221597,0.00008975797,0.000187641],"domain_scores_gemma":[0.9993388,0.0001588233,0.00002743993,0.0003995751,0.00002536243,0.0000499837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001181367,0.00009965175,0.001236666,0.00001428983,0.00006273838,0.000006697542,0.0009685101,0.0000802383,0.0004038124,0.4920527,0.3233583,0.1817151],"study_design_scores_gemma":[0.0001175315,0.00003603698,0.00003439834,0.00001616208,0.000008601788,0.000002815118,0.00006657362,0.8842532,0.000288478,0.003680669,0.1113669,0.0001285891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002208981,0.00008689753,0.984776,0.001496203,0.00009847465,0.00002987228,0.000003741252,0.0001512496,0.01114855],"genre_scores_gemma":[0.2172014,0.00000539847,0.7761476,0.0005835572,0.00006845301,0.00001054832,0.000001478058,0.000003655254,0.005977941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.884173,"threshold_uncertainty_score":0.2533816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W130931946","doi":"10.1007/978-1-4615-1507-4_16","title":"Recent Advances in Tabu Search","year":2002,"lang":"en","type":"book-chapter","venue":"Operations research, computer science. Interface series","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Tabu search; Guided Local Search; Focus (optics); Computer science; Field (mathematics); Hill climbing; Artificial intelligence; Mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.07058871474709118,"gpt":0.3526118933868006,"spread":0.2820231786397094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003195598,0.0004753377,0.0005747213,0.002667745,0.001334718,0.003454703,0.005905786,0.0002037466,0.001246219],"category_scores_gemma":[0.000142102,0.0004335908,0.0001201777,0.002114982,0.002201885,0.005929175,0.003836223,0.001506526,0.0008956005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005405701,"about_ca_system_score_gemma":0.001047944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006470268,"about_ca_topic_score_gemma":0.0007609226,"domain_scores_codex":[0.9933782,0.0002238397,0.0007478735,0.001930188,0.002523642,0.001196216],"domain_scores_gemma":[0.9955798,0.0001642405,0.00006601163,0.002227498,0.001595742,0.0003667385],"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":[0.00001385869,0.0001555268,0.00001529062,0.00005392542,0.0000486275,0.0001567691,0.003486058,0.03262949,0.0002209781,0.3048886,0.01208904,0.6462418],"study_design_scores_gemma":[0.0001707018,0.0004091936,0.00001462054,0.0003756449,0.000004607826,0.00005324701,0.0000839166,0.3910233,0.001059623,0.001918746,0.6043121,0.0005741983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002758111,0.01547569,0.4177156,0.01057429,0.001992477,0.001212948,0.0001117964,0.000425363,0.552216],"genre_scores_gemma":[0.009248008,0.0621475,0.1616708,0.0002598437,0.000705166,0.0001082975,0.00005279079,0.0001007308,0.7657069],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6456677,"threshold_uncertainty_score":0.9999654,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167213883","doi":"10.1145/2047196.2047224","title":"Query-feature graphs","year":2011,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; USable; Web query classification; Feature (linguistics); Information retrieval; Graphics; Web search query; Search engine; Theoretical computer science; World Wide Web; Computer graphics (images)","retraction":null,"screen_n_in":null,"score":{"opus":0.02612589293753511,"gpt":0.2131534380683716,"spread":0.1870275451308365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008495395,0.00004942056,0.00005898312,0.00006572879,0.00004038153,0.00004271934,0.0005861491,0.00002572202,0.0001552371],"category_scores_gemma":[0.000007847414,0.00003591947,0.00004674369,0.0003047886,0.00001317456,0.0002634584,0.0001111101,0.0000505403,0.0001848164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000234876,"about_ca_system_score_gemma":0.00001087108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001129213,"about_ca_topic_score_gemma":0.00001771076,"domain_scores_codex":[0.9995664,0.00001372237,0.00004975892,0.0001757113,0.00008264052,0.0001118163],"domain_scores_gemma":[0.9994518,0.000008789099,0.00001705764,0.0004544425,0.00001933037,0.00004854925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001283204,0.00006419521,0.007951891,0.000003196755,0.00004795453,0.00003157277,0.001171171,6.338596e-7,0.0002963851,0.8106776,0.1193157,0.06043842],"study_design_scores_gemma":[0.001698446,0.0006616171,0.1896765,0.00009833591,0.0001900676,0.0002110339,0.001133686,0.09706364,0.06181862,0.1738527,0.4703353,0.003260002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009700574,0.00009005867,0.6491408,0.0008949235,0.0002264565,0.00002953418,0.000002308768,0.0004781009,0.3394372],"genre_scores_gemma":[0.7098071,0.000008874708,0.2783869,0.0007101046,0.00002007375,0.000002206249,0.000002837633,0.000003309974,0.01105863],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7001065,"threshold_uncertainty_score":0.2375503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1870211331","doi":"10.1007/11944935_13","title":"Text Mining Through Semi Automatic Semantic Annotation","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Queen's University","funders":"","keywords":"Annotation; Computer science; Semantic annotation; Information retrieval; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01645471353785901,"gpt":0.2481572614898082,"spread":0.2317025479519492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007634613,0.0005578172,0.0006417283,0.0008304099,0.0003502003,0.0009510412,0.003156659,0.0002816799,0.0000234946],"category_scores_gemma":[0.0001073857,0.0005152645,0.0001739661,0.00117266,0.0004654852,0.001190247,0.001005871,0.0005345498,0.0001040846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000221457,"about_ca_system_score_gemma":0.0004135201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009331155,"about_ca_topic_score_gemma":0.00007612987,"domain_scores_codex":[0.9957564,0.00004717959,0.0006934504,0.001669013,0.001141208,0.0006927483],"domain_scores_gemma":[0.9970496,0.0005460088,0.0004433478,0.00166203,0.0001936129,0.0001053665],"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":[0.000001308182,0.00004537244,0.0001665938,0.0001076725,0.00003559149,0.0001905563,0.002131153,0.07717852,0.0001702909,0.005783079,0.0008573057,0.9133326],"study_design_scores_gemma":[0.0001641291,0.00007529391,0.0002090262,0.000616482,0.00002696097,0.00006393519,4.874441e-7,0.9655421,0.000362475,0.03105261,0.001236933,0.0006495703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005542247,0.0003281872,0.9914007,0.000660244,0.0008599896,0.0001749663,0.000008029298,0.0003128108,0.005700812],"genre_scores_gemma":[0.2694538,0.00002347933,0.7273995,0.001275486,0.0005368557,0.00000859528,0.00004624562,0.00004699277,0.001209037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.912683,"threshold_uncertainty_score":0.9997299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110780226","doi":"10.1145/1031453.1031458","title":"Probabilistic models for focused web crawling","year":2004,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Mitacs","keywords":"CRFS; Crawling; Computer science; Conditional random field; Hidden Markov model; Web crawler; Probabilistic logic; Context (archaeology); Relevance (law); Artificial intelligence; Web page; Machine learning; Information retrieval; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03819472388232283,"gpt":0.2513862193380534,"spread":0.2131914954557306,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001809545,0.00007208861,0.0001040583,0.00006251258,0.00009119912,0.0001418294,0.000526754,0.0000258511,0.000004320128],"category_scores_gemma":[0.00005136069,0.00005804471,0.00006924535,0.0002253588,0.00001433154,0.0004123337,0.00008893119,0.00003413849,0.0000241066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002531919,"about_ca_system_score_gemma":0.00009767306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003497794,"about_ca_topic_score_gemma":0.00003152163,"domain_scores_codex":[0.9992788,0.000007434523,0.0001316334,0.0002836322,0.000112695,0.000185801],"domain_scores_gemma":[0.9993896,0.00005512786,0.00002933769,0.0004154501,0.00005469858,0.00005580628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003667182,0.0001105114,0.00001572174,0.00002848168,0.00003985649,0.000004128738,0.0004460265,0.1215669,0.00126328,0.851074,0.0007363201,0.0247111],"study_design_scores_gemma":[0.000363364,0.00003481131,0.000003702689,0.00001102262,0.000009669058,0.000001459414,0.000009662352,0.8530109,0.0009054922,0.1450061,0.0005428778,0.0001009731],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005660754,0.00001780369,0.9906815,0.001248732,0.00005709464,0.00008891656,0.000004258619,0.0001966984,0.002044259],"genre_scores_gemma":[0.6617559,0.000001300644,0.337736,0.0001547639,0.00002964726,0.00001766122,0.000003392564,0.000003853642,0.0002975781],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7314439,"threshold_uncertainty_score":0.2366995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963451689","doi":"","title":"SocialScope: Enabling Information Discovery on Social Content Sites","year":2009,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; World Wide Web; Presentation (obstetrics); Data science; Information sharing; Content management; Knowledge management","retraction":null,"screen_n_in":null,"score":{"opus":0.05891721385290173,"gpt":0.2718646654349444,"spread":0.2129474515820426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001824203,0.00007022098,0.000102873,0.00009214316,0.0001895476,0.000590571,0.0003274734,0.00003139898,0.00001039223],"category_scores_gemma":[0.00004790103,0.00005535729,0.00006562032,0.0002314678,0.00001066027,0.002566254,0.00005048092,0.00005918811,0.0001304689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002500758,"about_ca_system_score_gemma":0.00002820465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002362115,"about_ca_topic_score_gemma":0.000002908902,"domain_scores_codex":[0.9993531,0.00002221606,0.0001622197,0.0001158767,0.0002009424,0.0001456635],"domain_scores_gemma":[0.9996758,0.00003117074,0.00006702522,0.0001579657,0.00004123115,0.00002678504],"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":[0.00001005224,0.00009862275,0.0002391697,0.000005341146,0.0000361282,0.000002800444,0.002283463,0.0000845,0.002785275,0.3636734,0.02818101,0.6026003],"study_design_scores_gemma":[0.009037825,0.002783619,0.2875828,0.0003660825,0.0003223227,0.00002581931,0.0134215,0.324215,0.1270061,0.04587077,0.1831053,0.006262828],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1760098,0.0000320653,0.7794191,0.01326325,0.0001843504,0.0001025032,0.00001364703,0.0003991539,0.03057615],"genre_scores_gemma":[0.9920069,0.000007290455,0.00381569,0.003378635,0.0001071138,0.0000012647,0.00003029024,0.000001174044,0.0006516661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8159971,"threshold_uncertainty_score":0.569489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W23637940","doi":"10.1371/journal.pone.0061981","title":"Crawling rich internet applications: the state of the art","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Crawling; Computer science; Ajax; World Wide Web; Web crawler; The Internet; Web application; Asynchronous communication; Rich Internet application; State (computer science); Server; Multimedia; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.04276188563729921,"gpt":0.2296142188181238,"spread":0.1868523331808246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002846614,0.00003987207,0.00006931563,0.00002096798,0.00005090626,0.0000375636,0.000829811,0.000008566532,0.000008143968],"category_scores_gemma":[0.00003201186,0.00002152931,0.00002778097,0.0002930466,0.00003212141,0.0001496021,0.0002533517,0.00006929518,0.0001284546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006599036,"about_ca_system_score_gemma":0.00001008472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001362127,"about_ca_topic_score_gemma":0.000003590977,"domain_scores_codex":[0.9994637,0.00003996899,0.0001095305,0.00008895311,0.0001873871,0.0001104643],"domain_scores_gemma":[0.9991848,0.00007590777,0.00007415729,0.0006054518,0.00003713235,0.00002257644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002053453,0.0127527,0.332672,0.0004874157,0.004333219,0.000001629167,0.04832392,0.0004246315,0.2174969,0.06860824,0.03144264,0.2834362],"study_design_scores_gemma":[0.0004793257,0.0000853222,0.0417241,0.0004609114,0.0006289574,0.000005838112,0.0003175552,0.1727744,0.732846,0.008197951,0.04181616,0.0006635024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5334896,0.0006715035,0.4591759,0.003214632,0.00006547872,0.0002599996,0.00001434129,0.00009025733,0.003018289],"genre_scores_gemma":[0.9898269,0.00001525247,0.00810725,0.000172737,0.00005026986,0.00002599445,0.000001872906,0.000002767197,0.001796994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5153491,"threshold_uncertainty_score":0.1651067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4251596819","doi":"10.1007/978-3-540-78646-7_22","title":"Automatic Extraction of Domain-Specific Stopwords from Labeled Documents","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Classifier (UML); Information loss; Filter (signal processing); Data mining; Set (abstract data type); Artificial intelligence; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.01686015710638942,"gpt":0.2507353239094569,"spread":0.2338751668030674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005685133,0.0004611121,0.0007144873,0.0009218386,0.00022429,0.0003105444,0.00324057,0.0002685499,0.00009807832],"category_scores_gemma":[0.00002816236,0.0004235386,0.0001835756,0.0008394179,0.0005470251,0.0008323549,0.0008830786,0.0005886424,0.00007184635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000241596,"about_ca_system_score_gemma":0.0003357242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009649203,"about_ca_topic_score_gemma":0.00003643994,"domain_scores_codex":[0.9960269,0.00005559881,0.0007367163,0.001409783,0.001294151,0.0004768731],"domain_scores_gemma":[0.9966972,0.0005081561,0.0005803902,0.001882266,0.0001896217,0.0001423012],"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":[0.000005330824,0.00008038662,0.000136131,0.00002757705,0.00006076199,0.0001644221,0.001761362,0.00359744,0.001781219,0.003539741,0.000313313,0.9885323],"study_design_scores_gemma":[0.001720727,0.000497993,0.002765621,0.002203528,0.00007830363,0.000229893,0.000002212671,0.7865798,0.008852035,0.1558921,0.03845384,0.002723909],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005549271,0.0008302531,0.9907745,0.0002089819,0.00116562,0.0001661493,0.00002022944,0.0001387368,0.001146309],"genre_scores_gemma":[0.1770677,0.0003736501,0.821592,0.0002720333,0.0003798171,0.000005874115,0.00003567184,0.00003178826,0.0002414825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9858084,"threshold_uncertainty_score":0.9998217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166367071","doi":"10.1109/wi.2006.103","title":"Interactive Web Information Retrieval Using WordBars","year":2006,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Information retrieval; Web query classification; Web search query; Query expansion; Set (abstract data type); sort; Result set; Search engine; Query language; World Wide Web; Information needs","retraction":null,"screen_n_in":null,"score":{"opus":0.009736650522841726,"gpt":0.2347955252822921,"spread":0.2250588747594504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001211767,0.00005272263,0.00006373247,0.000133256,0.00006088534,0.0002459956,0.0002755061,0.00002139104,0.00002657708],"category_scores_gemma":[0.00002434557,0.00004501192,0.00003405434,0.0004461848,0.00001055464,0.002385691,0.0001106495,0.00005350113,0.0001165509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003277053,"about_ca_system_score_gemma":0.00003827223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002087054,"about_ca_topic_score_gemma":0.000008439682,"domain_scores_codex":[0.9994941,0.00001668424,0.0001460108,0.00009659526,0.0001395283,0.0001070685],"domain_scores_gemma":[0.9996101,0.00002792133,0.00006222152,0.000224137,0.00005381659,0.00002186408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001810281,0.0006680457,0.02716201,0.00009049876,0.0004972948,0.0000878049,0.007013578,0.04171094,0.07176636,0.3991368,0.1966652,0.2550204],"study_design_scores_gemma":[0.0001564354,0.0000135066,0.0008355207,0.00001043946,0.000007923043,0.000008386565,0.00009421077,0.9808185,0.004265213,0.0005262863,0.01314248,0.0001211025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1519666,0.00000655389,0.8311692,0.0003414646,0.0001634644,0.00002679883,0.000003425284,0.0001498127,0.01617264],"genre_scores_gemma":[0.9451444,7.61142e-7,0.05418165,0.0001789417,0.00004797742,1.503867e-7,0.00001418777,0.00000148407,0.0004304101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391075,"threshold_uncertainty_score":0.2372141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166597489","doi":"10.1145/1978942.1979205","title":"Characterizing the usability of interactive applications through query log analysis","year":2011,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Usability; Computer science; Troubleshooting; Web search query; Set (abstract data type); Information retrieval; Selection (genetic algorithm); Web query classification; Process (computing); Product (mathematics); Usability inspection; The Internet; Query expansion; Heuristic evaluation; Search engine; World Wide Web; Human–computer interaction; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04529209062245151,"gpt":0.2802455875017747,"spread":0.2349534968793232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003188915,0.00007252478,0.0001790326,0.00007824323,0.00008758426,0.00003905104,0.0009321092,0.00002273646,0.0001229434],"category_scores_gemma":[0.00002951417,0.00004494188,0.0001694933,0.001258616,0.00008784665,0.0005445027,0.0002527868,0.00007729168,0.00002965819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001293342,"about_ca_system_score_gemma":0.00002175081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009591319,"about_ca_topic_score_gemma":0.00008260845,"domain_scores_codex":[0.9991742,0.00007655077,0.000238823,0.00027904,0.0001191405,0.0001122739],"domain_scores_gemma":[0.9985272,0.0001520283,0.0001512355,0.001059335,0.00008545937,0.00002476725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000361793,0.001860574,0.2336857,0.0000595956,0.007272086,0.000005132416,0.06896123,0.00008254909,0.01379169,0.5024407,0.0008689251,0.1709357],"study_design_scores_gemma":[0.0004156442,0.0001886455,0.7102805,0.00003524679,0.002672519,0.00001104619,0.007613963,0.1178626,0.1165699,0.02780573,0.0154628,0.001081399],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02670684,0.0000124502,0.9578514,0.0003709406,0.00002332717,0.00006712082,0.000009090495,0.0000511492,0.0149077],"genre_scores_gemma":[0.9616671,0.000006680943,0.03795437,0.0002057652,0.00001498642,0.00002562172,0.000007813777,0.000001870671,0.0001158451],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9349602,"threshold_uncertainty_score":0.1832677,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972495172","doi":"10.1145/2723372.2723725","title":"TEGRA","year":2015,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Row; Table (database); Relational database; Schema (genetic algorithms); World Wide Web; Data mining; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05405638443133703,"gpt":0.2543020114080482,"spread":0.2002456269767112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001181607,0.00002244298,0.00003221582,0.00002662053,0.00001247838,0.00006447211,0.0003508708,0.000007729604,0.00001124004],"category_scores_gemma":[0.00002171598,0.00001578906,0.00001360657,0.0001672697,0.00000503926,0.0001850491,0.00008672709,0.00001691835,0.0004681987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004261344,"about_ca_system_score_gemma":0.00002274285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005067269,"about_ca_topic_score_gemma":0.00000395906,"domain_scores_codex":[0.9997216,0.000008058665,0.00003571447,0.0000897749,0.00008457583,0.00006027089],"domain_scores_gemma":[0.9996362,0.00000719293,0.000007269954,0.0002649324,0.00002123388,0.00006313045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[5.843197e-7,0.00004253317,0.003927458,9.882434e-7,0.00001902175,0.00001862197,0.0005953561,0.00004687567,0.0001177846,0.4050894,0.3886074,0.2015339],"study_design_scores_gemma":[0.0004840447,0.0001003566,0.001501801,0.000005889883,0.00001093384,0.00002485533,0.0003487799,0.3468917,0.002535295,0.01873536,0.6290069,0.0003541325],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003046207,0.0000210777,0.8709035,0.001354074,0.00007446687,0.000005884822,2.60153e-7,0.0001505161,0.124444],"genre_scores_gemma":[0.803246,8.004026e-7,0.1876387,0.0005232495,0.00003767908,8.703718e-7,0.000001627288,0.000001352695,0.008549749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8001997,"threshold_uncertainty_score":0.6017903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W108479605","doi":"","title":"A New Similarity Measure to Understand Visitor Behavior in a Web Site","year":2004,"lang":"en","type":"article","venue":"IEICE Transactions on Information and Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Visitor pattern; Computer science; World Wide Web; Cluster analysis; Similarity (geometry); Web page; Similarity measure; The Internet; Web site; Information retrieval; Measure (data warehouse); Web analytics; Site map; Order (exchange); Web mining; Web navigation; Web modeling; Static web page; Data mining; Web intelligence; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02053953015793934,"gpt":0.2451619656474609,"spread":0.2246224354895215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002522626,0.0001025875,0.0001413595,0.0003979607,0.0001387685,0.0004339127,0.0001815661,0.00006541835,0.000005836164],"category_scores_gemma":[0.000007263403,0.00009618542,0.00004083737,0.0006131664,0.000007762989,0.001571376,0.000004706844,0.0001265106,0.00008989099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001097919,"about_ca_system_score_gemma":0.0001275254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008332104,"about_ca_topic_score_gemma":0.000681976,"domain_scores_codex":[0.9990989,0.00003065496,0.0003127515,0.0001391789,0.0002734776,0.0001450172],"domain_scores_gemma":[0.9994446,0.00002304818,0.00005796194,0.0002650474,0.00005264792,0.0001566975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002834273,0.0008549458,0.002173999,0.0004941026,0.0002651159,0.00005301798,0.1547769,0.4178716,0.002346548,0.03454749,0.004101695,0.3822311],"study_design_scores_gemma":[0.0245978,0.00280089,0.02673056,0.002631598,0.0005005132,0.000591871,0.06026988,0.7730143,0.002397618,0.0005347901,0.1012582,0.004671986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03177799,0.00002183483,0.966359,0.0008443641,0.0002156446,0.0002042304,0.00003436959,0.00008982998,0.0004527602],"genre_scores_gemma":[0.9965994,0.000009332167,0.003023579,0.0002391476,0.00001823488,0.00001767771,0.000005816805,0.000002741406,0.00008409814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9648214,"threshold_uncertainty_score":0.418423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1533716782","doi":"10.1007/978-3-540-28637-0_20","title":"Web Page Transformation When Switching Devices","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Transformation (genetics); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01583395283593206,"gpt":0.2348622141047844,"spread":0.2190282612688523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009833629,0.0004759648,0.0004947758,0.00101711,0.0003475341,0.001043797,0.003679711,0.0002573192,0.00003630619],"category_scores_gemma":[0.00003994609,0.0004206507,0.0001724897,0.0005839603,0.0002110316,0.001706731,0.0006224724,0.000731691,0.00008784459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002829183,"about_ca_system_score_gemma":0.0007162347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000685894,"about_ca_topic_score_gemma":0.0002558794,"domain_scores_codex":[0.9965377,0.00002913929,0.0005712745,0.001257776,0.001023045,0.0005810466],"domain_scores_gemma":[0.9979495,0.0002082059,0.0002811611,0.001263055,0.0001365635,0.0001615547],"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":[0.000002271749,0.00002275409,0.00004320352,0.00007093814,0.00002439793,0.0000670478,0.003845979,0.0195457,0.0004381359,0.03219478,0.00001599571,0.9437288],"study_design_scores_gemma":[0.0003546257,0.0001008931,0.00005612076,0.0008243019,0.00002687347,0.00005205352,6.700112e-7,0.7974206,0.0007405352,0.1970726,0.002507466,0.0008433243],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002517689,0.00029006,0.9918311,0.001567665,0.0006880112,0.0001689971,0.000008549186,0.0002190945,0.004974782],"genre_scores_gemma":[0.6292889,0.00005175507,0.3686137,0.001538959,0.0003310873,0.00000491727,0.00001869027,0.00002619173,0.0001258227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9428855,"threshold_uncertainty_score":0.9999932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039447541","doi":"10.1145/564376.564448","title":"The impact of corpus size on question answering performance","year":2002,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Terabyte; Question answering; Computer science; Information retrieval; World Wide Web; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01666226182163508,"gpt":0.2518497277000022,"spread":0.2351874658783671,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001697943,0.00004766377,0.00005832432,0.00002281386,0.00009071308,0.00005974135,0.000363861,0.00001248587,0.00002306771],"category_scores_gemma":[0.00004994874,0.00002566378,0.00004888967,0.0002036222,0.0000187651,0.0001863676,0.0000447627,0.00004305907,0.00004638056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001536615,"about_ca_system_score_gemma":0.000005773703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134263,"about_ca_topic_score_gemma":0.000003509957,"domain_scores_codex":[0.9995749,0.00001999076,0.00009138564,0.0001018614,0.0001093554,0.000102506],"domain_scores_gemma":[0.9994258,0.0001229685,0.00004329389,0.0003596525,0.00002375171,0.0000245544],"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":[0.000008366389,0.0001103427,0.02390298,0.000007407549,0.00007127712,0.000003071069,0.0004960637,0.00791045,0.002816969,0.009970454,0.006116265,0.9485863],"study_design_scores_gemma":[0.00007748289,0.0002059328,0.04350453,0.00001769648,0.00000281226,0.000003562292,0.000006867611,0.9532937,0.002321785,0.00004865432,0.0004526391,0.0000643448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737213,0.00007421481,0.01757686,0.0003828239,0.00006578366,0.00002418457,0.000001100303,0.00006972318,0.008084022],"genre_scores_gemma":[0.9969836,0.0001013475,0.0016996,0.00002067436,0.00001583944,8.563716e-7,2.447425e-7,0.000001615159,0.001176204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.948522,"threshold_uncertainty_score":0.1046539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}