{"meta":{"query_hash":"b0f5578f786e","filters":{"venue":"World Wide Web"},"cohort_total":29,"direct_labels_cover":0,"predictions_cover":29,"exported":29,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/b0f5578f786e","api":"https://metacan.xera.ac/api/v1/cohort?venue=World+Wide+Web"},"results":[{"id":"W1480033117","doi":"10.1023/a:1015185802583","title":"Integrating Web Prefetching and Caching Using Prediction Models","year":2001,"lang":"en","type":"article","venue":"World Wide Web","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.030650988922576547,"score_gpt":0.259374212231979,"score_spread":0.22872322330940242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480033117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17673637,0.00030948268,0.81926894,0.00038135576,0.00020646764,0.00012265494,0.0000073110477,0.00095796224,0.0020094446],"genre_scores_gemma":[0.74557006,0.000042457043,0.25409228,0.00012422971,0.000040185307,0.0000063522625,0.0000029673627,0.000012059373,0.00010939989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987255,0.00004405662,0.00025400615,0.00046256228,0.00019754989,0.00031636833],"domain_scores_gemma":[0.99906397,0.00014506537,0.00012359583,0.00057666027,0.000033116856,0.0000576019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028211946,0.00017202119,0.00016608936,0.0003178787,0.00029428746,0.00019292314,0.0005594926,0.000051144933,0.0000033241322],"category_scores_gemma":[0.00016092087,0.0001628211,0.000028516453,0.0006132541,0.00006201194,0.0025036577,0.00064014917,0.0003597054,0.0000032770172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029293295,0.0001013087,0.03080932,0.000073759205,0.000071465016,0.00023907251,0.0023743284,0.22783373,0.06578244,0.2711029,0.0015883603,0.39999402],"study_design_scores_gemma":[0.0001666868,0.000016324111,0.00012135951,0.00010906231,0.0000058645164,0.00006348025,0.00009118988,0.97071224,0.0003267243,0.024894357,0.0033278053,0.00016491725],"about_ca_topic_score_codex":0.000071657654,"about_ca_topic_score_gemma":0.00039755052,"teacher_disagreement_score":0.7428785,"about_ca_system_score_codex":0.00012597578,"about_ca_system_score_gemma":0.000049801256,"threshold_uncertainty_score":0.66396517},"labels":[],"label_agreement":null},{"id":"W1493789029","doi":"10.1023/a:1012408428703","title":"A Conceptual Model and Rule-Based Query Language for HTML","year":2001,"lang":"en","type":"article","venue":"World Wide Web","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Query language; Information retrieval; Simple (philosophy); Semantics (computer science); Conceptual graph; Programming language; Knowledge representation and reasoning; Artificial intelligence","score_opus":0.020280491436409195,"score_gpt":0.2545614389812293,"score_spread":0.2342809475448201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493789029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26453966,0.0005333106,0.72571284,0.0045361607,0.00009957942,0.0001414805,0.000058958733,0.0002718707,0.0041061505],"genre_scores_gemma":[0.92695093,0.000005888748,0.065579586,0.0019017016,0.00005856623,0.000020113017,0.000022373368,0.0000085489055,0.0054522995],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919754,0.000023110586,0.0001328829,0.0003048635,0.00012058136,0.00022101047],"domain_scores_gemma":[0.99924785,0.00020395202,0.000047001642,0.00038693458,0.000027717631,0.0000865232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018620458,0.00010162909,0.00014871127,0.00013971902,0.00009179644,0.00010797469,0.0003496876,0.000023867407,0.000014492606],"category_scores_gemma":[0.000060324266,0.00009261964,0.00006162015,0.00030059804,0.00006197121,0.00020428609,0.000082823055,0.00006433199,0.000016897478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022860614,0.0006443863,0.0488997,0.00012774597,0.00036662188,0.00037809994,0.010006344,0.037946794,0.022274034,0.3074173,0.3355173,0.23619306],"study_design_scores_gemma":[0.0005909597,0.000021638778,0.00023786022,0.00002379851,0.000019264817,0.0000028443599,0.000090622205,0.9716007,0.0003240294,0.0005955894,0.026317345,0.00017535851],"about_ca_topic_score_codex":0.00004144382,"about_ca_topic_score_gemma":0.00039638698,"teacher_disagreement_score":0.9336539,"about_ca_system_score_codex":0.000014907434,"about_ca_system_score_gemma":0.000078606856,"threshold_uncertainty_score":0.37769192},"labels":[],"label_agreement":null},{"id":"W1493874060","doi":"10.1023/a:1019217210183","title":"Digital payment systems for Internet commerce: The state of the art","year":2000,"lang":"en","type":"article","venue":"World Wide Web","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Payment; The Internet; Context (archaeology); Principal (computer security); Protocol (science); Taxonomy (biology); World Wide Web; Computer security","score_opus":0.010617747578999234,"score_gpt":0.2196965376633797,"score_spread":0.20907879008438046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493874060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43331194,0.004346256,0.36452717,0.033588205,0.0058006174,0.0057673664,0.0023512086,0.00062247866,0.14968477],"genre_scores_gemma":[0.99451923,0.000021309403,0.00020856931,0.00061182445,0.000030690248,0.000030393157,0.000009488332,0.000004847355,0.004563637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992415,0.000042595417,0.00020375973,0.00016642062,0.00017863448,0.00016712447],"domain_scores_gemma":[0.9990066,0.00022033683,0.00007010332,0.00064297195,0.00002576644,0.00003421772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000215029,0.000085786996,0.00010592716,0.0000331476,0.00007345454,0.000213793,0.0010616829,0.000010086062,0.00002576993],"category_scores_gemma":[0.000010565685,0.00004603739,0.00011016052,0.00031615826,0.00008829857,0.00023345358,0.00017358629,0.00008549453,0.000032106447],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006252243,0.00023119185,0.009334625,0.00006927547,0.00009674805,0.0000022756064,0.0019181663,0.0004399916,0.00003341641,0.19305353,0.6804501,0.11430821],"study_design_scores_gemma":[0.00019692341,0.00002943323,0.0032305897,0.00004587009,0.000004986552,0.0000027811038,0.00001629213,0.013328165,0.00008987673,0.002985556,0.9799904,0.00007913144],"about_ca_topic_score_codex":0.000032824406,"about_ca_topic_score_gemma":0.00016378817,"teacher_disagreement_score":0.5612073,"about_ca_system_score_codex":0.0000113316855,"about_ca_system_score_gemma":0.00002163979,"threshold_uncertainty_score":0.20616108},"labels":[],"label_agreement":null},{"id":"W1605784496","doi":"10.1023/a:1020912027991","title":"Editorial: Introduction to Web Media Information Systems","year":2002,"lang":"en","type":"article","venue":"World Wide Web","topic":"Web Applications and Data Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.009203799279004997,"score_gpt":0.20404112497799054,"score_spread":0.19483732569898554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605784496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008032499,0.00019432043,0.52703226,0.07291725,0.33597806,0.0018229859,0.00005670735,0.0015193182,0.05967584],"genre_scores_gemma":[0.68884027,0.00012719024,0.041137755,0.0035088914,0.25759897,0.000797026,0.00018341145,0.000031866763,0.007774609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895847,0.000024065968,0.0002607438,0.00022272088,0.00035395322,0.00018002566],"domain_scores_gemma":[0.9988769,0.000045512774,0.00008051864,0.0008063861,0.00009501702,0.00009563541],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031222161,0.000091445705,0.00009370974,0.0003175398,0.00009652704,0.0004230017,0.0005922429,0.000024982499,0.000048630507],"category_scores_gemma":[0.000075752825,0.000087907625,0.000021825008,0.0009421433,0.000011036384,0.0014674214,0.00022728395,0.000077471064,0.003111254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.4831803e-7,0.000013022666,0.00002560749,0.0000067570545,0.0000033139236,1.3350463e-7,0.00009766977,0.00030739722,0.00004099973,0.0813685,0.9107929,0.007342959],"study_design_scores_gemma":[0.000118259144,0.000010281563,0.00014348446,0.000006064285,0.0000032179591,7.6698996e-7,0.00001739678,0.031975184,0.000018805798,0.00011297761,0.96749127,0.000102285376],"about_ca_topic_score_codex":0.000030278545,"about_ca_topic_score_gemma":0.000054112606,"teacher_disagreement_score":0.68803704,"about_ca_system_score_codex":0.0000768695,"about_ca_system_score_gemma":0.000014535101,"threshold_uncertainty_score":0.9976649},"labels":[],"label_agreement":null},{"id":"W2011562771","doi":"10.1007/s11280-007-0033-x","title":"Bringing Semantics to Web Services with OWL-S","year":2007,"lang":"en","type":"article","venue":"World Wide Web","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":502,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Defense Advanced Research Projects Agency","keywords":"Computer science; OWL-S; Web service; World Wide Web; Web standards; Semantic Web; WS-Policy; Web modeling; Social Semantic Web; WS-I Basic Profile; Semantic Web Stack; Ontology; Semantic Web Rule Language; Software engineering; Web development; Semantic analytics; Web intelligence; Web application security","score_opus":0.004156329108519309,"score_gpt":0.21374029839463912,"score_spread":0.2095839692861198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011562771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8403519,0.00030089705,0.09695017,0.010633709,0.000928843,0.00047147015,0.000004686303,0.0010771073,0.04928126],"genre_scores_gemma":[0.9419162,0.0000044590565,0.04291684,0.014000812,0.0002433707,0.000006727059,0.0000037103057,0.000030368645,0.0008774847],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777246,0.00003073457,0.00031120595,0.00062165206,0.0005160445,0.000747881],"domain_scores_gemma":[0.9983269,0.00021425945,0.00011336519,0.00089837203,0.00012083953,0.00032626063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043411227,0.00028891323,0.00025046922,0.00057999423,0.00022093745,0.00026578156,0.0015001775,0.000045046294,0.000028401912],"category_scores_gemma":[0.0000032976059,0.00023757057,0.0000624519,0.0022373335,0.000023144095,0.0004056139,0.0005150502,0.00023678866,0.00024675767],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006784378,0.00095978996,0.5481755,0.0021722557,0.0007604103,0.0025394047,0.052605204,0.010357966,0.071149975,0.16531372,0.007887743,0.13739958],"study_design_scores_gemma":[0.0016513529,0.0003484604,0.055871908,0.0010959157,0.0000716641,0.0001449332,0.00094705884,0.049423624,0.024013344,0.0015710685,0.8631099,0.0017507954],"about_ca_topic_score_codex":0.0001953552,"about_ca_topic_score_gemma":0.028048355,"teacher_disagreement_score":0.8552221,"about_ca_system_score_codex":0.0000390728,"about_ca_system_score_gemma":0.0000756718,"threshold_uncertainty_score":0.9896872},"labels":[],"label_agreement":null},{"id":"W2017082499","doi":"10.1007/s11280-012-0168-2","title":"Finding email correspondents in online social networks","year":2012,"lang":"en","type":"article","venue":"World Wide Web","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Similarity (geometry); Social network (sociolinguistics); World Wide Web; Data science; Graph; Information retrieval; Social media; Artificial intelligence; Theoretical computer science","score_opus":0.021668976744591402,"score_gpt":0.2994256717349167,"score_spread":0.2777566949903253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017082499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745469,0.0001913579,0.0061955643,0.00030439114,0.0003400492,0.00019495342,0.000016346472,0.00012758716,0.018082825],"genre_scores_gemma":[0.9939765,0.0000016146836,0.0005830359,0.00016136837,0.0016007142,0.000020010119,0.00009206223,0.00002392332,0.0035407809],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99880743,0.000085744665,0.00028719462,0.00017405789,0.00014897234,0.0004966085],"domain_scores_gemma":[0.9994813,0.00012686865,0.00011432534,0.0001801944,0.000019319843,0.00007799721],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002829568,0.00015932952,0.00025779428,0.00022811834,0.000110860914,0.000036374095,0.00020297282,0.00003104877,0.0012420852],"category_scores_gemma":[0.000004907914,0.00016744825,0.00013653935,0.00071242015,0.000030922823,0.00014629992,0.00013073382,0.0002943915,0.000044175948],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014514955,0.00018665771,0.9538961,0.0000015177976,0.00003410359,0.0000010944013,0.00012496422,0.00020257667,0.000046183846,0.005642105,0.028721947,0.011128257],"study_design_scores_gemma":[0.0011095504,0.000018969393,0.7844618,0.000118957076,0.00011333635,6.765442e-7,0.00034497606,0.034160934,0.00014754478,0.0041539986,0.17451946,0.0008497785],"about_ca_topic_score_codex":0.0001395234,"about_ca_topic_score_gemma":0.00068844284,"teacher_disagreement_score":0.16943426,"about_ca_system_score_codex":0.000064879554,"about_ca_system_score_gemma":0.000020507778,"threshold_uncertainty_score":0.9996709},"labels":[],"label_agreement":null},{"id":"W2034320955","doi":"10.1007/s11280-015-0323-7","title":"MUBaaS: mobile ubiquitous brokerage as a service","year":2015,"lang":"en","type":"article","venue":"World Wide Web","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Scalability; Cloud computing; Mobile device; Computer network; Synchronization (alternating current); Middleware (distributed applications); Latency (audio); Ubiquitous computing; Wireless network; Mobile computing; Distributed computing; Wireless; World Wide Web; Telecommunications; Channel (broadcasting); Operating system","score_opus":0.02015686498433985,"score_gpt":0.2526832242808479,"score_spread":0.23252635929650803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034320955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67716044,0.0015613158,0.032445513,0.010859279,0.037969906,0.00085660355,9.1959e-7,0.0024416815,0.23670433],"genre_scores_gemma":[0.9501727,0.0000059200397,0.017749881,0.010578739,0.004091795,0.000051224597,0.000005657363,0.00004583693,0.017298209],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983278,0.00007315965,0.00026155877,0.00045572274,0.00036984365,0.0005119523],"domain_scores_gemma":[0.99859333,0.0001496744,0.00009110562,0.0007425191,0.00013536047,0.00028802047],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043287556,0.00019707848,0.00021119516,0.00018980527,0.00014029357,0.0002697356,0.0011645242,0.000050070834,0.000014520847],"category_scores_gemma":[0.00005285174,0.00019108398,0.00006882403,0.0011201787,0.000022819559,0.00042190036,0.0006631387,0.00022423304,0.0021111704],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003498676,0.000280568,0.004639665,0.00008510116,0.00006381789,0.00053768454,0.010121833,0.0013842414,0.0011141971,0.008437188,0.8747604,0.09854031],"study_design_scores_gemma":[0.00061998185,0.00010682214,0.0003589994,0.000057921443,0.0000070646224,0.000059172315,0.00004365476,0.047252644,0.0009849863,0.0043175807,0.9458129,0.00037830367],"about_ca_topic_score_codex":0.00021650916,"about_ca_topic_score_gemma":0.00014951419,"teacher_disagreement_score":0.27301228,"about_ca_system_score_codex":0.000091862574,"about_ca_system_score_gemma":0.00027024176,"threshold_uncertainty_score":0.9986658},"labels":[],"label_agreement":null},{"id":"W2038680758","doi":"10.1007/s11280-012-0179-z","title":"Riding the tide of sentiment change: sentiment analysis with evolving online reviews","year":2012,"lang":"en","type":"article","venue":"World Wide Web","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Sentiment analysis; Revenue; Data science; Work (physics); Data mining; Information retrieval; Artificial intelligence","score_opus":0.050330644985061776,"score_gpt":0.29485799971546356,"score_spread":0.24452735473040177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038680758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5600815,0.095547706,0.29379645,0.029613521,0.0033642454,0.0042378977,0.00004806908,0.0006558832,0.012654745],"genre_scores_gemma":[0.9725785,0.00025426122,0.023663292,0.0008417093,0.0002833462,0.00003793624,0.000023348088,0.000013902282,0.0023036757],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789596,0.00019687029,0.00056223583,0.00034977123,0.0005448886,0.00045030226],"domain_scores_gemma":[0.9982007,0.0001712396,0.0005017595,0.0009135511,0.000083610015,0.00012912673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013364351,0.00022404028,0.0005174287,0.0005191431,0.00018388224,0.00010963765,0.00067649095,0.000022111122,0.00027588257],"category_scores_gemma":[0.000027323304,0.00013791084,0.00035497424,0.0031054255,0.00004722106,0.0005572183,0.00031774465,0.0001341567,0.00005743424],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016053524,0.0007310081,0.93510234,0.00008708627,0.0031999366,0.000008042741,0.0051641315,0.0007465005,0.00236467,0.005551256,0.023873046,0.023155922],"study_design_scores_gemma":[0.0013535181,0.00013766163,0.21584454,0.000896988,0.004891,0.000012027378,0.00078609213,0.376835,0.012294391,0.000073422,0.3854279,0.0014474561],"about_ca_topic_score_codex":0.000075530195,"about_ca_topic_score_gemma":0.0002555302,"teacher_disagreement_score":0.71925783,"about_ca_system_score_codex":0.000065788285,"about_ca_system_score_gemma":0.000022732,"threshold_uncertainty_score":0.5623841},"labels":[],"label_agreement":null},{"id":"W2042613727","doi":"10.1007/s11280-008-0049-x","title":"An Operable Email Based Intelligent Personal Assistant","year":2008,"lang":"en","type":"article","venue":"World Wide Web","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Natural Science Foundation of China; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Computer science; World Wide Web; sort; Ontology; Key (lock); Email authentication; Function (biology); Software; Information retrieval; Computer security","score_opus":0.024955714377033183,"score_gpt":0.23863493392537954,"score_spread":0.21367921954834637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042613727","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49729913,0.0003922482,0.47790456,0.0045064026,0.0023067961,0.00026325908,0.0000060158186,0.0008655302,0.01645607],"genre_scores_gemma":[0.984304,0.0000072932057,0.011362444,0.0014958543,0.0001210289,0.0000103602315,0.0000028744425,0.000009621477,0.0026865145],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989166,0.00007380861,0.000152604,0.0003369443,0.0002829352,0.00023707435],"domain_scores_gemma":[0.99928766,0.00007610023,0.00004238857,0.00040548915,0.000052028583,0.00013634922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025125025,0.00011522421,0.000114585615,0.00015291353,0.00028684278,0.0001323451,0.0004915059,0.000030686533,0.00021387331],"category_scores_gemma":[0.000026369074,0.00010660797,0.00006528836,0.0005080969,0.00004133386,0.00040103018,0.00004275393,0.00015660078,0.00016928927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000496523,0.0034417529,0.25007835,0.00018345084,0.00024863533,0.0019319215,0.02775031,0.014690232,0.09176011,0.045469183,0.3793915,0.18455805],"study_design_scores_gemma":[0.0005111316,0.00025886242,0.021383272,0.00005108778,0.000008598512,0.000056883535,0.000047623835,0.6694435,0.020523021,0.00042758524,0.2867834,0.00050505163],"about_ca_topic_score_codex":0.00013546093,"about_ca_topic_score_gemma":0.00048079438,"teacher_disagreement_score":0.6547532,"about_ca_system_score_codex":0.00008125581,"about_ca_system_score_gemma":0.00014968634,"threshold_uncertainty_score":0.43473467},"labels":[],"label_agreement":null},{"id":"W2046598510","doi":"10.1007/s11280-013-0204-x","title":"Mining most frequently changing component in evolving graphs","year":2013,"lang":"en","type":"article","venue":"World Wide Web","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Intuition; Component (thermodynamics); Graph; Data mining; Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.00964463561293763,"score_gpt":0.23155167089314238,"score_spread":0.22190703528020475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046598510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94991004,0.00020115585,0.0018301522,0.00051473425,0.000094791736,0.0003308577,0.0000031198647,0.00015828644,0.04695687],"genre_scores_gemma":[0.99478686,0.0000017670147,0.003769947,0.00017557557,0.00014041727,0.00010597511,0.00003235706,0.000025430234,0.0009616748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987418,0.000052272688,0.00032156176,0.00027297033,0.00015230029,0.0004590635],"domain_scores_gemma":[0.9993355,0.0001285366,0.00011234509,0.00029986078,0.000046949724,0.00007676143],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018611748,0.00018000664,0.00026531436,0.00060487684,0.00011157292,0.000103837156,0.00022458137,0.000017131471,0.0021665343],"category_scores_gemma":[0.000004685612,0.0001870367,0.000115701114,0.0011109404,0.00003256344,0.00019661132,0.00013552004,0.00017641729,0.00007999842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020034254,0.00009044631,0.9355883,0.0000060291286,0.00007086086,0.0000039442175,0.00036704625,0.00022350463,0.0041627227,0.02396165,0.022483446,0.013040022],"study_design_scores_gemma":[0.0028288024,0.00009525428,0.40898916,0.0017600894,0.00022921088,0.0000030272693,0.0038389221,0.34614196,0.0098425215,0.13355054,0.08930179,0.0034187317],"about_ca_topic_score_codex":0.0014133105,"about_ca_topic_score_gemma":0.00057298806,"teacher_disagreement_score":0.52659917,"about_ca_system_score_codex":0.00005301808,"about_ca_system_score_gemma":0.000020530708,"threshold_uncertainty_score":0.9987456},"labels":[],"label_agreement":null},{"id":"W2053259448","doi":"10.1007/s11280-007-0029-6","title":"Clustered Chain Path Index for XML Document: Efficiently Processing Branch Queries","year":2007,"lang":"en","type":"article","venue":"World Wide Web","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; National University of Singapore","keywords":"Computer science; Cardinality (data modeling); XML; Path (computing); Scalability; Index (typography); Data mining; Path expression; Inverted index; XPath; Tree (set theory); Stream processing; Search engine indexing; XML database; Algorithm; Information retrieval; Database; Query language; Parallel computing; Programming language","score_opus":0.009802303416945914,"score_gpt":0.2593626724000832,"score_spread":0.2495603689831373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053259448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006748549,0.00064852973,0.9883742,0.00062745233,0.000620612,0.0005294367,0.000020190293,0.00027517648,0.00215589],"genre_scores_gemma":[0.914048,0.0000053295244,0.08064592,0.0008524208,0.00023531853,0.00006723295,0.0000185899,0.000026542926,0.004100629],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804276,0.00003361958,0.00045824784,0.00053071487,0.0003276163,0.0006070559],"domain_scores_gemma":[0.99874634,0.0002131529,0.00022003816,0.0005621523,0.00012076459,0.00013756756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083703647,0.00023083581,0.00027142803,0.00023443584,0.0003549815,0.00015632572,0.00039851514,0.00004670708,0.000009382751],"category_scores_gemma":[0.00009220564,0.00020538943,0.000081810715,0.0007024625,0.00008995419,0.0009541175,0.00023501409,0.00013016093,0.000016893347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003621071,0.00024043494,0.009356876,0.000987816,0.00006131429,0.00008746613,0.0058334502,0.0011871599,0.0048881536,0.6028149,0.010878198,0.3633021],"study_design_scores_gemma":[0.0015393208,0.00010760839,0.0026737805,0.00042241218,0.000008821017,0.00002184006,0.00023233198,0.019876862,0.004343525,0.003398897,0.9667112,0.00066338264],"about_ca_topic_score_codex":0.000032806056,"about_ca_topic_score_gemma":0.0009631747,"teacher_disagreement_score":0.955833,"about_ca_system_score_codex":0.000079439866,"about_ca_system_score_gemma":0.00012278676,"threshold_uncertainty_score":0.8375538},"labels":[],"label_agreement":null},{"id":"W2057871674","doi":"10.1007/s11280-013-0250-4","title":"Malicious URL detection by dynamically mining patterns without pre-defined elements","year":2013,"lang":"en","type":"article","venue":"World Wide Web","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Flexibility (engineering); Task (project management); Data mining; Feature selection; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence","score_opus":0.005457942593613912,"score_gpt":0.2096292484384356,"score_spread":0.2041713058448217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057871674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7725047,0.000030906573,0.22317842,0.0008788658,0.0012620781,0.00028701848,0.0000030103583,0.00045209646,0.001402939],"genre_scores_gemma":[0.99007857,0.0000034856714,0.004809718,0.00081775466,0.000094272116,0.000081477905,0.0000064136602,0.000021359803,0.004086932],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851876,0.000081166865,0.00030470314,0.0004336837,0.00030199913,0.00035970344],"domain_scores_gemma":[0.99910814,0.00009814212,0.00014652492,0.0004633159,0.0000636468,0.00012025579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020164446,0.00017944467,0.00015539031,0.00016838669,0.00016533998,0.00033247116,0.0005079274,0.000058688132,0.00010896206],"category_scores_gemma":[0.000057671266,0.00017592816,0.000060245504,0.00039427282,0.000019062169,0.00056750234,0.00014323868,0.00018088993,0.00021722514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004634219,0.0002394982,0.4329687,0.00005525151,0.00012561778,0.000012093841,0.001429057,0.00019715689,0.13549627,0.00032341934,0.045751233,0.38335535],"study_design_scores_gemma":[0.0013916518,0.00039422634,0.22969139,0.00013459477,0.000030937237,0.00003082965,0.000036863865,0.71255237,0.020929633,0.001107527,0.03277304,0.00092696084],"about_ca_topic_score_codex":0.00064764183,"about_ca_topic_score_gemma":0.0021189596,"teacher_disagreement_score":0.7123552,"about_ca_system_score_codex":0.00010124534,"about_ca_system_score_gemma":0.00002058442,"threshold_uncertainty_score":0.71741426},"labels":[],"label_agreement":null},{"id":"W2125999281","doi":"10.1007/s11280-010-0094-0","title":"Mining discriminative items in multiple data streams","year":2010,"lang":"en","type":"article","venue":"World Wide Web","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Discriminative model; Data stream; Data stream mining; Heuristic; Information retrieval; Volume (thermodynamics); Space (punctuation); Data mining; Reading (process); Streaming data; Raw data; STREAMS; Artificial intelligence","score_opus":0.04568083920431813,"score_gpt":0.2889493389425767,"score_spread":0.24326849973825854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125999281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7221877,0.00018135674,0.21121493,0.017568858,0.0029736252,0.0010363136,0.0008386122,0.00088812044,0.04311048],"genre_scores_gemma":[0.787156,0.0000029072762,0.2113175,0.00018728181,0.00008465022,0.000030532967,0.00013336418,0.000008851807,0.0010789103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889207,0.00002107277,0.000193272,0.0005071072,0.00014991318,0.00023655682],"domain_scores_gemma":[0.99790674,0.0003649742,0.00006717978,0.0015588499,0.000024082881,0.000078195575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030590632,0.00010674241,0.000116353884,0.00014758098,0.00009718798,0.00016401974,0.0019924561,0.000025629484,0.000020239959],"category_scores_gemma":[0.00019383561,0.000099039666,0.000016304917,0.00061449595,0.000061512015,0.00073979207,0.00090123375,0.00023098664,0.000065253764],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028627753,0.0002817482,0.047810897,0.000009904034,0.000013918137,0.000028837436,0.0017509371,0.000019452851,0.004072876,0.0353619,0.04370196,0.86694473],"study_design_scores_gemma":[0.00037981255,0.000012442609,0.025542699,0.000034927456,0.0000042025626,0.000004561027,0.00016928678,0.7583588,0.00060025434,0.0007087748,0.21393773,0.00024652868],"about_ca_topic_score_codex":0.00026130394,"about_ca_topic_score_gemma":0.0113237025,"teacher_disagreement_score":0.86669815,"about_ca_system_score_codex":0.000012557677,"about_ca_system_score_gemma":0.000059692582,"threshold_uncertainty_score":0.6318892},"labels":[],"label_agreement":null},{"id":"W2126514643","doi":"10.1023/a:1019697023170","title":"Evaluation of Strong Consistency Web Caching Techniques","year":2002,"lang":"en","type":"article","venue":"World Wide Web","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; University of Wisconsin-Madison","keywords":"Computer science; Cache; Cache invalidation; Cache algorithms; Smart Cache; Distributed computing; Consistency (knowledge bases); Eventual consistency; Cache coherence; Causal consistency; Consistency model; Computer network; CPU cache; Data consistency; Sequential consistency","score_opus":0.05286046055294654,"score_gpt":0.2679706923057275,"score_spread":0.21511023175278096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126514643","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41169316,0.006195048,0.039942317,0.005522096,0.0014329444,0.0010069043,0.000015087704,0.0014122737,0.5327802],"genre_scores_gemma":[0.9963525,0.000020030246,0.0022680352,0.0002000094,0.00004352716,0.000014949934,9.1121433e-7,0.000006695031,0.0010933576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984878,0.00019773473,0.00025374437,0.0002471511,0.00063832616,0.00017529765],"domain_scores_gemma":[0.99902135,0.000120661345,0.00012062524,0.00046973408,0.00022157292,0.00004605601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012258001,0.000103363745,0.00014948695,0.00022699084,0.00009554984,0.000059213668,0.00040799592,0.000027334425,0.000087215245],"category_scores_gemma":[0.0001422072,0.00010087072,0.0000839697,0.0003224373,0.000037863232,0.0003030818,0.000107313455,0.0001408626,0.00003116625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008129497,0.0003431495,0.014350312,0.0000493799,0.00013963615,0.000022964621,0.0008923965,0.0011097648,0.042400353,0.074927405,0.036292072,0.82946444],"study_design_scores_gemma":[0.0004793648,0.000061300525,0.0009790052,0.00016231266,0.000078245335,0.0000112744565,0.000036241192,0.98576385,0.0027399855,0.0016771697,0.0077445135,0.00026674735],"about_ca_topic_score_codex":0.00007610298,"about_ca_topic_score_gemma":0.00027672318,"teacher_disagreement_score":0.98465407,"about_ca_system_score_codex":0.00008017695,"about_ca_system_score_gemma":0.000078492056,"threshold_uncertainty_score":0.41133884},"labels":[],"label_agreement":null},{"id":"W2137580272","doi":"10.1007/s11280-005-1544-y","title":"Studying the XML Web: Gathering Statistics from an XML Sample","year":2005,"lang":"en","type":"article","venue":"World Wide Web","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Computer science; XML validation; Efficient XML Interchange; XML Schema Editor; XML Base; Streaming XML; Document Structure Description; XML Signature; XML Encryption; Information retrieval; World Wide Web; XML database; cXML; XML; Database","score_opus":0.02279868175895083,"score_gpt":0.2698407601171572,"score_spread":0.24704207835820635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137580272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01930918,0.00034043833,0.97724086,0.0010956309,0.00046641543,0.00017725982,0.00034704103,0.00022443205,0.0007987552],"genre_scores_gemma":[0.4280125,0.000023555765,0.5693811,0.0012031803,0.000507595,0.000026366955,0.000036622037,0.000023278337,0.0007858186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866736,0.0000923418,0.0002769695,0.00037477622,0.0002740943,0.00031446223],"domain_scores_gemma":[0.9982024,0.0006047207,0.00011256915,0.0009379047,0.000044221022,0.00009817519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027652353,0.00016423831,0.00017799115,0.00005789367,0.00032415762,0.00014158884,0.0006087224,0.000018316194,0.000087742104],"category_scores_gemma":[0.00010089992,0.00012098196,0.000032669992,0.00027677126,0.000057460406,0.00075412437,0.00030497793,0.00016613961,0.000102496204],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002357697,0.00019188203,0.016748868,0.000029344681,0.00009911246,0.000060172984,0.0070516826,0.0049020275,0.004503118,0.69745094,0.023454754,0.2454845],"study_design_scores_gemma":[0.00024985676,0.00002479608,0.0025527105,0.00004118465,0.0000074429418,0.00000279766,0.00022926662,0.07355724,0.00030697882,0.0021430764,0.920643,0.00024168959],"about_ca_topic_score_codex":0.00049736333,"about_ca_topic_score_gemma":0.011272832,"teacher_disagreement_score":0.8971882,"about_ca_system_score_codex":0.000050617837,"about_ca_system_score_gemma":0.00006895511,"threshold_uncertainty_score":0.6290505},"labels":[],"label_agreement":null},{"id":"W2141289279","doi":"10.1007/s11280-006-8563-1","title":"Alternative Architectures and Protocols for Providing Strong Consistency in Dynamic Web Applications","year":2006,"lang":"en","type":"article","venue":"World Wide Web","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Consistency (knowledge bases); Overhead (engineering); Distributed computing; Latency (audio); Data consistency; Scheme (mathematics); Consistency model; Computer network; Operating system","score_opus":0.014750956803868528,"score_gpt":0.27154439381855583,"score_spread":0.2567934370146873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141289279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25497222,0.0007054685,0.6862654,0.0046917624,0.00019371924,0.040913425,0.00007150159,0.0005435054,0.011642992],"genre_scores_gemma":[0.9820088,0.0000010209903,0.0060101533,0.00012851418,0.00004173546,0.011021512,0.0000037498448,0.000008090659,0.0007764161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991068,0.000036323738,0.00020289831,0.00033419466,0.000108814806,0.000210962],"domain_scores_gemma":[0.99937433,0.00023086253,0.00007865716,0.00024741344,0.00003400792,0.000034704466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016509816,0.00011007971,0.00013335914,0.00021331251,0.000117305965,0.00012578025,0.00029871886,0.000018187344,9.656295e-7],"category_scores_gemma":[0.000019869305,0.000103946404,0.00004363345,0.00021934103,0.000047215453,0.00009694715,0.000092988725,0.00011527939,0.0000022900572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013604957,0.00056835095,0.0711867,0.00040996203,0.00007740105,0.00003667862,0.00080913625,0.008894687,0.045960467,0.71981686,0.0022626799,0.14984103],"study_design_scores_gemma":[0.001874582,0.0001011406,0.007858029,0.0002630351,0.0000114796,0.000015181646,0.000043049877,0.91447735,0.0005509993,0.054559246,0.019791199,0.0004546877],"about_ca_topic_score_codex":0.00016259485,"about_ca_topic_score_gemma":0.0033387712,"teacher_disagreement_score":0.90558267,"about_ca_system_score_codex":0.000053490305,"about_ca_system_score_gemma":0.000078615594,"threshold_uncertainty_score":0.4238811},"labels":[],"label_agreement":null},{"id":"W2146492580","doi":"10.1007/s11280-011-0127-3","title":"Opinion helpfulness prediction in the presence of “words of few mouths”","year":2011,"lang":"en","type":"article","venue":"World Wide Web","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Helpfulness; Probabilistic logic; Computer science; Phenomenon; Support vector machine; Logistic regression; Artificial intelligence; Machine learning; Metric (unit); Context (archaeology); Recommender system; Psychology; Social psychology","score_opus":0.03919549582236045,"score_gpt":0.25529995848637765,"score_spread":0.2161044626640172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146492580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74520683,0.0016820598,0.1759293,0.003125357,0.0036587704,0.0010070985,0.00001881519,0.00017081077,0.06920098],"genre_scores_gemma":[0.9971233,0.000015370486,0.0023276247,0.000051836036,0.000034092565,0.000010025066,0.0000022886513,0.0000030547317,0.00043240548],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989473,0.00011448497,0.0003305199,0.00018615069,0.00029347072,0.00012804371],"domain_scores_gemma":[0.9991767,0.00013541714,0.0001771953,0.00044216015,0.000047268153,0.000021280728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060895237,0.00007351421,0.00015039124,0.00023485009,0.000031587577,0.000017407745,0.0007126767,0.000021921016,0.00007201507],"category_scores_gemma":[0.000038789512,0.000053567775,0.00006943969,0.0009955514,0.000048092803,0.00024330227,0.00011374626,0.000077902325,0.0000073498977],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008434697,0.00083350885,0.7475804,0.00016425151,0.00013180441,0.000008903785,0.042350307,0.0008907675,0.0030406283,0.14562988,0.01890307,0.040382102],"study_design_scores_gemma":[0.0017289742,0.00034498217,0.67575604,0.0008930248,0.000056924353,0.000007155313,0.0029040999,0.24414845,0.04977736,0.008494213,0.015338247,0.00055055635],"about_ca_topic_score_codex":0.0001225911,"about_ca_topic_score_gemma":0.0001084518,"teacher_disagreement_score":0.2519165,"about_ca_system_score_codex":0.000008726954,"about_ca_system_score_gemma":0.00003045216,"threshold_uncertainty_score":0.21844305},"labels":[],"label_agreement":null},{"id":"W2153910905","doi":"10.1007/s11280-013-0240-6","title":"Neighborhood randomization for link privacy in social network analysis","year":2013,"lang":"en","type":"article","venue":"World Wide Web","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Renmin University of China","keywords":"Computer science; Graph; Social network (sociolinguistics); Link (geometry); Theoretical computer science; Randomization; Node (physics); Computer network","score_opus":0.017844404823865186,"score_gpt":0.2628639492616792,"score_spread":0.24501954443781404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153910905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030260496,0.00013889062,0.8846192,0.10906591,0.00030405103,0.00079474377,0.0000071418604,0.0006494724,0.0013945798],"genre_scores_gemma":[0.7308007,0.000018998096,0.26745436,0.0008862003,0.00027824694,0.00027399787,0.000042325617,0.000015380328,0.00022978063],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983123,0.00009784522,0.00040265959,0.00049933157,0.0002064209,0.00048145987],"domain_scores_gemma":[0.9959088,0.0006299109,0.00017815953,0.0031504799,0.0000880199,0.000044655655],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005904449,0.0001619236,0.00036950127,0.0005428931,0.00016698144,0.00024797878,0.011239622,0.00010213853,0.00005452347],"category_scores_gemma":[0.0066440487,0.00015752492,0.0001559797,0.0038860172,0.000048670747,0.0007506232,0.014544885,0.000199931,0.000046272446],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035662964,0.000051400562,0.058160376,0.000015165578,0.00020334656,0.000003542624,0.0000837108,0.0012281835,0.000054890264,0.0190175,0.8858182,0.03532805],"study_design_scores_gemma":[0.0017592782,0.000011619965,0.012791087,0.000010348596,0.00004362404,3.478242e-7,0.0000024900578,0.57397556,0.000047661662,0.4014998,0.009661273,0.00019691349],"about_ca_topic_score_codex":0.000039552873,"about_ca_topic_score_gemma":0.00024260466,"teacher_disagreement_score":0.8761569,"about_ca_system_score_codex":0.00009029711,"about_ca_system_score_gemma":0.000056172277,"threshold_uncertainty_score":0.99411005},"labels":[],"label_agreement":null},{"id":"W2270926629","doi":"10.1007/s11280-015-0370-0","title":"Identifying semantic blocks in Web pages using Gestalt laws of grouping","year":2015,"lang":"en","type":"article","venue":"World Wide Web","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council","keywords":"Computer science; Gestalt psychology; Web page; Information retrieval; Merge (version control); Artificial intelligence; Natural language processing; Data mining; Theoretical computer science; Algorithm; Perception; World Wide Web","score_opus":0.07740306236981702,"score_gpt":0.30177331895730586,"score_spread":0.22437025658748883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270926629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40837628,0.001366492,0.5776315,0.0023144262,0.000613255,0.0004804511,0.0000030985257,0.0006775855,0.00853695],"genre_scores_gemma":[0.97108895,0.000036033558,0.028080516,0.00012353862,0.00003175541,0.0000052845257,8.902621e-7,0.000010105469,0.0006229503],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987015,0.000081593105,0.00037307534,0.00028248897,0.00031712133,0.00024420107],"domain_scores_gemma":[0.999129,0.000089367466,0.00017585744,0.00041804666,0.00010948416,0.00007823019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006748162,0.00011990216,0.00020907965,0.00039220724,0.000048014168,0.00010677733,0.0005603893,0.00004051585,0.000007337286],"category_scores_gemma":[0.000101801306,0.00011780049,0.000054970198,0.0011359262,0.00006158129,0.0004942593,0.00024377198,0.0001540376,0.000011551876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004324002,0.00050833833,0.13399242,0.0004498383,0.00006470909,0.00024721076,0.00459113,0.00017230905,0.7224828,0.055585645,0.005328736,0.076533616],"study_design_scores_gemma":[0.0015329098,0.000110345565,0.017591622,0.0014275452,0.000037929825,0.00006423735,0.0005402811,0.471089,0.4695987,0.022646159,0.014282163,0.0010790761],"about_ca_topic_score_codex":0.000068239315,"about_ca_topic_score_gemma":0.00024711053,"teacher_disagreement_score":0.5627126,"about_ca_system_score_codex":0.00009034257,"about_ca_system_score_gemma":0.00014641267,"threshold_uncertainty_score":0.48037645},"labels":[],"label_agreement":null},{"id":"W2508222813","doi":"10.1007/s11280-016-0410-4","title":"Crawling ranked deep Web data sources","year":2016,"lang":"en","type":"article","venue":"World Wide Web","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Crawling; Ranking (information retrieval); Web crawler; Information retrieval; Deep Web; Hyperlink; Web search query; Variety (cybernetics); Web page; Data mining; Learning to rank; World Wide Web; Search engine; Artificial intelligence; The Internet","score_opus":0.02944221598943287,"score_gpt":0.2526845032144845,"score_spread":0.22324228722505163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508222813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10070893,0.0015897251,0.8451302,0.035903845,0.0012157209,0.0001831593,0.00016524644,0.0013607275,0.013742462],"genre_scores_gemma":[0.9706023,0.000047210888,0.022691475,0.0007288522,0.00022043788,0.000004009802,0.000023523246,0.0000135739665,0.0056686457],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983179,0.00008109201,0.00026436304,0.00067408424,0.0003012345,0.00036133672],"domain_scores_gemma":[0.99692094,0.00045570658,0.00010739357,0.0023494002,0.000038720435,0.000127859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005952448,0.00015295648,0.00021418622,0.00024841342,0.00016984853,0.00024494523,0.0030800388,0.00003010939,0.0001575488],"category_scores_gemma":[0.00024279609,0.00010294448,0.000065972876,0.000702623,0.00006810174,0.0009391605,0.0012090844,0.00009257252,0.0006961977],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035978388,0.00025058156,0.11849231,0.00005119202,0.00068549067,0.00021767127,0.00093814905,0.00010302865,0.056857016,0.0143799735,0.20614566,0.60184294],"study_design_scores_gemma":[0.001065985,0.000024380042,0.0023953426,0.00019820292,0.00007733131,0.000010802578,0.000042796462,0.13482472,0.002455202,0.0011588004,0.85713416,0.00061228976],"about_ca_topic_score_codex":0.0000277888,"about_ca_topic_score_gemma":0.0007837945,"teacher_disagreement_score":0.8698933,"about_ca_system_score_codex":0.000021439697,"about_ca_system_score_gemma":0.00008746487,"threshold_uncertainty_score":0.8948445},"labels":[],"label_agreement":null},{"id":"W2609579487","doi":"10.1007/s11280-017-0460-2","title":"Collaborative text categorization via exploiting sparse coefficients","year":2017,"lang":"en","type":"article","venue":"World Wide Web","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Sparse approximation; Pattern recognition (psychology); Categorization; Artificial intelligence; Classifier (UML); Sparse matrix; Representation (politics); Information retrieval; Data mining","score_opus":0.019044466667129008,"score_gpt":0.2666869600097453,"score_spread":0.2476424933426163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609579487","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02720687,0.00012912905,0.91645813,0.013269135,0.0012456408,0.00045927882,0.000005538569,0.0013426712,0.03988361],"genre_scores_gemma":[0.98786503,0.000015826874,0.007503513,0.00018753536,0.000038612692,0.00003819998,0.000005017593,0.000009036043,0.004337231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998906,0.00003104236,0.00021255169,0.00036666376,0.00024049846,0.00024325252],"domain_scores_gemma":[0.99830776,0.00007460759,0.00032295336,0.0010938606,0.00014618541,0.000054601158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018038097,0.00013101351,0.00013315557,0.00019458505,0.0007185917,0.0007188632,0.0014099866,0.00004425931,0.000032990723],"category_scores_gemma":[0.00027135122,0.00012419962,0.000030827156,0.00047149355,0.00013132251,0.0010194043,0.0003947787,0.00010755054,0.0003174217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012519431,0.0001837013,0.042144645,0.00001737512,0.000033146764,0.000023587714,0.001110046,0.00020776545,0.011683137,0.651364,0.02749866,0.26572135],"study_design_scores_gemma":[0.0024930586,0.00017406992,0.094983295,0.00016163738,0.000031888914,0.000007934374,0.00092520413,0.15702607,0.13421296,0.05507298,0.5532948,0.0016161042],"about_ca_topic_score_codex":0.00001744491,"about_ca_topic_score_gemma":0.000107687454,"teacher_disagreement_score":0.96065813,"about_ca_system_score_codex":0.00006153612,"about_ca_system_score_gemma":0.0000763657,"threshold_uncertainty_score":0.6932015},"labels":[],"label_agreement":null},{"id":"W2843323114","doi":"10.1007/s11280-018-0616-8","title":"MPE: a mobility pattern embedding model for predicting next locations","year":2018,"lang":"en","type":"article","venue":"World Wide Web","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; York University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Trajectory; Embedding; Salient; Object (grammar); Range (aeronautics); Variety (cybernetics); Location data","score_opus":0.04345428430531642,"score_gpt":0.3420575332160506,"score_spread":0.2986032489107342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2843323114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41790977,0.00009239323,0.5554844,0.0067050597,0.00034750058,0.0010776633,0.000059733076,0.0003857423,0.0179377],"genre_scores_gemma":[0.9918669,0.0000052108667,0.0009104208,0.00070440624,0.00058143033,0.00015980257,0.000019669462,0.000012058294,0.005740117],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863946,0.00012153634,0.000297093,0.00034356918,0.0002568698,0.00034145277],"domain_scores_gemma":[0.9985919,0.0005341635,0.000103229635,0.0003385258,0.00030147991,0.00013069663],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0013566583,0.0001029357,0.00015284464,0.00013410572,0.0014293136,0.00013684343,0.00027023835,0.00005645774,0.0005558071],"category_scores_gemma":[0.0007297619,0.00011005859,0.00012931493,0.00050268346,0.00039343655,0.00026741155,0.00003173567,0.00010550762,0.00007106417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100994934,0.0013958117,0.45938542,0.00032434653,0.0003776206,0.0000016207863,0.16884834,0.06840302,0.0009157715,0.030840885,0.042706367,0.2266998],"study_design_scores_gemma":[0.00015647404,0.000016738844,0.0012870798,0.000033209275,0.000056167297,3.7045734e-8,0.002668045,0.975912,0.000044141005,0.004080848,0.015601274,0.00014402816],"about_ca_topic_score_codex":0.003654915,"about_ca_topic_score_gemma":0.26746398,"teacher_disagreement_score":0.9075089,"about_ca_system_score_codex":0.00018866519,"about_ca_system_score_gemma":0.00041382085,"threshold_uncertainty_score":0.9998707},"labels":[],"label_agreement":null},{"id":"W2943003953","doi":"10.1007/s11280-019-00686-w","title":"Mining top-k sequential patterns in transaction database graphs","year":2019,"lang":"en","type":"article","venue":"World Wide Web","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China; Ministry of Science and Technology","keywords":"Computer science; Database transaction; Graph database; Database; Graph; Sequence (biology); Sequence database; Vertex (graph theory); Transaction data; Theoretical computer science; Algorithm","score_opus":0.016127278338139275,"score_gpt":0.25254544302669313,"score_spread":0.23641816468855387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943003953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6942971,0.00004292812,0.29964253,0.0016891949,0.00074106647,0.00026914565,0.00007639737,0.000188094,0.0030535283],"genre_scores_gemma":[0.9648704,0.000010526544,0.03359148,0.000359199,0.000034267032,0.000029423381,0.00005673173,0.000008528306,0.0010394703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999057,0.00002778874,0.0001824291,0.0003663945,0.00015419221,0.00021221634],"domain_scores_gemma":[0.9992357,0.00006708804,0.00004796668,0.00057879713,0.000014524399,0.000055915592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019240641,0.00009384951,0.00010546289,0.00022010953,0.000045781104,0.00010495722,0.00049721054,0.000020952788,0.00011246206],"category_scores_gemma":[0.0000049588384,0.000096860786,0.000037263202,0.00058706326,0.0000121135345,0.00056930626,0.0000763598,0.00012306227,0.00014130626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027322281,0.0005666827,0.32895392,0.0001460186,0.00006461881,0.00011139971,0.002941799,0.0007104072,0.027534237,0.079486236,0.015135266,0.5443221],"study_design_scores_gemma":[0.0031110705,0.0001342395,0.09916561,0.0005332067,0.0000315985,0.000043807275,0.00038533358,0.6445836,0.011627381,0.0019373767,0.23704723,0.0013995996],"about_ca_topic_score_codex":0.00019812078,"about_ca_topic_score_gemma":0.0008828432,"teacher_disagreement_score":0.64387316,"about_ca_system_score_codex":0.000026790829,"about_ca_system_score_gemma":0.00004057371,"threshold_uncertainty_score":0.39498684},"labels":[],"label_agreement":null},{"id":"W2990135320","doi":"10.1007/s11280-019-00746-1","title":"A survey on data provenance in IoT","year":2019,"lang":"en","type":"article","venue":"World Wide Web","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"National Postdoctoral Program for Innovative Talents; China Electronics Technology Group Corporation; Higher Education Discipline Innovation Project; China Postdoctoral Science Foundation; Aalto-Yliopisto; Ministry of Public Security of the People's Republic of China; Academy of Finland; National Natural Science Foundation of China","keywords":"Computer science; Internet of Things; Data science; Provenance; Big data; Data mining; Computer security","score_opus":0.23854317414185094,"score_gpt":0.40592950515442955,"score_spread":0.1673863310125786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990135320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8924169,0.00010836441,0.0002799863,0.00327959,0.0041709743,0.0005954819,0.00034818632,0.00008424276,0.09871628],"genre_scores_gemma":[0.9300696,0.0000010228207,0.000297664,0.0007198604,0.000030791853,0.0000019453328,0.00006381437,0.0000057484094,0.06880952],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9969155,0.0002489263,0.00042930798,0.0010882807,0.001049882,0.00026806266],"domain_scores_gemma":[0.9937202,0.002240772,0.00013089234,0.0037966205,0.000055004803,0.000056559336],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011563576,0.00009776508,0.00019339847,0.00046739535,0.000047549805,0.0003518021,0.002693243,0.000015804679,0.00056347606],"category_scores_gemma":[0.0042513064,0.00007199513,0.000024197318,0.0021330316,0.000035714373,0.00017565934,0.0012648664,0.00012871539,0.0066500395],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021352873,0.000056211386,0.34274253,0.0000017613486,0.0000022110128,0.0000058084715,0.000028175831,0.0004794934,0.0000130134495,0.0007404498,0.61739355,0.03851541],"study_design_scores_gemma":[0.00021024846,0.000013252972,0.5282978,0.000031020034,6.4696013e-7,1.15222974e-7,0.000020714437,0.027838022,0.0000065986856,0.00082022016,0.44267672,0.000084683365],"about_ca_topic_score_codex":0.00034822407,"about_ca_topic_score_gemma":0.01121742,"teacher_disagreement_score":0.18555522,"about_ca_system_score_codex":0.000030067618,"about_ca_system_score_gemma":0.00006504141,"threshold_uncertainty_score":0.9941234},"labels":[],"label_agreement":null},{"id":"W2999796443","doi":"10.1007/s11280-019-00755-0","title":"A multiview learning method for malware threat hunting: windows, IoT and android as case studies","year":2020,"lang":"en","type":"article","venue":"World Wide Web","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Malware; Android (operating system); Android malware; Computer security; Artificial intelligence; Internet of Things; Machine learning; Operating system","score_opus":0.04135592852039305,"score_gpt":0.34943411146994025,"score_spread":0.3080781829495472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999796443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062909247,0.0029191806,0.9841799,0.004180636,0.00011958477,0.0007027029,0.000004152109,0.0012358368,0.00036706205],"genre_scores_gemma":[0.3702901,0.00013070031,0.62688106,0.0017022883,0.00008358365,0.00015007214,9.776002e-7,0.000027704746,0.0007335398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985656,0.00012108419,0.00026384156,0.0006128558,0.00014356237,0.00029306646],"domain_scores_gemma":[0.9984128,0.0009048242,0.00015473539,0.0002555229,0.00013905799,0.00013307086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037580202,0.00021781887,0.00036377442,0.00013125729,0.00033028537,0.00009933035,0.00025365947,0.000040415096,0.0000069879734],"category_scores_gemma":[0.0010773384,0.00020663127,0.00008351606,0.00053339376,0.00005463645,0.00030049752,0.00042566526,0.00025793415,0.000009728448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011863628,0.000058919464,0.0036646258,0.000774534,0.00023151969,0.0020891344,0.0054674214,0.0010314093,0.008045051,0.011633128,0.0034186866,0.96346694],"study_design_scores_gemma":[0.003251698,0.0016632124,0.00026987097,0.0005606046,0.00016142044,0.0038260168,0.0019570622,0.23793663,0.10986573,0.023180405,0.6154058,0.0019215299],"about_ca_topic_score_codex":0.000023620223,"about_ca_topic_score_gemma":0.0001491689,"teacher_disagreement_score":0.9615454,"about_ca_system_score_codex":0.00004186327,"about_ca_system_score_gemma":0.000030839754,"threshold_uncertainty_score":0.8426179},"labels":[],"label_agreement":null},{"id":"W3007466464","doi":"10.1007/s11280-020-00785-z","title":"A comprehensive analysis of adverb types for mining user sentiments on amazon product reviews","year":2020,"lang":"en","type":"article","venue":"World Wide Web","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Adverb; Sentiment analysis; Superlative; Computer science; Natural language processing; Degree (music); Artificial intelligence; Product (mathematics); Meaning (existential); Linguistics; Information retrieval; Noun; Mathematics; Psychology","score_opus":0.05783494863255713,"score_gpt":0.30315538942918363,"score_spread":0.24532044079662652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007466464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71833223,0.019293817,0.19080879,0.054194424,0.0026909541,0.005140246,0.000099626006,0.0007276146,0.008712334],"genre_scores_gemma":[0.9464176,0.00014912701,0.045304697,0.0048653684,0.00019132884,0.00004678666,0.000054868833,0.000021454509,0.0029487116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998452,0.000084638086,0.00047358286,0.0005208353,0.00026409005,0.00020482454],"domain_scores_gemma":[0.998818,0.00019768075,0.0003288488,0.000455812,0.00011090908,0.00008878682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021184029,0.00016338709,0.0005873991,0.00040459613,0.000071700255,0.000059078444,0.000461898,0.000017371616,0.00008968357],"category_scores_gemma":[0.00008120945,0.0001413358,0.00040104598,0.002430926,0.000021322092,0.00015720967,0.00013105288,0.000060870298,0.000049827744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045414714,0.0010049487,0.20726348,0.0009999037,0.016601708,0.000032547443,0.010353385,0.025433214,0.058717895,0.02393887,0.5672143,0.08798558],"study_design_scores_gemma":[0.0009157639,0.00020334923,0.010191837,0.00021340785,0.0014865722,2.116216e-7,0.00008571021,0.3576406,0.017790444,0.000025181982,0.61094284,0.0005040652],"about_ca_topic_score_codex":0.0000045228385,"about_ca_topic_score_gemma":0.000013999689,"teacher_disagreement_score":0.33220738,"about_ca_system_score_codex":0.000017743761,"about_ca_system_score_gemma":0.000023687902,"threshold_uncertainty_score":0.5763506},"labels":[],"label_agreement":null},{"id":"W3032897077","doi":"10.1007/s11280-021-00874-7","title":"Distributed attribute-based access control system using permissioned blockchain","year":2021,"lang":"en","type":"preprint","venue":"World Wide Web","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Linux Foundation","keywords":"Access control; Computer science; Blockchain; Computer security; Transparency (behavior); Discretionary access control; Audit; Context (archaeology); Process (computing); Overhead (engineering); Role-based access control; Operating system; Business","score_opus":0.026169402922599456,"score_gpt":0.2754544998696013,"score_spread":0.24928509694700185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032897077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08813477,0.0009471802,0.8982303,0.008687251,0.0008514367,0.0010285642,0.00033815563,0.0016607568,0.000121580364],"genre_scores_gemma":[0.98201567,0.000005242172,0.016449604,0.0007733955,0.00012138354,0.00032846886,0.00019803259,0.00003846843,0.00006974395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607474,0.0003419626,0.0008270108,0.001542983,0.00051607843,0.00069722807],"domain_scores_gemma":[0.9951395,0.00038942095,0.0006325583,0.0031031067,0.00046909877,0.00026635997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074447406,0.00058557384,0.0009602826,0.0005549913,0.00054008956,0.0007793468,0.0040088827,0.00063816743,0.000035139878],"category_scores_gemma":[0.0001429648,0.000600024,0.00036873293,0.0016894002,0.00015824437,0.000102930055,0.0028611885,0.0013917241,0.000013114625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025664674,0.004375478,0.10692614,0.007227351,0.002704056,0.0036735658,0.00092853786,0.48645884,0.013158626,0.3140887,0.04242318,0.017778879],"study_design_scores_gemma":[0.0009869543,0.000011232158,0.0011365744,0.00066512363,0.00009536685,0.000017858718,0.00003936523,0.9898826,0.0022695805,0.0010781882,0.0031168382,0.00070030714],"about_ca_topic_score_codex":0.00017751179,"about_ca_topic_score_gemma":0.00019749258,"teacher_disagreement_score":0.8938809,"about_ca_system_score_codex":0.0005724198,"about_ca_system_score_gemma":0.0011691967,"threshold_uncertainty_score":0.9996451},"labels":[],"label_agreement":null},{"id":"W4226101728","doi":"10.1007/s11280-021-00972-6","title":"HOPLoP: multi-hop link prediction over knowledge graph embeddings","year":2021,"lang":"en","type":"article","venue":"World Wide Web","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Traverse; Embedding; Knowledge graph; Theoretical computer science; Graph; Margin (machine learning); Generalization; Machine learning; Artificial intelligence; Mathematics","score_opus":0.015868101327976156,"score_gpt":0.2643288682557699,"score_spread":0.24846076692779373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226101728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040551547,0.0064420183,0.9202047,0.00619009,0.008400173,0.0006389827,0.000028053659,0.0027485355,0.014795929],"genre_scores_gemma":[0.87402683,0.00034528534,0.10201154,0.0026612543,0.0007823559,0.000062766674,0.00002615084,0.00006875821,0.02001508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980286,0.00009932342,0.00034258215,0.0007606125,0.00026809177,0.0005008038],"domain_scores_gemma":[0.9984113,0.00025914973,0.00011768315,0.0008431546,0.00017517422,0.0001935604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015874254,0.00025140916,0.00024547492,0.00027847115,0.00020790602,0.00015838558,0.00063417054,0.00008770088,0.0000622337],"category_scores_gemma":[0.00009441192,0.0002565257,0.00018427739,0.0023940424,0.00007624952,0.0007829491,0.0004623604,0.00043978263,0.00013499279],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008431669,0.0012786436,0.11539889,0.0002201145,0.00038713834,0.0011934901,0.0035594506,0.014065981,0.0408207,0.13232517,0.366287,0.32437912],"study_design_scores_gemma":[0.002172655,0.0000840804,0.047826722,0.00030156833,0.000039471295,0.00006947674,0.000026439551,0.37965885,0.006955142,0.0129818935,0.5489263,0.00095743954],"about_ca_topic_score_codex":0.0000034876475,"about_ca_topic_score_gemma":0.00037242495,"teacher_disagreement_score":0.8334753,"about_ca_system_score_codex":0.000064088876,"about_ca_system_score_gemma":0.00009152884,"threshold_uncertainty_score":0.9999887},"labels":[],"label_agreement":null},{"id":"W4385607465","doi":"10.1007/s11280-023-01201-y","title":"A large-scale holistic measurement of crowdsourced edge cloud platform","year":2023,"lang":"en","type":"article","venue":"World Wide Web","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Server; Enhanced Data Rates for GSM Evolution; Cloud computing; Quality of service; Edge device; Edge computing; Service (business); Computer network; Software deployment; Distributed computing; Operating system; Telecommunications","score_opus":0.04959657868932868,"score_gpt":0.2611838857615039,"score_spread":0.21158730707217524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385607465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6606522,0.0004934197,0.2532532,0.0035184561,0.036635745,0.00069557317,0.000004576501,0.0021323115,0.042614512],"genre_scores_gemma":[0.99320596,0.000003611511,0.0028862052,0.00025806137,0.0013254418,0.000009697116,0.0000037833133,0.000020390498,0.0022868467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812317,0.00003491376,0.00035593894,0.00035110995,0.00057469,0.0005601641],"domain_scores_gemma":[0.9989206,0.00014645678,0.00012490922,0.0005830924,0.00010559695,0.00011931721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072702,0.0001633465,0.00025071012,0.00032738605,0.00017877179,0.00008405917,0.00079345115,0.00004033186,0.000009458786],"category_scores_gemma":[0.000106386135,0.00015698723,0.000118932956,0.0014829584,0.000037376467,0.00015690549,0.0005091384,0.00016850351,0.0003618122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004665187,0.00035062968,0.018893838,0.00035665405,0.00015009042,0.0001395826,0.011027128,0.0011158489,0.00850615,0.021612236,0.9121489,0.02565231],"study_design_scores_gemma":[0.0017349139,0.00011902835,0.024415575,0.000382057,0.00003375892,0.000011553019,0.00012386878,0.27978984,0.007383168,0.007864709,0.6773945,0.00074705016],"about_ca_topic_score_codex":0.000015453297,"about_ca_topic_score_gemma":0.00007334299,"teacher_disagreement_score":0.33255374,"about_ca_system_score_codex":0.00008491748,"about_ca_system_score_gemma":0.000117936645,"threshold_uncertainty_score":0.64017534},"labels":[],"label_agreement":null}]}