{"meta":{"query_hash":"2d95964af09c","filters":{"venue":"ACM Transactions on Knowledge Discovery from Data"},"cohort_total":47,"direct_labels_cover":0,"predictions_cover":47,"exported":47,"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/2d95964af09c","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Knowledge+Discovery+from+Data"},"results":[{"id":"W1965792576","doi":"10.1145/1376815.1376816","title":"Joint cluster analysis of attribute data and relationship data","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":50,"is_retracted":false,"has_abstract":true,"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","keywords":"Computer science; Data mining; Cluster analysis; Heuristic; Identification (biology); Tree (set theory); Machine learning; Mathematics; Artificial intelligence","score_opus":0.15403939983569437,"score_gpt":0.3374659296680593,"score_spread":0.1834265298323649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965792576","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":[0.09494489,0.0003875556,0.8141442,0.00025722134,0.00008240924,0.00019978463,0.089615226,0.00005537998,0.00031334066],"genre_scores_gemma":[0.89811295,0.0001050399,0.007239299,0.000020575999,0.00011936637,0.000008927831,0.094046615,0.0000228407,0.00032436653],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976367,0.00016247833,0.0005974874,0.0011498448,0.00022594258,0.00022758603],"domain_scores_gemma":[0.986357,0.00077650853,0.00020559385,0.012500946,0.00006924662,0.00009073617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042657237,0.00025256,0.0005923204,0.00037261262,0.0003128995,0.00008344376,0.003680263,0.000063807376,0.00042191125],"category_scores_gemma":[0.000053482414,0.00024434118,0.00012153805,0.0012208215,0.00018552845,0.0020655415,0.0011117562,0.00030936726,0.000026012955],"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":[0.00026030277,0.004562328,0.73960197,0.00006616323,0.027235094,0.000009455821,0.0015691904,0.002690768,0.00040947425,0.0013642674,0.1356031,0.08662786],"study_design_scores_gemma":[0.0020830883,0.000110605324,0.3737023,0.00021628848,0.024075156,0.0000040688924,0.0007328013,0.5546895,0.0008371073,0.005674841,0.036280446,0.001593761],"about_ca_topic_score_codex":0.0012199297,"about_ca_topic_score_gemma":0.0012996616,"teacher_disagreement_score":0.8069049,"about_ca_system_score_codex":0.000021909264,"about_ca_system_score_gemma":0.00010558071,"threshold_uncertainty_score":0.9963944},"labels":[],"label_agreement":null},{"id":"W1973522621","doi":"10.1145/2757281","title":"Refining Social Graph Connectivity via Shortcut Edge Addition","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":52,"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":"","keywords":"Computer science; Graph; Computation; Theoretical computer science; Algorithm; Data mining","score_opus":0.08509666336746628,"score_gpt":0.3278070009381637,"score_spread":0.24271033757069738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973522621","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":[0.04771097,0.00009028627,0.9375229,0.00015629394,0.0004231863,0.00015567723,0.008145196,0.00022061767,0.005574883],"genre_scores_gemma":[0.9878633,0.0000038093358,0.0022048918,0.000029750125,0.0007953213,0.00007107351,0.008639165,0.000039806993,0.00035285135],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982305,0.00017496252,0.00033490607,0.0007235213,0.00022753565,0.00030857068],"domain_scores_gemma":[0.99753755,0.00028920575,0.0001241657,0.0018159585,0.00010729399,0.00012583542],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029147568,0.00028770647,0.00037482165,0.00015850857,0.00037615266,0.0001712347,0.0011029074,0.00008236161,0.000662064],"category_scores_gemma":[0.000015644806,0.00030026853,0.00020554896,0.00048754257,0.00010586474,0.0013260074,0.0001145437,0.0003934701,0.00016441235],"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":[0.00036820146,0.0037669113,0.008584977,0.00001787253,0.001964874,0.00000673108,0.0014178226,0.0003137023,0.0013285655,0.004451393,0.12913099,0.84864795],"study_design_scores_gemma":[0.009899933,0.0011208312,0.027096214,0.0006909956,0.006016416,0.000009991234,0.0058952505,0.039972622,0.027976407,0.5094182,0.3643956,0.0075075733],"about_ca_topic_score_codex":0.0011997157,"about_ca_topic_score_gemma":0.0013300957,"teacher_disagreement_score":0.94015235,"about_ca_system_score_codex":0.000085016036,"about_ca_system_score_gemma":0.00012535935,"threshold_uncertainty_score":0.9999449},"labels":[],"label_agreement":null},{"id":"W1993150471","doi":"10.1145/1870096.1870099","title":"Discovering Knowledge-Sharing Communities in Question-Answering Forums","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Cluster analysis; Transaction data; Question answering; Set (abstract data type); Information retrieval; Identification (biology); Focus (optics); Function (biology); Database transaction; Data mining; Artificial intelligence; Database","score_opus":0.055056583051641024,"score_gpt":0.32007919195545265,"score_spread":0.26502260890381163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993150471","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":[0.26678598,0.00057611085,0.72437537,0.00027306608,0.00447211,0.00027793436,0.0005851359,0.00034833714,0.002305943],"genre_scores_gemma":[0.98700625,0.00014636896,0.011352762,0.00003342347,0.00023299192,0.000080469894,0.00036229828,0.00004675918,0.00073866715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997538,0.00015268182,0.00058406405,0.00090612407,0.00023915486,0.00057998556],"domain_scores_gemma":[0.9928135,0.00077612,0.000109027504,0.0061013913,0.000056181234,0.00014375546],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007541249,0.00038608597,0.00041080234,0.00041705216,0.00053778297,0.000904344,0.006632241,0.00018925921,0.00003992235],"category_scores_gemma":[0.00009476159,0.00038207188,0.000115033,0.0006400475,0.00012337316,0.0047908896,0.00067154266,0.0010651567,0.00021106614],"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":[0.0004013876,0.012666151,0.0924859,0.0010566034,0.001389587,0.00019539696,0.17774434,0.015539391,0.054892875,0.1526833,0.0049817767,0.48596328],"study_design_scores_gemma":[0.006587896,0.0005311692,0.024749156,0.005993009,0.0002010722,0.00012690948,0.014738234,0.7858169,0.023917357,0.026428776,0.10496845,0.0059410445],"about_ca_topic_score_codex":0.004609925,"about_ca_topic_score_gemma":0.041093912,"teacher_disagreement_score":0.77027756,"about_ca_system_score_codex":0.00012215834,"about_ca_system_score_gemma":0.0001542525,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W1993625478","doi":"10.1145/1409620.1409623","title":"On disclosure risk analysis of anonymized itemsets in the presence of prior knowledge","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hacker; Computer science; Heuristics; Context (archaeology); Set (abstract data type); Function (biology); Data mining; Benchmark (surveying); Information retrieval; Computer security","score_opus":0.05564791742840004,"score_gpt":0.3095288978769892,"score_spread":0.25388098044858914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993625478","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":[0.43290374,0.0009632585,0.5506737,0.0013855998,0.00044747329,0.0005512838,0.012463729,0.00016421593,0.00044700317],"genre_scores_gemma":[0.97518307,0.0008281052,0.023312712,0.000019993533,0.000018058241,0.000045803827,0.0005120702,0.000017046845,0.000063112355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965252,0.0006299415,0.00077682507,0.00116728,0.0005311152,0.0003696233],"domain_scores_gemma":[0.9646866,0.0048139375,0.0003663938,0.029973978,0.000106374675,0.000052731586],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00094587094,0.0003307804,0.00071127276,0.0008995895,0.00023690646,0.000080158745,0.053634718,0.00018813075,0.000039815426],"category_scores_gemma":[0.009050614,0.000245792,0.0002514653,0.004344023,0.00044973855,0.001973043,0.0068645715,0.00066666334,0.000032846714],"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":[0.00295063,0.049918193,0.11466779,0.00069422,0.017285055,0.00029223133,0.040189262,0.0110602975,0.0068597505,0.007807199,0.27976507,0.4685103],"study_design_scores_gemma":[0.0069835074,0.0011546405,0.30522785,0.0010915573,0.003302871,0.000019507897,0.0012852845,0.54992217,0.031182766,0.09408648,0.0035466761,0.002196695],"about_ca_topic_score_codex":0.00069368863,"about_ca_topic_score_gemma":0.002103097,"teacher_disagreement_score":0.54227936,"about_ca_system_score_codex":0.00006737896,"about_ca_system_score_gemma":0.00022166956,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W2020791430","doi":"10.1145/1552303.1552306","title":"Link spam target detection using page farms","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"PageRank; Computer science; Backlink; Web page; Spamdexing; HITS algorithm; Information retrieval; Ranking (information retrieval); Link analysis; Search engine; Precision and recall; Data mining; World Wide Web; Web search engine; Static web page; Web search query; Web development","score_opus":0.05779916987046218,"score_gpt":0.2945533312560526,"score_spread":0.2367541613855904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020791430","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":[0.026723418,0.00029014563,0.96871984,0.00056019804,0.002444731,0.00018909638,0.00038692504,0.00035419106,0.00033146408],"genre_scores_gemma":[0.966371,0.00006263352,0.032452516,0.00021016315,0.00046341956,0.000006834159,0.00017085318,0.000021087695,0.00024147275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797153,0.00012329772,0.00032280164,0.00096709485,0.00026834992,0.0003469131],"domain_scores_gemma":[0.9959709,0.00019333995,0.00010119793,0.00355343,0.00005980282,0.00012132856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027135437,0.00027853771,0.00023581102,0.00023325233,0.000488733,0.0005919617,0.0026364264,0.00016915002,0.00004022597],"category_scores_gemma":[0.00006658066,0.00027620365,0.0001170533,0.0007371004,0.000039897084,0.004181034,0.00008185375,0.00045037642,0.00017353139],"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":[0.00012064665,0.0008594718,0.00008298398,0.000017570715,0.00014344467,0.000021414964,0.0011129489,0.0028001308,0.053625513,0.00028612284,0.0004991576,0.9404306],"study_design_scores_gemma":[0.0019123111,0.00083710765,0.005347279,0.00023926012,0.00023825292,0.00006133546,0.00014878578,0.7392189,0.17972836,0.038067847,0.032544687,0.0016558666],"about_ca_topic_score_codex":0.00030277195,"about_ca_topic_score_gemma":0.00022197583,"teacher_disagreement_score":0.9396476,"about_ca_system_score_codex":0.00013332101,"about_ca_system_score_gemma":0.000098770106,"threshold_uncertainty_score":0.999969},"labels":[],"label_agreement":null},{"id":"W2038873345","doi":"10.1145/1857947.1857950","title":"Centralized and Distributed Anonymization for High-Dimensional Healthcare Data","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data anonymization; Scalability; Data sharing; Information privacy; Information sharing; Health care; Data mining; Data science; Computer security; Database; World Wide Web; Medicine","score_opus":0.06175333628821846,"score_gpt":0.3219685442326207,"score_spread":0.2602152079444023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038873345","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":[0.009220356,0.00022886468,0.8705069,0.023218844,0.0015967038,0.00045414024,0.0943409,0.00042918755,0.0000041303165],"genre_scores_gemma":[0.48199597,0.00015745811,0.46579325,0.00014919063,0.000102005004,0.0000451894,0.051697772,0.000028710094,0.000030460838],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972908,0.00008210045,0.0003737494,0.0015820693,0.0002537421,0.00041755737],"domain_scores_gemma":[0.9677362,0.0008684548,0.00012286805,0.03103032,0.00011054337,0.0001316327],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00040262454,0.0002735404,0.00028818965,0.00013500854,0.0004234759,0.00042143854,0.038974836,0.00022502008,0.000031878048],"category_scores_gemma":[0.0052625863,0.00026234734,0.000032821103,0.0004515256,0.000170844,0.004624877,0.01800042,0.000491575,0.000023045259],"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":[0.00041940968,0.002090731,0.0010400297,0.00022259886,0.00052633235,0.000018714925,0.0001605154,0.00007400884,0.008612551,0.012001772,0.48743185,0.4874015],"study_design_scores_gemma":[0.004153802,0.00022832472,0.005488982,0.00019620243,0.00020069559,0.000024230265,0.00005714233,0.6566705,0.009264846,0.28889316,0.033593655,0.001228471],"about_ca_topic_score_codex":0.0004180405,"about_ca_topic_score_gemma":0.0016101735,"teacher_disagreement_score":0.6565965,"about_ca_system_score_codex":0.00004474717,"about_ca_system_score_gemma":0.0002294687,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W2045929671","doi":"10.1145/1376815.1376819","title":"Semantic text similarity using corpus-based word similarity and string similarity","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Topic Modeling","field":"Computer Science","cited_by":485,"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 Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Semantic similarity; String metric; Artificial intelligence; Word (group theory); Natural language processing; Longest common subsequence problem; Focus (optics); String searching algorithm; String (physics); Representation (politics); Information retrieval; Matching (statistics); Pattern matching; Mathematics; Algorithm","score_opus":0.12043376955524356,"score_gpt":0.3074205502158795,"score_spread":0.18698678066063595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045929671","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":[0.25789788,0.00048201028,0.7391785,0.000449269,0.000602322,0.00025516204,0.00088225957,0.00020093721,0.00005164174],"genre_scores_gemma":[0.9141459,0.00017585357,0.08496581,0.00028326202,0.000120357145,0.000007870697,0.00018579145,0.00003426243,0.000080889076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996618,0.00022238604,0.00055153435,0.0015962564,0.00044516736,0.00056669087],"domain_scores_gemma":[0.9936689,0.00076636515,0.00014528865,0.0050732847,0.00010570969,0.00024043958],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042791144,0.00044899504,0.0004991243,0.00024116387,0.0008887696,0.00039133965,0.0032301676,0.00023176032,0.000043926728],"category_scores_gemma":[0.00016730548,0.00047388067,0.00013005742,0.00060182676,0.00022301223,0.0032008956,0.00044917647,0.000779875,0.000028486513],"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":[0.0010535731,0.014235256,0.08035918,0.0013299697,0.0020464158,0.0012449422,0.009301427,0.14382386,0.013503698,0.005221042,0.0035612078,0.7243194],"study_design_scores_gemma":[0.0015206332,0.00007072123,0.00786985,0.00022321615,0.00015579273,0.000037824124,0.000058879064,0.9804195,0.00405095,0.0030562957,0.0016796701,0.00085665035],"about_ca_topic_score_codex":0.00093957665,"about_ca_topic_score_gemma":0.0012531956,"teacher_disagreement_score":0.83659565,"about_ca_system_score_codex":0.00015528634,"about_ca_system_score_gemma":0.00045360302,"threshold_uncertainty_score":0.9997713},"labels":[],"label_agreement":null},{"id":"W2055028639","doi":"10.1145/1460797.1460801","title":"On domination game analysis for microeconomic data mining","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National University of Singapore","keywords":"Nash equilibrium; Game theory; Dimension (graph theory); Product (mathematics); Commodity; Computer science; Point (geometry); Best response; Space (punctuation); Mathematical economics; Economics; Mathematics","score_opus":0.07051834428210217,"score_gpt":0.3199586946775136,"score_spread":0.2494403503954114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055028639","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":[0.0044774367,0.00010304156,0.9809259,0.0014280102,0.0005887669,0.0002954917,0.011784271,0.00010654453,0.00029053618],"genre_scores_gemma":[0.7845188,0.00015401628,0.17293312,0.0008776998,0.00026214932,0.00003804383,0.03901297,0.00002821637,0.0021750059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977795,0.000051939878,0.00034330256,0.0013842093,0.00015082635,0.00029021583],"domain_scores_gemma":[0.9912363,0.0005368976,0.00011953549,0.008002349,0.000034095374,0.00007080908],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00040747118,0.00023613879,0.000299319,0.00046676432,0.00020514576,0.0007781206,0.008054944,0.00006041589,0.000044419714],"category_scores_gemma":[0.00007240747,0.00023555128,0.00011379865,0.0006892997,0.00003098208,0.007757449,0.00027915722,0.00012350363,0.00014928392],"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":[0.000096161755,0.001059067,0.00003071685,0.000013033335,0.0010063165,0.000004474022,0.0002748016,0.00094930787,0.00019843207,0.0030602731,0.01889881,0.9744086],"study_design_scores_gemma":[0.0023783317,0.00038204176,0.004677538,0.00008602093,0.0014706386,0.0000011931073,0.00015139682,0.92917657,0.0013410322,0.009165676,0.05022168,0.000947855],"about_ca_topic_score_codex":0.00003846171,"about_ca_topic_score_gemma":0.00022095325,"teacher_disagreement_score":0.97346073,"about_ca_system_score_codex":0.000063257845,"about_ca_system_score_gemma":0.000055482953,"threshold_uncertainty_score":0.99731195},"labels":[],"label_agreement":null},{"id":"W2069857456","doi":"10.1145/1993077.1993080","title":"Can the Utility of Anonymized Data be Used for Privacy Breaches?","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Office of Integrative Activities; Office of International Science and Engineering; Division of Information and Intelligent Systems; Research Grants Council, University Grants Committee","keywords":"Data publishing; Computer science; Data anonymization; Adversary; Anonymity; Information privacy; k-anonymity; Closeness; Internet privacy; Data mining; Computer security; Data science; Publishing; Mathematics","score_opus":0.21436211065159538,"score_gpt":0.3377835758204947,"score_spread":0.12342146516889929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069857456","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":[0.0072539276,0.00024144248,0.93075854,0.009254766,0.00076148653,0.00078217074,0.05035718,0.00037878478,0.00021170476],"genre_scores_gemma":[0.7224647,0.00009986045,0.27354145,0.00009728933,0.00004282353,0.00007632699,0.0035836522,0.00003068657,0.00006321892],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968375,0.00020287027,0.0005793292,0.0015828899,0.00034473333,0.00045270263],"domain_scores_gemma":[0.92076,0.0017377668,0.00023207777,0.07709621,0.000096818025,0.00007714401],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0010916331,0.00033063654,0.00043329617,0.00014316528,0.00031575406,0.00019113302,0.13792646,0.0001796375,0.00010543851],"category_scores_gemma":[0.0069446787,0.0002543618,0.000111704365,0.0006280677,0.0004210921,0.003849493,0.03717623,0.00043071798,0.000017431214],"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":[0.0007105922,0.0056845015,0.0017561284,0.00026094486,0.0017320184,0.000012080781,0.006062005,0.0000026868645,0.0025666028,0.0019490571,0.579182,0.40008137],"study_design_scores_gemma":[0.006062807,0.00050086965,0.011240957,0.00037609422,0.0008645111,0.000018778903,0.0011715527,0.39618433,0.09721239,0.4344465,0.050039586,0.0018816214],"about_ca_topic_score_codex":0.0015125099,"about_ca_topic_score_gemma":0.001952232,"teacher_disagreement_score":0.71521074,"about_ca_system_score_codex":0.00004479426,"about_ca_system_score_gemma":0.00034411444,"threshold_uncertainty_score":0.9999909},"labels":[],"label_agreement":null},{"id":"W2096281132","doi":"10.1145/1460797.1460799","title":"Mining frequent cross-graph quasi-cliques","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Division of Information and Intelligent Systems","keywords":"Heuristics; Computer science; Clique; Data mining; Vertex (graph theory); Graph; Theoretical computer science; Combinatorics; Mathematics","score_opus":0.05441437221485232,"score_gpt":0.33723344906684105,"score_spread":0.2828190768519887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096281132","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":[0.012472598,0.00042671373,0.98059565,0.0014078666,0.00052384665,0.00017446764,0.0030557145,0.00034462538,0.0009985437],"genre_scores_gemma":[0.6445814,0.0003035009,0.35063124,0.0006728818,0.0002588474,0.000062475316,0.0021565172,0.000031048414,0.0013021133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997773,0.00006394223,0.00039921017,0.0011404849,0.00025285778,0.00037052232],"domain_scores_gemma":[0.9936654,0.00032689545,0.000099170255,0.0056838365,0.00007367355,0.00015105026],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00025767714,0.0002756208,0.0002505935,0.00016847078,0.00045294897,0.0010065353,0.0054776412,0.00010263589,0.00004795776],"category_scores_gemma":[0.00005580661,0.0002644818,0.000105453546,0.0006260281,0.000094126175,0.0039624446,0.00014439914,0.00027201508,0.0002608568],"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":[0.000020532716,0.0021144429,0.00015572525,0.0000092581395,0.000113127746,0.000013167568,0.0011025767,0.00008252992,0.0008425939,0.006032854,0.009839436,0.97967374],"study_design_scores_gemma":[0.0075096297,0.0034051384,0.074288696,0.0015124219,0.0007096319,0.00011749928,0.0014798366,0.30309513,0.052909065,0.18510486,0.36235136,0.0075167445],"about_ca_topic_score_codex":0.0001861997,"about_ca_topic_score_gemma":0.00014733316,"teacher_disagreement_score":0.972157,"about_ca_system_score_codex":0.000053744723,"about_ca_system_score_gemma":0.0001393637,"threshold_uncertainty_score":0.99998075},"labels":[],"label_agreement":null},{"id":"W2180566385","doi":"10.1145/2733381","title":"Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":857,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Computer science; Visualization; Outlier; Anomaly detection; Data mining; Hierarchy; Hierarchical clustering; Pattern recognition (psychology); CURE data clustering algorithm; Mathematics; Artificial intelligence; Correlation clustering","score_opus":0.09123092616616002,"score_gpt":0.34674055329636305,"score_spread":0.25550962713020303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180566385","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":[0.0028126193,0.00013982081,0.99430025,0.00033434745,0.00033503308,0.0004047899,0.0012741553,0.00034260095,0.0000563591],"genre_scores_gemma":[0.8109892,0.00006770592,0.1868007,0.00012715303,0.00013535263,0.00012516971,0.0014515695,0.000030536055,0.00027259148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983726,0.000049497638,0.0002716901,0.00095925434,0.00015042735,0.00019650072],"domain_scores_gemma":[0.99550456,0.00029294696,0.000078260215,0.003856342,0.00011648104,0.00015141336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032451277,0.00018488643,0.00018450592,0.00011841388,0.00036828665,0.00039129797,0.0024180699,0.00010381401,0.0000056187178],"category_scores_gemma":[0.0001649733,0.00018104671,0.00003250396,0.00030550046,0.00008700784,0.0023790856,0.0005098539,0.00015196647,0.000025779138],"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":[0.00030573053,0.0018055422,0.0005945723,0.00010529674,0.0003625728,0.00000400909,0.0017706957,0.00028852772,0.002929705,0.009771018,0.016538572,0.9655238],"study_design_scores_gemma":[0.00068030355,0.00019127945,0.0007163838,0.000032662057,0.00010315328,0.000017179287,0.0000833254,0.9418531,0.009978435,0.017274806,0.028692147,0.0003772346],"about_ca_topic_score_codex":0.0001832148,"about_ca_topic_score_gemma":0.0007949124,"teacher_disagreement_score":0.96514654,"about_ca_system_score_codex":0.00005027113,"about_ca_system_score_gemma":0.000101262085,"threshold_uncertainty_score":0.73828703},"labels":[],"label_agreement":null},{"id":"W2214080290","doi":"10.1145/2700409","title":"Classification with Streaming Features: An Emerging-Pattern Mining Approach","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"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; Streaming data; Feature selection; Data mining; Benchmark (surveying); Classifier (UML); Curse of dimensionality; Feature (linguistics); Machine learning; Artificial intelligence; Feature vector; Pattern recognition (psychology)","score_opus":0.11101318228584427,"score_gpt":0.32390555529082665,"score_spread":0.21289237300498237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2214080290","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":[0.011983963,0.00011765834,0.9838828,0.00042787273,0.0002481344,0.00019464835,0.0021292283,0.00023487116,0.0007808366],"genre_scores_gemma":[0.6339324,0.000022045539,0.3589927,0.00008992276,0.0001823147,0.00010920639,0.00618889,0.000038523114,0.00044398368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785596,0.00008783719,0.0002636352,0.0011767807,0.0003220275,0.00029376222],"domain_scores_gemma":[0.9941777,0.00014583333,0.000114205424,0.0052391486,0.00009999767,0.00022311948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028233425,0.00025839993,0.00020490504,0.00015062651,0.000305398,0.0006896158,0.00408963,0.00008465454,0.000006092324],"category_scores_gemma":[0.000031022624,0.00022290775,0.00003379272,0.00060235313,0.000074977426,0.004448361,0.00014923529,0.00026243474,0.00005466597],"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":[0.000025305688,0.0013972207,0.000352817,0.000013827687,0.000115001385,0.0000044938697,0.0048229913,0.00044518302,0.00013743309,0.0006365609,0.0035387059,0.98851043],"study_design_scores_gemma":[0.0023003768,0.0005671641,0.012483664,0.00023387396,0.00025116093,0.000054799337,0.011667481,0.9490593,0.00084679504,0.00097578025,0.020088654,0.0014709743],"about_ca_topic_score_codex":0.00044661193,"about_ca_topic_score_gemma":0.00054693787,"teacher_disagreement_score":0.9870395,"about_ca_system_score_codex":0.00007163878,"about_ca_system_score_gemma":0.00022629791,"threshold_uncertainty_score":0.90899146},"labels":[],"label_agreement":null},{"id":"W2257410811","doi":"10.1145/3365672","title":"A New Smooth Approximation to the Zero One Loss with a Probabilistic Interpretation","year":2019,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hinge loss; Algorithm; Computer science; Probabilistic logic; Maxima and minima; Artificial intelligence; Mathematics; Benchmark (surveying); Mathematical optimization; Machine learning; Pattern recognition (psychology); Support vector machine","score_opus":0.04480686181851787,"score_gpt":0.29227264341833536,"score_spread":0.2474657815998175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2257410811","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":[0.00093433744,0.00014212125,0.9888692,0.0045040334,0.0012872105,0.0013871726,0.0021757896,0.00023489713,0.0004652418],"genre_scores_gemma":[0.83079356,0.00006072625,0.15743405,0.00027864357,0.00029090562,0.00028548852,0.009030242,0.000061182574,0.0017651916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99676436,0.00030442406,0.00045259207,0.001712724,0.00048008777,0.00028580945],"domain_scores_gemma":[0.98912203,0.00058334286,0.00028546425,0.0096945325,0.00017845693,0.00013615491],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00046095715,0.0004188118,0.000379028,0.00022670158,0.00022435997,0.0012554944,0.006803858,0.00018822083,0.00003136076],"category_scores_gemma":[0.0003629158,0.00030823261,0.000085581705,0.00054083986,0.000050545896,0.0016375467,0.00076448807,0.0010007573,0.0006361347],"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":[0.00053991645,0.0011664821,0.0001980154,0.00043416207,0.00050473784,0.0000028455177,0.009378181,0.1168347,0.0000756471,0.004556789,0.008698326,0.8576102],"study_design_scores_gemma":[0.0014017521,0.00055215805,0.009106469,0.0023730258,0.00063517713,0.0000064011842,0.00016676915,0.92506737,0.00026666006,0.0217589,0.037090816,0.0015744811],"about_ca_topic_score_codex":0.00094172196,"about_ca_topic_score_gemma":0.0014147349,"teacher_disagreement_score":0.8560357,"about_ca_system_score_codex":0.00018099057,"about_ca_system_score_gemma":0.00075720565,"threshold_uncertainty_score":0.999937},"labels":[],"label_agreement":null},{"id":"W2257550357","doi":"10.1145/2976744","title":"Scalable and Accurate Online Feature Selection for Big Data","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"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","keywords":"Feature selection; Pairwise comparison; Big data; Computer science; Scalability; Feature (linguistics); Benchmark (surveying); Curse of dimensionality; Selection (genetic algorithm); Artificial intelligence; Data mining; Dimensionality reduction; Set (abstract data type); Machine learning; Pattern recognition (psychology); Database","score_opus":0.10563085290882107,"score_gpt":0.31964763730881357,"score_spread":0.2140167843999925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2257550357","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":[0.009845309,0.0002938883,0.9651958,0.003746215,0.0013181885,0.00027411673,0.019159844,0.00013287802,0.00003376177],"genre_scores_gemma":[0.74293935,0.00363117,0.21649936,0.0010078659,0.002167817,0.00019216399,0.01975499,0.00012106677,0.013686225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983029,0.00006206945,0.00019189015,0.0010454891,0.00013963063,0.0002580295],"domain_scores_gemma":[0.9959974,0.00057710265,0.000070090784,0.0031764817,0.0000809767,0.00009792568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018636447,0.00019579213,0.00018290676,0.000116667514,0.0002927425,0.0002974211,0.0026195098,0.00012293148,0.000021823987],"category_scores_gemma":[0.00013225546,0.00013626,0.000035483175,0.00028598448,0.0000496266,0.0046993988,0.00030986508,0.00014658112,0.00007797],"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":[0.00010649015,0.00047115653,0.00007300702,0.000026771071,0.00008721461,8.3050264e-7,0.00007678995,0.000009124652,0.011226474,0.00004088049,0.05770346,0.9301778],"study_design_scores_gemma":[0.008352399,0.00072586717,0.0038499837,0.0016458621,0.00047424997,0.000042421776,0.0002922225,0.15707129,0.067971155,0.015166702,0.74236244,0.0020453986],"about_ca_topic_score_codex":0.00006390895,"about_ca_topic_score_gemma":0.0010234073,"teacher_disagreement_score":0.9281324,"about_ca_system_score_codex":0.000029895096,"about_ca_system_score_gemma":0.000116834504,"threshold_uncertainty_score":0.55565214},"labels":[],"label_agreement":null},{"id":"W2325563383","doi":"10.1145/2297456.2297460","title":"The Latent Maximum Entropy Principle","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Principle of maximum entropy; Mathematics; Statistics","score_opus":0.04418102761629817,"score_gpt":0.30897019030708406,"score_spread":0.2647891626907859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325563383","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":[0.020554347,0.0003623116,0.96732175,0.00037819886,0.0020930888,0.00023242222,0.007676215,0.00003956582,0.001342109],"genre_scores_gemma":[0.9953382,0.000048061855,0.0015885013,0.000033955213,0.00055935245,0.0000456838,0.0009954231,0.000028627574,0.0013622063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987931,0.00006058747,0.00022785662,0.00031768417,0.00015699353,0.00044374744],"domain_scores_gemma":[0.9974007,0.00048126493,0.00005324579,0.0018847632,0.000027397216,0.00015265644],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015287667,0.00018534996,0.00015219483,0.000023944569,0.00043499455,0.00017374152,0.0010288111,0.000034808625,0.0009448302],"category_scores_gemma":[0.000020273517,0.00012855935,0.000085484106,0.00011297394,0.000050985967,0.0005700155,0.00009299676,0.00024078564,0.0008741162],"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":[0.00018233011,0.0023120272,0.0057400055,0.000011275643,0.0007423863,0.000001424076,0.00038325277,0.000040993265,0.0005643795,0.5820554,0.009639564,0.39832696],"study_design_scores_gemma":[0.0024104186,0.00018289949,0.011861431,0.000097497905,0.00067416346,0.0000017480653,0.00086984213,0.017353322,0.0072395788,0.16866754,0.7894835,0.0011580917],"about_ca_topic_score_codex":0.00016937965,"about_ca_topic_score_gemma":0.000014242968,"teacher_disagreement_score":0.97478384,"about_ca_system_score_codex":0.000033247605,"about_ca_system_score_gemma":0.000042967786,"threshold_uncertainty_score":0.99996847},"labels":[],"label_agreement":null},{"id":"W2400248106","doi":"10.1145/2724720","title":"Improving Top-N Recommendation for Cold-Start Users via Cross-Domain Information","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Cold start (automotive); Computer science; Domain (mathematical analysis); Matrix decomposition; Cluster analysis; Precision and recall; Recommender system; Data mining; Artificial intelligence; Machine learning; Information retrieval; Mathematics; Engineering","score_opus":0.06982123719770345,"score_gpt":0.32001129143094836,"score_spread":0.2501900542332449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400248106","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":[0.0025579534,0.000039052917,0.99153423,0.0008588435,0.00182409,0.0006651043,0.0018464657,0.0002962637,0.00037796798],"genre_scores_gemma":[0.6877248,0.000026622734,0.30662832,0.0005049883,0.00025623146,0.00041042644,0.004009229,0.000040182338,0.0003991507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839556,0.00009190167,0.00051346485,0.0005209323,0.00018640002,0.00029176695],"domain_scores_gemma":[0.9968312,0.00027106053,0.00019825224,0.0023752984,0.0001832672,0.00014095336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076230435,0.00023103952,0.00023515742,0.00019464004,0.0002783944,0.0009873555,0.0021733665,0.00012706891,0.000014659292],"category_scores_gemma":[0.000080710575,0.00021730558,0.00008876645,0.0002998618,0.00003340177,0.012033333,0.00015967662,0.00017738476,0.00008282127],"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":[0.00018133028,0.0007228827,0.00066296203,0.00013987783,0.00023232054,0.0000016510154,0.00408406,0.00013170998,0.0012461356,0.0042063487,0.04893838,0.93945235],"study_design_scores_gemma":[0.0045063887,0.0007969041,0.00050479907,0.00016380634,0.00008993933,0.000014771821,0.00093506643,0.15082428,0.031420104,0.022325093,0.7870683,0.0013505237],"about_ca_topic_score_codex":0.0006296077,"about_ca_topic_score_gemma":0.00033511888,"teacher_disagreement_score":0.9381018,"about_ca_system_score_codex":0.00020677857,"about_ca_system_score_gemma":0.00020160561,"threshold_uncertainty_score":0.95210916},"labels":[],"label_agreement":null},{"id":"W2405494619","doi":"10.1145/2983533","title":"Structural Analysis of User Choices for Mobile App Recommendation","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Mobile apps; App store; Variety (cybernetics); Recommender system; World Wide Web; Margin (machine learning); Focus (optics); Taxonomy (biology); Data science; Human–computer interaction; Artificial intelligence; Machine learning","score_opus":0.05976271325554005,"score_gpt":0.3313509147680883,"score_spread":0.27158820151254826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405494619","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":[0.015047497,0.000071621624,0.9777194,0.00034785704,0.00056847563,0.000357523,0.0056474283,0.00012634374,0.00011385588],"genre_scores_gemma":[0.9662873,0.00007953702,0.031994607,0.000033118842,0.00006105348,0.00016029728,0.0008113271,0.000014311239,0.0005584374],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857265,0.00008040207,0.00040230053,0.0006417609,0.000118179836,0.00018473748],"domain_scores_gemma":[0.99631244,0.00075359346,0.00017652185,0.0026177051,0.000088013716,0.00005172679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002458964,0.00016979287,0.00033924822,0.00035046285,0.00012520538,0.00013423682,0.0022756453,0.00007735258,0.00010792388],"category_scores_gemma":[0.000028619848,0.00011652,0.00017947805,0.0006481597,0.00003565233,0.002727094,0.00010207816,0.00006304806,0.000010037784],"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":[0.00004939041,0.00029578322,0.0012294004,0.000034414283,0.0017338328,2.7557837e-7,0.00039394133,0.000041768904,0.0026642988,0.0014819849,0.0035628092,0.9885121],"study_design_scores_gemma":[0.007133161,0.0018981183,0.05084994,0.0008072035,0.0051664095,0.0000071273726,0.000639175,0.16215973,0.17572339,0.025924532,0.56621695,0.0034742556],"about_ca_topic_score_codex":0.0002623748,"about_ca_topic_score_gemma":0.0008108974,"teacher_disagreement_score":0.98503786,"about_ca_system_score_codex":0.000051175324,"about_ca_system_score_gemma":0.00004669107,"threshold_uncertainty_score":0.47515476},"labels":[],"label_agreement":null},{"id":"W2504431993","doi":"10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Naive Bayes classifier; Computer science; Machine learning; Missing data; Bayes' theorem; Artificial intelligence; Convergence (economics); Data mining; Bayesian probability; Support vector machine","score_opus":0.05267241250637728,"score_gpt":0.3180910509676954,"score_spread":0.26541863846131813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2504431993","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":[0.0024778892,0.00012111405,0.925047,0.0008988146,0.0007544235,0.00033049317,0.07009839,0.00016450968,0.000107356784],"genre_scores_gemma":[0.9836447,0.0008412626,0.012249186,0.000121869954,0.000054365162,0.00016141894,0.0023418511,0.000025372743,0.00055994577],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99791545,0.000157279,0.00041405216,0.00086044107,0.00033082106,0.000321951],"domain_scores_gemma":[0.9897711,0.0012239489,0.00018627678,0.00865044,0.0000859293,0.00008229438],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00039857035,0.00022520123,0.00020829738,0.0001054803,0.00032572672,0.00014977409,0.00716618,0.00008459675,0.00008766792],"category_scores_gemma":[0.00021198651,0.00013870203,0.00006730847,0.0003405692,0.00021525106,0.0026634822,0.00033874833,0.0001821051,0.0003999763],"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":[0.0002863266,0.0044664163,0.0014160891,0.00003639912,0.0002943533,0.000023102883,0.00056974543,0.0000034966556,0.039795004,0.061819907,0.12564114,0.765648],"study_design_scores_gemma":[0.0022989998,0.0005847816,0.020563984,0.00063083845,0.00021107323,0.00001063036,0.00021404884,0.002315516,0.6187772,0.009784552,0.34336403,0.001244325],"about_ca_topic_score_codex":0.000052194628,"about_ca_topic_score_gemma":0.0002123773,"teacher_disagreement_score":0.98116684,"about_ca_system_score_codex":0.00006625922,"about_ca_system_score_gemma":0.00014602898,"threshold_uncertainty_score":0.99820554},"labels":[],"label_agreement":null},{"id":"W2602756700","doi":"10.1145/3046941","title":"An Influence Propagation View of PageRank","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":82,"is_retracted":false,"has_abstract":true,"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; National Science Fund for Distinguished Young Scholars; Youth Innovation Promotion Association; National Science Foundation","keywords":"PageRank; Computer science; Ranking (information retrieval); Computation; Constraint (computer-aided design); Node (physics); Theoretical computer science; Data mining; Information retrieval; Algorithm; Mathematics","score_opus":0.041134871033084615,"score_gpt":0.345878011987555,"score_spread":0.3047431409544704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602756700","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":[0.81428635,0.00006966068,0.1748541,0.00018054803,0.00047750553,0.0002849894,0.008456795,0.00002699591,0.0013630593],"genre_scores_gemma":[0.9980007,0.00003975412,0.00077892706,0.000016465328,0.00012314557,0.00002033627,0.00086486107,0.00001593207,0.00013992419],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999001,0.00005231127,0.00026791397,0.0003985611,0.00012906038,0.0001511102],"domain_scores_gemma":[0.99615777,0.000082791776,0.00019721428,0.0034014045,0.00009480951,0.000066004264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013727004,0.00014991873,0.00021248269,0.000036791687,0.00051755377,0.00027604026,0.0019578952,0.000047635167,0.0001525846],"category_scores_gemma":[0.000018843164,0.00014384012,0.00006861816,0.000064529726,0.0001631119,0.0026952047,0.000054666256,0.00016984418,0.000055775745],"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":[0.0001585767,0.0036183014,0.054103665,0.000118033946,0.00056702463,0.0000023564758,0.0025448368,0.0019175564,0.014216561,0.022314273,0.0002467643,0.900192],"study_design_scores_gemma":[0.0059351455,0.0008841513,0.7445435,0.0019495871,0.00087912905,0.000001141107,0.0025389346,0.05087984,0.042988602,0.12580536,0.020258617,0.0033360026],"about_ca_topic_score_codex":0.0016776919,"about_ca_topic_score_gemma":0.0001811374,"teacher_disagreement_score":0.89685607,"about_ca_system_score_codex":0.000014700314,"about_ca_system_score_gemma":0.00011599045,"threshold_uncertainty_score":0.586563},"labels":[],"label_agreement":null},{"id":"W2724995883","doi":"10.1145/3080574","title":"Mining Community Structures in Multidimensional Networks","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Identification (biology); Set (abstract data type); Data mining; Node (physics); Function (biology); Machine learning; Feature (linguistics); Artificial intelligence; Data science","score_opus":0.06927095770474913,"score_gpt":0.3432355618617533,"score_spread":0.2739646041570042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724995883","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":[0.58439726,0.0001259744,0.41122234,0.0001119057,0.0003713024,0.00020277147,0.0017128059,0.00006569144,0.0017899462],"genre_scores_gemma":[0.9904635,0.000011570471,0.0070524705,0.000020327623,0.00022787073,0.000022093553,0.002001588,0.000025647525,0.00017495062],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986789,0.00020392549,0.0003016838,0.00042494945,0.00012368686,0.00026682162],"domain_scores_gemma":[0.9940179,0.00054773415,0.00015087564,0.005182915,0.00003522127,0.000065349835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026990066,0.00023666913,0.00031636062,0.00010023454,0.0010706406,0.0002616713,0.002574512,0.000065351625,0.0004004307],"category_scores_gemma":[0.000024368674,0.00023102756,0.00011218866,0.00010812128,0.00014199749,0.0010223454,0.0003250817,0.0006925988,0.00001709593],"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":[0.0003706893,0.0040926994,0.1904051,0.000022842418,0.001501451,0.000012694685,0.0019756875,0.017712055,0.00079088047,0.0046688616,0.011029308,0.7674177],"study_design_scores_gemma":[0.004907799,0.0001948734,0.61251396,0.0008766637,0.0008468434,0.0000021946034,0.003147614,0.2836301,0.0049823606,0.07225421,0.014103233,0.0025401372],"about_ca_topic_score_codex":0.0063241147,"about_ca_topic_score_gemma":0.006171139,"teacher_disagreement_score":0.7648776,"about_ca_system_score_codex":0.000036620753,"about_ca_system_score_gemma":0.00005237741,"threshold_uncertainty_score":0.9560212},"labels":[],"label_agreement":null},{"id":"W2786524829","doi":"10.1145/3047010","title":"ATR-Vis","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; Natural Sciences and Engineering Research Council of Canada; International Development Research Centre","keywords":"Computer science; Variety (cybernetics); Terminology; Task (project management); Information retrieval; Set (abstract data type); Visualization; Data science; World Wide Web; Data mining; Artificial intelligence","score_opus":0.048978138937205005,"score_gpt":0.29976558278340987,"score_spread":0.2507874438462049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786524829","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":[0.0036780934,0.00013269346,0.99198544,0.00082565437,0.0009220093,0.00008480417,0.0005920965,0.00013378938,0.0016454486],"genre_scores_gemma":[0.97432286,0.00008205503,0.022013647,0.00028581283,0.00033902083,0.0000100869065,0.00063836057,0.000017562457,0.0022905709],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838114,0.00009083856,0.0002704878,0.00080316095,0.00022356644,0.00023081274],"domain_scores_gemma":[0.9948745,0.00018755744,0.00006324652,0.0046843803,0.00010131046,0.00008905334],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020233815,0.00017426263,0.00019297571,0.0001550685,0.00034959606,0.0004488364,0.003781453,0.00007617232,0.0002364659],"category_scores_gemma":[0.000060542905,0.00015658658,0.00009409136,0.0007084415,0.00008617219,0.0030887795,0.00018270663,0.0001444941,0.0012691062],"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":[0.00007747742,0.0018079816,0.0018294564,0.000021857113,0.00073476066,0.000014462751,0.0024762521,0.00018783075,0.0025988675,0.0077780136,0.05139454,0.9310785],"study_design_scores_gemma":[0.0028730426,0.0008774126,0.020496387,0.0003060813,0.0007580318,0.000010340545,0.0004210156,0.5091985,0.02839396,0.030936703,0.40317994,0.0025485693],"about_ca_topic_score_codex":0.00022833102,"about_ca_topic_score_gemma":0.0013417568,"teacher_disagreement_score":0.9706448,"about_ca_system_score_codex":0.00004108521,"about_ca_system_score_gemma":0.000107431064,"threshold_uncertainty_score":0.9995085},"labels":[],"label_agreement":null},{"id":"W2791982474","doi":"10.1145/3023363","title":"Visual Analysis of Brain Networks Using Sparse Regression Models","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; National Institute of Biomedical Imaging and Bioengineering; DoD Alzheimer's Disease Neuroimaging Initiative; Defense Threat Reduction Agency; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; National Natural Science Foundation of China","keywords":"Visual analytics; Computer science; Discriminative model; Visualization; Artificial intelligence; Machine learning; Intersection (aeronautics); Human–computer interaction","score_opus":0.09753420314028476,"score_gpt":0.3740269390566549,"score_spread":0.27649273591637014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791982474","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":[0.008855609,0.00011062921,0.9886715,0.00012009346,0.0004394872,0.00008018603,0.0015179015,0.00006838386,0.00013620181],"genre_scores_gemma":[0.97287726,0.000077811914,0.024459181,0.00024737572,0.00012531421,0.0000021543437,0.0018889793,0.000019090927,0.00030285443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981413,0.00014910904,0.0004342823,0.00075222383,0.00028076064,0.00024232024],"domain_scores_gemma":[0.9958083,0.00030555605,0.00017780834,0.0034560263,0.00014746911,0.000104848725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003019046,0.00020729545,0.00037042462,0.000506204,0.00022882449,0.00024052431,0.0028151916,0.00010216711,0.0001002847],"category_scores_gemma":[0.000057998517,0.0001841209,0.00014322123,0.0025330302,0.0001438186,0.003128313,0.00027933737,0.000142958,0.00002453889],"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":[0.00041949228,0.0082348585,0.001585734,0.00009120104,0.009920169,0.00003076947,0.0057102256,0.6115114,0.005851765,0.023799654,0.02646744,0.3063773],"study_design_scores_gemma":[0.00024719926,0.000056512406,0.00016949244,0.00007731325,0.00052897795,5.8022107e-7,0.000060382303,0.9961469,0.0010608804,0.0006744854,0.0007730899,0.00020418226],"about_ca_topic_score_codex":0.00019510605,"about_ca_topic_score_gemma":0.00048404944,"teacher_disagreement_score":0.9642123,"about_ca_system_score_codex":0.000041993088,"about_ca_system_score_gemma":0.00012162289,"threshold_uncertainty_score":0.75082326},"labels":[],"label_agreement":null},{"id":"W2895492593","doi":"10.1145/3237191","title":"Enumerating Trillion Subgraphs On Distributed Systems","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Chongqing Research Program of Basic Research and Frontier Technology","keywords":"Enumeration; Computer science; Scalability; Theoretical computer science; Graph; Algorithm; Combinatorics; Mathematics; Database","score_opus":0.04566446021945211,"score_gpt":0.28904636755667584,"score_spread":0.24338190733722373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895492593","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":[0.017828893,0.00027661942,0.97283804,0.000190587,0.0032855356,0.00024379957,0.004623828,0.00025867517,0.00045402208],"genre_scores_gemma":[0.99477166,0.000047079186,0.0033720993,0.000081624574,0.00035195856,0.000030686697,0.0010525424,0.000022456,0.00026991242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976575,0.00026649202,0.00037296058,0.0010337858,0.0002839442,0.0003853411],"domain_scores_gemma":[0.9947031,0.0006028771,0.00010947441,0.004350277,0.00009966771,0.0001345708],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041730353,0.00029926957,0.00028228312,0.00022963036,0.0006710373,0.0006479366,0.0036279818,0.000116821764,0.000039398477],"category_scores_gemma":[0.000082560975,0.000264526,0.00011429503,0.0009657373,0.00015003623,0.002271482,0.0001264033,0.00031853118,0.0005212574],"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":[0.00092153146,0.0076232622,0.0005006992,0.00017961426,0.0017410117,0.00012511271,0.0067781066,0.0031335116,0.008384954,0.1452656,0.018827645,0.806519],"study_design_scores_gemma":[0.008786706,0.004692369,0.0055746017,0.0024832857,0.00064244855,0.000094770854,0.0021226776,0.6988614,0.07799484,0.09197768,0.101272285,0.0054969494],"about_ca_topic_score_codex":0.000102552556,"about_ca_topic_score_gemma":0.00007370039,"teacher_disagreement_score":0.9769428,"about_ca_system_score_codex":0.000048944945,"about_ca_system_score_gemma":0.000078823,"threshold_uncertainty_score":0.9999807},"labels":[],"label_agreement":null},{"id":"W3011191765","doi":"10.1145/3380928","title":"Continuous Influence Maximization","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Maximization; Computer science; Benchmark (surveying); Mathematical optimization; Product (mathematics); Function (biology); Mathematics","score_opus":0.041078501605940246,"score_gpt":0.291683042845804,"score_spread":0.25060454123986375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011191765","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":[0.056282673,0.00008864502,0.9383768,0.00055602775,0.00008491256,0.00019665158,0.0029392617,0.00017021415,0.001304808],"genre_scores_gemma":[0.99262077,0.00001625906,0.0041850586,0.00016798158,0.00025764445,0.000026138083,0.0025026042,0.000026966292,0.00019660586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876577,0.00006299142,0.00027702836,0.0005761653,0.00013015933,0.00018790377],"domain_scores_gemma":[0.997926,0.00016317054,0.00008436337,0.0016677661,0.000058553655,0.00010017585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058887377,0.00019579357,0.00025455683,0.000051105326,0.00015323736,0.00016609448,0.0013439509,0.00003772815,0.0007697274],"category_scores_gemma":[0.000017470442,0.00019789033,0.00009920794,0.00040077118,0.00005185266,0.0010157361,0.00009347358,0.00022884949,0.0002676182],"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":[0.00044309063,0.002973827,0.04091348,0.00005839509,0.0023363184,0.000011894092,0.0029351695,0.016830951,0.008597204,0.0058334568,0.049735263,0.86933094],"study_design_scores_gemma":[0.008153361,0.0011123453,0.03485236,0.0008486583,0.004612334,0.0000031645536,0.0037516528,0.31522366,0.08678443,0.09504409,0.4429159,0.0066980426],"about_ca_topic_score_codex":0.00034387654,"about_ca_topic_score_gemma":0.000058088324,"teacher_disagreement_score":0.93633807,"about_ca_system_score_codex":0.000018437564,"about_ca_system_score_gemma":0.000056318957,"threshold_uncertainty_score":0.8427975},"labels":[],"label_agreement":null},{"id":"W3027864066","doi":"10.1145/3377939","title":"Story Forest","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":60,"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 Alberta","funders":"","keywords":"Timeline; Computer science; Event (particle physics); Information retrieval; The Internet; Novelty; World Wide Web; Cluster analysis; Set (abstract data type); News aggregator; Graph; Data science; Artificial intelligence; History","score_opus":0.06664237805374586,"score_gpt":0.31143453917885444,"score_spread":0.2447921611251086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027864066","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":[0.0012818293,0.00035721823,0.9932447,0.0030503715,0.00022077406,0.00014411473,0.000643295,0.00058132946,0.00047638902],"genre_scores_gemma":[0.8561631,0.0001285432,0.14195356,0.0007959017,0.00015258684,0.000029941071,0.00038892665,0.000030129637,0.0003573156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981965,0.00009602082,0.00023930662,0.0009877858,0.00023205952,0.0002483482],"domain_scores_gemma":[0.995061,0.0003462591,0.000075508455,0.0043085604,0.00004851175,0.00016017193],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00012105525,0.0002262196,0.00025762097,0.000106142965,0.00021761477,0.00021561839,0.0058762324,0.000075891505,0.00005461461],"category_scores_gemma":[0.00011339957,0.00021976218,0.00011378573,0.0006317184,0.00007222089,0.003915032,0.0003020019,0.00039071694,0.00048925646],"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":[0.00011850766,0.0015119255,0.0006964733,0.00005939703,0.00068428303,0.000071722796,0.0032724647,0.0019353784,0.005527878,0.010437296,0.049011376,0.9266733],"study_design_scores_gemma":[0.0026126516,0.0008706229,0.0046979073,0.0002544108,0.0006033848,0.000011236802,0.0005607742,0.2985135,0.04590346,0.063127816,0.5796736,0.0031706733],"about_ca_topic_score_codex":0.00003863608,"about_ca_topic_score_gemma":0.00028112388,"teacher_disagreement_score":0.9235026,"about_ca_system_score_codex":0.000058666643,"about_ca_system_score_gemma":0.0001077944,"threshold_uncertainty_score":0.9995025},"labels":[],"label_agreement":null},{"id":"W3039137796","doi":"10.1145/3394053","title":"Internal Evaluation of Unsupervised Outlier Detection","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Outlier; Anomaly detection; Computer science; Cluster analysis; Data mining; Artificial intelligence; Domain (mathematical analysis); Pattern recognition (psychology); Binary number; Mathematics","score_opus":0.1100711224031969,"score_gpt":0.32755916439882915,"score_spread":0.21748804199563226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039137796","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":[0.019308383,0.00010768334,0.9780458,0.0007170492,0.00023641532,0.00032099013,0.0005167158,0.00019983476,0.0005471258],"genre_scores_gemma":[0.98686296,0.00003857337,0.012630235,0.00013122067,0.00008374235,0.000073489,0.00010662593,0.000014288283,0.000058851678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984031,0.00012483388,0.0003400802,0.00064221915,0.00035486656,0.00013495058],"domain_scores_gemma":[0.9973517,0.00012403564,0.00011194914,0.0021407101,0.00018103488,0.0000905405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029692875,0.0001534508,0.00017394463,0.000100673344,0.00013929866,0.000116203904,0.002318597,0.00007887397,0.00012245901],"category_scores_gemma":[0.000075098935,0.00015156652,0.00009180734,0.00056323764,0.00004761198,0.0015288091,0.00013279935,0.00020976523,0.00012115627],"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":[0.00005553005,0.00044508235,0.000058062946,0.000017328774,0.00011862043,5.2802733e-7,0.0008607258,0.00045662586,0.022800341,0.00047335736,0.0005580741,0.9741557],"study_design_scores_gemma":[0.001273032,0.00034590828,0.0023815536,0.000062015235,0.00025793072,0.0000037230036,0.00023207815,0.6556272,0.32453197,0.0061374228,0.008700502,0.00044664342],"about_ca_topic_score_codex":0.0001415572,"about_ca_topic_score_gemma":0.00010752028,"teacher_disagreement_score":0.9737091,"about_ca_system_score_codex":0.00006210299,"about_ca_system_score_gemma":0.00011596031,"threshold_uncertainty_score":0.61807036},"labels":[],"label_agreement":null},{"id":"W3044604502","doi":"10.1145/3480243","title":"Time-Aware Graph Embedding: A Temporal Smoothness and Task-Oriented Approach","year":2021,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Embedding; Computer science; Granularity; Theoretical computer science; Graph embedding; Graph; Smoothing; Artificial intelligence; Machine learning","score_opus":0.038241671914906405,"score_gpt":0.2946700430901839,"score_spread":0.2564283711752775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044604502","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":[0.010730222,0.0031505013,0.9775425,0.00024660275,0.0020844662,0.0006665132,0.00501364,0.00044052352,0.00012501712],"genre_scores_gemma":[0.69744295,0.0019646725,0.27316913,0.0002599502,0.00044520272,0.00037287298,0.025117679,0.00020939327,0.0010181814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994463,0.00033006797,0.00067406445,0.003404497,0.0004937968,0.00063456106],"domain_scores_gemma":[0.9893352,0.0004983218,0.00029893976,0.009411076,0.00016792481,0.00028858124],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002520662,0.0008635396,0.0008942301,0.00039647182,0.0004419841,0.0010387978,0.0063143503,0.00052772014,0.000029391784],"category_scores_gemma":[0.00004214874,0.0008714191,0.00029027654,0.0011134683,0.00032439342,0.0031876178,0.002556949,0.0017979471,0.000028733706],"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":[0.0012224894,0.019981597,0.0017395962,0.002994747,0.008175198,0.0011715969,0.02127901,0.2325454,0.002408377,0.003428422,0.03721682,0.6678367],"study_design_scores_gemma":[0.0032938935,0.00026355745,0.0013308622,0.0023260766,0.00072158047,0.00010797735,0.0010890391,0.9544118,0.0010671631,0.016337479,0.014128042,0.004922511],"about_ca_topic_score_codex":0.00012213326,"about_ca_topic_score_gemma":0.00011030024,"teacher_disagreement_score":0.7218664,"about_ca_system_score_codex":0.000092471455,"about_ca_system_score_gemma":0.00028643783,"threshold_uncertainty_score":0.9999982},"labels":[],"label_agreement":null},{"id":"W3119526997","doi":"10.1145/3428077","title":"Context-Based Evaluation of Dimensionality Reduction Algorithms—Experiments and Statistical Significance Analysis","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Dimensionality reduction; Computer science; Data mining; Curse of dimensionality; Algorithm; Redundancy (engineering); Context (archaeology); Generalizability theory; Parametric statistics; Machine learning; Reduction (mathematics); Artificial intelligence; Mathematics; Statistics","score_opus":0.10026200597180086,"score_gpt":0.3783655596835932,"score_spread":0.27810355371179235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119526997","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":[0.0746853,0.00054126146,0.92098683,0.00026608544,0.00035845552,0.00015988063,0.0029225233,0.000030078418,0.00004960396],"genre_scores_gemma":[0.9573767,0.000042929765,0.04000604,0.000039674927,0.000021054346,0.00003527327,0.0024229167,0.0000065063223,0.000048907925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784046,0.00042261175,0.00032446525,0.0007724981,0.0005045613,0.00013542899],"domain_scores_gemma":[0.99733734,0.00040421725,0.00010210202,0.0017232607,0.00035366384,0.000079410376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048698692,0.00014238722,0.00025417225,0.00013555284,0.00016194036,0.00011469356,0.0005295743,0.000069151756,0.00020585874],"category_scores_gemma":[0.00012965438,0.00013891769,0.00006735561,0.0006325153,0.00008992623,0.0011070522,0.00006821756,0.00012234438,0.0000182194],"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":[0.00023259726,0.004277564,0.00038100383,0.00007062621,0.0018023951,0.0000114739,0.0010167019,0.006813079,0.06351519,0.0011322788,0.0019246732,0.9188224],"study_design_scores_gemma":[0.0019669596,0.00010061865,0.008935197,0.00013951855,0.0015929572,0.0000029677947,0.00070290297,0.70747274,0.27327415,0.0050084135,0.00039539515,0.0004081913],"about_ca_topic_score_codex":0.0002122728,"about_ca_topic_score_gemma":0.00013742445,"teacher_disagreement_score":0.91841424,"about_ca_system_score_codex":0.000058126152,"about_ca_system_score_gemma":0.00032295953,"threshold_uncertainty_score":0.5664899},"labels":[],"label_agreement":null},{"id":"W3120491054","doi":"10.1145/3424672","title":"Knowledge Graph Embedding for Link Prediction","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":476,"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 Alberta","funders":"","keywords":"Computer science; Variety (cybernetics); Embedding; Link (geometry); Graph; Scale (ratio); Knowledge graph; Data science; Machine learning; Data mining; Artificial intelligence; Theoretical computer science","score_opus":0.06056504407758513,"score_gpt":0.32793144493453946,"score_spread":0.26736640085695434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120491054","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":[0.0010274919,0.0030198605,0.9866519,0.0007681875,0.0038325158,0.0003725753,0.0035940055,0.0003885637,0.00034487553],"genre_scores_gemma":[0.5396911,0.00286968,0.4436336,0.00052758574,0.0019532922,0.00045993575,0.006690711,0.0001821905,0.0039919023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971006,0.0001379858,0.0004704845,0.0015653883,0.00021430443,0.00051124225],"domain_scores_gemma":[0.99330395,0.00121803,0.00010631437,0.004986697,0.00021514272,0.00016983417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021335336,0.0003577867,0.00034772686,0.00021170963,0.00053947576,0.00041484495,0.0032765584,0.00018488147,0.000031350457],"category_scores_gemma":[0.00010684334,0.00037020253,0.00023996177,0.0012114805,0.00008668724,0.0040898737,0.00029353795,0.00046002638,0.000092098286],"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":[0.00015083805,0.0017347051,0.000121366575,0.00010724586,0.00050922995,0.00003732799,0.0012344314,0.008586855,0.005688496,0.009830159,0.019951787,0.9520476],"study_design_scores_gemma":[0.0050814697,0.0005496453,0.0014967568,0.00086570194,0.0004141126,0.00007229965,0.00033568352,0.48921257,0.043782406,0.1320297,0.3239738,0.0021858765],"about_ca_topic_score_codex":0.0000074234904,"about_ca_topic_score_gemma":0.00016949401,"teacher_disagreement_score":0.9498617,"about_ca_system_score_codex":0.00007979282,"about_ca_system_score_gemma":0.00019610135,"threshold_uncertainty_score":0.999875},"labels":[],"label_agreement":null},{"id":"W3163912335","doi":"10.1145/3448021","title":"Similarity Embedding Networks for Robust Human Activity Recognition","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":11,"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 Alberta","funders":"","keywords":"Artificial intelligence; Computer science; Embedding; Pattern recognition (psychology); Similarity (geometry); Pairwise comparison; Activity recognition; Cluster analysis; Convolutional neural network; Deep learning; Machine learning; Generalization; Data mining; Mathematics","score_opus":0.1595380997247741,"score_gpt":0.34323993684266196,"score_spread":0.18370183711788787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163912335","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":[0.0131797185,0.00019498281,0.97814023,0.00055435306,0.0019245548,0.00051500084,0.004792968,0.00031500575,0.00038316546],"genre_scores_gemma":[0.9676756,0.000060273178,0.027743699,0.0001741879,0.00044286507,0.0001868176,0.0030767343,0.000049934064,0.00058987224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684066,0.0003772203,0.00044117146,0.0015800818,0.00028465345,0.0004762025],"domain_scores_gemma":[0.9933999,0.0017545619,0.00019265235,0.004151868,0.00033689753,0.00016412343],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053577754,0.0003652805,0.00047438836,0.00016240487,0.00077469845,0.0009140321,0.002319765,0.00023993583,0.000121689234],"category_scores_gemma":[0.000237235,0.00041531547,0.00024948776,0.0006500361,0.000065242755,0.0054396032,0.00029220735,0.00052930164,0.00010161159],"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":[0.000106568616,0.002286644,0.000103102255,0.000092909955,0.00048734702,0.000027951059,0.0004422146,0.0016560786,0.0044210283,0.00010890332,0.0043911566,0.9858761],"study_design_scores_gemma":[0.005971317,0.0004454757,0.0034831762,0.001203792,0.00069810025,0.00009736064,0.00065202,0.88670665,0.064204454,0.013579221,0.019902363,0.0030560952],"about_ca_topic_score_codex":0.00022330646,"about_ca_topic_score_gemma":0.0031458747,"teacher_disagreement_score":0.98282,"about_ca_system_score_codex":0.00018094305,"about_ca_system_score_gemma":0.00026083627,"threshold_uncertainty_score":0.9998299},"labels":[],"label_agreement":null},{"id":"W3209720970","doi":"10.1145/3473910","title":"Semi-Supervised Ensemble Learning for Dealing with Inaccurate and Incomplete Supervision","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Ensemble learning; Supervised learning; Noise (video); Semi-supervised learning; Labeled data; Data mining; Artificial neural network","score_opus":0.059776607221555915,"score_gpt":0.3027910564366063,"score_spread":0.2430144492150504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209720970","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":[0.039680418,0.0006353926,0.9573585,0.0011622432,0.0001706511,0.00016293427,0.00046720746,0.00014129691,0.00022139557],"genre_scores_gemma":[0.91025007,0.00041198917,0.08588918,0.00009828782,0.00006424505,0.000030046223,0.0028408028,0.0000277228,0.0003876642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822265,0.0001513577,0.0002477473,0.00096790574,0.00016898336,0.00024137204],"domain_scores_gemma":[0.99657106,0.0008309593,0.00007348633,0.0022910624,0.00013550125,0.00009794674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027541383,0.00020894116,0.00022742298,0.00007963314,0.0005407056,0.0005617004,0.0012116978,0.00007216357,0.000024323075],"category_scores_gemma":[0.00019108846,0.00018670829,0.000041444335,0.00027109066,0.000040446135,0.0020904588,0.00018756269,0.00032287385,0.00002749107],"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":[0.0002385264,0.0004968649,0.0021240085,0.00016635965,0.00022034548,0.000022512397,0.0020543423,0.0029826562,0.022526728,0.005456049,0.0003800954,0.9633315],"study_design_scores_gemma":[0.0029418538,0.000413971,0.007561781,0.00043186973,0.00017337438,0.000045883135,0.0008076325,0.91626984,0.0096697975,0.0027544764,0.05805703,0.0008724777],"about_ca_topic_score_codex":0.00021632719,"about_ca_topic_score_gemma":0.0005946452,"teacher_disagreement_score":0.962459,"about_ca_system_score_codex":0.000028545657,"about_ca_system_score_gemma":0.00013747974,"threshold_uncertainty_score":0.7613743},"labels":[],"label_agreement":null},{"id":"W3212326024","doi":"10.1145/3487046","title":"Scalable Mining of High-Utility Sequential Patterns With Three-Tier MapReduce Model","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Narodowe Centrum Badań i Rozwoju; Høgskulen på Vestlandet","keywords":"Computer science; Scalability; Correctness; Data mining; Completeness (order theory); Computation; Scale (ratio); Database; Algorithm","score_opus":0.05944832735846505,"score_gpt":0.28622481848680353,"score_spread":0.22677649112833848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212326024","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":[0.100224584,0.00009536712,0.88596976,0.00032724222,0.0002481706,0.00011628532,0.012777335,0.00007420725,0.00016707793],"genre_scores_gemma":[0.7326949,0.00002942583,0.2648723,0.000033786502,0.000045942394,0.000033762437,0.0018059406,0.000018826244,0.00046507127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979524,0.000083059946,0.00033866335,0.0010624115,0.00028063165,0.00028281164],"domain_scores_gemma":[0.99418455,0.00019856551,0.00010232656,0.0052701617,0.00014032342,0.000104068255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002332727,0.00022152533,0.00029202588,0.00007448958,0.00022186466,0.0002669857,0.0028298225,0.00007829855,0.000088574],"category_scores_gemma":[0.000023688748,0.00020415557,0.000064458756,0.00050868595,0.00009732098,0.002242213,0.00033665542,0.00021597004,0.00003197923],"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":[0.00008769757,0.005021908,0.0019225747,0.00017488074,0.00079627277,0.000043540906,0.0020238338,0.009585463,0.0049179774,0.0036118387,0.003961254,0.9678528],"study_design_scores_gemma":[0.0011736405,0.00010129725,0.0057399757,0.00031217356,0.00023368915,0.000017465865,0.00029601637,0.9467992,0.03906717,0.0047532683,0.00088346173,0.00062259944],"about_ca_topic_score_codex":0.0005649258,"about_ca_topic_score_gemma":0.0014609449,"teacher_disagreement_score":0.96723014,"about_ca_system_score_codex":0.000036049558,"about_ca_system_score_gemma":0.0004455495,"threshold_uncertainty_score":0.8325223},"labels":[],"label_agreement":null},{"id":"W4205969642","doi":"10.1145/3495011","title":"sGrapp: Butterfly Approximation in Streaming Graphs","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":23,"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 Waterloo","funders":"","keywords":"Computer science; Bipartite graph; Theoretical computer science; Streaming algorithm; Graph; Mathematics; Upper and lower bounds","score_opus":0.034768323639447415,"score_gpt":0.2913620502884173,"score_spread":0.25659372664896984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205969642","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":[0.3186788,0.0001851852,0.66899437,0.00020145338,0.00029131983,0.00043840657,0.008857011,0.00014741014,0.0022060168],"genre_scores_gemma":[0.99128985,0.000008632991,0.0022618417,0.000025410502,0.00007788634,0.00020375712,0.005833315,0.00002754909,0.00027174872],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984317,0.00016912825,0.00034169253,0.0006127123,0.00020024207,0.00024453556],"domain_scores_gemma":[0.997589,0.00021625799,0.00009572983,0.0020371282,0.000019239533,0.000042625757],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002256185,0.00020235425,0.0002481447,0.00030618277,0.0003551564,0.000109361725,0.0013791379,0.000023582714,0.001126247],"category_scores_gemma":[0.0000036731317,0.00022571886,0.00012730081,0.0007959368,0.00003814382,0.0007656152,0.00017925518,0.000431032,0.000025761983],"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":[0.00026776153,0.007529104,0.048944194,0.00003366795,0.0010953879,0.000011291012,0.002732551,0.009087197,0.002555304,0.011475436,0.010778426,0.9054897],"study_design_scores_gemma":[0.0076403916,0.0007592749,0.0461773,0.00047027657,0.0018543934,0.0000064366077,0.0163635,0.21653031,0.014497528,0.593302,0.09747471,0.004923868],"about_ca_topic_score_codex":0.0015664075,"about_ca_topic_score_gemma":0.00052877114,"teacher_disagreement_score":0.9005658,"about_ca_system_score_codex":0.00007732025,"about_ca_system_score_gemma":0.000058642458,"threshold_uncertainty_score":0.99978685},"labels":[],"label_agreement":null},{"id":"W4220966911","doi":"10.1145/3502727","title":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Dirichlet process; Hierarchical Dirichlet process; Topic model; Computer science; Measure (data warehouse); Dirichlet distribution; Inference; Prior probability; Parametric statistics; Bayesian inference; Posterior probability; Mathematics; Bayesian probability; Applied mathematics; Artificial intelligence; Data mining; Statistics","score_opus":0.04890874881870901,"score_gpt":0.30447905946343445,"score_spread":0.25557031064472546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220966911","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":[0.00075371406,0.0001397633,0.9948135,0.00078322034,0.0004282722,0.0002509056,0.0025815496,0.00005919693,0.00018985667],"genre_scores_gemma":[0.53854185,0.00001192953,0.46027473,0.000107633634,0.000042535274,0.000092085575,0.00062498014,0.000016660737,0.00028761773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804693,0.0002525247,0.00036015178,0.00071352517,0.00041156955,0.00021531002],"domain_scores_gemma":[0.99740034,0.00035983065,0.00011571077,0.001965271,0.00007810251,0.00008071945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038951464,0.00017920171,0.00025811064,0.00018272456,0.00038985474,0.00008887001,0.0026198367,0.000057516616,0.00012545632],"category_scores_gemma":[0.00004735011,0.00017741033,0.00008688738,0.0005522099,0.000047502363,0.0011138809,0.00028503532,0.0004107635,0.0000045648762],"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":[0.000046766214,0.0007779908,0.000006229852,0.000016962673,0.00008472484,0.0000015493542,0.00111712,0.96532774,0.0000610475,0.013236632,0.00019185955,0.01913139],"study_design_scores_gemma":[0.00045083414,0.00007737064,0.000060110156,0.000016161202,0.000059494574,0.0000035676558,0.000019037616,0.95721227,0.00011747921,0.041748453,0.00005026381,0.00018495855],"about_ca_topic_score_codex":0.000027745271,"about_ca_topic_score_gemma":0.000013356408,"teacher_disagreement_score":0.5377881,"about_ca_system_score_codex":0.0000690711,"about_ca_system_score_gemma":0.00035591918,"threshold_uncertainty_score":0.72345835},"labels":[],"label_agreement":null},{"id":"W4225986943","doi":"10.1145/3502726","title":"On the Robustness of Metric Learning: An Adversarial Perspective","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"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":"National Science Foundation","keywords":"Robustness (evolution); Pairwise comparison; Computer science; Metric (unit); Adversarial system; Artificial intelligence; Machine learning","score_opus":0.04692128029731266,"score_gpt":0.309908607807081,"score_spread":0.26298732750976833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225986943","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":[0.01792742,0.00013429514,0.97656024,0.0011210763,0.0021610283,0.0003199448,0.0006358135,0.0001608647,0.0009793086],"genre_scores_gemma":[0.9923961,0.000013242335,0.006515086,0.00008091056,0.00018074445,0.00005504578,0.0002281117,0.000037793925,0.0004929465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962942,0.00121517,0.0003509263,0.0011145461,0.00069338793,0.0003317745],"domain_scores_gemma":[0.99248314,0.0026395672,0.0002366613,0.00443688,0.00011760796,0.00008614439],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009261291,0.0002917069,0.00032911028,0.00040225085,0.001256691,0.000188141,0.007974978,0.00006977667,0.0004969681],"category_scores_gemma":[0.00080278347,0.00024588744,0.00014546016,0.0017894936,0.00014365725,0.002013296,0.0008124592,0.0014485139,0.00003293797],"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":[0.0002589897,0.0011457144,0.000044323813,0.000005832664,0.00021147824,0.000008411846,0.003144259,0.949181,0.000079394624,0.030194592,0.0005748522,0.015151151],"study_design_scores_gemma":[0.0019684583,0.0012855676,0.000665868,0.00004306127,0.00022330826,0.00001183923,0.010455024,0.96807456,0.0006083731,0.011155119,0.0047197165,0.00078908453],"about_ca_topic_score_codex":0.0005903402,"about_ca_topic_score_gemma":0.00010148004,"teacher_disagreement_score":0.9744687,"about_ca_system_score_codex":0.00030224165,"about_ca_system_score_gemma":0.0003151656,"threshold_uncertainty_score":0.99999934},"labels":[],"label_agreement":null},{"id":"W4281975883","doi":"10.1145/3805034","title":"Streaming Hierarchical Clustering Based on Point-Set Kernel","year":2022,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"State Key Laboratory of Novel Software Technology; Nanjing University; National Natural Science Foundation of China","keywords":"Hierarchical clustering; Cluster analysis; Computer science; Data mining; Single-linkage clustering; Brown clustering; Tree (set theory); Consensus clustering; Correlation clustering; Hierarchical clustering of networks; CURE data clustering algorithm; Scalability; Kernel (algebra); Tree structure; Constrained clustering; Artificial intelligence; Mathematics; Algorithm; Database; Binary tree","score_opus":0.07734526681048454,"score_gpt":0.3535982704819712,"score_spread":0.27625300367148664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281975883","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":[0.0012679024,0.00018135423,0.9770254,0.0012663078,0.0029646347,0.0006946734,0.015346482,0.0005050921,0.00074818905],"genre_scores_gemma":[0.61897045,0.0003504675,0.36034438,0.00067186996,0.0008721789,0.0009623643,0.013910856,0.00038374704,0.0035337035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99318516,0.0006159127,0.0007285065,0.0033244956,0.001233428,0.00091251987],"domain_scores_gemma":[0.98299664,0.0022263443,0.00021714186,0.014140242,0.00008985901,0.00032974168],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00070927443,0.00080463546,0.0007222937,0.0007342101,0.0007524445,0.001117058,0.015223838,0.00032993368,0.00039372497],"category_scores_gemma":[0.00029067448,0.00086370966,0.00031083543,0.00071031175,0.00017588827,0.0017131012,0.00629926,0.0039671496,0.0001945419],"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":[0.00040064214,0.0022305262,0.00003715876,0.00034975112,0.000398753,0.00028046654,0.0012783553,0.5905523,0.00016991487,0.00013936317,0.001121284,0.40304148],"study_design_scores_gemma":[0.0010509464,0.00026300322,0.00032107218,0.0005240484,0.000057740857,0.000007303931,0.0001385141,0.98849374,0.00033412813,0.0034224214,0.004437756,0.00094933016],"about_ca_topic_score_codex":0.00044571806,"about_ca_topic_score_gemma":0.0004940313,"teacher_disagreement_score":0.61770254,"about_ca_system_score_codex":0.0008173398,"about_ca_system_score_gemma":0.0008914137,"threshold_uncertainty_score":0.9999199},"labels":[],"label_agreement":null},{"id":"W4306407742","doi":"10.1145/3563947","title":"Lifelong Online Learning from Accumulated Knowledge","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Université Laval","funders":"Universidade de Macau","keywords":"Computer science; Lifelong learning; Task (project management); Artificial intelligence; Machine learning; Process (computing); Transfer of learning; Knowledge base; Online learning; Multi-task learning; Knowledge transfer; Knowledge management","score_opus":0.09332883032205538,"score_gpt":0.3227769710322922,"score_spread":0.2294481407102368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306407742","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":[0.05493166,0.0013349381,0.9360772,0.00079374516,0.0023232927,0.00027371602,0.0025838588,0.0006593003,0.0010223377],"genre_scores_gemma":[0.9690897,0.000116830124,0.018682968,0.0003405742,0.00025074443,0.00005368877,0.006518397,0.000064857064,0.004882248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639404,0.0006919604,0.0005413843,0.0014233091,0.00046557694,0.00048376032],"domain_scores_gemma":[0.994554,0.0013404093,0.0001890495,0.003627887,0.00008430141,0.00020434777],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043987116,0.00037553042,0.00038470523,0.00032665333,0.0013779576,0.00053502567,0.005736408,0.00009982175,0.0011150481],"category_scores_gemma":[0.00020375058,0.0004123793,0.00015818045,0.0012075431,0.00007289518,0.002599806,0.0009377652,0.0014035819,0.00062340574],"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":[0.0003212774,0.00555113,0.0012893179,0.000028501227,0.0008688688,0.00010549077,0.01791124,0.08472993,0.003565111,0.0012389105,0.008201253,0.876189],"study_design_scores_gemma":[0.0025352028,0.00029311326,0.007699175,0.00009282937,0.00014483226,0.000011221625,0.0029381155,0.65343153,0.000564508,0.0020241272,0.3291465,0.0011188564],"about_ca_topic_score_codex":0.00047893854,"about_ca_topic_score_gemma":0.00048332632,"teacher_disagreement_score":0.91739416,"about_ca_system_score_codex":0.00020447023,"about_ca_system_score_gemma":0.00031183768,"threshold_uncertainty_score":0.9999221},"labels":[],"label_agreement":null},{"id":"W4313437244","doi":"10.1145/3578586","title":"Summarizing User-item Matrix By Group Utility Maximization","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Greedy algorithm; Computer science; Selection (genetic algorithm); Population; Similarity (geometry); Group (periodic table); Maximization; Data mining; Preference; Cluster analysis; Information retrieval; Theoretical computer science; Artificial intelligence; Algorithm; Mathematical optimization; Mathematics; Statistics","score_opus":0.06137206547769925,"score_gpt":0.3151175045849592,"score_spread":0.25374543910725994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313437244","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":[0.0029487778,0.00033430764,0.9903732,0.000678908,0.00118214,0.00031848653,0.0026133112,0.0010984982,0.00045236244],"genre_scores_gemma":[0.9570478,0.0006031288,0.033602193,0.00014829273,0.00015114709,0.00012942188,0.0053471304,0.0000634964,0.0029073916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977576,0.00018533906,0.00042684335,0.0010074802,0.00026587342,0.00035684675],"domain_scores_gemma":[0.99504066,0.00050755445,0.00010351173,0.004199936,0.00004613778,0.0001021917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049987563,0.00025754605,0.0002751549,0.00021596614,0.00033792824,0.00060824526,0.0036376982,0.0001394252,0.000042693155],"category_scores_gemma":[0.000051602783,0.00024893653,0.00009790914,0.0010187209,0.000038378228,0.003631687,0.00032314946,0.00026172967,0.0002322959],"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":[0.00006147296,0.0014362136,0.0038452225,0.00016650849,0.00037504325,0.000025579973,0.0011709847,0.000059194856,0.002822097,0.005100809,0.40413544,0.5808014],"study_design_scores_gemma":[0.0017568952,0.00028441363,0.009898155,0.00046004364,0.00014857364,0.000014177149,0.00047025684,0.2840926,0.013137718,0.017178463,0.6707206,0.001838109],"about_ca_topic_score_codex":0.0006806146,"about_ca_topic_score_gemma":0.0004006017,"teacher_disagreement_score":0.956771,"about_ca_system_score_codex":0.000071041875,"about_ca_system_score_gemma":0.000059207585,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4317209824","doi":"10.1145/3580367","title":"Differentially Private Release of Heterogeneous Network for Managing Healthcare Data","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Flexibility (engineering); Computer science; Health care; Scalability; Variety (cybernetics); Data sharing; Data science; Enhanced Data Rates for GSM Evolution; Big data; Information exchange; Private information retrieval; Information sharing; Data mining; Computer security; World Wide Web; Database; Artificial intelligence","score_opus":0.09979903213826967,"score_gpt":0.33325412466265963,"score_spread":0.23345509252438995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317209824","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":[0.007168433,0.0006564875,0.9493866,0.010079213,0.0015887498,0.00057528657,0.029552223,0.0009772334,0.000015771284],"genre_scores_gemma":[0.5809961,0.001886667,0.39277473,0.00018074011,0.00027399356,0.00012434389,0.023532048,0.00009784979,0.00013354584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965449,0.00013673597,0.0005864924,0.0017321389,0.00033402265,0.00066573516],"domain_scores_gemma":[0.94981366,0.0010555118,0.0002005362,0.048752017,0.000070202164,0.00010809491],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005383591,0.0003248335,0.00043263732,0.00025625617,0.00035460843,0.00026481855,0.081995115,0.00016450162,0.00001209401],"category_scores_gemma":[0.002564168,0.00032635868,0.00009877373,0.0011560164,0.00012941207,0.0026236977,0.040286563,0.00035494805,0.000075799246],"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":[0.0002777313,0.0008178037,0.00041810778,0.00059598987,0.000854411,0.00005664916,0.00019078713,0.0020148286,0.0007570342,0.0025238886,0.2832617,0.7082311],"study_design_scores_gemma":[0.0010490617,0.000204361,0.0007853986,0.0005074403,0.0001510667,0.0000067683404,0.000045793262,0.67283875,0.0034879001,0.30756032,0.0126783885,0.0006847488],"about_ca_topic_score_codex":0.00022996716,"about_ca_topic_score_gemma":0.000766352,"teacher_disagreement_score":0.7075463,"about_ca_system_score_codex":0.000065447166,"about_ca_system_score_gemma":0.00016373218,"threshold_uncertainty_score":0.9999188},"labels":[],"label_agreement":null},{"id":"W4319349118","doi":"10.1145/3563040","title":"DeltaShield: Information Theory for Human- Trafficking Detection","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Computer science; Interpretability; Scalability; Spotting; Domain (mathematical analysis); Law enforcement; Laptop; Information retrieval; Data mining; Matching (statistics); Artificial intelligence; Database","score_opus":0.059850506837205636,"score_gpt":0.3110097719310146,"score_spread":0.2511592650938089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319349118","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":[0.023246298,0.000038235277,0.9724162,0.00018992071,0.002057566,0.00032790218,0.0008128742,0.000727051,0.0001839567],"genre_scores_gemma":[0.99494845,0.00003112354,0.003158568,0.00010206578,0.00019103331,0.000111033376,0.0012037209,0.00001859898,0.00023539588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986272,0.00009537957,0.00031500554,0.0004896586,0.00019467552,0.0002780675],"domain_scores_gemma":[0.996879,0.0007663606,0.0000954904,0.0021255577,0.000070546914,0.00006303997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006332241,0.0001864712,0.00015579276,0.0003763043,0.00068066176,0.0005933723,0.0020106062,0.0001313036,0.000016152277],"category_scores_gemma":[0.00015444854,0.0001884134,0.00010364127,0.00084259245,0.000033647728,0.006602312,0.00008667887,0.00022921404,0.0003382978],"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":[0.00008668934,0.0001351518,0.0000088930565,0.00003999065,0.00010429137,9.80983e-7,0.0022113507,0.0014339003,0.0026899942,0.0034650392,0.0014867372,0.988337],"study_design_scores_gemma":[0.0056840577,0.0013294086,0.0063315793,0.00044138046,0.0004941474,0.000023204795,0.002527423,0.48100016,0.12806964,0.22968489,0.14180097,0.0026131554],"about_ca_topic_score_codex":0.000094011586,"about_ca_topic_score_gemma":0.00048451507,"teacher_disagreement_score":0.98572385,"about_ca_system_score_codex":0.000071009534,"about_ca_system_score_gemma":0.000059874226,"threshold_uncertainty_score":0.76832753},"labels":[],"label_agreement":null},{"id":"W4366087542","doi":"10.1145/3592857","title":"Modeling Regime Shifts in Multiple Time Series","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Computer science; Time series; Dependency (UML); Representation (politics); Grid; Machine learning; Artificial intelligence; Data mining; Mathematics","score_opus":0.06498033503273945,"score_gpt":0.2730715737043471,"score_spread":0.20809123867160764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366087542","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":[0.061591975,0.00022717033,0.9346733,0.0009737907,0.00045174774,0.00016889053,0.0010391751,0.0004177961,0.0004561362],"genre_scores_gemma":[0.978622,0.00016140686,0.017405942,0.000041566047,0.00009881467,0.000026621401,0.0009835234,0.00003403601,0.0026260554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980708,0.0000777739,0.00037654207,0.00087271485,0.00021310104,0.00038908995],"domain_scores_gemma":[0.9964082,0.0002876419,0.00004988098,0.0031366474,0.00003804085,0.0000795884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032916627,0.00022002224,0.00029323448,0.00031605258,0.0002753528,0.00037212842,0.0029324922,0.00008369961,0.00006788974],"category_scores_gemma":[0.00010714785,0.0002128397,0.00010209436,0.0014587035,0.00004459436,0.0041786507,0.00032603074,0.00024928994,0.0011528421],"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":[0.00033059076,0.0015207242,0.0008326042,0.00009962261,0.00069775875,0.00018866494,0.008966154,0.48908365,0.0043875575,0.0022908628,0.0055198595,0.48608196],"study_design_scores_gemma":[0.0003171043,0.0000335074,0.000404985,0.00008170404,0.000024008723,0.0000012818341,0.000194944,0.99469846,0.00023363052,0.002177953,0.0015653397,0.00026706562],"about_ca_topic_score_codex":0.00051744614,"about_ca_topic_score_gemma":0.0019669856,"teacher_disagreement_score":0.9172674,"about_ca_system_score_codex":0.000050197625,"about_ca_system_score_gemma":0.00008493378,"threshold_uncertainty_score":0.99962485},"labels":[],"label_agreement":null},{"id":"W4386497976","doi":"10.1145/3622940","title":"Discovering Interesting Patterns from Hypergraphs","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Hypergraph; Data mining; Computer science; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.07976721731493004,"score_gpt":0.31524831086129085,"score_spread":0.23548109354636082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386497976","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":[0.12797542,0.000082362894,0.8534598,0.00058018934,0.00096390373,0.00013504873,0.016073024,0.0005542049,0.00017606516],"genre_scores_gemma":[0.94733584,0.00022033186,0.044535972,0.00011166901,0.00025908978,0.00009260102,0.0068550673,0.000048019665,0.00054139877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774593,0.00006013424,0.0003523463,0.0012149205,0.00024119235,0.00038549321],"domain_scores_gemma":[0.9936139,0.00078367,0.00008274014,0.00536118,0.000031658816,0.00012685606],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001784589,0.00026761045,0.00023923922,0.00021257365,0.00037948863,0.00076320814,0.0056080706,0.000075535914,0.000053174506],"category_scores_gemma":[0.00007505007,0.000259243,0.000094544455,0.0008407405,0.000052785595,0.003305503,0.0006782473,0.00031658754,0.0009672329],"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":[0.000017081282,0.0006436243,0.0017333233,0.000025358499,0.00031515418,0.00003847947,0.0022259443,0.00047849992,0.0023986404,0.0013669779,0.0063863564,0.9843706],"study_design_scores_gemma":[0.0024278942,0.00022901624,0.07162513,0.0013798096,0.0003279841,0.000014694995,0.002454008,0.8276272,0.012941786,0.027994221,0.050227396,0.0027508975],"about_ca_topic_score_codex":0.0016907239,"about_ca_topic_score_gemma":0.0008285621,"teacher_disagreement_score":0.98161966,"about_ca_system_score_codex":0.000042617085,"about_ca_system_score_gemma":0.00007908837,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W4388421529","doi":"10.1145/3631609","title":"Laplacian Change Point Detection for Single and Multi-view Dynamic Graphs","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Anomaly detection; Laplacian matrix; Snapshot (computer storage); Laplace operator; Embedding; Theoretical computer science; Graph; Algorithm; Data mining; Artificial intelligence; Mathematics","score_opus":0.09321852727549758,"score_gpt":0.335970799174395,"score_spread":0.24275227189889742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388421529","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":[0.05113339,0.0004360422,0.9386553,0.00024359701,0.0003607133,0.00082117616,0.007877279,0.00033603574,0.00013646709],"genre_scores_gemma":[0.99258745,0.00012002211,0.0028422065,0.00002228388,0.00012007026,0.00032118472,0.0036055646,0.000041761134,0.00033943585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987683,0.000053745312,0.00023733114,0.0005968026,0.00008222154,0.00026155091],"domain_scores_gemma":[0.9982471,0.0002588322,0.0000709272,0.0013168775,0.00003936082,0.00006694474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001606441,0.00021685132,0.0002615508,0.00020648997,0.000294201,0.00013516344,0.0005313893,0.00005152387,0.0000774448],"category_scores_gemma":[0.000008750712,0.0002185579,0.0001410436,0.0004790481,0.000054565622,0.0006474492,0.000074742,0.00015154573,0.00005431413],"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":[0.000050085102,0.0005948372,0.00038983993,0.000037956735,0.00035330726,8.1201455e-7,0.00037904596,0.000015458822,0.003246224,0.00017020655,0.00062206475,0.99414015],"study_design_scores_gemma":[0.009509834,0.0014951897,0.032308284,0.0016067016,0.0046305354,0.000007846293,0.0048567895,0.6067781,0.039533865,0.15308234,0.14103039,0.00516016],"about_ca_topic_score_codex":0.0004873243,"about_ca_topic_score_gemma":0.003308335,"teacher_disagreement_score":0.98898,"about_ca_system_score_codex":0.0000359563,"about_ca_system_score_gemma":0.000016514807,"threshold_uncertainty_score":0.8912533},"labels":[],"label_agreement":null},{"id":"W4391026313","doi":"10.1145/3641108","title":"Interpreting Deep Forest through Feature Contribution and MDI Feature Importance","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Interpretability; Categorical variable; Feature (linguistics); Random forest; Computer science; Tree (set theory); Artificial intelligence; Variety (cybernetics); Feature model; Data mining; Layer (electronics); Machine learning; Pattern recognition (psychology); Mathematics; Software","score_opus":0.031627270126612386,"score_gpt":0.3094050055243785,"score_spread":0.2777777353977661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391026313","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":[0.008634987,0.008707508,0.97405374,0.004713938,0.0016654148,0.0003145796,0.001048774,0.00036383327,0.0004972343],"genre_scores_gemma":[0.9754582,0.0006251948,0.021891933,0.00029718515,0.00021115488,0.00004452325,0.00066199346,0.00003575359,0.00077406527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765986,0.00010144492,0.00028922342,0.0012687448,0.0002382861,0.00044242208],"domain_scores_gemma":[0.99628735,0.00075596455,0.00006697805,0.002690597,0.000094277006,0.000104830455],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003044838,0.00032256136,0.00027192238,0.000119979115,0.00038501056,0.0012920587,0.0024090626,0.00020658075,0.00002853731],"category_scores_gemma":[0.00021305529,0.00029159526,0.00009749954,0.00072911684,0.00013021634,0.006327083,0.00026306487,0.0006720266,0.00021043848],"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":[0.0004845089,0.0015906603,0.0048880517,0.000591853,0.0015030272,0.00080514204,0.023780737,0.0016781582,0.0097205825,0.17716019,0.07676279,0.7010343],"study_design_scores_gemma":[0.00066307076,0.00040895003,0.0024104156,0.0019115893,0.00034109762,0.0001394918,0.0018916603,0.5436649,0.033323985,0.13702376,0.2763359,0.0018852076],"about_ca_topic_score_codex":0.00014102078,"about_ca_topic_score_gemma":0.0028907503,"teacher_disagreement_score":0.9668232,"about_ca_system_score_codex":0.00014097517,"about_ca_system_score_gemma":0.00013354298,"threshold_uncertainty_score":0.9999536},"labels":[],"label_agreement":null},{"id":"W4399815117","doi":"10.1145/3673761","title":"Learning Individual Treatment Effects under Heterogeneous Interference in Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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 Waterloo","funders":"National Natural Science Foundation of China","keywords":"Weighting; Benchmark (surveying); Interference (communication); Computer science; Generalization; Regression; Spillover effect; Observational study; Range (aeronautics); Confounding; Sample (material); Process (computing); Machine learning; Artificial intelligence; Mathematics; Statistics; Medicine","score_opus":0.16936547919897604,"score_gpt":0.4090027000751428,"score_spread":0.23963722087616673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399815117","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":[0.06544109,0.0013175621,0.9307624,0.000080874794,0.0005373316,0.00042651495,0.00063453306,0.00058054907,0.00021915582],"genre_scores_gemma":[0.99103624,0.00055406225,0.006857961,0.00003149366,0.00009440262,0.00016134398,0.0006290935,0.000071109855,0.0005643214],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981499,0.00019800321,0.00036454253,0.00078798766,0.00014209226,0.00035752656],"domain_scores_gemma":[0.9952724,0.002961618,0.00004923349,0.0016225765,0.00001990836,0.000074242125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018764404,0.00036068115,0.00036565,0.0002312582,0.00010258633,0.00026487454,0.0009986944,0.00017267457,0.000114273724],"category_scores_gemma":[0.00012948146,0.00031188942,0.00009673797,0.00036047806,0.00008045635,0.0009977834,0.00011116696,0.0006170847,0.00008598671],"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":[0.00028281345,0.0031897947,0.0003974202,0.00038379623,0.0014776937,0.00037108737,0.0047205454,0.0153815495,0.0013056712,0.006385251,0.0012355152,0.96486884],"study_design_scores_gemma":[0.003558624,0.005103437,0.0009495682,0.007596092,0.002090263,0.00010604079,0.001710208,0.14749944,0.067888804,0.75274134,0.0070654084,0.0036907825],"about_ca_topic_score_codex":0.00012531327,"about_ca_topic_score_gemma":0.0016319739,"teacher_disagreement_score":0.96117806,"about_ca_system_score_codex":0.0003590089,"about_ca_system_score_gemma":0.000114815775,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4408221131","doi":"10.1145/3721983","title":"SED2AM: Solving Multi-Trip Time-Dependent Vehicle Routing Problem Using Deep Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Smart Parking Systems Research","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Vehicle routing problem; Computer science; Routing (electronic design automation); Artificial intelligence; Reinforcement; Mathematical optimization; Machine learning; Mathematics; Engineering; Computer network","score_opus":0.04577542143170239,"score_gpt":0.30683840944866225,"score_spread":0.2610629880169599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408221131","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":[0.036065437,0.00086155994,0.9587902,0.000033358712,0.00089352054,0.00064059487,0.00015436996,0.00056426594,0.001996735],"genre_scores_gemma":[0.9896431,0.00007387958,0.0054659103,0.000012981594,0.0001374647,0.00006211149,0.0003804405,0.00009589556,0.0041281977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740976,0.00018050084,0.0006323584,0.0007394305,0.00037852055,0.0006594099],"domain_scores_gemma":[0.99715817,0.00053158874,0.00006946154,0.0020445583,0.000085540734,0.0001106622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064861804,0.00037238968,0.00039567015,0.0003871805,0.00056286715,0.00041549766,0.0014956419,0.00017830622,0.0001625558],"category_scores_gemma":[0.00015326696,0.00040837153,0.00010998394,0.0006335167,0.000052783576,0.0012581142,0.0002086543,0.00084897224,0.0004159987],"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":[0.000047307527,0.00019105447,0.0011879402,0.00025343025,0.0005918757,0.000011680339,0.0009142538,0.931405,0.041567437,0.000012410074,0.00034539532,0.023472236],"study_design_scores_gemma":[0.0010098942,0.000027234439,0.00026053583,0.0007102435,0.00012067096,0.0000028394893,0.0004104542,0.9825137,0.012246282,0.000023717055,0.002275222,0.0003991825],"about_ca_topic_score_codex":0.0005649583,"about_ca_topic_score_gemma":0.0004061587,"teacher_disagreement_score":0.9535777,"about_ca_system_score_codex":0.0006060851,"about_ca_system_score_gemma":0.00016187898,"threshold_uncertainty_score":0.9998368},"labels":[],"label_agreement":null},{"id":"W4413592351","doi":"10.1145/3762667","title":"ORIC V2: Improved Feature Interaction Detection Model through Online Random Interaction Chains for Click-Through Rate Prediction","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Petro-Canada","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Random forest; Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining","score_opus":0.0650397683175733,"score_gpt":0.3459675967337768,"score_spread":0.2809278284162035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413592351","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":[0.0019395694,0.00025575777,0.98421377,0.0022500253,0.0061616455,0.0013369224,0.0027627947,0.0006733954,0.0004060902],"genre_scores_gemma":[0.9031737,0.0010306793,0.087473504,0.0005886611,0.0005298284,0.00073883776,0.0030629744,0.00006665194,0.003335166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713933,0.00023407192,0.0006900277,0.001376691,0.00017232775,0.00038754448],"domain_scores_gemma":[0.9956956,0.00066063524,0.00029558505,0.0030714842,0.00021570735,0.000061023045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040490806,0.00045234116,0.0004885676,0.00030165765,0.00055884966,0.00055546785,0.0018989177,0.00032639486,0.000006489574],"category_scores_gemma":[0.0001199553,0.00041996283,0.0002648173,0.0007598414,0.000043547177,0.008134626,0.00017414193,0.0006882851,0.000012298114],"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":[0.003829096,0.0053347754,0.00004721415,0.00059957325,0.001921533,0.000004515759,0.005332298,0.005942837,0.041172992,0.0044569876,0.048044987,0.8833132],"study_design_scores_gemma":[0.0029852302,0.0002953544,0.000105821746,0.00040449953,0.00022721876,0.000008492936,0.00038487118,0.8918769,0.037678733,0.010804727,0.054772656,0.0004554891],"about_ca_topic_score_codex":0.00063896395,"about_ca_topic_score_gemma":0.0022626421,"teacher_disagreement_score":0.90123415,"about_ca_system_score_codex":0.00041465924,"about_ca_system_score_gemma":0.00018200256,"threshold_uncertainty_score":0.99982524},"labels":[],"label_agreement":null}]}