{"meta":{"query_hash":"84a422687fe3","filters":{"venue":"ACM SIGKDD Explorations Newsletter"},"cohort_total":40,"direct_labels_cover":0,"predictions_cover":40,"exported":40,"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/84a422687fe3","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+SIGKDD+Explorations+Newsletter"},"results":[{"id":"W1965269329","doi":"10.1145/1147234.1147235","title":"Introduction to the special issue on successful real-world data mining applications","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","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 Alberta","funders":"","keywords":"Computer science; Data science; Field (mathematics); Database transaction; Transaction data; Knowledge extraction; Data discovery; Data stream mining; Data mining; World Wide Web; Database; Metadata","score_opus":0.03975452893360564,"score_gpt":0.2972189779695197,"score_spread":0.25746444903591403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965269329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093167846,0.0000065948752,0.51617223,0.4758727,0.0006168491,0.00069631374,0.0001309938,0.0002681296,0.0053045233],"genre_scores_gemma":[0.0112359375,0.00003559257,0.7524106,0.022443635,0.19326705,0.0032426391,0.0038736486,0.00009291311,0.013398022],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978976,0.000073646224,0.00039806427,0.0009443877,0.00035877878,0.00032749926],"domain_scores_gemma":[0.99390376,0.00024532623,0.00014318635,0.005519689,0.0001066958,0.00008136641],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035467194,0.00020247974,0.00015686931,0.00024662868,0.00074485247,0.0006953455,0.003949926,0.00003456088,0.00010867927],"category_scores_gemma":[0.00008774236,0.00016626329,0.00003728142,0.0018792045,0.00007766521,0.0012483933,0.0010439291,0.00019077367,0.0028253032],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018728387,0.000071820934,0.00008404116,0.0000012647122,0.0000067974447,8.364476e-7,0.00018133916,0.00043664454,0.00010748858,0.015517133,0.8766944,0.106896356],"study_design_scores_gemma":[0.00009453623,0.000028861296,0.0012457431,0.000005073036,0.000013324541,0.0000028435984,0.000088601344,0.004151499,0.0004977924,0.0009199587,0.9927419,0.00020989944],"about_ca_topic_score_codex":0.00037897253,"about_ca_topic_score_gemma":0.0019327798,"teacher_disagreement_score":0.45342907,"about_ca_system_score_codex":0.00006296162,"about_ca_system_score_gemma":0.000049663435,"threshold_uncertainty_score":0.9979511},"labels":[],"label_agreement":null},{"id":"W1967519701","doi":"10.1145/772862.772885","title":"KDD-2002 workshop report fractals and self-similarity in data mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Carnegie Mellon University; University of Southern California; National Science Foundation","keywords":"Computer science; Similarity (geometry); Data mining; Conjunction (astronomy); Fractal; Data science; Self-similarity; Information retrieval; Artificial intelligence; Mathematics","score_opus":0.11892294112044009,"score_gpt":0.29976370573021005,"score_spread":0.18084076460976994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967519701","genre_codex":"commentary","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":[0.1849016,0.0010724589,0.3305137,0.4766368,0.0006803012,0.0012614882,0.000029745013,0.0009804813,0.003923443],"genre_scores_gemma":[0.6947733,0.00038063078,0.28732526,0.01496035,0.00063579134,0.00025865433,0.00011054644,0.00003842528,0.0015170015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981542,0.00007134223,0.00044809424,0.00077297393,0.0002240074,0.0003293306],"domain_scores_gemma":[0.996377,0.00035925338,0.00013663292,0.0029735945,0.000045886976,0.00010764513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029077005,0.00018147929,0.0001905285,0.00012887991,0.00024274092,0.00036678443,0.0015440377,0.000093930124,0.000093420655],"category_scores_gemma":[0.00020114056,0.00017876843,0.000028667515,0.0007667208,0.000047484467,0.0021848173,0.0011733436,0.0002657523,0.00011323634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019218112,0.00047664216,0.006092973,0.000012191293,0.000035475958,0.00040945338,0.0028119795,0.000389156,0.00069294666,0.0021369995,0.95041966,0.03652057],"study_design_scores_gemma":[0.0007548552,0.000037750513,0.0069074696,0.00007140483,0.00003568544,0.0003375091,0.00019895802,0.41664234,0.00023286331,0.0033161917,0.5705238,0.00094118854],"about_ca_topic_score_codex":0.000013131405,"about_ca_topic_score_gemma":0.00013598059,"teacher_disagreement_score":0.5098717,"about_ca_system_score_codex":0.000023243258,"about_ca_system_score_gemma":0.000015838425,"threshold_uncertainty_score":0.7289965},"labels":[],"label_agreement":null},{"id":"W1968064480","doi":"10.1145/2031331.2031336","title":"Trajectory anonymity in publishing personal mobility data","year":2011,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":68,"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":"Computer science; Data publishing; Identifier; Anonymity; Global Positioning System; TRACE (psycholinguistics); Location-based service; Computer security; Object (grammar); World Wide Web; GSM; Mobile device; Location data; Personally identifiable information; k-anonymity; Internet privacy; Data science; Publishing; Computer network; Telecommunications","score_opus":0.2671506687550872,"score_gpt":0.34191459208467995,"score_spread":0.07476392332959275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968064480","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":[0.930638,0.0001181379,0.008889571,0.038799852,0.00038615445,0.0007443435,0.00010614918,0.00025752682,0.02006026],"genre_scores_gemma":[0.99458593,0.000015665659,0.0015626607,0.0027862047,0.00039281632,0.00008858523,0.00026185633,0.000011233851,0.00029503586],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99755937,0.0006625482,0.00038996091,0.0005807514,0.0004390621,0.00036832737],"domain_scores_gemma":[0.99779886,0.00041008694,0.000094461204,0.0014128736,0.00014754367,0.0001361956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024784585,0.00013694644,0.00018755623,0.00022310052,0.00062562193,0.00033796346,0.0014772965,0.00015090592,0.0033750718],"category_scores_gemma":[0.0029350074,0.00014522999,0.00007853329,0.0008327702,0.00038252014,0.004363537,0.0002149604,0.00036988175,0.00018163765],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097178636,0.0025287934,0.3501081,0.000058123784,0.00016525856,0.000043521202,0.44839814,0.00011848397,0.0006883172,0.006954949,0.14865501,0.042184137],"study_design_scores_gemma":[0.0027921584,0.00016926623,0.48527214,0.00013406994,0.0003572935,0.0000023327846,0.18308857,0.009371085,0.00067805883,0.040191233,0.2752893,0.0026544812],"about_ca_topic_score_codex":0.028433854,"about_ca_topic_score_gemma":0.17767525,"teacher_disagreement_score":0.26530957,"about_ca_system_score_codex":0.00018207719,"about_ca_system_score_gemma":0.00040008937,"threshold_uncertainty_score":0.997536},"labels":[],"label_agreement":null},{"id":"W1972132022","doi":"10.1145/1046456.1046468","title":"Subspace clustering for high dimensional categorical data","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Categorical variable; Correlation clustering; CURE data clustering algorithm; Data mining; Subspace topology; Canopy clustering algorithm; Data stream clustering; Focus (optics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","score_opus":0.11230554248111278,"score_gpt":0.34489126193553477,"score_spread":0.23258571945442197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972132022","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027341736,0.000037744605,0.92149484,0.07449408,0.0005146203,0.00042097952,0.000024876723,0.0002542343,0.000024437457],"genre_scores_gemma":[0.20555148,0.000007963334,0.79005224,0.0030100294,0.0005358455,0.00025416387,0.00023651395,0.000041219362,0.0003105326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766606,0.000050961775,0.0003247646,0.00088154984,0.00049714406,0.00057949696],"domain_scores_gemma":[0.99597746,0.0003470546,0.00007833023,0.003250398,0.00017988641,0.00016689605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028889067,0.00022371842,0.00020806375,0.0001738008,0.00041065164,0.0003026644,0.003262907,0.00008812359,0.0000130062435],"category_scores_gemma":[0.0004711494,0.00021567714,0.000050599414,0.0005390499,0.0000772248,0.0024638136,0.003044442,0.00025831372,0.00023062172],"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":[0.00019316973,0.0011348899,0.00012823619,0.00018608617,0.00033566562,0.00049634743,0.0048464206,0.5114476,0.06080486,0.14269635,0.15488613,0.12284425],"study_design_scores_gemma":[0.006744563,0.00066955073,0.0006657018,0.0000906792,0.000049621234,0.00026373108,0.00016407653,0.72116345,0.019552743,0.1915259,0.057022095,0.002087855],"about_ca_topic_score_codex":0.00008112521,"about_ca_topic_score_gemma":0.00007934668,"teacher_disagreement_score":0.20971589,"about_ca_system_score_codex":0.00017663324,"about_ca_system_score_gemma":0.00016029322,"threshold_uncertainty_score":0.8795058},"labels":[],"label_agreement":null},{"id":"W1977843657","doi":"10.1145/1540276.1540279","title":"A brief survey on anonymization techniques for privacy preserving publishing of social network data","year":2008,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":419,"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":"Data publishing; Computer science; Publishing; Social network (sociolinguistics); Information privacy; Data science; k-anonymity; Data anonymization; Graph; Cluster analysis; Internet privacy; Privacy protection; World Wide Web; Data mining; Social media; Artificial intelligence; Theoretical computer science","score_opus":0.1723603973409118,"score_gpt":0.3270708739991915,"score_spread":0.1547104766582797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977843657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039122715,0.000031279273,0.88103753,0.11254203,0.00026445443,0.0007330213,0.00028849242,0.00093861314,0.00025231324],"genre_scores_gemma":[0.16286333,0.00004144316,0.8304577,0.0032249847,0.0005591472,0.00022914157,0.0025238977,0.000048172675,0.000052171923],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723315,0.0002720589,0.00061401963,0.0008864873,0.00050061743,0.00049366005],"domain_scores_gemma":[0.9828647,0.0013147604,0.00040823923,0.0150492005,0.0003119466,0.00005119694],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0012529141,0.00024434904,0.0003201296,0.0002659801,0.0006265719,0.0005322439,0.04230956,0.00024173023,0.000011296019],"category_scores_gemma":[0.06553122,0.00025310845,0.00006436601,0.0013479566,0.0001505883,0.00844533,0.068166636,0.0003458058,0.0000068978206],"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":[0.00001747726,0.000074643416,0.0021915496,0.000015306385,0.000028698827,0.0000027974734,0.00027671247,0.000055112036,0.00062823255,0.0022151684,0.99009156,0.004402713],"study_design_scores_gemma":[0.0028051543,0.0007730193,0.06549464,0.00037246099,0.00008122946,0.00003425672,0.00009752735,0.301464,0.04426176,0.33207327,0.24988015,0.0026625644],"about_ca_topic_score_codex":0.00015940545,"about_ca_topic_score_gemma":0.00008246764,"teacher_disagreement_score":0.7402114,"about_ca_system_score_codex":0.000055916324,"about_ca_system_score_gemma":0.0001503939,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W1978091735","doi":"10.1145/1809400.1809419","title":"Summary of the first ACM SIGKDD workshop on knowledge discovery from uncertain data (U'09)","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Data science; Knowledge extraction; Information retrieval; Data mining","score_opus":0.07323755533522192,"score_gpt":0.30366766048651916,"score_spread":0.23043010515129725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978091735","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":[0.12091319,0.00032164328,0.43391764,0.43040198,0.0056367763,0.0017298263,0.002945855,0.0005901469,0.0035429387],"genre_scores_gemma":[0.5047298,0.00016446388,0.4583522,0.022302486,0.004049383,0.00092365895,0.0038993831,0.00016778738,0.005410825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792427,0.0000793913,0.00045420724,0.00086325174,0.00035307553,0.00032581552],"domain_scores_gemma":[0.986958,0.0013564479,0.00021081638,0.011288213,0.00009734762,0.000089132736],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002917747,0.00026419453,0.0002366237,0.00010961533,0.0004920158,0.00048117427,0.01011466,0.00013456639,0.000043319415],"category_scores_gemma":[0.00083119917,0.00019641028,0.00009644545,0.00088808127,0.00020492269,0.0024098763,0.004830461,0.00057095545,0.0003129413],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009514864,0.0005399824,0.0011907947,0.000012223302,0.00007791811,0.0000046287314,0.0022456194,0.00016089441,0.00787264,0.013875176,0.9097424,0.06426821],"study_design_scores_gemma":[0.00081846456,0.0000607579,0.008407855,0.00024194736,0.00008254375,0.0000054640977,0.00033356543,0.035154402,0.0066960673,0.016204964,0.9311208,0.0008731411],"about_ca_topic_score_codex":0.00018409996,"about_ca_topic_score_gemma":0.0011217617,"teacher_disagreement_score":0.4080995,"about_ca_system_score_codex":0.000029239165,"about_ca_system_score_gemma":0.00015679283,"threshold_uncertainty_score":0.9952411},"labels":[],"label_agreement":null},{"id":"W1983506100","doi":"10.1145/568574.568581","title":"Exploiting succinct constraints using FP-trees","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":76,"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":"Computer science; Pruning; Focus (optics); Succinctness; Set (abstract data type); Constraint (computer-aided design); Tree (set theory); Data mining; Search tree; Theoretical computer science; Algorithm; Search algorithm; Programming language; Mathematics","score_opus":0.10287589201954778,"score_gpt":0.27695920445099,"score_spread":0.1740833124314422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983506100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032464813,0.00007545909,0.94446635,0.02026837,0.000286302,0.00024320022,0.000027106664,0.00043135017,0.0017370374],"genre_scores_gemma":[0.47567862,0.000020799524,0.5189343,0.0044301767,0.00043572093,0.00012621003,0.000038229908,0.000029416013,0.0003064811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983338,0.000062146806,0.00038206048,0.00054486265,0.00027300345,0.0004041172],"domain_scores_gemma":[0.9978729,0.0002036635,0.00013112676,0.0015674612,0.000097581426,0.00012728029],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016220106,0.00021074887,0.00017931394,0.00017212314,0.0005220603,0.0005072649,0.0013643987,0.00006757799,0.0003183651],"category_scores_gemma":[0.00016796232,0.00021191195,0.000077567835,0.000653903,0.00012544073,0.0020287656,0.000453727,0.00019116815,0.0008853036],"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":[0.0000025480388,0.00065495685,0.002313134,0.00002598022,0.00015553385,0.00013478879,0.010429923,0.0015137445,0.053110488,0.060536098,0.28411305,0.5870098],"study_design_scores_gemma":[0.0013024649,0.0001173687,0.0010748705,0.0001351538,0.000067685614,0.0002432443,0.001198638,0.8644307,0.010126384,0.00726872,0.112382844,0.0016519199],"about_ca_topic_score_codex":0.000030293228,"about_ca_topic_score_gemma":0.000011648975,"teacher_disagreement_score":0.86291695,"about_ca_system_score_codex":0.000049215683,"about_ca_system_score_gemma":0.000026511487,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W1984606279","doi":"10.1145/380995.381002","title":"Mining frequent patterns by pattern-growth","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":275,"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":"Citation; Computer science; Data science; Library science","score_opus":0.021176622480086907,"score_gpt":0.24134360734380278,"score_spread":0.2201669848637159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984606279","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":[0.07965271,0.000057087047,0.8564917,0.0613567,0.00020689047,0.0002710413,0.00013475947,0.00044927804,0.001379858],"genre_scores_gemma":[0.6903612,0.00020210861,0.25105074,0.05034975,0.00091768993,0.0011929864,0.001130294,0.00010067247,0.0046945564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981863,0.00006391955,0.00038111059,0.0006405247,0.00031312005,0.0004150621],"domain_scores_gemma":[0.99788076,0.00012932769,0.000081510945,0.0016896973,0.00006922123,0.0001495148],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001337912,0.00023529098,0.00017480752,0.00009736033,0.0003345378,0.00050161773,0.0018365806,0.00007490819,0.00068797823],"category_scores_gemma":[0.000036892397,0.00023057776,0.00007552326,0.00043170984,0.000043155662,0.0014982685,0.0002511895,0.00017510788,0.0014284027],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010984022,0.00016537678,0.0019095851,0.0000072635676,0.00003179656,0.000015313452,0.0016985992,0.000026242511,0.0019000482,0.00096226955,0.6575571,0.33572534],"study_design_scores_gemma":[0.0017247061,0.0002854518,0.005215254,0.00013986761,0.000067323555,0.000082399645,0.00044498744,0.044501483,0.019164953,0.0046053715,0.9215177,0.0022504856],"about_ca_topic_score_codex":0.00016371098,"about_ca_topic_score_gemma":0.00002027323,"teacher_disagreement_score":0.6107085,"about_ca_system_score_codex":0.000043036194,"about_ca_system_score_gemma":0.000031815052,"threshold_uncertainty_score":0.9993491},"labels":[],"label_agreement":null},{"id":"W1993415883","doi":"10.1145/1809400.1809407","title":"FpVAT","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":68,"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 Manitoba","funders":"","keywords":"Computer science; Process (computing); Knowledge extraction; Representation (politics); Data mining; Simple (philosophy); Visualization; Information retrieval; Visual analytics; Machine learning; Artificial intelligence","score_opus":0.03376557419937707,"score_gpt":0.29607554267871694,"score_spread":0.26230996847933985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993415883","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":[0.008213704,0.0000055622604,0.9294605,0.05797812,0.00094441744,0.00010735584,0.0000064849028,0.00035528466,0.002928566],"genre_scores_gemma":[0.6315231,0.000018471595,0.29538885,0.06708454,0.0010891693,0.000083034385,0.00020870671,0.000041503707,0.004562652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907887,0.000028891493,0.0002042153,0.00028304494,0.00020833782,0.00019665879],"domain_scores_gemma":[0.9981973,0.00007614224,0.00005660593,0.0014821598,0.00009410874,0.00009364242],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001290463,0.000111255235,0.00009055741,0.00013118396,0.00017611316,0.0003949959,0.0013309806,0.000058214973,0.00024972894],"category_scores_gemma":[0.0002528138,0.000102577695,0.000046877707,0.00049793895,0.000044576467,0.0014936585,0.0003539959,0.00019263705,0.0016913218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.040673e-7,0.000099740704,0.0008720043,0.0000040826303,0.000015835742,0.000012365439,0.00078847393,0.00003808741,0.037052758,0.39884892,0.55303115,0.009235666],"study_design_scores_gemma":[0.00030626735,0.00002716609,0.0005831405,0.0000049214127,0.000008884928,0.0000135041255,0.000041686842,0.019721733,0.010445629,0.014199102,0.95430523,0.0003427349],"about_ca_topic_score_codex":0.000005639026,"about_ca_topic_score_gemma":0.0000359033,"teacher_disagreement_score":0.63407165,"about_ca_system_score_codex":0.0000075956596,"about_ca_system_score_gemma":0.000041118034,"threshold_uncertainty_score":0.99908596},"labels":[],"label_agreement":null},{"id":"W1997102766","doi":"10.1145/1882471.1882478","title":"A brief survey on sequence classification","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":552,"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; Sequence (biology); Feature selection; Artificial intelligence; Feature vector; Task (project management); Feature (linguistics); Machine learning; Pattern recognition (psychology); One-class classification; Support vector machine; Data mining","score_opus":0.11534281954831148,"score_gpt":0.3164656778829131,"score_spread":0.20112285833460158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997102766","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":[0.09228618,0.000009077189,0.86820585,0.035357915,0.0017942815,0.00037158906,0.000073632145,0.0004644681,0.0014370043],"genre_scores_gemma":[0.89421445,0.000008327051,0.09627791,0.008443297,0.0003719966,0.000099804434,0.00033248923,0.00001980526,0.0002319422],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984847,0.00012749773,0.00026091756,0.00053945044,0.00033203777,0.0002554012],"domain_scores_gemma":[0.9969554,0.0003475122,0.0001081661,0.0023647044,0.00011342994,0.000110779125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030919202,0.00016700443,0.00012488144,0.00013110765,0.00030147232,0.00039059843,0.0016223188,0.00010184111,0.000057383582],"category_scores_gemma":[0.0004714458,0.00014592611,0.00004387678,0.00047825347,0.00006592059,0.0015791984,0.00035742283,0.00038643295,0.0006626029],"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":[0.000021661474,0.00034224798,0.004535983,0.000006223268,0.000022720196,0.000026290252,0.00095429557,0.000110008754,0.45190167,0.08969273,0.3611196,0.09126659],"study_design_scores_gemma":[0.0016388189,0.00041790953,0.42252123,0.00007307317,0.000019956839,0.00004848029,0.000059683123,0.15496136,0.052407287,0.020922303,0.34502938,0.0019005279],"about_ca_topic_score_codex":0.00015286567,"about_ca_topic_score_gemma":0.00014430235,"teacher_disagreement_score":0.8019282,"about_ca_system_score_codex":0.000017287273,"about_ca_system_score_gemma":0.000071117036,"threshold_uncertainty_score":0.85166407},"labels":[],"label_agreement":null},{"id":"W2011376672","doi":"10.1145/1007730.1007737","title":"Class imbalances versus small disjuncts","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":681,"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; Class (philosophy); Focus (optics); Classifier (UML); Artificial intelligence; Machine learning","score_opus":0.068174256664078,"score_gpt":0.27984716191671505,"score_spread":0.21167290525263704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011376672","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":[0.008144988,0.00005157474,0.90442705,0.08279607,0.000939207,0.00034627883,0.000014351824,0.001199726,0.0020807404],"genre_scores_gemma":[0.5063142,0.00007157026,0.4810038,0.011148973,0.00044987816,0.0004912788,0.00016999706,0.000039314473,0.0003109741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99811745,0.00006877974,0.0003845946,0.0006315607,0.00036870706,0.00042892195],"domain_scores_gemma":[0.9968916,0.0001860733,0.00015573841,0.002498135,0.00014358852,0.00012482172],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020526625,0.00024690153,0.00019711319,0.00020124507,0.00027290804,0.00044784517,0.0026103356,0.000115136405,0.000025576723],"category_scores_gemma":[0.0003292368,0.00023413372,0.00008341561,0.0007420649,0.00011352304,0.0020114526,0.0005548025,0.00024680153,0.0010543634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007889464,0.0005443797,0.00082105276,0.00003678228,0.00012090244,0.00008160621,0.003674977,0.00087153894,0.047750205,0.6932518,0.21748663,0.03528124],"study_design_scores_gemma":[0.0061004064,0.0007120852,0.0054148105,0.00012843915,0.000060494243,0.000042071944,0.00048954674,0.0022682433,0.22972727,0.15012863,0.60260624,0.0023217543],"about_ca_topic_score_codex":0.00003110094,"about_ca_topic_score_gemma":0.00007739377,"teacher_disagreement_score":0.5431231,"about_ca_system_score_codex":0.00016506619,"about_ca_system_score_gemma":0.00013704643,"threshold_uncertainty_score":0.99972343},"labels":[],"label_agreement":null},{"id":"W2024539262","doi":"10.1145/1294301.1294307","title":"Novel approaches for small biomolecule classification and structural similarity search","year":2007,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Computational Drug Discovery Methods","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":"Simon Fraser University","funders":"","keywords":"Computer science; Nearest neighbor search; Classifier (UML); Minkowski distance; Pruning; Similarity (geometry); Artificial intelligence; Data mining; Pattern recognition (psychology); Binary classification; k-nearest neighbors algorithm; Machine learning; Euclidean distance; Support vector machine","score_opus":0.2537296575736704,"score_gpt":0.3552435413062274,"score_spread":0.10151388373255699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024539262","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12666184,0.000027224532,0.8549194,0.017563414,0.0001716863,0.0004284697,0.000013280119,0.00009278283,0.000121946934],"genre_scores_gemma":[0.4397019,0.0000010976055,0.55864644,0.0013486759,0.00014521957,0.0000538855,0.000057583286,0.000012428849,0.000032777727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998477,0.00008784428,0.000316855,0.0005402273,0.0002463705,0.0003317224],"domain_scores_gemma":[0.99798095,0.00095893047,0.0000810989,0.00071582035,0.00015560522,0.000107599386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008900145,0.00017117715,0.00014114904,0.0002180294,0.00030850765,0.00032149596,0.00071226,0.000083477236,0.0000031223797],"category_scores_gemma":[0.0003088171,0.0001678824,0.00006503037,0.00047022407,0.00009806947,0.0008881051,0.0003516371,0.00015105403,0.00000916197],"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":[0.000100065896,0.00030445404,0.0029219214,0.00011224588,0.00013588021,0.000008733562,0.007497697,0.018636929,0.15101075,0.58633745,0.0039935037,0.2289404],"study_design_scores_gemma":[0.00095664896,0.00010402822,0.058860607,0.000011537256,0.00002136612,0.000033029963,0.00034111566,0.8737705,0.018390955,0.04412705,0.002860351,0.0005228289],"about_ca_topic_score_codex":0.000017332197,"about_ca_topic_score_gemma":0.000040957435,"teacher_disagreement_score":0.85513353,"about_ca_system_score_codex":0.00006195376,"about_ca_system_score_gemma":0.000076968754,"threshold_uncertainty_score":0.6846046},"labels":[],"label_agreement":null},{"id":"W2028572284","doi":"10.1145/846183.846208","title":"Discovering geographic knowledge in data rich environments","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"City, University of London; University of Utah; University of Florida; Florida State University","keywords":"Data science; Identification (biology); Computer science; Geographic information system; Knowledge extraction; Data mining; Geography; Cartography","score_opus":0.05390222068445348,"score_gpt":0.2862366298714703,"score_spread":0.2323344091870168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028572284","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":[0.30840704,0.00046787437,0.64443237,0.04009342,0.0004003402,0.00078711077,0.00021991516,0.00037962606,0.004812312],"genre_scores_gemma":[0.61449873,0.0006758735,0.3705802,0.0055297855,0.0006758542,0.000808151,0.0018787313,0.00007802594,0.0052746567],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854195,0.000052622207,0.0002898689,0.0006521598,0.00016832085,0.00029508636],"domain_scores_gemma":[0.9964285,0.00009535511,0.000041767096,0.0033578712,0.0000071483814,0.00006935592],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019263933,0.00015295246,0.00012712459,0.00015942148,0.00018261689,0.00026332476,0.0029823573,0.000047588805,0.00013343223],"category_scores_gemma":[0.000025764775,0.00015264026,0.000025850131,0.0007174892,0.000052645682,0.002675874,0.0009630269,0.00016996326,0.0013707065],"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":[0.000007642443,0.0014942716,0.008502877,0.000019221909,0.00008321429,0.000049328642,0.0061788294,0.0018998762,0.003834649,0.0075111235,0.16755109,0.8028679],"study_design_scores_gemma":[0.0006696104,0.000033639488,0.017721988,0.000041710784,0.000016333892,0.000011483449,0.000115596435,0.08759618,0.00045596628,0.002310041,0.89041954,0.00060788775],"about_ca_topic_score_codex":0.00005165968,"about_ca_topic_score_gemma":0.000109700195,"teacher_disagreement_score":0.80226,"about_ca_system_score_codex":0.000027349814,"about_ca_system_score_gemma":0.000025701218,"threshold_uncertainty_score":0.9994068},"labels":[],"label_agreement":null},{"id":"W2034607275","doi":"10.1145/1046456.1046459","title":"Learning important models for web page blocks based on layout and content analysis","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"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; Web page; Block (permutation group theory); Information retrieval; Partition (number theory); Page view; Static web page; Data mining; World Wide Web; Web navigation","score_opus":0.07156513468895788,"score_gpt":0.263723749372729,"score_spread":0.19215861468377116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034607275","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":[0.12407268,0.00003243297,0.851975,0.023423804,0.000051976174,0.00017119401,0.000031464315,0.00015409998,0.00008732],"genre_scores_gemma":[0.9279734,0.000009580306,0.06680482,0.0046792557,0.00007397772,0.00012243113,0.00016404083,0.000013735461,0.00015879261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839514,0.00005916821,0.00039221413,0.0005910995,0.00026614906,0.00029623217],"domain_scores_gemma":[0.99832374,0.00023168015,0.00015601386,0.001065966,0.00010718658,0.00011544209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003536036,0.00020027747,0.0002997896,0.00048059446,0.0003528921,0.00035484426,0.0005988899,0.000066871115,0.000011932816],"category_scores_gemma":[0.00020695782,0.00017546378,0.00020843725,0.0008906577,0.000041388626,0.0007449358,0.00014841779,0.00016445428,0.000014904173],"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":[0.000032709988,0.00029202324,0.0066428636,0.000016915896,0.00083558547,0.000046079036,0.0030738362,0.95748925,0.0130038075,0.008258896,0.005671036,0.0046370216],"study_design_scores_gemma":[0.0008253599,0.00017120542,0.00017563504,0.000018529703,0.00031284976,0.000001281562,0.00023501064,0.9943652,0.0007692239,0.0016174383,0.0012288074,0.00027947206],"about_ca_topic_score_codex":0.00006150408,"about_ca_topic_score_gemma":0.0000766659,"teacher_disagreement_score":0.80390066,"about_ca_system_score_codex":0.000041783063,"about_ca_system_score_gemma":0.00007187721,"threshold_uncertainty_score":0.7155205},"labels":[],"label_agreement":null},{"id":"W2039552226","doi":"10.1145/2207243.2207248","title":"Mapping question items to skills with non-negative matrix factorization","year":2012,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Non-negative matrix factorization; Matrix decomposition; Task (project management); Variance (accounting); Machine learning; Process (computing); Matrix (chemical analysis); Artificial intelligence; Automation; Data science","score_opus":0.02240098912766123,"score_gpt":0.27459348238239056,"score_spread":0.2521924932547293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039552226","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":[0.040802293,0.000014295568,0.9532901,0.0038925079,0.0010112216,0.00042231815,0.000001766766,0.00020008568,0.00036540636],"genre_scores_gemma":[0.88647074,0.000002108466,0.107190676,0.0011950156,0.0012382523,0.00014898629,0.00001445886,0.000026287806,0.003713462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843574,0.00013044055,0.00030267326,0.00034977152,0.00034805038,0.0004333366],"domain_scores_gemma":[0.9986187,0.00018250562,0.00015049774,0.0006758757,0.00021410255,0.0001582837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032127346,0.00021459437,0.00017699049,0.0002825498,0.00030802604,0.00029826074,0.0005205843,0.00007046193,0.00001855726],"category_scores_gemma":[0.00021539384,0.00018154497,0.000045663473,0.00076473044,0.00001728649,0.0024629605,0.00017378782,0.00018709943,0.00085437775],"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":[0.00004640735,0.00083193684,0.1440743,0.00013918437,0.00036854245,0.000025967078,0.23706052,0.043865968,0.1791833,0.32356638,0.0520613,0.018776212],"study_design_scores_gemma":[0.0015052,0.000870163,0.08026609,0.0011829651,0.000052712632,0.00007895455,0.005121108,0.008711734,0.102313,0.0023400246,0.7943868,0.00317127],"about_ca_topic_score_codex":0.00007741132,"about_ca_topic_score_gemma":0.0000072826615,"teacher_disagreement_score":0.84609944,"about_ca_system_score_codex":0.00013226786,"about_ca_system_score_gemma":0.000034129782,"threshold_uncertainty_score":0.9999236},"labels":[],"label_agreement":null},{"id":"W2039760999","doi":"10.1145/380995.381054","title":"Report on MDM/KDD2000","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","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 Alberta","funders":"","keywords":"Citation; Library science; Computer science; World Wide Web","score_opus":0.03370207834165126,"score_gpt":0.2762263369441018,"score_spread":0.24252425860245055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039760999","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":[0.010688082,0.0000703258,0.7768957,0.16783373,0.0004015473,0.00056878885,0.000005901985,0.0019719873,0.041563943],"genre_scores_gemma":[0.672691,0.0002207806,0.18709627,0.07430854,0.0012707815,0.0007680494,0.00015595827,0.00009355212,0.063395076],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843925,0.0000707976,0.0003692929,0.00049941614,0.00035532392,0.00026590476],"domain_scores_gemma":[0.99758893,0.00009677128,0.00008567079,0.0020461634,0.00009390722,0.00008857747],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019970897,0.00017385095,0.0001415909,0.00013493006,0.00023532097,0.00026393932,0.0011128247,0.00008220874,0.00085055205],"category_scores_gemma":[0.00011283095,0.00015435384,0.00008924718,0.0005990344,0.00005717962,0.0010682807,0.00009190646,0.00018812256,0.0033821699],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025744439,0.0004158422,0.00036266274,0.0000094846255,0.000039846513,0.00040505067,0.0009378252,0.00007535395,0.007870147,0.037541106,0.5245359,0.42778108],"study_design_scores_gemma":[0.00026015934,0.0001451925,0.0013446946,0.000022582079,0.000009120191,0.00013309828,0.000014493018,0.0016346624,0.08777832,0.014317474,0.8938747,0.00046551146],"about_ca_topic_score_codex":0.0000103071825,"about_ca_topic_score_gemma":0.0000014564646,"teacher_disagreement_score":0.6620029,"about_ca_system_score_codex":0.000050163726,"about_ca_system_score_gemma":0.000054923352,"threshold_uncertainty_score":0.9973938},"labels":[],"label_agreement":null},{"id":"W2040010062","doi":"10.1145/1007730.1007736","title":"Learning from imbalanced data sets with boosting and data generation","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":606,"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":"Boosting (machine learning); Machine learning; Computer science; Artificial intelligence; Benchmarking; Classifier (UML); Training set; Gradient boosting; Ensemble learning; Data mining; Random forest","score_opus":0.14587677944015098,"score_gpt":0.31587666002732545,"score_spread":0.16999988058717447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040010062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022824487,0.00006450046,0.9509304,0.025077892,0.0000963905,0.0002634567,0.00012269046,0.00054543914,0.00007473868],"genre_scores_gemma":[0.37854064,0.0000515419,0.6110542,0.0026441817,0.00023267814,0.00004877903,0.0073798634,0.000022367261,0.000025803334],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789584,0.00009588418,0.00031387233,0.0011359652,0.00030559453,0.000252875],"domain_scores_gemma":[0.99358374,0.00014698908,0.00019090337,0.0059089293,0.000091913906,0.0000775059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032223857,0.00019806148,0.00016735587,0.000105695064,0.00038364236,0.0006368018,0.0034325176,0.000072862706,0.000008761832],"category_scores_gemma":[0.00049666595,0.00018070023,0.000008969001,0.00036909958,0.00007639533,0.006221595,0.002521853,0.00027318398,0.00006503921],"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":[0.000049953393,0.00041404448,0.013119821,0.000047403955,0.0002928872,0.00014221165,0.009118505,0.0060617793,0.5167028,0.019365951,0.2208476,0.21383706],"study_design_scores_gemma":[0.0046656895,0.0005391771,0.014499639,0.00033866105,0.00015847365,0.00013027729,0.00071808946,0.7545464,0.085383154,0.017434167,0.11876088,0.0028253945],"about_ca_topic_score_codex":0.00012762267,"about_ca_topic_score_gemma":0.00014094487,"teacher_disagreement_score":0.7484846,"about_ca_system_score_codex":0.0000469216,"about_ca_system_score_gemma":0.00010443835,"threshold_uncertainty_score":0.7368741},"labels":[],"label_agreement":null},{"id":"W2044306058","doi":"10.1145/568574.568580","title":"Constrained frequent pattern mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":133,"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; Data mining; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Context (archaeology); Process (computing); Association rule learning; Mathematics","score_opus":0.06108663403363127,"score_gpt":0.2512890157389533,"score_spread":0.19020238170532203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044306058","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":[0.007530511,0.00006043923,0.91633564,0.07278986,0.00027719786,0.0002006276,0.000028852888,0.00037741315,0.0023994565],"genre_scores_gemma":[0.48987183,0.000033390956,0.48828405,0.019532802,0.0005169626,0.0004371201,0.00010270821,0.00003444347,0.0011867016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986045,0.000045084496,0.00031846244,0.00047319027,0.00023603028,0.00032272883],"domain_scores_gemma":[0.9979687,0.00016106541,0.00009386214,0.0015890902,0.0000705095,0.000116796524],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011383035,0.00017483343,0.00014347618,0.00012620982,0.00029436365,0.00036685335,0.0013601776,0.00005798034,0.00034322654],"category_scores_gemma":[0.00009434052,0.00017088666,0.000063848245,0.00045524817,0.00007311427,0.0011320596,0.0003261844,0.00013910796,0.0014439062],"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":[3.931375e-7,0.00019547078,0.0006060497,0.0000067020296,0.00004190476,0.000038198337,0.0042448714,0.000065533095,0.0032116794,0.00869386,0.45526764,0.5276277],"study_design_scores_gemma":[0.0016957351,0.0002245147,0.0015346489,0.000092382164,0.000053951175,0.00015114977,0.000771306,0.46535555,0.0048505124,0.0053600604,0.5182254,0.0016848466],"about_ca_topic_score_codex":0.00002311195,"about_ca_topic_score_gemma":0.000010825362,"teacher_disagreement_score":0.52594286,"about_ca_system_score_codex":0.000030892646,"about_ca_system_score_gemma":0.000016646887,"threshold_uncertainty_score":0.99933356},"labels":[],"label_agreement":null},{"id":"W2048976003","doi":"10.1145/1540276.1540299","title":"WebKDD 2008","year":2008,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"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; Knowledge extraction; Las vegas; Conjunction (astronomy); Data science; Library science; World Wide Web; Data mining; History; Archaeology; Tourism","score_opus":0.05751956576975635,"score_gpt":0.2554444167508769,"score_spread":0.19792485098112056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048976003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010265849,0.00007493906,0.9276432,0.058523163,0.00031856485,0.00020386372,0.000018103054,0.00048391815,0.0024684002],"genre_scores_gemma":[0.11913334,0.00011936485,0.85886055,0.016744027,0.0007241712,0.00047996832,0.00014745911,0.000036455596,0.0037546493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987483,0.000035368914,0.00025538987,0.00043096757,0.0002444575,0.00028550188],"domain_scores_gemma":[0.99775344,0.00010791281,0.00006823026,0.0018747628,0.0000861102,0.0001095665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009131375,0.00015016586,0.00012863765,0.00012416071,0.0005236179,0.00014225353,0.001569447,0.000053848824,0.000079138255],"category_scores_gemma":[0.00009057507,0.00014374351,0.00006161067,0.0006272701,0.0000870205,0.0014797566,0.00041526818,0.0001525293,0.0024770172],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.723085e-7,0.00010844616,0.0003528106,0.0000020265318,0.000016224145,0.000034496046,0.0013722066,0.000054755616,0.0019942163,0.015017623,0.96312726,0.017919093],"study_design_scores_gemma":[0.00048543853,0.000068043075,0.0032650428,0.000011870335,0.000010530563,0.00017840437,0.00006679335,0.015713891,0.004100855,0.005662871,0.969869,0.0005672364],"about_ca_topic_score_codex":0.000026595475,"about_ca_topic_score_gemma":0.0000070395395,"teacher_disagreement_score":0.108867496,"about_ca_system_score_codex":0.000025480893,"about_ca_system_score_gemma":0.00007354696,"threshold_uncertainty_score":0.99829966},"labels":[],"label_agreement":null},{"id":"W2067575620","doi":"10.1145/772862.772886","title":"MDM/KDD2002","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Conjunction (astronomy); Knowledge extraction; Data science; Series (stratigraphy); Information retrieval; Data mining; Geology","score_opus":0.07236190396419816,"score_gpt":0.24746513484452987,"score_spread":0.1751032308803317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067575620","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":[0.0005972741,0.00015074605,0.89776886,0.0923724,0.00023066826,0.00019987772,0.0000022286629,0.0008684323,0.0078095295],"genre_scores_gemma":[0.68298995,0.00027486563,0.26536956,0.03554424,0.00070134114,0.00042460574,0.000023606024,0.000052875756,0.014618984],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872065,0.0000660103,0.00027921173,0.00037799386,0.000282468,0.00027368506],"domain_scores_gemma":[0.9981063,0.00009717185,0.00008348512,0.0015066225,0.00011861362,0.00008779445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011422338,0.00015576693,0.00012686994,0.0001568725,0.000228612,0.00029854418,0.0013450625,0.00007549529,0.00056568923],"category_scores_gemma":[0.00015093583,0.00014235137,0.00008067198,0.00068940746,0.000060565282,0.0015452122,0.00024818853,0.00016396676,0.003491788],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001764165,0.00023486742,0.00019950572,0.000009302689,0.00002405492,0.00002532238,0.0016450821,0.0000074521727,0.023352155,0.05892117,0.8011663,0.114413016],"study_design_scores_gemma":[0.00041695056,0.00011637282,0.00045241075,0.000019086177,0.000013879864,0.000035175326,0.00005936665,0.027265131,0.108286485,0.01763752,0.84502983,0.0006677849],"about_ca_topic_score_codex":0.0000043582654,"about_ca_topic_score_gemma":0.0000013258642,"teacher_disagreement_score":0.68239266,"about_ca_system_score_codex":0.000039573915,"about_ca_system_score_gemma":0.000011746517,"threshold_uncertainty_score":0.9972841},"labels":[],"label_agreement":null},{"id":"W2069116068","doi":"10.1145/507515.507523","title":"KDD Cup 2001 report","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Imperial Bank of Commerce (Canada)","funders":"National Science Foundation","keywords":"Computer science; Artificial intelligence","score_opus":0.036488664020318924,"score_gpt":0.2723488489952492,"score_spread":0.23586018497493028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069116068","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":[0.7355424,0.0005940037,0.07506728,0.08697352,0.0016001891,0.0010883351,0.000041328065,0.0003766677,0.09871628],"genre_scores_gemma":[0.8407871,0.00028310943,0.07345465,0.030205922,0.0025736927,0.00024618025,0.0014647548,0.00013035248,0.050854214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880004,0.000052260035,0.0003749913,0.00028072676,0.00018537603,0.0003065941],"domain_scores_gemma":[0.99839246,0.00002402311,0.00014123751,0.001262724,0.00008701246,0.00009253453],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016167008,0.00018139447,0.00012631327,0.00006850316,0.00016187633,0.00006956306,0.00037789042,0.00014248744,0.00084254483],"category_scores_gemma":[0.00073968334,0.00017424223,0.000090639194,0.00014947445,0.000066991735,0.000023387242,0.00020325785,0.00017802163,0.0009980784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005581297,0.00005974116,0.0043858495,0.00000917409,0.00003892383,0.0000332745,0.00023332766,0.0003191782,0.035700895,0.000060126982,0.95732206,0.0018318591],"study_design_scores_gemma":[0.00034279499,0.000097095464,0.0007456791,0.000007566597,0.000020352216,0.00022152599,0.00006188864,0.0016102843,0.011487916,0.000107467116,0.98497504,0.00032240042],"about_ca_topic_score_codex":0.000009239325,"about_ca_topic_score_gemma":0.000013544336,"teacher_disagreement_score":0.10524473,"about_ca_system_score_codex":0.000014520348,"about_ca_system_score_gemma":0.000017796963,"threshold_uncertainty_score":0.99977976},"labels":[],"label_agreement":null},{"id":"W2082225138","doi":"10.1145/1046456.1046458","title":"Extracting relational data from HTML repositories","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"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":"Computer science; Set (abstract data type); Information retrieval; Data mining; Information extraction; Quality (philosophy)","score_opus":0.12972045116927916,"score_gpt":0.3005306323875561,"score_spread":0.17081018121827696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082225138","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023914978,0.000081565435,0.92408866,0.050488442,0.00055285136,0.0000621739,0.00007072955,0.00025231644,0.00048829446],"genre_scores_gemma":[0.4474546,0.000009312016,0.5466772,0.0027412234,0.0011698534,0.000023154196,0.0016253695,0.000016709066,0.0002826246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832976,0.00006130678,0.0003608278,0.0006717383,0.00036094864,0.00021541632],"domain_scores_gemma":[0.9957921,0.00035003762,0.00015216597,0.0035495223,0.00008079632,0.00007536652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022295651,0.0001487216,0.00014647066,0.000115563445,0.0004240787,0.0005240083,0.002295598,0.00006853427,0.000047771384],"category_scores_gemma":[0.00068610505,0.00014417866,0.000049647897,0.00051007466,0.000055313754,0.004812952,0.0010880234,0.00021475188,0.0006338899],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030492474,0.00085153966,0.02478451,0.00001994753,0.0009527984,0.0005288162,0.018149234,0.018373528,0.08105386,0.14750381,0.6748206,0.032930877],"study_design_scores_gemma":[0.0042622453,0.00022094512,0.025296278,0.0004093976,0.000585851,0.00016620298,0.0024518427,0.085471645,0.035181563,0.17577058,0.6662915,0.0038919558],"about_ca_topic_score_codex":0.00024604888,"about_ca_topic_score_gemma":0.00006659404,"teacher_disagreement_score":0.42353964,"about_ca_system_score_codex":0.000046350076,"about_ca_system_score_gemma":0.000111466994,"threshold_uncertainty_score":0.8147584},"labels":[],"label_agreement":null},{"id":"W2085995514","doi":"10.1145/772862.772888","title":"WEBKDD 2002","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"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; Conjunction (astronomy); Theme (computing); Knowledge extraction; Data science; Web mining; Data mining; Information retrieval; World Wide Web; Web service","score_opus":0.061081370656482024,"score_gpt":0.2461904553370433,"score_spread":0.18510908468056128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085995514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012913476,0.00016329005,0.8694026,0.11766384,0.00036270526,0.00022791745,0.000020493691,0.00054330647,0.010324523],"genre_scores_gemma":[0.064365305,0.00012769687,0.8908682,0.026654605,0.0009823841,0.0006612905,0.00006880781,0.000050193023,0.016221538],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875677,0.00003602663,0.0002511246,0.00043478142,0.00022605983,0.00029526243],"domain_scores_gemma":[0.9977036,0.00010940734,0.00006701175,0.0019462118,0.0000668754,0.00010688079],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009465607,0.0001505933,0.00011891373,0.00012154481,0.00030574732,0.00036582188,0.0016171412,0.00005447474,0.0007991404],"category_scores_gemma":[0.00009062627,0.00014464713,0.000058441237,0.00063059514,0.00004911833,0.0015122447,0.000381909,0.00015278596,0.009211446],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.868557e-7,0.00008768721,0.000036956044,0.0000016903076,0.000010327788,0.0000067009773,0.00067036296,0.000027961789,0.0008553639,0.015129661,0.92101,0.062163077],"study_design_scores_gemma":[0.00026876127,0.000039552095,0.0002452775,0.00000933591,0.000009227774,0.000020299361,0.000044274737,0.074081324,0.0011077833,0.0029977679,0.9208354,0.0003410088],"about_ca_topic_score_codex":0.000010831199,"about_ca_topic_score_gemma":0.0000060447555,"teacher_disagreement_score":0.09100924,"about_ca_system_score_codex":0.000024493414,"about_ca_system_score_gemma":0.000011389334,"threshold_uncertainty_score":0.99156},"labels":[],"label_agreement":null},{"id":"W2101549186","doi":"10.1145/2594473.2594476","title":"Ensembles for unsupervised outlier detection","year":2014,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":273,"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; Anomaly detection; Outlier; Cluster analysis; Artificial intelligence; Focus (optics); Machine learning; Unsupervised learning; Core (optical fiber); Ensemble learning; Data mining; Pattern recognition (psychology); Data science","score_opus":0.025405331016139964,"score_gpt":0.2520752218889637,"score_spread":0.22666989087282374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101549186","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":[0.006314207,0.000008645937,0.9750851,0.01672688,0.00018764546,0.00047386627,0.0000032357966,0.0006554846,0.0005449311],"genre_scores_gemma":[0.78647304,0.000006516992,0.20564054,0.005538486,0.00036253495,0.001402254,0.000015369984,0.000023616381,0.00053763774],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988793,0.000053573083,0.0002717203,0.0004144664,0.00014091174,0.000240003],"domain_scores_gemma":[0.99829346,0.00020546914,0.000085926426,0.001194462,0.00014646834,0.00007421961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002037994,0.00015210595,0.0001334638,0.00015597243,0.00044387637,0.00021285337,0.00075663114,0.000091194175,0.000018243856],"category_scores_gemma":[0.00014098475,0.00014779455,0.00011172874,0.00039116104,0.00003353989,0.0007242203,0.00014096628,0.0001021698,0.00018755521],"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":[0.000019915286,0.00021629503,0.00018051539,0.00003215574,0.000053039705,8.2876215e-7,0.0012777802,0.0003665082,0.2771104,0.1591019,0.07778127,0.4838594],"study_design_scores_gemma":[0.0005373735,0.00023295722,0.00037718457,0.000009045884,0.000020840213,0.000008951378,0.000052979398,0.0540096,0.23203392,0.060020402,0.65224487,0.00045188473],"about_ca_topic_score_codex":0.00001195514,"about_ca_topic_score_gemma":0.000023765197,"teacher_disagreement_score":0.7801588,"about_ca_system_score_codex":0.000034742287,"about_ca_system_score_gemma":0.000018073599,"threshold_uncertainty_score":0.60268867},"labels":[],"label_agreement":null},{"id":"W2110788923","doi":"10.1145/1117454.1117475","title":"WebKDD 2005","year":2005,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Recommender Systems and Techniques","field":"Computer Science","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 Alberta","funders":"","keywords":"Computer science; Theme (computing); Conjunction (astronomy); Web mining; World Wide Web; Data science; Knowledge extraction; Data mining; Web service","score_opus":0.036298116636475024,"score_gpt":0.2671368829012802,"score_spread":0.23083876626480515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110788923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001420844,0.000121394914,0.79111457,0.1986726,0.00036346298,0.0002431326,0.0000019321922,0.0007552133,0.0073068663],"genre_scores_gemma":[0.45893058,0.00005260508,0.5038363,0.031297695,0.0014857394,0.00036159775,0.00001624361,0.000035224242,0.0039840667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986441,0.00007471738,0.00033366034,0.0003757262,0.00022565546,0.00034610016],"domain_scores_gemma":[0.9981062,0.000082075516,0.00008646292,0.0015632748,0.000059272643,0.00010274919],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002289697,0.00016899867,0.0001573733,0.00016612351,0.00019181387,0.00032332595,0.0013547991,0.000077933495,0.00014181319],"category_scores_gemma":[0.000040214123,0.0001522928,0.000083678446,0.0002730613,0.000025319889,0.0020086116,0.00035406346,0.000158722,0.0014211952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.911828e-7,0.00005921818,0.0001698563,0.0000031517359,0.000015215121,0.0000055106552,0.00066355674,0.00003309548,0.001970605,0.028061641,0.9299879,0.039029434],"study_design_scores_gemma":[0.0001689266,0.000026708352,0.00014893233,0.000010849948,0.0000036141032,0.000018586978,0.00002160439,0.002277733,0.009263871,0.004240742,0.9835811,0.00023730993],"about_ca_topic_score_codex":0.000021521884,"about_ca_topic_score_gemma":0.00007364607,"teacher_disagreement_score":0.45750973,"about_ca_system_score_codex":0.000063646534,"about_ca_system_score_gemma":0.00003877861,"threshold_uncertainty_score":0.9993563},"labels":[],"label_agreement":null},{"id":"W2112993176","doi":"10.1145/1294301.1294305","title":"Introduction to the special issue on data mining for health informatics","year":2007,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"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; University of British Columbia","funders":"","keywords":"Personalized medicine; Computer science; Profiling (computer programming); Computational biology; Informatics; Metabolite profiling; Biomedicine; Data science; Oligonucleotide; Bioinformatics; Data mining; DNA; Biology; Metabolomics; Genetics","score_opus":0.05493152489629841,"score_gpt":0.3437162114384144,"score_spread":0.288784686542116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112993176","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023473537,0.000056693618,0.3767184,0.5946853,0.002612405,0.0012104372,0.000092688024,0.000034899214,0.0011156133],"genre_scores_gemma":[0.13402793,0.0002681687,0.16031021,0.34106758,0.33831927,0.0008189677,0.0124945985,0.00015469233,0.012538601],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990582,0.000030449151,0.00032634512,0.00024812223,0.00013504436,0.00020182738],"domain_scores_gemma":[0.9982943,0.000029095881,0.00011941084,0.0014177565,0.000070753216,0.00006871221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056040054,0.00010127572,0.00007592058,0.00007044816,0.00025008718,0.00005445051,0.0005033108,0.00005763962,0.000047410264],"category_scores_gemma":[0.00037955688,0.000078877034,0.000028451539,0.00016012105,0.000021130503,0.000019367344,0.00016139164,0.0000635561,0.00010900333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006640516,0.000020039228,0.000014999143,0.00000444396,0.000008475768,3.801105e-8,0.0006578343,0.00017326591,0.015588714,0.00004720006,0.9356904,0.047728203],"study_design_scores_gemma":[0.00019056289,0.00017154904,0.00015800049,0.000005031522,0.000004831381,0.0000012580198,0.0010477093,0.00006601208,0.023810588,0.0000157478,0.9744355,0.000093192706],"about_ca_topic_score_codex":0.0000021925123,"about_ca_topic_score_gemma":0.000084185966,"teacher_disagreement_score":0.33570686,"about_ca_system_score_codex":0.000025276393,"about_ca_system_score_gemma":0.00005855213,"threshold_uncertainty_score":0.32165122},"labels":[],"label_agreement":null},{"id":"W2122949122","doi":"10.1145/507515.507524","title":"MDM/KDD","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":18,"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; Data science; Work (physics); Information retrieval; World Wide Web","score_opus":0.0716650625786421,"score_gpt":0.24935752757947455,"score_spread":0.17769246500083247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122949122","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":[0.0011310453,0.00014490014,0.90393966,0.08787797,0.00023673112,0.00021214075,0.0000020147763,0.0008634162,0.005592132],"genre_scores_gemma":[0.7835759,0.00018999758,0.18440023,0.02437182,0.00052212685,0.0003437634,0.000018914989,0.00003775714,0.0065394714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879,0.00005861926,0.00026131302,0.0003661195,0.00027163257,0.0002522772],"domain_scores_gemma":[0.9982014,0.00009051853,0.00007829085,0.0014395339,0.00010959624,0.00008070119],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000107352156,0.00014502538,0.00011772424,0.00014377166,0.00021135426,0.00026407244,0.0012926003,0.00007210408,0.00042315025],"category_scores_gemma":[0.00013241475,0.00013203952,0.00007644011,0.0006322605,0.000055571683,0.0014687272,0.00024609297,0.00015953988,0.0027363955],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039802862,0.00028980908,0.0002878362,0.000015546284,0.00002823356,0.00003078793,0.0027750866,0.0000065052154,0.020733984,0.07439851,0.72287726,0.17855246],"study_design_scores_gemma":[0.00060551614,0.00017283378,0.00070085196,0.000036217683,0.000015707996,0.00004015054,0.0001064139,0.03625016,0.1314373,0.02181254,0.8079756,0.0008467101],"about_ca_topic_score_codex":0.000005314058,"about_ca_topic_score_gemma":0.0000015207805,"teacher_disagreement_score":0.7824449,"about_ca_system_score_codex":0.00003592918,"about_ca_system_score_gemma":0.000011625632,"threshold_uncertainty_score":0.9980401},"labels":[],"label_agreement":null},{"id":"W2128899929","doi":"10.1145/2207243.2207247","title":"Social network analysis and mining to support the assessment of on-line student participation","year":2012,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Automatic summarization; Computer science; Toolbox; Social network analysis; Identification (biology); Visualization; Data science; World Wide Web; Exploit; Social media; Online discussion; Information retrieval; Data mining","score_opus":0.076759501794539,"score_gpt":0.40748789889979475,"score_spread":0.33072839710525576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128899929","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":[0.8210824,0.000005436405,0.16993365,0.0078081167,0.000048022033,0.00027705944,0.000007667259,0.000029090472,0.00080854853],"genre_scores_gemma":[0.99060076,7.384612e-7,0.0067817327,0.0011328427,0.0010625152,0.00024639873,0.0001025312,0.000011526703,0.000060962673],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998857,0.00012749352,0.00035079065,0.00016878368,0.00023287705,0.00026300797],"domain_scores_gemma":[0.99908006,0.00020039882,0.00015756114,0.00042959367,0.000067894725,0.00006451679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040137154,0.00012981861,0.0002480144,0.00012285523,0.0002568244,0.000058483092,0.00020357198,0.000021824855,0.00025521795],"category_scores_gemma":[0.000008619527,0.000100669626,0.00013224213,0.00080631353,0.00003651984,0.00016778793,0.00017139682,0.00009505467,0.000009949673],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000570051,0.00024544264,0.91705954,0.000001642886,0.00090813224,1.4721992e-7,0.003428632,0.0127487285,0.0002315046,0.010800372,0.04620362,0.008366523],"study_design_scores_gemma":[0.00041054434,0.00030619654,0.96702355,0.00001530777,0.0027980646,1.3483904e-7,0.0015136747,0.0064179846,0.0011168378,0.0025594346,0.017335204,0.00050306064],"about_ca_topic_score_codex":0.00002695778,"about_ca_topic_score_gemma":0.00003980912,"teacher_disagreement_score":0.16951834,"about_ca_system_score_codex":0.00002206436,"about_ca_system_score_gemma":0.000014070927,"threshold_uncertainty_score":0.41051883},"labels":[],"label_agreement":null},{"id":"W2155709205","doi":"10.1145/846183.846209","title":"WEBKDD'99","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"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":"York University; DePaul University","keywords":"Computer science; Profiling (computer programming); Knowledge extraction; Data science; World Wide Web; Information retrieval; Data mining","score_opus":0.027504247362564814,"score_gpt":0.25488755574249206,"score_spread":0.22738330837992723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155709205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020672448,0.00009545448,0.82259226,0.13858964,0.00034010463,0.00038630702,0.000038343984,0.0009320123,0.016353447],"genre_scores_gemma":[0.081570975,0.00012345429,0.87214375,0.03206619,0.00096174935,0.00068886107,0.0002196891,0.000049272843,0.0121760545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987972,0.00005004189,0.00024171188,0.00042970644,0.0002060006,0.0002753455],"domain_scores_gemma":[0.9978099,0.00012120652,0.000040682175,0.0018821927,0.000046974525,0.00009907814],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015130418,0.00014320103,0.00011395154,0.00008192117,0.00030136656,0.00035898862,0.0015989078,0.000051002928,0.00079273776],"category_scores_gemma":[0.000050093615,0.00013657629,0.000056505734,0.00055890385,0.000047917056,0.0014652649,0.0001981412,0.00013854212,0.0062517216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021323817,0.00011403855,0.000061026483,0.0000024848491,0.000017508575,0.0000101396045,0.00095877325,0.00013592902,0.0012393966,0.017907085,0.55157423,0.42797726],"study_design_scores_gemma":[0.0002414497,0.000035628676,0.00067815115,0.000008945807,0.000008039963,0.000016906213,0.000029657886,0.0136871245,0.0012336615,0.0068723806,0.9768925,0.0002955806],"about_ca_topic_score_codex":0.000023702003,"about_ca_topic_score_gemma":0.000008108878,"teacher_disagreement_score":0.42768168,"about_ca_system_score_codex":0.000022167522,"about_ca_system_score_gemma":0.00003870443,"threshold_uncertainty_score":0.99452204},"labels":[],"label_agreement":null},{"id":"W2160036998","doi":"10.1145/1233321.1233324","title":"Utility-based anonymization for privacy preservation with less information loss","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":78,"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":"Chinese University of Hong Kong; National Natural Science Foundation of China","keywords":"Computer science; Data anonymization; Microdata (statistics); Categorical variable; Data mining; Identifier; Information loss; Heuristic; Set (abstract data type); Data quality; Information privacy; Machine learning; Artificial intelligence","score_opus":0.04348191414472581,"score_gpt":0.25740419416415156,"score_spread":0.21392228001942576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160036998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016987773,0.000009203228,0.83516616,0.1457968,0.00013627033,0.0008398555,0.00004322151,0.00085911015,0.00016162732],"genre_scores_gemma":[0.32706493,0.0000022794331,0.66819596,0.0026931444,0.000109947236,0.00055653113,0.0013209231,0.000019289322,0.00003701146],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981841,0.00006765687,0.00050254614,0.00044455566,0.00042544297,0.0003757299],"domain_scores_gemma":[0.99170905,0.00031920496,0.00028854507,0.0072088493,0.00043385767,0.00004049365],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00028542904,0.00023802515,0.0001788607,0.00034043414,0.0003498292,0.0005911413,0.010147537,0.00015280425,0.0000109235725],"category_scores_gemma":[0.0050751697,0.00021829254,0.00005420535,0.0009909652,0.00010397166,0.009924433,0.005933374,0.00016857646,0.00004259977],"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":[0.00008173741,0.00022011696,0.016800554,0.000120518474,0.0000318828,0.0000039864212,0.00027293948,0.0046446007,0.0010474429,0.020455522,0.9409957,0.015325027],"study_design_scores_gemma":[0.0019323512,0.00017651673,0.0062901773,0.000058821657,0.000026839318,0.00000425732,0.000046660523,0.6446371,0.022820242,0.20027862,0.123097464,0.000630921],"about_ca_topic_score_codex":0.000070582915,"about_ca_topic_score_gemma":0.000067670786,"teacher_disagreement_score":0.8178982,"about_ca_system_score_codex":0.00007718174,"about_ca_system_score_gemma":0.0001462626,"threshold_uncertainty_score":0.995208},"labels":[],"label_agreement":null},{"id":"W2246590112","doi":"10.1145/2783702.2783708","title":"New Research Directions in Knowledge Discovery and Allied Spheres","year":2015,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Knowledge extraction; Data science; Schema (genetic algorithms); Viewpoints; Domain knowledge; Realm; Point (geometry); Information retrieval; World Wide Web; Knowledge management; Data mining","score_opus":0.16935484731935074,"score_gpt":0.3730839166959473,"score_spread":0.20372906937659657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246590112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018209307,0.0017249177,0.9564835,0.018488837,0.0006466082,0.00040748355,0.000009844724,0.00017294324,0.0038565777],"genre_scores_gemma":[0.29796645,0.0003822098,0.67521566,0.0020453273,0.0018550736,0.00063772744,0.00008948611,0.0000788677,0.021729171],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853486,0.00021253912,0.00025724742,0.00042336568,0.00025218827,0.00031980377],"domain_scores_gemma":[0.9983687,0.00030924942,0.00003828654,0.0009859193,0.00012392183,0.00017393229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039068618,0.00013094749,0.00015714348,0.00023983022,0.00018325038,0.00025918544,0.00044712948,0.00005277616,0.000012405529],"category_scores_gemma":[0.0004550656,0.000117387994,0.000023963205,0.00089487876,0.00008135365,0.0036551831,0.0006691057,0.0002369572,0.00020634032],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023114393,0.0001544585,0.003925543,0.000021686556,0.000023602299,0.00004300908,0.013029595,0.00020604668,0.0033105789,0.29646188,0.64441216,0.03838832],"study_design_scores_gemma":[0.0007100333,0.00009023337,0.0012072265,0.00006548728,0.0000031639684,0.000015968619,0.0019144674,0.0007447511,0.0015119483,0.01795678,0.9754686,0.00031134233],"about_ca_topic_score_codex":0.00065899827,"about_ca_topic_score_gemma":0.0046918713,"teacher_disagreement_score":0.33105645,"about_ca_system_score_codex":0.00007695411,"about_ca_system_score_gemma":0.00022929382,"threshold_uncertainty_score":0.47869435},"labels":[],"label_agreement":null},{"id":"W2627710665","doi":"10.1145/772862.772887","title":"Multi-relational data mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Relational database; Data mining; Information retrieval","score_opus":0.25641928703070915,"score_gpt":0.30813698964909747,"score_spread":0.05171770261838832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2627710665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010828099,0.000094022886,0.9488583,0.0485773,0.00023524847,0.00014772864,0.00008144328,0.00026765498,0.00065545534],"genre_scores_gemma":[0.014243886,0.000018999119,0.97903776,0.004486531,0.00029559105,0.00010158494,0.00044775076,0.000016425442,0.0013514847],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851495,0.00004265557,0.0002995264,0.00062400626,0.0002613833,0.00025749745],"domain_scores_gemma":[0.99608016,0.00021421254,0.00009046302,0.0034526973,0.00006902614,0.00009346687],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017221608,0.00014829852,0.00011374346,0.00012149544,0.0003725353,0.00030574447,0.002887266,0.00005766753,0.00022333325],"category_scores_gemma":[0.00024093872,0.00014748231,0.00003282268,0.00054237933,0.000052406464,0.0028583193,0.0012553595,0.00014572237,0.0019058794],"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":[4.674853e-7,0.00023078767,0.00050262385,0.0000032471335,0.000034156885,0.000010253828,0.001797058,0.00015607518,0.001179554,0.007773654,0.8761573,0.11215483],"study_design_scores_gemma":[0.00030251066,0.000014318684,0.0009458337,0.000009769948,0.0000099612425,0.000013484307,0.000056322027,0.73513675,0.0000852517,0.0002755928,0.26290494,0.00024523248],"about_ca_topic_score_codex":0.000011405284,"about_ca_topic_score_gemma":0.000013226337,"teacher_disagreement_score":0.7349807,"about_ca_system_score_codex":0.000021849517,"about_ca_system_score_gemma":0.000020918327,"threshold_uncertainty_score":0.99887127},"labels":[],"label_agreement":null},{"id":"W2736013904","doi":"10.1145/1809400.1809425","title":"Efficient algorithms for the mining of constrained frequent patterns from uncertain data","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"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 Manitoba","funders":"","keywords":"Computer science; Association rule learning; Data mining; K-optimal pattern discovery; Database transaction; Uncertain data; Data stream mining; Knowledge extraction; Geodetic datum; Data science; Database","score_opus":0.10363999971016609,"score_gpt":0.321903110243897,"score_spread":0.21826311053373093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736013904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040138505,0.000024517556,0.92135346,0.03570633,0.0005976473,0.00047698608,0.0015901268,0.00008451256,0.000027898179],"genre_scores_gemma":[0.24172062,0.0000053849762,0.7544978,0.0019075897,0.000465042,0.00037742086,0.00097012153,0.000018970637,0.00003702473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984226,0.000035627727,0.00041877344,0.0005906566,0.00026496043,0.00026736798],"domain_scores_gemma":[0.99416286,0.0013996863,0.00019326521,0.0040305755,0.00013949329,0.00007414871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041543145,0.00017095591,0.00017627727,0.00007159861,0.0003302856,0.00023213797,0.00385701,0.00006809274,0.000047553964],"category_scores_gemma":[0.00036593436,0.00012777658,0.000063149986,0.00025910107,0.00014264535,0.0003631421,0.0008965662,0.00019504988,0.000026571133],"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":[0.00001703593,0.0008670771,0.0013394715,0.0000412675,0.0004615174,0.000014430323,0.011871804,0.0046292692,0.12162717,0.04939465,0.20599014,0.6037462],"study_design_scores_gemma":[0.0005061816,0.000038395006,0.00062401127,0.000021519787,0.000048541926,0.000004921725,0.00047544308,0.9605882,0.0033060992,0.0012754803,0.032858778,0.000252436],"about_ca_topic_score_codex":0.00030003043,"about_ca_topic_score_gemma":0.00013338205,"teacher_disagreement_score":0.9559589,"about_ca_system_score_codex":0.000011905109,"about_ca_system_score_gemma":0.00010244061,"threshold_uncertainty_score":0.7167348},"labels":[],"label_agreement":null},{"id":"W2945319864","doi":"10.1145/3331651.3331653","title":"Urban Human Mobility","year":2019,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":107,"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":"","keywords":"Computer science; Multidisciplinary approach; Data science; Context (archaeology); Mobility model; Perspective (graphical); Field (mathematics); Global Positioning System; Urban computing; Human dynamics; Human–computer interaction; Artificial intelligence; Telecommunications; Sociology","score_opus":0.036755788776791795,"score_gpt":0.3235828484170946,"score_spread":0.2868270596403028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945319864","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":[0.93221813,0.000038194736,0.001855172,0.03522222,0.0002957495,0.0007142736,0.000009557358,0.00026818708,0.029378522],"genre_scores_gemma":[0.9841303,0.0000049612513,0.0002128028,0.0036865587,0.0005213185,0.000113434864,0.000080867525,0.000013529056,0.011236232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820983,0.00034836345,0.00032230103,0.00039834276,0.00039951302,0.0003216358],"domain_scores_gemma":[0.9982471,0.00026335957,0.000087163084,0.0011085949,0.00017089026,0.00012289995],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000755789,0.00013282157,0.0001863057,0.00013495746,0.00093891454,0.00017704304,0.0005797626,0.00011536288,0.0064826123],"category_scores_gemma":[0.0003641611,0.00013704246,0.00014903386,0.0005422241,0.00024992914,0.00062977656,0.000068287394,0.00019234313,0.003427998],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023797587,0.0011146908,0.2847053,0.000062057814,0.00020913691,0.0000064071064,0.094978295,0.0008138325,0.014593534,0.14417845,0.4529069,0.006407578],"study_design_scores_gemma":[0.0005513287,0.00008723201,0.015757898,0.00002321368,0.00008721892,2.0916089e-7,0.011127409,0.0001943996,0.0008783243,0.01440172,0.95627123,0.0006197932],"about_ca_topic_score_codex":0.003406378,"about_ca_topic_score_gemma":0.008887506,"teacher_disagreement_score":0.5033644,"about_ca_system_score_codex":0.00014762304,"about_ca_system_score_gemma":0.00013892891,"threshold_uncertainty_score":0.99734795},"labels":[],"label_agreement":null},{"id":"W3034271075","doi":"10.1145/3262579","title":"Session details: Special issue on learning from imbalanced datasets","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"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; Canadian Imperial Bank of Commerce (Canada)","funders":"","keywords":"Computer science; Session (web analytics); Machine learning; Data science; Artificial intelligence; World Wide Web","score_opus":0.037927200654235056,"score_gpt":0.28477606922886783,"score_spread":0.24684886857463278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034271075","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008008929,0.00001909062,0.93825734,0.0492662,0.000906585,0.00045813186,0.00014218275,0.001169885,0.0017716504],"genre_scores_gemma":[0.33378574,0.00012588402,0.61442584,0.031592593,0.011213247,0.0005770806,0.007502315,0.00010983858,0.00066744816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978307,0.00014420498,0.00041863022,0.00078070234,0.00046153206,0.00036425228],"domain_scores_gemma":[0.99700755,0.00020817386,0.00020683609,0.002386504,0.0000756632,0.000115254894],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017711539,0.00026920903,0.00022633285,0.00021089085,0.00039545968,0.00042112335,0.0019409466,0.00013222104,0.00024671253],"category_scores_gemma":[0.00044308105,0.00025750464,0.000064150125,0.00054518937,0.00006758717,0.0023621344,0.0005267443,0.00045053763,0.0031942427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039706847,0.00037079683,0.0006314472,0.000009276623,0.000044778513,0.00007641559,0.0025817913,0.0023420579,0.07868935,0.018976783,0.8267455,0.06949207],"study_design_scores_gemma":[0.0010959075,0.00018588266,0.0026257725,0.00010546145,0.000014621241,0.000006345567,0.00013356697,0.001201242,0.16474563,0.021924723,0.8072844,0.00067641435],"about_ca_topic_score_codex":0.000050483555,"about_ca_topic_score_gemma":0.000025475565,"teacher_disagreement_score":0.3257768,"about_ca_system_score_codex":0.00016118966,"about_ca_system_score_gemma":0.00008072608,"threshold_uncertainty_score":0.9999877},"labels":[],"label_agreement":null},{"id":"W3112675244","doi":"10.1145/3447556.3447563","title":"A Report on the First Workshop on Document Intelligence (DI) at NeurIPS 2019","year":2021,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Library science; Intelligence analysis; Data science; World Wide Web; Computer security","score_opus":0.051440865561647335,"score_gpt":0.2786518561287233,"score_spread":0.22721099056707594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112675244","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03661755,0.000107228116,0.22215873,0.7373458,0.0009890738,0.00024555123,0.0000093010485,0.00024256505,0.0022841948],"genre_scores_gemma":[0.81781036,0.000302881,0.018598499,0.13356608,0.0011932688,0.00043361704,0.00037546712,0.00006916877,0.027650667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789715,0.00013655842,0.0004103722,0.000755664,0.0004892443,0.00031100409],"domain_scores_gemma":[0.995096,0.0008347482,0.00014979475,0.0037254267,0.0001110391,0.00008295264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035213324,0.00021496587,0.0001820753,0.00011948867,0.0005679362,0.00055325107,0.0014798315,0.00006105982,0.00021567875],"category_scores_gemma":[0.0007854542,0.00015515684,0.00014768899,0.0009199952,0.000056292418,0.0005802693,0.00089331233,0.00028387696,0.0022701884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009326516,0.00016832426,0.0005204177,0.0000045615643,0.00009317496,0.0008501337,0.0015107117,0.0051266956,0.0004008307,0.015320502,0.9650748,0.010920564],"study_design_scores_gemma":[0.00024233974,0.00014723759,0.001361453,0.00022736382,0.000079006706,0.00023353523,0.0004476396,0.010595642,0.028989168,0.0060636424,0.95072407,0.00088890333],"about_ca_topic_score_codex":0.000019995166,"about_ca_topic_score_gemma":0.00011219052,"teacher_disagreement_score":0.7811928,"about_ca_system_score_codex":0.00009031579,"about_ca_system_score_gemma":0.00006513412,"threshold_uncertainty_score":0.99850667},"labels":[],"label_agreement":null},{"id":"W3165211483","doi":"10.1145/3468507.3468511","title":"On the Applicability of Machine Learning Fairness Notions","year":2021,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":70,"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 à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Subjectivity; Set (abstract data type); Computer science; Artificial intelligence; Machine learning; Fairness measure; Epistemology","score_opus":0.08874008202605167,"score_gpt":0.35175980610599283,"score_spread":0.2630197240799412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165211483","genre_codex":"commentary","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":[0.25679553,0.00005106695,0.0040710717,0.6982925,0.00026427172,0.00034070853,0.00002150168,0.00009424293,0.040069155],"genre_scores_gemma":[0.9909679,0.00005428437,0.00039931422,0.0070537576,0.00022403013,0.000050315655,0.00002258578,0.000010649079,0.0012171379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99844104,0.0005586323,0.00021428867,0.00018881825,0.00038744128,0.00020979843],"domain_scores_gemma":[0.99700534,0.0019190842,0.00009096908,0.0004975414,0.00041879198,0.000068293615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088338344,0.00008786815,0.00013399548,0.000034275585,0.0012908869,0.00014599998,0.00034978305,0.00011078782,0.00071201],"category_scores_gemma":[0.0075985286,0.00006976276,0.00010387595,0.00048016306,0.0003835852,0.00030791308,0.000098049735,0.00044314918,0.000099984936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008483336,0.0002577631,0.0020388535,0.000010108238,0.00004744386,0.0000044129215,0.04671756,0.0004465157,0.0042837784,0.9249121,0.019558728,0.0017142791],"study_design_scores_gemma":[0.0005400453,0.00013293774,0.0032655965,0.00006611514,0.00008160824,9.582085e-7,0.043746278,0.00024536913,0.009189707,0.5769877,0.36516726,0.0005764677],"about_ca_topic_score_codex":0.00067654473,"about_ca_topic_score_gemma":0.002637025,"teacher_disagreement_score":0.7341724,"about_ca_system_score_codex":0.00004842909,"about_ca_system_score_gemma":0.00020371267,"threshold_uncertainty_score":0.9928589},"labels":[],"label_agreement":null},{"id":"W4311079932","doi":"10.1145/3575637.3575645","title":"Finding Multidimensional Simpson's Paradox","year":2022,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","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; Burnaby Hospital","funders":"","keywords":"Computer science; Curse of dimensionality; Multidimensional data; Data science; Phenomenon; Data mining; Machine learning; Epistemology","score_opus":0.04358511030504669,"score_gpt":0.2740753601844798,"score_spread":0.23049024987943312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311079932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02590994,0.000060412032,0.8863432,0.0856034,0.0006901848,0.0003528875,0.00009484245,0.00045145964,0.0004936737],"genre_scores_gemma":[0.3049092,0.0000074965137,0.6744365,0.017088741,0.00034553386,0.0013988529,0.0003911996,0.00003600204,0.0013864432],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984572,0.00009051751,0.0002539345,0.0004958439,0.00040411856,0.0002984201],"domain_scores_gemma":[0.9981133,0.00023431043,0.00009561512,0.0014230849,0.000045182976,0.00008851895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024511263,0.0001459361,0.00012362769,0.00015849061,0.0011346235,0.000165658,0.0014549644,0.000026429767,0.00026553226],"category_scores_gemma":[0.00008149783,0.00015391229,0.000067241956,0.0007123972,0.000034677327,0.00089449564,0.0015031989,0.0002694154,0.00042315378],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054293832,0.00037800323,0.00047023757,0.0000047368026,0.000049363847,0.000055602875,0.0032685648,0.0071844724,0.008874969,0.1003354,0.8149069,0.064466305],"study_design_scores_gemma":[0.000477965,0.00008666827,0.00070568774,0.000005104156,0.000012069259,0.00005239129,0.0003280089,0.13893926,0.0011994814,0.0052950033,0.8524459,0.0004524876],"about_ca_topic_score_codex":0.000020865893,"about_ca_topic_score_gemma":0.0000029988848,"teacher_disagreement_score":0.27899927,"about_ca_system_score_codex":0.000071928094,"about_ca_system_score_gemma":0.00006901292,"threshold_uncertainty_score":0.8726722},"labels":[],"label_agreement":null},{"id":"W4311079975","doi":"10.1145/3575637.3575654","title":"Experiences with Contrastive Predictive Coding in Industrial Time-Series Classification","year":2022,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Time Series Analysis and Forecasting","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","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Machine learning; Coding (social sciences); Data mining; Multivariate statistics; Pattern recognition (psychology); Artificial neural network; Time series; Statistics","score_opus":0.04476407521292988,"score_gpt":0.22947922000461182,"score_spread":0.18471514479168194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311079975","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":[0.4936736,0.00006550954,0.4679309,0.03387409,0.00058540836,0.0010189345,0.000032722837,0.00037553918,0.0024432936],"genre_scores_gemma":[0.99196273,0.0000018759777,0.006127668,0.00057390507,0.0001459378,0.0008502738,0.000042413732,0.0000116183355,0.00028358086],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839765,0.00018481602,0.00032852014,0.00044449267,0.00037525228,0.00026929416],"domain_scores_gemma":[0.9990015,0.00016383674,0.00018531847,0.0005248213,0.000072292096,0.000052253807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027170646,0.00015391153,0.00019996401,0.00022628969,0.0005843135,0.00022655619,0.0007669563,0.00003879572,0.00026336478],"category_scores_gemma":[0.00012724314,0.00013803084,0.000044830904,0.0011583436,0.000102638995,0.00186368,0.0003847385,0.0002856266,0.000026384774],"study_design_candidate":"qualitative","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":[0.0015817403,0.0013862638,0.036126047,0.000021710632,0.000654422,0.00037482995,0.64107466,0.0637811,0.028109226,0.06280996,0.10455343,0.05952664],"study_design_scores_gemma":[0.005537843,0.004024673,0.008957387,0.00012704151,0.00013843033,0.00014656548,0.34627876,0.5733794,0.00867636,0.00308427,0.04715133,0.0024979212],"about_ca_topic_score_codex":0.000030609437,"about_ca_topic_score_gemma":0.00002770495,"teacher_disagreement_score":0.5095983,"about_ca_system_score_codex":0.00012527745,"about_ca_system_score_gemma":0.000100734105,"threshold_uncertainty_score":0.5628734},"labels":[],"label_agreement":null},{"id":"W4406939872","doi":"10.1145/3715073.3715081","title":"Graph Fairness via Authentic Counterfactuals: Tackling Structural and Causal Challenges","year":2025,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","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":"University of Manitoba","funders":"","keywords":"Counterfactual conditional; Computer science; Psychology; Counterfactual thinking; Social psychology","score_opus":0.058918373595661724,"score_gpt":0.36371029940612337,"score_spread":0.30479192581046166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406939872","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":[0.59301203,0.0015249248,0.0050445446,0.38924694,0.0014772022,0.00051453663,0.000013715929,0.00022910058,0.008937026],"genre_scores_gemma":[0.99289644,0.0007557444,0.00042391225,0.0047699986,0.00035211924,0.000032399068,0.000009697217,0.00001395645,0.0007457126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985232,0.00023062962,0.00025338365,0.00029900883,0.0003203373,0.00037349382],"domain_scores_gemma":[0.998674,0.00054691866,0.0000794982,0.0003425516,0.00024364275,0.00011340834],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005661293,0.00016506643,0.00020403028,0.00016711703,0.0013438511,0.0004557107,0.00036344447,0.00020888132,0.00008545507],"category_scores_gemma":[0.00096669164,0.00016068606,0.00006195723,0.00028861774,0.0004783691,0.0010980954,0.00012742793,0.00030600312,0.000027381611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004526832,0.00010164941,0.0031383878,0.0001287312,0.00034496764,0.000021679594,0.37191215,0.00006696635,0.0035881042,0.5650857,0.024769792,0.030796604],"study_design_scores_gemma":[0.00085327233,0.00010039946,0.005976699,0.00016861297,0.00016233287,0.0000019363688,0.057647806,0.00021122555,0.0007615753,0.8496167,0.08369065,0.0008087755],"about_ca_topic_score_codex":0.0009489833,"about_ca_topic_score_gemma":0.004117316,"teacher_disagreement_score":0.39988446,"about_ca_system_score_codex":0.00006630329,"about_ca_system_score_gemma":0.00014548573,"threshold_uncertainty_score":0.99995625},"labels":[],"label_agreement":null}]}