{"meta":{"query_hash":"d5e1e7be5d0e","filters":{"venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/d5e1e7be5d0e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+Fifteenth+ACM+International+Conference+on+Web+Search+and+Data+Mining"},"results":[{"id":"W4200631100","doi":"10.1145/3488560.3498498","title":"Differentially Private Ensemble Classifiers for Data Streams","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data stream mining; Concept drift; Computer science; Competitor analysis; Data stream; Data mining; STREAMS; Private information retrieval; Black box; Ensemble forecasting; Machine learning; Regression; Artificial intelligence; Data modeling; Statistics; Database; Mathematics; Computer security","score_opus":0.16805348750242247,"score_gpt":0.35826392776550936,"score_spread":0.1902104402630869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200631100","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":[0.9128559,0.00006494098,0.037515774,0.020332161,0.0013759655,0.0018436685,0.014964842,0.00042626215,0.010620452],"genre_scores_gemma":[0.87441283,0.00005623304,0.1242261,0.00015426056,0.000059480943,0.00006073039,0.0008382201,0.000014265662,0.00017788469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99761593,0.000023834018,0.00031378443,0.000883501,0.00084971637,0.00031324232],"domain_scores_gemma":[0.99759984,0.00019039835,0.00022441652,0.0016655339,0.00022806022,0.000091765396],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0010873931,0.00017335241,0.00018640004,0.00018022316,0.00032988648,0.00046128305,0.017360635,0.000035306493,0.000046734596],"category_scores_gemma":[0.0010021102,0.00014183202,0.000032892094,0.00020469038,0.0001238846,0.0012395185,0.0276701,0.00028145802,0.000001115575],"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":[0.00041236685,0.00038338048,0.0141225085,0.00013675426,0.0002763538,0.0000030367,0.0010359522,0.0000033825445,0.039209407,0.5543621,0.0810115,0.30904326],"study_design_scores_gemma":[0.001416726,0.0007752525,0.0022919558,0.00027008954,0.00004284276,0.000037119073,0.0013426204,0.93200535,0.013884237,0.01418482,0.03321337,0.00053559465],"about_ca_topic_score_codex":0.000033890898,"about_ca_topic_score_gemma":0.0000075522294,"teacher_disagreement_score":0.932002,"about_ca_system_score_codex":0.000047898255,"about_ca_system_score_gemma":0.00018999055,"threshold_uncertainty_score":0.9879559},"labels":[],"label_agreement":null},{"id":"W4206865191","doi":"10.1145/3488560.3498419","title":"Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Knowledge graph; Computer science; Recommender system; Theoretical computer science; Semantics (computer science); Graph; Semantic space; ENCODE; Unification; Information retrieval; Artificial intelligence","score_opus":0.12534980454359115,"score_gpt":0.3362451936795552,"score_spread":0.21089538913596403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206865191","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":[0.8885276,0.00012005042,0.072272934,0.022783963,0.0009494548,0.0016738044,0.0015356869,0.00027075637,0.011865802],"genre_scores_gemma":[0.97222537,0.000047809855,0.027269308,0.00010845554,0.000046929992,0.00012097548,0.000080618345,0.000011548803,0.00008896556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985677,0.000020759053,0.00025906297,0.0005063285,0.00042807558,0.00021805972],"domain_scores_gemma":[0.9987721,0.00010034339,0.0001254816,0.00052837323,0.00040837805,0.00006535735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009848436,0.00013599283,0.0001623014,0.00027673377,0.0003473257,0.0002660943,0.0047336025,0.000028560224,0.000026139378],"category_scores_gemma":[0.0001930136,0.00010159351,0.00003726282,0.0002993465,0.00004214008,0.0007489291,0.005022071,0.00021939367,4.155901e-7],"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":[0.00081234664,0.0008872704,0.03598703,0.00063849427,0.0005293229,0.0000014884498,0.0069528413,0.00018907635,0.0056935204,0.532971,0.038818814,0.3765188],"study_design_scores_gemma":[0.0006972639,0.00035325743,0.0002454967,0.00015382779,0.000009688088,0.00002535675,0.001966392,0.98724914,0.0008752084,0.0053053354,0.002929755,0.00018928522],"about_ca_topic_score_codex":0.000049024533,"about_ca_topic_score_gemma":0.000016252408,"teacher_disagreement_score":0.98706007,"about_ca_system_score_codex":0.000046507026,"about_ca_system_score_gemma":0.00010831068,"threshold_uncertainty_score":0.879629},"labels":[],"label_agreement":null},{"id":"W4212816054","doi":"10.1145/3488560.3498376","title":"An Ensemble Model for Combating Label Noise","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Noise (video); Machine learning; Artificial neural network; Consistency (knowledge bases); Pattern recognition (psychology); Image (mathematics); Set (abstract data type); Matching (statistics); Measure (data warehouse); Function (biology); Data mining; Mathematics; Statistics","score_opus":0.16405802616967322,"score_gpt":0.37567839057985014,"score_spread":0.21162036441017693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212816054","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":[0.8992205,0.00003764257,0.07265512,0.01833172,0.00040976374,0.00071890745,0.0013814861,0.00014876203,0.00709605],"genre_scores_gemma":[0.9331508,0.000015108698,0.06607331,0.00021460571,0.0000377583,0.00004433429,0.00020274645,0.000007696831,0.00025361055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985311,0.000022421325,0.00021107712,0.0004912479,0.00055427896,0.0001898934],"domain_scores_gemma":[0.9988223,0.00011437674,0.00015958703,0.0005627071,0.00026896136,0.000072108494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011180412,0.00010215367,0.00010721057,0.00011710799,0.00041340993,0.00029829162,0.00484807,0.000021334976,0.000016702617],"category_scores_gemma":[0.00065027946,0.000084894724,0.000020093918,0.00014557656,0.000047930705,0.0008387347,0.0031596057,0.00023308137,9.146743e-7],"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":[0.0002435007,0.0003721188,0.0134535665,0.000093373295,0.000057265162,4.1156588e-7,0.0031919838,0.0009620961,0.07399175,0.7485186,0.005198983,0.15391633],"study_design_scores_gemma":[0.00039753458,0.00015526098,0.00067972025,0.00002618944,0.0000044679377,0.0000042804313,0.00059527665,0.99466383,0.00048414015,0.0022420406,0.0006526155,0.00009462829],"about_ca_topic_score_codex":0.000021194644,"about_ca_topic_score_gemma":0.0000041126095,"teacher_disagreement_score":0.99370176,"about_ca_system_score_codex":0.000028612832,"about_ca_system_score_gemma":0.00013112476,"threshold_uncertainty_score":0.90090007},"labels":[],"label_agreement":null},{"id":"W4213017138","doi":"10.1145/3488560.3498507","title":"A GNN-based Multi-task Learning Framework for Personalized Video Search","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Multimodal Machine Learning 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":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Task (project management); Human–computer interaction; Multimedia; Systems engineering; Engineering","score_opus":0.12830707427337426,"score_gpt":0.3845772540133766,"score_spread":0.2562701797400023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213017138","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":[0.7793296,0.00009053453,0.17471012,0.04107394,0.00041103878,0.001661834,0.0009624957,0.00025896062,0.001501456],"genre_scores_gemma":[0.809578,0.0000112791295,0.18956938,0.00027530783,0.00005165685,0.0001813725,0.00008497149,0.000015594165,0.0002324462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975807,0.00006476993,0.00028530654,0.00075986795,0.00096381904,0.00034553785],"domain_scores_gemma":[0.99793583,0.000711427,0.00019001601,0.00058506493,0.00045867029,0.00011898358],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0015282499,0.00017383254,0.00018873093,0.00023281958,0.0007355177,0.0003613566,0.0059990417,0.0000471009,0.000117708136],"category_scores_gemma":[0.0026292887,0.00015064082,0.000070130416,0.00036663606,0.00015244818,0.00037404118,0.004582709,0.00079477613,0.000004550345],"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":[0.00058194867,0.0005249693,0.08413579,0.0002080808,0.00019108577,0.000001574795,0.005449163,0.0025047325,0.02044212,0.83732694,0.0012267032,0.047406897],"study_design_scores_gemma":[0.00089953316,0.00020191116,0.0046717497,0.000099235964,0.000009134086,0.000005653245,0.0011261894,0.9872219,0.0005350826,0.0014125528,0.0036447127,0.00017235283],"about_ca_topic_score_codex":0.00010792217,"about_ca_topic_score_gemma":0.0000024054486,"teacher_disagreement_score":0.98471713,"about_ca_system_score_codex":0.00007616987,"about_ca_system_score_gemma":0.00027132907,"threshold_uncertainty_score":0.999379},"labels":[],"label_agreement":null},{"id":"W4213235855","doi":"10.1145/3488560.3498387","title":"Translating Human Mobility Forecasting through Natural Language Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Traffic Prediction and Management Techniques","field":"Engineering","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 Waterloo","funders":"Australian Research Council","keywords":"Computer science; Bottleneck; Pipeline (software); Artificial intelligence; Natural language generation; Natural language; Machine learning; Mobility model; Data mining; Distributed computing","score_opus":0.13119351836417423,"score_gpt":0.33133583547336554,"score_spread":0.2001423171091913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213235855","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":[0.9861929,0.00006477001,0.00026553206,0.0005482471,0.00025941659,0.00023618418,0.00023313389,0.00033081605,0.01186904],"genre_scores_gemma":[0.9966969,0.000022258017,0.0029049914,0.000050135084,0.0000801687,0.00003010684,0.00015026066,0.000010691308,0.000054503627],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990671,0.000009377402,0.00019274253,0.000223088,0.00037063938,0.00013700352],"domain_scores_gemma":[0.9996713,0.000019851122,0.000046563073,0.00017689297,0.00006182845,0.000023581952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041685623,0.000093992996,0.000086074375,0.00007450871,0.0002199224,0.00008530344,0.00096541434,0.000018304088,0.00006511956],"category_scores_gemma":[0.00010028024,0.00008221771,0.000024178278,0.000100440484,0.00004363354,0.00039989487,0.00080590684,0.00025993,2.9244652e-7],"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":[0.00017951902,0.0002934622,0.0117131565,0.0005891366,0.00045142518,0.000005419141,0.019292578,0.0021326519,0.58068556,0.082325146,0.042972956,0.25935897],"study_design_scores_gemma":[0.00029959134,0.000056019217,0.0006212932,0.000051807358,0.000010290769,0.0000061954274,0.0036574597,0.9902948,0.0039029098,0.00010362645,0.0008842618,0.00011171446],"about_ca_topic_score_codex":0.000021457512,"about_ca_topic_score_gemma":0.000015297697,"teacher_disagreement_score":0.98816216,"about_ca_system_score_codex":0.000042879987,"about_ca_system_score_gemma":0.00001365947,"threshold_uncertainty_score":0.3352741},"labels":[],"label_agreement":null}]}