{"meta":{"query_hash":"3b3b69ad4986","filters":{"topic":"Algorithms and Data Compression"},"cohort_total":1336,"direct_labels_cover":0,"predictions_cover":1336,"exported":1336,"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/3b3b69ad4986","api":"https://metacan.xera.ac/api/v1/cohort?topic=Algorithms+and+Data+Compression"},"results":[{"id":"W108609803","doi":"","title":"Open BEAGLE: a new C++ Evolutionary Computation framework","year":2002,"lang":"en","type":"article","venue":"Genetic and Evolutionary Computation Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Beagle; Evolutionary computation; Computer science; Computation; Biology; Artificial intelligence; Programming language; Genetics","score_opus":0.04547421984359133,"score_gpt":0.27476853603485335,"score_spread":0.229294316191262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W108609803","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014778103,0.0002261,0.97657895,0.00024497535,0.00015738238,0.00010168709,0.0003271558,0.015316226,0.0055697616],"genre_scores_gemma":[0.03462913,0.0005925684,0.94667125,0.0005528331,0.000106673455,0.0005159855,0.0018032624,0.0070519997,0.0080762915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984717,0.0003301289,0.00010462314,0.00024388374,0.0006926246,0.00015704655],"domain_scores_gemma":[0.9987185,0.00047500912,0.000062176565,0.0002784377,0.00034572877,0.00012014052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021910674,0.00094938354,0.0008664647,0.0010995498,0.0008413173,0.0024212408,0.0037303306,0.0016473996,0.012786172],"category_scores_gemma":[0.0058499025,0.000717445,0.0012964068,0.0009969738,0.0009956852,0.0028889368,0.002081539,0.002796482,0.0041984185],"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":[0.0004900388,0.00019754515,0.0008820282,0.00046950314,0.00019064067,0.00041953733,0.00030779274,0.12205528,0.015300842,0.23278442,0.07889084,0.54801154],"study_design_scores_gemma":[0.00025341503,0.0001287502,0.0003478268,0.00012805808,0.000080301026,0.00045909334,0.000040992323,0.51216817,0.01173264,0.1394404,0.3350859,0.00013438813],"about_ca_topic_score_codex":0.0037147119,"about_ca_topic_score_gemma":0.0035195565,"teacher_disagreement_score":0.012786172,"about_ca_system_score_codex":0.0006667106,"about_ca_system_score_gemma":0.0013959104,"threshold_uncertainty_score":0.04277402},"labels":[],"label_agreement":null},{"id":"W108848441","doi":"10.3233/978-1-58603-891-5-495","title":"Compressing Pattern Databases with Learning","year":2008,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Database; Computer science","score_opus":0.05287514117073378,"score_gpt":0.2700487376627026,"score_spread":0.21717359649196882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W108848441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044173457,0.0033586153,0.9329293,0.00061982847,0.00026362084,0.00026161846,0.001842606,0.0075652637,0.008985742],"genre_scores_gemma":[0.13981266,0.0027008236,0.84228325,0.0002652097,0.00013299487,0.00033093945,0.004814757,0.00048275111,0.009176523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936026,0.00007586549,0.000078279256,0.00014248869,0.0003019689,0.0000410652],"domain_scores_gemma":[0.9982864,0.00062033464,0.00008200182,0.0006174868,0.00036145982,0.000032299144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005675572,0.0007879993,0.0009388801,0.002078912,0.00043971758,0.0015165927,0.0016992164,0.000610038,0.007533963],"category_scores_gemma":[0.0038943987,0.00047551014,0.0005474584,0.004932819,0.00051187986,0.004010457,0.0015158918,0.0009881053,0.0023066874],"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":[0.00015053754,0.00005920466,0.00039964193,0.0002927833,0.000029781388,0.00014683873,0.00011251175,0.02862707,0.009394718,0.013898621,0.012995378,0.9338929],"study_design_scores_gemma":[0.00012501347,0.00019405279,0.0007880329,0.00013446977,0.00008196035,0.0011098275,0.00026519736,0.757943,0.08050828,0.07668378,0.08209906,0.0000673365],"about_ca_topic_score_codex":0.0021583736,"about_ca_topic_score_gemma":0.0017570356,"teacher_disagreement_score":0.007533963,"about_ca_system_score_codex":0.000644171,"about_ca_system_score_gemma":0.0008727758,"threshold_uncertainty_score":0.025203645},"labels":[],"label_agreement":null},{"id":"W111403613","doi":"10.1007/978-3-642-29344-3_43","title":"Independence of Tabulation-Based Hash Classes","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hash function; Independence (probability theory); Discrete mathematics; Mathematics; Characterization (materials science); Combinatorics; Computer science; Statistics","score_opus":0.019587056982460393,"score_gpt":0.2527400644051529,"score_spread":0.23315300742269252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W111403613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054409098,0.0016352737,0.8644966,0.0009789439,0.0006792781,0.00033219747,0.001581142,0.007470453,0.068416975],"genre_scores_gemma":[0.7319266,0.0018741167,0.211733,0.0012100375,0.0010621235,0.00068824424,0.003993149,0.005021096,0.04249166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99350595,0.0012669143,0.00048346745,0.0012006251,0.0025906547,0.0009524117],"domain_scores_gemma":[0.973389,0.010614075,0.00066824665,0.012432594,0.0023515676,0.00054445106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003505407,0.00087980274,0.0015027347,0.0017550588,0.0015887069,0.0065242546,0.0041368743,0.0016211346,0.019241784],"category_scores_gemma":[0.023333682,0.0017112072,0.0017495896,0.002471418,0.0034596205,0.016815538,0.0061022947,0.0047002276,0.010049745],"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":[0.0013378409,0.00018311919,0.0015919028,0.00048579703,0.000067125104,0.00011244567,0.00039445815,0.0075642387,0.011986235,0.74525124,0.016346162,0.21467945],"study_design_scores_gemma":[0.00017375899,0.00018265791,0.0010596976,0.00014591479,0.00016140856,0.00053901586,0.00014871852,0.08319763,0.041914664,0.8372809,0.035081238,0.000114396214],"about_ca_topic_score_codex":0.000543494,"about_ca_topic_score_gemma":0.000626848,"teacher_disagreement_score":0.019241784,"about_ca_system_score_codex":0.001209691,"about_ca_system_score_gemma":0.0018361999,"threshold_uncertainty_score":0.064370155},"labels":[],"label_agreement":null},{"id":"W119709885","doi":"","title":"Genome Homology Visualization by Short Similar Substring Enumeration (Acceleration and Visualization of Computation for Enumeration Problems)","year":2009,"lang":"en","type":"article","venue":"Kyoto University Research Information Repository (Kyoto University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Institute of Genetics; National Institute of Informatics; Hokkaido University","keywords":"Enumeration; Substring; Visualization; Computation; Genome; Computer science; Data visualization; Homology (biology); Mathematics; Theoretical computer science; Biology; Combinatorics; Algorithm; Genetics; Data structure; Artificial intelligence; Programming language","score_opus":0.027031169655029514,"score_gpt":0.27915958385638745,"score_spread":0.25212841420135795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W119709885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03608199,0.0003909604,0.9520793,0.00035124063,0.00004969191,0.000102844795,0.00041547208,0.00806406,0.0024643142],"genre_scores_gemma":[0.124314584,0.00023339847,0.87257916,0.00009284861,0.000032575343,0.00015553637,0.0009312242,0.0002956582,0.0013650388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928707,0.00024168323,0.000038802857,0.00017755495,0.0001767329,0.00007807313],"domain_scores_gemma":[0.99867344,0.00063203357,0.00015016545,0.00032278852,0.00012776819,0.00009392749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008204636,0.00090004393,0.00092739816,0.0021212315,0.00058952,0.0016227777,0.0016558621,0.0014315568,0.0051336363],"category_scores_gemma":[0.0038126954,0.00047487373,0.0010672392,0.0026031123,0.00063909276,0.0032369783,0.0024208827,0.0011690208,0.0011999307],"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":[0.0007239648,0.00036504265,0.004421269,0.00052880443,0.000101702746,0.00034517044,0.00062446523,0.11894321,0.07318496,0.07154595,0.017730525,0.7114849],"study_design_scores_gemma":[0.00006333834,0.00012102295,0.0014559872,0.000041992276,0.000015783924,0.00036097478,0.00010561338,0.90836126,0.023056708,0.056787774,0.009587067,0.000042430052],"about_ca_topic_score_codex":0.0019965284,"about_ca_topic_score_gemma":0.0013455317,"teacher_disagreement_score":0.0051336363,"about_ca_system_score_codex":0.0006624783,"about_ca_system_score_gemma":0.00065964455,"threshold_uncertainty_score":0.017173707},"labels":[],"label_agreement":null},{"id":"W1201605537","doi":"10.1016/j.tcs.2015.08.008","title":"FM-index of alignment: A compressed index for similar strings","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Education, Science and Technology; Ministère des Affaires Etrangères; Providence Health Care; Ministry of Science, ICT and Future Planning; National Research Foundation of Korea","keywords":"Suffix; Index (typography); Suffix array; Computer science; Compressed suffix array; Inverted index; Suffix tree; Algorithm; Search engine indexing; Mathematics; Artificial intelligence; Data structure","score_opus":0.02091421018035305,"score_gpt":0.2700424881084069,"score_spread":0.24912827792805387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1201605537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068787076,0.0036898972,0.890504,0.0015436535,0.0012475258,0.00053011,0.010146149,0.011362443,0.012189238],"genre_scores_gemma":[0.22010046,0.0014077895,0.7468106,0.0008026382,0.0011574391,0.0008296287,0.017189054,0.0017065433,0.009995821],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841905,0.0002408252,0.00016171878,0.00023518325,0.0007811031,0.00016207204],"domain_scores_gemma":[0.99513173,0.00125516,0.00031599047,0.0020660525,0.0009611616,0.00026995302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010746052,0.0010454147,0.0015723843,0.0059004757,0.0011935914,0.0019610808,0.001967459,0.0017086009,0.011049816],"category_scores_gemma":[0.013004641,0.00047740835,0.00060567353,0.008002302,0.0009446137,0.0051706787,0.002890503,0.0016975874,0.0042603584],"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":[0.0021587273,0.00026721956,0.0016844561,0.00048290542,0.00008401223,0.0004170956,0.00033319314,0.01133116,0.041816052,0.057357512,0.055311985,0.8287557],"study_design_scores_gemma":[0.0005814429,0.0014690724,0.0040171575,0.0004229803,0.00025506262,0.0041088425,0.0005280274,0.45694515,0.11091165,0.28424305,0.13624203,0.00027555288],"about_ca_topic_score_codex":0.0011802887,"about_ca_topic_score_gemma":0.0014775933,"teacher_disagreement_score":0.011049816,"about_ca_system_score_codex":0.0009334921,"about_ca_system_score_gemma":0.0017886695,"threshold_uncertainty_score":0.03696531},"labels":[],"label_agreement":null},{"id":"W120212917","doi":"10.46298/dmtcs.308","title":"The Cycles of the Multiway Perfect Shuffle Permutation","year":2002,"lang":"en","type":"article","venue":"Discrete Mathematics & Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Permutation (music); Mathematics; Combinatorics; Deck; Discrete mathematics; Space (punctuation); Algorithm; Computer science","score_opus":0.013691370650729482,"score_gpt":0.2519285687985683,"score_spread":0.2382371981478388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W120212917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33632302,0.001203189,0.6267328,0.0005469534,0.00018482955,0.0003831197,0.0011585471,0.0011242782,0.032343164],"genre_scores_gemma":[0.7555978,0.00076951535,0.2171167,0.00023173823,0.000086001535,0.00032743163,0.0012427067,0.00034936282,0.02427869],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996444,0.0000697266,0.000024369318,0.00010458752,0.00008647949,0.00007044425],"domain_scores_gemma":[0.9995443,0.00012620765,0.00007867052,0.00012870498,0.00007420427,0.000047807225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020095835,0.0004199094,0.00030383366,0.0009520053,0.000772899,0.0012444301,0.00043404053,0.00055079296,0.0043450776],"category_scores_gemma":[0.0016565117,0.0004111771,0.00045242172,0.0008625671,0.0010290674,0.0022281522,0.0009753547,0.00061078294,0.0012805875],"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":[0.0006394678,0.00007821586,0.0027073105,0.00027191342,0.000038404934,0.00044391063,0.0009326776,0.04257584,0.019719442,0.67021513,0.007679617,0.25469816],"study_design_scores_gemma":[0.000055233475,0.00017496907,0.0013217647,0.000097659315,0.000027439652,0.00047693378,0.00024809703,0.096435085,0.03204905,0.81793916,0.051095724,0.00007902623],"about_ca_topic_score_codex":0.0017298639,"about_ca_topic_score_gemma":0.0021245426,"teacher_disagreement_score":0.0043450776,"about_ca_system_score_codex":0.00066014635,"about_ca_system_score_gemma":0.0009930417,"threshold_uncertainty_score":0.014535785},"labels":[],"label_agreement":null},{"id":"W122288055","doi":"10.1007/978-3-642-03367-4_21","title":"Efficient Construction of Near-Optimal Binary and Multiway Search Trees","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Binary search tree; Optimal binary search tree; Upper and lower bounds; Binary tree; Binary number; Weight-balanced tree; Random binary tree; Tree (set theory); Search tree; Ternary search tree; Node (physics); Self-balancing binary search tree; Mathematics; Computer science; Search algorithm; Combinatorics; Algorithm; Interval tree; Engineering","score_opus":0.013243371820295748,"score_gpt":0.24605463827257854,"score_spread":0.23281126645228278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W122288055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10232851,0.0018744221,0.8739252,0.00053629675,0.00016469583,0.00019347241,0.0010422786,0.0034717114,0.016463365],"genre_scores_gemma":[0.256336,0.0005706045,0.7344253,0.00015210983,0.00006217579,0.00022363964,0.0015186466,0.00050490146,0.00620662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912614,0.00018097425,0.0000689436,0.00013917549,0.0003446457,0.00014010943],"domain_scores_gemma":[0.99835485,0.0007450997,0.0001060898,0.0004120317,0.0002814594,0.0001005126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058385276,0.00045247498,0.0013767718,0.0012769153,0.0007775227,0.0014977768,0.0015047687,0.0011835542,0.0053844196],"category_scores_gemma":[0.0046948506,0.00069209735,0.0007409888,0.0022373302,0.0006325687,0.0025796082,0.002407362,0.0012481582,0.0017432983],"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":[0.00078662264,0.00029801723,0.0013823858,0.00064522645,0.000055718512,0.0001898737,0.0004369667,0.10890718,0.02935582,0.14924031,0.023788717,0.6849131],"study_design_scores_gemma":[0.00015170504,0.00020899187,0.0009654186,0.00011193839,0.00006225528,0.0004338473,0.0002183107,0.77763784,0.015562034,0.18505594,0.019541608,0.00005007675],"about_ca_topic_score_codex":0.000721874,"about_ca_topic_score_gemma":0.0020751522,"teacher_disagreement_score":0.0053844196,"about_ca_system_score_codex":0.00082895625,"about_ca_system_score_gemma":0.0012448373,"threshold_uncertainty_score":0.018012643},"labels":[],"label_agreement":null},{"id":"W123161494","doi":"","title":"Algorithms and Data Structures: 9th International Workshop, WADS 2005, Waterloo, Canada, August 15-17, 2005, Proceedings (Lecture Notes in Computer Science)","year":2005,"lang":"en","type":"book","venue":"Springer eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Computer science; Operations research; Data science; Regional science; Geography; Engineering","score_opus":0.016800869980371846,"score_gpt":0.24739205018795132,"score_spread":0.2305911802075795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W123161494","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010548197,0.06382586,0.8089899,0.010767239,0.008426656,0.00067510677,0.0056941938,0.022387808,0.06868512],"genre_scores_gemma":[0.026675068,0.04014813,0.49644554,0.0015075346,0.0015568336,0.00058204005,0.017592454,0.005937913,0.40955454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834037,0.00015979788,0.00013707018,0.00027572893,0.00091093517,0.00017605767],"domain_scores_gemma":[0.99740237,0.00042465722,0.000062984844,0.00050189596,0.0013893372,0.00021868237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026048806,0.0023326045,0.0021061322,0.002567664,0.0018087305,0.008035977,0.0037242838,0.0017356896,0.04638428],"category_scores_gemma":[0.004153555,0.0020608697,0.0013320061,0.006233394,0.002163877,0.005569426,0.0022797177,0.0031819528,0.02121705],"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":[0.00015968361,0.0001208547,0.0003015715,0.0004685547,0.000035478566,0.00006761675,0.00029184928,0.0017531577,0.0038184142,0.01935779,0.53029644,0.4433286],"study_design_scores_gemma":[0.00009045641,0.0001023467,0.0012086867,0.00036920418,0.00006354949,0.00049609836,0.00036192778,0.018198388,0.011205438,0.035087604,0.93275416,0.00006216989],"about_ca_topic_score_codex":0.077510074,"about_ca_topic_score_gemma":0.1411008,"teacher_disagreement_score":0.077510074,"about_ca_system_score_codex":0.005297767,"about_ca_system_score_gemma":0.010615948,"threshold_uncertainty_score":0.15517086},"labels":[],"label_agreement":null},{"id":"W124361772","doi":"","title":"A square-covering problem.","year":2007,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Square (algebra); Applied mathematics; Mathematical economics; Geometry","score_opus":0.010201964206524496,"score_gpt":0.24114374877150277,"score_spread":0.23094178456497827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W124361772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26670402,0.004927321,0.5450049,0.014485827,0.0011797566,0.00033328138,0.005117396,0.0019740611,0.1602735],"genre_scores_gemma":[0.79283994,0.0021994258,0.15844235,0.001674207,0.00059013464,0.0002505765,0.0051165647,0.00044930156,0.038437452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987841,0.0003042358,0.00007523925,0.00029970877,0.0003462922,0.00019050122],"domain_scores_gemma":[0.99477226,0.0034287919,0.00023982432,0.0010105709,0.00029292091,0.00025572858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007929285,0.0004790109,0.0008124029,0.00068139704,0.00095389795,0.0025765516,0.0009917524,0.0015593895,0.015759068],"category_scores_gemma":[0.008187809,0.0003450969,0.0007056432,0.0022748692,0.0011126079,0.004385459,0.0020255127,0.0018772662,0.0025004975],"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":[0.0006126223,0.00030665178,0.0020874296,0.00062948355,0.0001522223,0.00065840146,0.0005476871,0.03331702,0.005765615,0.5241034,0.09771122,0.33410823],"study_design_scores_gemma":[0.000097713266,0.00008283601,0.00088612165,0.00008879637,0.00006476636,0.0010721005,0.00038563952,0.09837218,0.005231075,0.8522412,0.041453592,0.000023987312],"about_ca_topic_score_codex":0.0008767546,"about_ca_topic_score_gemma":0.00094470097,"teacher_disagreement_score":0.015759068,"about_ca_system_score_codex":0.00076142815,"about_ca_system_score_gemma":0.0009120244,"threshold_uncertainty_score":0.052719355},"labels":[],"label_agreement":null},{"id":"W1248144726","doi":"10.3233/fi-2015-1228","title":"Simple Linear Comparison of Strings in <i>V</i> -order","year":2015,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Lexicographical order; Simple (philosophy); Order (exchange); Focus (optics); Algorithm; Computer science; Mathematics; Theoretical computer science; Discrete mathematics; Combinatorics; Physics","score_opus":0.05041916041186955,"score_gpt":0.3242366516021957,"score_spread":0.27381749119032617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1248144726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12215501,0.0011943778,0.8509914,0.00040028492,0.00045964858,0.0003020417,0.0012512389,0.0049179625,0.01832802],"genre_scores_gemma":[0.38705105,0.0004606425,0.59792495,0.0002517905,0.00015430916,0.00024482416,0.002400459,0.0008705374,0.010641444],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977842,0.0003596127,0.00030391495,0.0005462522,0.0007709796,0.0002351144],"domain_scores_gemma":[0.99484825,0.0025107455,0.00046766846,0.0009604183,0.0010250501,0.00018799881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008238821,0.0006631173,0.00092478504,0.0016966987,0.00083294493,0.0025556218,0.0013780377,0.0006461781,0.0078038652],"category_scores_gemma":[0.008529906,0.00037263593,0.00057663093,0.00339356,0.0011186107,0.004429055,0.0015879166,0.0009621988,0.0028743723],"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":[0.0015565567,0.00019316144,0.0036096156,0.0009487106,0.00010362315,0.00045249122,0.0006524915,0.014492587,0.05600417,0.12285508,0.009428807,0.7897028],"study_design_scores_gemma":[0.00023019854,0.0016695545,0.0042789066,0.00044088726,0.00015987962,0.0017941734,0.0011425302,0.16326028,0.22892562,0.514264,0.08358623,0.00024773955],"about_ca_topic_score_codex":0.0009644236,"about_ca_topic_score_gemma":0.0014838843,"teacher_disagreement_score":0.0078038652,"about_ca_system_score_codex":0.00086043734,"about_ca_system_score_gemma":0.0014565818,"threshold_uncertainty_score":0.026106477},"labels":[],"label_agreement":null},{"id":"W133997040","doi":"10.1007/978-3-642-40104-6_46","title":"The Greedy Gray Code Algorithm","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Gray code; Computer science; Greedy algorithm; Algorithm; Binary tree; Gray (unit); Binary number; Object (grammar); Binary code; Theoretical computer science; Artificial intelligence; Mathematics; Arithmetic","score_opus":0.013970511928237074,"score_gpt":0.23753943651793286,"score_spread":0.2235689245896958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W133997040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045235157,0.0013026706,0.96759987,0.000391922,0.00022293314,0.000061713305,0.00011203199,0.00090534176,0.024880007],"genre_scores_gemma":[0.12583789,0.0018312898,0.8240201,0.00057195453,0.0002574587,0.00020782345,0.00046722495,0.0005744642,0.04623184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995185,0.00009420496,0.000016163605,0.00008492013,0.00022444082,0.000061657156],"domain_scores_gemma":[0.9995455,0.00015954634,0.000020396197,0.00015551223,0.00009505981,0.000023924773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000424119,0.00065216667,0.00081319263,0.001063905,0.00053528004,0.0013181331,0.0011399504,0.0010857509,0.011013525],"category_scores_gemma":[0.002068791,0.00031924286,0.00047770652,0.0015817273,0.0009297352,0.0012340518,0.001407461,0.0013402585,0.004433119],"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":[0.00018025038,0.000056752124,0.00021006868,0.00012320293,0.000032428787,0.00006657744,0.00004975485,0.060346562,0.005735138,0.212527,0.024886847,0.69578546],"study_design_scores_gemma":[0.00007608719,0.000071933966,0.00030244014,0.00007196567,0.0000360791,0.0003782994,0.000030190904,0.66036654,0.009033184,0.27850077,0.051093474,0.000038926966],"about_ca_topic_score_codex":0.0021317878,"about_ca_topic_score_gemma":0.0021770194,"teacher_disagreement_score":0.011013525,"about_ca_system_score_codex":0.0007150665,"about_ca_system_score_gemma":0.0015852939,"threshold_uncertainty_score":0.036843956},"labels":[],"label_agreement":null},{"id":"W135380274","doi":"10.1007/978-3-642-40273-9_21","title":"Array Range Queries","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Range (aeronautics); Database; Information retrieval; Aerospace engineering; Engineering","score_opus":0.014912736884772312,"score_gpt":0.2317038123007456,"score_spread":0.21679107541597328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W135380274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009121179,0.0066541415,0.64031756,0.0021318314,0.0010173139,0.00036628396,0.006309321,0.01828707,0.31579533],"genre_scores_gemma":[0.18486123,0.010560657,0.4832967,0.0029458955,0.0015268355,0.0007172172,0.022909878,0.0065235184,0.2866581],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986965,0.00015341445,0.00009844871,0.000251892,0.0006708543,0.00012892134],"domain_scores_gemma":[0.99854654,0.00045335214,0.000055562316,0.00062709244,0.00026208925,0.000055236756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062224944,0.0011133013,0.0011966274,0.0017308226,0.00084454095,0.0032070195,0.0016917451,0.0010270199,0.075510524],"category_scores_gemma":[0.0037824125,0.00051517016,0.0007075186,0.0036466003,0.0007640193,0.0062539657,0.0033265373,0.0016592297,0.03966437],"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":[0.0002540341,0.00010945101,0.00032626183,0.0005565563,0.00003366729,0.0001259747,0.00018936074,0.0033100506,0.01170153,0.1799631,0.19739664,0.6060333],"study_design_scores_gemma":[0.00008028625,0.00011605329,0.00036151265,0.00023846587,0.0000632489,0.001244857,0.0002599743,0.03254391,0.029548988,0.31201458,0.6234617,0.0000663016],"about_ca_topic_score_codex":0.00044552112,"about_ca_topic_score_gemma":0.00061312085,"teacher_disagreement_score":0.075510524,"about_ca_system_score_codex":0.00063939893,"about_ca_system_score_gemma":0.0005180486,"threshold_uncertainty_score":0.25260788},"labels":[],"label_agreement":null},{"id":"W136834064","doi":"","title":"Teaching Computational Modeling to Non-Computer Scientists.","year":2004,"lang":"en","type":"article","venue":"International Conference on Cognitive Modelling","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Implementation; Computer science; Focus (optics); Code (set theory); Simple (philosophy); Sample (material); Computational thinking; Software engineering; Theoretical computer science; Mathematics education; Programming language; Computer engineering; Artificial intelligence; Set (abstract data type); Mathematics","score_opus":0.07032030075495373,"score_gpt":0.3232691839808703,"score_spread":0.2529488832259166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W136834064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013794143,0.0079500675,0.6401159,0.03569668,0.0058402163,0.00050059817,0.00089716667,0.004079135,0.29112613],"genre_scores_gemma":[0.14119594,0.029240442,0.49106494,0.013740644,0.0042360546,0.0012596563,0.0020534468,0.0014642052,0.31574473],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948955,0.00010823962,0.000021911648,0.00011584884,0.0001848985,0.000079538186],"domain_scores_gemma":[0.99731976,0.0012053059,0.00016443034,0.00035771256,0.0002890889,0.00066370104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010962088,0.0012874391,0.0006728676,0.0008003577,0.0007938168,0.0032165959,0.0012351825,0.0015944754,0.053923246],"category_scores_gemma":[0.007344818,0.00050514156,0.0007160079,0.00093576463,0.0010135126,0.0037503147,0.0025499505,0.003677099,0.021692183],"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":[0.000058219,0.0006909706,0.0010601832,0.000594159,0.000026646116,0.00019910336,0.0015856787,0.0054265517,0.0029438161,0.19192573,0.39568883,0.39980006],"study_design_scores_gemma":[0.00003592035,0.000110267254,0.0009845396,0.00040699966,0.000011332327,0.00049042434,0.0005640025,0.009050818,0.0022739337,0.37879065,0.60726035,0.000020735562],"about_ca_topic_score_codex":0.0006659187,"about_ca_topic_score_gemma":0.0014847867,"teacher_disagreement_score":0.053923246,"about_ca_system_score_codex":0.0013563696,"about_ca_system_score_gemma":0.0020785301,"threshold_uncertainty_score":0.18039125},"labels":[],"label_agreement":null},{"id":"W138321218","doi":"10.1017/9781009302180.034","title":"Randomized Algorithms","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Algorithms and Data Compression","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":"York University","funders":"","keywords":"Coupon; Computer science; Algorithm; Randomized algorithm","score_opus":0.02124760119569156,"score_gpt":0.2107354347120427,"score_spread":0.18948783351635115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W138321218","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011954211,0.012860803,0.75159204,0.006936586,0.002300912,0.00029560458,0.001099672,0.0032874052,0.22043155],"genre_scores_gemma":[0.040026277,0.018011056,0.65151453,0.007529836,0.0025262304,0.001663667,0.0034072676,0.002869158,0.27245197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972228,0.0008519067,0.00016282122,0.00047675226,0.001118969,0.00016674554],"domain_scores_gemma":[0.99725443,0.0015960404,0.00010065347,0.0006018722,0.00036773508,0.000079322184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024632916,0.0014965251,0.0012068925,0.0011071813,0.0007516619,0.0037187943,0.001955357,0.0018521625,0.07125626],"category_scores_gemma":[0.01107144,0.0006603581,0.0010026471,0.0018059604,0.001667583,0.005356156,0.002328346,0.0047052964,0.044847354],"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":[0.000042375807,0.000057653247,0.00021918032,0.0004925482,0.000042952135,0.00004560869,0.00013391697,0.005572376,0.00062487513,0.4971415,0.21580337,0.27982357],"study_design_scores_gemma":[0.000034215383,0.000050279687,0.00021385575,0.0003799422,0.00001579184,0.00024659288,0.0000540679,0.014160701,0.00080351235,0.46123073,0.52278227,0.000027898468],"about_ca_topic_score_codex":0.00067841803,"about_ca_topic_score_gemma":0.00094958977,"teacher_disagreement_score":0.07125626,"about_ca_system_score_codex":0.0015462972,"about_ca_system_score_gemma":0.0015354172,"threshold_uncertainty_score":0.2383759},"labels":[],"label_agreement":null},{"id":"W143017274","doi":"10.1007/978-3-540-89550-3_11","title":"Fast Skew Partition Recognition","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Skew; Partition (number theory); Combinatorics; Graph partition; Vertex (graph theory); Graph; Time complexity; Induced subgraph; Computer science; Mathematics; Discrete mathematics","score_opus":0.02626673958242408,"score_gpt":0.2395240015017815,"score_spread":0.2132572619193574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W143017274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02842337,0.001124995,0.93152976,0.00016923346,0.00045777738,0.00016908537,0.0010378519,0.016298905,0.020789092],"genre_scores_gemma":[0.1946738,0.0007754772,0.760127,0.00021933625,0.00014243301,0.00017140638,0.005081988,0.0016497768,0.03715875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956983,0.000034876946,0.000024018582,0.00011622722,0.00018313363,0.00007184204],"domain_scores_gemma":[0.99954385,0.000068137924,0.000025767014,0.00019693945,0.00013364368,0.000031645766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025188565,0.0010734724,0.00096380303,0.0013350436,0.00069153094,0.0014656787,0.0011273115,0.000639079,0.029124089],"category_scores_gemma":[0.0008593697,0.00052384136,0.0006402456,0.0016277746,0.00037556014,0.0016030113,0.0018245468,0.0008205124,0.013368418],"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":[0.00021697918,0.000042837484,0.0003727915,0.00009508218,0.000018225386,0.00008214094,0.000038215952,0.004399722,0.03814137,0.006264434,0.019357616,0.93097067],"study_design_scores_gemma":[0.00009057268,0.00039443417,0.00418405,0.00010964355,0.000092360206,0.0022234942,0.00033588923,0.51708055,0.2786097,0.057036325,0.13973364,0.000109413326],"about_ca_topic_score_codex":0.0010718226,"about_ca_topic_score_gemma":0.0026977872,"teacher_disagreement_score":0.029124089,"about_ca_system_score_codex":0.00037190944,"about_ca_system_score_gemma":0.0006771313,"threshold_uncertainty_score":0.09742975},"labels":[],"label_agreement":null},{"id":"W143656656","doi":"","title":"Computing Fréchet Distance with Speed Limits.","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","score_opus":0.013038335154697314,"score_gpt":0.2397514136043584,"score_spread":0.22671307844966107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W143656656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049411844,0.00085439766,0.9447401,0.00048732347,0.0001104634,0.000071979026,0.0001784193,0.0008432767,0.0033022307],"genre_scores_gemma":[0.44032338,0.00060579274,0.55311143,0.00016442484,0.00019031933,0.00021317192,0.0010477782,0.00029256768,0.0040511303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776614,0.00039836523,0.00015839862,0.00065458554,0.00075707503,0.00026537047],"domain_scores_gemma":[0.9950772,0.0030092557,0.00038362958,0.0008740496,0.0004868128,0.00016907211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001752914,0.001115138,0.0016180889,0.002007154,0.0013271448,0.0023779236,0.00239718,0.0024593475,0.0054973294],"category_scores_gemma":[0.017427307,0.00073445705,0.0008949758,0.002790437,0.0019315116,0.010204917,0.0026552924,0.00238334,0.0012079887],"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":[0.0005765074,0.00021455645,0.003278634,0.0003921409,0.00011711011,0.00029680654,0.00030479592,0.4356773,0.008677292,0.27023122,0.008432277,0.27180132],"study_design_scores_gemma":[0.000030969928,0.0000848117,0.00038096667,0.000024793293,0.000015310523,0.0002323046,0.00008957422,0.7576301,0.0046139895,0.23151274,0.0053523495,0.000032080377],"about_ca_topic_score_codex":0.0024214631,"about_ca_topic_score_gemma":0.0019342942,"teacher_disagreement_score":0.0054973294,"about_ca_system_score_codex":0.0021325173,"about_ca_system_score_gemma":0.0013736618,"threshold_uncertainty_score":0.018390417},"labels":[],"label_agreement":null},{"id":"W1479984205","doi":"10.1109/dcc.1994.305931","title":"Highly efficient universal coding with classifying to subdictionaries for text compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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; Parsing; Data compression; Compression ratio; Hash function; String (physics); Compression (physics); Algorithm; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Data mining; Mathematics","score_opus":0.027836320000639934,"score_gpt":0.2304418808840361,"score_spread":0.20260556088339618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1479984205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00626966,0.00040009542,0.9865805,0.00013044091,0.000108159,0.00011174239,0.00020110139,0.00349183,0.002706457],"genre_scores_gemma":[0.073896565,0.0005091899,0.91655165,0.00025914295,0.00017069696,0.00029288055,0.0012287586,0.0006552791,0.0064357817],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993185,0.00011756109,0.00009244863,0.000109682485,0.0002843019,0.00007750168],"domain_scores_gemma":[0.9988593,0.0003943386,0.000068964306,0.00043628248,0.00021623165,0.000024940917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060489646,0.0006777679,0.0005965661,0.0021730359,0.0007000767,0.001106555,0.0012025377,0.0006505669,0.0038899253],"category_scores_gemma":[0.0027692742,0.00031427015,0.00053393503,0.0024108263,0.0009995512,0.0019463254,0.0016100791,0.0011452487,0.002622834],"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":[0.00018546567,0.000072493276,0.00053419336,0.00017436284,0.000029081044,0.00012734864,0.0002922166,0.013531651,0.044164944,0.09988116,0.0139495265,0.8270574],"study_design_scores_gemma":[0.000081419086,0.00021856806,0.0009763318,0.00009488691,0.000058861307,0.0007681693,0.0001421116,0.51587754,0.266862,0.101139896,0.11366221,0.000118021235],"about_ca_topic_score_codex":0.0014434796,"about_ca_topic_score_gemma":0.0018829315,"teacher_disagreement_score":0.0038899253,"about_ca_system_score_codex":0.0008495394,"about_ca_system_score_gemma":0.00077474583,"threshold_uncertainty_score":0.013013065},"labels":[],"label_agreement":null},{"id":"W1480087548","doi":"10.1007/978-3-540-70600-7_5","title":"Fast Structured Motif Search in DNA Sequences","year":2008,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Motif (music); Suffix tree; Computer science; Suffix; Computational biology; Generalized suffix tree; Information retrieval; Theoretical computer science; Biology; Data structure; Programming language; Physics","score_opus":0.04631917222744384,"score_gpt":0.29691647539454136,"score_spread":0.2505973031670975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480087548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034976635,0.0018601791,0.9564682,0.00015471857,0.00015713017,0.00008999748,0.0004250373,0.0019482856,0.0039197486],"genre_scores_gemma":[0.100551136,0.0008577037,0.8886404,0.00009487081,0.00007304514,0.0001641896,0.0014565667,0.00026532452,0.007896716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997396,0.000059344777,0.000015285555,0.00004882639,0.000116585354,0.00002039751],"domain_scores_gemma":[0.9994369,0.00031053412,0.000036527537,0.00008901772,0.00009931837,0.000027594422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003779048,0.00054015446,0.0007906047,0.0008446175,0.00028230873,0.00046590695,0.0011515465,0.0007714329,0.004870874],"category_scores_gemma":[0.0018912716,0.0003751461,0.0004256808,0.001737414,0.00036360134,0.0010437125,0.000686628,0.0006989781,0.0019104752],"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":[0.00052981987,0.000108624256,0.0005674085,0.00070881844,0.000082971645,0.00023229573,0.0001574435,0.1089743,0.05575938,0.06477794,0.014371272,0.75372976],"study_design_scores_gemma":[0.000111194924,0.00030446236,0.00031027067,0.00006306117,0.000025942025,0.000434278,0.00006332803,0.8483802,0.026752362,0.10859371,0.014934424,0.000026751275],"about_ca_topic_score_codex":0.00041035202,"about_ca_topic_score_gemma":0.000954022,"teacher_disagreement_score":0.004870874,"about_ca_system_score_codex":0.00024997478,"about_ca_system_score_gemma":0.00051025965,"threshold_uncertainty_score":0.016294658},"labels":[],"label_agreement":null},{"id":"W1480201994","doi":"10.1007/978-3-642-17517-6_12","title":"Should Static Search Trees Ever Be Unbalanced?","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Tree (set theory); Computer science; Search tree; R-tree; Binary logarithm; Optimal binary search tree; K-ary tree; Running time; Combinatorics; Tree structure; Algorithm; Mathematics; Search algorithm; Interval tree; Binary tree; Statistics","score_opus":0.03550106160354684,"score_gpt":0.288388382224733,"score_spread":0.2528873206211862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480201994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12067375,0.012129117,0.6011597,0.06490701,0.008242345,0.00019743283,0.003046501,0.009022164,0.180622],"genre_scores_gemma":[0.6619639,0.007271592,0.23515975,0.013223048,0.003916855,0.0002789979,0.0037361064,0.004742709,0.06970706],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998467,0.00028616062,0.00008399358,0.00026295663,0.0006441968,0.00025562872],"domain_scores_gemma":[0.988079,0.0058172112,0.0006327695,0.003077023,0.001999246,0.0003947582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022908617,0.0005365044,0.00078518246,0.0008358426,0.0011957227,0.002022132,0.0014274436,0.002025239,0.01575293],"category_scores_gemma":[0.039256897,0.0006678817,0.00027337088,0.002155261,0.0018968316,0.013520633,0.0016392721,0.0018250445,0.0075591253],"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":[0.0005792763,0.00008346468,0.0032370444,0.00042392482,0.000039157032,0.00036111267,0.00045685287,0.008654671,0.0071814023,0.36550796,0.15216674,0.46130833],"study_design_scores_gemma":[0.000064822256,0.00008271765,0.0009496907,0.00023097609,0.000049432925,0.0008165235,0.00037979096,0.02679918,0.0073830667,0.76863474,0.19457082,0.00003820594],"about_ca_topic_score_codex":0.0009888159,"about_ca_topic_score_gemma":0.0019594128,"teacher_disagreement_score":0.01575293,"about_ca_system_score_codex":0.0008605759,"about_ca_system_score_gemma":0.0009709061,"threshold_uncertainty_score":0.05269885},"labels":[],"label_agreement":null},{"id":"W1480443064","doi":"10.1109/isit.1991.695432","title":"Distortion-free Compression Of Musical Scores","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Computer science; Distortion (music); Compression (physics); Musical; Speech recognition; Telecommunications; Materials science; Bandwidth (computing)","score_opus":0.012288941682176983,"score_gpt":0.24017489382018892,"score_spread":0.22788595213801194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480443064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110974036,0.0015647373,0.87619895,0.0003123681,0.00026821397,0.000110231216,0.0003750752,0.001075839,0.00912058],"genre_scores_gemma":[0.5617584,0.0022970163,0.41581413,0.00013543326,0.00034502137,0.00017260193,0.0015396962,0.00024870184,0.017689066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995585,0.00005367258,0.00002992821,0.00004923178,0.00027320502,0.000035439392],"domain_scores_gemma":[0.99916446,0.00032076665,0.000048073012,0.00022544728,0.00021587279,0.000025402347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042082588,0.0005963157,0.0005835073,0.000934674,0.0002370017,0.00075874163,0.0006614525,0.0003900937,0.0022676878],"category_scores_gemma":[0.002917711,0.0001611796,0.00027693968,0.0011295963,0.00042971614,0.0008985329,0.0007354218,0.00045640857,0.0010287032],"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":[0.0010942875,0.00009072252,0.00067468075,0.0003457201,0.000061614606,0.00061279273,0.00025733322,0.052594677,0.16232127,0.031439412,0.005518475,0.744989],"study_design_scores_gemma":[0.0001447744,0.00038293027,0.0029666272,0.000084130894,0.00009272013,0.001853031,0.00017097224,0.5961856,0.3463194,0.024575992,0.027159594,0.0000641702],"about_ca_topic_score_codex":0.00047559128,"about_ca_topic_score_gemma":0.0005566407,"teacher_disagreement_score":0.0022676878,"about_ca_system_score_codex":0.00026555063,"about_ca_system_score_gemma":0.00031545796,"threshold_uncertainty_score":0.007586181},"labels":[],"label_agreement":null},{"id":"W1480727843","doi":"10.1007/11569596_97","title":"Recovering the Lattice of Repetitive Sub-functions","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Lattice (music); Algorithm; Physics","score_opus":0.014731412835415196,"score_gpt":0.2342191281384933,"score_spread":0.2194877153030781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480727843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09891814,0.0003562244,0.8901035,0.0002995458,0.00012509864,0.000031773623,0.00031752855,0.0010749416,0.008773271],"genre_scores_gemma":[0.5415592,0.00056851795,0.43770236,0.00021340142,0.00023335757,0.000069383284,0.0014072203,0.00059641514,0.017650085],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993519,0.00013535639,0.00003034243,0.00009729283,0.00030035138,0.00008477053],"domain_scores_gemma":[0.9983791,0.00054563,0.00010243879,0.000644636,0.00021718892,0.00011090745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005500569,0.000716695,0.0008873072,0.0011533217,0.00051350525,0.0012998193,0.0011115819,0.0010328164,0.0047534667],"category_scores_gemma":[0.0036101784,0.00046465066,0.0005481769,0.0011116215,0.0010534498,0.0020110703,0.0014439959,0.0020107755,0.0024768831],"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":[0.0008492675,0.00019896375,0.0020927882,0.00032844598,0.000076748525,0.00082457135,0.00031819692,0.095521994,0.08017903,0.24947476,0.013825589,0.5563096],"study_design_scores_gemma":[0.000043544955,0.00012104776,0.0006415673,0.000034251887,0.00001858517,0.00082904036,0.00018381445,0.70539916,0.027004745,0.25684366,0.008839194,0.000041464868],"about_ca_topic_score_codex":0.0004551226,"about_ca_topic_score_gemma":0.0007060203,"teacher_disagreement_score":0.0047534667,"about_ca_system_score_codex":0.0002939678,"about_ca_system_score_gemma":0.00044097626,"threshold_uncertainty_score":0.015901923},"labels":[],"label_agreement":null},{"id":"W1480780803","doi":"10.1109/dcc.1997.581951","title":"Linear-time, incremental hierarchy inference for compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":107,"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; Compression (physics); Data compression; Hierarchy; Sequence (biology); Paraphrase; Compression ratio; Artificial intelligence; Algorithm; Data compression ratio; Image compression; Theoretical computer science; Image (mathematics); Image processing","score_opus":0.034545880495914234,"score_gpt":0.27938073763912996,"score_spread":0.24483485714321573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480780803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016893351,0.0013243693,0.9628123,0.0013133232,0.00020441989,0.00018518874,0.0007036836,0.010113962,0.0064494032],"genre_scores_gemma":[0.23780538,0.00052774657,0.7531076,0.00071825605,0.0003278888,0.00029177335,0.0022633562,0.0006434593,0.0043144953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982387,0.00041400958,0.00011721632,0.0003959176,0.00065657625,0.00017760649],"domain_scores_gemma":[0.99392384,0.003379898,0.00024109505,0.0017155692,0.00059621484,0.00014331732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016432969,0.0010369014,0.0010742664,0.0016951567,0.0011175052,0.0016593839,0.0034613835,0.0013963924,0.007610481],"category_scores_gemma":[0.014723052,0.00065226114,0.0009805079,0.002270569,0.0019828556,0.0059408015,0.0026506784,0.003030476,0.0022915942],"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":[0.000551195,0.00023859166,0.001565114,0.0005031733,0.00008918508,0.00022727775,0.0004154968,0.13280068,0.009010643,0.14139113,0.04769071,0.66551685],"study_design_scores_gemma":[0.000064444386,0.000067125606,0.00030238734,0.000040622443,0.000028233742,0.00013721496,0.00006724088,0.8438805,0.006655441,0.14158338,0.007150004,0.000023411863],"about_ca_topic_score_codex":0.008257102,"about_ca_topic_score_gemma":0.017640421,"teacher_disagreement_score":0.008257102,"about_ca_system_score_codex":0.0025494462,"about_ca_system_score_gemma":0.0025196632,"threshold_uncertainty_score":0.025459588},"labels":[],"label_agreement":null},{"id":"W1480850188","doi":"10.1109/ccece.2015.7129477","title":"Performance optimization of big data in mobile networks","year":2015,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Bandwidth (computing); Cache; Service provider; Computer network; Mobile telephony; Transfer (computing); Big data; Data as a service; Data transmission; Service (business); Mobile radio; Data mining","score_opus":0.06008354313924276,"score_gpt":0.2659210519668033,"score_spread":0.20583750882756058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480850188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3521493,0.0034770959,0.63334835,0.0013288178,0.00016021747,0.00011694538,0.00020343575,0.0010981115,0.008117716],"genre_scores_gemma":[0.9657291,0.00031302302,0.0329759,0.000058278878,0.000038438084,0.0000340978,0.00007326929,0.00004118938,0.00073669275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931264,0.0002447913,0.000030470737,0.000083570405,0.00020917293,0.00011933031],"domain_scores_gemma":[0.9982216,0.0011947529,0.00012895788,0.00011105865,0.000252587,0.00009101373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012430327,0.00074460387,0.0006196434,0.0006517153,0.00063447,0.0009089888,0.0007595312,0.00053447706,0.0006867697],"category_scores_gemma":[0.003392296,0.0002171511,0.00020472992,0.0010410348,0.0005880037,0.001291682,0.0007101369,0.00051004713,0.00012288848],"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":[0.00020956875,0.000076082746,0.0011305026,0.000060978382,0.00002667958,0.000046870944,0.000048153575,0.9430551,0.004266687,0.004276746,0.001252185,0.045550488],"study_design_scores_gemma":[0.0000042503257,0.000028957225,0.00014641587,0.0000014656549,0.0000024818564,0.000010192909,0.0000147341825,0.99739045,0.0011186321,0.0011413776,0.00013910714,0.0000020120206],"about_ca_topic_score_codex":0.0029204616,"about_ca_topic_score_gemma":0.0027444712,"teacher_disagreement_score":0.0029204616,"about_ca_system_score_codex":0.0012327031,"about_ca_system_score_gemma":0.0007061528,"threshold_uncertainty_score":0.008943915},"labels":[],"label_agreement":null},{"id":"W1481266406","doi":"10.1002/spe.2327","title":"Stringlish: improved English string searching in binary files","year":2015,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","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":"University of Calgary","funders":"","keywords":"String (physics); Binary number; Computer science; False positive paradox; Theoretical computer science; Mathematics; Artificial intelligence; Physics; Arithmetic; Theoretical physics","score_opus":0.02811363975311193,"score_gpt":0.2985223667986366,"score_spread":0.27040872704552465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1481266406","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07468742,0.0017466948,0.7691192,0.0012637145,0.0007371596,0.00032824714,0.005895691,0.1326106,0.013611259],"genre_scores_gemma":[0.27286747,0.00065316993,0.6752903,0.0011792111,0.00045322374,0.00031867527,0.013352912,0.01184509,0.024040002],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978404,0.00031463947,0.00029321498,0.0004073992,0.0009696737,0.00017462808],"domain_scores_gemma":[0.994785,0.0018673798,0.0004013405,0.0014120033,0.0012896869,0.00024469756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015532544,0.0008734551,0.0009401754,0.0028367185,0.0008203681,0.001584725,0.0015973145,0.00083389593,0.023105372],"category_scores_gemma":[0.009509587,0.00037104447,0.0006229013,0.0033825517,0.00071904424,0.0033294032,0.0022211126,0.00091641763,0.010455565],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001064314,0.00018239845,0.0043418854,0.0006655796,0.00008664674,0.0006753311,0.00046408898,0.003928918,0.055806827,0.01223436,0.09554522,0.82500434],"study_design_scores_gemma":[0.000440189,0.0009940666,0.010600905,0.0003798519,0.00020048216,0.00406007,0.00066485966,0.2904367,0.35064209,0.048109937,0.29308683,0.0003839386],"about_ca_topic_score_codex":0.0016273151,"about_ca_topic_score_gemma":0.0021850243,"teacher_disagreement_score":0.023105372,"about_ca_system_score_codex":0.0004457556,"about_ca_system_score_gemma":0.0010786133,"threshold_uncertainty_score":0.077295184},"labels":[],"label_agreement":null},{"id":"W1482000113","doi":"10.1007/978-3-540-89097-3_26","title":"On the Structure of Small Motif Recognition Instances","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hamming distance; Sequence (biology); Cardinality (data modeling); Degeneracy (biology); Combinatorics; Pairwise comparison; Consensus sequence; Computer science; Algorithm; Mathematics; Artificial intelligence; Data mining; Genetics; Base sequence; DNA","score_opus":0.02696922047178994,"score_gpt":0.22526910068021222,"score_spread":0.1982998802084223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482000113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30077153,0.002224039,0.6643714,0.0014644157,0.000183673,0.00015661826,0.0031162726,0.0019824505,0.025729587],"genre_scores_gemma":[0.7648369,0.0010208255,0.20774423,0.00035633484,0.00028353382,0.00022465014,0.008495694,0.00074535015,0.016292414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995208,0.000088142464,0.00003790855,0.00018058221,0.00011237644,0.00006019909],"domain_scores_gemma":[0.99488586,0.0030847983,0.0005394523,0.00082144904,0.00040668537,0.00026165566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003506112,0.00049332017,0.0010872275,0.0014448803,0.00083913526,0.0018401843,0.0018456717,0.0011382928,0.008395767],"category_scores_gemma":[0.0071969316,0.0005554132,0.00052198296,0.0025434315,0.0010928815,0.0039033901,0.0013457246,0.0018988983,0.0014607892],"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":[0.00053515687,0.00020598486,0.007687328,0.00057676743,0.00008494486,0.0007386193,0.00079652254,0.06906575,0.012044898,0.5275977,0.02832731,0.35233894],"study_design_scores_gemma":[0.00002919389,0.0000865545,0.0014619507,0.000060517286,0.000026259157,0.0004769739,0.00013028683,0.27811578,0.002420352,0.7095203,0.0076485337,0.000023368768],"about_ca_topic_score_codex":0.0009303719,"about_ca_topic_score_gemma":0.0016614516,"teacher_disagreement_score":0.008395767,"about_ca_system_score_codex":0.00056721433,"about_ca_system_score_gemma":0.00042058885,"threshold_uncertainty_score":0.028086603},"labels":[],"label_agreement":null},{"id":"W1482525343","doi":"10.1007/11496656_25","title":"A Simple Fast Hybrid Pattern-Matching Algorithm","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University","funders":"","keywords":"Computer science; Alphabet; Algorithm; Simple (philosophy); Pattern matching; Matching (statistics); SIMPLE algorithm; Independence (probability theory); String searching algorithm; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.011466572529676733,"score_gpt":0.24155032637219173,"score_spread":0.230083753842515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482525343","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069330367,0.00031831273,0.98376036,0.00008486368,0.00019300768,0.00015270582,0.00023727678,0.004429873,0.0038906725],"genre_scores_gemma":[0.036747217,0.00017549923,0.9496357,0.0001337942,0.00006339391,0.00019586345,0.0008531422,0.00035158894,0.011843843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992161,0.0000750163,0.000055210683,0.00020039557,0.00038237544,0.00007090477],"domain_scores_gemma":[0.9993699,0.00012774408,0.000028557646,0.00021886689,0.00022080721,0.000034156932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005313306,0.0010414881,0.001333276,0.0017181687,0.00079056213,0.0011514396,0.0027039999,0.0012640096,0.022353893],"category_scores_gemma":[0.0014514261,0.0005814346,0.00080932735,0.0029238139,0.0003498031,0.002115506,0.00203343,0.00079453614,0.012011124],"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":[0.00031006025,0.00011618359,0.0003480746,0.00017322467,0.00007581878,0.00009492345,0.000025345977,0.006459826,0.036739998,0.0074836663,0.011525883,0.9366471],"study_design_scores_gemma":[0.00046073002,0.00061568344,0.0022377667,0.000067389934,0.00029088388,0.0022038247,0.00011431774,0.72018915,0.12047685,0.064218864,0.08899068,0.00013374918],"about_ca_topic_score_codex":0.0012866956,"about_ca_topic_score_gemma":0.0020125457,"teacher_disagreement_score":0.022353893,"about_ca_system_score_codex":0.00037677848,"about_ca_system_score_gemma":0.0009256675,"threshold_uncertainty_score":0.07478118},"labels":[],"label_agreement":null},{"id":"W1484399819","doi":"10.1089/cmb.2005.12.129","title":"More Reliable Protein NMR Peak Assignment via Improved 2-Interval Scheduling","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scheduling (production processes); Subsequence; Job shop scheduling; Computer science; Interval (graph theory); Combinatorics; Mathematical optimization; Algorithm; Mathematics; Schedule","score_opus":0.012112642861767222,"score_gpt":0.2743904457364027,"score_spread":0.2622778028746355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484399819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061925776,0.0005049661,0.931424,0.00032866906,0.00028484012,0.00012913227,0.00024610106,0.0018856225,0.0032709527],"genre_scores_gemma":[0.34588528,0.00027603505,0.64849573,0.00024231021,0.0001978295,0.00021855441,0.0011164312,0.0005158044,0.00305199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982528,0.000372356,0.000085508036,0.0004692331,0.00047352418,0.00034651518],"domain_scores_gemma":[0.9974935,0.00093078933,0.00025243356,0.000573662,0.00041039928,0.00033920238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018783564,0.0012253871,0.0018857805,0.0009444823,0.00081666646,0.0013479751,0.002853032,0.0010160872,0.004155962],"category_scores_gemma":[0.0045032385,0.0005170218,0.0010229528,0.0016169247,0.00057318626,0.0016849074,0.0013328805,0.0020251146,0.0012898443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001015401,0.0006720181,0.0013257302,0.00021500827,0.0000661595,0.0002577045,0.00025575754,0.79631186,0.029085523,0.021897875,0.010818654,0.13807832],"study_design_scores_gemma":[0.000049123795,0.00007763553,0.00015528475,0.0000037851748,0.0000067855935,0.00002689473,0.000014774231,0.99183804,0.0018175374,0.0048904154,0.001106988,0.000012728267],"about_ca_topic_score_codex":0.004414738,"about_ca_topic_score_gemma":0.0039931447,"teacher_disagreement_score":0.004414738,"about_ca_system_score_codex":0.0013404557,"about_ca_system_score_gemma":0.0025957292,"threshold_uncertainty_score":0.013903081},"labels":[],"label_agreement":null},{"id":"W1484834310","doi":"10.1007/978-3-540-68083-3_24","title":"Protein Sequence Motif Discovery on Distributed Supercomputer","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; De Bruijn graph; De Bruijn sequence; Motif (music); Probabilistic logic; Supercomputer; Parallel computing; Massively parallel; Multi-core processor; Theoretical computer science; Graph; Distributed computing; Artificial intelligence; Mathematics","score_opus":0.023561479120725953,"score_gpt":0.2429333179217539,"score_spread":0.21937183880102795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484834310","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68471754,0.0024446608,0.29392603,0.00063285016,0.00016176848,0.00014117289,0.0016297902,0.0070340796,0.009312032],"genre_scores_gemma":[0.6060336,0.0009882607,0.3786158,0.00011480912,0.00010848989,0.00013584705,0.004342198,0.00043230358,0.009228662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966276,0.0000514915,0.000019346326,0.0000984813,0.00013084857,0.000037091013],"domain_scores_gemma":[0.99937856,0.00020701815,0.000044333698,0.00015769956,0.00014956247,0.0000628955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046995006,0.00039269956,0.0007502028,0.001034937,0.0005497765,0.0006999476,0.0011389289,0.00052366685,0.00226851],"category_scores_gemma":[0.0013457207,0.0003327765,0.000402675,0.0028184808,0.00022510813,0.00091658096,0.00058756286,0.0006241133,0.0008947405],"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":[0.0013136914,0.0004156994,0.016126582,0.00038882188,0.00021077796,0.0006999228,0.00027957023,0.058164008,0.1913574,0.0071813376,0.01850319,0.705359],"study_design_scores_gemma":[0.00012873352,0.00024299603,0.006959474,0.000023364677,0.00007857076,0.0007374208,0.0002502996,0.8535189,0.10377817,0.021400932,0.012853325,0.000027834973],"about_ca_topic_score_codex":0.0011354862,"about_ca_topic_score_gemma":0.0028532315,"teacher_disagreement_score":0.00226851,"about_ca_system_score_codex":0.0003399103,"about_ca_system_score_gemma":0.00048246142,"threshold_uncertainty_score":0.0075889826},"labels":[],"label_agreement":null},{"id":"W1485068757","doi":"10.1109/pacrim.2003.1235900","title":"Distributed multidimensional suffix arrays for string search","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Lethbridge","funders":"","keywords":"Suffix; Computer science; Pointer (user interface); Suffix tree; Generalized suffix tree; Compressed suffix array; Data structure; String (physics); String searching algorithm; Theoretical computer science; Suffix array; Algorithm; Artificial intelligence; Mathematics; Programming language","score_opus":0.02673894112890789,"score_gpt":0.276574704709041,"score_spread":0.2498357635801331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485068757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009292377,0.001711147,0.97963834,0.00036637034,0.00016363038,0.00006837425,0.00034901188,0.003242339,0.00516834],"genre_scores_gemma":[0.07995137,0.0010582752,0.91294193,0.00017750643,0.00018301101,0.00021916673,0.0010415564,0.0002503163,0.004176887],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993001,0.00017892479,0.000072371404,0.00012324042,0.00028864594,0.000036623056],"domain_scores_gemma":[0.9979639,0.000632056,0.00014062716,0.0006647428,0.0005377563,0.000060970793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053961517,0.0003882887,0.0005992045,0.0010480678,0.00069810165,0.001308903,0.00117672,0.0007392171,0.005412837],"category_scores_gemma":[0.0040083225,0.00022634394,0.00036167953,0.0030107698,0.00045926872,0.00274752,0.00091806456,0.0009100474,0.0030970103],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033795854,0.000083021994,0.00091602496,0.00032128344,0.000050894134,0.00014673587,0.0002094171,0.033442426,0.034443438,0.1425528,0.019681048,0.76781493],"study_design_scores_gemma":[0.00018754682,0.00038286415,0.0008871128,0.0001315329,0.00007381022,0.00081231474,0.0002309543,0.5239243,0.07886556,0.21134782,0.18307278,0.00008346518],"about_ca_topic_score_codex":0.0007407456,"about_ca_topic_score_gemma":0.0012361641,"teacher_disagreement_score":0.005412837,"about_ca_system_score_codex":0.0005814673,"about_ca_system_score_gemma":0.0009800933,"threshold_uncertainty_score":0.018107772},"labels":[],"label_agreement":null},{"id":"W1489137","doi":"10.1007/978-3-319-05290-8_7","title":"Lossless Compression Algorithms","year":2014,"lang":"en","type":"book-chapter","venue":"Texts in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Lossless compression; Lossy compression; Huffman coding; Entropy encoding; Arithmetic coding; Data compression; Computer science; Tunstall coding; Adaptive coding; Algorithm; Context-adaptive binary arithmetic coding; Lossless JPEG; Data compression ratio; Shannon–Fano coding; Image compression; Theoretical computer science; Coding (social sciences); Mathematics; Artificial intelligence; Image processing; Image (mathematics)","score_opus":0.020990245588252184,"score_gpt":0.26106665215835995,"score_spread":0.24007640657010776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028089285,0.02674926,0.8077215,0.0014417528,0.0019998616,0.00016972056,0.00084149797,0.003508595,0.15475887],"genre_scores_gemma":[0.063163884,0.042909414,0.47871011,0.0021102328,0.0035784654,0.00040802886,0.0044174353,0.0022308438,0.40247154],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992786,0.000055087068,0.00003592835,0.0001125928,0.00047861866,0.000039094517],"domain_scores_gemma":[0.99937457,0.00020836598,0.00002755641,0.00022555425,0.00014560626,0.000018459788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004859558,0.0014531099,0.000881138,0.0022180385,0.000551559,0.0020961103,0.001442548,0.0011967659,0.03362418],"category_scores_gemma":[0.0018224161,0.0005190579,0.00048747432,0.0027246536,0.0012449517,0.0031008832,0.0013649195,0.0026519394,0.02435472],"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":[0.000051201692,0.000051669896,0.00006278408,0.00038553958,0.000023563145,0.0000572765,0.00006451756,0.0057562725,0.008242316,0.113236286,0.068492375,0.8035762],"study_design_scores_gemma":[0.00004114966,0.0001253962,0.0005155905,0.00045481397,0.000048832797,0.001467226,0.00005476858,0.06325222,0.05011945,0.25007057,0.6337734,0.000076640215],"about_ca_topic_score_codex":0.00027621372,"about_ca_topic_score_gemma":0.00033825648,"teacher_disagreement_score":0.03362418,"about_ca_system_score_codex":0.00064897817,"about_ca_system_score_gemma":0.000530372,"threshold_uncertainty_score":0.11248404},"labels":[],"label_agreement":null},{"id":"W1490473477","doi":"10.1007/3-540-44808-x_7","title":"Experiments on Adaptive Set Intersections for Text Retrieval Systems","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Waterloo","funders":"","keywords":"Computer science; Intersection (aeronautics); Set (abstract data type); Factor (programming language); Algorithm; Measure (data warehouse); Theoretical computer science; Data mining","score_opus":0.043217197523913974,"score_gpt":0.2900568023509737,"score_spread":0.24683960482705972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490473477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.959784,0.0025227244,0.027315294,0.00027065066,0.00027534176,0.0005778678,0.0014120252,0.0028634798,0.0049785855],"genre_scores_gemma":[0.919875,0.00088547735,0.06724279,0.000113118476,0.00017703578,0.0004634462,0.0052059344,0.00054366613,0.005493484],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931298,0.0028383282,0.0010148168,0.0007659954,0.0017580012,0.0004930826],"domain_scores_gemma":[0.9465094,0.04186928,0.0011426976,0.0040924177,0.0055216504,0.00086453656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004561859,0.001265812,0.0026195229,0.0020942308,0.0018740678,0.0017790393,0.0025439675,0.0016927763,0.009762547],"category_scores_gemma":[0.032764133,0.00084754033,0.00096379296,0.0033761968,0.00090538786,0.0042460645,0.0020023335,0.0013972424,0.0026761924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04886555,0.012780968,0.009982395,0.00494097,0.001219194,0.00070712395,0.002297622,0.22039334,0.112304054,0.007156982,0.018400805,0.560951],"study_design_scores_gemma":[0.0035757555,0.016309178,0.0083718235,0.00013090327,0.00096646225,0.0006834763,0.0015343418,0.799854,0.1497308,0.0076043634,0.0109937815,0.0002450846],"about_ca_topic_score_codex":0.005319709,"about_ca_topic_score_gemma":0.0028728081,"teacher_disagreement_score":0.009762547,"about_ca_system_score_codex":0.0012258033,"about_ca_system_score_gemma":0.0011762505,"threshold_uncertainty_score":0.032658994},"labels":[],"label_agreement":null},{"id":"W1491300721","doi":"10.1007/11821069_25","title":"The Lempel-Ziv Complexity of Fixed Points of Morphisms","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Morphism; Combinatorics on words; Measure (data warehouse); Word (group theory); Complexity class; Mathematics; Fixed point; Discrete mathematics; Time complexity; Computational complexity theory; Function (biology); Combinatorics; Computer science; Algorithm; Data mining","score_opus":0.025591890400312532,"score_gpt":0.2466015201112427,"score_spread":0.22100962971093016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1491300721","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55161256,0.0097228475,0.17685746,0.00877289,0.00048292073,0.00009820201,0.0015298498,0.0005602336,0.250363],"genre_scores_gemma":[0.959754,0.003056799,0.015287545,0.0003947699,0.0005997872,0.00015757841,0.00081655587,0.00017351571,0.019759493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820876,0.00036020996,0.000091726826,0.0003171686,0.00074744225,0.00027466647],"domain_scores_gemma":[0.9943962,0.0039761406,0.00035794912,0.0005607089,0.00037913636,0.0003298681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001538823,0.0009053887,0.00183325,0.0043407576,0.0025220672,0.006656431,0.002244843,0.0021441723,0.010432142],"category_scores_gemma":[0.011002612,0.0009488455,0.0011984702,0.005162128,0.005827983,0.015409873,0.003880707,0.0056211906,0.0013361711],"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":[0.00005428115,0.0000145767135,0.00029678064,0.000051581937,0.000011666389,0.000039890692,0.00019727382,0.0024281475,0.00031366586,0.9883406,0.0012572316,0.006994188],"study_design_scores_gemma":[0.000010541767,0.0000068134004,0.00022398638,0.000014978043,0.000008060869,0.000033403216,0.000039291433,0.003710996,0.00022087245,0.9942713,0.0014475847,0.000012235943],"about_ca_topic_score_codex":0.0018409649,"about_ca_topic_score_gemma":0.0012150013,"teacher_disagreement_score":0.010432142,"about_ca_system_score_codex":0.004460225,"about_ca_system_score_gemma":0.0010485442,"threshold_uncertainty_score":0.034899056},"labels":[],"label_agreement":null},{"id":"W149246287","doi":"10.1007/978-3-642-22300-6_42","title":"Space Efficient Data Structures for Dynamic Orthogonal Range Counting","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Integer (computer science); Computer science; Sequence (biology); Range (aeronautics); Space (punctuation); Data structure; Set (abstract data type); Grid; Plane (geometry); Algorithm; Linear space; Combinatorics; Discrete mathematics; Mathematics; Geometry","score_opus":0.0301063962871892,"score_gpt":0.2689048071365918,"score_spread":0.23879841084940262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W149246287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02110922,0.002141143,0.95085764,0.0004509342,0.00027331637,0.00018636105,0.0011871032,0.004874255,0.018919999],"genre_scores_gemma":[0.22805004,0.0015948204,0.7456658,0.0004502419,0.00035847153,0.00076089776,0.003673879,0.0014478001,0.017998131],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99741745,0.00034035774,0.00030966292,0.00033647523,0.001269923,0.0003262555],"domain_scores_gemma":[0.9965249,0.0010026749,0.00022447201,0.0015788549,0.00057629205,0.000092750524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010122147,0.0009937609,0.0014698957,0.002489063,0.0013201224,0.0036389853,0.0024980914,0.00088257686,0.011050576],"category_scores_gemma":[0.00570896,0.0007417794,0.0009674638,0.006783822,0.001346983,0.0070325597,0.004531976,0.0023694816,0.003784632],"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":[0.00037992757,0.00018929369,0.00052061945,0.00035038576,0.00003806916,0.00008732903,0.0002696275,0.014177061,0.0125576975,0.4520379,0.02528641,0.49410555],"study_design_scores_gemma":[0.00011290827,0.00021020383,0.00034966526,0.0001751356,0.00006260096,0.0004328262,0.00022224573,0.14002798,0.02948373,0.76101756,0.06780238,0.00010284141],"about_ca_topic_score_codex":0.000899572,"about_ca_topic_score_gemma":0.001628914,"teacher_disagreement_score":0.011050576,"about_ca_system_score_codex":0.0012750324,"about_ca_system_score_gemma":0.0014716141,"threshold_uncertainty_score":0.036967874},"labels":[],"label_agreement":null},{"id":"W1492505833","doi":"10.1016/j.ipl.2016.07.001","title":"Palindromic rich words and run-length encodings","year":2016,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Palindrome; Upper and lower bounds; Integer (computer science); Function (biology); Combinatorics; Binary number; Word (group theory); Word length; Mathematics; Order (exchange); Discrete mathematics; Computer science; Arithmetic; Natural language processing; Geometry","score_opus":0.0070363417484431085,"score_gpt":0.20831222670602956,"score_spread":0.20127588495758644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492505833","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20494011,0.0023319025,0.749554,0.001507967,0.0003878758,0.00009674901,0.0007636806,0.0018953136,0.0385224],"genre_scores_gemma":[0.76861644,0.0015222399,0.20083152,0.0005803893,0.0005547353,0.00018483444,0.0012552673,0.000798959,0.02565568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992218,0.00025010182,0.000077472454,0.00012751484,0.0002181714,0.00010488204],"domain_scores_gemma":[0.99754673,0.0011746077,0.0002539979,0.00075032,0.00021287141,0.00006151822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005960768,0.0005270779,0.0004793313,0.0010423497,0.0005176883,0.0014110752,0.0007485806,0.00090348255,0.0053799143],"category_scores_gemma":[0.0042441534,0.000305681,0.0003931408,0.0013157198,0.0010116006,0.0024157637,0.0012807809,0.0012726597,0.0021780056],"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":[0.00055460585,0.00007126434,0.00052951253,0.00019440298,0.000026050946,0.0006742512,0.0003658858,0.021284744,0.024999753,0.7939263,0.004508789,0.15286441],"study_design_scores_gemma":[0.000039817958,0.00013818471,0.0004019836,0.00009617672,0.000042854517,0.00095027545,0.00015203217,0.09530105,0.028164137,0.85997623,0.014676945,0.000060381208],"about_ca_topic_score_codex":0.000250906,"about_ca_topic_score_gemma":0.00033764483,"teacher_disagreement_score":0.0053799143,"about_ca_system_score_codex":0.00039770358,"about_ca_system_score_gemma":0.00037176037,"threshold_uncertainty_score":0.017997622},"labels":[],"label_agreement":null},{"id":"W1492872125","doi":"","title":"An asymptotic lower bound for the maximal-number-of-runs function.","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Upper and lower bounds; Combinatorics; Sequence (biology); Mathematics; Function (biology); String (physics); Binary number; Discrete mathematics; Mathematical analysis; Arithmetic; Mathematical physics","score_opus":0.011723054998973347,"score_gpt":0.25460319210618954,"score_spread":0.24288013710721618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492872125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061117835,0.016067883,0.82429105,0.007381945,0.00080230756,0.00021565684,0.0014469549,0.0049059377,0.083770536],"genre_scores_gemma":[0.65864885,0.006274638,0.2967778,0.004557278,0.0021905694,0.0011308339,0.0033446471,0.0027459003,0.024329392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99102485,0.0021676717,0.00037792663,0.0013278885,0.0035213826,0.0015802637],"domain_scores_gemma":[0.9460866,0.039740864,0.001832788,0.0062468634,0.0039438223,0.00214911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010155004,0.0026739775,0.002511123,0.00461808,0.0022868423,0.0042942837,0.005372703,0.0034391088,0.013298043],"category_scores_gemma":[0.06705324,0.000918292,0.002124217,0.0032395378,0.0041970355,0.014575214,0.005786481,0.0074549676,0.0053005344],"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":[0.0022878642,0.0006169618,0.009026881,0.0012443955,0.00021939985,0.0005812808,0.00058293564,0.08326225,0.021090457,0.63087726,0.041076824,0.20913349],"study_design_scores_gemma":[0.00008255705,0.00036407768,0.0033708904,0.0005274335,0.00019681046,0.0017199009,0.00015729918,0.44334042,0.018880999,0.50293064,0.028297024,0.0001319102],"about_ca_topic_score_codex":0.0011007054,"about_ca_topic_score_gemma":0.0015046692,"teacher_disagreement_score":0.013298043,"about_ca_system_score_codex":0.0053861155,"about_ca_system_score_gemma":0.0031944243,"threshold_uncertainty_score":0.053705454},"labels":[],"label_agreement":null},{"id":"W1493085632","doi":"10.1007/978-3-540-92182-0_34","title":"Evaluation of General Set Expressions","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Concordia University","funders":"","keywords":"Computer science; Set (abstract data type); Algorithm; Programming language","score_opus":0.049047617759110235,"score_gpt":0.29884758397342837,"score_spread":0.24979996621431813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493085632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090045415,0.002025009,0.8029104,0.00087110914,0.00042705727,0.00031771118,0.00087928376,0.006170833,0.096353136],"genre_scores_gemma":[0.637583,0.0011204713,0.31377813,0.00042016633,0.00028526643,0.00024501423,0.0023526426,0.0027260801,0.04148928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596393,0.00087625335,0.0002111236,0.00049088435,0.0020650697,0.00039280838],"domain_scores_gemma":[0.9961647,0.0017675204,0.00015198418,0.00083976786,0.00094819465,0.00012775706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026891131,0.00083080307,0.0010745663,0.0012378508,0.0008061167,0.0027630816,0.001892651,0.00087250804,0.013273789],"category_scores_gemma":[0.008771821,0.00047309586,0.0011575829,0.0016970905,0.0018765829,0.0051378,0.002886965,0.0014218031,0.0024713485],"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":[0.00074156787,0.00011805096,0.0011047722,0.00065983937,0.00008487587,0.00025638484,0.0005086015,0.024441388,0.018545337,0.6359809,0.016552025,0.3010062],"study_design_scores_gemma":[0.000080154496,0.00023329482,0.00078912615,0.00016906002,0.00013296682,0.00038230236,0.00024155376,0.16690657,0.03996165,0.7378844,0.053157445,0.000061482264],"about_ca_topic_score_codex":0.0010830351,"about_ca_topic_score_gemma":0.0016229731,"teacher_disagreement_score":0.013273789,"about_ca_system_score_codex":0.001983164,"about_ca_system_score_gemma":0.0011075083,"threshold_uncertainty_score":0.044405222},"labels":[],"label_agreement":null},{"id":"W1494010234","doi":"10.1007/978-3-642-02927-1_37","title":"Dynamic Succinct Ordered Trees","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Theoretical computer science; Programming language","score_opus":0.0100627812561948,"score_gpt":0.24065924692145846,"score_spread":0.23059646566526365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494010234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03928866,0.0028557058,0.7770325,0.001710688,0.00069003046,0.00019695576,0.004148273,0.0037172362,0.17035988],"genre_scores_gemma":[0.39755446,0.004882364,0.43498987,0.00070843706,0.00042315558,0.00027182145,0.010888156,0.0021646852,0.14811705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995078,0.00005860295,0.000030215908,0.000075067124,0.0002718221,0.00005643498],"domain_scores_gemma":[0.9989856,0.00034082978,0.00005101136,0.00038200954,0.00017714186,0.00006349549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045270624,0.00048838963,0.00050018565,0.0010565902,0.0006214251,0.0016433399,0.0010510124,0.00056225393,0.020449433],"category_scores_gemma":[0.002333517,0.0004922225,0.00035128635,0.002239635,0.00081533805,0.0049614967,0.0018791651,0.0017674682,0.004755322],"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":[0.00020800253,0.000090044785,0.00026099986,0.00028207657,0.000016430087,0.00019887794,0.00030267966,0.014607838,0.008242133,0.6141301,0.037389282,0.32427156],"study_design_scores_gemma":[0.000040844585,0.00005713359,0.0002671524,0.0001597385,0.000024669453,0.0005105573,0.00015836713,0.056397174,0.011471694,0.76427555,0.16660528,0.00003183708],"about_ca_topic_score_codex":0.00067224714,"about_ca_topic_score_gemma":0.0014951804,"teacher_disagreement_score":0.020449433,"about_ca_system_score_codex":0.0008948722,"about_ca_system_score_gemma":0.0007027076,"threshold_uncertainty_score":0.06841016},"labels":[],"label_agreement":null},{"id":"W1494877715","doi":"10.1007/978-3-642-02011-7_14","title":"An Application of Self-organizing Data Structures to Compression","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Locality of reference; Data compression; Locality; Compression (physics); Algorithm; Subroutine; Construct (python library); Lossless compression; Theoretical computer science; Cache; Parallel computing; Programming language","score_opus":0.01986597128195474,"score_gpt":0.2784942480151792,"score_spread":0.25862827673322447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494877715","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012079518,0.001847345,0.9739102,0.00025413634,0.00026859785,0.0000671293,0.00006805605,0.0012173853,0.010287679],"genre_scores_gemma":[0.19155896,0.002690765,0.79205173,0.00018610417,0.00047592394,0.00015529816,0.00020646703,0.00025204231,0.012422686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996557,0.00006450034,0.000026928365,0.000051391893,0.00018016585,0.000021231468],"domain_scores_gemma":[0.99916315,0.00043481472,0.000036646616,0.00020528902,0.0001369459,0.00002313443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003822901,0.00040642582,0.00048269486,0.0012902779,0.0005409056,0.0010769407,0.0008589055,0.00066889,0.0038828496],"category_scores_gemma":[0.0019540202,0.00032944183,0.00046428276,0.0023211397,0.0010135893,0.0014415481,0.0008480671,0.00070239964,0.0008287702],"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":[0.00012774656,0.0000934719,0.00030717163,0.00027383096,0.00003904616,0.00022201553,0.0002778995,0.043375175,0.023549557,0.32102242,0.007946767,0.60276496],"study_design_scores_gemma":[0.00005455936,0.0001855663,0.0005286325,0.00007440409,0.000045724202,0.0011393883,0.000120714256,0.59881014,0.034560617,0.3115,0.05293134,0.0000489471],"about_ca_topic_score_codex":0.00058098696,"about_ca_topic_score_gemma":0.00050300395,"teacher_disagreement_score":0.0038828496,"about_ca_system_score_codex":0.00038585975,"about_ca_system_score_gemma":0.00029405413,"threshold_uncertainty_score":0.012989461},"labels":[],"label_agreement":null},{"id":"W1495731517","doi":"10.1007/978-3-642-03367-4_9","title":"Succinct Orthogonal Range Search Structures on a Grid with Applications to Text Indexing","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Carleton University","funders":"","keywords":"Search engine indexing; Substring; Range (aeronautics); Computer science; Grid; Combinatorics; Set (abstract data type); Key (lock); Data structure; Space (punctuation); Representation (politics); Mathematics; Information retrieval","score_opus":0.018884239051182312,"score_gpt":0.2678463420359224,"score_spread":0.24896210298474009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1495731517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0342129,0.0010022849,0.94322103,0.0005492092,0.00020349356,0.00024957175,0.0017951558,0.007813679,0.010952719],"genre_scores_gemma":[0.19340934,0.0006652301,0.79268026,0.00014906615,0.00013268844,0.00037219585,0.0029774334,0.0008018484,0.008811897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.00025323554,0.000202048,0.00016086671,0.00047887402,0.00014161161],"domain_scores_gemma":[0.9954194,0.0015570464,0.00030511545,0.001922339,0.00064785365,0.00014827008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010201859,0.0005260582,0.0016787337,0.0018985603,0.0010050528,0.002257263,0.0020422505,0.00080422044,0.009973122],"category_scores_gemma":[0.0062709334,0.000573892,0.0006186598,0.007627224,0.0010309588,0.0051625487,0.0037929902,0.0013035913,0.00275432],"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":[0.0009567902,0.00036858785,0.0012857792,0.00046219016,0.000038732305,0.00025242346,0.0003883389,0.08060538,0.010117383,0.26805788,0.037795242,0.5996713],"study_design_scores_gemma":[0.00026850562,0.00027383014,0.00043104062,0.000090167676,0.000044244887,0.00036355355,0.00022626552,0.57203007,0.010807816,0.3824392,0.03295009,0.00007523438],"about_ca_topic_score_codex":0.0026967637,"about_ca_topic_score_gemma":0.004182125,"teacher_disagreement_score":0.009973122,"about_ca_system_score_codex":0.000851098,"about_ca_system_score_gemma":0.0014051895,"threshold_uncertainty_score":0.033363402},"labels":[],"label_agreement":null},{"id":"W1500816613","doi":"10.1007/s11390-010-9361-x","title":"A New Approach for Multi-Document Update Summarization","year":2010,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; NIST; Multi-document summarization; Information retrieval; Set (abstract data type); The Internet; Data mining; World Wide Web; Natural language processing","score_opus":0.013781065863221347,"score_gpt":0.268831526655241,"score_spread":0.25505046079201965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500816613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028628695,0.000933682,0.9910595,0.00021007074,0.0004308325,0.0001790607,0.00029584122,0.0028553996,0.0011726681],"genre_scores_gemma":[0.032798313,0.0007759003,0.9544558,0.0001985409,0.00072630926,0.00024708672,0.0013070102,0.0003358734,0.009155205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975706,0.00032387002,0.00030931373,0.00053868076,0.0011333313,0.00012419926],"domain_scores_gemma":[0.99737716,0.00062985957,0.00013381976,0.0005452137,0.0012232203,0.00009068014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012770559,0.0014615156,0.0017657804,0.004232118,0.0013017228,0.0025910127,0.0017374486,0.0013871018,0.0060694884],"category_scores_gemma":[0.0037997316,0.00055211596,0.0012478003,0.0037443016,0.00054971623,0.0028917897,0.0017035964,0.0015993165,0.004200967],"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":[0.00020600132,0.00012161569,0.00030335988,0.00023416786,0.00013558492,0.00013438631,0.0001535514,0.0056777955,0.03124106,0.006845803,0.011864901,0.9430818],"study_design_scores_gemma":[0.00015915347,0.0005530834,0.0015003763,0.00008538424,0.0005608184,0.0013395479,0.0002822015,0.78871197,0.081605054,0.026938036,0.09809916,0.00016532038],"about_ca_topic_score_codex":0.002544437,"about_ca_topic_score_gemma":0.005218999,"teacher_disagreement_score":0.0060694884,"about_ca_system_score_codex":0.00055612385,"about_ca_system_score_gemma":0.0013149192,"threshold_uncertainty_score":0.020304441},"labels":[],"label_agreement":null},{"id":"W1502353290","doi":"10.1007/978-3-540-69311-6_7","title":"A PTAS for the k-Consensus Structures Problem Under Euclidean Squared Distance","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Mathematics; Euclidean distance; Fragment (logic); Euclidean space; Sequence (biology); Simple (philosophy); Euclidean geometry; Space (punctuation); Set (abstract data type); Discrete mathematics; Algorithm; Computer science; Geometry","score_opus":0.023892291777611215,"score_gpt":0.2551792729855504,"score_spread":0.23128698120793917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502353290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013743587,0.00040706262,0.9704513,0.0017946679,0.0003032832,0.0002358926,0.00030881725,0.0005730876,0.012182358],"genre_scores_gemma":[0.44475335,0.0013914753,0.51241124,0.0011626343,0.0009080877,0.001261734,0.0012665442,0.0006464318,0.036198527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963521,0.0011444564,0.00023033565,0.0010429387,0.00092170644,0.00030847898],"domain_scores_gemma":[0.9919453,0.004579894,0.00064841396,0.0013181982,0.00095093914,0.00055726053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003260963,0.001420815,0.0027928622,0.00092123257,0.0016112062,0.003053038,0.004866981,0.0044155684,0.014551167],"category_scores_gemma":[0.020400185,0.00071971235,0.0017551868,0.0027121324,0.0022892775,0.010178498,0.0054197675,0.006316962,0.0028656365],"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":[0.0009102816,0.00030017513,0.00045305322,0.0005973024,0.0001253105,0.00020683433,0.00040119255,0.26656312,0.004463949,0.5514818,0.029416116,0.14508092],"study_design_scores_gemma":[0.000103074766,0.00018535365,0.00012725765,0.000042060758,0.000030106403,0.00014663547,0.00008814568,0.6210632,0.0008723852,0.37281916,0.0044887597,0.000033902394],"about_ca_topic_score_codex":0.0018041331,"about_ca_topic_score_gemma":0.0013144308,"teacher_disagreement_score":0.014551167,"about_ca_system_score_codex":0.0022317765,"about_ca_system_score_gemma":0.0029088766,"threshold_uncertainty_score":0.048678517},"labels":[],"label_agreement":null},{"id":"W1503091585","doi":"10.1007/978-3-642-03555-5_8","title":"Optimizing XML Compression","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Lossless compression; Data compression; XML; Encoding (memory); Compression (physics); Data compression ratio; Set (abstract data type)","score_opus":0.017331452299173072,"score_gpt":0.2503684150358275,"score_spread":0.23303696273665445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503091585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07861253,0.0046084463,0.8172388,0.0009079554,0.0006487597,0.0002668758,0.0013001136,0.023921665,0.07249487],"genre_scores_gemma":[0.39801463,0.0020179902,0.5413882,0.00041538992,0.00033441256,0.00018579466,0.004177226,0.0023460123,0.05112031],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992768,0.00008972231,0.00004931154,0.000102050944,0.00040394434,0.00007820064],"domain_scores_gemma":[0.99927586,0.00022163727,0.00003532812,0.00026214265,0.00018764887,0.000017316634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038416628,0.00095358933,0.0006548398,0.0011020362,0.0004667542,0.0013314037,0.0011419778,0.00065243465,0.014389306],"category_scores_gemma":[0.00184068,0.0004064291,0.00041345423,0.0020925067,0.00035469935,0.0017953251,0.0009413913,0.00072022073,0.004085378],"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":[0.00035656054,0.00012473151,0.0007322171,0.00021762669,0.000040625982,0.00017055019,0.000065083295,0.028867591,0.043158587,0.024631275,0.029884977,0.8717502],"study_design_scores_gemma":[0.000096543496,0.0002299281,0.0013432191,0.000086827895,0.00011604682,0.00100642,0.00012251447,0.6346701,0.25170046,0.050593577,0.05998107,0.000053256517],"about_ca_topic_score_codex":0.0011514028,"about_ca_topic_score_gemma":0.0017359961,"teacher_disagreement_score":0.014389306,"about_ca_system_score_codex":0.0005549081,"about_ca_system_score_gemma":0.00052395667,"threshold_uncertainty_score":0.04813701},"labels":[],"label_agreement":null},{"id":"W1504040240","doi":"10.1007/978-3-642-02882-3_19","title":"Three New Algorithms for Regular Language Enumeration","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lexicographical order; Enumeration; Computer science; Word (group theory); Section (typography); Algorithm; Order (exchange); Word problem (mathematics education); Arithmetic; Mathematics; Discrete mathematics; Combinatorics","score_opus":0.019740628694283606,"score_gpt":0.2635594364890722,"score_spread":0.2438188077947886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504040240","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005548441,0.0005675337,0.96125454,0.00089872006,0.0005689551,0.000205775,0.0003665517,0.004508921,0.026080558],"genre_scores_gemma":[0.046549853,0.00058278796,0.9149122,0.0006000944,0.00042946852,0.00054506504,0.0015183915,0.0017307269,0.03313129],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596524,0.00060577574,0.00038772746,0.00086611893,0.0016343221,0.0005408086],"domain_scores_gemma":[0.99453706,0.0020506056,0.00022158053,0.0020436205,0.0008634611,0.00028362565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020110551,0.0017480796,0.0018225957,0.0032831545,0.0026430024,0.0061196308,0.0060920506,0.002462446,0.02793161],"category_scores_gemma":[0.011561043,0.0013108498,0.0028995324,0.0054567847,0.0033283245,0.011874284,0.007368842,0.0051360843,0.010345885],"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":[0.00030016317,0.00020769774,0.00028448759,0.0002699533,0.000034605633,0.00007564059,0.0003438458,0.004807479,0.0037279467,0.45183298,0.03226166,0.5058535],"study_design_scores_gemma":[0.00017711749,0.0001028637,0.0003382623,0.00010619799,0.000083309984,0.00053231634,0.00024921008,0.068591975,0.009306678,0.84516776,0.075229645,0.00011463178],"about_ca_topic_score_codex":0.0015734634,"about_ca_topic_score_gemma":0.0027658686,"teacher_disagreement_score":0.02793161,"about_ca_system_score_codex":0.002527489,"about_ca_system_score_gemma":0.0020746635,"threshold_uncertainty_score":0.09344053},"labels":[],"label_agreement":null},{"id":"W1504447126","doi":"10.1109/dcc.1998.672161","title":"Bayesian state combining for context models","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science; Context (archaeology); Tree (set theory); Estimator; Context model; Algorithm; Theoretical computer science; Artificial intelligence; Machine learning; Mathematics; Data mining; Statistics","score_opus":0.04550364765399028,"score_gpt":0.24185389045955918,"score_spread":0.1963502428055689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504447126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067849993,0.00018372895,0.9902262,0.00008438029,0.000019472523,0.000026310692,0.00009253691,0.00040816356,0.0021742021],"genre_scores_gemma":[0.3434809,0.00043510293,0.64954734,0.00021285325,0.00010318169,0.0002636307,0.0006627239,0.00039365614,0.004900618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772567,0.0009450136,0.00007485629,0.0004275804,0.00067873026,0.00014816895],"domain_scores_gemma":[0.9960037,0.0027072132,0.00024469703,0.0006253613,0.00031535534,0.0001036758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025790944,0.00095435564,0.001264811,0.0013705199,0.00092326064,0.0020943796,0.0019619835,0.0011885682,0.004747479],"category_scores_gemma":[0.009483877,0.0008646976,0.0014803375,0.0013198465,0.0011382261,0.003946912,0.0038897754,0.002520894,0.0010344983],"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":[0.00021254491,0.00009110894,0.0013057083,0.00014893372,0.00011181589,0.000108253575,0.00038217314,0.40478274,0.0044869203,0.38507953,0.002389977,0.20090033],"study_design_scores_gemma":[0.000007301623,0.000028462204,0.00017094433,0.0000130290955,0.00001791634,0.000025789073,0.00001794163,0.87556064,0.0014035353,0.12059212,0.0021424666,0.000019836045],"about_ca_topic_score_codex":0.0034447452,"about_ca_topic_score_gemma":0.0038240203,"teacher_disagreement_score":0.004747479,"about_ca_system_score_codex":0.0017128836,"about_ca_system_score_gemma":0.0016693496,"threshold_uncertainty_score":0.015881896},"labels":[],"label_agreement":null},{"id":"W1505889193","doi":"10.37236/2404","title":"Stamp Foldings, Semi-Meanders, and Open Meanders: Fast Generation Algorithms","year":2012,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amortized analysis; Permutation (music); Mathematics; Algorithm; Constant (computer programming); Representation (politics); Polyomino; Construct (python library); Tree (set theory); Combinatorics; Computer science; Data structure; Geometry; Programming language","score_opus":0.026854551415974974,"score_gpt":0.26951137571001754,"score_spread":0.24265682429404256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505889193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040456638,0.00031416278,0.9498425,0.00031872964,0.00013663922,0.00013378839,0.0004518082,0.0046858843,0.0036598109],"genre_scores_gemma":[0.21700162,0.0002454856,0.7749134,0.00018354783,0.00009747827,0.00030280947,0.0013738442,0.00083965715,0.005042132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925023,0.00012865127,0.00009177043,0.00012066896,0.0002924488,0.0001162641],"domain_scores_gemma":[0.99652123,0.0011996718,0.00018204862,0.0015098588,0.00047014156,0.00011710307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010168323,0.0005101711,0.0006613166,0.000998654,0.00075108156,0.0012955009,0.0015696156,0.001097169,0.006258572],"category_scores_gemma":[0.006970681,0.00046590515,0.00085506187,0.0018929293,0.0009035798,0.003237074,0.0020305058,0.0013090022,0.002141008],"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":[0.00073095184,0.00019006671,0.0019241337,0.00028055525,0.000037870665,0.00021788865,0.00035588566,0.070695356,0.017102974,0.17147385,0.028692696,0.7082977],"study_design_scores_gemma":[0.00020759838,0.00031581146,0.0005203567,0.00006498726,0.000048634418,0.0005109712,0.00011236119,0.5164809,0.038337555,0.42226318,0.021060562,0.00007700019],"about_ca_topic_score_codex":0.0005418797,"about_ca_topic_score_gemma":0.0011402256,"teacher_disagreement_score":0.006258572,"about_ca_system_score_codex":0.00065199856,"about_ca_system_score_gemma":0.001058085,"threshold_uncertainty_score":0.020937026},"labels":[],"label_agreement":null},{"id":"W1509287145","doi":"10.3233/fi-2009-202","title":"Combinatorics of Unique Maximal Factorization Families (UMFFs)","year":2009,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"McMaster University","funders":"Centre International de Recherche sur le Cancer","keywords":"Lexicographical order; Combinatorics; Factorization; Mathematics; Alphabet; String (physics); Set (abstract data type); Word (group theory); Discrete mathematics; Computer science; Algorithm","score_opus":0.010013033749252725,"score_gpt":0.23239784096643004,"score_spread":0.22238480721717732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509287145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2751786,0.004262846,0.6305194,0.0016213395,0.00038886437,0.00024528036,0.0022116154,0.0010365766,0.08453548],"genre_scores_gemma":[0.74306667,0.0022207312,0.21965662,0.0007675355,0.0005867342,0.00073393487,0.0028655583,0.0004342442,0.02966802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99744844,0.0004755683,0.00025725694,0.0007063722,0.00058212416,0.0005301286],"domain_scores_gemma":[0.9946398,0.003008626,0.0006794309,0.00067521614,0.0006349829,0.0003619777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017011798,0.0007389244,0.0011708468,0.003417971,0.0036415707,0.0034943908,0.0013167885,0.0011842675,0.014453761],"category_scores_gemma":[0.008210031,0.00089368486,0.0017330353,0.00334159,0.0036535903,0.0063038208,0.0030880475,0.0014334414,0.0018868813],"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":[0.000062445564,0.000026008158,0.00092552276,0.000121029996,0.000016175436,0.00032188228,0.00044823508,0.0017168928,0.0008586872,0.96688277,0.0029280938,0.025692109],"study_design_scores_gemma":[0.000020326499,0.00002741126,0.00036835246,0.00006666424,0.000016139256,0.00081113545,0.00018292437,0.0047008675,0.0010889916,0.9771966,0.015485614,0.00003501082],"about_ca_topic_score_codex":0.0011758069,"about_ca_topic_score_gemma":0.0011532409,"teacher_disagreement_score":0.014453761,"about_ca_system_score_codex":0.0020123972,"about_ca_system_score_gemma":0.00082012045,"threshold_uncertainty_score":0.04835266},"labels":[],"label_agreement":null},{"id":"W1509582226","doi":"10.1007/978-3-540-24596-4_47","title":"Crafting Data Structures: A Study of Reference Locality in Refinement-Based Pathfinding","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Locality; Computer science; Locality of reference; Compiler; Pathfinding; CAS latency; Exploit; Data structure; Parallel computing; Transformation (genetics); Theoretical computer science; Algorithm; Programming language; Memory controller; Computer hardware; Cache","score_opus":0.06679665395620887,"score_gpt":0.3025072823659228,"score_spread":0.2357106284097139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509582226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06843002,0.0011945681,0.92426544,0.0004895657,0.000029022674,0.00009518364,0.0000786794,0.00066656695,0.004750995],"genre_scores_gemma":[0.46816838,0.0013650204,0.52292466,0.00013063647,0.000067306406,0.00014045462,0.0003512623,0.00062345294,0.0062288544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974062,0.0008941674,0.0001751402,0.00047723958,0.0007814664,0.000265874],"domain_scores_gemma":[0.9628322,0.02559512,0.0018919659,0.0071070385,0.0022122485,0.0003613681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044385563,0.0005170918,0.0018104764,0.0028140522,0.0021899357,0.002517866,0.004733376,0.0019632287,0.0042002313],"category_scores_gemma":[0.038222406,0.0011175494,0.0012110503,0.0068324567,0.0049553043,0.010786348,0.0033600114,0.0026057444,0.00055707194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027040078,0.00012007192,0.0036127868,0.00053585175,0.000063169995,0.00020366588,0.0028519498,0.12100144,0.0055604815,0.6555537,0.0031067056,0.2071198],"study_design_scores_gemma":[0.00003933165,0.00018104348,0.0007553773,0.00010256503,0.00009806574,0.000258876,0.00080825813,0.48104516,0.007328965,0.50304997,0.0062702606,0.00006214189],"about_ca_topic_score_codex":0.011715083,"about_ca_topic_score_gemma":0.011178058,"teacher_disagreement_score":0.011715083,"about_ca_system_score_codex":0.0016669662,"about_ca_system_score_gemma":0.0023003707,"threshold_uncertainty_score":0.02347356},"labels":[],"label_agreement":null},{"id":"W1510678864","doi":"10.1016/j.endm.2007.07.091","title":"A fast algorithm to generate Beckett-Gray codes","year":2007,"lang":"en","type":"article","venue":"Electronic Notes in Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Gray code; Heuristics; Gray (unit); Algorithm; Computation; Binary number; Mathematics; Computer science; Combinatorics; Arithmetic; Mathematical optimization","score_opus":0.011812435253359876,"score_gpt":0.2756582649566635,"score_spread":0.2638458297033036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510678864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013030301,0.00017580633,0.97409374,0.00021418199,0.00020580989,0.00020117887,0.00016808658,0.0017089875,0.010201868],"genre_scores_gemma":[0.11156731,0.00016195538,0.8750631,0.00016960884,0.00004511549,0.0003000501,0.000446231,0.00047839098,0.011768181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994709,0.00008617652,0.000030190626,0.000074782474,0.00027118987,0.00006684918],"domain_scores_gemma":[0.9993849,0.00019394301,0.000033155728,0.00015155332,0.00018561016,0.00005089988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053732964,0.000870122,0.000511696,0.0015483903,0.0008191083,0.0010193591,0.00076486904,0.00089443836,0.01317531],"category_scores_gemma":[0.0026743005,0.00037714755,0.00054325577,0.0013255936,0.00060550467,0.00095119386,0.0020464074,0.001151314,0.004944677],"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":[0.00042812256,0.00013408081,0.00069039926,0.00018343178,0.000046331785,0.00022259646,0.00024374433,0.026889019,0.03239977,0.23898774,0.0140655525,0.6857093],"study_design_scores_gemma":[0.00034537757,0.00035445608,0.00079749076,0.00012340116,0.000082212304,0.00080260047,0.0001635397,0.46695623,0.10194926,0.36606428,0.062240023,0.00012116299],"about_ca_topic_score_codex":0.00082771864,"about_ca_topic_score_gemma":0.0016162504,"teacher_disagreement_score":0.01317531,"about_ca_system_score_codex":0.0005915871,"about_ca_system_score_gemma":0.0010899242,"threshold_uncertainty_score":0.044075787},"labels":[],"label_agreement":null},{"id":"W1511951313","doi":"10.1007/978-3-642-11829-6_18","title":"Evolving Schemas for Streaming XML","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; XML; Streaming XML; Document Structure Description; XML Schema (W3C); Efficient XML Interchange; XML Schema Editor; Information retrieval; Programming language; World Wide Web; XML Encryption","score_opus":0.016097597737693148,"score_gpt":0.25388809504499166,"score_spread":0.2377904973072985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511951313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010413224,0.00074834906,0.97157043,0.00050999643,0.00017967403,0.00016943403,0.00090929016,0.007918265,0.007581339],"genre_scores_gemma":[0.090628736,0.0012020746,0.8863912,0.00023451405,0.000086916545,0.00024985016,0.0048113973,0.0024938013,0.013901515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881566,0.00024559483,0.00017732571,0.0002085601,0.00049314526,0.00005978009],"domain_scores_gemma":[0.9968549,0.0012173019,0.0001124776,0.0012219364,0.00047151354,0.00012180428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025302821,0.0005235049,0.0006133184,0.0010997426,0.0007651286,0.0026722106,0.0025724813,0.0012318557,0.008154413],"category_scores_gemma":[0.008850157,0.000836602,0.00090242556,0.0018897948,0.0009390528,0.006215302,0.0025358736,0.0021417271,0.0022240311],"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":[0.00023956875,0.00013067092,0.0011111314,0.00032856152,0.000049419894,0.00032173123,0.0009502647,0.02317099,0.009874001,0.45661226,0.028395798,0.47881556],"study_design_scores_gemma":[0.00007749919,0.00010144487,0.00042949853,0.00019234953,0.00008012454,0.00076493266,0.00035572637,0.32290643,0.028898599,0.4354602,0.21065678,0.00007646893],"about_ca_topic_score_codex":0.002067055,"about_ca_topic_score_gemma":0.002219809,"teacher_disagreement_score":0.008154413,"about_ca_system_score_codex":0.0011239487,"about_ca_system_score_gemma":0.0008476986,"threshold_uncertainty_score":0.027279258},"labels":[],"label_agreement":null},{"id":"W1513208069","doi":"","title":"On the ratio between the maximal T-complexity and the T-complexity of random strings","year":2012,"lang":"en","type":"article","venue":"ResearchSpace (University of Auckland)","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Code word; Limit (mathematics); Mathematics; Combinatorics; String (physics); Discrete mathematics; Computational complexity theory; Algorithm; Decoding methods; Mathematical analysis","score_opus":0.07485299543413734,"score_gpt":0.2641319730999454,"score_spread":0.18927897766580806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1513208069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30482942,0.005622338,0.64833313,0.0033494392,0.00026392378,0.0002198784,0.00081340695,0.0018198381,0.034748685],"genre_scores_gemma":[0.90439487,0.0029420075,0.08608981,0.000778082,0.00056486303,0.00045165213,0.00058197556,0.0007263561,0.0034703875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99376935,0.0018158797,0.00034931902,0.0014155222,0.0018028578,0.0008470221],"domain_scores_gemma":[0.83167255,0.14840293,0.0056045395,0.007937426,0.003775067,0.0026074818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061105248,0.0011863466,0.0016633604,0.002929069,0.0010861994,0.003287197,0.0023792349,0.0022672962,0.005775023],"category_scores_gemma":[0.13233034,0.0007561168,0.00089740223,0.0018583739,0.005009683,0.0099104075,0.0032901324,0.0037959737,0.0014277494],"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":[0.0015889854,0.00043618286,0.016112052,0.0011529371,0.0002815306,0.0013474181,0.0010301389,0.2096513,0.036242437,0.59918475,0.00889749,0.124074765],"study_design_scores_gemma":[0.000073079005,0.0005238962,0.006410196,0.00026811002,0.00011431344,0.003311601,0.0002560822,0.5889282,0.015320722,0.3813896,0.003193085,0.00021100929],"about_ca_topic_score_codex":0.00074314815,"about_ca_topic_score_gemma":0.00055981014,"teacher_disagreement_score":0.0061105248,"about_ca_system_score_codex":0.002319963,"about_ca_system_score_gemma":0.0017397453,"threshold_uncertainty_score":0.03231591},"labels":[],"label_agreement":null},{"id":"W1515132277","doi":"10.1007/978-3-540-27868-9_26","title":"Dictionary-Based Syntactic Pattern Recognition Using Tries","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Levenshtein distance; Computer science; String (physics); Prefix; Edit distance; Set (abstract data type); Computation; Representation (politics); Element (criminal law); Algorithm; Substitution (logic); Theoretical computer science; Data structure; Mathematics; Programming language","score_opus":0.03047022484350267,"score_gpt":0.25345434159893476,"score_spread":0.2229841167554321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515132277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018556971,0.0006684977,0.9525971,0.00016419076,0.00032293468,0.00020508212,0.0011386949,0.01903809,0.0073084403],"genre_scores_gemma":[0.13217272,0.0010132361,0.84329695,0.0002691025,0.00012668465,0.0003053438,0.005164162,0.0017629305,0.01588884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992428,0.00013558564,0.00008508978,0.00021620907,0.00023824179,0.00008217327],"domain_scores_gemma":[0.9987212,0.0004820554,0.000057386245,0.00029528796,0.00038752766,0.000056523873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059757737,0.0014586637,0.0019629202,0.0029944528,0.0007751516,0.0022597858,0.0019269107,0.00097463554,0.016823566],"category_scores_gemma":[0.0020871984,0.00068719295,0.0013870477,0.0038550687,0.0008090374,0.0029088394,0.0022300517,0.0013416256,0.016381912],"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":[0.00040368058,0.00007244161,0.0007532861,0.00037342985,0.00010596704,0.00031800527,0.0001447137,0.00502501,0.03313907,0.011424436,0.012780706,0.9354593],"study_design_scores_gemma":[0.00020230863,0.00048943126,0.0017630341,0.00020278497,0.00039925645,0.0026013323,0.0008117009,0.72054935,0.16915405,0.055789758,0.04786464,0.00017237224],"about_ca_topic_score_codex":0.001618797,"about_ca_topic_score_gemma":0.0030299935,"teacher_disagreement_score":0.016823566,"about_ca_system_score_codex":0.00030741698,"about_ca_system_score_gemma":0.0011460318,"threshold_uncertainty_score":0.056280434},"labels":[],"label_agreement":null},{"id":"W1517466281","doi":"10.1007/978-0-387-30162-4_411","title":"Succinct Encoding of Permutations: Applications to Text Indexing","year":2008,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Encoding (memory); Search engine indexing; Computer science; Information retrieval; Artificial intelligence","score_opus":0.01961642112949077,"score_gpt":0.25951106128939977,"score_spread":0.239894640159909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517466281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011095064,0.002227826,0.9607731,0.0011066821,0.00063428463,0.0001873368,0.0016399161,0.003503267,0.018832548],"genre_scores_gemma":[0.14853163,0.0036857277,0.81988615,0.00064346683,0.00057545217,0.00051979866,0.0044489237,0.0011497635,0.020559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888855,0.00030784862,0.00012688455,0.00014288614,0.00045951974,0.00007424849],"domain_scores_gemma":[0.9970048,0.0013172163,0.00016014837,0.0010263977,0.00040788556,0.00008363288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001138707,0.00096961984,0.0009266956,0.0014617947,0.00077422,0.0029091462,0.001692384,0.0012149093,0.012770616],"category_scores_gemma":[0.0072119483,0.00057058723,0.0006053607,0.004421635,0.0012037731,0.0052312827,0.002274221,0.0019624943,0.004685697],"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":[0.00038404608,0.00014823518,0.00022990041,0.00042990208,0.000022786453,0.00018297971,0.0002828801,0.02385548,0.008291682,0.35562,0.03982612,0.5707259],"study_design_scores_gemma":[0.00013069836,0.00013090631,0.00014377889,0.00018677217,0.000037768812,0.00048997375,0.00012556546,0.13300815,0.015368502,0.7771818,0.07313085,0.000065261265],"about_ca_topic_score_codex":0.0008801188,"about_ca_topic_score_gemma":0.0014891076,"teacher_disagreement_score":0.012770616,"about_ca_system_score_codex":0.0008648629,"about_ca_system_score_gemma":0.001406357,"threshold_uncertainty_score":0.042721987},"labels":[],"label_agreement":null},{"id":"W1518463267","doi":"10.1109/pacrim.2001.953552","title":"Reduced code transmission and high speed reconstruction of Huffman tables","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Windsor","funders":"","keywords":"Huffman coding; Canonical Huffman code; Prefix code; Computer science; Tunstall coding; Shannon–Fano coding; Table (database); Code (set theory); Algorithm; Parallel computing; Coding (social sciences); Data compression; Decoding methods; Block code; Mathematics; Code rate; Concatenated error correction code; Programming language; Statistics; Data mining; Systematic code","score_opus":0.02135958668999454,"score_gpt":0.22345424862239968,"score_spread":0.20209466193240513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518463267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044595283,0.0009306145,0.94595736,0.00017095942,0.00010326759,0.00004650584,0.00009675867,0.00075438747,0.0073448527],"genre_scores_gemma":[0.49843612,0.0012094941,0.48981237,0.00012773329,0.00012992434,0.000095129406,0.00042427063,0.00015856209,0.009606415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995291,0.00008848649,0.000017487717,0.00005336823,0.0002680238,0.000043517855],"domain_scores_gemma":[0.9994081,0.0002567851,0.000052913743,0.00014915837,0.000118574586,0.000014526821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031696077,0.0003000786,0.00042741201,0.0005075606,0.00028947697,0.0005790063,0.00058086903,0.0005484314,0.0016867082],"category_scores_gemma":[0.0020212922,0.00024045158,0.0003247453,0.000722014,0.00044834637,0.0008349327,0.000523568,0.0007420357,0.00064473023],"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":[0.0005450778,0.000073749405,0.0006932845,0.00033946816,0.000065975524,0.0009568165,0.00042615712,0.14392985,0.15947418,0.33921722,0.0059538614,0.34832442],"study_design_scores_gemma":[0.000051322055,0.00016154569,0.0004183925,0.00004347072,0.00003648327,0.0014621136,0.00004483994,0.7385318,0.19487198,0.045183938,0.019143505,0.000050578543],"about_ca_topic_score_codex":0.0007201871,"about_ca_topic_score_gemma":0.00053604256,"teacher_disagreement_score":0.0016867082,"about_ca_system_score_codex":0.00033169074,"about_ca_system_score_gemma":0.00037024572,"threshold_uncertainty_score":0.0056426525},"labels":[],"label_agreement":null},{"id":"W1518516024","doi":"","title":"Faster algorithms for finding missing patterns","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Combinatorics; Algorithm; Time complexity; Binary logarithm; String (physics); Upper and lower bounds; Simple (philosophy); Mathematics; Quadratic equation; Computer science","score_opus":0.033190445207223106,"score_gpt":0.27979444756938354,"score_spread":0.24660400236216043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518516024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005633798,0.0008870239,0.9874922,0.00034505926,0.00019146957,0.00017004274,0.0003549121,0.0037884775,0.0011371103],"genre_scores_gemma":[0.02501137,0.00042476086,0.9700069,0.00016205314,0.00014402396,0.00032072727,0.0014054818,0.00037186,0.0021527652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99442226,0.0010247895,0.0006242285,0.001365148,0.0021030214,0.0004605492],"domain_scores_gemma":[0.98516786,0.0073446906,0.0009387872,0.0043652314,0.0018871436,0.0002962042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041539334,0.002775985,0.0032282253,0.004695947,0.0017676937,0.003323268,0.006823496,0.0031874173,0.015600912],"category_scores_gemma":[0.02163867,0.0016326973,0.0023700634,0.00693972,0.0012071937,0.009873388,0.004365189,0.0034113196,0.0073584067],"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":[0.00064950035,0.0002842508,0.0012041179,0.00073801685,0.00014430705,0.00017615431,0.000336011,0.038946077,0.008975268,0.031308632,0.018780991,0.8984566],"study_design_scores_gemma":[0.0007533076,0.00030723956,0.0011132729,0.00016702047,0.0001730063,0.0013248386,0.00035837755,0.733428,0.019967424,0.20739412,0.034886297,0.00012706575],"about_ca_topic_score_codex":0.002138144,"about_ca_topic_score_gemma":0.0034178004,"teacher_disagreement_score":0.015600912,"about_ca_system_score_codex":0.0013900965,"about_ca_system_score_gemma":0.0027061752,"threshold_uncertainty_score":0.052190304},"labels":[],"label_agreement":null},{"id":"W1518570358","doi":"10.1109/cwit.2015.7255153","title":"Using bit recycling to reduce the redundancy in plurally parsable dictionaries","year":2015,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Redundancy (engineering); Computer science; Binary number; Algorithm; Coding (social sciences); Binary code; Theoretical computer science; Random variable; Arithmetic; Mathematics; Statistics","score_opus":0.13499260333907487,"score_gpt":0.33876672357437515,"score_spread":0.20377412023530028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518570358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09912688,0.00029757543,0.89651805,0.00016061091,0.000047133453,0.000047556165,0.00004712285,0.0007621805,0.0029928666],"genre_scores_gemma":[0.4072596,0.00023746153,0.5878567,0.0001568078,0.0000389171,0.00007760432,0.00014102257,0.00020959864,0.004022352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991425,0.00017294381,0.000108416374,0.0001500554,0.0003376669,0.00008838834],"domain_scores_gemma":[0.9961786,0.00143703,0.00037468367,0.0013710738,0.0005662459,0.00007244485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009859143,0.00047364435,0.0006455671,0.0009864208,0.00066980644,0.0009800429,0.00096002175,0.0007205959,0.0016268208],"category_scores_gemma":[0.007310892,0.00029560545,0.00038414393,0.0013358447,0.0013859187,0.002157036,0.0016127072,0.0009598823,0.0007480237],"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":[0.0010810164,0.00012134417,0.002351736,0.00023161725,0.00006278315,0.00036960086,0.00056692894,0.09118922,0.111790605,0.19113682,0.002471793,0.59862655],"study_design_scores_gemma":[0.00007185419,0.00043451897,0.00064604543,0.000096369935,0.000053540483,0.0009462181,0.00015443168,0.6712454,0.23899531,0.07666701,0.0105970185,0.00009234967],"about_ca_topic_score_codex":0.00060437346,"about_ca_topic_score_gemma":0.001109243,"teacher_disagreement_score":0.0016268208,"about_ca_system_score_codex":0.00040807,"about_ca_system_score_gemma":0.0007168542,"threshold_uncertainty_score":0.0054422617},"labels":[],"label_agreement":null},{"id":"W1518644579","doi":"10.1007/11561071_66","title":"Finding Frequent Patterns in a String in Sublinear Time","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Sublinear function; String (physics); Focus (optics); Property (philosophy); Computer science; Alphabet; Algorithm; Combinatorics; Discrete mathematics; Mathematics; Physics","score_opus":0.018829689908549815,"score_gpt":0.25062956708516604,"score_spread":0.2317998771766162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518644579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15658382,0.005577653,0.7500838,0.010938619,0.0017003216,0.0011585243,0.015120464,0.032823935,0.026012832],"genre_scores_gemma":[0.19058652,0.0016963657,0.7509814,0.0016396956,0.00092234765,0.0007595702,0.021439238,0.0025109123,0.029463986],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924516,0.00104958,0.0008429885,0.0016843869,0.0032624241,0.0007090205],"domain_scores_gemma":[0.9653577,0.025760882,0.001211492,0.005457439,0.0015095231,0.000703037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002304155,0.0023218025,0.0035363906,0.003144608,0.0013700507,0.005976808,0.003671211,0.002447146,0.030955182],"category_scores_gemma":[0.019818256,0.0015479899,0.0044945697,0.008047731,0.001641314,0.015625134,0.003601025,0.0032900057,0.013695449],"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":[0.0030635106,0.0007219925,0.0059270384,0.0023485806,0.00059541553,0.0007925787,0.0005726932,0.024432426,0.035067998,0.01441384,0.07413479,0.8379292],"study_design_scores_gemma":[0.0017592665,0.0008003261,0.0046649654,0.00025576397,0.000991142,0.0037521392,0.0012986166,0.6705627,0.037353873,0.23965296,0.038769595,0.00013861715],"about_ca_topic_score_codex":0.0028903477,"about_ca_topic_score_gemma":0.0075203585,"teacher_disagreement_score":0.030955182,"about_ca_system_score_codex":0.002154064,"about_ca_system_score_gemma":0.0044340156,"threshold_uncertainty_score":0.10355544},"labels":[],"label_agreement":null},{"id":"W1519416322","doi":"10.1007/3-540-44888-8_19","title":"Alignment between Two Multiple Alignments","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Heuristic; Affine transformation; Dynamic programming; Multiple sequence alignment; Sequence (biology); Algorithm; Mathematical optimization; Mathematics; Sequence alignment; Artificial intelligence","score_opus":0.022002496849299415,"score_gpt":0.26083262514084604,"score_spread":0.23883012829154662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519416322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031783413,0.0027630685,0.904476,0.001541016,0.003272057,0.0005063542,0.008008074,0.020256178,0.027393837],"genre_scores_gemma":[0.099654794,0.001964445,0.83973515,0.000641508,0.0004847067,0.0004964776,0.029193012,0.006290402,0.021539526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980294,0.00041001732,0.00026267447,0.0007028401,0.00046542232,0.00012957773],"domain_scores_gemma":[0.9961273,0.0012737331,0.00036401217,0.0012812923,0.00085274276,0.00010097702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001498849,0.0020741355,0.0017226918,0.0030932128,0.0018116229,0.003068502,0.0015644633,0.0023874308,0.032710392],"category_scores_gemma":[0.0093087545,0.0013963298,0.0018211518,0.0051387167,0.00063424755,0.0032798392,0.0022234102,0.0029008398,0.026538106],"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":[0.0015660756,0.0003373254,0.0022565967,0.0036995374,0.0005320261,0.0044968245,0.0020749092,0.005802314,0.20485353,0.05656563,0.10183968,0.6159755],"study_design_scores_gemma":[0.00024771687,0.0005344409,0.0032248881,0.001057628,0.00087657495,0.004998104,0.0014271872,0.04802463,0.18618004,0.11976835,0.63344383,0.00021663638],"about_ca_topic_score_codex":0.000322152,"about_ca_topic_score_gemma":0.0005983049,"teacher_disagreement_score":0.032710392,"about_ca_system_score_codex":0.00041930962,"about_ca_system_score_gemma":0.001002162,"threshold_uncertainty_score":0.10942721},"labels":[],"label_agreement":null},{"id":"W1522106723","doi":"10.1109/sips.2004.1363067","title":"ASIC implementation of a high speed WGNG for communication channel emulation [white Gaussian noise generator]","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Emulation; Application-specific integrated circuit; Field-programmable gate array; Computer science; Embedded system; Channel (broadcasting); CMOS; Hardware emulation; Design flow; Computer hardware; Electronic engineering; Engineering; Telecommunications","score_opus":0.023425829052376033,"score_gpt":0.2965199840913289,"score_spread":0.27309415503895285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522106723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089521,0.00044066258,0.88221246,0.00028975995,0.00044924676,0.00045082267,0.00023360977,0.006419186,0.019983342],"genre_scores_gemma":[0.5960249,0.00035799856,0.38511142,0.000343863,0.00009718796,0.00031063776,0.00046736523,0.00025943917,0.017027233],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996885,0.000058051624,0.000018609633,0.00006299546,0.00012296681,0.000048945247],"domain_scores_gemma":[0.9997608,0.000037775557,0.00003266388,0.000054217395,0.000102385384,0.000012194419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022860322,0.00051627005,0.00028126285,0.00029682886,0.00025301473,0.00052382913,0.0008947755,0.00045021577,0.0028439548],"category_scores_gemma":[0.00039509693,0.00018558816,0.00019744258,0.00031763324,0.00026441299,0.00038555163,0.00013638884,0.0004199196,0.0010441452],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072560133,0.00021712038,0.0017080024,0.0005379093,0.00014597739,0.00082762097,0.00031357174,0.027501894,0.7144205,0.025436174,0.010767249,0.21739842],"study_design_scores_gemma":[0.00017538606,0.0013803302,0.0014385029,0.00004510631,0.00013365922,0.0016335186,0.000049753788,0.1255683,0.79128885,0.00172443,0.07652217,0.000040064704],"about_ca_topic_score_codex":0.0005674284,"about_ca_topic_score_gemma":0.00128177,"teacher_disagreement_score":0.0028439548,"about_ca_system_score_codex":0.00047316286,"about_ca_system_score_gemma":0.00042667415,"threshold_uncertainty_score":0.009513974},"labels":[],"label_agreement":null},{"id":"W1522987234","doi":"10.1007/11559573_41","title":"Grayscale Two-Dimensional Lempel-Ziv Encoding","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Lossless compression; Computer science; Grayscale; JPEG; Color Cell Compression; Image compression; Data compression; Artificial intelligence; Compression (physics); Lossy compression; Data compression ratio; Computer vision; Compression ratio; Lossless JPEG; Encoding (memory); JPEG 2000; Pixel; Pattern recognition (psychology); Image (mathematics); Image processing","score_opus":0.01639603914863114,"score_gpt":0.25129319283220836,"score_spread":0.23489715368357722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522987234","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046598475,0.0029171621,0.84744304,0.0015715387,0.0007010085,0.00018882885,0.0018756381,0.0038158689,0.09488845],"genre_scores_gemma":[0.4848263,0.0029794993,0.43727177,0.0015063131,0.0003380729,0.00034439936,0.0037449873,0.0006283341,0.06836036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998173,0.000029446053,0.000014687791,0.0000255913,0.000078626064,0.000034316505],"domain_scores_gemma":[0.999736,0.00006315991,0.000017765582,0.00010557039,0.00006315474,0.000014324316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019026232,0.00047845527,0.00044070015,0.0008882508,0.00034803327,0.0011972089,0.0006069234,0.00080266886,0.012847984],"category_scores_gemma":[0.0011703772,0.00015239268,0.00029865323,0.0012836679,0.00041544446,0.0013345121,0.001039771,0.00087273796,0.0041087586],"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":[0.00049113465,0.00012509042,0.00025896975,0.0004056108,0.000025368958,0.00038401928,0.00015451702,0.021698913,0.06036799,0.2813843,0.031109834,0.60359436],"study_design_scores_gemma":[0.00018624119,0.0003169413,0.0010154392,0.00045639955,0.000077197554,0.0024599342,0.0001824888,0.3748921,0.18462774,0.3038116,0.1318011,0.0001728473],"about_ca_topic_score_codex":0.0004678897,"about_ca_topic_score_gemma":0.0007291579,"teacher_disagreement_score":0.012847984,"about_ca_system_score_codex":0.0004324983,"about_ca_system_score_gemma":0.000515344,"threshold_uncertainty_score":0.04298079},"labels":[],"label_agreement":null},{"id":"W1523223925","doi":"10.1109/dcc.1995.515576","title":"Bitgroup modeling of signal data for image compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Gray code; Lossless compression; Algorithm; Binary number; Computer science; Data compression; Bit plane; Binary data; Hamming distance; Binary code; Hamming code; Arithmetic coding; Context-adaptive binary arithmetic coding; Mathematics; Decoding methods; Arithmetic; Block code; Bit field","score_opus":0.10548326407247734,"score_gpt":0.2927010384008144,"score_spread":0.18721777432833708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523223925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014855425,0.004282791,0.9583421,0.0010315357,0.00093570194,0.00014404209,0.0004398726,0.0012960054,0.018672531],"genre_scores_gemma":[0.46888098,0.014412217,0.43383873,0.00058731897,0.0014423856,0.0005017728,0.0026009544,0.0006321465,0.0771036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996475,0.00011323793,0.000017369974,0.000047717596,0.00015157391,0.000022516948],"domain_scores_gemma":[0.99928856,0.0003159727,0.000039082755,0.00018936253,0.00014119115,0.000025869522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004177578,0.0006818095,0.0005485119,0.0005625643,0.0002142764,0.0009328595,0.0007626943,0.0006379818,0.019339595],"category_scores_gemma":[0.0023992108,0.0001491317,0.00035143676,0.0011568057,0.00042522576,0.0013854105,0.00048503306,0.00076129613,0.0059424182],"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":[0.00035702292,0.00007410397,0.00083661097,0.00064550457,0.00007174058,0.00020865469,0.00013701276,0.16125508,0.022696216,0.22201672,0.03218297,0.5595183],"study_design_scores_gemma":[0.000019697398,0.00016181676,0.00032050416,0.00009267371,0.000038995604,0.00017358418,0.000037902064,0.87244344,0.009607939,0.049147863,0.06793442,0.00002119851],"about_ca_topic_score_codex":0.001134203,"about_ca_topic_score_gemma":0.001331703,"teacher_disagreement_score":0.019339595,"about_ca_system_score_codex":0.0005109724,"about_ca_system_score_gemma":0.00029230857,"threshold_uncertainty_score":0.064697385},"labels":[],"label_agreement":null},{"id":"W1524289721","doi":"10.1007/978-3-642-03784-9_24","title":"Faster Algorithms for Sampling and Counting Biological Sequences","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pairwise comparison; Bounded function; Sequence (biology); Mathematics; Combinatorics; Hamming distance; Algorithm; Computer science; Discrete mathematics; Artificial intelligence","score_opus":0.05671718658480474,"score_gpt":0.29382078062225203,"score_spread":0.2371035940374473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524289721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004825869,0.00069495797,0.9894566,0.00016549083,0.00017932638,0.00008982371,0.0002871068,0.003049812,0.0012510042],"genre_scores_gemma":[0.02675757,0.00044572988,0.96626705,0.00015560104,0.00021122966,0.00040248796,0.0014587112,0.0005249906,0.0037766115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593484,0.0007273462,0.00039155333,0.00087046874,0.0018301568,0.0002456094],"domain_scores_gemma":[0.98580116,0.0073598805,0.0006229331,0.0042533353,0.0015654818,0.00039727153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003702854,0.002636428,0.0032137642,0.00500811,0.0012846654,0.003804149,0.005682126,0.002416114,0.019981725],"category_scores_gemma":[0.018811941,0.0014888813,0.0023590804,0.0074017146,0.0014385538,0.00792811,0.0034615444,0.0039137155,0.0070339884],"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":[0.00055263785,0.00016761357,0.0012502332,0.000540583,0.00016377796,0.00009382652,0.00030496056,0.05248075,0.01234571,0.06918364,0.01526406,0.8476522],"study_design_scores_gemma":[0.00030690432,0.00014563295,0.00101215,0.00008151679,0.00011979177,0.00046447336,0.0001312327,0.72091144,0.013166205,0.24421132,0.019374369,0.00007496477],"about_ca_topic_score_codex":0.0037065593,"about_ca_topic_score_gemma":0.006605345,"teacher_disagreement_score":0.019981725,"about_ca_system_score_codex":0.002269475,"about_ca_system_score_gemma":0.00218663,"threshold_uncertainty_score":0.06684548},"labels":[],"label_agreement":null},{"id":"W1525678880","doi":"","title":"On the Generation of Aperiodic and Periodic Necklaces via T-augmentation","year":2008,"lang":"en","type":"article","venue":"ResearchSpace (University of Auckland)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Aperiodic graph; Mathematics; Combinatorics; Simple (philosophy); Discrete mathematics","score_opus":0.04769660513597747,"score_gpt":0.23503373671859584,"score_spread":0.1873371315826184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525678880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4615647,0.000809885,0.5156488,0.0002997625,0.00011738018,0.00019546458,0.00025908486,0.00045332965,0.020651719],"genre_scores_gemma":[0.8233191,0.0005905743,0.16890669,0.00016472732,0.000087018045,0.00032018992,0.000423495,0.000102886304,0.0060853194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994423,0.00012910462,0.000052613785,0.00010920986,0.00018228892,0.00008449295],"domain_scores_gemma":[0.99704224,0.0015589468,0.0003971756,0.00061826006,0.0002618427,0.00012149673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061731186,0.0003322069,0.00040535018,0.0008071524,0.00059281,0.0005820564,0.00043596915,0.000348259,0.0017179511],"category_scores_gemma":[0.0039244336,0.00027183254,0.0006005701,0.0006104544,0.0014380758,0.0014646198,0.0012834619,0.0006389274,0.0003283951],"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":[0.0006580693,0.000103698134,0.00210808,0.0003047907,0.000035568,0.0006561795,0.0010033635,0.111357525,0.068098545,0.68777853,0.0020467658,0.12584889],"study_design_scores_gemma":[0.00010236749,0.00054015644,0.001301499,0.00012597025,0.000038902483,0.0010688923,0.0002272188,0.42807105,0.09478161,0.45602882,0.017608935,0.000104651655],"about_ca_topic_score_codex":0.00037322252,"about_ca_topic_score_gemma":0.0004462371,"teacher_disagreement_score":0.0017179511,"about_ca_system_score_codex":0.00041814303,"about_ca_system_score_gemma":0.0004625458,"threshold_uncertainty_score":0.0057471395},"labels":[],"label_agreement":null},{"id":"W1526131532","doi":"10.1007/bfb0028285","title":"Sorting multisets and vectors in-place","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multiset; Lexicographical order; Sorting; Upper and lower bounds; sort; Combinatorics; Mathematics; Sorting algorithm; Order (exchange); Discrete mathematics; Term (time); Algorithm; Computer science; Arithmetic","score_opus":0.01316834236935435,"score_gpt":0.24801868069461194,"score_spread":0.2348503383252576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526131532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03223909,0.0053002215,0.88703036,0.0008581512,0.0015535377,0.00018748314,0.0007783428,0.0033580202,0.06869476],"genre_scores_gemma":[0.1918845,0.004491088,0.6671115,0.0004617076,0.00070430746,0.00021353184,0.002633307,0.001334018,0.13116594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886715,0.00012390739,0.00011817103,0.00021198129,0.0005487621,0.00013004444],"domain_scores_gemma":[0.9989667,0.00023417007,0.00008548468,0.00042867096,0.00022818471,0.000056747904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005709186,0.0010269118,0.0012674442,0.0027707182,0.0014495378,0.0036400363,0.0017970307,0.00086983177,0.019794103],"category_scores_gemma":[0.0026110986,0.0007766803,0.0009959418,0.009163208,0.0017103913,0.007966704,0.0026790854,0.001938037,0.005809146],"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":[0.00020924985,0.000075279204,0.00049287995,0.00043125713,0.000040196068,0.00011160028,0.0003136571,0.008721563,0.00597917,0.53793734,0.017650971,0.4280368],"study_design_scores_gemma":[0.000024626088,0.00011571206,0.00043044466,0.00014080644,0.00003911553,0.0004718065,0.0002918902,0.021977214,0.0143424785,0.8457994,0.11631593,0.000050508686],"about_ca_topic_score_codex":0.00082256977,"about_ca_topic_score_gemma":0.0014247334,"teacher_disagreement_score":0.019794103,"about_ca_system_score_codex":0.0010846809,"about_ca_system_score_gemma":0.00083884783,"threshold_uncertainty_score":0.0662179},"labels":[],"label_agreement":null},{"id":"W152712179","doi":"10.1007/978-3-642-40273-9_19","title":"A Survey of Data Structures in the Bitprobe Model","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computation; Computer science; Context (archaeology); Perceptron; Algorithm; Bit (key); Data structure; Theoretical computer science; Arithmetic; Artificial intelligence; Mathematics; Programming language; Geography; Artificial neural network; Computer security","score_opus":0.07149321344670191,"score_gpt":0.2928878472238789,"score_spread":0.221394633777177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152712179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0171728,0.19430259,0.7311096,0.0067372657,0.0010587753,0.00031338213,0.0017452053,0.0026308084,0.04492951],"genre_scores_gemma":[0.1904003,0.25063634,0.5166189,0.0055024265,0.0029044156,0.0010431593,0.0045079486,0.0024839155,0.025902554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996942,0.00065923657,0.00029018903,0.00046730466,0.0014060185,0.00023518718],"domain_scores_gemma":[0.99564016,0.0019778921,0.00028239554,0.0014735971,0.00048980385,0.00013618248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029750876,0.001247663,0.0019372,0.0035494687,0.0014670506,0.005483795,0.0036048996,0.0022590829,0.009160455],"category_scores_gemma":[0.008277956,0.0015585538,0.0013785877,0.014186877,0.0030019116,0.018327193,0.003198604,0.0038255753,0.004019293],"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":[0.00013924362,0.00011391188,0.00059994636,0.0012496082,0.000030983818,0.00007445828,0.00019410522,0.013921464,0.0015531239,0.7271211,0.02154369,0.23345828],"study_design_scores_gemma":[0.000032629363,0.00014201313,0.00030957584,0.0006410787,0.000043468102,0.000591996,0.00009948723,0.043344744,0.0028981552,0.78197914,0.16984633,0.00007129417],"about_ca_topic_score_codex":0.0014868532,"about_ca_topic_score_gemma":0.0013763241,"teacher_disagreement_score":0.009160455,"about_ca_system_score_codex":0.0033829971,"about_ca_system_score_gemma":0.002992792,"threshold_uncertainty_score":0.030644774},"labels":[],"label_agreement":null},{"id":"W1528425384","doi":"10.1109/spdp.1990.143551","title":"An optimal parallel minimax tree algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Minimax; Computer science; Tree (set theory); Construct (python library); Algorithm; Parallel algorithm; Running time; Theoretical computer science; Mathematics; Combinatorics; Mathematical optimization; Programming language","score_opus":0.02218531080508962,"score_gpt":0.2459469508847347,"score_spread":0.22376164007964508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528425384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015352146,0.00048388357,0.9690833,0.00054312526,0.00011246332,0.00010903677,0.00019674013,0.0016767057,0.012442591],"genre_scores_gemma":[0.11930434,0.00027775546,0.86514395,0.0002422915,0.00008797858,0.0002890859,0.00050583103,0.00027261995,0.013876104],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99954575,0.0000662235,0.000022929573,0.00010913672,0.00019262776,0.00006326447],"domain_scores_gemma":[0.99974257,0.00008944829,0.00001875181,0.00006436178,0.00006501986,0.00001987824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043884845,0.00044360038,0.00085226045,0.0008204221,0.000805431,0.0009360941,0.0013291365,0.0008788962,0.01067389],"category_scores_gemma":[0.0017136412,0.0004144927,0.00049841066,0.0010846917,0.00046125398,0.0017559362,0.001308058,0.0009660908,0.0027308227],"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":[0.00035953597,0.00017593717,0.0004157486,0.00022412089,0.0000418251,0.00015338416,0.00012829092,0.17612365,0.01246234,0.13490668,0.030098254,0.6449102],"study_design_scores_gemma":[0.0002281179,0.00013938331,0.00021875314,0.000035470126,0.000020057696,0.00024914558,0.000048603946,0.8402898,0.0053368118,0.13373166,0.019677773,0.000024394192],"about_ca_topic_score_codex":0.0010068503,"about_ca_topic_score_gemma":0.0017186997,"teacher_disagreement_score":0.01067389,"about_ca_system_score_codex":0.0005869916,"about_ca_system_score_gemma":0.0014121615,"threshold_uncertainty_score":0.035707712},"labels":[],"label_agreement":null},{"id":"W1530348136","doi":"10.1016/j.ascom.2015.05.003","title":"Data compression in the petascale astronomy era: A GERLUMPH case study","year":2015,"lang":"en","type":"article","venue":"Astronomy and Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Petascale computing; Computer science; Astronomy; Supercomputer; Parallel computing; Physics","score_opus":0.06503489010864412,"score_gpt":0.3028874195124404,"score_spread":0.2378525294037963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530348136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8590479,0.0056642108,0.06091182,0.010362855,0.0002593486,0.0002491176,0.0011381722,0.0013858234,0.060980562],"genre_scores_gemma":[0.94658834,0.0020303382,0.036917068,0.0005699317,0.00016866166,0.00004527517,0.00044731723,0.00021451873,0.013018437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903536,0.00018522119,0.000043759224,0.00008857666,0.0005102385,0.00013697227],"domain_scores_gemma":[0.9965783,0.002175163,0.00015107999,0.0005704082,0.00037353134,0.00015152009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011034817,0.00039657255,0.00040539348,0.0008143267,0.0012401349,0.0020695943,0.0012120809,0.0017347654,0.0029599508],"category_scores_gemma":[0.006216842,0.00016931209,0.0003348157,0.0025005178,0.0016297362,0.0021034312,0.001308832,0.000976749,0.00064023066],"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":[0.0028485986,0.0015438604,0.042244315,0.0011623369,0.00020635506,0.03723483,0.004316917,0.12711467,0.021275256,0.12371103,0.071411915,0.56692994],"study_design_scores_gemma":[0.00043710924,0.0014398004,0.032542106,0.00036586926,0.00019729264,0.04992003,0.0063957665,0.49839512,0.08969223,0.105692945,0.21469651,0.0002251868],"about_ca_topic_score_codex":0.004525142,"about_ca_topic_score_gemma":0.0053283726,"teacher_disagreement_score":0.004525142,"about_ca_system_score_codex":0.00094572536,"about_ca_system_score_gemma":0.0005291808,"threshold_uncertainty_score":0.009902},"labels":[],"label_agreement":null},{"id":"W1532348468","doi":"10.1007/978-3-540-30140-0_33","title":"Dynamic Shannon Coding","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Huffman coding; Shannon–Fano coding; Variable-length code; Tunstall coding; Computer science; Coding (social sciences); Context-adaptive binary arithmetic coding; Algorithm; Upper and lower bounds; Context-adaptive variable-length coding; Prefix code; Prefix; Arithmetic coding; Theoretical computer science; Data compression; Mathematics; Decoding methods; Block code; Linear code; Statistics","score_opus":0.013131127827712762,"score_gpt":0.24681742799066775,"score_spread":0.233686300162955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532348468","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009950103,0.0047635543,0.45590806,0.0020840338,0.0015754128,0.0000898237,0.0007097848,0.0009875724,0.5239316],"genre_scores_gemma":[0.41288704,0.011069896,0.15699556,0.002185594,0.0017663648,0.00034012343,0.0019203866,0.0011204528,0.41171455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99962103,0.0000619066,0.000014579469,0.00005414234,0.00020707153,0.0000411905],"domain_scores_gemma":[0.9995555,0.00014893217,0.000024820203,0.0001473493,0.000093830065,0.00002966343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037507317,0.000705495,0.00051995914,0.0013476484,0.00078730605,0.0016467065,0.0006697655,0.0009743984,0.021422045],"category_scores_gemma":[0.0016497525,0.00033455627,0.00033133168,0.0014605612,0.0014312678,0.0019755955,0.001565089,0.0018323228,0.005543996],"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":[0.000020577485,0.000009990539,0.000048018886,0.000042016836,0.000005490782,0.000039367183,0.000044804903,0.0035789867,0.0017316227,0.91959316,0.0123871695,0.062498827],"study_design_scores_gemma":[0.000009686129,0.000022706045,0.00013694908,0.000068996225,0.000011598783,0.0003217277,0.00003331203,0.027628627,0.004901294,0.8775314,0.08929989,0.000033878205],"about_ca_topic_score_codex":0.0005496471,"about_ca_topic_score_gemma":0.0005485174,"teacher_disagreement_score":0.021422045,"about_ca_system_score_codex":0.00074089173,"about_ca_system_score_gemma":0.0007403705,"threshold_uncertainty_score":0.071663916},"labels":[],"label_agreement":null},{"id":"W1532366404","doi":"10.1007/3-540-45784-4_7","title":"Improved Approximation Algorithms for NMR Spectral Peak Assignment","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bipartite graph; Disjoint sets; Matching (statistics); Combinatorics; Mathematics; Algorithm; Approximation algorithm; Blossom algorithm; Graph; Discrete mathematics","score_opus":0.023991185663024207,"score_gpt":0.25009370055341273,"score_spread":0.22610251489038852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532366404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002476184,0.0003350487,0.99477947,0.00012278427,0.00008682537,0.00003687686,0.000091793634,0.0009025823,0.0011684746],"genre_scores_gemma":[0.031568184,0.00041803764,0.9629164,0.00012312457,0.00014756233,0.00022631673,0.00057717756,0.00037848306,0.003644736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749124,0.0007363017,0.00016666498,0.00037139977,0.00097316253,0.00026122914],"domain_scores_gemma":[0.9930347,0.0038412677,0.00031783103,0.0016690663,0.0009528909,0.00018434373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029998573,0.0023189567,0.0026023162,0.0022739267,0.001109232,0.0027813085,0.005173534,0.0022907897,0.012241632],"category_scores_gemma":[0.015357594,0.0011294768,0.0015940055,0.00511744,0.0014244099,0.004616009,0.003530766,0.0045687174,0.005494892],"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":[0.00075187715,0.0003084965,0.0004396972,0.00031363446,0.00009113662,0.0000843652,0.00018762525,0.24267584,0.0055057216,0.07169739,0.018383471,0.65956074],"study_design_scores_gemma":[0.000075219235,0.00004123868,0.00012904238,0.00002077542,0.000027652404,0.00007963441,0.00003677711,0.932414,0.002163041,0.061356623,0.0036359236,0.000020063464],"about_ca_topic_score_codex":0.004711576,"about_ca_topic_score_gemma":0.0057023834,"teacher_disagreement_score":0.012241632,"about_ca_system_score_codex":0.0021727858,"about_ca_system_score_gemma":0.0022449915,"threshold_uncertainty_score":0.040952325},"labels":[],"label_agreement":null},{"id":"W1532640741","doi":"","title":"On the top-down tree inclusion","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"Combinatorics; Tree (set theory); Mathematics; Matching (statistics); Space (punctuation); Node (physics); Discrete mathematics; Computer science; Physics; Statistics","score_opus":0.008249338377277203,"score_gpt":0.21734069712212556,"score_spread":0.20909135874484835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532640741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025881212,0.0012014972,0.9534336,0.0013614643,0.00020044784,0.0002768888,0.00072388235,0.0017427597,0.01517832],"genre_scores_gemma":[0.15075657,0.0013444811,0.8262601,0.00090453355,0.00027100806,0.00028046485,0.0019569567,0.00051923376,0.017706651],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981256,0.00031381226,0.00012530836,0.0004767413,0.0007188998,0.00023967634],"domain_scores_gemma":[0.9975514,0.0009311195,0.0001372244,0.0009276336,0.00033126143,0.00012131626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001379316,0.0008140191,0.0013020148,0.0019128086,0.0014594072,0.00261491,0.0026547634,0.0014694688,0.00894365],"category_scores_gemma":[0.0064050686,0.0006117459,0.001447814,0.0037403493,0.0015533979,0.008214998,0.005373185,0.0019774672,0.0029343644],"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":[0.0005668153,0.0003303686,0.0012049725,0.0006020199,0.00007834246,0.0005242305,0.00052106247,0.052098297,0.007458638,0.15801325,0.027257059,0.75134504],"study_design_scores_gemma":[0.00007954822,0.00018557301,0.00047605694,0.00017729407,0.00009620159,0.00079399976,0.00031456113,0.42998323,0.015101058,0.5105591,0.042189386,0.000044026452],"about_ca_topic_score_codex":0.002280681,"about_ca_topic_score_gemma":0.0031344588,"teacher_disagreement_score":0.00894365,"about_ca_system_score_codex":0.00081445865,"about_ca_system_score_gemma":0.0013490757,"threshold_uncertainty_score":0.029919505},"labels":[],"label_agreement":null},{"id":"W1533424905","doi":"10.1109/pimrc.2005.1651608","title":"Improved Upper Bound for Erasure Recovery in Binary Product Codes","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Erasure; Online codes; Erasure code; Tornado code; Decoding methods; Computer science; Hamming code; Hamming distance; Code (set theory); Binary number; Binary erasure channel; Upper and lower bounds; Algorithm; Focus (optics); Product (mathematics); Block code; Mathematics; Arithmetic; Telecommunications","score_opus":0.011314947642831055,"score_gpt":0.23831085645256767,"score_spread":0.2269959088097366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533424905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04775199,0.0076079587,0.91789776,0.0006612232,0.00021872901,0.00007965331,0.00025059114,0.0011342475,0.024397897],"genre_scores_gemma":[0.8317772,0.00729266,0.15297447,0.00049559725,0.0003560297,0.00024389767,0.00043893504,0.00036520092,0.006055905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99653685,0.00060473476,0.00012915934,0.00029422823,0.0019613055,0.00047370442],"domain_scores_gemma":[0.9884701,0.007806204,0.00058424857,0.0013797422,0.0015945657,0.00016520322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031380411,0.0016908025,0.0014492534,0.0026426972,0.0007476605,0.0027650716,0.0020319268,0.0016378398,0.004636539],"category_scores_gemma":[0.023518967,0.00062064023,0.000749339,0.0018802152,0.0020941931,0.0048600966,0.0026961006,0.002945664,0.0012288024],"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":[0.00034624428,0.00013662156,0.0009537855,0.00047763827,0.00006798988,0.0004108045,0.0002886649,0.6080369,0.019088881,0.30745715,0.0032830369,0.05945226],"study_design_scores_gemma":[0.000010815038,0.000075838456,0.00031485833,0.00011730832,0.000027716425,0.0002222237,0.000038133825,0.9185685,0.0090947505,0.06927335,0.002211168,0.000045375135],"about_ca_topic_score_codex":0.0014764323,"about_ca_topic_score_gemma":0.0012815375,"teacher_disagreement_score":0.004636539,"about_ca_system_score_codex":0.002299397,"about_ca_system_score_gemma":0.0014093482,"threshold_uncertainty_score":0.0166834},"labels":[],"label_agreement":null},{"id":"W1534895432","doi":"","title":"The Shortest Common Superstring Problem and Viral Genome Compression","year":2006,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Superstring theory; Upper and lower bounds; Genome; Combinatorics; Mathematics; Computer science; Algorithm; Gene; Biology; Genetics; Supersymmetry","score_opus":0.006281524256892357,"score_gpt":0.2102484524311311,"score_spread":0.20396692817423875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534895432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12956001,0.0036716487,0.85061216,0.0018711465,0.00023597102,0.000104057865,0.00043041012,0.0005746285,0.01293994],"genre_scores_gemma":[0.59418833,0.003560291,0.38952616,0.00046033823,0.0004355629,0.0003670689,0.0019388681,0.00034270264,0.009180711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987281,0.00039424337,0.00007522082,0.00017738796,0.00046716965,0.00015782041],"domain_scores_gemma":[0.9967533,0.0022729414,0.00026841948,0.00038377146,0.0002453609,0.000076229364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010486277,0.00061959797,0.0009920968,0.001573835,0.0007601565,0.0016962852,0.001076211,0.0017127083,0.002976167],"category_scores_gemma":[0.006903034,0.00037174302,0.00067746406,0.003136028,0.0016750395,0.0034987188,0.0014145533,0.0016247667,0.000651159],"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":[0.0003234071,0.00012150874,0.0013044672,0.00029527946,0.000067788846,0.00027086097,0.0002608397,0.44437137,0.007649849,0.35231388,0.009951338,0.18306948],"study_design_scores_gemma":[0.00002842266,0.000059198264,0.00039941134,0.000035578203,0.0000143899,0.00024757054,0.000093762814,0.58388644,0.005745233,0.40380362,0.005663745,0.000022558575],"about_ca_topic_score_codex":0.0011470857,"about_ca_topic_score_gemma":0.0008507825,"teacher_disagreement_score":0.002976167,"about_ca_system_score_codex":0.0011175255,"about_ca_system_score_gemma":0.00081525603,"threshold_uncertainty_score":0.0099563},"labels":[],"label_agreement":null},{"id":"W1537569686","doi":"10.1109/pacrim.2005.1517260","title":"Selection in multimode coding for multiple constraints","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multi-mode optical fiber; Coding (social sciences); Computer science; Decoding methods; Encoding (memory); Selection (genetic algorithm); Channel code; Constraint (computer-aided design); Cascade; Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Telecommunications; Engineering; Optical fiber","score_opus":0.02314587946194829,"score_gpt":0.27412997167123715,"score_spread":0.25098409220928886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537569686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07336372,0.00028035472,0.92115444,0.00014101194,0.00003738897,0.000057705358,0.000040277955,0.00017884804,0.0047462746],"genre_scores_gemma":[0.6511325,0.0002787136,0.34507793,0.00013446216,0.00004707478,0.00016225869,0.000090531226,0.000055019045,0.0030214714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995357,0.00014516329,0.000018193974,0.00006908028,0.00018492801,0.000046919497],"domain_scores_gemma":[0.99904484,0.00057702465,0.000084530744,0.00010107777,0.00015956437,0.000032869237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041081643,0.0003976581,0.00026477702,0.0004144447,0.00039618145,0.000334082,0.0004737933,0.00039276583,0.0013485138],"category_scores_gemma":[0.0017432758,0.00016564789,0.00025345222,0.00063137495,0.0003974631,0.000842048,0.00047148284,0.00046799137,0.00026312415],"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":[0.0004902387,0.00012934986,0.0020071599,0.0002063434,0.000066979446,0.0007888425,0.0005036464,0.30242845,0.25835642,0.12603219,0.0027830987,0.3062072],"study_design_scores_gemma":[0.000031135536,0.00018148101,0.00041502848,0.000017631486,0.000014137267,0.0003077657,0.000031539497,0.92424345,0.050462093,0.020510428,0.003755971,0.000029396979],"about_ca_topic_score_codex":0.0010129971,"about_ca_topic_score_gemma":0.0017104361,"teacher_disagreement_score":0.0013485138,"about_ca_system_score_codex":0.00037462704,"about_ca_system_score_gemma":0.00038427854,"threshold_uncertainty_score":0.004511237},"labels":[],"label_agreement":null},{"id":"W1539533914","doi":"10.1007/978-3-540-30219-3_27","title":"New Algorithms for Multiple DNA Sequence Alignment","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Algorithm; Sequence (biology); Computational biology; Multiple sequence alignment; DNA sequencing; DNA; Sequence alignment; Biology; Genetics; Gene; Peptide sequence","score_opus":0.033965492137359596,"score_gpt":0.2731560222180068,"score_spread":0.23919053008064717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539533914","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051343744,0.0010399702,0.99512863,0.00008884209,0.0003501499,0.000032709468,0.00008310202,0.0019227088,0.00084040035],"genre_scores_gemma":[0.0032863477,0.0008518322,0.99166745,0.00009744074,0.00019250774,0.00012631674,0.0005521755,0.00040225446,0.0028236746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705493,0.00057980674,0.00029424028,0.0006372131,0.0013199983,0.000113733615],"domain_scores_gemma":[0.99635124,0.0016397103,0.00023448878,0.00087006355,0.000800312,0.00010422687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002550392,0.002682558,0.002512815,0.003662344,0.0013168425,0.0030261816,0.0044758017,0.0023743787,0.011181605],"category_scores_gemma":[0.008208598,0.0018718346,0.0016436591,0.005325611,0.0011829489,0.0069741243,0.0028818783,0.0049352753,0.011663401],"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":[0.00019423949,0.000102005426,0.00020647542,0.00047059002,0.0001271773,0.00012617595,0.00013844375,0.017225053,0.017581701,0.04120382,0.021607462,0.9010169],"study_design_scores_gemma":[0.00017596278,0.00018014299,0.00051408436,0.0002466805,0.00018745256,0.0015439381,0.00012021427,0.57614356,0.04591749,0.20827003,0.16654366,0.00015683532],"about_ca_topic_score_codex":0.00069377536,"about_ca_topic_score_gemma":0.0012408822,"teacher_disagreement_score":0.011181605,"about_ca_system_score_codex":0.000845214,"about_ca_system_score_gemma":0.0007423649,"threshold_uncertainty_score":0.037406147},"labels":[],"label_agreement":null},{"id":"W1539735287","doi":"10.1007/978-3-540-73545-8_47","title":"An Improved Algorithm for Tree Edit Distance Incorporating Structural Linearity","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Linearity; Algorithm; Computer science; Tree (set theory); Edit distance; Mathematics; Engineering; Combinatorics; Electronic engineering","score_opus":0.019891060574186565,"score_gpt":0.2802475830311097,"score_spread":0.26035652245692315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539735287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038021454,0.00013941305,0.9921456,0.000047303973,0.00011359566,0.00007213077,0.0001208038,0.0026077563,0.00095128175],"genre_scores_gemma":[0.022107577,0.00007803165,0.97355765,0.00005250436,0.00006734535,0.000101129845,0.0004326173,0.00041788252,0.0031851581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668604,0.00044801852,0.00028443616,0.0008480062,0.00153827,0.00019517214],"domain_scores_gemma":[0.99507326,0.0014596417,0.00014255258,0.0018056531,0.0013778807,0.00014093347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016193212,0.0012166005,0.002099438,0.0027292103,0.0012599918,0.0021293792,0.0038459583,0.0015934578,0.008265674],"category_scores_gemma":[0.007441988,0.00081210036,0.0013360961,0.0038562152,0.0008995141,0.0045687957,0.0036047553,0.0024990898,0.005446306],"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":[0.00023829806,0.00022139832,0.0005768604,0.0002280097,0.00009143313,0.00013074704,0.00020012051,0.021603124,0.028090823,0.0328354,0.010289555,0.90549433],"study_design_scores_gemma":[0.00019686493,0.0004900746,0.00092351175,0.00005072131,0.00016295588,0.0009894276,0.00015590727,0.80563855,0.064544275,0.07821751,0.048481353,0.00014882836],"about_ca_topic_score_codex":0.0033418126,"about_ca_topic_score_gemma":0.006716433,"teacher_disagreement_score":0.008265674,"about_ca_system_score_codex":0.0010284215,"about_ca_system_score_gemma":0.0020567628,"threshold_uncertainty_score":0.02765143},"labels":[],"label_agreement":null},{"id":"W1540226096","doi":"10.1007/978-3-540-71233-6_36","title":"Efficient and Scalable Indexing Techniques for Biological Sequence Data","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Search engine indexing; Scalability; Computer science; Suffix tree; Suffix; Sequence (biology); Data mining; Data structure; Search algorithm; Representation (politics); Variety (cybernetics); Theoretical computer science; Information retrieval; Algorithm; Artificial intelligence; Database; Programming language","score_opus":0.08733877345549901,"score_gpt":0.32181524515835597,"score_spread":0.23447647170285696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540226096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017150095,0.0059560384,0.95344764,0.000768153,0.00064789545,0.00031285424,0.0042307363,0.014562899,0.002923653],"genre_scores_gemma":[0.046722263,0.0034355656,0.9319419,0.00020961191,0.00043742196,0.00048911164,0.012212234,0.0007992432,0.003752512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984829,0.00016769188,0.00022804615,0.00022309598,0.00076607923,0.00013218111],"domain_scores_gemma":[0.9962029,0.0012708752,0.00029588433,0.001502922,0.00059956656,0.00012777085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013018685,0.0013821563,0.0017970095,0.004764658,0.001311132,0.0027599852,0.0030415778,0.0011743858,0.0044739577],"category_scores_gemma":[0.0056828507,0.00081246224,0.0013077733,0.011815498,0.00094805245,0.0055184574,0.0028823717,0.0017769971,0.0037927597],"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":[0.00033572482,0.00017288078,0.00058164983,0.0008768181,0.00008688069,0.00022329591,0.0002961799,0.010870646,0.07502332,0.022518521,0.041151643,0.8478625],"study_design_scores_gemma":[0.0003950494,0.0005671501,0.0020959089,0.00026990304,0.00025390444,0.0019271165,0.0005356073,0.50482106,0.18589734,0.2032437,0.09979426,0.00019901498],"about_ca_topic_score_codex":0.001686538,"about_ca_topic_score_gemma":0.0028055161,"teacher_disagreement_score":0.004764658,"about_ca_system_score_codex":0.00096361304,"about_ca_system_score_gemma":0.0019096951,"threshold_uncertainty_score":0.0149668455},"labels":[],"label_agreement":null},{"id":"W1541587921","doi":"10.1016/j.tcs.2015.06.056","title":"Indeterminate strings, prefix arrays &amp; undirected graphs","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Mathematics; Cardinality (data modeling); String (physics); Prefix; Indeterminate; Alphabet; Discrete mathematics; Graph; Upper and lower bounds; Computer science","score_opus":0.025247949617459544,"score_gpt":0.26912634536172153,"score_spread":0.24387839574426198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541587921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068775624,0.009918264,0.8495553,0.0061457558,0.00089797593,0.00009440406,0.0014407247,0.0010677135,0.062104203],"genre_scores_gemma":[0.6256497,0.011771301,0.31642175,0.0015323535,0.0012671055,0.00026595965,0.0015615164,0.0004976071,0.041032758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989698,0.00043278368,0.000053840024,0.00023422664,0.00024204583,0.00006725082],"domain_scores_gemma":[0.9941274,0.0041395216,0.0005007154,0.0007105062,0.00038536955,0.00013647666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009051395,0.0005132273,0.00058903306,0.001992193,0.00087038445,0.0028481677,0.0009895429,0.001361048,0.005307146],"category_scores_gemma":[0.009265632,0.0004115518,0.0002968113,0.0051901164,0.0025813105,0.004412358,0.001082903,0.0018305707,0.0013432014],"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":[0.000063161984,0.000023127492,0.00031792105,0.00013837841,0.000009373449,0.0001162537,0.00014459716,0.016203854,0.00076340855,0.902028,0.008395742,0.07179625],"study_design_scores_gemma":[0.000004387886,0.000008809888,0.00007459281,0.000029880252,0.0000065535555,0.00013241597,0.00005423219,0.025458554,0.00033685178,0.96264976,0.011233625,0.000010336446],"about_ca_topic_score_codex":0.0010752298,"about_ca_topic_score_gemma":0.0012202029,"teacher_disagreement_score":0.005307146,"about_ca_system_score_codex":0.00088238734,"about_ca_system_score_gemma":0.0006717402,"threshold_uncertainty_score":0.017754138},"labels":[],"label_agreement":null},{"id":"W1541952385","doi":"10.1007/3-540-45123-4","title":"Combinatorial Pattern Matching: 11th Annual Symposium. CPM 2000, Montreal, Canada, June 21-23, 2000, Proceedings","year":2000,"lang":"en","type":"book","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Substring; String searching algorithm; Suffix tree; Edit distance; Time complexity; Computer science; String (physics); Suffix; Combinatorics; Pattern matching; Upper and lower bounds; Compressed suffix array; Algorithm; Approximation algorithm; Trie; Mathematics; Data structure; Artificial intelligence","score_opus":0.005044390872451964,"score_gpt":0.19488955570965671,"score_spread":0.18984516483720476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541952385","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008850009,0.18281026,0.4645316,0.010448668,0.019537654,0.00053297746,0.007845675,0.014010397,0.29143283],"genre_scores_gemma":[0.035034657,0.1336912,0.17261316,0.0016758207,0.004679034,0.00046142944,0.017315704,0.0030968848,0.6314321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994361,0.00007790788,0.000031362866,0.00011471031,0.00027137806,0.000068496716],"domain_scores_gemma":[0.9987539,0.00031075336,0.000038642564,0.00023918744,0.00046509193,0.0001924089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012456292,0.001702395,0.0018041064,0.0025109856,0.000815732,0.0033533084,0.0026786178,0.0011078786,0.07474854],"category_scores_gemma":[0.0025571818,0.000942642,0.00066595647,0.006213959,0.0010937544,0.0037311937,0.0016612825,0.0016405149,0.03960189],"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":[0.000094652954,0.00007491536,0.0002869534,0.000445045,0.00004398137,0.00007720061,0.00004414938,0.0020515928,0.0017924765,0.009627381,0.71341187,0.27204973],"study_design_scores_gemma":[0.000053911175,0.00008593122,0.0014334306,0.0003626062,0.00008240975,0.0007570115,0.00010668185,0.019053021,0.0030809434,0.029951196,0.9449904,0.00004254707],"about_ca_topic_score_codex":0.01999397,"about_ca_topic_score_gemma":0.05502734,"teacher_disagreement_score":0.07474854,"about_ca_system_score_codex":0.0028860194,"about_ca_system_score_gemma":0.0038078518,"threshold_uncertainty_score":0.25005877},"labels":[],"label_agreement":null},{"id":"W1542422837","doi":"10.3233/fi-2011-536","title":"Minimum Unique Substrings and Maximum Repeats","year":2011,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"McMaster University; Western University","funders":"","keywords":"Substring; Computer science; Mathematics; Programming language; Data structure","score_opus":0.02942245181713476,"score_gpt":0.2242724471165491,"score_spread":0.19484999529941432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542422837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11930379,0.002732041,0.86716527,0.00067603093,0.000112215435,0.00005474637,0.00045139896,0.000379562,0.009124887],"genre_scores_gemma":[0.53561825,0.0016570332,0.4573568,0.0002451814,0.0002661819,0.00012068016,0.0008528887,0.00022843387,0.0036545603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983962,0.00043629235,0.00014224782,0.0005456797,0.00036426657,0.00011524875],"domain_scores_gemma":[0.9907346,0.0063003474,0.00093155727,0.0012465733,0.0005406629,0.00024618246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013131246,0.00040355464,0.0011258529,0.0018595725,0.0008863376,0.0016242632,0.0013105402,0.0010581551,0.0028239256],"category_scores_gemma":[0.013023989,0.00046169956,0.0006690415,0.0023184207,0.0016354627,0.0052847117,0.0015970658,0.0017420249,0.00066080916],"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":[0.00028729538,0.00009493139,0.0034067067,0.00067668996,0.00006091563,0.00031925956,0.0004423302,0.033070832,0.011656383,0.6910986,0.0039168163,0.25496942],"study_design_scores_gemma":[0.00001655324,0.000060161918,0.00076976314,0.000059298378,0.000021180056,0.0006329946,0.00011225479,0.060990594,0.0083133355,0.9227368,0.0062595685,0.000027387185],"about_ca_topic_score_codex":0.0002234021,"about_ca_topic_score_gemma":0.00024698218,"teacher_disagreement_score":0.0028239256,"about_ca_system_score_codex":0.0006109314,"about_ca_system_score_gemma":0.0005589427,"threshold_uncertainty_score":0.009446979},"labels":[],"label_agreement":null},{"id":"W1543447953","doi":"10.1136/jamia.2002.0090409","title":"American College of Medical Informatics Fellows and International Associates, 2001","year":2002,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Library science; Informatics; Medical school; Research center; Political science; Medical education; Medicine; Computer science; Law","score_opus":0.01296708532550859,"score_gpt":0.26989050053070085,"score_spread":0.25692341520519224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543447953","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015519311,0.03073068,0.010473489,0.08801862,0.034754008,0.0005507029,0.0032923387,0.0024185462,0.82820964],"genre_scores_gemma":[0.0056503178,0.026196163,0.011135588,0.0136490865,0.0053085564,0.0006131856,0.0037118027,0.000678898,0.9330564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747866,0.00045876787,0.00029255546,0.0003274326,0.0010604325,0.00038222416],"domain_scores_gemma":[0.9901928,0.0011941947,0.00050329184,0.0010052446,0.0039541903,0.0031502682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042916154,0.0010206748,0.0006399829,0.004501802,0.001984909,0.006458115,0.0015712649,0.0029543585,0.27921048],"category_scores_gemma":[0.014780442,0.0007097289,0.00048556132,0.005364675,0.0011090708,0.0063089575,0.0046289405,0.0044468152,0.23160441],"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":[0.0000118067555,0.000032375894,0.00034462518,0.000057451583,0.0000017247633,0.000038361883,0.0000743834,0.00001569167,0.00006211801,0.0035508543,0.86057156,0.13523914],"study_design_scores_gemma":[0.000003506794,0.0000047109256,0.00041510392,0.00010135422,0.0000011835255,0.00012822385,0.000063872176,0.000021442316,0.00002327355,0.0010881361,0.9981458,0.000003335673],"about_ca_topic_score_codex":0.0022062778,"about_ca_topic_score_gemma":0.0050288816,"teacher_disagreement_score":0.27921048,"about_ca_system_score_codex":0.001502478,"about_ca_system_score_gemma":0.0065391934,"threshold_uncertainty_score":0.9340521},"labels":[],"label_agreement":null},{"id":"W1545746670","doi":"10.1109/dcc.1998.672253","title":"Higher compression from the Burrows-Wheeler transform by modified sorting","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"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":"Substring; Sorting; Computer science; Algorithm; ASCII; Character (mathematics); Lossless compression; Sorting algorithm; Data compression; sort; Compression (physics); Encoding (memory); Compression ratio; Set (abstract data type); Theoretical computer science; Mathematics; Artificial intelligence; Information retrieval","score_opus":0.03153017270255547,"score_gpt":0.23198447448910098,"score_spread":0.2004543017865455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1545746670","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17128517,0.0063082627,0.6996413,0.002906994,0.0057844827,0.00034442174,0.0043234373,0.0137067195,0.09569927],"genre_scores_gemma":[0.46527848,0.0027876543,0.45040342,0.00102529,0.0017920836,0.00028703143,0.008919771,0.0015790509,0.06792721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995925,0.000028145578,0.000030051524,0.000038213097,0.00026913837,0.000041916235],"domain_scores_gemma":[0.9992855,0.00023406817,0.000030673884,0.00020226065,0.00022652723,0.000020966943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030236857,0.00048244256,0.0005473671,0.0010956341,0.00034829119,0.0009805472,0.0006949155,0.00048756984,0.018493528],"category_scores_gemma":[0.0016712744,0.00012507461,0.00037699964,0.0023490386,0.00040004493,0.0011522049,0.0007194699,0.0009436615,0.0048846197],"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":[0.0006522703,0.00012044082,0.0008415268,0.0005545151,0.00005040476,0.0010038961,0.00028697224,0.025405925,0.14480959,0.06744016,0.060426023,0.69840825],"study_design_scores_gemma":[0.00017667838,0.00041331633,0.0027474153,0.00017476696,0.00010413811,0.0019942317,0.00015785017,0.3518064,0.33046553,0.039692912,0.27212155,0.00014513098],"about_ca_topic_score_codex":0.0014208461,"about_ca_topic_score_gemma":0.0015221925,"teacher_disagreement_score":0.018493528,"about_ca_system_score_codex":0.00053931895,"about_ca_system_score_gemma":0.00040494118,"threshold_uncertainty_score":0.06186706},"labels":[],"label_agreement":null},{"id":"W1546006857","doi":"10.1007/978-3-540-30500-2_16","title":"An Automata Approach to Match Gapped Sequence Tags Against Protein Database","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Automaton; Sequence (biology); Database; Theoretical computer science; Information retrieval; Artificial intelligence","score_opus":0.028416006976202217,"score_gpt":0.271612990929167,"score_spread":0.2431969839529648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546006857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024698095,0.00018928254,0.96768326,0.00018734175,0.00014494648,0.00010262212,0.00031229862,0.0044233575,0.002258854],"genre_scores_gemma":[0.32464197,0.0003071143,0.66723955,0.00033209077,0.000073448085,0.0002894403,0.00092217675,0.00042307063,0.005771156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991456,0.00015874986,0.0001147691,0.0002631627,0.00023643288,0.00008113874],"domain_scores_gemma":[0.99765575,0.0012434919,0.00009124303,0.0005135454,0.0004105232,0.000085470994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000762437,0.0006136309,0.0009573614,0.001334591,0.000932956,0.0014902728,0.0023270573,0.0013172074,0.0037813596],"category_scores_gemma":[0.0032939436,0.00054874405,0.0012030315,0.0012887875,0.0010283573,0.0027090257,0.0019168949,0.0010230255,0.0016203307],"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":[0.001067017,0.0004860977,0.003505947,0.00055482716,0.0002818318,0.00089246046,0.00071803946,0.20905265,0.065702006,0.15537354,0.009846602,0.552519],"study_design_scores_gemma":[0.000022486129,0.00011854653,0.00022511459,0.000024292372,0.000065025386,0.00023264113,0.00011881216,0.8656087,0.021788241,0.10772735,0.004037241,0.000031570962],"about_ca_topic_score_codex":0.0038579227,"about_ca_topic_score_gemma":0.004642337,"teacher_disagreement_score":0.0038579227,"about_ca_system_score_codex":0.0008086763,"about_ca_system_score_gemma":0.0010992896,"threshold_uncertainty_score":0.012649894},"labels":[],"label_agreement":null},{"id":"W1548829356","doi":"","title":"Branching fractions for chi(cJ) -> p(p)over-bar pi(0), p(p)over-bar eta, and p(p)over-bar omega","year":2010,"lang":"en","type":"article","venue":"Purdue e-Pubs (Purdue University System)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Alfred P. Sloan Foundation; U.S. Department of Energy; Science and Technology Facilities Council; National Science Foundation","keywords":"Physics; Humanities; Theology; Combinatorics; Philosophy; Mathematics","score_opus":0.008706116039169712,"score_gpt":0.21500157624557295,"score_spread":0.20629546020640324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548829356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814997,0.00049354613,0.007549556,0.00006023521,0.000016375276,0.000026030471,0.002312636,0.00041793144,0.007624076],"genre_scores_gemma":[0.9900906,0.00032900347,0.0042113326,0.000060087536,0.000011304388,0.000036861522,0.003483583,0.00013880861,0.0016383728],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99956053,0.000037689766,0.000020510652,0.00015220746,0.00013618919,0.00009286996],"domain_scores_gemma":[0.998473,0.000604472,0.00038601775,0.000121084195,0.0002655106,0.00014991326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010263157,0.00069817086,0.0002951239,0.0016451323,0.00070330023,0.0010234202,0.00057770207,0.0005185582,0.0041468698],"category_scores_gemma":[0.0018769071,0.00031703088,0.0003362098,0.0020695718,0.00043303418,0.0007904465,0.00066122715,0.000744074,0.00052930514],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056274557,0.0005751163,0.31930265,0.0003575095,0.00038183838,0.0014192455,0.000606148,0.011480513,0.59273463,0.011889275,0.0040320535,0.051593553],"study_design_scores_gemma":[0.00012110439,0.00080393715,0.4803842,0.00005671282,0.00022798113,0.003911539,0.0004789493,0.040538367,0.45754954,0.004403855,0.011336087,0.00018775799],"about_ca_topic_score_codex":0.0015466418,"about_ca_topic_score_gemma":0.0035056067,"teacher_disagreement_score":0.0041468698,"about_ca_system_score_codex":0.0005316721,"about_ca_system_score_gemma":0.00029564014,"threshold_uncertainty_score":0.013872683},"labels":[],"label_agreement":null},{"id":"W1549299641","doi":"10.1007/978-3-540-69068-9_27","title":"Towards a Solution to the “Runs” Conjecture","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Conjecture; Upper and lower bounds; String (physics); Combinatorics; Mathematics; Computer science; Mathematical physics; Mathematical analysis","score_opus":0.0195496255433816,"score_gpt":0.24630945086831418,"score_spread":0.22675982532493258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1549299641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055207662,0.0038909186,0.64721996,0.053046245,0.005281102,0.00009704401,0.0008365425,0.0029315292,0.23148906],"genre_scores_gemma":[0.57780373,0.0042342436,0.27656737,0.019047793,0.00656781,0.00046748543,0.0027833367,0.0030981225,0.10943013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99747854,0.00078526465,0.00009948136,0.00066514825,0.00065199827,0.00031953116],"domain_scores_gemma":[0.9902484,0.00594605,0.0003827061,0.0023507024,0.00076584955,0.00030627014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028677136,0.001445682,0.0018677001,0.0011074487,0.0028181646,0.004242308,0.0031089108,0.0048291027,0.018238036],"category_scores_gemma":[0.019153312,0.0010579716,0.0018237507,0.0014985201,0.0065372055,0.01505559,0.0063647614,0.010905105,0.006582306],"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":[0.00009862617,0.00003026713,0.00022362759,0.00011293741,0.00002353132,0.00006427424,0.00017147676,0.002473202,0.0005437341,0.95998687,0.022713162,0.013558313],"study_design_scores_gemma":[0.000023249011,0.000010953428,0.0000667298,0.000031881355,0.000010278701,0.000038340757,0.000049978167,0.0061482615,0.00027477485,0.9839631,0.009371085,0.000011433697],"about_ca_topic_score_codex":0.0011582501,"about_ca_topic_score_gemma":0.0011933481,"teacher_disagreement_score":0.018238036,"about_ca_system_score_codex":0.0011878071,"about_ca_system_score_gemma":0.0014143129,"threshold_uncertainty_score":0.061012328},"labels":[],"label_agreement":null},{"id":"W1550577131","doi":"10.1007/978-3-642-16321-0_10","title":"Why Large Closest String Instances Are Easy to Solve in Practice","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"String (physics); Hamming distance; Greedy algorithm; String searching algorithm; Computer science; Approximation algorithm; String metric; Combinatorics; Algorithm; Discrete mathematics; Mathematics; Data structure","score_opus":0.015514006894249336,"score_gpt":0.26807139282740855,"score_spread":0.25255738593315924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550577131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09161564,0.0041061346,0.80421215,0.021145768,0.0017661131,0.00033228556,0.00123824,0.0069288346,0.068654895],"genre_scores_gemma":[0.29615316,0.002235789,0.66375154,0.002341648,0.0012261515,0.00043668464,0.002166313,0.0036840758,0.028004672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937669,0.0019785815,0.00043111594,0.0017650248,0.0015212608,0.0005371494],"domain_scores_gemma":[0.9522256,0.035763673,0.0013031358,0.00788399,0.0021223044,0.00070129917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037272556,0.0010647603,0.0016061654,0.0010742147,0.0019876398,0.0057313386,0.0025431302,0.0040842625,0.044783607],"category_scores_gemma":[0.073339,0.001586777,0.0013633748,0.0030871301,0.0022527012,0.0213833,0.0038876312,0.0054449253,0.017330928],"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":[0.00076541514,0.000457178,0.0037768062,0.0014051547,0.00016376725,0.00061397697,0.0009579175,0.04481035,0.0037970198,0.2759211,0.14525865,0.5220727],"study_design_scores_gemma":[0.00017796025,0.00010789296,0.00045348928,0.00012605595,0.000039481092,0.0010348646,0.00068600464,0.076520704,0.0025348647,0.89523655,0.023045732,0.000036389938],"about_ca_topic_score_codex":0.0009202097,"about_ca_topic_score_gemma":0.0014158619,"teacher_disagreement_score":0.044783607,"about_ca_system_score_codex":0.00076540356,"about_ca_system_score_gemma":0.0020839018,"threshold_uncertainty_score":0.14981616},"labels":[],"label_agreement":null},{"id":"W1550738266","doi":"10.25596/jalc-2004-217","title":"State Complexity of Shuffle on Trajectories","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"Queen's University","funders":"","keywords":"Nondeterministic algorithm; Upper and lower bounds; State (computer science); String (physics); Mathematics; Computational complexity theory; Constant (computer programming); Trajectory; Combinatorics; Time complexity; Discrete mathematics; Computer science; Algorithm; Mathematical analysis; Physics","score_opus":0.04238509054814154,"score_gpt":0.2690829022559006,"score_spread":0.22669781170775904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550738266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4954309,0.00042245883,0.48901293,0.00093050743,0.00004117081,0.00015989163,0.0016852046,0.0012318072,0.011085201],"genre_scores_gemma":[0.93103236,0.00039120912,0.05877889,0.00013291258,0.000035824345,0.0003178782,0.0020465741,0.00033365624,0.0069306293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972173,0.0003343709,0.00023537915,0.0005540008,0.00086644397,0.0007924502],"domain_scores_gemma":[0.98387724,0.009959818,0.0010393905,0.0027446465,0.0016817439,0.00069714454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012740756,0.00055646134,0.0011608634,0.0013147459,0.0012742225,0.0031035303,0.0014738322,0.0011094973,0.007234414],"category_scores_gemma":[0.012017327,0.00044581236,0.0013917133,0.0016436082,0.0018629434,0.007799344,0.0025986603,0.0022497473,0.0007676182],"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":[0.0011413367,0.0001759154,0.005567547,0.00047984367,0.00008747448,0.00025113983,0.0006066353,0.46300164,0.02604355,0.44320425,0.0027953275,0.05664532],"study_design_scores_gemma":[0.000019054565,0.00008518149,0.00085019757,0.000032760785,0.00002448424,0.00008334543,0.000078973106,0.6701007,0.018767167,0.30827597,0.0016416761,0.000040516563],"about_ca_topic_score_codex":0.0029701272,"about_ca_topic_score_gemma":0.002835358,"teacher_disagreement_score":0.007234414,"about_ca_system_score_codex":0.0027643773,"about_ca_system_score_gemma":0.002588511,"threshold_uncertainty_score":0.024201572},"labels":[],"label_agreement":null},{"id":"W1551534812","doi":"10.1007/978-3-642-03784-9_30","title":"Practical Algorithms for the Longest Common Extension Problem","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Substring; Computer science; String (physics); Computation; Algorithm; Constant (computer programming); Extension (predicate logic); Preprocessor; Time complexity; String searching algorithm; Theoretical computer science; Data structure; Mathematics; Artificial intelligence","score_opus":0.041541350322374326,"score_gpt":0.3083783851601656,"score_spread":0.26683703483779125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1551534812","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008673394,0.0011362915,0.9705154,0.0011466303,0.00033846634,0.00025310268,0.00043647512,0.0018905286,0.015609609],"genre_scores_gemma":[0.0814061,0.0010402108,0.90289986,0.00039339595,0.00060424604,0.0006418747,0.0016884183,0.0009015975,0.010424265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952468,0.0011380705,0.00037486767,0.0012172295,0.0014227965,0.0006001796],"domain_scores_gemma":[0.9862255,0.008164376,0.000587691,0.0034603062,0.0012256713,0.00033653443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004145273,0.002576587,0.0028109804,0.002977854,0.0025981772,0.0053766156,0.0059717186,0.0032084407,0.028274966],"category_scores_gemma":[0.01961007,0.0014777664,0.0026537168,0.0059092618,0.002912033,0.011824186,0.0066699046,0.0062864963,0.007842009],"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":[0.00070854364,0.00046511405,0.0006340281,0.00073460425,0.00011866919,0.00015078313,0.00049918966,0.05952926,0.003753493,0.36214626,0.044284232,0.52697575],"study_design_scores_gemma":[0.0003662999,0.0001072174,0.00020680812,0.00010324289,0.00006761659,0.0003329964,0.00020340952,0.18710785,0.0023833031,0.79323685,0.015825462,0.00005907666],"about_ca_topic_score_codex":0.0019561073,"about_ca_topic_score_gemma":0.0028746703,"teacher_disagreement_score":0.028274966,"about_ca_system_score_codex":0.0026186947,"about_ca_system_score_gemma":0.0037871625,"threshold_uncertainty_score":0.094589114},"labels":[],"label_agreement":null},{"id":"W1553071595","doi":"10.3233/fi-2011-565","title":"Self-Indexed Grammar-Based Compression","year":2011,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":96,"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; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Computer science; Grammar; Compression (physics); Natural language processing; Linguistics; Materials science; Philosophy","score_opus":0.030419670666367606,"score_gpt":0.22433861280715583,"score_spread":0.19391894214078823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553071595","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067241944,0.0011098324,0.8819641,0.0006033234,0.00039554032,0.00041058593,0.0028884513,0.022838246,0.022548039],"genre_scores_gemma":[0.33598748,0.0009934411,0.6262264,0.0007206728,0.0002605786,0.0005700882,0.008795657,0.0029708198,0.023474796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991122,0.00009194478,0.00009025502,0.00016322917,0.00044284787,0.000099521305],"domain_scores_gemma":[0.99816567,0.0004146512,0.00009111989,0.0007299236,0.00055231364,0.000046257526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041877574,0.00056997256,0.00061803416,0.0016255621,0.000423991,0.0010855746,0.0013735016,0.0006184369,0.0062914994],"category_scores_gemma":[0.0028924234,0.0003041316,0.0005496937,0.002300026,0.00076268404,0.0021346554,0.0016654284,0.000781142,0.0027054083],"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":[0.00046296863,0.00021688706,0.0013541719,0.00044363958,0.000060017046,0.000821639,0.00051541504,0.032897525,0.10285846,0.08769705,0.042428803,0.7302435],"study_design_scores_gemma":[0.00020093363,0.00040099918,0.0016835603,0.00012433954,0.000102110025,0.0020689175,0.00023848125,0.48446676,0.27051568,0.12285126,0.117229044,0.00011787172],"about_ca_topic_score_codex":0.0011471857,"about_ca_topic_score_gemma":0.0012253736,"teacher_disagreement_score":0.0062914994,"about_ca_system_score_codex":0.00068013516,"about_ca_system_score_gemma":0.0011387765,"threshold_uncertainty_score":0.021047175},"labels":[],"label_agreement":null},{"id":"W1553958932","doi":"10.1016/j.jda.2014.11.002","title":"The complexity of string partitioning","year":2014,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"European Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Alphabet; String (physics); Partition (number theory); Combinatorics; Integer (computer science); Collision; Mathematics; Computer science; Discrete mathematics","score_opus":0.03160110801655073,"score_gpt":0.2713666600122118,"score_spread":0.2397655519956611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553958932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3918485,0.0044468683,0.47631973,0.033148523,0.0010472109,0.00042965933,0.004676363,0.002087002,0.08599612],"genre_scores_gemma":[0.8498493,0.0017789343,0.12462864,0.0013917547,0.00093443965,0.00042814907,0.0032269575,0.0010364281,0.016725445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9917561,0.0026955456,0.00056798814,0.0010064116,0.0032055103,0.00076853856],"domain_scores_gemma":[0.93032795,0.05713623,0.0018497482,0.0074719223,0.0021478734,0.0010662548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004147049,0.00087531167,0.0019684976,0.002013814,0.0025000835,0.0075044595,0.0040413965,0.003524624,0.021785038],"category_scores_gemma":[0.052541386,0.0013466958,0.001799657,0.005152078,0.0035735115,0.01990876,0.005081049,0.0047856234,0.0023872603],"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":[0.0017934322,0.00036663187,0.0064947647,0.00062126626,0.00020737007,0.0004789807,0.00078961306,0.28004843,0.006856428,0.47999388,0.03989146,0.18245773],"study_design_scores_gemma":[0.00013271911,0.00006628749,0.0010917058,0.000047996495,0.00008312561,0.00027146717,0.00020442034,0.5213436,0.0025713067,0.47027093,0.003873803,0.000042741558],"about_ca_topic_score_codex":0.0031200454,"about_ca_topic_score_gemma":0.003923688,"teacher_disagreement_score":0.021785038,"about_ca_system_score_codex":0.004306825,"about_ca_system_score_gemma":0.004124241,"threshold_uncertainty_score":0.07287824},"labels":[],"label_agreement":null},{"id":"W1554279770","doi":"10.1109/icip.1999.821602","title":"A fast segmentation algorithm for bi-level image compression using JBIG2","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"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; Skew; Encoder; Encoding (memory); Compression (physics); Data compression; Segmentation; Image compression; Image segmentation; Artificial intelligence; Computer vision; Compression ratio; Algorithm; Image (mathematics); Line (geometry); Pattern recognition (psychology); Image processing; Mathematics","score_opus":0.051355080619956604,"score_gpt":0.30942601357248173,"score_spread":0.25807093295252514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554279770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035762067,0.0004042343,0.9896912,0.00013488605,0.00015486297,0.00008410941,0.000120843884,0.004021288,0.0018123463],"genre_scores_gemma":[0.029829843,0.00033637282,0.96382415,0.00013975678,0.00008468614,0.00016437468,0.00071575266,0.0005949443,0.0043100393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940526,0.000045355275,0.00005181044,0.000078279794,0.00036172778,0.000057577232],"domain_scores_gemma":[0.9993031,0.00012872546,0.00005632691,0.00015165815,0.0003197452,0.000040385345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056779984,0.0012199647,0.0006925968,0.002317308,0.0008175225,0.0012210575,0.0013569238,0.0013162418,0.006020014],"category_scores_gemma":[0.0015510854,0.0005632755,0.0005789862,0.0019120952,0.00069280405,0.0015273482,0.0012081704,0.001617198,0.004991947],"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":[0.00030437898,0.00007120706,0.00032672603,0.00019757266,0.000029341501,0.00013247196,0.00012257755,0.0067643514,0.17121308,0.007997383,0.018019924,0.79482096],"study_design_scores_gemma":[0.00019633297,0.00036292535,0.0026465952,0.00010056917,0.000074280186,0.0018493304,0.00013634365,0.43481576,0.43837363,0.015600936,0.10566601,0.00017731235],"about_ca_topic_score_codex":0.0019492649,"about_ca_topic_score_gemma":0.0029172988,"teacher_disagreement_score":0.006020014,"about_ca_system_score_codex":0.00062941713,"about_ca_system_score_gemma":0.00097020617,"threshold_uncertainty_score":0.02013892},"labels":[],"label_agreement":null},{"id":"W1554777263","doi":"10.3233/fi-2009-203","title":"Faster Algorithms for Computing Maximal Multirepeats in Multiple Sequences","year":2009,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.044114998271657734,"score_gpt":0.29313819367518373,"score_spread":0.249023195403526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554777263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043859586,0.0010240212,0.94849443,0.00026345477,0.000099478726,0.00017102865,0.000335954,0.0030874878,0.0026646524],"genre_scores_gemma":[0.097765885,0.00036979106,0.89795685,0.00010128575,0.00008649147,0.0002554613,0.0011977393,0.00031491453,0.0019515996],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984497,0.00028977238,0.0001975899,0.00037153155,0.0005247901,0.00016661777],"domain_scores_gemma":[0.99500763,0.002698271,0.0004557312,0.00102912,0.00069931947,0.000109943765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013960805,0.0011642167,0.0013397442,0.002057541,0.001065771,0.0018789861,0.0021051802,0.0013857419,0.0046796896],"category_scores_gemma":[0.008979109,0.0007131189,0.0011457829,0.004000831,0.00066277635,0.0051678484,0.0017225868,0.001303096,0.0019000998],"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":[0.00075110816,0.0002672678,0.0034751599,0.0005953567,0.00019032018,0.00024773667,0.0006599236,0.12785992,0.021739006,0.0612687,0.010247934,0.7726976],"study_design_scores_gemma":[0.0002742179,0.00024225898,0.0010341224,0.000083218016,0.00009238139,0.0005142085,0.00025743194,0.81222874,0.026549648,0.1426751,0.015981037,0.00006772665],"about_ca_topic_score_codex":0.0015526903,"about_ca_topic_score_gemma":0.003081806,"teacher_disagreement_score":0.0046796896,"about_ca_system_score_codex":0.0009779936,"about_ca_system_score_gemma":0.0017852691,"threshold_uncertainty_score":0.0156551},"labels":[],"label_agreement":null},{"id":"W1555054364","doi":"10.1007/11534273","title":"Algorithms and data structures : 9th International Workshop, WADS 2005, Waterloo, Canada, August 15-17, 2005 : proceedings","year":2005,"lang":"en","type":"book","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Combinatorics; Approximation algorithm; Algorithm; Mathematics; Discrete mathematics","score_opus":0.019826579352606517,"score_gpt":0.25347323845897685,"score_spread":0.23364665910637034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1555054364","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066809054,0.067516804,0.78958845,0.008526431,0.009706185,0.000622159,0.0060622683,0.022356424,0.08894041],"genre_scores_gemma":[0.018010996,0.045929704,0.42428908,0.0013774127,0.001807012,0.00046529263,0.017336186,0.0059622526,0.4848221],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985287,0.00014712075,0.000107301305,0.00021878447,0.00087083946,0.0001272628],"domain_scores_gemma":[0.9972677,0.0005205662,0.00006015196,0.0004963067,0.00147584,0.00017943079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020718607,0.0021951778,0.0022746583,0.0027900988,0.0015104546,0.007073749,0.0032795116,0.0015389784,0.057579886],"category_scores_gemma":[0.003915824,0.0017343978,0.0013208626,0.0072693336,0.0018343708,0.004941034,0.0018601755,0.0030551546,0.028808191],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009075265,0.00007637272,0.00017389654,0.00043754996,0.000030779393,0.000051864474,0.00017302427,0.0014319087,0.0024014344,0.016630277,0.6066997,0.37180248],"study_design_scores_gemma":[0.00005593097,0.000067460285,0.000801275,0.00032606482,0.000055834185,0.00046011468,0.00019669329,0.014955756,0.0074046203,0.029689942,0.9459336,0.000052672724],"about_ca_topic_score_codex":0.05677052,"about_ca_topic_score_gemma":0.10130314,"teacher_disagreement_score":0.9432295,"about_ca_system_score_codex":0.0046361345,"about_ca_system_score_gemma":0.008491793,"threshold_uncertainty_score":0.19262391},"labels":[],"label_agreement":null},{"id":"W1556137908","doi":"","title":"Automatic algorithm configuration based on local search","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":235,"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":"Heuristics; Computer science; Algorithm; Local search (optimization); Heuristic; Search algorithm; Mathematical optimization; Flexibility (engineering); Mathematics; Artificial intelligence","score_opus":0.015611851023779889,"score_gpt":0.273821400177054,"score_spread":0.2582095491532741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556137908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026638,0.0003656287,0.95710814,0.00011007465,0.000045413723,0.00026317572,0.00007344226,0.010614086,0.0047820727],"genre_scores_gemma":[0.37280133,0.00016815592,0.6217779,0.00018629822,0.000035933437,0.0007613899,0.00033968742,0.0026593688,0.0012698482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921157,0.0034834102,0.0006740905,0.0015419672,0.0016999947,0.00048473806],"domain_scores_gemma":[0.9848069,0.0077863703,0.0010420729,0.004240686,0.0018604919,0.00026342281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00523827,0.0019032719,0.0022531643,0.0027090556,0.0014308563,0.0027624276,0.0038131208,0.0021686617,0.005760484],"category_scores_gemma":[0.030583208,0.0012004108,0.0008793691,0.0017902383,0.0020445446,0.00374894,0.0032755847,0.002304123,0.0030496726],"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":[0.0012655037,0.0003687584,0.00503841,0.0007628044,0.00025635347,0.0004759081,0.00083229993,0.36144534,0.03552613,0.028487,0.010514968,0.55502653],"study_design_scores_gemma":[0.0002512655,0.00024009467,0.00075207505,0.00011340523,0.00008821393,0.00044843828,0.00013018724,0.9367786,0.03207092,0.022669733,0.006353297,0.000103852835],"about_ca_topic_score_codex":0.000822422,"about_ca_topic_score_gemma":0.0012178991,"teacher_disagreement_score":0.005760484,"about_ca_system_score_codex":0.0011667362,"about_ca_system_score_gemma":0.0015407819,"threshold_uncertainty_score":0.027702928},"labels":[],"label_agreement":null},{"id":"W1556792431","doi":"10.5555/1496770.1496877","title":"Loopless generation of multiset permutations using a constant number of variables by prefix shifts","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"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 Victoria","funders":"","keywords":"Multiset; Permutation (music); Combinatorics; Mathematics; Prefix; Constant (computer programming); Discrete mathematics; Sublinear function; Set (abstract data type); Parity of a permutation; Cyclic permutation; Computer science; Symmetric group","score_opus":0.037627436958205966,"score_gpt":0.30143663564159096,"score_spread":0.263809198683385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556792431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082596995,0.00038134772,0.90848213,0.00028238268,0.0001629938,0.00010912872,0.00012464341,0.0018478296,0.0060125156],"genre_scores_gemma":[0.39784905,0.0002589136,0.5946669,0.00024010138,0.0001152563,0.00020931922,0.00029899657,0.000437777,0.0059237126],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916553,0.00019885087,0.00007344758,0.000187986,0.0002774197,0.00009669255],"domain_scores_gemma":[0.9973718,0.0012105781,0.00017355497,0.0009912588,0.00020306466,0.000049675986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007414886,0.00044562455,0.00055815215,0.00063480693,0.0005038288,0.000826701,0.00090507517,0.00048674626,0.003969918],"category_scores_gemma":[0.004340092,0.0003230676,0.0005212702,0.00080673944,0.0010493442,0.0031025787,0.0013396261,0.0008720073,0.0012061204],"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":[0.0010197222,0.00021125669,0.0012990079,0.00036563078,0.00006139714,0.00031683425,0.0005016064,0.0535996,0.06419551,0.31007013,0.005225595,0.5631337],"study_design_scores_gemma":[0.00024067388,0.0006076748,0.0005664578,0.000118555654,0.00007765865,0.00065752194,0.00015319185,0.28791335,0.15820846,0.5193891,0.031989947,0.0000773573],"about_ca_topic_score_codex":0.00017052788,"about_ca_topic_score_gemma":0.0003697905,"teacher_disagreement_score":0.003969918,"about_ca_system_score_codex":0.0004101672,"about_ca_system_score_gemma":0.0005092082,"threshold_uncertainty_score":0.01328069},"labels":[],"label_agreement":null},{"id":"W1558034224","doi":"10.1007/978-3-642-14518-6_29","title":"Improved Primality Proving with Eisenstein Pseudocubes","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Primality test; Mathematics; Prime (order theory); Combinatorics","score_opus":0.009704069767134891,"score_gpt":0.22605510917721278,"score_spread":0.21635103941007788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558034224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07820152,0.0020984411,0.79883325,0.0026962792,0.00094198686,0.0001326955,0.00031387975,0.0016258698,0.11515607],"genre_scores_gemma":[0.63617766,0.002197728,0.31736287,0.0011677155,0.0011564669,0.00033469909,0.0008625786,0.0011662121,0.039574087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963612,0.0016250075,0.00016128669,0.00042519247,0.001081422,0.0003458073],"domain_scores_gemma":[0.9941842,0.0037442206,0.00019107264,0.0010604416,0.0005768623,0.00024329918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043385224,0.0018701357,0.0021716147,0.0030969381,0.0020788952,0.0036775165,0.0021001317,0.0016327834,0.011145989],"category_scores_gemma":[0.010695927,0.0014116492,0.0016789952,0.0026094238,0.0042382693,0.010823195,0.008283212,0.007343247,0.0024348532],"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":[0.00012921129,0.000052569296,0.00024183144,0.00013644934,0.000024756571,0.000113756694,0.00016117792,0.005750479,0.0017646932,0.9658911,0.0041416893,0.021592213],"study_design_scores_gemma":[0.000026699225,0.000027566091,0.000072244555,0.000030892494,0.000017840815,0.00007465088,0.000032297467,0.019822476,0.0020253796,0.9732116,0.0046396325,0.0000188111],"about_ca_topic_score_codex":0.00041715882,"about_ca_topic_score_gemma":0.0005488422,"teacher_disagreement_score":0.011145989,"about_ca_system_score_codex":0.0014754477,"about_ca_system_score_gemma":0.00069634744,"threshold_uncertainty_score":0.037286997},"labels":[],"label_agreement":null},{"id":"W1558845130","doi":"10.1023/a:1009841718561","title":"A Heuristic Algorithm for Multiple Sequence Alignment Based on Blocks","year":2001,"lang":"en","type":"article","venue":"Journal of Combinatorial Optimization","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Pairwise comparison; Sequence (biology); Computer science; Similarity (geometry); Theory of computation; Multiple sequence alignment; Process (computing); Algorithm; Theoretical computer science; Mathematics; Sequence alignment; Artificial intelligence; Image (mathematics); Biology","score_opus":0.01824847569133728,"score_gpt":0.26190464464571916,"score_spread":0.24365616895438189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558845130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050638514,0.0002594376,0.99223495,0.000084187544,0.000066511,0.00012310862,0.000078262834,0.0012467562,0.000842995],"genre_scores_gemma":[0.022090066,0.00013874016,0.9757514,0.00007722052,0.000025162914,0.00025678755,0.00031888162,0.00018173798,0.0011599599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887687,0.00040665103,0.00007965964,0.0002125015,0.00030076082,0.00012346437],"domain_scores_gemma":[0.9979254,0.0011922775,0.00014461519,0.00033475645,0.00030661523,0.00009630325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015087395,0.0012796334,0.0023169431,0.0021710538,0.0014961333,0.0013088195,0.002382797,0.0018855688,0.006091779],"category_scores_gemma":[0.004717684,0.0012043191,0.0012060468,0.0029543696,0.0008272388,0.0021468133,0.0018124034,0.0021427027,0.0032201875],"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":[0.0007302079,0.00024560018,0.00058017665,0.00025367117,0.00014362365,0.00017730147,0.00020232827,0.19301276,0.019177202,0.026206022,0.010512773,0.7487584],"study_design_scores_gemma":[0.0001352085,0.00019242952,0.00020686771,0.000036513487,0.000058502,0.00019240218,0.00005011353,0.9642169,0.00721767,0.020498455,0.0071544396,0.000040525778],"about_ca_topic_score_codex":0.0045681926,"about_ca_topic_score_gemma":0.0061005102,"teacher_disagreement_score":0.006091779,"about_ca_system_score_codex":0.0010191421,"about_ca_system_score_gemma":0.0024449448,"threshold_uncertainty_score":0.020379007},"labels":[],"label_agreement":null},{"id":"W1561182462","doi":"10.1109/csb.2003.1227408","title":"GenericBioMatch: A novel generic pattern match algorithm for biological sequences","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"National Research Council Canada","funders":"","keywords":"Computer science; Algorithm; Probabilistic logic; Java; Overhead (engineering); Probabilistic analysis of algorithms; DNA sequencing; Software; Biological data; Genomics; Theoretical computer science; Bioinformatics; DNA; Artificial intelligence; Biology; Genetics; Programming language; Genome","score_opus":0.05855086822525702,"score_gpt":0.27447261492191793,"score_spread":0.21592174669666092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561182462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043713874,0.00031224513,0.97528243,0.0000996736,0.000070824775,0.000114655355,0.000998766,0.01723699,0.0015130308],"genre_scores_gemma":[0.022817599,0.00025257983,0.9681957,0.0001880872,0.000041646734,0.00023992658,0.0040951646,0.0016050321,0.002564269],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808,0.00020113755,0.0002046,0.0004945702,0.0008763888,0.00014320549],"domain_scores_gemma":[0.99862444,0.00039153875,0.00017909768,0.0004335977,0.00028937045,0.00008194264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016723712,0.0014386099,0.0012676603,0.0034538142,0.001067044,0.0020080255,0.0040929434,0.002467504,0.011990471],"category_scores_gemma":[0.005570937,0.0008085288,0.001738414,0.0045988574,0.00092957844,0.0043047806,0.0036510103,0.0015545749,0.006968387],"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":[0.00061512744,0.00019493938,0.0027864017,0.0008242811,0.00019614854,0.0004082379,0.0002777041,0.019147549,0.033214632,0.023094652,0.049047876,0.8701924],"study_design_scores_gemma":[0.00035070023,0.00034034948,0.0021689087,0.00014805484,0.00012357521,0.0028158869,0.00023878472,0.5803228,0.09712995,0.12098611,0.19520272,0.00017219814],"about_ca_topic_score_codex":0.001327258,"about_ca_topic_score_gemma":0.00216925,"teacher_disagreement_score":0.011990471,"about_ca_system_score_codex":0.00071345567,"about_ca_system_score_gemma":0.0014174228,"threshold_uncertainty_score":0.04011208},"labels":[],"label_agreement":null},{"id":"W1561364077","doi":"10.1007/978-3-540-30480-7_70","title":"A Graphical XQuery Language Using Nested Windows","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"XQuery; Computer science; Programming language; World Wide Web; XML; XML database","score_opus":0.016472987807269614,"score_gpt":0.2572567745422869,"score_spread":0.2407837867350173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561364077","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021861834,0.00017522021,0.9129628,0.00019573119,0.00012660395,0.00019204721,0.0011799785,0.07566825,0.0073131695],"genre_scores_gemma":[0.06356012,0.0011181573,0.76123655,0.0009844524,0.00022662623,0.0011492567,0.01094734,0.10147491,0.059302572],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812716,0.0002844815,0.00028757888,0.0003402777,0.0007688876,0.00019159241],"domain_scores_gemma":[0.9980538,0.001079287,0.000096781456,0.0003408454,0.00030711503,0.00012231196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020157152,0.002026608,0.0015559884,0.0010559784,0.00095249846,0.0039412472,0.003647534,0.0016248649,0.039810713],"category_scores_gemma":[0.004243805,0.002223277,0.0018934447,0.0013546248,0.0015756643,0.0053163012,0.0032127043,0.0035564022,0.018417459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014730265,0.00026925406,0.0011053875,0.0020241633,0.00016633583,0.0010467699,0.0028909342,0.0067358282,0.077364236,0.24701469,0.23110878,0.42880055],"study_design_scores_gemma":[0.0006607729,0.00026975013,0.00058380194,0.00057372573,0.0002436714,0.0015402298,0.00035119246,0.072045535,0.09791572,0.11241416,0.71308345,0.0003179775],"about_ca_topic_score_codex":0.0022970953,"about_ca_topic_score_gemma":0.001978496,"teacher_disagreement_score":0.039810713,"about_ca_system_score_codex":0.0006556876,"about_ca_system_score_gemma":0.0010245529,"threshold_uncertainty_score":0.13318014},"labels":[],"label_agreement":null},{"id":"W1561988317","doi":"10.1007/11764298_13","title":"Faster Adaptive Set Intersections for Text Searching","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Intersection (aeronautics); Computer science; Binary search algorithm; Set (abstract data type); Context (archaeology); Task (project management); Binary number; Search algorithm; Interpolation (computer graphics); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Arithmetic; Programming language","score_opus":0.02964560611851291,"score_gpt":0.27309941166129553,"score_spread":0.24345380554278262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561988317","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057758782,0.002868926,0.8953728,0.00041644037,0.00067177287,0.00046608408,0.0016374061,0.025553899,0.0152539],"genre_scores_gemma":[0.13285825,0.0005506891,0.8465598,0.00016662461,0.00023898437,0.00036230308,0.0028723346,0.0017348912,0.014656159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708945,0.00042004936,0.00023336921,0.0005050001,0.0014991632,0.00025295533],"domain_scores_gemma":[0.99449867,0.0027296725,0.00019645509,0.0014588148,0.0009348647,0.00018152533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009940942,0.0014291689,0.003037903,0.0041416707,0.0017184877,0.0024726747,0.0038159383,0.0015127374,0.03846127],"category_scores_gemma":[0.007385764,0.0009734858,0.001259732,0.0073169162,0.0009362534,0.0059198793,0.004312773,0.002015442,0.008882645],"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":[0.0011814565,0.0002632176,0.00063925755,0.00039255645,0.000068292895,0.000087924025,0.000275643,0.013443124,0.017783673,0.024801828,0.028269066,0.91279393],"study_design_scores_gemma":[0.00040715016,0.00078536995,0.0012440118,0.00015693952,0.0001645076,0.00075759285,0.0005404292,0.76402974,0.07147676,0.10336283,0.056931186,0.00014356355],"about_ca_topic_score_codex":0.0038291623,"about_ca_topic_score_gemma":0.0063252016,"teacher_disagreement_score":0.03846127,"about_ca_system_score_codex":0.0011210701,"about_ca_system_score_gemma":0.0013873264,"threshold_uncertainty_score":0.12866575},"labels":[],"label_agreement":null},{"id":"W1562046265","doi":"","title":"Search for D-0 -> (p)over-bare(+) and D-0 -> pe(-)","year":2009,"lang":"en","type":"article","venue":"Purdue e-Pubs (Purdue University System)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; Science and Technology Facilities Council; National Science Foundation","keywords":"Physics; Combinatorics; Humanities; Philosophy; Theology; Mathematics","score_opus":0.012030537560846067,"score_gpt":0.2144707415556572,"score_spread":0.20244020399481114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1562046265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54274744,0.0065410975,0.12786524,0.007832999,0.0021898735,0.00019846048,0.0051441374,0.0073271664,0.3001537],"genre_scores_gemma":[0.9107281,0.0007720941,0.04890842,0.0019408166,0.00018842271,0.0001023747,0.004554754,0.0016594084,0.031145519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996117,0.000047597536,0.000016899681,0.000121776844,0.00006807909,0.00013404617],"domain_scores_gemma":[0.99915004,0.0002612676,0.00012434894,0.00015748694,0.00016016544,0.00014668299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000664924,0.0008051045,0.00086843065,0.0015914895,0.001967607,0.0018310961,0.0013608314,0.0012031645,0.021864567],"category_scores_gemma":[0.0024137935,0.00044964146,0.00090692553,0.0010010661,0.00078628643,0.0023006399,0.0016644408,0.0015638779,0.006161396],"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":[0.0018233078,0.0006874214,0.023733336,0.001242538,0.00028397742,0.0032289359,0.00044468846,0.010811156,0.030558918,0.57807505,0.14446501,0.20464572],"study_design_scores_gemma":[0.0003527032,0.00055082666,0.00499946,0.00027986133,0.00023093393,0.0031235248,0.0012239413,0.102800906,0.0377764,0.7010066,0.14747784,0.00017704396],"about_ca_topic_score_codex":0.0016264198,"about_ca_topic_score_gemma":0.0050093783,"teacher_disagreement_score":0.021864567,"about_ca_system_score_codex":0.00073458126,"about_ca_system_score_gemma":0.0011004113,"threshold_uncertainty_score":0.07314426},"labels":[],"label_agreement":null},{"id":"W1563080589","doi":"10.48550/arxiv.1304.3666","title":"Sets Represented as the Length-n Factors of a Word","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Combinatorics; Word (group theory); Upper and lower bounds; Mathematics; Sigma; Set (abstract data type); Superstring theory; Binary number; Discrete mathematics; Computer science; Arithmetic; Physics","score_opus":0.07740893054860999,"score_gpt":0.20323340586249203,"score_spread":0.12582447531388202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563080589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64353645,0.0011834509,0.3352453,0.001362334,0.00016419051,0.0000961653,0.0012090513,0.0007332911,0.016469747],"genre_scores_gemma":[0.8076752,0.0006715715,0.17812686,0.0003955457,0.00020028772,0.00027689672,0.0020066772,0.00032145772,0.010325495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977506,0.00047212513,0.000255688,0.0006584883,0.0005920155,0.00027113003],"domain_scores_gemma":[0.9938513,0.0035286446,0.0006337281,0.001322611,0.00043539776,0.00022833225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010525079,0.0006662428,0.00109298,0.0013617008,0.0014118428,0.0029227105,0.0013020266,0.001073677,0.0063620964],"category_scores_gemma":[0.010170416,0.0005736989,0.0010392972,0.0020346437,0.0019432416,0.009777567,0.0017192028,0.0014535575,0.0011454734],"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":[0.0012159331,0.00018690994,0.0056437985,0.00038387877,0.00012426011,0.00063638674,0.0020160223,0.035865784,0.021535957,0.7946727,0.0050935857,0.1326248],"study_design_scores_gemma":[0.000045192668,0.0001666081,0.0011717454,0.00013977922,0.00008506733,0.0008242324,0.00084041996,0.097219445,0.02002288,0.8619561,0.017449375,0.00007926183],"about_ca_topic_score_codex":0.0007648786,"about_ca_topic_score_gemma":0.0007658048,"teacher_disagreement_score":0.0063620964,"about_ca_system_score_codex":0.0012915295,"about_ca_system_score_gemma":0.0006080704,"threshold_uncertainty_score":0.021283388},"labels":[],"label_agreement":null},{"id":"W1566077545","doi":"10.1002/9780470932025.ch15","title":"Case Study: Pattern Matching","year":2011,"lang":"en","type":"other","venue":"","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Matching (statistics); Computer science; Mathematics; Statistics","score_opus":0.03423518785129278,"score_gpt":0.2667768436085806,"score_spread":0.23254165575728783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566077545","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38937983,0.0010804792,0.44664982,0.005272403,0.0004328089,0.0016702119,0.0047293454,0.0042680264,0.14651702],"genre_scores_gemma":[0.6546813,0.00048915396,0.28784755,0.0006932669,0.00006131374,0.00047904652,0.0025266171,0.0005761181,0.05264559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976248,0.00065933116,0.0001763094,0.00034305287,0.00086597266,0.00033041876],"domain_scores_gemma":[0.996549,0.001966943,0.00015409301,0.00061332947,0.00054172555,0.00017493013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015488709,0.00047942493,0.00044686667,0.0010737267,0.001404189,0.0014951534,0.0017615871,0.0027343011,0.017747734],"category_scores_gemma":[0.009772403,0.00027076376,0.0006158782,0.0029992585,0.0008835867,0.00261167,0.0011842799,0.0009974018,0.0028489179],"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":[0.0014676925,0.0022867115,0.025113942,0.0019640075,0.00021929714,0.025960343,0.002576264,0.0800328,0.019085865,0.18062691,0.0783232,0.5823429],"study_design_scores_gemma":[0.0005383293,0.0010337662,0.010663297,0.0003508174,0.00023423809,0.027981875,0.005468545,0.3049903,0.087497324,0.14942965,0.41168472,0.00012722705],"about_ca_topic_score_codex":0.004661017,"about_ca_topic_score_gemma":0.006456616,"teacher_disagreement_score":0.017747734,"about_ca_system_score_codex":0.0008827762,"about_ca_system_score_gemma":0.001499173,"threshold_uncertainty_score":0.059372067},"labels":[],"label_agreement":null},{"id":"W1570431431","doi":"10.1007/11735106_21","title":"A Hybrid Approach to Index Maintenance in Dynamic Text Retrieval Systems","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Merge (version control); Computer science; Search engine indexing; Information retrieval; Data mining; Inverted index","score_opus":0.009936672657317182,"score_gpt":0.2235050912192837,"score_spread":0.2135684185619665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570431431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014650985,0.000935377,0.9792236,0.00022647352,0.00011485232,0.00017096846,0.00020185471,0.0029411546,0.0015348148],"genre_scores_gemma":[0.21304724,0.0005557114,0.7770634,0.00023484511,0.00026889236,0.00037248063,0.0008068879,0.0006669528,0.0069835624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972984,0.00055878016,0.0003120303,0.00043365487,0.001216348,0.00018071831],"domain_scores_gemma":[0.9933129,0.002378964,0.00026555997,0.0023950448,0.0014902512,0.00015726512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025743013,0.0007212816,0.0021289121,0.0031004206,0.001536945,0.0032853195,0.004552845,0.0017181631,0.004820659],"category_scores_gemma":[0.0075302804,0.0009805762,0.0010047824,0.004514755,0.0012446062,0.006353538,0.002850709,0.0014638848,0.0017115029],"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":[0.0007231503,0.00037983005,0.0012151873,0.00043551115,0.0002000437,0.00020024335,0.00047876628,0.067685015,0.030817872,0.02814749,0.010282589,0.8594343],"study_design_scores_gemma":[0.00011356461,0.00029568886,0.00063901173,0.00003062105,0.00018771375,0.00046862138,0.00012572997,0.9293322,0.017277177,0.040117636,0.011335708,0.00007630659],"about_ca_topic_score_codex":0.0031311975,"about_ca_topic_score_gemma":0.004733203,"teacher_disagreement_score":0.004820659,"about_ca_system_score_codex":0.0009561882,"about_ca_system_score_gemma":0.0012977226,"threshold_uncertainty_score":0.016126692},"labels":[],"label_agreement":null},{"id":"W1570532020","doi":"10.1007/978-3-642-03816-7_21","title":"Self-indexed Text Compression Using Straight-Line Programs","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; Computer science; Grammar; Representation (politics); Natural language processing; Line (geometry); Artificial intelligence; Context (archaeology); Compression (physics); Programming language; Mathematics; Data structure; Linguistics","score_opus":0.026033658037124936,"score_gpt":0.26681504136117684,"score_spread":0.2407813833240519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570532020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04340924,0.0009397328,0.92074,0.00016019275,0.00027012487,0.00020971945,0.00044068406,0.016985895,0.016844386],"genre_scores_gemma":[0.25800076,0.00092427485,0.6991137,0.0002016984,0.00022135893,0.00029992993,0.0019198125,0.0018072252,0.037511166],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996432,0.000045953482,0.000038296686,0.00006416278,0.00016928629,0.00003904197],"domain_scores_gemma":[0.9990108,0.00033889562,0.00007271097,0.00025226915,0.0002954474,0.00002972736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029491834,0.0007333642,0.0004676705,0.0013946474,0.0004411423,0.0010317301,0.0008986725,0.0005152173,0.013630206],"category_scores_gemma":[0.0013943937,0.00025349355,0.00033785877,0.0020011056,0.0004319857,0.001576555,0.0009169098,0.0005755013,0.0060245437],"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":[0.0005172482,0.00016670316,0.00037883344,0.00031318612,0.000031069834,0.00029936014,0.00016501371,0.006123492,0.08919684,0.024853198,0.013475531,0.86447954],"study_design_scores_gemma":[0.00016424607,0.0007231398,0.0010942332,0.00013433337,0.00009583011,0.0021875326,0.00017879858,0.31300545,0.577936,0.03030629,0.074091725,0.00008248933],"about_ca_topic_score_codex":0.00040342944,"about_ca_topic_score_gemma":0.0005941089,"teacher_disagreement_score":0.013630206,"about_ca_system_score_codex":0.00028164123,"about_ca_system_score_gemma":0.0004363107,"threshold_uncertainty_score":0.045597613},"labels":[],"label_agreement":null},{"id":"W1571061178","doi":"10.48550/arxiv.0811.3959","title":"A polytime proof of correctness of the Rabin-Miller algorithm from Fermat's little theorem","year":2008,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Correctness; Mathematical proof; Primality test; Discrete mathematics; Computer science; Class (philosophy); Mathematics; Algorithm; Prime number; Artificial intelligence","score_opus":0.025985978573711998,"score_gpt":0.24155024338044886,"score_spread":0.21556426480673688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571061178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014684387,0.00076716184,0.9450708,0.0048679416,0.00047989428,0.00020968948,0.000507687,0.0022794283,0.031133033],"genre_scores_gemma":[0.45352504,0.0016888136,0.5138394,0.006539685,0.0012856929,0.0010390709,0.001277649,0.0016806957,0.019124057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928792,0.0014158305,0.00037535775,0.0012551065,0.003233687,0.0008408654],"domain_scores_gemma":[0.9826885,0.011468982,0.0006218957,0.0026052287,0.0023119731,0.000303402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004402641,0.0013034206,0.0014124169,0.0013514567,0.0021064067,0.0040792534,0.0026573858,0.0020423518,0.011012973],"category_scores_gemma":[0.026177576,0.0009887165,0.003122955,0.0019521678,0.00707976,0.008357826,0.0040502544,0.007426833,0.003521114],"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":[0.00016725938,0.000117472664,0.00052564865,0.0002681611,0.00004703356,0.00019644809,0.00032431408,0.011399928,0.0041255155,0.9265881,0.012370317,0.04386983],"study_design_scores_gemma":[0.00010233541,0.00007068976,0.00032263593,0.000094017676,0.00005148207,0.00023843149,0.0000598103,0.044293836,0.009300936,0.930449,0.0149555,0.00006136902],"about_ca_topic_score_codex":0.0024300967,"about_ca_topic_score_gemma":0.0022637888,"teacher_disagreement_score":0.011012973,"about_ca_system_score_codex":0.0032064999,"about_ca_system_score_gemma":0.0045287954,"threshold_uncertainty_score":0.03684205},"labels":[],"label_agreement":null},{"id":"W157198660","doi":"10.1007/978-3-540-68155-7_31","title":"The Weighted Cfg Constraint","year":2008,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.014062009062723467,"score_gpt":0.24066382845883094,"score_spread":0.22660181939610746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W157198660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02035123,0.0011120224,0.8170055,0.004450958,0.0011573277,0.00022276322,0.0022852106,0.0011415766,0.15227354],"genre_scores_gemma":[0.45469356,0.0016783027,0.46636447,0.004070048,0.001034977,0.0005685318,0.0045538386,0.0023126863,0.06472362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965752,0.0008339646,0.00022758765,0.00077621,0.0011805961,0.0004063721],"domain_scores_gemma":[0.9931948,0.0025474518,0.0002263718,0.0026101293,0.001247032,0.00017411719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001942048,0.00080503925,0.0009419701,0.001468349,0.0015291563,0.0027943514,0.0024400405,0.0025275538,0.028322302],"category_scores_gemma":[0.015234521,0.00069268525,0.0009649948,0.0031075056,0.0018531274,0.0075378492,0.0031057706,0.0039067473,0.0044613113],"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":[0.00008918069,0.000032754007,0.00023373091,0.00017902473,0.000028782186,0.00029548493,0.000104820814,0.0040670796,0.0025486755,0.90041894,0.017668242,0.07433328],"study_design_scores_gemma":[0.000025473422,0.000019079549,0.000121794925,0.00007269656,0.00003141399,0.00036025024,0.000058153975,0.022644652,0.0032999772,0.9226503,0.05069465,0.00002165975],"about_ca_topic_score_codex":0.0033688643,"about_ca_topic_score_gemma":0.004191793,"teacher_disagreement_score":0.028322302,"about_ca_system_score_codex":0.00091934996,"about_ca_system_score_gemma":0.0019813671,"threshold_uncertainty_score":0.09474754},"labels":[],"label_agreement":null},{"id":"W1572771042","doi":"10.1007/978-3-540-30586-6_89","title":"Automatic Language Identification Using Multivariate Analysis","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Computer science; Identification (biology); Multivariate statistics; Character (mathematics); Artificial intelligence; Language identification; Curse of dimensionality; Dimensionality reduction; Natural language processing; Natural language; Machine learning; Mathematics","score_opus":0.01789968486689885,"score_gpt":0.28437675549080843,"score_spread":0.2664770706239096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1572771042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0103255715,0.0003574234,0.9779273,0.00017426057,0.000108353874,0.000040788702,0.0005396325,0.0071897223,0.0033368915],"genre_scores_gemma":[0.18571785,0.00083962333,0.78914267,0.00016942048,0.00024262973,0.00020066886,0.0035237412,0.0021500816,0.018013353],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912363,0.00021370828,0.000059826412,0.0002204137,0.00025587025,0.00012657535],"domain_scores_gemma":[0.99882704,0.0005005172,0.00009510497,0.00022322714,0.00030069592,0.0000534736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071993907,0.0010387701,0.000986871,0.0025475684,0.00081316865,0.0017895211,0.00093053817,0.00061899563,0.012524841],"category_scores_gemma":[0.0025118697,0.0004292682,0.0012511809,0.0022740243,0.0005480771,0.0022447158,0.0018028078,0.0013676194,0.011029917],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020931987,0.000070115115,0.0008728939,0.00014749757,0.000050248174,0.00014527663,0.00014293229,0.0042598085,0.053296126,0.013543964,0.010302628,0.9169591],"study_design_scores_gemma":[0.00005160396,0.0001680306,0.005603171,0.00009756979,0.00017564288,0.0013838247,0.00050053326,0.73263216,0.12262271,0.08641984,0.05017269,0.00017234373],"about_ca_topic_score_codex":0.0010235538,"about_ca_topic_score_gemma":0.0014353961,"teacher_disagreement_score":0.012524841,"about_ca_system_score_codex":0.00032603208,"about_ca_system_score_gemma":0.0007606547,"threshold_uncertainty_score":0.0418998},"labels":[],"label_agreement":null},{"id":"W1573155476","doi":"10.1007/978-3-642-15105-7_22","title":"An Occurrence Based Approach to Mine Emerging Sequences","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Discriminative model; Constraint (computer-aided design); Computer science; Sequence (biology); Uniqueness; Contrast (vision); Selection (genetic algorithm); Data mining; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.022220720251300223,"score_gpt":0.26902535060711463,"score_spread":0.2468046303558144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573155476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025200013,0.0009481518,0.9658337,0.00019153091,0.00010887612,0.0002702655,0.002232991,0.002823566,0.002390893],"genre_scores_gemma":[0.13665523,0.0009889071,0.8499744,0.00015185731,0.00017989939,0.00024374717,0.006069327,0.00021768139,0.005518938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987966,0.00009995386,0.00015307643,0.0002956963,0.000546605,0.00010802912],"domain_scores_gemma":[0.9970457,0.0014554395,0.00025550957,0.00029456886,0.0007978886,0.00015091422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085671,0.0010252891,0.0010722593,0.007896981,0.0010551547,0.0015914282,0.0019056386,0.0013669586,0.0035755984],"category_scores_gemma":[0.0035019207,0.00043804516,0.0013475745,0.007909241,0.00056397496,0.0020316686,0.0013713398,0.0012938597,0.002857447],"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":[0.00044424995,0.00041054658,0.011221778,0.0005322782,0.00020836464,0.0011959209,0.00037887658,0.010815796,0.030399013,0.010099012,0.010613916,0.92368025],"study_design_scores_gemma":[0.00009903378,0.0005082587,0.012690126,0.00020177435,0.00048598478,0.0058460785,0.0010033972,0.84705514,0.038760945,0.057638805,0.03558045,0.00013002161],"about_ca_topic_score_codex":0.0043310765,"about_ca_topic_score_gemma":0.00796664,"teacher_disagreement_score":0.007896981,"about_ca_system_score_codex":0.00031759054,"about_ca_system_score_gemma":0.0011300021,"threshold_uncertainty_score":0.011961579},"labels":[],"label_agreement":null},{"id":"W1576322457","doi":"","title":"String regularities with don't cares","year":2002,"lang":"en","type":"preprint","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":28,"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; String (physics); Theoretical computer science; Theoretical physics; Physics","score_opus":0.06045206818662486,"score_gpt":0.2668074180198588,"score_spread":0.20635534983323395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576322457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12999962,0.0005725778,0.85499525,0.00063800457,0.00012398261,0.00018055455,0.00061513926,0.0044111134,0.008463774],"genre_scores_gemma":[0.520646,0.00035354067,0.47008783,0.000289228,0.00012874059,0.00024058149,0.0014756277,0.000628836,0.006149639],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812156,0.00026210965,0.00016036964,0.0005438691,0.00066959247,0.00024241226],"domain_scores_gemma":[0.9950624,0.0019073645,0.00042753996,0.0020415834,0.00042374418,0.00013746337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010087164,0.00055478653,0.0008911445,0.001389096,0.0010674594,0.0014960798,0.001385821,0.000784318,0.003702163],"category_scores_gemma":[0.010407892,0.000566779,0.00094507274,0.002033066,0.001831354,0.0038732747,0.0020156137,0.0012884124,0.0012982417],"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":[0.0017709967,0.0002708492,0.009252443,0.00041761796,0.00011448168,0.00064377923,0.0009618904,0.0863125,0.022708647,0.26227584,0.014926365,0.60034454],"study_design_scores_gemma":[0.00010077117,0.00026197507,0.0018269958,0.00008550039,0.000074823096,0.001182886,0.0002473644,0.51397276,0.04569282,0.41078272,0.025699414,0.00007194782],"about_ca_topic_score_codex":0.0010388017,"about_ca_topic_score_gemma":0.0013202953,"teacher_disagreement_score":0.003702163,"about_ca_system_score_codex":0.00094931567,"about_ca_system_score_gemma":0.0009899673,"threshold_uncertainty_score":0.012384951},"labels":[],"label_agreement":null},{"id":"W1577418030","doi":"10.1007/11533719_58","title":"Generating Combinations by Prefix Shifts","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Prefix; Gray code; Computer science; Simple (philosophy); Algorithm; Code (set theory); String (physics); Combinatorics; Discrete mathematics; Arithmetic; Mathematics; Set (abstract data type); Programming language","score_opus":0.013827903776525437,"score_gpt":0.2439113502292458,"score_spread":0.23008344645272036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577418030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07056472,0.00047403225,0.86527413,0.0003824232,0.00046696482,0.00022920012,0.0004326601,0.0026554484,0.059520304],"genre_scores_gemma":[0.3808615,0.0006431002,0.5830444,0.00031738757,0.00025954173,0.0003716434,0.0012024929,0.0018763945,0.031423606],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887806,0.0002286945,0.000071224946,0.0002529894,0.0004421565,0.00012686264],"domain_scores_gemma":[0.99866843,0.0006702347,0.000059927377,0.00038156094,0.00015669464,0.000063215215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067554566,0.00092263764,0.00095678377,0.0014568064,0.0010336998,0.0013767869,0.0010870482,0.00091408007,0.018175578],"category_scores_gemma":[0.0027178067,0.00083277945,0.0011782848,0.0018221117,0.0013543261,0.002788934,0.0034534892,0.0017152285,0.0056087603],"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":[0.00041366587,0.00013166523,0.0007320375,0.00037835026,0.0000664071,0.00077808613,0.0006973336,0.009312184,0.03385447,0.37443513,0.014541291,0.56465936],"study_design_scores_gemma":[0.000087341476,0.00023713363,0.00033791413,0.00012142712,0.00012716814,0.001471916,0.0002480096,0.08532166,0.054491423,0.794165,0.063323304,0.00006767221],"about_ca_topic_score_codex":0.00013637636,"about_ca_topic_score_gemma":0.00029594556,"teacher_disagreement_score":0.018175578,"about_ca_system_score_codex":0.00035003724,"about_ca_system_score_gemma":0.00031737168,"threshold_uncertainty_score":0.060803354},"labels":[],"label_agreement":null},{"id":"W1578234187","doi":"10.37236/2051","title":"Efficient Oracles for Generating Binary Bubble Languages","year":2012,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicographical order; Mathematics; Combinatorics; Amortized analysis; Oracle; Binary number; Object (grammar); Discrete mathematics; Simple (philosophy); Computer science; Data structure; Arithmetic; Programming language","score_opus":0.010715838502216083,"score_gpt":0.26557888174185246,"score_spread":0.2548630432396364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578234187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024364982,0.00029303407,0.9489024,0.00044955744,0.000078337725,0.00029234408,0.0015181703,0.012636264,0.011464873],"genre_scores_gemma":[0.26055956,0.00031649074,0.72002923,0.00029937478,0.00007334927,0.00097130536,0.0047550914,0.0028626402,0.010132901],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987565,0.00027354664,0.00011648082,0.00021231365,0.00045247705,0.00018873072],"domain_scores_gemma":[0.9971559,0.0014665622,0.00014708671,0.00082286575,0.00028022335,0.0001274093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013014092,0.00094436033,0.0009469755,0.0012028201,0.0005018753,0.002154573,0.0025940125,0.0011802476,0.018489858],"category_scores_gemma":[0.008133155,0.00070979446,0.00094383775,0.0015761685,0.0009751595,0.0040851003,0.0033598356,0.0018222124,0.005874652],"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":[0.001131934,0.0003255304,0.0016387049,0.00091196655,0.000052742107,0.0003224056,0.0004380302,0.055251464,0.023753287,0.38574314,0.02742441,0.50300634],"study_design_scores_gemma":[0.00034103196,0.00027959686,0.00042208403,0.00016279278,0.00006218975,0.00050524983,0.00020420366,0.4674869,0.05935873,0.4368667,0.034199465,0.000111077934],"about_ca_topic_score_codex":0.0006340363,"about_ca_topic_score_gemma":0.0010693418,"teacher_disagreement_score":0.018489858,"about_ca_system_score_codex":0.0010922847,"about_ca_system_score_gemma":0.0014565665,"threshold_uncertainty_score":0.06185478},"labels":[],"label_agreement":null},{"id":"W1579884944","doi":"10.37236/4459","title":"Counting the Palstars","year":2014,"lang":"en","type":"preprint","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Alphabet; Concatenation (mathematics); Combinatorics; Constant (computer programming); Palindrome; Mathematics; Alpha (finance); Discrete mathematics; Arithmetic; Computer science; Statistics; Biology; Philosophy; Genetics","score_opus":0.008666077975984345,"score_gpt":0.23485763773083845,"score_spread":0.2261915597548541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579884944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38150162,0.0017955796,0.48344967,0.0032221735,0.0005367319,0.00024018632,0.0021534169,0.0036570346,0.12344352],"genre_scores_gemma":[0.820287,0.0010338017,0.1285096,0.00080646464,0.00030028634,0.0004341167,0.0025777007,0.0011893897,0.044861723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976156,0.0004712651,0.00015000167,0.0006319318,0.0006843879,0.0004468781],"domain_scores_gemma":[0.9918549,0.0047247224,0.0004069663,0.0015143895,0.0010126146,0.0004864213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001256791,0.00075313787,0.0010860618,0.0019042414,0.0025750948,0.0036721167,0.0021486548,0.0013732845,0.02604411],"category_scores_gemma":[0.018390445,0.00087748625,0.00097419467,0.0018020878,0.0027970313,0.008980721,0.0044586565,0.0025831147,0.005504125],"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":[0.00055517023,0.000103544364,0.0037912142,0.00032719888,0.00005405899,0.0004058688,0.0012366978,0.012911407,0.010272825,0.8434887,0.023714827,0.103138484],"study_design_scores_gemma":[0.000059517835,0.00014157484,0.00094710116,0.000100208505,0.00005887865,0.0010080369,0.0005423012,0.051327493,0.010337275,0.9041162,0.031292845,0.00006851709],"about_ca_topic_score_codex":0.0010230942,"about_ca_topic_score_gemma":0.001245074,"teacher_disagreement_score":0.02604411,"about_ca_system_score_codex":0.0013488553,"about_ca_system_score_gemma":0.0012106472,"threshold_uncertainty_score":0.087126195},"labels":[],"label_agreement":null},{"id":"W1580838969","doi":"10.1023/a:1020839810474","title":"Intelligent Search Methods for Software Maintenance","year":2002,"lang":"en","type":"article","venue":"Information Systems Frontiers","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Concatenation (mathematics); Software; Information retrieval; Data mining; Software engineering; Artificial intelligence; Programming language","score_opus":0.03686711213378269,"score_gpt":0.30218566705703004,"score_spread":0.26531855492324735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1580838969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011405093,0.0062675276,0.97614974,0.00075201615,0.00009349013,0.000047336445,0.000076868426,0.0006421587,0.0045657675],"genre_scores_gemma":[0.3732429,0.0047009755,0.6123524,0.00025903046,0.00036140415,0.0002314019,0.00040095803,0.00023610456,0.00821489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989209,0.00042691478,0.00007115358,0.00013945246,0.00038236493,0.000059129256],"domain_scores_gemma":[0.99665666,0.0023823662,0.00017352896,0.0003746224,0.00036640876,0.000046308887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017460819,0.0005761786,0.0011341594,0.002053126,0.0005477932,0.0013088643,0.0013329433,0.0011670114,0.0030859841],"category_scores_gemma":[0.009060246,0.00035840675,0.00047627997,0.0022996115,0.0013019727,0.003615012,0.0010078802,0.0012313959,0.0006457142],"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":[0.00018218327,0.000110630914,0.00064888684,0.0003419972,0.00007319639,0.00004237886,0.00019931822,0.18855369,0.0014145977,0.17961946,0.010474115,0.6183396],"study_design_scores_gemma":[0.000046878922,0.00004357997,0.00021593053,0.000048942005,0.000029763522,0.00005133678,0.000041607072,0.664639,0.0008307352,0.32823926,0.0058011017,0.00001188996],"about_ca_topic_score_codex":0.001916273,"about_ca_topic_score_gemma":0.0019265467,"teacher_disagreement_score":0.0030859841,"about_ca_system_score_codex":0.00093999034,"about_ca_system_score_gemma":0.000746757,"threshold_uncertainty_score":0.010323584},"labels":[],"label_agreement":null},{"id":"W1581173031","doi":"10.1007/3-540-32390-2_8","title":"A Look-Ahead Branch and Bound Pruning Scheme for Trie-Based Approximate String Matching","year":2008,"lang":"en","type":"book-chapter","venue":"Advances in soft computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Pruning; Benchmark (surveying); String (physics); Levenshtein distance; String searching algorithm; Algorithm; Approximate string matching; Computation; Mathematics; Matching (statistics); Element (criminal law); A priori and a posteriori; Computer science; Combinatorics; Pattern matching; Data structure; Artificial intelligence; Statistics","score_opus":0.01958908214814302,"score_gpt":0.2718124686346245,"score_spread":0.25222338648648146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581173031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088062575,0.0008992586,0.98272544,0.00020304811,0.00014762023,0.00016961405,0.00033865822,0.0032438517,0.0034661985],"genre_scores_gemma":[0.05463108,0.00042312863,0.93786395,0.00015540046,0.00006680357,0.00018651523,0.0010652269,0.00031945747,0.005288364],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979709,0.00027296756,0.00021469526,0.00028052914,0.0010986616,0.00016223894],"domain_scores_gemma":[0.9972108,0.0010102233,0.0001351299,0.0009887281,0.0005629264,0.00009215656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013167716,0.0008577789,0.0023708753,0.0029508208,0.0012362989,0.002077834,0.003538278,0.0017523984,0.009806362],"category_scores_gemma":[0.006600225,0.0008340903,0.0010562742,0.0059484183,0.0008753522,0.0033852726,0.002606202,0.0021425548,0.0034920834],"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":[0.000456486,0.00023906479,0.00044530298,0.00021120707,0.000082424514,0.0001080943,0.00015510838,0.054707404,0.011036443,0.024332702,0.01575121,0.89247453],"study_design_scores_gemma":[0.00010668858,0.00016720388,0.00041398674,0.00005800906,0.00008903332,0.00030182383,0.000084309846,0.9284138,0.013019804,0.044910923,0.012378642,0.00005576985],"about_ca_topic_score_codex":0.0044880947,"about_ca_topic_score_gemma":0.0075118258,"teacher_disagreement_score":0.009806362,"about_ca_system_score_codex":0.0012052894,"about_ca_system_score_gemma":0.0021280807,"threshold_uncertainty_score":0.032805562},"labels":[],"label_agreement":null},{"id":"W1581358566","doi":"10.1109/aero.2006.1656064","title":"CompreX: Further Developments in XML Compression","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"International Development Research Centre","keywords":"Computer science; Efficient XML Interchange; Streaming XML; XML Signature; XML framework; XML Encryption; XML Schema Editor; XML; Document Structure Description; XML validation; cXML; World Wide Web","score_opus":0.007678888421291165,"score_gpt":0.21825838753823926,"score_spread":0.2105794991169481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581358566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018384662,0.01811491,0.9045391,0.004928215,0.0018857308,0.00046736692,0.0004358227,0.008091079,0.043153077],"genre_scores_gemma":[0.098561935,0.022245176,0.82808363,0.0025245873,0.0032022095,0.00034699886,0.002646262,0.0019326449,0.040456567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974687,0.00052827207,0.0002659107,0.00036826247,0.0012116589,0.00015725895],"domain_scores_gemma":[0.99360365,0.0023627456,0.00025621546,0.0013529453,0.0022536428,0.00017080737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00474905,0.0012709209,0.000851044,0.002946363,0.00057223235,0.0029228965,0.0020564026,0.001312412,0.011338605],"category_scores_gemma":[0.011422011,0.0005379879,0.00075532426,0.0029867853,0.0013796721,0.007751486,0.0017240675,0.002735045,0.0045083244],"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":[0.00030688068,0.00018476765,0.00060334126,0.00033479725,0.000034904777,0.00028842755,0.00026147044,0.0052995137,0.012973745,0.08063268,0.014993695,0.88408583],"study_design_scores_gemma":[0.00024894418,0.0011067711,0.0018154749,0.0008190989,0.00011905919,0.0038261975,0.00030531833,0.17620283,0.13569298,0.092852846,0.5867774,0.00023309457],"about_ca_topic_score_codex":0.0011303901,"about_ca_topic_score_gemma":0.0005406077,"teacher_disagreement_score":0.011338605,"about_ca_system_score_codex":0.0008846754,"about_ca_system_score_gemma":0.00096513,"threshold_uncertainty_score":0.037931383},"labels":[],"label_agreement":null},{"id":"W1583784647","doi":"10.1007/978-3-540-30198-1_24","title":"On Families of New Adaptive Compression Algorithms Suitable for Time-Varying Source Data","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Windsor","funders":"","keywords":"Computer science; Entropy encoding; Adaptive coding; Algorithm; Decoding methods; Coding (social sciences); Entropy (arrow of time); Data compression; Encoding (memory); Theoretical computer science; Artificial intelligence; Lossless compression; Mathematics; Statistics","score_opus":0.03784189393798354,"score_gpt":0.27284935411761757,"score_spread":0.23500746017963403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583784647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011239442,0.0022623884,0.9802484,0.0002247121,0.00015986577,0.000072790994,0.00009761696,0.00029453967,0.0054003657],"genre_scores_gemma":[0.1695051,0.008969335,0.8035424,0.0005794438,0.00090760493,0.0006768605,0.00089189963,0.0006848012,0.014242522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864084,0.00039913677,0.000100807534,0.00022385934,0.0005253919,0.000109995555],"domain_scores_gemma":[0.9907218,0.006908814,0.00046294488,0.000865295,0.000853175,0.0001879466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031197353,0.0018826213,0.0010047259,0.0018530752,0.00078414043,0.001642187,0.0016299146,0.0015649705,0.0035093084],"category_scores_gemma":[0.014981231,0.0006456391,0.0013961855,0.0024246983,0.001749558,0.0033028116,0.002152827,0.0029231748,0.00094746373],"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":[0.00042005698,0.00011501941,0.0009969609,0.00045116126,0.00011403456,0.00037468414,0.00032141973,0.0990718,0.019103616,0.5570528,0.011499818,0.31047872],"study_design_scores_gemma":[0.00006287183,0.00014790057,0.00049347285,0.00011463901,0.000055649907,0.0010848169,0.000057223788,0.74396694,0.0077779945,0.23385745,0.012310606,0.00007046161],"about_ca_topic_score_codex":0.000530706,"about_ca_topic_score_gemma":0.00059267523,"teacher_disagreement_score":0.0035093084,"about_ca_system_score_codex":0.0009331106,"about_ca_system_score_gemma":0.0006466688,"threshold_uncertainty_score":0.016498923},"labels":[],"label_agreement":null},{"id":"W1583922594","doi":"10.1007/978-3-540-74553-2_25","title":"An Efficient Algorithm for Identifying the Most Contributory Substring","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Substring; Set (abstract data type); Algorithm; Computer science; Running time; Mathematics; Combinatorics","score_opus":0.030714934167529826,"score_gpt":0.2923358769748553,"score_spread":0.26162094280732545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583922594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031831793,0.0010708194,0.9510003,0.00047005014,0.00048857165,0.0005406075,0.0014302933,0.008544171,0.004623492],"genre_scores_gemma":[0.041202746,0.00032794772,0.94642097,0.0001154785,0.00011549525,0.00023571143,0.0024336807,0.00036704558,0.00878092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988757,0.00008110336,0.00012056922,0.00032445212,0.00047865295,0.00011945265],"domain_scores_gemma":[0.9974795,0.00081550796,0.00018710301,0.0005916352,0.0007836943,0.00014259276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010098014,0.0016165184,0.001739949,0.005295099,0.0018258056,0.002206536,0.0022779233,0.0018772805,0.011300987],"category_scores_gemma":[0.005066859,0.0006693473,0.00096220244,0.0049838894,0.0008160181,0.002796046,0.0029752518,0.0012824807,0.008766914],"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":[0.0003977911,0.0001674335,0.0014408303,0.00022444042,0.000043786826,0.0001940315,0.00018241833,0.0043098023,0.038878527,0.006762168,0.01583201,0.9315668],"study_design_scores_gemma":[0.0005018092,0.0008976626,0.0063879127,0.00025027094,0.00040916452,0.004307051,0.0011752172,0.58574224,0.18488194,0.09033475,0.12489884,0.00021317617],"about_ca_topic_score_codex":0.0019403691,"about_ca_topic_score_gemma":0.0049134823,"teacher_disagreement_score":0.011300987,"about_ca_system_score_codex":0.00077716116,"about_ca_system_score_gemma":0.002818899,"threshold_uncertainty_score":0.037805557},"labels":[],"label_agreement":null},{"id":"W1586348459","doi":"10.1007/3-540-45452-7_21","title":"Statistical Identification of Uniformly Mutated Segments within Repeats","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"","keywords":"String (physics); Random permutation; Combinatorics; Algorithm; Binary number; Computer science; Mathematics; Permutation (music); Set (abstract data type); Discrete mathematics; Block (permutation group theory); Arithmetic; Physics","score_opus":0.017599046285431325,"score_gpt":0.2543448751767846,"score_spread":0.2367458288913533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586348459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5651189,0.0007753081,0.42859474,0.00013642586,0.00006743421,0.00006135312,0.0007917859,0.0014856976,0.0029684086],"genre_scores_gemma":[0.8820889,0.0002833364,0.11185696,0.00007500103,0.0000580566,0.000069464775,0.0022525664,0.00039585138,0.0029198776],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992355,0.00016545047,0.00004447904,0.00028594804,0.00020428693,0.00006438861],"domain_scores_gemma":[0.9953701,0.0023849756,0.0007082696,0.00085678,0.00049644255,0.00018338356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081850507,0.0003154456,0.000599072,0.001726819,0.00042457023,0.0008017474,0.001128174,0.0008965643,0.0018921762],"category_scores_gemma":[0.00584797,0.00032429886,0.00040653086,0.0014206492,0.00062325556,0.0009170159,0.00066306005,0.00064912543,0.0010848877],"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":[0.002076367,0.00023628776,0.042451523,0.00046124877,0.00018735536,0.0011787041,0.0005753262,0.06122775,0.53345996,0.035841446,0.0032528045,0.31905118],"study_design_scores_gemma":[0.000045393586,0.00026123776,0.027412355,0.000054214055,0.00014781035,0.0019918159,0.00019599065,0.7469764,0.19218609,0.026085183,0.004567642,0.000075890726],"about_ca_topic_score_codex":0.00051168667,"about_ca_topic_score_gemma":0.0011068023,"teacher_disagreement_score":0.0018921762,"about_ca_system_score_codex":0.00034537405,"about_ca_system_score_gemma":0.00035305403,"threshold_uncertainty_score":0.0063299537},"labels":[],"label_agreement":null},{"id":"W1586783524","doi":"10.1007/978-3-540-30500-2_10","title":"Viral Gene Compression: Complexity and Verification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Western University","funders":"University of Saskatchewan","keywords":"Genome; Computer science; Metric (unit); Set (abstract data type); Gene; Computational biology; Compression (physics); Point (geometry); Theoretical computer science; Biology; Genetics; Programming language; Mathematics; Physics","score_opus":0.027882458544481046,"score_gpt":0.2581603538261157,"score_spread":0.23027789528163464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586783524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079210944,0.0029341737,0.84951174,0.0025588658,0.00040065008,0.00019852523,0.0005560672,0.0011381503,0.06349085],"genre_scores_gemma":[0.76205677,0.0024157339,0.20817593,0.00045479205,0.00056094024,0.00028093526,0.0010615771,0.0004499791,0.024543388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981654,0.00026941288,0.00008010056,0.00023217112,0.0010931846,0.0001598066],"domain_scores_gemma":[0.9924149,0.0050590103,0.0004034949,0.0013445586,0.0006892206,0.00008878641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012235047,0.00052216207,0.0010386821,0.0009566479,0.00091369956,0.002892341,0.0017082763,0.0015697739,0.0067309802],"category_scores_gemma":[0.010237155,0.000565671,0.00089780934,0.0011407151,0.0027468787,0.005066068,0.0019047057,0.0022780772,0.0014364867],"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":[0.00016915912,0.00004870426,0.0007102087,0.00016471489,0.00001750887,0.0001736295,0.00015166521,0.037560385,0.0071990564,0.83647984,0.0071906676,0.11013453],"study_design_scores_gemma":[0.000022817278,0.000043335687,0.00032819016,0.000042965494,0.000012467235,0.00041401634,0.00005580015,0.23464696,0.01571641,0.74146736,0.0072190855,0.000030641637],"about_ca_topic_score_codex":0.00084270816,"about_ca_topic_score_gemma":0.00063016836,"teacher_disagreement_score":0.0067309802,"about_ca_system_score_codex":0.0014452691,"about_ca_system_score_gemma":0.0012405544,"threshold_uncertainty_score":0.022517323},"labels":[],"label_agreement":null},{"id":"W1587123803","doi":"10.1007/978-3-540-92182-0_13","title":"Succinct and I/O Efficient Data Structures for Traversal in Trees","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Tree traversal; Tree (set theory); Path (computing); Binary tree; Binary logarithm; Node (physics); Combinatorics; Graph traversal; Computer science; Data structure; Constant (computer programming); Root (linguistics); B-tree; Discrete mathematics; Asymptotically optimal algorithm; Binary number; Binary search tree; Mathematics; Algorithm; Arithmetic; Physics; Computer network; Operating system","score_opus":0.028592262608921098,"score_gpt":0.2633235455582299,"score_spread":0.2347312829493088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587123803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0373994,0.0019189394,0.9395187,0.0008377791,0.00028760917,0.00021206851,0.0026296002,0.0054742815,0.011721637],"genre_scores_gemma":[0.24041344,0.0018968366,0.72617906,0.0004802536,0.00020109808,0.0004982986,0.00800948,0.0024374803,0.019884005],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987804,0.00014309105,0.00017527552,0.00012584041,0.00063800765,0.00013736989],"domain_scores_gemma":[0.99661654,0.0011745861,0.00026417416,0.0013274563,0.0005049255,0.00011225356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007074127,0.0010187611,0.0008747381,0.001362154,0.00081445783,0.0025871708,0.002091794,0.0009989666,0.008292759],"category_scores_gemma":[0.0052013453,0.0009237961,0.0009126881,0.0044574123,0.001180213,0.0062026936,0.002225045,0.0023162102,0.0027685552],"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":[0.0007573222,0.00035581435,0.0017753838,0.0011276854,0.00006330932,0.00026357587,0.0008952178,0.046498876,0.038820222,0.29774582,0.060894582,0.5508022],"study_design_scores_gemma":[0.00024577935,0.00039689612,0.0010733777,0.00047878647,0.0001380958,0.00065443787,0.000522439,0.27995822,0.07225783,0.5636604,0.080471985,0.00014170351],"about_ca_topic_score_codex":0.001408195,"about_ca_topic_score_gemma":0.003174902,"teacher_disagreement_score":0.008292759,"about_ca_system_score_codex":0.0012887028,"about_ca_system_score_gemma":0.0015131653,"threshold_uncertainty_score":0.027742088},"labels":[],"label_agreement":null},{"id":"W1588039295","doi":"10.1007/11925903_9","title":"Viral Genome Compression","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Superstring theory; Genome; Upper and lower bounds; Computer science; Algorithm; Combinatorics; Gene; Mathematics; Biology; Genetics","score_opus":0.012140324300758176,"score_gpt":0.23265016003624933,"score_spread":0.22050983573549116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588039295","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0918749,0.022187466,0.6864956,0.002826398,0.0042107743,0.00059366797,0.002713668,0.007423303,0.18167421],"genre_scores_gemma":[0.5176057,0.011728223,0.2951278,0.001168848,0.0010817338,0.00038907447,0.008323096,0.0010273608,0.16354802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997414,0.00002760246,0.000010575985,0.00004309382,0.00014285996,0.000034397974],"domain_scores_gemma":[0.9997149,0.00006976312,0.000014828317,0.00009452516,0.000086577194,0.000019466264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002771145,0.0005669922,0.00051483244,0.0010856278,0.0006183328,0.0010238561,0.0007888998,0.0007820443,0.012528486],"category_scores_gemma":[0.0009611744,0.00024833495,0.00040847083,0.0014212074,0.000437893,0.0010708562,0.00092651235,0.00087094354,0.004801935],"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":[0.0004548419,0.00014708382,0.0004080697,0.00034635,0.00004710766,0.00036699575,0.00009888198,0.018553566,0.16415603,0.056567598,0.033619955,0.72523355],"study_design_scores_gemma":[0.00008768379,0.00033427236,0.0011860573,0.00015154142,0.000065891625,0.0026326594,0.00014106152,0.2574776,0.48191038,0.06791944,0.188013,0.00008044076],"about_ca_topic_score_codex":0.0005824846,"about_ca_topic_score_gemma":0.0005750681,"teacher_disagreement_score":0.012528486,"about_ca_system_score_codex":0.0004988135,"about_ca_system_score_gemma":0.00036023837,"threshold_uncertainty_score":0.04191196},"labels":[],"label_agreement":null},{"id":"W1589106868","doi":"10.1109/dcc.1998.672310","title":"A memory-efficient adaptive Huffman coding algorithm for very large sets of symbols","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Huffman coding; Algorithm; Computer science; Shannon–Fano coding; Prefix code; Decoding methods; Canonical Huffman code; Coding (social sciences); Variable-length code; Theoretical computer science; Data compression; Mathematics; Block code; Code rate; Concatenated error correction code; Systematic code","score_opus":0.03235594851528556,"score_gpt":0.2578982604893415,"score_spread":0.22554231197405594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589106868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012681769,0.00029926092,0.98279965,0.00017180995,0.00006599896,0.00008579948,0.00012120848,0.0022229396,0.0015515225],"genre_scores_gemma":[0.05404971,0.00013002253,0.9422293,0.00010622873,0.00004661455,0.00018038452,0.00042633637,0.00014666276,0.0026847303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999498,0.00008419537,0.000049553528,0.00012427474,0.00018443828,0.00005944592],"domain_scores_gemma":[0.9987161,0.00061465555,0.000091462214,0.00020979383,0.00033102382,0.00003699237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000628915,0.0006770584,0.00075051456,0.0011736864,0.00074068067,0.00092512707,0.001773069,0.0009291866,0.0038801096],"category_scores_gemma":[0.0035925184,0.00033002024,0.00049687707,0.0018618992,0.0007000076,0.0012530873,0.0011157272,0.0010695613,0.0018090301],"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":[0.00021843414,0.00005089668,0.0005578459,0.000107779415,0.00003071045,0.00012548728,0.00016412721,0.054000396,0.019078258,0.017031029,0.009270588,0.8993645],"study_design_scores_gemma":[0.00005186868,0.0000783311,0.00035262527,0.00003008148,0.000019971963,0.0001788706,0.000075578326,0.9498371,0.023598973,0.017313503,0.008440035,0.000023038154],"about_ca_topic_score_codex":0.008279265,"about_ca_topic_score_gemma":0.008899793,"teacher_disagreement_score":0.008279265,"about_ca_system_score_codex":0.0011589648,"about_ca_system_score_gemma":0.0018447951,"threshold_uncertainty_score":0.016462147},"labels":[],"label_agreement":null},{"id":"W1590367822","doi":"10.1007/978-3-642-27848-8_73-2","title":"Closest String and Substring Problems","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; String (physics); Computer science; Mathematics; Physics; Theoretical physics; Programming language; Data structure","score_opus":0.012930917182556796,"score_gpt":0.214215555415739,"score_spread":0.2012846382331822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590367822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008845926,0.07164707,0.6206198,0.006121702,0.0051363325,0.00016357888,0.0013329947,0.0015839564,0.2845487],"genre_scores_gemma":[0.11476811,0.0861453,0.53634906,0.0019993256,0.00918587,0.0005371823,0.0065744035,0.0015836832,0.24285711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984231,0.0002550783,0.00010981186,0.00031380044,0.00083573366,0.00006240491],"domain_scores_gemma":[0.99889106,0.00058207224,0.00006975763,0.00025593903,0.00015182047,0.00004931042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007122281,0.0012549919,0.0018517087,0.002492615,0.0010417531,0.0032823232,0.0022778367,0.0022456783,0.024793249],"category_scores_gemma":[0.005254074,0.0005409254,0.00089104613,0.008250393,0.0019237997,0.006750103,0.0026673132,0.0037386424,0.010855922],"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":[0.00005319667,0.00006588216,0.00016225003,0.00075201807,0.000030718977,0.00011630783,0.00012672092,0.010952601,0.0009040342,0.4305581,0.08531644,0.47096172],"study_design_scores_gemma":[0.000014645906,0.000022600649,0.000118633485,0.00014127335,0.000013555394,0.00042747927,0.000046765683,0.014344595,0.0006508386,0.884962,0.099240705,0.000016954942],"about_ca_topic_score_codex":0.00060659176,"about_ca_topic_score_gemma":0.0005530962,"teacher_disagreement_score":0.024793249,"about_ca_system_score_codex":0.0012119112,"about_ca_system_score_gemma":0.0011756215,"threshold_uncertainty_score":0.08294165},"labels":[],"label_agreement":null},{"id":"W1592629156","doi":"10.1007/978-3-540-77120-3_29","title":"Succinct Representation of Labeled Graphs","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Waterloo","funders":"","keywords":"Combinatorics; Vertex (graph theory); Planar graph; Adjacency list; Representation (politics); Computer science; Graph; Mathematics; Discrete mathematics","score_opus":0.026763144151920562,"score_gpt":0.28531081786383844,"score_spread":0.2585476737119179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1592629156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010987321,0.00037727307,0.96735716,0.0005815262,0.0001632123,0.00014883513,0.004377609,0.00269493,0.013312118],"genre_scores_gemma":[0.18826135,0.0012522092,0.76873434,0.00043907782,0.00017293567,0.0005737905,0.018580213,0.0013318667,0.020654123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991726,0.00023229329,0.00007109248,0.00015353295,0.00029563732,0.000074825984],"domain_scores_gemma":[0.9975178,0.00095540984,0.00015813313,0.00083553634,0.00045404755,0.00007911577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056534196,0.00086070347,0.0006950801,0.0014865239,0.0005443855,0.0025501044,0.0019502317,0.0010485008,0.012646342],"category_scores_gemma":[0.004115884,0.00059346884,0.00070579024,0.002691608,0.0007083599,0.004698343,0.0017442668,0.0020189756,0.0035157187],"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":[0.00027351,0.0001438521,0.00031209958,0.0005402246,0.00003344239,0.00028787236,0.00046381346,0.085153274,0.007349837,0.58457834,0.034775782,0.286088],"study_design_scores_gemma":[0.000035090434,0.00003349729,0.00011837195,0.00012696683,0.000025281466,0.00016319666,0.000092377035,0.18727593,0.0053582736,0.7720475,0.034697715,0.000025889836],"about_ca_topic_score_codex":0.0016258701,"about_ca_topic_score_gemma":0.0035875312,"teacher_disagreement_score":0.012646342,"about_ca_system_score_codex":0.00097650615,"about_ca_system_score_gemma":0.0009776535,"threshold_uncertainty_score":0.042306244},"labels":[],"label_agreement":null},{"id":"W1593036127","doi":"10.37236/701","title":"Minimum Light Numbers in the $\\sigma$-Game and Lit-Only $\\sigma$-Game on Unicyclic and Grid Graphs","year":2011,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Banff International Research Station for Mathematical Innovation and Discovery; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; West Virginia University","keywords":"Combinatorics; Mathematics; Vertex (graph theory); Graph; Connectivity; Discrete mathematics","score_opus":0.011314398516359401,"score_gpt":0.21595381190169358,"score_spread":0.20463941338533417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593036127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6635116,0.00046278813,0.2206516,0.0041005397,0.00021109568,0.00045264835,0.0013576292,0.0006959136,0.1085562],"genre_scores_gemma":[0.92403907,0.00032314996,0.053212713,0.00062205433,0.00006347817,0.00045067075,0.00095098326,0.00021037957,0.020127406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998511,0.00048185672,0.00008643451,0.00026537213,0.0002357976,0.00041953087],"domain_scores_gemma":[0.9954881,0.0024764466,0.00035673942,0.00032524203,0.00024581997,0.0011076779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013282197,0.0011496991,0.001662849,0.0009598951,0.002075086,0.003951192,0.0022258402,0.0020642802,0.011545387],"category_scores_gemma":[0.007400982,0.00058014534,0.0009308521,0.0010666923,0.003257583,0.005749094,0.0028929366,0.0027432577,0.0009980154],"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":[0.0006769736,0.0001613581,0.0010183043,0.0001967354,0.000040671697,0.00025775732,0.00058545714,0.038639843,0.002724204,0.9316054,0.0071345153,0.016958797],"study_design_scores_gemma":[0.000144464,0.000085957,0.0002553359,0.000037710637,0.000019340187,0.00009613984,0.00019498075,0.12438671,0.0008521715,0.87083876,0.0030548458,0.000033629894],"about_ca_topic_score_codex":0.0038701172,"about_ca_topic_score_gemma":0.00484008,"teacher_disagreement_score":0.011545387,"about_ca_system_score_codex":0.0027385617,"about_ca_system_score_gemma":0.0017587361,"threshold_uncertainty_score":0.038623154},"labels":[],"label_agreement":null},{"id":"W1594439285","doi":"","title":"OVERLAY PROBLEMS FOR MUSIC AND COMBINATORICS 1,2","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Pacific Institute for the Mathematical Sciences","funders":"","keywords":"Substring; Computer science; Conjecture; String searching algorithm; Deterministic finite automaton; Decision problem; Automaton; String (physics); Theoretical computer science; Suffix; Type (biology); Combinatorial optimization; Pattern matching; Combinatorics; Algorithm; Mathematics; Data structure; Artificial intelligence; Programming language","score_opus":0.028362694850264724,"score_gpt":0.251765867156383,"score_spread":0.22340317230611828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594439285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09276322,0.019056562,0.76685727,0.015232464,0.0012478406,0.0002930835,0.0017474357,0.0011975061,0.101604685],"genre_scores_gemma":[0.5609548,0.010023501,0.38888174,0.0012454236,0.0017896767,0.0004782273,0.0023176575,0.00052451465,0.033784445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838877,0.0004591755,0.00013283711,0.0003966181,0.00046525587,0.00015743538],"domain_scores_gemma":[0.99542964,0.0033965951,0.00021236758,0.0005291849,0.00024353867,0.00018870216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001217902,0.0009661926,0.0011420089,0.0015284874,0.0022406015,0.004955396,0.0015641818,0.0021271796,0.014756907],"category_scores_gemma":[0.007617165,0.0004572196,0.0009444953,0.00520468,0.003927785,0.008519854,0.002436924,0.004417529,0.0017788148],"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":[0.00009397071,0.00009054708,0.00055075594,0.0004011817,0.000019914698,0.00011587225,0.00020995985,0.011791072,0.001215112,0.88539207,0.016905094,0.08321453],"study_design_scores_gemma":[0.000017521583,0.000016515824,0.0001929952,0.00003645301,0.000008815784,0.00015874884,0.00011821076,0.01987249,0.0007009636,0.9597069,0.01915824,0.000012153431],"about_ca_topic_score_codex":0.0018488696,"about_ca_topic_score_gemma":0.0018934051,"teacher_disagreement_score":0.014756907,"about_ca_system_score_codex":0.003198835,"about_ca_system_score_gemma":0.0015902898,"threshold_uncertainty_score":0.04936683},"labels":[],"label_agreement":null},{"id":"W1595525475","doi":"10.1007/978-3-642-10631-6_97","title":"Lower Bounds on Fast Searching","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Time complexity; Graph; Combinatorics; Quadratic equation; Jump; Enhanced Data Rates for GSM Evolution; Discrete mathematics; Algorithm; Mathematics; Theoretical computer science; Artificial intelligence","score_opus":0.01611362933346579,"score_gpt":0.2583661912551287,"score_spread":0.24225256192166292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595525475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028373023,0.02144092,0.6093898,0.010694816,0.0025987425,0.00034801094,0.0032178613,0.004604497,0.31933242],"genre_scores_gemma":[0.44219145,0.024278652,0.3156098,0.005616356,0.008035413,0.002586054,0.0067551383,0.008731334,0.18619578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98756963,0.0020638665,0.00052406464,0.0018771497,0.005293812,0.0026713894],"domain_scores_gemma":[0.9336351,0.04856205,0.0015798927,0.0108937975,0.0032444126,0.0020847297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006233899,0.0057335594,0.006411007,0.008129491,0.0048603043,0.010588761,0.012691612,0.005427193,0.05678498],"category_scores_gemma":[0.055390496,0.0029931762,0.003686928,0.014606518,0.007695243,0.028343685,0.012313224,0.017170375,0.012938169],"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":[0.00090938964,0.00025004186,0.0005155132,0.0009029204,0.000102379236,0.00009084053,0.00033918352,0.032897566,0.0020298841,0.7868465,0.058326814,0.116788924],"study_design_scores_gemma":[0.00009229937,0.000066001776,0.00026393056,0.00018715159,0.00011327321,0.00015618932,0.00006935348,0.074237615,0.0012393233,0.9091506,0.014371461,0.00005282005],"about_ca_topic_score_codex":0.0041291513,"about_ca_topic_score_gemma":0.004721969,"teacher_disagreement_score":0.05678498,"about_ca_system_score_codex":0.007873871,"about_ca_system_score_gemma":0.0053948793,"threshold_uncertainty_score":0.18996471},"labels":[],"label_agreement":null},{"id":"W1596809600","doi":"","title":"Suffix arrays: what are they good for?","year":2006,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Suffix; Compressed suffix array; Computer science; Generalized suffix tree; Suffix array; Suffix tree; Theoretical computer science; Algorithm; Linguistics","score_opus":0.03750431777709179,"score_gpt":0.27228025771620495,"score_spread":0.23477593993911317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1596809600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04514812,0.17113654,0.44699883,0.23963825,0.015898474,0.00033725423,0.0029042442,0.0053260657,0.072612256],"genre_scores_gemma":[0.26361957,0.09790182,0.54985553,0.031530466,0.015667973,0.0007727392,0.0034578273,0.0042247525,0.03296928],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895439,0.0045366655,0.00083075574,0.0013124924,0.003210592,0.0005655313],"domain_scores_gemma":[0.9341604,0.03633433,0.0025713677,0.016470322,0.008502471,0.001961145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01120759,0.0011692311,0.0024042958,0.0029172336,0.0026672792,0.010903129,0.0027230617,0.0052823736,0.01377457],"category_scores_gemma":[0.12922743,0.001128008,0.0009488654,0.005749077,0.00909532,0.040969845,0.0041219615,0.0057094498,0.012070433],"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":[0.000725674,0.00008688158,0.003375349,0.0012441004,0.00011425313,0.00019629695,0.0013134112,0.0025510346,0.0031985121,0.39480644,0.0713283,0.5210597],"study_design_scores_gemma":[0.00008267082,0.00022254806,0.0007243018,0.0010734216,0.00006756546,0.0007653414,0.0013529984,0.004849057,0.0037806155,0.66209245,0.32489786,0.00009111648],"about_ca_topic_score_codex":0.00076755346,"about_ca_topic_score_gemma":0.0008743631,"teacher_disagreement_score":0.01377457,"about_ca_system_score_codex":0.0014645228,"about_ca_system_score_gemma":0.001921333,"threshold_uncertainty_score":0.05927211},"labels":[],"label_agreement":null},{"id":"W1597468572","doi":"10.1007/978-3-642-02927-1_38","title":"Universal Succinct Representations of Trees?","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Theoretical computer science; Programming language","score_opus":0.014718702996058803,"score_gpt":0.25614461260910765,"score_spread":0.24142590961304886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597468572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052470427,0.0054081767,0.8395491,0.0058273333,0.0011740173,0.00009998255,0.0018165736,0.0018934193,0.09176086],"genre_scores_gemma":[0.6811872,0.007379437,0.25675777,0.0024342085,0.001221575,0.00033454254,0.003972327,0.0014871196,0.045225795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991041,0.00020050826,0.00007781378,0.00015673295,0.0003223597,0.0001384845],"domain_scores_gemma":[0.9975968,0.0011093343,0.00015834137,0.0008336945,0.00020467947,0.00009717459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085837493,0.00060298917,0.00078012137,0.00083739957,0.0005459709,0.0031394735,0.0013014204,0.0012206871,0.01473615],"category_scores_gemma":[0.007248002,0.00065439846,0.00054774916,0.0017673749,0.0016559432,0.010617832,0.002613269,0.003127745,0.0030301274],"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":[0.000055540455,0.000020770287,0.00007201617,0.00009869227,0.00000749278,0.000032109576,0.0002269616,0.0029893448,0.0008788795,0.9334584,0.007874736,0.054284997],"study_design_scores_gemma":[0.000011491328,0.0000080753725,0.000032770826,0.00005072969,0.0000064513642,0.00005257675,0.000051593077,0.0055819186,0.00078760996,0.9814973,0.011910756,0.000008802242],"about_ca_topic_score_codex":0.00047545874,"about_ca_topic_score_gemma":0.0006295401,"teacher_disagreement_score":0.01473615,"about_ca_system_score_codex":0.00078266836,"about_ca_system_score_gemma":0.00055380724,"threshold_uncertainty_score":0.049297333},"labels":[],"label_agreement":null},{"id":"W1597749830","doi":"10.1109/dcc.2002.1000008","title":"Turbo source coding: a noise-robust approach to data compression","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":48,"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":"Huffman coding; Shannon–Fano coding; Tunstall coding; Variable-length code; Computer science; Algorithm; Additive white Gaussian noise; Arithmetic coding; Context-adaptive binary arithmetic coding; Turbo code; Data compression; Decoding methods; Concatenated error correction code; Entropy encoding; Theoretical computer science; Speech recognition; White noise; Block code; Telecommunications","score_opus":0.08087794821133999,"score_gpt":0.26880481143722906,"score_spread":0.18792686322588908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597749830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027700618,0.006408057,0.9785646,0.00063200813,0.00060373184,0.00007554364,0.000117018346,0.00085653976,0.009972503],"genre_scores_gemma":[0.21314293,0.030300418,0.71412104,0.0006811672,0.0037856754,0.0003471422,0.00093909854,0.00058011705,0.036102347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995448,0.000105593484,0.000028324752,0.000049312115,0.00024471767,0.000027148071],"domain_scores_gemma":[0.9992004,0.00032286125,0.000045936195,0.00009994318,0.0003032749,0.000027540313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005086894,0.0007957405,0.0008017283,0.0010629487,0.00028032454,0.0009490874,0.0010516819,0.0009027433,0.0064434],"category_scores_gemma":[0.0021170015,0.00021705835,0.00044276917,0.0018413652,0.00094573846,0.0011403282,0.0005874772,0.0010298167,0.003090945],"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":[0.00022995418,0.000054021562,0.00031303306,0.0007897318,0.00012654532,0.0005522215,0.00012556041,0.15574375,0.03271081,0.16330841,0.0403414,0.60570455],"study_design_scores_gemma":[0.00004141599,0.00020903339,0.00023372726,0.00014566365,0.000064604945,0.0006870671,0.00002504171,0.82402635,0.025109323,0.0929915,0.0563866,0.000079684],"about_ca_topic_score_codex":0.0008714225,"about_ca_topic_score_gemma":0.00083895493,"teacher_disagreement_score":0.0064434,"about_ca_system_score_codex":0.0004653916,"about_ca_system_score_gemma":0.000550412,"threshold_uncertainty_score":0.021555364},"labels":[],"label_agreement":null},{"id":"W1597806222","doi":"10.1007/3-540-45655-4_35","title":"Repetition Complexity of Words","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Repetition (rhetorical device); De Bruijn sequence; Word (group theory); Iterated function; Computational complexity theory; Morphism; Logarithm; Time complexity; Complexity class; Combinatorics on words; Combinatorics; Discrete mathematics; Mathematics; Prefix; Computer science; Arithmetic; Algorithm","score_opus":0.035674482716048415,"score_gpt":0.2534903773255783,"score_spread":0.21781589460952985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597806222","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5074577,0.0030728194,0.15520489,0.004359839,0.00042845268,0.00012079232,0.0014359143,0.0008497254,0.32706988],"genre_scores_gemma":[0.928985,0.0011238392,0.019686004,0.00035816187,0.0005729057,0.0001798543,0.0009839771,0.00032804997,0.04778223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838006,0.00027680217,0.00009991208,0.000312051,0.00068446505,0.00024672982],"domain_scores_gemma":[0.99500483,0.003228099,0.0003750191,0.0006922752,0.00041936905,0.0002803705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005235865,0.0005851396,0.0010756518,0.0027063373,0.0016794477,0.0035525362,0.0016256844,0.0011650076,0.017907789],"category_scores_gemma":[0.0058970866,0.0005950437,0.0011096785,0.0031347852,0.0026929395,0.007981815,0.0027317333,0.003177512,0.0022133864],"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":[0.00007092689,0.000018958144,0.0004402164,0.00007662154,0.000013325522,0.00010771797,0.0003986367,0.0023252484,0.0012205718,0.97631425,0.0036583003,0.015355271],"study_design_scores_gemma":[0.000008116544,0.000014370334,0.00030197614,0.00000951012,0.000011385141,0.00014748334,0.00005085027,0.0047122533,0.00070806185,0.9904522,0.003570442,0.000013317257],"about_ca_topic_score_codex":0.0010682055,"about_ca_topic_score_gemma":0.0009807574,"teacher_disagreement_score":0.017907789,"about_ca_system_score_codex":0.0017332697,"about_ca_system_score_gemma":0.0008248971,"threshold_uncertainty_score":0.059907556},"labels":[],"label_agreement":null},{"id":"W1599214081","doi":"10.1145/1242471.1242472","title":"A taxonomy of suffix array construction algorithms","year":2007,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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":"Suffix array; Compressed suffix array; Computer science; Suffix; Generalized suffix tree; Suffix tree; Algorithm; Implementation; Theoretical computer science; Data structure; Programming language","score_opus":0.03606046574601381,"score_gpt":0.27250997427313595,"score_spread":0.23644950852712213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599214081","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063042208,0.02035573,0.9523004,0.00097509957,0.00035664684,0.00043852584,0.0008933913,0.004028228,0.014347656],"genre_scores_gemma":[0.023962984,0.021727769,0.942918,0.0005846171,0.00034898976,0.0006270643,0.0030396988,0.0006196312,0.0061712633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99594456,0.00073615805,0.00064489915,0.00070403406,0.001690631,0.00027965909],"domain_scores_gemma":[0.99148715,0.00385494,0.00045718314,0.0019350518,0.002102972,0.00016272027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030566046,0.0017400617,0.001747181,0.0063184677,0.0017660981,0.0048729936,0.003949937,0.0023125822,0.00512405],"category_scores_gemma":[0.01444847,0.0013057604,0.0016106355,0.016752422,0.0012062518,0.0087514715,0.0028182236,0.0030239695,0.0067258333],"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":[0.00013453182,0.00013654877,0.0014857844,0.0013462352,0.000052518077,0.000094845345,0.00027674143,0.010037489,0.004600808,0.08318765,0.020730011,0.8779169],"study_design_scores_gemma":[0.000120909106,0.00045699123,0.0017664857,0.0011870539,0.00014886321,0.004281283,0.00057786296,0.20903763,0.032038487,0.2945013,0.45566595,0.00021708106],"about_ca_topic_score_codex":0.0010871772,"about_ca_topic_score_gemma":0.0010540306,"teacher_disagreement_score":0.0063184677,"about_ca_system_score_codex":0.0012021133,"about_ca_system_score_gemma":0.0025220898,"threshold_uncertainty_score":0.0171417},"labels":[],"label_agreement":null},{"id":"W1599317246","doi":"10.1007/978-3-540-87744-8_33","title":"Succinct Representations of Arbitrary Graphs","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Upper and lower bounds; Combinatorics; Vertex (graph theory); Constant (computer programming); Discrete mathematics; Mathematics; Multiplicative function; Graph; Computer science","score_opus":0.017594277416723068,"score_gpt":0.25533276676203776,"score_spread":0.2377384893453147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599317246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03579318,0.001395187,0.91068864,0.001402571,0.00037662164,0.0001702393,0.004886398,0.0030230742,0.04226413],"genre_scores_gemma":[0.42405066,0.003704271,0.50819474,0.0006850513,0.00034396237,0.0005664522,0.0167478,0.0019467989,0.04376013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993487,0.0001728807,0.000054258555,0.000103189355,0.00025354177,0.000067472945],"domain_scores_gemma":[0.99790394,0.0008753388,0.00013170583,0.0007789599,0.00024512273,0.000064956635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048311584,0.0009388801,0.00067367667,0.0012600013,0.00048376495,0.0024254657,0.0015204512,0.0010202208,0.014132634],"category_scores_gemma":[0.003920905,0.0005790165,0.00056033704,0.002527708,0.00083318626,0.006188648,0.002036708,0.0023055528,0.0028659878],"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":[0.00025606932,0.00008424338,0.00020879987,0.00038134702,0.000022141992,0.00024039537,0.0004205468,0.05183286,0.0046220156,0.7157811,0.028344408,0.1978061],"study_design_scores_gemma":[0.000029997622,0.000028151737,0.00009446884,0.000094012015,0.00001784619,0.00018194053,0.000106759624,0.0852118,0.0037962815,0.879272,0.03114834,0.000018397996],"about_ca_topic_score_codex":0.000693051,"about_ca_topic_score_gemma":0.0015491231,"teacher_disagreement_score":0.014132634,"about_ca_system_score_codex":0.00064279913,"about_ca_system_score_gemma":0.000526314,"threshold_uncertainty_score":0.047278404},"labels":[],"label_agreement":null},{"id":"W1600674239","doi":"10.1016/j.dam.2015.05.019","title":"Computing covers using prefix tables","year":2015,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; London Mathematical Society; Bangladesh University of Engineering and Technology; Government of the United Kingdom","keywords":"Substring; Cover (algebra); Mathematics; Combinatorics; Integer (computer science); Prefix; String (physics); Alphabet; Sequence (biology); Table (database); Discrete mathematics; Algorithm; Data structure; Computer science","score_opus":0.049241740002295066,"score_gpt":0.2826943611037871,"score_spread":0.23345262110149204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600674239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16547765,0.001803225,0.8126972,0.0007172645,0.00020095309,0.000118283366,0.00182446,0.0027270205,0.014434065],"genre_scores_gemma":[0.6183391,0.0016752643,0.36636278,0.0002665683,0.00033436046,0.00020164777,0.004552075,0.0006200181,0.0076481774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99793434,0.00033443017,0.00019205622,0.000407075,0.0009059692,0.00022609778],"domain_scores_gemma":[0.9940189,0.0030961954,0.00026413644,0.0018573167,0.0005584367,0.00020494874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011784312,0.00073671667,0.0014649518,0.003366635,0.0010384584,0.0040912163,0.0011548195,0.0008288011,0.007525706],"category_scores_gemma":[0.0093003865,0.0006706077,0.0010649227,0.005797544,0.001214988,0.011348604,0.0033652147,0.0014691645,0.0020884464],"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":[0.00080790155,0.000112533795,0.004086637,0.0004139447,0.00013920183,0.0002921201,0.0005579903,0.07492542,0.009157959,0.48677006,0.01352019,0.40921608],"study_design_scores_gemma":[0.000028914688,0.00010843882,0.0005361509,0.00008790819,0.00007137588,0.00027791303,0.00016312879,0.22671665,0.010642473,0.74666446,0.014676297,0.00002627325],"about_ca_topic_score_codex":0.0008796913,"about_ca_topic_score_gemma":0.0013089753,"teacher_disagreement_score":0.007525706,"about_ca_system_score_codex":0.001171442,"about_ca_system_score_gemma":0.00090789126,"threshold_uncertainty_score":0.025175989},"labels":[],"label_agreement":null},{"id":"W1601419553","doi":"10.1007/978-3-540-30219-3_36","title":"The Most Probable Labeling Problem in HMMs and Its Application to Bioinformatics","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Computer science; Sequence labeling; Heuristics; Sequence (biology); Annotation; Path (computing); Artificial intelligence; Algorithm; Pattern recognition (psychology); Theoretical computer science; Biology; Genetics; Programming language","score_opus":0.010959327423742858,"score_gpt":0.23299681353526347,"score_spread":0.2220374861115206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601419553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021887796,0.0015122022,0.99422234,0.0007279776,0.000113392234,0.000017257296,0.00012859982,0.00044704683,0.0006423363],"genre_scores_gemma":[0.07402998,0.004062102,0.91143537,0.0005875922,0.0010864488,0.000274548,0.0013020126,0.0007597594,0.0064622113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963491,0.001884646,0.00026125222,0.0007055748,0.00067024166,0.00012910618],"domain_scores_gemma":[0.96505827,0.030470109,0.00062768214,0.002341233,0.0011446624,0.00035802848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006995272,0.0011937022,0.0031796107,0.002407024,0.0023158279,0.003598412,0.0046814936,0.0063514193,0.0051090736],"category_scores_gemma":[0.042076502,0.002632374,0.0017676449,0.007160297,0.0037292195,0.008029165,0.0035017729,0.0072313743,0.0028501917],"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":[0.00027974712,0.00016271493,0.0017594065,0.0006452874,0.000118922806,0.00037747773,0.00071879034,0.32855707,0.0023457725,0.2557829,0.022162773,0.38708907],"study_design_scores_gemma":[0.000019221246,0.000012684166,0.00017134733,0.00002677661,0.00001842319,0.00013699749,0.000044441,0.53704184,0.0006610075,0.45833445,0.0035032497,0.000029533901],"about_ca_topic_score_codex":0.0042524277,"about_ca_topic_score_gemma":0.0035788657,"teacher_disagreement_score":0.006995272,"about_ca_system_score_codex":0.0015474298,"about_ca_system_score_gemma":0.0015474056,"threshold_uncertainty_score":0.036994994},"labels":[],"label_agreement":null},{"id":"W1605680918","doi":"10.1007/11815921_2","title":"On the Theory and Applications of Sequence Based Estimation of Independent Binomial Random Variables","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Sequence (biology); Cardinality (data modeling); Estimation; Set (abstract data type); Convergence (economics); Markov chain; Mathematics; Binomial (polynomial); Statistics; Maximum likelihood; Random variable; Binomial distribution; Computer science; Algorithm; Econometrics; Data mining","score_opus":0.011239497373828096,"score_gpt":0.23598331258427305,"score_spread":0.22474381521044495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605680918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009916426,0.0013336412,0.9962219,0.00014056374,0.00009496201,0.00001732201,0.000025943125,0.00005035229,0.0011237729],"genre_scores_gemma":[0.12272723,0.0138708465,0.85224885,0.0009232607,0.0019236075,0.0005199608,0.00057328533,0.0002511481,0.006961774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99205583,0.0050729928,0.00037527457,0.0006148416,0.0016488486,0.00023221257],"domain_scores_gemma":[0.93846184,0.05585007,0.0012599824,0.0020852168,0.0020352139,0.00030765455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010991079,0.0018603614,0.0028910558,0.0030204884,0.00088788953,0.0028907175,0.0035598595,0.0032150198,0.004202106],"category_scores_gemma":[0.05890411,0.0016111387,0.001849563,0.005905109,0.004055603,0.0058012228,0.004123743,0.0043049357,0.0011462725],"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":[0.00009245426,0.00004385707,0.00089499186,0.00030863294,0.0001222043,0.00016233843,0.00023647214,0.20069827,0.0013771134,0.7008228,0.0030057067,0.092235245],"study_design_scores_gemma":[0.000015580134,0.000044416785,0.00029098266,0.00011677469,0.000033109078,0.00025786567,0.000027097423,0.6402145,0.0006269819,0.35444874,0.0038742598,0.000049785296],"about_ca_topic_score_codex":0.0022578936,"about_ca_topic_score_gemma":0.0016924742,"teacher_disagreement_score":0.010991079,"about_ca_system_score_codex":0.0012808033,"about_ca_system_score_gemma":0.0015287808,"threshold_uncertainty_score":0.058127105},"labels":[],"label_agreement":null},{"id":"W1607454116","doi":"10.1007/978-3-642-04747-3_29","title":"Contrasting Sequence Groups by Emerging Sequences","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Categorical variable; Classifier (UML); Suffix tree; Artificial intelligence; Sequence (biology); Contrast (vision); Suffix; Matching (statistics); Pattern recognition (psychology); Machine learning; Data structure; Mathematics; Statistics","score_opus":0.01930631283835114,"score_gpt":0.2575602706210861,"score_spread":0.23825395778273498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607454116","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19790211,0.00073089893,0.7582725,0.00044571838,0.0002424288,0.00014738883,0.00028353505,0.0005646242,0.041410774],"genre_scores_gemma":[0.67057765,0.0006846234,0.30653423,0.00020523154,0.00023266229,0.00020892899,0.0010898398,0.00043314797,0.02003369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927324,0.00023781638,0.000040189116,0.00018419907,0.00018395753,0.000080632635],"domain_scores_gemma":[0.9956067,0.0023499988,0.0003715369,0.00066443335,0.0007161664,0.0002911777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010916844,0.00046768808,0.00043918178,0.0019691752,0.0007340071,0.002081753,0.00089102227,0.00080607407,0.010713348],"category_scores_gemma":[0.0076001887,0.00027703316,0.00047250904,0.0015979626,0.0015018437,0.003858234,0.0017010957,0.0012311707,0.0017943726],"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":[0.00048763095,0.000046752695,0.002907959,0.0002274015,0.000025805406,0.00046076856,0.001846181,0.0062419353,0.031213608,0.78040576,0.0029913539,0.17314482],"study_design_scores_gemma":[0.000033957123,0.00018169881,0.0021447034,0.00008454816,0.00003006117,0.0006328402,0.001129009,0.04614633,0.012329435,0.9098846,0.027377509,0.000025416899],"about_ca_topic_score_codex":0.00018562534,"about_ca_topic_score_gemma":0.0002864936,"teacher_disagreement_score":0.010713348,"about_ca_system_score_codex":0.0003933027,"about_ca_system_score_gemma":0.0002676744,"threshold_uncertainty_score":0.035839677},"labels":[],"label_agreement":null},{"id":"W1608696406","doi":"10.1007/978-3-642-16321-0_12","title":"On the Hardness of Counting and Sampling Center Strings","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"String (physics); Hamming distance; Center (category theory); Combinatorics; Sampling (signal processing); Discrete mathematics; Set (abstract data type); Hamming code; Mathematics; Computer science; Algorithm","score_opus":0.021761438101420977,"score_gpt":0.2469438099727687,"score_spread":0.22518237187134774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1608696406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14225173,0.006247825,0.6065449,0.019240353,0.0012888241,0.00031144856,0.0029380675,0.0028714885,0.2183054],"genre_scores_gemma":[0.75248224,0.004725324,0.16377059,0.004770476,0.003365655,0.0009884726,0.004650911,0.0025540157,0.06269225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9914588,0.0023577083,0.00048700318,0.0016556126,0.0029878544,0.00105306],"domain_scores_gemma":[0.94331425,0.046841033,0.0012613641,0.0059704375,0.0017281496,0.00088469015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00450258,0.0017869812,0.003829823,0.0030977598,0.0043081786,0.008103107,0.0064082006,0.00522259,0.01787349],"category_scores_gemma":[0.04369351,0.001904915,0.0030191662,0.00702565,0.008327296,0.02487689,0.007974883,0.012111791,0.0030345442],"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":[0.00047306655,0.000115869385,0.00081495184,0.00028501407,0.00004689312,0.00008864751,0.0003603996,0.017419213,0.0010355561,0.9147546,0.018910334,0.0456954],"study_design_scores_gemma":[0.00005176504,0.000016980805,0.00019329804,0.000038564936,0.000020786334,0.000066738095,0.000049163187,0.031467043,0.00070268684,0.96411306,0.003259164,0.000020698999],"about_ca_topic_score_codex":0.002994265,"about_ca_topic_score_gemma":0.002129513,"teacher_disagreement_score":0.01787349,"about_ca_system_score_codex":0.004898502,"about_ca_system_score_gemma":0.0029864316,"threshold_uncertainty_score":0.059792817},"labels":[],"label_agreement":null},{"id":"W162020490","doi":"","title":"Algorithmic approaches to joint source-channel coding","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Binary erasure channel; Computer science; Redundancy (engineering); Channel (broadcasting); Coding (social sciences); Erasure; Algorithm; Decoding methods; Scalability; Erasure code; Source code; Variable-length code; Shannon–Fano coding; Theoretical computer science; Network packet; Channel capacity; Computer network; Mathematics; Statistics","score_opus":0.12769003452396208,"score_gpt":0.2368964247133945,"score_spread":0.10920639018943243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W162020490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016175362,0.0003492089,0.99100715,0.0002591237,0.000031836324,0.000041367137,0.00004672497,0.0000711493,0.0065758023],"genre_scores_gemma":[0.17180067,0.0018458465,0.81698203,0.000329788,0.0002577684,0.00063155015,0.00038645318,0.00013127495,0.0076345643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825674,0.00071101025,0.00007872677,0.00026266216,0.00053560646,0.00015517877],"domain_scores_gemma":[0.9969195,0.0021197041,0.00014497207,0.00038803535,0.00037413952,0.000053691314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021400466,0.0011539645,0.00078740326,0.0013386804,0.00096839375,0.0021859184,0.0024120111,0.0016715268,0.005466036],"category_scores_gemma":[0.006007586,0.0007281493,0.0010237796,0.0015442836,0.002440706,0.0024114342,0.0026942294,0.0025598418,0.0010066647],"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":[0.000021986,0.000034609162,0.00021738657,0.00010744126,0.00002934257,0.000049869806,0.00009138444,0.32007042,0.00060876645,0.64822054,0.001525864,0.029022489],"study_design_scores_gemma":[0.000021767444,0.000024737901,0.000055401048,0.000028338542,0.000008927702,0.000036756235,0.000026706144,0.58087397,0.00039199696,0.4136008,0.0049138675,0.000016742013],"about_ca_topic_score_codex":0.0024013093,"about_ca_topic_score_gemma":0.0026638196,"teacher_disagreement_score":0.005466036,"about_ca_system_score_codex":0.0018618434,"about_ca_system_score_gemma":0.0022673502,"threshold_uncertainty_score":0.018285751},"labels":[],"label_agreement":null},{"id":"W162020651","doi":"10.4018/978-1-60566-058-5.ch014","title":"Indexing Textual Information","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Algorithms and Data Compression","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":"","keywords":"Search engine indexing; Computer science; Information retrieval; String (physics); Representation (politics); Data structure; Implementation; Space (punctuation); Theoretical computer science; Mathematics; Programming language","score_opus":0.013208433049296888,"score_gpt":0.23186070739766598,"score_spread":0.2186522743483691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W162020651","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031188188,0.026995093,0.52003974,0.0043147993,0.00327701,0.0020439285,0.042947415,0.017830767,0.351363],"genre_scores_gemma":[0.1459928,0.02709875,0.5352199,0.0020559998,0.0022861953,0.0012666621,0.07710541,0.003922902,0.20505138],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990761,0.00015866755,0.00011454636,0.00017250997,0.00041530776,0.000062772095],"domain_scores_gemma":[0.9968617,0.0014106826,0.00022343987,0.0006640552,0.0007262693,0.000113835384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007866035,0.00088836596,0.0008431363,0.009467647,0.0012380254,0.0038941072,0.0017396475,0.00087755144,0.057922717],"category_scores_gemma":[0.0069732917,0.0003603694,0.00061277737,0.013101065,0.00088998966,0.0062026293,0.002401724,0.0008176698,0.030724786],"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":[0.00009954291,0.000085094856,0.00038741724,0.0016469338,0.00003412481,0.00023454498,0.00066815515,0.0011219697,0.010740792,0.07274685,0.10120084,0.8110337],"study_design_scores_gemma":[0.00004272994,0.0000975566,0.0013410996,0.0009075922,0.00009628927,0.0013408887,0.0007714817,0.013299558,0.020557154,0.09138955,0.87007636,0.000079697835],"about_ca_topic_score_codex":0.0012335088,"about_ca_topic_score_gemma":0.0015324608,"teacher_disagreement_score":0.057922717,"about_ca_system_score_codex":0.0012207045,"about_ca_system_score_gemma":0.0013383323,"threshold_uncertainty_score":0.19377083},"labels":[],"label_agreement":null},{"id":"W1627186833","doi":"10.48550/arxiv.cs/0611099","title":"On the space complexity of one-pass compression","year":2006,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"","keywords":"Combinatorics; Mathematics; Binary logarithm; Order (exchange); String (physics); Memory footprint; Compression (physics); Entropy (arrow of time); Footprint; Space (punctuation); Discrete mathematics; Physics; Mathematical physics; Computer science; Quantum mechanics; Thermodynamics","score_opus":0.11265318535818436,"score_gpt":0.28642590181039546,"score_spread":0.1737727164522111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1627186833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48871782,0.012896681,0.431467,0.011218004,0.0005094635,0.00036507274,0.0017003384,0.0060946858,0.047030926],"genre_scores_gemma":[0.8145882,0.002999135,0.162345,0.001062023,0.0005546276,0.00050800445,0.0015887748,0.001056789,0.015297362],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993807,0.00141848,0.00046057013,0.00071802776,0.0025443733,0.0010514521],"domain_scores_gemma":[0.9732747,0.019683931,0.00093864155,0.0044802236,0.001204402,0.00041806055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033978233,0.0015107478,0.0020667305,0.0017386465,0.001653085,0.004752445,0.003103281,0.0024528776,0.010871344],"category_scores_gemma":[0.023070708,0.000753173,0.0012100218,0.0039193877,0.002530518,0.01590593,0.004339575,0.0025588619,0.0026941],"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":[0.0054639573,0.0006229704,0.008528506,0.0010652865,0.00032928272,0.0006670357,0.0010873141,0.24796788,0.030159231,0.16967145,0.031571686,0.5028654],"study_design_scores_gemma":[0.00026023155,0.00036752032,0.0013379722,0.00009699849,0.00014083873,0.0005492148,0.0003049336,0.8420122,0.014865935,0.1343415,0.005651716,0.000070887756],"about_ca_topic_score_codex":0.0030846524,"about_ca_topic_score_gemma":0.0040235464,"teacher_disagreement_score":0.010871344,"about_ca_system_score_codex":0.0028616781,"about_ca_system_score_gemma":0.0028893764,"threshold_uncertainty_score":0.03636831},"labels":[],"label_agreement":null},{"id":"W1632814704","doi":"10.1109/dcc.2003.1194060","title":"Pattern matching by means of multi-resolution compression","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Pattern matching; Computer science; Compression (physics); Matching (statistics); Data compression; Scheme (mathematics); Compression ratio; Algorithm; Artificial intelligence; Mathematics; Engineering","score_opus":0.018909053177966206,"score_gpt":0.2530720331481034,"score_spread":0.2341629799701372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1632814704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008854921,0.0014560428,0.97534573,0.00036877795,0.0005205676,0.0002426333,0.0009460746,0.0043782587,0.007887043],"genre_scores_gemma":[0.07936074,0.0016301698,0.89661115,0.00021559077,0.00034485164,0.00031231157,0.0037880342,0.0008417782,0.016895425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880207,0.00015411052,0.00014662687,0.00031378397,0.00050420134,0.000079220874],"domain_scores_gemma":[0.99741876,0.000619891,0.00014543804,0.0010512444,0.0007004785,0.000064232205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007992743,0.0008340966,0.0011941491,0.0033281632,0.00069802813,0.001848917,0.0018777836,0.0008316871,0.034181803],"category_scores_gemma":[0.0054105786,0.0003420048,0.0007941126,0.006509337,0.00064728415,0.002972635,0.0014067655,0.0008899901,0.0126726795],"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":[0.00021329414,0.000048543156,0.00047544902,0.00042208604,0.000067375964,0.0003565509,0.00008740118,0.007478387,0.02563802,0.015731344,0.020647489,0.92883396],"study_design_scores_gemma":[0.00017889662,0.00042775122,0.003633123,0.00027547148,0.0002600479,0.0050001484,0.00032060803,0.40951473,0.22967291,0.06534951,0.2851757,0.00019117596],"about_ca_topic_score_codex":0.001189024,"about_ca_topic_score_gemma":0.0012542737,"teacher_disagreement_score":0.034181803,"about_ca_system_score_codex":0.00060054555,"about_ca_system_score_gemma":0.0006004654,"threshold_uncertainty_score":0.114349544},"labels":[],"label_agreement":null},{"id":"W1650804014","doi":"10.1007/978-3-642-22300-6_17","title":"Streaming and Dynamic Algorithms for Minimum Enclosing Balls in High Dimensions","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ball (mathematics); Combinatorics; Approx; Euclidean space; Upper and lower bounds; Algorithm; Mathematics; Space (punctuation); Discrete mathematics; Computer science; Geometry; Mathematical analysis","score_opus":0.018604654738011733,"score_gpt":0.2528615788993372,"score_spread":0.23425692416132546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1650804014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015139811,0.0012543572,0.9772081,0.00045318814,0.00018125425,0.000077835386,0.00025914193,0.0008018673,0.0046244035],"genre_scores_gemma":[0.17417601,0.0015794022,0.8104031,0.00021303559,0.00045454348,0.0003879026,0.0013406259,0.0006713375,0.010774036],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988457,0.00023196626,0.00008649598,0.00024362563,0.00045923213,0.00013297069],"domain_scores_gemma":[0.9955031,0.0025825459,0.00023086261,0.00091186975,0.000507528,0.00026412902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014944338,0.0016580849,0.002268835,0.0018108608,0.0011305964,0.0018351462,0.004614189,0.0017515303,0.010660605],"category_scores_gemma":[0.010603659,0.0010466035,0.0011796099,0.003604781,0.0015748964,0.0056874384,0.004372935,0.003506888,0.0018729254],"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":[0.0008815937,0.00026889253,0.0008623534,0.0006082262,0.00008050503,0.000099063494,0.00043747225,0.29642144,0.008007562,0.27765253,0.027286224,0.38739407],"study_design_scores_gemma":[0.00008477549,0.000069065354,0.0001953176,0.000039290044,0.000016272501,0.00009731402,0.00006410459,0.8279084,0.0020104342,0.16374601,0.005748338,0.000020571879],"about_ca_topic_score_codex":0.002878745,"about_ca_topic_score_gemma":0.0029020787,"teacher_disagreement_score":0.010660605,"about_ca_system_score_codex":0.0015682381,"about_ca_system_score_gemma":0.0010012244,"threshold_uncertainty_score":0.035663307},"labels":[],"label_agreement":null},{"id":"W167104252","doi":"","title":"Path Spectra and Forbidden Families.","year":2001,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Path (computing); Spectral line; Combinatorics; Computer science; Computer network; Physics; Astronomy","score_opus":0.010339195753276423,"score_gpt":0.22733423903899458,"score_spread":0.21699504328571817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W167104252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10967694,0.006921677,0.7177559,0.004802049,0.0006733281,0.00013721614,0.0017722483,0.002000497,0.15626012],"genre_scores_gemma":[0.7638776,0.0046501756,0.17657073,0.00126242,0.0005455628,0.00035484676,0.0021874667,0.00066294987,0.049888343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985067,0.000502101,0.00008919163,0.00025292914,0.0004794038,0.00016956827],"domain_scores_gemma":[0.99586076,0.0025893562,0.00026433935,0.00084979454,0.00028585686,0.00014990928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009988786,0.00047009383,0.0005224964,0.0021250986,0.0014978268,0.0027031614,0.00095538463,0.00085188006,0.012249442],"category_scores_gemma":[0.007766267,0.00038885398,0.00047702718,0.002506251,0.0023034096,0.0050387476,0.002212943,0.0020607244,0.0023360727],"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":[0.00009453325,0.000036247857,0.00039449797,0.00008886491,0.0000167063,0.0001420454,0.0002111809,0.0027888191,0.0011386261,0.91666657,0.009849835,0.06857214],"study_design_scores_gemma":[0.000008404238,0.000009859943,0.000105979,0.000037162343,0.0000064039505,0.00026391947,0.00008341123,0.0065296725,0.0010424126,0.98049635,0.011407924,0.000008475292],"about_ca_topic_score_codex":0.0005711665,"about_ca_topic_score_gemma":0.0007609664,"teacher_disagreement_score":0.012249442,"about_ca_system_score_codex":0.0012346191,"about_ca_system_score_gemma":0.0008660124,"threshold_uncertainty_score":0.04097843},"labels":[],"label_agreement":null},{"id":"W1685302609","doi":"","title":"Generating balanced parentheses and binary trees by prefix shifts","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Prefix; Parenthesis; Multiset; Binary tree; Combinatorics; Mathematics; Pointer (user interface); Binary number; Algorithm; Tree (set theory); Discrete mathematics; Computer science; Arithmetic","score_opus":0.02152215730994049,"score_gpt":0.23598887179455968,"score_spread":0.21446671448461918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1685302609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11392877,0.0004833354,0.8687242,0.00024185734,0.0001349585,0.0001531303,0.0004169959,0.0021319904,0.013784677],"genre_scores_gemma":[0.35252047,0.0003636715,0.6355072,0.00018295353,0.000078914134,0.00027059208,0.0009340846,0.000561896,0.009580098],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999143,0.00016981782,0.00006812522,0.00014507693,0.0003660234,0.00010796409],"domain_scores_gemma":[0.99892104,0.0004757427,0.00011953852,0.0002470955,0.00019128945,0.00004537374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055482937,0.00053491944,0.00054234103,0.000952179,0.0006543644,0.00090854295,0.00066506123,0.0005111363,0.0053083063],"category_scores_gemma":[0.0032520755,0.00031911233,0.0003863136,0.0013998257,0.00071803556,0.0019969863,0.001438138,0.0005566712,0.002249119],"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":[0.00061530364,0.00013708876,0.0016259025,0.00032635845,0.00004180253,0.00078526133,0.00070916844,0.04148446,0.08381997,0.25950754,0.010802912,0.6001441],"study_design_scores_gemma":[0.00021678518,0.00047967816,0.0010529713,0.00013350399,0.00008721063,0.0015863497,0.0002791161,0.29569346,0.19197854,0.44670847,0.06168297,0.000100970916],"about_ca_topic_score_codex":0.00039483033,"about_ca_topic_score_gemma":0.0006904537,"teacher_disagreement_score":0.0053083063,"about_ca_system_score_codex":0.00034260345,"about_ca_system_score_gemma":0.00044695698,"threshold_uncertainty_score":0.017758012},"labels":[],"label_agreement":null},{"id":"W1685382382","doi":"10.1007/s00453-008-9247-2","title":"Integer Representation and Counting in the Bit Probe Model","year":2008,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Integer (computer science); Bitwise operation; Logarithm; Theory of computation; Bit (key); Extension (predicate logic); Subtraction; Data structure; Mathematics; Representation (politics); Discrete mathematics; Arithmetic; Constant (computer programming); Computation; Algorithm; Computer science","score_opus":0.03527612363550482,"score_gpt":0.26384907289120285,"score_spread":0.22857294925569804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1685382382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055028666,0.0014503467,0.90362376,0.0040405164,0.00034716487,0.00006950764,0.00037380398,0.0006826398,0.034383558],"genre_scores_gemma":[0.7244157,0.0022650685,0.23335914,0.0016698933,0.0010385491,0.00050279277,0.0008881614,0.0007269052,0.03513374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740356,0.0009116574,0.00011755668,0.0003495285,0.0008479824,0.00036967278],"domain_scores_gemma":[0.99269134,0.0044336743,0.0004902777,0.0017424441,0.00044850665,0.00019375414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002233354,0.0010144897,0.0015161574,0.0022621835,0.0013922335,0.005157482,0.0027625049,0.0025138059,0.008971661],"category_scores_gemma":[0.018238697,0.0005579375,0.0009367968,0.003959221,0.0037675232,0.014149453,0.0029067793,0.0039657983,0.0018087788],"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":[0.00005390125,0.000019396031,0.0000928618,0.000025024898,0.000003494475,0.000027044072,0.000045796296,0.0086673265,0.00029857326,0.9788745,0.0018111871,0.010080934],"study_design_scores_gemma":[0.000008085524,0.0000073122874,0.000022344166,0.000009803472,0.0000041388284,0.000037758262,0.000015008161,0.061532844,0.00036169152,0.936631,0.0013612052,0.000008845844],"about_ca_topic_score_codex":0.0009650247,"about_ca_topic_score_gemma":0.00066231226,"teacher_disagreement_score":0.008971661,"about_ca_system_score_codex":0.0019105033,"about_ca_system_score_gemma":0.0013515815,"threshold_uncertainty_score":0.030013204},"labels":[],"label_agreement":null},{"id":"W1712117507","doi":"10.37236/3053","title":"Nested Recursions, Simultaneous Parameters and Tree Superpositions","year":2014,"lang":"en","type":"preprint","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Arity; Recursion (computer science); Tree (set theory); Sequence (biology); Combinatorics; Natural number; Mathematics; Order (exchange); Discrete mathematics; Algorithm","score_opus":0.008347747079386849,"score_gpt":0.23257732825101787,"score_spread":0.22422958117163103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1712117507","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028644487,0.000071172275,0.9641961,0.00013599571,0.000036657173,0.00005213052,0.000044402164,0.00021460255,0.0066045374],"genre_scores_gemma":[0.29024246,0.00017827644,0.6991134,0.00019064789,0.00006229937,0.00031526203,0.00017172855,0.000497833,0.009228076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987727,0.00031072632,0.000071828516,0.00022639133,0.00042349714,0.00019490076],"domain_scores_gemma":[0.99845326,0.00079806644,0.0001500546,0.00035033212,0.00016030685,0.00008791198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017066363,0.0006305871,0.0009177235,0.0008906603,0.0011883649,0.0013503387,0.0020704584,0.0017456248,0.0058778496],"category_scores_gemma":[0.0066420254,0.00057843403,0.001977698,0.0009829904,0.0022918275,0.0032367846,0.0025333492,0.0027784482,0.0011112007],"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":[0.00003136543,0.00005291587,0.0006938676,0.000084282525,0.000023142291,0.00015437914,0.00065426907,0.059293926,0.007880861,0.9036163,0.00083084684,0.026683927],"study_design_scores_gemma":[0.000021031035,0.000039270915,0.00018007241,0.00003698133,0.000024376799,0.00011326198,0.00012495885,0.39911973,0.0039799046,0.58826166,0.008063573,0.00003528911],"about_ca_topic_score_codex":0.0017390804,"about_ca_topic_score_gemma":0.0039755953,"teacher_disagreement_score":0.0058778496,"about_ca_system_score_codex":0.0012108053,"about_ca_system_score_gemma":0.0015265058,"threshold_uncertainty_score":0.019663393},"labels":[],"label_agreement":null},{"id":"W1712310231","doi":"10.1007/3-540-48080-3_7","title":"Compressibility as a Measure of Local Coherence in Web Graphs","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Measure (data warehouse); Compressibility; Link (geometry); Space (punctuation); Coherence (philosophical gambling strategy); Theoretical computer science; Data mining; Algorithm; Information retrieval; Mathematics; Computer network; Physics","score_opus":0.020416964883758604,"score_gpt":0.24502192666209177,"score_spread":0.22460496177833317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1712310231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87486875,0.0015015819,0.11590236,0.0007131428,0.00003182525,0.000057268622,0.0007117948,0.00038725897,0.0058260835],"genre_scores_gemma":[0.9925547,0.0003418184,0.0059810453,0.00004575582,0.00008429551,0.00003605527,0.0002660559,0.00006338515,0.00062683533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992448,0.00021579176,0.00005268492,0.00016233206,0.00021996185,0.00010442543],"domain_scores_gemma":[0.9731032,0.020645017,0.0026225944,0.0020030364,0.0008483145,0.00077779935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010709959,0.00029995845,0.0007142533,0.00454219,0.000734987,0.0015313785,0.0008531587,0.00095885346,0.0023348792],"category_scores_gemma":[0.012798638,0.0005115816,0.00028813796,0.0032913645,0.0019759734,0.0049336595,0.0011207109,0.0009789589,0.00018677757],"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":[0.0019726912,0.00037120175,0.047422152,0.000841407,0.00033323403,0.0015272239,0.004281159,0.3082203,0.06035156,0.42279547,0.0067446283,0.14513905],"study_design_scores_gemma":[0.00007466932,0.00023104897,0.026567237,0.00007872696,0.00014608935,0.00077438256,0.0010516192,0.5020616,0.016430158,0.4505876,0.0019133372,0.00008351432],"about_ca_topic_score_codex":0.0010129517,"about_ca_topic_score_gemma":0.0010522592,"teacher_disagreement_score":0.00454219,"about_ca_system_score_codex":0.00076428836,"about_ca_system_score_gemma":0.00022009268,"threshold_uncertainty_score":0.00781101},"labels":[],"label_agreement":null},{"id":"W171561842","doi":"","title":"Solving 8&times8 Hex","year":2009,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Algorithms and Data Compression","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":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.10282745820924619,"score_gpt":0.32720784558054083,"score_spread":0.22438038737129465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W171561842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039625168,0.00018645814,0.9299639,0.00039780408,0.0002580679,0.00016083878,0.0005425801,0.0020300646,0.026835214],"genre_scores_gemma":[0.16734323,0.00015640157,0.80195385,0.00021840897,0.000074136056,0.00032434537,0.0009428633,0.0009817991,0.028004922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999546,0.00006304159,0.000032278644,0.000129292,0.00013324257,0.00009609559],"domain_scores_gemma":[0.9993924,0.000294751,0.00005844388,0.0001047427,0.00010791074,0.00004163477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048402877,0.0010826662,0.0011402805,0.000459609,0.0007191169,0.0011680969,0.0010354946,0.0010683867,0.050689094],"category_scores_gemma":[0.0014798963,0.0005848815,0.0009315326,0.0007638173,0.0006858145,0.0017726329,0.0019089499,0.0014403255,0.006044347],"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":[0.00061043375,0.00024847974,0.0020497441,0.00097134965,0.00009139856,0.000759259,0.00036135424,0.26073834,0.015670747,0.0905359,0.035328973,0.592634],"study_design_scores_gemma":[0.00018627523,0.0002606422,0.0006441452,0.000079419086,0.000030254045,0.0005922073,0.00060359394,0.81775653,0.018985795,0.10923983,0.051572517,0.000048765127],"about_ca_topic_score_codex":0.001158105,"about_ca_topic_score_gemma":0.0018081416,"teacher_disagreement_score":0.050689094,"about_ca_system_score_codex":0.0003908424,"about_ca_system_score_gemma":0.0009987872,"threshold_uncertainty_score":0.16957194},"labels":[],"label_agreement":null},{"id":"W1717515755","doi":"10.1016/j.dam.2011.11.009","title":"The universality of iterated hashing over variable-length strings","year":2011,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Iterated function; Hash function; Dynamic perfect hashing; Universal hashing; Double hashing; K-independent hashing; Perfect hash function; Combinatorics; Rolling hash; Discrete mathematics; Pairwise comparison; Collision resistance; Upper and lower bounds; Algorithm; Cryptographic hash function; Cryptography; Statistics; Computer science","score_opus":0.02156783680824183,"score_gpt":0.22221216568779847,"score_spread":0.20064432887955663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1717515755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40953413,0.0035570182,0.5665072,0.0014538864,0.00020224405,0.000067154644,0.00030639325,0.0010155586,0.017356304],"genre_scores_gemma":[0.96091235,0.00088026974,0.034140263,0.00029539835,0.00039097475,0.00007349688,0.00018552897,0.0001986419,0.0029230593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947484,0.0011513816,0.0004449971,0.0013533962,0.0014766512,0.0008251665],"domain_scores_gemma":[0.9621612,0.023133496,0.0025088438,0.009485071,0.0017934644,0.0009180221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040319148,0.0005259073,0.0016186676,0.0021556828,0.0016431271,0.0042336755,0.0026403214,0.0015889889,0.0020819977],"category_scores_gemma":[0.029641222,0.0010751279,0.0013803783,0.0020544014,0.008944965,0.011270377,0.0065531544,0.003746214,0.000418045],"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":[0.0002681629,0.000053483687,0.0020298453,0.00017604187,0.000055614128,0.00023766524,0.00094218634,0.017998368,0.004226206,0.9382081,0.00085825747,0.034946],"study_design_scores_gemma":[0.000033328386,0.00007035235,0.000489311,0.00005152372,0.000036696696,0.0002573858,0.000082424864,0.053674474,0.0027271453,0.9408962,0.0016343719,0.000046823843],"about_ca_topic_score_codex":0.0009460881,"about_ca_topic_score_gemma":0.0004871647,"teacher_disagreement_score":0.0042336755,"about_ca_system_score_codex":0.0016980966,"about_ca_system_score_gemma":0.0013348534,"threshold_uncertainty_score":0.021323025},"labels":[],"label_agreement":null},{"id":"W1737486334","doi":"10.48550/arxiv.1405.4892","title":"Alternative Algorithms for Lyndon Factorization","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Sheridan College","funders":"","keywords":"Factorization; Alphabet; String (physics); Combinatorics; Character (mathematics); Algorithm; Mathematics; Space (punctuation); Constant (computer programming); Computer science","score_opus":0.09168257609976917,"score_gpt":0.21590881896744596,"score_spread":0.12422624286767679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1737486334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065205838,0.0006171649,0.9856302,0.0002525786,0.00018237617,0.000083521154,0.00014124019,0.001753862,0.004818539],"genre_scores_gemma":[0.08189361,0.0005026019,0.9076898,0.00035347525,0.00019593404,0.00035956322,0.0009100529,0.0004997097,0.007595257],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955201,0.00093095,0.0004927549,0.0010780009,0.0014347734,0.0005434465],"domain_scores_gemma":[0.99467397,0.0019900212,0.00026026764,0.0016588832,0.0012454505,0.00017136963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00276776,0.0015936117,0.0014540179,0.0034013356,0.0018272061,0.0039884215,0.0032261484,0.0024021752,0.012810391],"category_scores_gemma":[0.013956761,0.00081513997,0.0016336248,0.0036324817,0.0021197936,0.0071032927,0.004219976,0.0025203524,0.0056056464],"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":[0.000909223,0.00020073468,0.0010810226,0.0004094216,0.000077868,0.00020317684,0.00063716713,0.029986234,0.012500927,0.36429843,0.013538087,0.5761577],"study_design_scores_gemma":[0.00028140369,0.00027021396,0.00039212665,0.00026444858,0.000060498453,0.00069242757,0.00034874788,0.45144466,0.032097794,0.450877,0.06309158,0.00017914898],"about_ca_topic_score_codex":0.003124259,"about_ca_topic_score_gemma":0.0052101635,"teacher_disagreement_score":0.012810391,"about_ca_system_score_codex":0.0023484004,"about_ca_system_score_gemma":0.0021659033,"threshold_uncertainty_score":0.042854965},"labels":[],"label_agreement":null},{"id":"W1740830514","doi":"10.1109/icsmc.2001.972876","title":"Enhanced static Fano coding","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Huffman coding; Fano plane; Lossless compression; Computer science; Algorithm; Shannon–Fano coding; Canonical Huffman code; Data compression; Coding (social sciences); Theoretical computer science; Decoding methods; Mathematics; Code rate; Systematic code","score_opus":0.02562122692773213,"score_gpt":0.2385757262851579,"score_spread":0.21295449935742577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1740830514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031195775,0.0004146574,0.9551285,0.00017749272,0.00009997065,0.000081260456,0.00019114255,0.0009519332,0.01175922],"genre_scores_gemma":[0.453343,0.00065013,0.527603,0.00026768804,0.00015179631,0.00019083224,0.0007163498,0.00026044773,0.016816666],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945873,0.00010818293,0.000025571026,0.00007928446,0.00025559482,0.00007259388],"domain_scores_gemma":[0.9986608,0.00046316546,0.0000907116,0.00036489934,0.00038124816,0.00003917448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000662022,0.00043321692,0.0004449524,0.0014404011,0.0006775532,0.000754286,0.0009387562,0.00047356237,0.0027068495],"category_scores_gemma":[0.0031569654,0.00017765007,0.0003234174,0.0016443329,0.00093120104,0.0017239755,0.0007254065,0.000497933,0.00061091426],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019876217,0.000043159253,0.0012059147,0.000120454904,0.000019098381,0.00027861763,0.00022600465,0.080949716,0.02906534,0.33936858,0.0065103276,0.5420141],"study_design_scores_gemma":[0.000026617843,0.000120762066,0.0007969589,0.000052757186,0.000030345756,0.00064973487,0.000067075576,0.7813817,0.045636903,0.12608337,0.045096193,0.000057561254],"about_ca_topic_score_codex":0.0023081528,"about_ca_topic_score_gemma":0.0035262073,"teacher_disagreement_score":0.0027068495,"about_ca_system_score_codex":0.0008818695,"about_ca_system_score_gemma":0.0008882835,"threshold_uncertainty_score":0.009055316},"labels":[],"label_agreement":null},{"id":"W1745342855","doi":"10.1016/j.disc.2015.08.002","title":"A surprisingly simple de Bruijn sequence construction","year":2015,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"De Bruijn sequence; Append; String (physics); Mathematics; Complement (music); Sequence (biology); Combinatorics; Amortized analysis; Discrete mathematics; Binary number; Simple (philosophy); Arithmetic; Computer science; Data structure; Programming language","score_opus":0.05442664942256222,"score_gpt":0.3003084988839092,"score_spread":0.24588184946134697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1745342855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07827208,0.0011178809,0.81015843,0.003427241,0.0016494672,0.00020956209,0.0005364544,0.0019085961,0.102720276],"genre_scores_gemma":[0.5470174,0.0012553796,0.3912754,0.0015196208,0.0009234695,0.00033975719,0.0008730835,0.00093647727,0.055859413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985825,0.0003611247,0.000070716815,0.0002800198,0.00056527695,0.00014036894],"domain_scores_gemma":[0.9977715,0.0011579716,0.000095167336,0.00062340137,0.00021474923,0.00013727037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008888227,0.0008496427,0.0008476243,0.001317146,0.001577127,0.0019105478,0.00121895,0.0015468871,0.011233482],"category_scores_gemma":[0.004667193,0.00054153835,0.00069706386,0.0016381713,0.0019496146,0.004187987,0.0028937168,0.0024357163,0.0040430934],"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":[0.00014083715,0.000099674864,0.00021653793,0.00015603054,0.000020886133,0.00020889012,0.00018572873,0.004022285,0.008841536,0.9127285,0.008005309,0.06537375],"study_design_scores_gemma":[0.000042650103,0.0000649286,0.00012785645,0.000037618775,0.00002246082,0.00043440648,0.000046574307,0.020123849,0.008954739,0.94834536,0.021758841,0.000040740622],"about_ca_topic_score_codex":0.00028504388,"about_ca_topic_score_gemma":0.0004226134,"teacher_disagreement_score":0.011233482,"about_ca_system_score_codex":0.00061759254,"about_ca_system_score_gemma":0.000903845,"threshold_uncertainty_score":0.037579715},"labels":[],"label_agreement":null},{"id":"W1753435468","doi":"10.1007/978-1-84882-171-2_4","title":"Qualitative Hidden Markov Models for Classifying Gene Expression Data","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Hidden Markov model; Computer science; Pattern recognition (psychology); Sequence (biology); Markov model; Artificial intelligence; Expression (computer science); Machine learning; Markov chain; Data mining","score_opus":0.1844179553609462,"score_gpt":0.36467433291848533,"score_spread":0.18025637755753912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1753435468","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011536059,0.0011964858,0.9948572,0.00026811849,0.00010518632,0.000025131025,0.000369053,0.00079981936,0.0012254678],"genre_scores_gemma":[0.07017352,0.0046201576,0.9067398,0.00046119295,0.00027186458,0.00042115647,0.0036103984,0.00043146635,0.0132703865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993685,0.00016501233,0.000042541986,0.00009548597,0.00030236298,0.00002615283],"domain_scores_gemma":[0.99801046,0.0014665878,0.00006329103,0.00026183116,0.0001745461,0.000023321982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012322242,0.0007219913,0.0007792647,0.0011122731,0.0002599298,0.0011036989,0.0015638407,0.0006810692,0.004705198],"category_scores_gemma":[0.003933305,0.000407563,0.0007933854,0.0020707469,0.0006847147,0.001644545,0.000645005,0.0016810001,0.0025788099],"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":[0.0000779342,0.000060234604,0.0006459497,0.00041386814,0.00005891097,0.00008843053,0.00017329748,0.08858887,0.006226489,0.1425712,0.02182119,0.73927367],"study_design_scores_gemma":[0.000011732857,0.000025349718,0.0004643696,0.0000724435,0.000026100535,0.00014947103,0.00004317914,0.6581197,0.0049970527,0.318903,0.017157124,0.000030525473],"about_ca_topic_score_codex":0.0015281376,"about_ca_topic_score_gemma":0.0017891744,"teacher_disagreement_score":0.004705198,"about_ca_system_score_codex":0.0008601299,"about_ca_system_score_gemma":0.0007270551,"threshold_uncertainty_score":0.015740454},"labels":[],"label_agreement":null},{"id":"W17603131","doi":"10.1123/jab.23.2.119","title":"Long spaced seeds for finding similarities between biological sequences.","year":2007,"lang":"en","type":"article","venue":"BIOCOMP","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Sensitivity (control systems); Homology (biology); Measure (data warehouse); Mathematics; Algorithm; Fraction (chemistry); Computer science; Biology; Data mining; Genetics; Gene","score_opus":0.07917843696535799,"score_gpt":0.31957608837918283,"score_spread":0.24039765141382485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W17603131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14718793,0.0031857106,0.8204731,0.0005413745,0.0014714759,0.00138463,0.005192058,0.009451803,0.011111983],"genre_scores_gemma":[0.31114843,0.000560414,0.67512774,0.0002398767,0.0002201523,0.0011104683,0.006465804,0.00058064004,0.0045464546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846846,0.00031797471,0.00017336146,0.00067969336,0.00029066633,0.0000699163],"domain_scores_gemma":[0.9955136,0.0021967315,0.000577063,0.00083246786,0.0006401302,0.00023993326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021390438,0.0008155237,0.0010656324,0.0041983705,0.0011239188,0.0010917744,0.0009653649,0.0012843662,0.008933035],"category_scores_gemma":[0.014931957,0.00037102203,0.0007033203,0.003535572,0.0009817012,0.0016531424,0.001141961,0.0010238205,0.006129952],"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":[0.0022420634,0.00045305438,0.024727616,0.0020874029,0.0005219729,0.0017729424,0.0014406884,0.015916003,0.17378162,0.031181235,0.014939514,0.73093593],"study_design_scores_gemma":[0.0006496643,0.0023276114,0.06303983,0.0011977667,0.0009436383,0.008189232,0.002248157,0.48412645,0.13705048,0.13105236,0.16892557,0.00024933278],"about_ca_topic_score_codex":0.0010039571,"about_ca_topic_score_gemma":0.0021275664,"teacher_disagreement_score":0.008933035,"about_ca_system_score_codex":0.0005381282,"about_ca_system_score_gemma":0.0012414703,"threshold_uncertainty_score":0.02988398},"labels":[],"label_agreement":null},{"id":"W1764008429","doi":"10.37236/161","title":"Counting Abelian Squares","year":2009,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Abelian group; Combinatorics; Permutation (music); Concatenation (mathematics); Discrete mathematics; String (physics)","score_opus":0.005164885710695032,"score_gpt":0.22530736828466943,"score_spread":0.2201424825739744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1764008429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24563882,0.00353414,0.62106484,0.0029680969,0.00089779886,0.000273102,0.0013516442,0.0015957579,0.1226758],"genre_scores_gemma":[0.7513624,0.0023295437,0.19830696,0.0011547969,0.0013436438,0.00078737544,0.0022967588,0.0011418434,0.041276745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951349,0.0012086593,0.00027131508,0.00090965664,0.001931876,0.00054358895],"domain_scores_gemma":[0.9839236,0.009967291,0.00096030673,0.0024275067,0.0020692125,0.0006521606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017596595,0.0008424195,0.0014243103,0.0036290952,0.0018481622,0.0037106974,0.0028203789,0.0015088732,0.015535608],"category_scores_gemma":[0.027259834,0.000707926,0.0007875504,0.0033194497,0.0031500778,0.012643317,0.003991586,0.0019292339,0.0031427613],"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":[0.00033506923,0.00010460384,0.0052645844,0.00046800092,0.00005271642,0.00046685437,0.00049165473,0.010416965,0.008495782,0.8626038,0.016837297,0.094462745],"study_design_scores_gemma":[0.00003346589,0.000072697665,0.0013013369,0.00009960968,0.000044971523,0.0016687084,0.00019020878,0.08032284,0.008274298,0.8890015,0.01893906,0.000051313065],"about_ca_topic_score_codex":0.00059012516,"about_ca_topic_score_gemma":0.00065236347,"teacher_disagreement_score":0.015535608,"about_ca_system_score_codex":0.0011748082,"about_ca_system_score_gemma":0.00086997193,"threshold_uncertainty_score":0.051971853},"labels":[],"label_agreement":null},{"id":"W1765644073","doi":"10.1007/978-3-540-69903-3_17","title":"A Uniform Approach Towards Succinct Representation of Trees","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Representation (politics); Binary tree; Theoretical computer science; Entropy (arrow of time); Set (abstract data type); Algorithm; Mathematics; Discrete mathematics","score_opus":0.02773717381977151,"score_gpt":0.2614565415251866,"score_spread":0.2337193677054151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1765644073","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011513042,0.00036606647,0.99409074,0.00019932585,0.000115484676,0.00005763822,0.00021581922,0.00064412,0.00315954],"genre_scores_gemma":[0.03540614,0.0016244671,0.9501581,0.0004890595,0.00029847692,0.00035691375,0.0015981981,0.00081937213,0.009249158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664426,0.0006834582,0.00046631473,0.000551699,0.0014574867,0.00019689152],"domain_scores_gemma":[0.9944819,0.0012309294,0.00017080858,0.0030198195,0.0009349256,0.00016166804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017860791,0.0012214821,0.0013485015,0.0025484688,0.0009349599,0.0047877044,0.0045679067,0.0018647885,0.011439754],"category_scores_gemma":[0.009306332,0.0011213163,0.001793441,0.004698448,0.002005194,0.011152487,0.006466136,0.005786037,0.005196704],"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":[0.00010979869,0.00007572219,0.00013663182,0.0003946502,0.00003395885,0.0001252364,0.0003072683,0.014039308,0.009153505,0.7328016,0.013044358,0.22977792],"study_design_scores_gemma":[0.000035891087,0.00007114281,0.00009903819,0.00019574267,0.000056141256,0.0004222338,0.000098991346,0.09273753,0.013127975,0.8320723,0.06103357,0.00004946078],"about_ca_topic_score_codex":0.00080296263,"about_ca_topic_score_gemma":0.0012072341,"teacher_disagreement_score":0.011439754,"about_ca_system_score_codex":0.0010619962,"about_ca_system_score_gemma":0.0011487511,"threshold_uncertainty_score":0.03826976},"labels":[],"label_agreement":null},{"id":"W1765826407","doi":"10.1007/11780441_13","title":"Common Substrings in Random Strings","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Substring; Bernoulli's principle; Computer science; Word (group theory); Set (abstract data type); Algorithm; Bernoulli distribution; Markov chain; Theoretical computer science; Discrete mathematics; Random variable; Mathematics; Machine learning; Statistics","score_opus":0.011593716415367827,"score_gpt":0.23181203703787936,"score_spread":0.22021832062251154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1765826407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17227864,0.0064360425,0.74497354,0.0014988298,0.00089676585,0.00022520375,0.00086458074,0.0015457082,0.07128068],"genre_scores_gemma":[0.72030336,0.0040448876,0.21262042,0.0006345839,0.0011252952,0.0003344159,0.0022724564,0.00091565977,0.057748996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765944,0.0004708478,0.00021410185,0.00048218053,0.0009805817,0.00019292068],"domain_scores_gemma":[0.99010414,0.0064466908,0.00064186275,0.0018027676,0.0007290233,0.00027543784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012910351,0.00057097897,0.0011290358,0.004047097,0.0012393107,0.00248288,0.001386623,0.0017694666,0.007897131],"category_scores_gemma":[0.012801361,0.0007579604,0.00094005,0.0055501275,0.0022681355,0.006568757,0.002556321,0.0017184732,0.0023129894],"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":[0.00024022147,0.00005178741,0.0010713934,0.0003417627,0.00004248552,0.00078636647,0.0005991836,0.0100766225,0.005000645,0.8286694,0.0060733366,0.14704686],"study_design_scores_gemma":[0.000022381044,0.00005817382,0.00054684834,0.00009943701,0.000035638488,0.0013200655,0.00013530851,0.041445136,0.0040839706,0.93905675,0.013167513,0.00002871205],"about_ca_topic_score_codex":0.00044360608,"about_ca_topic_score_gemma":0.0005898325,"teacher_disagreement_score":0.007897131,"about_ca_system_score_codex":0.00087061257,"about_ca_system_score_gemma":0.00065362273,"threshold_uncertainty_score":0.026418567},"labels":[],"label_agreement":null},{"id":"W1783789643","doi":"10.1007/3-540-45071-8_8","title":"A Space Efficient Algorithm for Sequence Alignment with Inversions","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Substring; Shuffling; Algorithm; Computation; Sequence (biology); Computer science; Smith–Waterman algorithm; Dynamic programming; Space (punctuation); Pairwise comparison; Multiple sequence alignment; Longest common subsequence problem; Sequence alignment; Combinatorics; Mathematics; Data structure; Genetics; Biology; Gene; Artificial intelligence","score_opus":0.019360991256674173,"score_gpt":0.24537314774323155,"score_spread":0.22601215648655737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1783789643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018036672,0.00021942852,0.99302,0.00006503793,0.000091919406,0.00006259446,0.00011214186,0.0036838013,0.0009414149],"genre_scores_gemma":[0.012489472,0.0001600463,0.9840103,0.00006207992,0.000049348877,0.00016494398,0.00055186095,0.00046575617,0.002046228],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830604,0.00036974766,0.00014830548,0.00037922958,0.0006243161,0.0001723706],"domain_scores_gemma":[0.9982545,0.000691833,0.00010754883,0.00048790165,0.00040479802,0.00005331573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012968767,0.0027110016,0.0020336767,0.0025717805,0.0016793517,0.0020340735,0.0026191678,0.0018129953,0.010609985],"category_scores_gemma":[0.0047713714,0.0010663458,0.0015665076,0.004834246,0.0010221165,0.0031334546,0.0032094808,0.002925605,0.009289952],"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":[0.00037392313,0.00016620534,0.00029601797,0.00026941946,0.00009679686,0.00016886552,0.00025090968,0.024240864,0.02805138,0.03822918,0.018972825,0.88888353],"study_design_scores_gemma":[0.00037715814,0.0005391953,0.00062914693,0.0001295206,0.00017234952,0.0012712748,0.0003322811,0.6321723,0.072222434,0.20385067,0.08811441,0.00018921275],"about_ca_topic_score_codex":0.0021757756,"about_ca_topic_score_gemma":0.0033264202,"teacher_disagreement_score":0.010609985,"about_ca_system_score_codex":0.0007649678,"about_ca_system_score_gemma":0.0017843344,"threshold_uncertainty_score":0.03549391},"labels":[],"label_agreement":null},{"id":"W1791987072","doi":"10.1002/spe.2203","title":"Decoding billions of integers per second through vectorization","year":2013,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Vectorization (mathematics); Scheme (mathematics); Encoding (memory); Data compression; Compression (physics)","score_opus":0.015749185143385063,"score_gpt":0.2803758415423402,"score_spread":0.2646266563989551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1791987072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04711363,0.001695903,0.9232878,0.00050044147,0.00036267596,0.00023797588,0.00054617255,0.015060417,0.011194994],"genre_scores_gemma":[0.24234438,0.0014741538,0.7368845,0.00030504697,0.00014499358,0.00036295006,0.0024235968,0.0010797484,0.0149806645],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992919,0.000095358904,0.00008126787,0.000094610405,0.0003772395,0.0000596152],"domain_scores_gemma":[0.9991148,0.00023813495,0.00007586155,0.0002796312,0.0002696565,0.00002194504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060075906,0.001046308,0.00047065073,0.0013347142,0.00038493334,0.0011296539,0.0009398051,0.00048141126,0.006816084],"category_scores_gemma":[0.002896723,0.00032019475,0.00033062676,0.0019147379,0.0005864769,0.0018705176,0.0013609313,0.0007055185,0.0037153456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055670127,0.00007000194,0.00071154744,0.000225372,0.000033719974,0.00014376263,0.00027052764,0.012281669,0.067647785,0.02612046,0.012913515,0.87902486],"study_design_scores_gemma":[0.00023911663,0.0006060284,0.0012809266,0.0001703044,0.00006834355,0.0010419338,0.00033869685,0.4025892,0.36989498,0.053014714,0.17062886,0.00012687186],"about_ca_topic_score_codex":0.0014031811,"about_ca_topic_score_gemma":0.0015119826,"teacher_disagreement_score":0.006816084,"about_ca_system_score_codex":0.0004706003,"about_ca_system_score_gemma":0.0008847202,"threshold_uncertainty_score":0.022802114},"labels":[],"label_agreement":null},{"id":"W1792817236","doi":"10.3233/fun-2006-71406","title":"On Problems in Polymorphic Object-Oriented Languages With Self Types and Matching","year":2006,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Programming language; Object (grammar); Matching (statistics); Object-oriented programming; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.004100339476644207,"score_gpt":0.20584280747812744,"score_spread":0.20174246800148324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1792817236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024916843,0.012526739,0.9196927,0.021579426,0.0006554174,0.00020992747,0.00012119478,0.00072692876,0.019570846],"genre_scores_gemma":[0.36262634,0.02050577,0.57092834,0.00794048,0.0055832486,0.0010076036,0.00052983797,0.0017690664,0.029109392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9750249,0.011133152,0.0022755943,0.003198793,0.0071425824,0.001225042],"domain_scores_gemma":[0.92755616,0.059029624,0.0031294075,0.006489319,0.0030753717,0.00072014827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023902964,0.0014179156,0.0024531272,0.003359328,0.0049480726,0.0090863295,0.004050064,0.009101876,0.005160441],"category_scores_gemma":[0.06331109,0.002123711,0.0030476637,0.008786602,0.015309034,0.042015463,0.009892276,0.009503907,0.0013502763],"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":[0.00005620234,0.000051970834,0.00044904472,0.00022875915,0.000024206975,0.00035913213,0.0012040767,0.005116057,0.0002918336,0.95395404,0.0037338957,0.03453085],"study_design_scores_gemma":[0.000020313484,0.000020426272,0.00013219578,0.0000977467,0.000014491236,0.0005657199,0.00023436545,0.011602241,0.00047099288,0.97573674,0.011072181,0.00003241405],"about_ca_topic_score_codex":0.002940761,"about_ca_topic_score_gemma":0.0013225306,"teacher_disagreement_score":0.023902964,"about_ca_system_score_codex":0.0040063867,"about_ca_system_score_gemma":0.0025400973,"threshold_uncertainty_score":0.12641251},"labels":[],"label_agreement":null},{"id":"W1794091211","doi":"","title":"A comparison of evolutionary algorithms for finding optimal error-correcting codes","year":2007,"lang":"en","type":"article","venue":"Computational intelligence","topic":"Algorithms and Data Compression","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":"Brock University; Simon Fraser University","funders":"","keywords":"Upper and lower bounds; Algorithm; Simulated annealing; Evolutionary algorithm; Mathematics; Hill climbing; Combinatorics; Coding (social sciences); Mathematical optimization; Computer science; Discrete mathematics; Statistics","score_opus":0.1125179554015422,"score_gpt":0.413086665582463,"score_spread":0.3005687101809208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794091211","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43387508,0.01300798,0.5306323,0.0013849136,0.00029267694,0.0002928175,0.00022307833,0.0012394334,0.019051628],"genre_scores_gemma":[0.5765702,0.0035346039,0.41683012,0.00025767065,0.00007412208,0.0002906621,0.00033291598,0.00015387347,0.0019558023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979037,0.0008135689,0.000133889,0.00019980456,0.00080585235,0.00014313706],"domain_scores_gemma":[0.99218315,0.005934021,0.0002830137,0.0005050922,0.0009783072,0.000116385105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033373178,0.00084784813,0.0012609817,0.002950863,0.0006908752,0.0008820091,0.0015000234,0.0022955418,0.0009460115],"category_scores_gemma":[0.01514255,0.0004027099,0.0008049012,0.0023967924,0.00092998863,0.0013258706,0.00074316905,0.00079111534,0.00018877478],"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":[0.00034285808,0.0001572342,0.0024840038,0.00019535185,0.00015452261,0.00004668353,0.0001466378,0.80428797,0.0015088669,0.015471876,0.00082185824,0.1743821],"study_design_scores_gemma":[0.000079152116,0.00016906166,0.0009247582,0.000040810595,0.000036651625,0.00007897921,0.00006687369,0.9907698,0.0015209805,0.005168329,0.0011249267,0.000019715637],"about_ca_topic_score_codex":0.0044760355,"about_ca_topic_score_gemma":0.003981175,"teacher_disagreement_score":0.0044760355,"about_ca_system_score_codex":0.0015319488,"about_ca_system_score_gemma":0.001498418,"threshold_uncertainty_score":0.01764965},"labels":[],"label_agreement":null},{"id":"W179872536","doi":"10.1007/978-3-319-02432-5_12","title":"Document Listing on Versioned Documents","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Substring; Listing (finance); Information retrieval; Index (typography); Ranking (information retrieval); Phrase; Space (punctuation); World Wide Web; Data structure; Natural language processing; Programming language","score_opus":0.01457403965835758,"score_gpt":0.2497860624078519,"score_spread":0.23521202274949432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W179872536","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013779344,0.0072529707,0.04093955,0.0025122794,0.015883747,0.0013316923,0.0874171,0.024825132,0.8184596],"genre_scores_gemma":[0.0027002045,0.005391524,0.013933417,0.0005321964,0.0012047616,0.00035836585,0.06215421,0.007948845,0.9057765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988418,0.00011254885,0.00014307459,0.00017773839,0.0006377132,0.00008703514],"domain_scores_gemma":[0.9948249,0.0008139428,0.0002559727,0.0011248909,0.0026257774,0.00035467185],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011969074,0.0016647356,0.0018222566,0.008365385,0.0010441522,0.008012153,0.002256431,0.001670084,0.7433828],"category_scores_gemma":[0.007964172,0.0011131497,0.0009402587,0.011057425,0.0004721462,0.0053939456,0.0015077731,0.0022679274,0.6681035],"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":[0.000036833582,0.000060801216,0.00004989162,0.0005502199,0.000008079028,0.000053807587,0.00002007177,0.00028896084,0.0013229095,0.0040533836,0.84721744,0.14633758],"study_design_scores_gemma":[0.000015149215,0.00002569802,0.00016877872,0.0002088108,0.000008284572,0.0001433315,0.000014266851,0.00026101898,0.0007851941,0.0017847704,0.99656796,0.000016682916],"about_ca_topic_score_codex":0.0022055905,"about_ca_topic_score_gemma":0.0020137872,"teacher_disagreement_score":0.7433828,"about_ca_system_score_codex":0.0011719364,"about_ca_system_score_gemma":0.0020765471,"threshold_uncertainty_score":0.36603326},"labels":[],"label_agreement":null},{"id":"W1801211801","doi":"","title":"Fast Data Compression with Antidictionaries","year":2004,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"Western University","funders":"","keywords":"Compression (physics); Computer science; Data compression; De Bruijn sequence; Algorithm; Overhead (engineering); Quadratic equation; Data compression ratio; Compressibility; Upper and lower bounds; Theoretical computer science; Mathematics; Discrete mathematics; Image compression; Artificial intelligence; Geometry; Mathematical analysis; Physics","score_opus":0.026892456964286292,"score_gpt":0.2527401879142297,"score_spread":0.2258477309499434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1801211801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035489,0.0012459102,0.9511959,0.0011903789,0.00032022258,0.00016239328,0.0005793496,0.003670239,0.0061466433],"genre_scores_gemma":[0.23201239,0.0007904535,0.7557002,0.0006346066,0.000301768,0.0003914731,0.0016766137,0.00086939824,0.007623109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792516,0.00037573223,0.00022069903,0.00050079165,0.0007631793,0.0002145037],"domain_scores_gemma":[0.99355304,0.0031819306,0.00031463645,0.0021300912,0.000734865,0.00008554479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011735874,0.0009805388,0.00090574555,0.0017017866,0.0010298893,0.0018975837,0.0019227646,0.0015583697,0.007092694],"category_scores_gemma":[0.008102007,0.0005494109,0.00083373307,0.002572157,0.0020141285,0.0061658965,0.0038125848,0.0024257426,0.0027827993],"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":[0.0011401381,0.00021211502,0.0015878404,0.0006875607,0.00008301578,0.00044504294,0.0006413308,0.041270442,0.057654828,0.18870598,0.014198138,0.6933736],"study_design_scores_gemma":[0.00018315043,0.00039811613,0.0008599456,0.00014949132,0.00006919587,0.0013694539,0.0002854786,0.49023917,0.16864452,0.29919386,0.03847718,0.00013048553],"about_ca_topic_score_codex":0.0009617071,"about_ca_topic_score_gemma":0.001376119,"teacher_disagreement_score":0.007092694,"about_ca_system_score_codex":0.0006999079,"about_ca_system_score_gemma":0.0008956476,"threshold_uncertainty_score":0.023727417},"labels":[],"label_agreement":null},{"id":"W1820209741","doi":"10.1007/978-3-642-20662-7_12","title":"Compressed String Dictionaries","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; String (physics); Search engine indexing; Theoretical computer science; Set (abstract data type); RDF; Space (punctuation); Information retrieval; Programming language; Mathematics; Semantic Web","score_opus":0.023098639261622336,"score_gpt":0.23298247406148845,"score_spread":0.2098838347998661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1820209741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020476317,0.005394819,0.8282157,0.0018877694,0.0040077018,0.00048488774,0.014201593,0.018407734,0.10692347],"genre_scores_gemma":[0.10179417,0.006507905,0.58964115,0.0014779173,0.0017809226,0.0006330342,0.05767567,0.0047017233,0.23578754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934214,0.00008144467,0.000067061424,0.00012364845,0.00033524702,0.000050448423],"domain_scores_gemma":[0.99870515,0.00029888074,0.000051082316,0.00055796176,0.00034073865,0.000046138684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003775866,0.0009307722,0.0008992459,0.0019904738,0.00059648056,0.0016837191,0.001286961,0.0010299428,0.06388634],"category_scores_gemma":[0.0026769014,0.0005448044,0.00048704608,0.0036495898,0.0006667525,0.002564769,0.0022056513,0.0016810106,0.04044203],"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":[0.00034531383,0.00009155073,0.00015285698,0.0004586674,0.000035044963,0.00023513731,0.00009132366,0.0059501994,0.023475362,0.056913756,0.08890474,0.823346],"study_design_scores_gemma":[0.00013129087,0.00029442372,0.0008910053,0.00041646592,0.00008591137,0.0023659226,0.00019456935,0.09486602,0.14576674,0.103505425,0.65136236,0.000119805445],"about_ca_topic_score_codex":0.00051763497,"about_ca_topic_score_gemma":0.00070558407,"teacher_disagreement_score":0.06388634,"about_ca_system_score_codex":0.0003643319,"about_ca_system_score_gemma":0.00072510244,"threshold_uncertainty_score":0.2137211},"labels":[],"label_agreement":null},{"id":"W1822932347","doi":"10.1007/3-540-44634-6_35","title":"Computing Phylogenetic Roots with Bounded Degrees and Errors","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"","keywords":"Phylogenetic tree; Combinatorics; Similarity (geometry); Phylogenetics; Mathematics; Tree (set theory); Bounded function; Vertex (graph theory); Graph; Phylogenetic network; Biology; Computer science; Artificial intelligence; Genetics; Image (mathematics)","score_opus":0.015868047004678792,"score_gpt":0.2381215292257102,"score_spread":0.22225348222103142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1822932347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09695104,0.0014366509,0.885581,0.0011142413,0.00025256013,0.00005080024,0.0005789734,0.0021712382,0.011863481],"genre_scores_gemma":[0.53889793,0.0009222093,0.4440031,0.0003200148,0.00032580693,0.00008022504,0.0013279358,0.0010919042,0.013030878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976259,0.00048856495,0.0001677409,0.0006317003,0.0008100231,0.00027616217],"domain_scores_gemma":[0.9814169,0.013013022,0.00082435884,0.0030938953,0.0012449037,0.0004069609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021439458,0.0010806086,0.0015780877,0.0018178868,0.0010800987,0.0028557682,0.002623132,0.0018725671,0.008836344],"category_scores_gemma":[0.026743852,0.00089788804,0.0007931696,0.002655527,0.003056593,0.010461659,0.0044664713,0.0027916566,0.0024233023],"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":[0.0007676064,0.000101352314,0.0038709778,0.0006842845,0.000097350014,0.000264863,0.0009149196,0.14224625,0.0092528565,0.5181604,0.011214438,0.31242475],"study_design_scores_gemma":[0.000041298234,0.000045844383,0.00035541508,0.000071584735,0.000030378833,0.0001450424,0.00014697819,0.122070596,0.0058910456,0.8658402,0.005337428,0.000024156217],"about_ca_topic_score_codex":0.00094713207,"about_ca_topic_score_gemma":0.002074867,"teacher_disagreement_score":0.008836344,"about_ca_system_score_codex":0.0012671454,"about_ca_system_score_gemma":0.0008432211,"threshold_uncertainty_score":0.029560566},"labels":[],"label_agreement":null},{"id":"W1823694584","doi":"10.1007/978-3-540-27836-8_84","title":"Succinct Representations of Functions","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.016982082124449977,"score_gpt":0.26036718963422534,"score_spread":0.24338510750977535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1823694584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00926976,0.0012918347,0.9375557,0.00074756605,0.00039748944,0.00010531895,0.0020101701,0.002616205,0.046005838],"genre_scores_gemma":[0.25464666,0.003935194,0.643475,0.0009475694,0.0005246928,0.0007307338,0.010642681,0.0023022874,0.08279523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882346,0.0002552845,0.000117998075,0.00017469712,0.00051851664,0.000109963126],"domain_scores_gemma":[0.99858046,0.00047520828,0.00007529187,0.0005991448,0.00022416541,0.000045861914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072056364,0.0013852498,0.00084976165,0.0016363919,0.0006421696,0.0039377855,0.0015709851,0.0013491735,0.022171643],"category_scores_gemma":[0.004013254,0.00070197304,0.0008406097,0.0026135163,0.0013179673,0.006895353,0.002261413,0.0031232925,0.008524121],"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":[0.00009277985,0.000033743672,0.00009841115,0.00018704723,0.0000104270075,0.00009023956,0.00025116032,0.007955784,0.002204997,0.82591844,0.015857933,0.14729895],"study_design_scores_gemma":[0.000021683929,0.000035791556,0.00009620391,0.0001282031,0.000019307176,0.0002262428,0.000072753486,0.027941966,0.0037260088,0.89226294,0.075443685,0.000025364285],"about_ca_topic_score_codex":0.00052586844,"about_ca_topic_score_gemma":0.0009104789,"teacher_disagreement_score":0.022171643,"about_ca_system_score_codex":0.00087496446,"about_ca_system_score_gemma":0.0006834323,"threshold_uncertainty_score":0.07417154},"labels":[],"label_agreement":null},{"id":"W1826207841","doi":"10.1007/978-3-540-85654-2_68","title":"Hierarchy Encoding with Multiple Genes","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Encoding (memory); Hierarchy; Computer science; Inheritance (genetic algorithm); Set (abstract data type); Theoretical computer science; Multiple inheritance; Simple (philosophy); Algorithm; Artificial intelligence; Gene; Genetics; Programming language; Biology","score_opus":0.01912843602434203,"score_gpt":0.23069644965088018,"score_spread":0.21156801362653815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826207841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050503727,0.0012144498,0.87316567,0.0014885839,0.0008371376,0.00017113432,0.002019336,0.006278272,0.06432163],"genre_scores_gemma":[0.31090555,0.0008310172,0.6396853,0.0006966726,0.00019795905,0.00022358912,0.0039639524,0.0013963402,0.0420997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997546,0.000046452653,0.000016356691,0.00006248063,0.00006937901,0.000050796974],"domain_scores_gemma":[0.9994954,0.00015357115,0.000021859722,0.00017834963,0.00010389448,0.00004691586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026953054,0.0003958292,0.0005762922,0.00067464076,0.0007174043,0.00097387214,0.00091138453,0.0006368394,0.0123127205],"category_scores_gemma":[0.0012050483,0.00026996285,0.0005622079,0.0010855937,0.00060682825,0.001510755,0.0011892216,0.0012623065,0.0026718762],"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":[0.00039958282,0.00012503407,0.0004936905,0.00036112865,0.000037149628,0.00038548117,0.0003593393,0.023412243,0.047011122,0.33190775,0.03611674,0.55939084],"study_design_scores_gemma":[0.00011494926,0.00023944942,0.0006358471,0.00022923264,0.00012062869,0.00049153133,0.00023427048,0.21238773,0.05179081,0.58315104,0.15052001,0.000084549094],"about_ca_topic_score_codex":0.001502287,"about_ca_topic_score_gemma":0.0032590928,"teacher_disagreement_score":0.0123127205,"about_ca_system_score_codex":0.00087556697,"about_ca_system_score_gemma":0.0007916089,"threshold_uncertainty_score":0.041190147},"labels":[],"label_agreement":null},{"id":"W1830327897","doi":"10.1007/978-3-642-10217-2_18","title":"LPF Computation Revisited","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Suffix array; Computation; Table (database); Suffix; Algorithm; Permutation (music); Computer science; Position (finance); Mathematics; Data structure; Data mining; Physics","score_opus":0.015785971753027674,"score_gpt":0.2574532700920008,"score_spread":0.24166729833897313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1830327897","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014853704,0.008447359,0.51847816,0.012340076,0.0035243514,0.000043195505,0.0004497136,0.000772319,0.4410911],"genre_scores_gemma":[0.49950293,0.009635827,0.20152946,0.0039218003,0.0064295074,0.00021071521,0.0012453587,0.0015170106,0.27600738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993124,0.00012779472,0.000031285264,0.00016038238,0.00028278478,0.00008527736],"domain_scores_gemma":[0.9989894,0.00045470698,0.000029300149,0.00030345123,0.00017624356,0.0000468664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006324686,0.0006725698,0.0010459078,0.001535635,0.0017303786,0.003521333,0.001819646,0.0014662322,0.025595782],"category_scores_gemma":[0.0047411076,0.00041881643,0.0008097061,0.0023808097,0.0027826724,0.0074708303,0.0023111415,0.003918667,0.005201592],"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":[0.000013918407,0.000006078681,0.00003996658,0.00003960756,0.0000033909898,0.00002687906,0.000053092896,0.0010165783,0.0001858072,0.96273154,0.009119214,0.02676399],"study_design_scores_gemma":[0.0000045499196,0.0000045677316,0.000057539604,0.00002828931,0.000003942546,0.00007835102,0.000031530846,0.008480277,0.00050349114,0.956559,0.034239408,0.000009107779],"about_ca_topic_score_codex":0.0020114724,"about_ca_topic_score_gemma":0.0015787926,"teacher_disagreement_score":0.025595782,"about_ca_system_score_codex":0.0013472865,"about_ca_system_score_gemma":0.00076227356,"threshold_uncertainty_score":0.08562642},"labels":[],"label_agreement":null},{"id":"W1842176639","doi":"10.1007/978-3-642-16321-0_35","title":"Succinct Representations of Dynamic Strings","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"String (physics); Word (group theory); Alphabet; Rank (graph theory); Omega; Combinatorics; Space (punctuation); Sigma; Computer science; Mathematics; Discrete mathematics; Physics; Geometry; Mathematical physics; Quantum mechanics","score_opus":0.010552717314922765,"score_gpt":0.26190641631291556,"score_spread":0.2513536989979928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842176639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019787824,0.0016662541,0.93776214,0.00083887816,0.00055310153,0.00013688604,0.003496918,0.0038083747,0.03194966],"genre_scores_gemma":[0.347481,0.004648323,0.5674546,0.0007476293,0.00055961113,0.00069904374,0.016758366,0.0025614304,0.059089936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989994,0.00019098893,0.00010691237,0.00014578193,0.0004530027,0.00010389513],"domain_scores_gemma":[0.9976192,0.0009395079,0.00015393138,0.0008867818,0.00033679404,0.000063787054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006166353,0.0009876,0.000752575,0.0016150174,0.0005290045,0.0026937285,0.001576047,0.0012901722,0.020000651],"category_scores_gemma":[0.0050807837,0.0006014386,0.0005702676,0.0031483308,0.0010700276,0.0063984655,0.0023049673,0.0020571689,0.005714839],"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":[0.00031849628,0.00008076189,0.00020658979,0.00042942274,0.000021011996,0.0003118894,0.00036993652,0.03176983,0.009450451,0.58728594,0.027016861,0.34273878],"study_design_scores_gemma":[0.000057534235,0.00009845177,0.0001728766,0.00030011308,0.00003297086,0.0006073376,0.00019218688,0.1205031,0.0180075,0.761883,0.098086916,0.000057897792],"about_ca_topic_score_codex":0.00045375584,"about_ca_topic_score_gemma":0.0007292065,"teacher_disagreement_score":0.020000651,"about_ca_system_score_codex":0.0006397945,"about_ca_system_score_gemma":0.00065082643,"threshold_uncertainty_score":0.066908896},"labels":[],"label_agreement":null},{"id":"W1844862792","doi":"10.1007/978-1-4613-0165-3_13","title":"Iterative Decoding of Tail-Biting Trellises and Connections with Symbolic Dynamics","year":2001,"lang":"en","type":"book-chapter","venue":"˜The œIMA volumes in mathematics and its applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Symbolic dynamics; Mathematics; Algorithm; Decoding methods; Product (mathematics); Berlekamp–Welch algorithm; Combinatorics; Limiting; Function (biology); Discrete mathematics; Maximum a posteriori estimation; Convergence (economics); Statistics; Maximum likelihood; Sequential decoding; Pure mathematics","score_opus":0.015364283632754059,"score_gpt":0.2408508710526786,"score_spread":0.22548658741992456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844862792","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03889496,0.003468285,0.8918221,0.00091544614,0.0002826975,0.00007035777,0.00020002198,0.00038005898,0.063966155],"genre_scores_gemma":[0.7496459,0.005837699,0.17923057,0.00062263827,0.0007040665,0.00027803064,0.00049179734,0.00064339186,0.06254581],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99901927,0.00034095277,0.00006549128,0.00012765956,0.0003235183,0.00012302824],"domain_scores_gemma":[0.9974058,0.0017100865,0.00017801955,0.00033509976,0.00030991013,0.00006111601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082692323,0.0007601,0.0008075632,0.0014226178,0.0009422397,0.002094778,0.0014133333,0.001634272,0.0048590587],"category_scores_gemma":[0.008280415,0.0006463779,0.0006866611,0.0021081083,0.0028746703,0.003219819,0.0018675722,0.0021832702,0.0015990776],"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":[0.000030363462,0.000012905382,0.00010726139,0.00006806281,0.000008724511,0.00005985924,0.00023084451,0.0388566,0.0020146498,0.9330398,0.0013775947,0.02419339],"study_design_scores_gemma":[0.000007977141,0.000018417011,0.0000538598,0.000034636712,0.0000040850045,0.00007737769,0.000024681847,0.09311644,0.0018415326,0.90203285,0.0027651507,0.000023017576],"about_ca_topic_score_codex":0.0013918251,"about_ca_topic_score_gemma":0.0011735874,"teacher_disagreement_score":0.0048590587,"about_ca_system_score_codex":0.0013717839,"about_ca_system_score_gemma":0.0008550871,"threshold_uncertainty_score":0.0162552},"labels":[],"label_agreement":null},{"id":"W1848498137","doi":"10.1002/cpe.1826","title":"Tsunami: massively parallel homomorphic hashing on many‐core GPUs","year":2011,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Algorithms and Data Compression","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 Calgary; University of Alberta","funders":"Hong Kong Baptist University; Nvidia","keywords":"Computer science; Homomorphic encryption; Massively parallel; Parallel computing; Multi-core processor; Hash function; Core (optical fiber); Computer security; Encryption; Telecommunications","score_opus":0.07882458477301257,"score_gpt":0.3203773420037976,"score_spread":0.241552757230785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1848498137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29354128,0.00075564143,0.6728119,0.0007424138,0.00037018172,0.00017753331,0.0002034692,0.009894387,0.021503193],"genre_scores_gemma":[0.7524513,0.00016257641,0.24188729,0.00011076138,0.00005188787,0.000081677485,0.0002440538,0.00023309905,0.004777316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970466,0.000065974295,0.000016297128,0.000036398764,0.00012613379,0.000050542683],"domain_scores_gemma":[0.9995561,0.00008928589,0.000036762493,0.00018205862,0.0000909229,0.000044740398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036992872,0.00033882758,0.0003316474,0.00030315024,0.00040180495,0.0006071982,0.0009030729,0.00032665214,0.0030666967],"category_scores_gemma":[0.0009622542,0.00019690227,0.0003076888,0.00044605057,0.0005678155,0.0007201284,0.0012375908,0.0005158097,0.0006215163],"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":[0.0012303246,0.0002014796,0.0049531516,0.00029631093,0.00017734026,0.00080464967,0.0004671162,0.4346371,0.09476749,0.096294895,0.036210507,0.3299597],"study_design_scores_gemma":[0.00010921364,0.0001266788,0.0006546756,0.000011246536,0.000012207429,0.00014102246,0.000047827347,0.94203925,0.028223028,0.017176107,0.011437275,0.000021495744],"about_ca_topic_score_codex":0.002234137,"about_ca_topic_score_gemma":0.002744385,"teacher_disagreement_score":0.0030666967,"about_ca_system_score_codex":0.00045895032,"about_ca_system_score_gemma":0.0006844074,"threshold_uncertainty_score":0.010259092},"labels":[],"label_agreement":null},{"id":"W1854930219","doi":"10.46298/dmtcs.3536","title":"The Height of List-tries and TST","year":2007,"lang":"en","type":"article","venue":"Discrete Mathematics & Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"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":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Mathematics; Combinatorics; Tree (set theory); Core (optical fiber); Ternary operation; Discrete mathematics; Computer science","score_opus":0.008907837914097917,"score_gpt":0.257480629632985,"score_spread":0.2485727917188871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1854930219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6338466,0.0064047333,0.26573625,0.0056266063,0.00042936322,0.00009741364,0.0017151099,0.0018020412,0.08434193],"genre_scores_gemma":[0.9704752,0.0017769948,0.018264195,0.00052185013,0.0005333888,0.00014001601,0.000742103,0.00041482737,0.0071312985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860173,0.00021540334,0.000048695158,0.00020196867,0.0005192942,0.00041291962],"domain_scores_gemma":[0.982777,0.011734104,0.0014196235,0.0014004889,0.0013191573,0.0013496052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018716092,0.00055438187,0.0007816408,0.0028137912,0.0014797907,0.0036631708,0.0019200048,0.001309988,0.009885501],"category_scores_gemma":[0.02563597,0.0006908255,0.0007065201,0.002551127,0.0039667273,0.0068171397,0.0036231258,0.0034249364,0.0016254823],"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":[0.00018834768,0.000040111598,0.00355917,0.00020630095,0.00002992165,0.00019401891,0.00060935476,0.016373876,0.0031452563,0.94865286,0.005469359,0.021531306],"study_design_scores_gemma":[0.000043448206,0.00007831604,0.0025290626,0.00009410122,0.000042409887,0.0005062811,0.0003250335,0.09134198,0.0031109203,0.89751446,0.0043648053,0.00004916378],"about_ca_topic_score_codex":0.0013325631,"about_ca_topic_score_gemma":0.0014434418,"teacher_disagreement_score":0.009885501,"about_ca_system_score_codex":0.0021085176,"about_ca_system_score_gemma":0.0013723426,"threshold_uncertainty_score":0.033070266},"labels":[],"label_agreement":null},{"id":"W1891841982","doi":"10.1007/978-3-642-27848-8_340-2","title":"Regular Expression Matching","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Matching (statistics); Expression (computer science); Computer science; Computational biology; Mathematics; Biology; Programming language; Statistics","score_opus":0.009862854529614681,"score_gpt":0.22153672295557092,"score_spread":0.21167386842595623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891841982","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005039811,0.0055754026,0.67338365,0.00140462,0.0010660319,0.00030519062,0.0033887892,0.010263374,0.2995732],"genre_scores_gemma":[0.057146575,0.008099866,0.46348056,0.0012270801,0.0004934938,0.00033478034,0.017910214,0.004932409,0.446375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895155,0.000110712484,0.00008631215,0.0002882287,0.00048772508,0.000075322794],"domain_scores_gemma":[0.9995158,0.00012311956,0.000022891654,0.00019278738,0.0001250156,0.000020501267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006473816,0.0009034162,0.00093601836,0.0019005183,0.000736744,0.0022055337,0.0017418973,0.0008847555,0.06694527],"category_scores_gemma":[0.0023651402,0.000567992,0.0009142086,0.0033530246,0.0007329083,0.004100387,0.0019502976,0.0014376417,0.049242757],"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":[0.000055183322,0.00007995763,0.00013490979,0.00029353233,0.000022064241,0.000094518204,0.00011536717,0.0020720137,0.004534421,0.16908228,0.10319077,0.72032505],"study_design_scores_gemma":[0.000015056419,0.000030886753,0.0002416033,0.00019609286,0.00003415381,0.0006601304,0.00007945673,0.014397582,0.013618576,0.2896012,0.6810947,0.000030534367],"about_ca_topic_score_codex":0.000949921,"about_ca_topic_score_gemma":0.0011440443,"teacher_disagreement_score":0.06694527,"about_ca_system_score_codex":0.0007591354,"about_ca_system_score_gemma":0.0010555651,"threshold_uncertainty_score":0.22395426},"labels":[],"label_agreement":null},{"id":"W1904872924","doi":"10.1002/0471250953.bi0912s31","title":"Using the Generic Synteny Browser (GBrowse_syn)","year":2010,"lang":"en","type":"article","venue":"Current Protocols in Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Synteny; Computer science; Biology; Genetics; Gene; Genome","score_opus":0.09153211497302881,"score_gpt":0.3662461542577841,"score_spread":0.2747140392847553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904872924","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010692784,0.0057718214,0.4055299,0.0010490217,0.0011386041,0.00091908075,0.2544708,0.28859314,0.03183487],"genre_scores_gemma":[0.015461966,0.0035273929,0.5382232,0.0008725857,0.00017082019,0.0018278515,0.37063107,0.043182626,0.02610248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747926,0.00046447178,0.00030292754,0.00087090785,0.0006363069,0.00024610833],"domain_scores_gemma":[0.99858993,0.00024116156,0.00020521274,0.0005422432,0.00025846102,0.00016292771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038422574,0.0027836622,0.0022832875,0.004986666,0.0011902603,0.00292728,0.003350503,0.0021216674,0.08306218],"category_scores_gemma":[0.0043264194,0.0023171988,0.0022397223,0.0058657695,0.0005131231,0.004996582,0.0046987645,0.0028175763,0.116780244],"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":[0.0009785085,0.00013556117,0.002692784,0.0033033984,0.0006204487,0.0004661867,0.00062921643,0.0006554285,0.09123407,0.0060335235,0.73197746,0.16127336],"study_design_scores_gemma":[0.00010532713,0.000054315784,0.003308529,0.00023278408,0.00011718633,0.00077673915,0.00010788156,0.0015509595,0.021354713,0.0034086392,0.96883607,0.00014683664],"about_ca_topic_score_codex":0.0040660035,"about_ca_topic_score_gemma":0.005331242,"teacher_disagreement_score":0.08306218,"about_ca_system_score_codex":0.0005474208,"about_ca_system_score_gemma":0.0015268059,"threshold_uncertainty_score":0.27787066},"labels":[],"label_agreement":null},{"id":"W1911127936","doi":"10.1007/978-1-84628-758-9_13","title":"Data Mining in E-Learning","year":2007,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.043341751328746965,"score_gpt":0.3072032505440172,"score_spread":0.26386149921527025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1911127936","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025827882,0.071778394,0.7695033,0.005303618,0.003128996,0.00017230834,0.0008101069,0.0018894877,0.14483097],"genre_scores_gemma":[0.027525838,0.076454505,0.5126375,0.0026906466,0.0030429529,0.00032898653,0.002062294,0.0007390738,0.3745182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994562,0.00008280742,0.000045924735,0.000093865674,0.00030130774,0.000019898167],"domain_scores_gemma":[0.99896085,0.0006256796,0.000033450524,0.0001738615,0.00017550825,0.000030548712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007241381,0.0008346265,0.0009797394,0.0017875776,0.00051347516,0.002580461,0.001442188,0.001046145,0.018737484],"category_scores_gemma":[0.002052037,0.00045458772,0.00051816,0.0044019264,0.0009283481,0.0048610996,0.0013582535,0.001982164,0.0123261],"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":[0.000016935312,0.00006209188,0.00017454302,0.00074363954,0.00002445194,0.0000714588,0.00014219605,0.002038093,0.0010921494,0.12595165,0.078074194,0.79160863],"study_design_scores_gemma":[0.000009462668,0.000030813346,0.00046483456,0.0005474241,0.000025769685,0.00069529563,0.000098859935,0.0153439175,0.0038105526,0.27322638,0.7057216,0.00002509981],"about_ca_topic_score_codex":0.00041729785,"about_ca_topic_score_gemma":0.0005550883,"teacher_disagreement_score":0.018737484,"about_ca_system_score_codex":0.00060510315,"about_ca_system_score_gemma":0.0007300625,"threshold_uncertainty_score":0.062683165},"labels":[],"label_agreement":null},{"id":"W1926490927","doi":"10.1017/cbo9780511808241.023","title":"Randomized Algorithms","year":2008,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Algorithms and Data Compression","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":"York University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.02514260031613216,"score_gpt":0.2033256912112604,"score_spread":0.17818309089512824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926490927","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013351188,0.005299388,0.9146778,0.0025406636,0.0011783529,0.00043000554,0.00072897587,0.0030785422,0.07073112],"genre_scores_gemma":[0.06637123,0.008911021,0.8438339,0.004127651,0.0019186453,0.0021937944,0.0027091359,0.0016131012,0.06832144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99454886,0.0020598616,0.0003412961,0.0009979582,0.0015863201,0.00046570812],"domain_scores_gemma":[0.99353325,0.0039099194,0.00020983568,0.0017930737,0.0004185987,0.00013530372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037233427,0.002274853,0.0019173357,0.0015176018,0.0015182456,0.0046007438,0.0037765235,0.002341354,0.040567167],"category_scores_gemma":[0.0144422185,0.0009370802,0.0019988425,0.0028277026,0.0023399966,0.005611691,0.003835853,0.005998925,0.018531647],"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":[0.00014637462,0.00012905472,0.00024634672,0.0005983403,0.00010566412,0.00007119009,0.00010017453,0.013504354,0.0007094139,0.6951844,0.0682944,0.22091031],"study_design_scores_gemma":[0.00018799801,0.00009427987,0.00015343439,0.00026387535,0.00006213462,0.00027679058,0.00004278721,0.05142921,0.0012127922,0.76880574,0.17743139,0.000039537827],"about_ca_topic_score_codex":0.0009768691,"about_ca_topic_score_gemma":0.0015126725,"teacher_disagreement_score":0.040567167,"about_ca_system_score_codex":0.0021169502,"about_ca_system_score_gemma":0.0025532418,"threshold_uncertainty_score":0.13571066},"labels":[],"label_agreement":null},{"id":"W1937352721","doi":"","title":"Pattern-matching with bounded gaps in genomic sequences","year":2009,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Bounded function; Matching (statistics); Mathematics; Upper and lower bounds; Discrete mathematics; Combinatorics; Computer science; Mathematical analysis","score_opus":0.14070707588774367,"score_gpt":0.4942824648591295,"score_spread":0.35357538897138585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1937352721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062018327,0.0013363301,0.9319454,0.00057766406,0.000077857214,0.00007553199,0.00034218348,0.0008636046,0.0027630418],"genre_scores_gemma":[0.45155832,0.0013075743,0.5413263,0.00039384142,0.00015855113,0.00032220513,0.0017290987,0.00030424912,0.0028998172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965418,0.0009269935,0.00043183265,0.0009090898,0.00085329125,0.00033689314],"domain_scores_gemma":[0.98729706,0.008611023,0.0009888158,0.0022444848,0.0006133596,0.00024519075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029498222,0.0007109996,0.0015158086,0.0018658459,0.00092584745,0.0022298098,0.0019597271,0.0020439452,0.0018403025],"category_scores_gemma":[0.023205299,0.0006357245,0.00092528964,0.0043504625,0.0018973579,0.0067857304,0.0039540813,0.0023395391,0.001075153],"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":[0.0013536502,0.00027727726,0.004522798,0.0010124111,0.0000903805,0.0010374145,0.0011869858,0.16508113,0.020805247,0.49177012,0.005479072,0.3073835],"study_design_scores_gemma":[0.000051540937,0.000110634224,0.00047098417,0.00012193128,0.00003184674,0.0007118129,0.00019845739,0.31953675,0.016189946,0.6536572,0.008891393,0.00002744104],"about_ca_topic_score_codex":0.00050477794,"about_ca_topic_score_gemma":0.00037764726,"teacher_disagreement_score":0.0029498222,"about_ca_system_score_codex":0.00075653306,"about_ca_system_score_gemma":0.00079424016,"threshold_uncertainty_score":0.015600324},"labels":[],"label_agreement":null},{"id":"W1937925830","doi":"10.1007/978-3-319-17142-5_29","title":"Algorithms in the Ultra-Wide Word Model","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Word (group theory); Parallel computing; Prefix; Concurrency; Context (archaeology); Programming paradigm; Theoretical computer science; Programming language","score_opus":0.03650257839557475,"score_gpt":0.26940851793368276,"score_spread":0.232905939538108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1937925830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066036982,0.0024261903,0.9800468,0.0010741962,0.0002214504,0.000030053514,0.00021316508,0.00057877286,0.008805669],"genre_scores_gemma":[0.23375297,0.0057055587,0.72368586,0.0018870533,0.0012686874,0.0004362344,0.0019513947,0.001014796,0.030297477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796605,0.00072514504,0.00018635,0.00038223393,0.0005689042,0.00017133605],"domain_scores_gemma":[0.9935361,0.004309451,0.00023602294,0.0012134084,0.00059566693,0.00010941013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019763599,0.00081084383,0.0014040258,0.0017527038,0.0008508061,0.0032931203,0.0025830606,0.0019257052,0.0066818283],"category_scores_gemma":[0.011823873,0.0005870775,0.0012303342,0.0029283657,0.002107959,0.01026586,0.0032307059,0.0037165352,0.0036215014],"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":[0.000056616347,0.000030147652,0.00016945759,0.0001645233,0.000026451162,0.000041798266,0.00012434596,0.01974387,0.0006691844,0.85999227,0.0069624833,0.112018816],"study_design_scores_gemma":[0.000008539627,0.000011308745,0.00003160384,0.00002586517,0.0000068168038,0.000048300895,0.00002053023,0.07078564,0.00035758447,0.9244497,0.004244634,0.000009399235],"about_ca_topic_score_codex":0.0011228968,"about_ca_topic_score_gemma":0.0010468569,"teacher_disagreement_score":0.0066818283,"about_ca_system_score_codex":0.0010905463,"about_ca_system_score_gemma":0.0010875589,"threshold_uncertainty_score":0.022352934},"labels":[],"label_agreement":null},{"id":"W1938119559","doi":"10.1109/sct.1990.113958","title":"Perfect hashing, graph entropy, and circuit complexity","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hash function; Boolean function; Entropy (arrow of time); Perfect hash function; Discrete mathematics; Graph; Boolean circuit; Computer science; Upper and lower bounds; Time complexity; Mathematics; Combinatorics; Hash table","score_opus":0.05915089932611687,"score_gpt":0.2331720587606091,"score_spread":0.17402115943449223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1938119559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3105827,0.0072129844,0.62841904,0.0043350467,0.00022779967,0.0000868072,0.00090688135,0.0010184776,0.047210258],"genre_scores_gemma":[0.965546,0.0016695892,0.027824657,0.00023547217,0.00021033059,0.00007403309,0.00040626078,0.0000882141,0.003945363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904567,0.00019252367,0.000039753195,0.00018266581,0.0003713806,0.00016798556],"domain_scores_gemma":[0.99258196,0.0055227536,0.00064875744,0.0008477793,0.000250927,0.00014772665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007930823,0.00041752643,0.0005113619,0.0014154055,0.0005631217,0.0019575236,0.0009915521,0.0009350423,0.003731786],"category_scores_gemma":[0.009912064,0.00034595418,0.00039903523,0.0019101569,0.0027135126,0.006288838,0.0016173766,0.0013649148,0.0004064712],"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":[0.00019565648,0.0000477844,0.0020788591,0.00017052203,0.000030198871,0.000108191074,0.00012972768,0.11735797,0.0034672248,0.82823515,0.0031991228,0.044979606],"study_design_scores_gemma":[0.000014453143,0.000040900435,0.0007186282,0.000021254737,0.000013663905,0.00015077091,0.000037689344,0.17707156,0.0025529375,0.81742054,0.0019395164,0.00001814849],"about_ca_topic_score_codex":0.0008042625,"about_ca_topic_score_gemma":0.00084085774,"teacher_disagreement_score":0.003731786,"about_ca_system_score_codex":0.001891204,"about_ca_system_score_gemma":0.00064436236,"threshold_uncertainty_score":0.013721764},"labels":[],"label_agreement":null},{"id":"W1943270577","doi":"10.4169/amer.math.monthly.119.07.550","title":"How to Make the Most of a Shared Meal: Plan the Last Bite First","year":2012,"lang":"en","type":"article","venue":"American Mathematical Monthly","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"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":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Simon Fraser University; National Science Foundation","keywords":"Favourite; Figuring; Mathematical economics; Plan (archaeology); Subgame perfect equilibrium; Advice (programming); Computer science; Game theory; Mathematics; Law; Political science; History","score_opus":0.020106877500671062,"score_gpt":0.24191736882020717,"score_spread":0.22181049131953612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1943270577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056537848,0.0012693872,0.8667213,0.017096829,0.00085126044,0.0002547027,0.00090569287,0.0017679196,0.054595064],"genre_scores_gemma":[0.36029547,0.0011202645,0.58787817,0.0016770252,0.00011485345,0.00017631405,0.00087334495,0.0008006667,0.047063965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999559,0.00011350933,0.000025087682,0.000117434276,0.000095244126,0.000089695626],"domain_scores_gemma":[0.99920887,0.00028338263,0.00006391783,0.00019375431,0.00012236595,0.0001277375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008868728,0.0006282892,0.00068431743,0.0004988848,0.0013153465,0.0018291745,0.0011931537,0.0016283247,0.01768365],"category_scores_gemma":[0.004237742,0.00042384514,0.0005930643,0.0007659369,0.0015905662,0.0064240317,0.0016759927,0.0016345902,0.007095699],"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":[0.0011448299,0.000404389,0.004967815,0.00043854103,0.00012364883,0.00097445253,0.002206282,0.027885955,0.015406713,0.32055923,0.09069104,0.53519714],"study_design_scores_gemma":[0.00009991831,0.00025683816,0.0016181179,0.00016915855,0.00008280644,0.0013637854,0.0026221734,0.14714636,0.015797071,0.7079718,0.12268215,0.00018984576],"about_ca_topic_score_codex":0.0032254586,"about_ca_topic_score_gemma":0.0056050858,"teacher_disagreement_score":0.01768365,"about_ca_system_score_codex":0.0008462173,"about_ca_system_score_gemma":0.0011412917,"threshold_uncertainty_score":0.05915773},"labels":[],"label_agreement":null},{"id":"W195053133","doi":"10.1007/978-3-642-21458-5_9","title":"A d-Step Approach for Distinct Squares in Strings","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Alphabet; Conjecture; String (physics); Bounded function; Combinatorics; Constant (computer programming); Computer science; String searching algorithm; Least-squares function approximation; Key (lock); Mathematics; Discrete mathematics; Algorithm; Pattern matching; Artificial intelligence; Mathematical analysis; Statistics","score_opus":0.026826963749004114,"score_gpt":0.24490103356850984,"score_spread":0.21807406981950572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W195053133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022308147,0.000099343175,0.99052584,0.0001232983,0.00013041936,0.000046922323,0.0000779355,0.00046209115,0.006303359],"genre_scores_gemma":[0.030097667,0.00016245371,0.95263666,0.00025480334,0.00008001237,0.000121381985,0.00023689229,0.00045780785,0.015952412],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905163,0.00022214357,0.00006751119,0.0001926565,0.00038866204,0.00007743039],"domain_scores_gemma":[0.99843186,0.00067977415,0.000034362096,0.0004401134,0.00034818193,0.000065709326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078503165,0.00081004377,0.00075010484,0.0014425225,0.0008562694,0.0013974147,0.002181566,0.001454292,0.02300753],"category_scores_gemma":[0.0043691495,0.00058222783,0.0014189726,0.0015484832,0.0012099798,0.0022429333,0.0036463486,0.0025312726,0.010018299],"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":[0.00016331988,0.0001209399,0.00036080135,0.00033965887,0.000039165232,0.00022575971,0.00026399712,0.018996535,0.015710058,0.44549796,0.019695597,0.49858615],"study_design_scores_gemma":[0.000052058556,0.0001458742,0.00023241795,0.000086470885,0.00003673285,0.00057037105,0.00017297057,0.34388965,0.021206949,0.5638232,0.06971705,0.00006618948],"about_ca_topic_score_codex":0.0008403035,"about_ca_topic_score_gemma":0.0018333043,"teacher_disagreement_score":0.02300753,"about_ca_system_score_codex":0.00045217664,"about_ca_system_score_gemma":0.0007576228,"threshold_uncertainty_score":0.076967895},"labels":[],"label_agreement":null},{"id":"W1963589141","doi":"10.1186/1756-0500-7-466","title":"Suffix tree searcher: exploration of common substrings in large DNA sequence sets","year":2014,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; University of Victoria","keywords":"Substring; Suffix tree; Computer science; Sequence (biology); Generalized suffix tree; Suffix; Tree (set theory); Computational biology; Artificial intelligence; Data mining; Mathematics; Set (abstract data type); Combinatorics; Genetics; Biology; Data structure; Programming language","score_opus":0.2928156735960591,"score_gpt":0.42940860053351254,"score_spread":0.13659292693745345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963589141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11119377,0.0021676905,0.6490242,0.00074935576,0.00020057577,0.00063250714,0.04839094,0.17813632,0.009504665],"genre_scores_gemma":[0.11120383,0.0009336752,0.8333282,0.00018978606,0.00006641032,0.00067601714,0.04521944,0.0057388176,0.0026438544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919397,0.00011534876,0.00010266828,0.00026844928,0.000271243,0.000048289934],"domain_scores_gemma":[0.9982712,0.0010712678,0.00020231007,0.00012805738,0.00020385499,0.00012325532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015939251,0.0014266784,0.0009461305,0.004005938,0.0010334803,0.0019279225,0.0016425343,0.0010336014,0.015802113],"category_scores_gemma":[0.005804981,0.00061676995,0.0011677397,0.0050533125,0.0005012751,0.0026094054,0.0017488103,0.0009913873,0.0062035318],"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":[0.0023758698,0.0005284209,0.035095632,0.0054077846,0.0005762574,0.0032364072,0.0024571992,0.022317266,0.12832959,0.017945556,0.1515864,0.63014364],"study_design_scores_gemma":[0.00067284534,0.0009034854,0.025465773,0.0007760579,0.0004102342,0.0058476524,0.0015291962,0.5612489,0.115811184,0.06147166,0.22555661,0.0003063153],"about_ca_topic_score_codex":0.0009920284,"about_ca_topic_score_gemma":0.0017254871,"teacher_disagreement_score":0.015802113,"about_ca_system_score_codex":0.00043737108,"about_ca_system_score_gemma":0.0014921998,"threshold_uncertainty_score":0.05286336},"labels":[],"label_agreement":null},{"id":"W1964432965","doi":"10.1016/j.tcs.2014.09.003","title":"Less space: Indexing for queries with wildcards","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Substring; Search engine indexing; Combinatorics; String (physics); Mathematics; Character (mathematics); Set (abstract data type); Space (punctuation); Alphabet; Upper and lower bounds; Computer science; Discrete mathematics; Information retrieval","score_opus":0.008467994323228173,"score_gpt":0.23809036300949935,"score_spread":0.22962236868627117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964432965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12661934,0.0064177383,0.805507,0.0050973417,0.0023268727,0.0007949222,0.0052477876,0.028217886,0.019771071],"genre_scores_gemma":[0.42889354,0.0019101204,0.53314626,0.0025007247,0.0020173169,0.0006084167,0.010929433,0.00502998,0.014964281],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9919235,0.0014387873,0.00095580466,0.0012938471,0.003392973,0.0009950486],"domain_scores_gemma":[0.9676614,0.008947948,0.001081909,0.01887639,0.002500875,0.000931519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038941456,0.001642023,0.0041983905,0.005840512,0.0025483111,0.0063709733,0.005175206,0.003465618,0.016452745],"category_scores_gemma":[0.032654405,0.0012403287,0.0016850083,0.011352377,0.003528334,0.02236094,0.0076304735,0.0029907224,0.004784236],"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":[0.0031735394,0.0009878566,0.0041737575,0.0009416877,0.00014150224,0.00041350786,0.001016201,0.018405898,0.025257736,0.18062416,0.103627466,0.66123676],"study_design_scores_gemma":[0.0005772143,0.0006494138,0.0010048064,0.00020025262,0.00022980699,0.001377998,0.0006574064,0.25081152,0.026974084,0.6691281,0.048178643,0.00021076614],"about_ca_topic_score_codex":0.0023511515,"about_ca_topic_score_gemma":0.0025377062,"teacher_disagreement_score":0.016452745,"about_ca_system_score_codex":0.002148615,"about_ca_system_score_gemma":0.0032512548,"threshold_uncertainty_score":0.055039942},"labels":[],"label_agreement":null},{"id":"W1964541472","doi":"10.1016/s0890-5401(03)00057-9","title":"Distinguishing string selection problems","year":2003,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":236,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Substring; String (physics); String metric; String searching algorithm; Approximate string matching; Mathematics; Combinatorics; Commentz-Walter algorithm; Time complexity; Edit distance; Set (abstract data type); Hamming distance; Discrete mathematics; Algorithm; Computer science; Pattern matching; Artificial intelligence","score_opus":0.013085671571315597,"score_gpt":0.23607142253529467,"score_spread":0.22298575096397907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964541472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15124805,0.003092619,0.7624175,0.013838127,0.00090790616,0.00020781056,0.00097163534,0.0012279049,0.06608844],"genre_scores_gemma":[0.81705564,0.0017841479,0.14300962,0.0022675293,0.0019557646,0.00026817134,0.0033927704,0.00055196893,0.029714432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.994379,0.0019547008,0.00036026345,0.0013165217,0.0015060082,0.00048346218],"domain_scores_gemma":[0.96654344,0.026854027,0.00093724416,0.0038549935,0.0010647353,0.00074564805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004320655,0.00081675086,0.0014711281,0.002288539,0.0017305557,0.0046814135,0.0023855858,0.0042709876,0.01228019],"category_scores_gemma":[0.026235849,0.0006582581,0.0015439454,0.0033418683,0.0031394109,0.012302675,0.0054156897,0.00613305,0.002485572],"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":[0.000423408,0.00016035543,0.001491378,0.00023541224,0.00004148676,0.00018994468,0.00023419989,0.0062504075,0.0016523569,0.8672848,0.013667797,0.1083686],"study_design_scores_gemma":[0.000029538505,0.00003701064,0.00026161096,0.000023743956,0.000015978381,0.00017363907,0.000057862606,0.028000064,0.0017970521,0.9642855,0.0053063724,0.000011583872],"about_ca_topic_score_codex":0.00020121317,"about_ca_topic_score_gemma":0.00018656149,"teacher_disagreement_score":0.01228019,"about_ca_system_score_codex":0.0011771708,"about_ca_system_score_gemma":0.0010112397,"threshold_uncertainty_score":0.04108137},"labels":[],"label_agreement":null},{"id":"W1965359119","doi":"10.1186/1748-7188-6-23","title":"ReCoil - an algorithm for compression of extremely large datasets of dna data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data compression; Redundancy (engineering); Algorithm; Encoding (memory); Compression (physics); Volume (thermodynamics); Data compression ratio; Lossless compression; Compression ratio; Sequence (biology); Data mining; Image compression; Artificial intelligence; Biology; Physics","score_opus":0.10042025754405944,"score_gpt":0.3489168214591663,"score_spread":0.24849656391510688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965359119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011216672,0.0008912312,0.98154026,0.00019866948,0.00011915559,0.00014197806,0.00033975928,0.004326735,0.001225478],"genre_scores_gemma":[0.050987583,0.0007941766,0.94133395,0.00013485295,0.00007784322,0.0003526822,0.001749144,0.00065903284,0.0039107166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919444,0.00008505272,0.00009562844,0.00014012423,0.00042152966,0.00006324489],"domain_scores_gemma":[0.99874383,0.00048183237,0.0001294765,0.0002732238,0.00032608298,0.000045583354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089211477,0.0010778476,0.000677414,0.0016711322,0.00074723817,0.0013135062,0.0014337131,0.0009189962,0.0032102054],"category_scores_gemma":[0.0035292257,0.00037120897,0.00062621385,0.0021343457,0.00071541476,0.0019472436,0.0014781661,0.001427954,0.002221529],"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":[0.00067196105,0.00013180074,0.0015128239,0.00041157045,0.000101256555,0.00038243085,0.00037809563,0.029566512,0.07874899,0.022335947,0.0179166,0.8478421],"study_design_scores_gemma":[0.0002282465,0.00040146126,0.0017564312,0.00012808133,0.0000649136,0.0019404469,0.00021259741,0.5980841,0.3018737,0.023736779,0.07145295,0.00012027011],"about_ca_topic_score_codex":0.00082282454,"about_ca_topic_score_gemma":0.0010348551,"teacher_disagreement_score":0.0032102054,"about_ca_system_score_codex":0.00050893327,"about_ca_system_score_gemma":0.0007632228,"threshold_uncertainty_score":0.010739267},"labels":[],"label_agreement":null},{"id":"W1965477500","doi":"10.5539/jmr.v5n1p114","title":"Note on the Rademacher-Walsh Polynomial Basis Functions","year":2013,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Basis (linear algebra); Polynomial; Walsh function; Function (biology); Kernel (algebra); Basis function; Set (abstract data type); Polynomial basis; Kernel density estimation; Probability density function; Discrete mathematics; Applied mathematics; Algorithm; Computer science; Statistics; Mathematical analysis; Estimator","score_opus":0.1189870925421049,"score_gpt":0.37266940438807417,"score_spread":0.25368231184596923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965477500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004059934,0.0070120296,0.9553475,0.003178526,0.0015550556,0.000029789075,0.00011538512,0.00018716032,0.028514711],"genre_scores_gemma":[0.22539459,0.020727849,0.7091794,0.0040106517,0.006605917,0.00033882417,0.0003612121,0.00054813956,0.032833416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99702257,0.0011532702,0.00014753596,0.00043811498,0.0010723029,0.00016618759],"domain_scores_gemma":[0.99242496,0.00560286,0.00018201023,0.00093424646,0.00072275015,0.00013325477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005410702,0.001332831,0.00091607316,0.0019669891,0.00092542416,0.0021100703,0.0014290009,0.0021168059,0.0036477437],"category_scores_gemma":[0.021888345,0.00076596934,0.0011851133,0.0020048134,0.0047640023,0.005506252,0.0029022319,0.010000466,0.0026467699],"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":[0.00003689001,0.000011553278,0.00011156447,0.000059598045,0.0000084924495,0.0001138882,0.00009427726,0.008341036,0.00088706706,0.9598228,0.0045275707,0.025985342],"study_design_scores_gemma":[0.000014086788,0.000073359384,0.00032761807,0.00016558317,0.000020234913,0.00046461914,0.000039965562,0.16481113,0.0032009336,0.7747329,0.056070328,0.00007918293],"about_ca_topic_score_codex":0.0023258075,"about_ca_topic_score_gemma":0.001190956,"teacher_disagreement_score":0.005410702,"about_ca_system_score_codex":0.0011858778,"about_ca_system_score_gemma":0.00093562336,"threshold_uncertainty_score":0.028614879},"labels":[],"label_agreement":null},{"id":"W1967770912","doi":"10.1142/s0129054112400205","title":"EXACT PARALLEL ALIGNMENT OF MEGABASE GENOMIC SEQUENCES WITH TUNABLE WORK DISTRIBUTION","year":2012,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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 Ottawa","funders":"","keywords":"Speedup; Computer science; Pairwise comparison; Quadratic equation; Heuristic; Multiple sequence alignment; Sequence (biology); Distribution (mathematics); Basis (linear algebra); Algorithm; Space (punctuation); Parallel computing; Theoretical computer science; Sequence alignment; Mathematics; Artificial intelligence; Biology","score_opus":0.017949975043012115,"score_gpt":0.28140875808261534,"score_spread":0.26345878303960324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967770912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40014434,0.0008569146,0.5869625,0.0002441602,0.00009944598,0.00020099063,0.00023733219,0.008000243,0.0032541284],"genre_scores_gemma":[0.5581478,0.00037870518,0.43742055,0.00009168757,0.000028876182,0.00033870048,0.00094108057,0.0005187781,0.0021338046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896336,0.00020605995,0.000094397816,0.00028210296,0.0003407458,0.00011329174],"domain_scores_gemma":[0.9986241,0.00041787743,0.00015208722,0.0005093373,0.00022917466,0.00006745136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010454691,0.0007439637,0.00078140927,0.00082590734,0.0007767214,0.0009402435,0.0016750386,0.0006139293,0.0015196074],"category_scores_gemma":[0.0033635134,0.00044695823,0.00034202205,0.0021203212,0.00057448685,0.0018324814,0.0011164906,0.00058094494,0.0008597333],"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":[0.0028135416,0.0006384684,0.0093869455,0.00060345326,0.00017540618,0.00048700342,0.0008090313,0.14465274,0.37430468,0.013823709,0.0061661247,0.4461388],"study_design_scores_gemma":[0.00029580394,0.0005376533,0.0038664306,0.000020548552,0.0000555496,0.00030714672,0.00023881574,0.72394824,0.25097585,0.012477165,0.0072097303,0.00006706442],"about_ca_topic_score_codex":0.0010833757,"about_ca_topic_score_gemma":0.0014961881,"teacher_disagreement_score":0.0016750386,"about_ca_system_score_codex":0.0006733548,"about_ca_system_score_gemma":0.0007508136,"threshold_uncertainty_score":0.0055289865},"labels":[],"label_agreement":null},{"id":"W1968342055","doi":"10.1117/12.448656","title":"&lt;title&gt;Exponential decomposition using displacement structure&lt;/title&gt;","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Decomposition; Exponential function; Sequence (biology); Algorithm; Computer science; Combinatorics; Mathematics; Discrete mathematics; Mathematical analysis; Chemistry","score_opus":0.011078585382406936,"score_gpt":0.24468143603024942,"score_spread":0.23360285064784247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968342055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009347034,0.0003572345,0.98242974,0.00026018452,0.00018653195,0.000029705065,0.0001193875,0.0011570998,0.006113121],"genre_scores_gemma":[0.17861265,0.0010287812,0.7866947,0.00021474416,0.00021084945,0.00008721329,0.0010895462,0.00091447914,0.031147081],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997168,0.000032517386,0.000014798551,0.000057801688,0.00014514128,0.000032937045],"domain_scores_gemma":[0.9993486,0.00020121023,0.00004858216,0.00022148012,0.00014573432,0.000034442422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039691065,0.00064446457,0.00054764573,0.00057982444,0.00046146617,0.0011128872,0.00089253264,0.00065711484,0.019810641],"category_scores_gemma":[0.0017246176,0.0002678475,0.00035113402,0.0010797791,0.0006184375,0.0023631724,0.0012551328,0.0013760817,0.008240305],"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":[0.0004998048,0.00006781196,0.0006355166,0.0002936789,0.000028452905,0.00023076666,0.000113898706,0.034223426,0.046989825,0.099437155,0.023783086,0.7936965],"study_design_scores_gemma":[0.00012934732,0.00027822956,0.0009028013,0.00009673358,0.00002546485,0.00065025996,0.00013477856,0.70313936,0.07362974,0.1228262,0.09810713,0.000079942656],"about_ca_topic_score_codex":0.0008792689,"about_ca_topic_score_gemma":0.0015902672,"teacher_disagreement_score":0.019810641,"about_ca_system_score_codex":0.00038807682,"about_ca_system_score_gemma":0.00048468716,"threshold_uncertainty_score":0.06627321},"labels":[],"label_agreement":null},{"id":"W1968497309","doi":"10.1016/j.aeue.2008.09.006","title":"Rate of convergence of the nearest neighbor entropy estimator","year":2008,"lang":"en","type":"article","venue":"AEU - International Journal of Electronics and Communications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Estimator; Mathematics; Ergodic theory; Rate of convergence; Bernoulli's principle; Entropy estimation; Applied mathematics; k-nearest neighbors algorithm; Entropy (arrow of time); Minimax estimator; Statistics; Minimum-variance unbiased estimator; Pure mathematics; Computer science; Physics; Artificial intelligence; Thermodynamics","score_opus":0.017611298263036597,"score_gpt":0.26514192231886763,"score_spread":0.24753062405583104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968497309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09059941,0.004204309,0.890753,0.0014999349,0.0004633925,0.00013051568,0.0006949125,0.0011265955,0.010528014],"genre_scores_gemma":[0.7576184,0.0027067068,0.22004037,0.00058083097,0.00047077335,0.00039065312,0.0021558767,0.0011143513,0.014921997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931492,0.0028371322,0.0003091711,0.0009796272,0.002279874,0.00044506328],"domain_scores_gemma":[0.9040733,0.07355546,0.0026802595,0.007858987,0.010812948,0.0010189948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014319891,0.0009447185,0.0014400554,0.002376624,0.0011885563,0.0023991582,0.0020062355,0.002226568,0.004336473],"category_scores_gemma":[0.117499195,0.0006071152,0.0008350206,0.0011636175,0.0020145224,0.0043194657,0.0037237727,0.0028437127,0.0018066828],"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":[0.001821005,0.00023306451,0.031526867,0.001149285,0.00046544912,0.00082532456,0.001009849,0.44510767,0.024600115,0.22130679,0.009067626,0.26288697],"study_design_scores_gemma":[0.000034211524,0.0001477978,0.0054396624,0.00014619395,0.000054715132,0.0010058683,0.00018604557,0.93767273,0.017692802,0.034639314,0.002882521,0.000098203716],"about_ca_topic_score_codex":0.0021309815,"about_ca_topic_score_gemma":0.0014460215,"teacher_disagreement_score":0.014319891,"about_ca_system_score_codex":0.0013327898,"about_ca_system_score_gemma":0.0016853397,"threshold_uncertainty_score":0.075731754},"labels":[],"label_agreement":null},{"id":"W1968600331","doi":"10.1002/1097-024x(20001110)30:13<1465::aid-spe345>3.0.co;2-d","title":"Improvements to Burrows-Wheeler compression algorithm","year":2000,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"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":"Silesian University of Technology","keywords":"Lossless compression; Computer science; Compression ratio; Algorithm; Data compression; Compression (physics); Class (philosophy); Data compression ratio; Image compression; Artificial intelligence; Engineering","score_opus":0.01028238630179139,"score_gpt":0.2851556309118273,"score_spread":0.27487324461003587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968600331","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009844394,0.0037757328,0.97674745,0.00046996362,0.0005676618,0.00024965938,0.00029866438,0.0038516587,0.004194817],"genre_scores_gemma":[0.030537043,0.002436783,0.95186585,0.00031656315,0.00038084248,0.00021675139,0.0012668482,0.0005365002,0.012442903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973226,0.00028427385,0.00027594552,0.00043239532,0.001524568,0.00016030532],"domain_scores_gemma":[0.9974764,0.00054531265,0.00013206803,0.00059310836,0.0011860634,0.000066919114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019467033,0.0013503773,0.0013315051,0.0039094575,0.00086715515,0.0019701472,0.0018877903,0.0015900922,0.00548604],"category_scores_gemma":[0.0068124435,0.0006162152,0.0012258202,0.0044552395,0.00084218034,0.0032721984,0.0014961504,0.0029862926,0.0060444362],"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":[0.00028494734,0.00012739793,0.00055716763,0.00023329852,0.000082901235,0.00022838915,0.00019403406,0.016079694,0.036688026,0.021248031,0.013747474,0.9105286],"study_design_scores_gemma":[0.00025107092,0.0004356728,0.0034046096,0.00020570445,0.0002199759,0.0027531718,0.00020562933,0.47511837,0.21938367,0.027108338,0.27059087,0.0003230145],"about_ca_topic_score_codex":0.0046344646,"about_ca_topic_score_gemma":0.0043693422,"teacher_disagreement_score":0.00548604,"about_ca_system_score_codex":0.00076970324,"about_ca_system_score_gemma":0.0014248067,"threshold_uncertainty_score":0.018352628},"labels":[],"label_agreement":null},{"id":"W1968727285","doi":"10.1007/s10115-012-0546-1","title":"Out-of-core detection of periodicity from sequence databases","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Tree traversal; Computer science; Scalability; Suffix tree; Pruning; Suffix; Out-of-core algorithm; Sequence (biology); Auxiliary memory; Tree (set theory); Core (optical fiber); Data structure; Time complexity; Algorithm; Generalized suffix tree; Series (stratigraphy); Theoretical computer science; Data mining; Database; Mathematics","score_opus":0.06032132968878795,"score_gpt":0.29010241177526475,"score_spread":0.2297810820864768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968727285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46887526,0.0014413733,0.525161,0.00030549936,0.00017704738,0.00012610768,0.000867567,0.0012380261,0.0018080925],"genre_scores_gemma":[0.8406058,0.0005502999,0.15538588,0.00012453523,0.00016449158,0.00008545324,0.0018812797,0.00011688129,0.0010853515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866223,0.00023122116,0.00018304396,0.00025272547,0.0004876338,0.00018310962],"domain_scores_gemma":[0.9943929,0.0021763209,0.00068838295,0.0014352552,0.0010060092,0.00030114464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014602747,0.00050571054,0.001186384,0.0031229153,0.00060277624,0.0010710929,0.00087952666,0.0008059649,0.000913612],"category_scores_gemma":[0.008954189,0.00033573274,0.00039365963,0.0021533761,0.0004600344,0.0015246354,0.0013038141,0.0008072993,0.00059897185],"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":[0.003343778,0.00056335534,0.025974939,0.00044408272,0.00015413445,0.0012993771,0.0004286017,0.024923326,0.12706633,0.01170883,0.0042313254,0.7998619],"study_design_scores_gemma":[0.000070241884,0.00064981,0.023376731,0.00007787119,0.00010446127,0.0026224332,0.0002936713,0.8805722,0.06815063,0.018840127,0.005191656,0.000050235773],"about_ca_topic_score_codex":0.00076661195,"about_ca_topic_score_gemma":0.001078438,"teacher_disagreement_score":0.0031229153,"about_ca_system_score_codex":0.0003033847,"about_ca_system_score_gemma":0.001042755,"threshold_uncertainty_score":0.0077227354},"labels":[],"label_agreement":null},{"id":"W1969174204","doi":"10.1016/s0306-4573(03)00007-4","title":"A nearly-optimal Fano-based coding algorithm","year":2003,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Windsor","funders":"","keywords":"Huffman coding; Fano plane; Algorithm; Lossless compression; Computer science; Shannon–Fano coding; Coding (social sciences); Data compression; Theoretical computer science; Mathematics; Statistics","score_opus":0.009329930075609541,"score_gpt":0.23006628050950442,"score_spread":0.2207363504338949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969174204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0151315145,0.00059452245,0.9743226,0.00044008117,0.0001762689,0.000055736167,0.00019686285,0.00057594856,0.00850645],"genre_scores_gemma":[0.2021653,0.0007442357,0.78624403,0.000389631,0.00016521112,0.00016034098,0.00049450994,0.00018205472,0.009454715],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995321,0.000116191586,0.000021911243,0.0000723733,0.0002076713,0.000049708342],"domain_scores_gemma":[0.99941945,0.00023860317,0.000028057151,0.00012148608,0.00016009742,0.00003235838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006927394,0.0006319571,0.0006113231,0.0010021209,0.0005076755,0.00079979317,0.0008124812,0.00094462093,0.0037272044],"category_scores_gemma":[0.002530212,0.00024024877,0.00028651542,0.0010745468,0.00062077394,0.0012696038,0.0009299602,0.00084741635,0.000930625],"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":[0.00049133966,0.00008971799,0.00048522,0.00013673591,0.000030014731,0.00010273895,0.000102901926,0.11082388,0.02798438,0.23707785,0.013664968,0.6090102],"study_design_scores_gemma":[0.00008138858,0.000086383174,0.00021673711,0.000051431536,0.000021567412,0.00028375888,0.00002540334,0.8693227,0.013866183,0.10491126,0.011088996,0.00004421633],"about_ca_topic_score_codex":0.0016033701,"about_ca_topic_score_gemma":0.0022670093,"teacher_disagreement_score":0.0037272044,"about_ca_system_score_codex":0.00056441594,"about_ca_system_score_gemma":0.0010913865,"threshold_uncertainty_score":0.012468696},"labels":[],"label_agreement":null},{"id":"W1969844667","doi":"10.1016/j.dam.2013.10.021","title":"A<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si22.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>d</mml:mi></mml:math>-step approach to the maximum number of distinct squares and runs in strings","year":2013,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Parameterized complexity; Mathematics; String (physics); Combinatorics; Upper and lower bounds; Computation; Discrete mathematics; Algorithm; Mathematical analysis","score_opus":0.014358841014989042,"score_gpt":0.236957026351675,"score_spread":0.22259818533668596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969844667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010576523,0.0003681493,0.91232234,0.0016592825,0.0006466437,0.0001096265,0.0059698434,0.014284519,0.0635819],"genre_scores_gemma":[0.029799676,0.0009652875,0.84427106,0.0011315105,0.00086499023,0.00037738818,0.011367616,0.017216088,0.09400639],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986291,0.00035643412,0.0001238011,0.00025171263,0.00056801783,0.00007099014],"domain_scores_gemma":[0.995531,0.0017523724,0.00016350878,0.001153705,0.0012148955,0.00018444515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014047173,0.0010719871,0.0008387543,0.003537419,0.0008922189,0.0036492813,0.0027491278,0.0017639181,0.17515838],"category_scores_gemma":[0.010377721,0.000806585,0.0009701692,0.003703227,0.0010167399,0.005732545,0.002388351,0.0035065096,0.11224647],"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":[0.00025046425,0.000085833184,0.00032223057,0.0005163136,0.000036893307,0.00018709897,0.000189478,0.003738439,0.006950858,0.33935875,0.4347277,0.21363597],"study_design_scores_gemma":[0.00007411424,0.00005936925,0.00069938763,0.00016141823,0.000021211255,0.0006668438,0.00008494387,0.07082006,0.01638581,0.36855644,0.54239804,0.000072207906],"about_ca_topic_score_codex":0.0014504588,"about_ca_topic_score_gemma":0.0031110605,"teacher_disagreement_score":0.17515838,"about_ca_system_score_codex":0.0012310188,"about_ca_system_score_gemma":0.0008697551,"threshold_uncertainty_score":0.58596313},"labels":[],"label_agreement":null},{"id":"W1969885991","doi":"10.1016/j.ejc.2012.07.010","title":"Computing regularities in strings: A survey","year":2012,"lang":"en","type":"article","venue":"European Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computation; Mathematics; Combinatorics; Algorithm","score_opus":0.02669545516524006,"score_gpt":0.24501842042849722,"score_spread":0.21832296526325717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969885991","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056440074,0.25685447,0.6546394,0.0046310485,0.00070693495,0.00022253225,0.0015419071,0.0022823862,0.02268119],"genre_scores_gemma":[0.2631171,0.26017353,0.4549259,0.0019097818,0.0038858724,0.00035852418,0.0053785453,0.0011542413,0.009096459],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99483275,0.00070741423,0.00062818476,0.0017045666,0.0018355474,0.00029150548],"domain_scores_gemma":[0.9846198,0.010848152,0.0005576808,0.0025443623,0.0010992619,0.00033081096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033483575,0.0013245877,0.0035077462,0.0058461046,0.0012369622,0.006223516,0.004216477,0.0020020152,0.005337258],"category_scores_gemma":[0.015247755,0.0015123544,0.002003422,0.012598952,0.002863792,0.015534647,0.003726657,0.003307543,0.0022881634],"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":[0.00020848567,0.0002461573,0.0051990827,0.0037117829,0.00014557783,0.000112239955,0.0004308547,0.011330884,0.0023732393,0.14749716,0.008337038,0.8204075],"study_design_scores_gemma":[0.00007621323,0.00032530067,0.0041977167,0.0016140044,0.00022167676,0.002006042,0.0007519932,0.09491748,0.010414929,0.7683935,0.11694682,0.00013433775],"about_ca_topic_score_codex":0.001327263,"about_ca_topic_score_gemma":0.001305764,"teacher_disagreement_score":0.006223516,"about_ca_system_score_codex":0.0016816069,"about_ca_system_score_gemma":0.0022297471,"threshold_uncertainty_score":0.017854929},"labels":[],"label_agreement":null},{"id":"W1969934278","doi":"10.1007/s11227-013-0906-y","title":"High performance data clustering: a comparative analysis of performance for GPU, RASC, MPI, and OpenMP implementations","year":2013,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"National Center for Research Resources; National Institute of General Medical Sciences","keywords":"Computer science; Parallel computing; Implementation; CUDA; Scalability; Cluster analysis; Supercomputer; Shared memory; Computer architecture; Programming paradigm; Distributed memory; Field-programmable gate array; Operating system; Programming language; Artificial intelligence","score_opus":0.07788277327650803,"score_gpt":0.3280618811365622,"score_spread":0.25017910786005415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969934278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86621904,0.0039698617,0.082769066,0.00079851475,0.00026279112,0.0002493893,0.0021627217,0.02081958,0.022749033],"genre_scores_gemma":[0.8877385,0.0009976572,0.100577325,0.00010014071,0.00006699729,0.00011247264,0.0035838503,0.0020884108,0.0047345953],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969675,0.0007056499,0.00015590871,0.00031717715,0.0015033307,0.00035049336],"domain_scores_gemma":[0.98833406,0.004565153,0.00047365186,0.0017702546,0.0043810694,0.00047586244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003263479,0.0008698306,0.0010996708,0.0027485185,0.0013571086,0.0022739724,0.002494685,0.0009950626,0.0031848883],"category_scores_gemma":[0.011757165,0.00044249638,0.0007618665,0.0062129283,0.00068830396,0.0020277482,0.0011139452,0.0007164467,0.00152784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01027323,0.0012882741,0.040711276,0.0019617837,0.0010117919,0.00030214834,0.0014594676,0.33582437,0.033082314,0.01644488,0.034860156,0.52278036],"study_design_scores_gemma":[0.00040179564,0.0012831963,0.03243146,0.00010913187,0.00029822008,0.0002967182,0.001038992,0.9108663,0.036198623,0.0064987065,0.010435182,0.00014159962],"about_ca_topic_score_codex":0.015013282,"about_ca_topic_score_gemma":0.014403251,"teacher_disagreement_score":0.015013282,"about_ca_system_score_codex":0.0015399525,"about_ca_system_score_gemma":0.0026334643,"threshold_uncertainty_score":0.029851794},"labels":[],"label_agreement":null},{"id":"W1970126214","doi":"10.5555/1109557.1109603","title":"Implicit dictionaries with O(1) modifications per update and fast search","year":2006,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Conjecture; Constant (computer programming); Set (abstract data type); Computer science; Order (exchange); Search cost; Combinatorics; Binary logarithm; Mathematics; Discrete mathematics; Theoretical computer science; Algorithm; Programming language","score_opus":0.008316166533379635,"score_gpt":0.23509778953857782,"score_spread":0.2267816230051982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970126214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15698376,0.001688325,0.82420707,0.0016616997,0.00021702518,0.00025432068,0.000516434,0.002573302,0.011898057],"genre_scores_gemma":[0.484574,0.00074513385,0.49969447,0.00046753316,0.00032545437,0.00039357715,0.0008710949,0.000421472,0.012507262],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979232,0.00039009206,0.00024531878,0.00033887292,0.0008122784,0.00029029435],"domain_scores_gemma":[0.9835374,0.007585921,0.0015691711,0.006310614,0.00074149546,0.00025552086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012156721,0.00071405317,0.0012692285,0.00068095885,0.00073364796,0.0018902556,0.0023640404,0.0015925165,0.0040705167],"category_scores_gemma":[0.014745355,0.00077691535,0.0004692439,0.0020944264,0.0015098677,0.011092788,0.0028775434,0.001747844,0.0023930636],"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":[0.0030785697,0.0005157469,0.0047848863,0.00078884244,0.00009666975,0.00036121314,0.00082804903,0.13935432,0.037983973,0.15897697,0.019062659,0.63416815],"study_design_scores_gemma":[0.00060720596,0.0011992892,0.0022274659,0.00016239115,0.000119011,0.0019846219,0.00041140796,0.7342826,0.053339057,0.17885685,0.026677636,0.00013250213],"about_ca_topic_score_codex":0.0007961873,"about_ca_topic_score_gemma":0.0018333783,"teacher_disagreement_score":0.0040705167,"about_ca_system_score_codex":0.00077287765,"about_ca_system_score_gemma":0.0013525655,"threshold_uncertainty_score":0.013617218},"labels":[],"label_agreement":null},{"id":"W1971444540","doi":"10.1002/spe.1070","title":"PPM compression without escapes","year":2011,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Compression (physics); Gas compressor; Data compression; Coding (social sciences); Binary number; Computer science; Compression ratio; Character (mathematics); Arithmetic; Statistics; Algorithm; Mathematics; Engineering; Mechanical engineering; Physics","score_opus":0.03167187098252218,"score_gpt":0.2839718654866127,"score_spread":0.2522999945040905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971444540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28218752,0.0046502342,0.6540101,0.0028425446,0.0013099,0.000366113,0.005381351,0.017377522,0.031874772],"genre_scores_gemma":[0.70997936,0.0013616146,0.26167035,0.0005882032,0.0003761199,0.0001994706,0.0067692054,0.0012985822,0.017756999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913245,0.00010593919,0.00008750463,0.00014160799,0.00045179925,0.000080748934],"domain_scores_gemma":[0.9970228,0.0008154249,0.00015134197,0.0009450596,0.0009983646,0.000066984954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061904604,0.0006471771,0.00067461666,0.0014131435,0.00057447836,0.000965922,0.00074453856,0.0005471569,0.007408472],"category_scores_gemma":[0.0052825063,0.000248762,0.0002780172,0.0017109694,0.0008719267,0.0013897325,0.0015127186,0.0012434734,0.0024579475],"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":[0.0007182097,0.00003494111,0.0018158145,0.00050700764,0.000043572876,0.0007613394,0.00031577275,0.009546763,0.1432313,0.012321801,0.016375117,0.81432825],"study_design_scores_gemma":[0.00015798434,0.00067308854,0.011971117,0.00041970957,0.00014697168,0.0033565224,0.00054891314,0.16004926,0.63341004,0.030300627,0.15880628,0.00015957946],"about_ca_topic_score_codex":0.0025374843,"about_ca_topic_score_gemma":0.0033248053,"teacher_disagreement_score":0.007408472,"about_ca_system_score_codex":0.00042628465,"about_ca_system_score_gemma":0.00076167524,"threshold_uncertainty_score":0.02478379},"labels":[],"label_agreement":null},{"id":"W1971591942","doi":"10.1109/waimw.2006.21","title":"On the Subset Matching","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"Alphabet; String searching algorithm; Combinatorics; Pattern matching; Extension (predicate logic); String (physics); Matching (statistics); Set (abstract data type); Mathematics; Approximate string matching; Position (finance); Probabilistic logic; Computer science; Discrete mathematics; Algorithm; Artificial intelligence; Statistics","score_opus":0.009619140117910343,"score_gpt":0.21077689986083092,"score_spread":0.20115775974292058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971591942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012428764,0.0026188614,0.97154254,0.0013321204,0.00025605885,0.00025724867,0.00048104717,0.0010295493,0.010053757],"genre_scores_gemma":[0.16995344,0.0067176055,0.80023247,0.0018151862,0.0016068496,0.00092174497,0.0029238625,0.0010525825,0.014776265],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916583,0.002780878,0.00055064564,0.0020997254,0.002333736,0.00057682773],"domain_scores_gemma":[0.98794717,0.0061861095,0.00044007876,0.0041459748,0.0010196354,0.00026093255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052157766,0.0018686061,0.0032893831,0.004480381,0.0025479102,0.0041329144,0.0039875824,0.0027289481,0.012327748],"category_scores_gemma":[0.021950277,0.0012208691,0.0022682478,0.009849167,0.0034404343,0.019242248,0.006877121,0.0036455642,0.0045175636],"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":[0.0007662533,0.00029277266,0.001568133,0.00043036236,0.00018538961,0.00020005445,0.00041623611,0.08178836,0.003159802,0.34176487,0.035823196,0.53360456],"study_design_scores_gemma":[0.00010164544,0.00017487648,0.00040030925,0.00012357025,0.00009645023,0.0005141234,0.00014213128,0.23614226,0.0031293212,0.7237996,0.035328485,0.00004717194],"about_ca_topic_score_codex":0.0022135621,"about_ca_topic_score_gemma":0.0016118169,"teacher_disagreement_score":0.012327748,"about_ca_system_score_codex":0.0019239124,"about_ca_system_score_gemma":0.0019509214,"threshold_uncertainty_score":0.041240454},"labels":[],"label_agreement":null},{"id":"W1971684295","doi":"10.1109/wosspa.2013.6602411","title":"Adaptation of bit recycling to arithmetic coding","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Huffman coding; Arithmetic coding; Computer science; Data compression; Redundancy (engineering); Arithmetic; Context-adaptive binary arithmetic coding; Coding (social sciences); Lossless compression; Adaptation (eye); Compression ratio; Encoding (memory); Algorithm; Parallel computing; Theoretical computer science; Mathematics; Artificial intelligence; Engineering","score_opus":0.02803285727302798,"score_gpt":0.24912836740957156,"score_spread":0.22109551013654358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971684295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084492326,0.0009375956,0.90458524,0.00019774052,0.00012812218,0.0002078609,0.000056373137,0.0017702533,0.007624544],"genre_scores_gemma":[0.61467713,0.00075948425,0.37890235,0.00028346825,0.000110633315,0.00019421417,0.00015312468,0.00029269152,0.0046269586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989826,0.00024065319,0.00007037251,0.00016720715,0.00041241033,0.00012675521],"domain_scores_gemma":[0.9977762,0.0006227254,0.00021631691,0.00074562005,0.0006003024,0.00003873089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080791186,0.00074099307,0.0005744636,0.0011960783,0.00035442738,0.000665286,0.0015113975,0.00079585006,0.0016537366],"category_scores_gemma":[0.003807034,0.00026809634,0.00051562313,0.0011916028,0.0010472588,0.0012076211,0.0010370713,0.00078530435,0.00067054894],"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":[0.0006254725,0.00023586203,0.0020794296,0.00035485072,0.0000932157,0.0004816895,0.0002277988,0.11781167,0.32071283,0.061740752,0.0020965345,0.49353996],"study_design_scores_gemma":[0.000039598515,0.00043932648,0.0014302386,0.000072488845,0.00009334126,0.001050594,0.00005207977,0.6707436,0.29658815,0.0177419,0.011648556,0.000100134916],"about_ca_topic_score_codex":0.00075830397,"about_ca_topic_score_gemma":0.0005839248,"teacher_disagreement_score":0.0016537366,"about_ca_system_score_codex":0.00045340264,"about_ca_system_score_gemma":0.0005337012,"threshold_uncertainty_score":0.0055322647},"labels":[],"label_agreement":null},{"id":"W1971921337","doi":"10.1007/s12243-009-0136-8","title":"On unequal error protection for LZSS compressed data","year":2009,"lang":"fr","type":"article","venue":"Annals of Telecommunications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep de Thetford","funders":"","keywords":"BCH code; Decoding methods; Block (permutation group theory); Computer science; Scheme (mathematics); Algorithm; Compression (physics); Data compression; Arithmetic; Error detection and correction; Mathematics","score_opus":0.4508805504770715,"score_gpt":0.44080235983970945,"score_spread":0.010078190637362039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971921337","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06474871,0.0036619008,0.91485614,0.0020143585,0.0005351972,0.00010710877,0.00032338468,0.0008239493,0.012929213],"genre_scores_gemma":[0.79161495,0.0035774405,0.19204892,0.00063803635,0.001211672,0.00018823285,0.00073974347,0.00029155464,0.0096894065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971685,0.00091888773,0.00017530282,0.00020291159,0.0011618315,0.0003725204],"domain_scores_gemma":[0.9931339,0.00418737,0.000297932,0.0017787,0.0005275285,0.000074451826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027471373,0.0012715323,0.001273212,0.0018267429,0.0009333347,0.0015969512,0.0013073668,0.0017171272,0.005557494],"category_scores_gemma":[0.011440056,0.00039027855,0.00057015504,0.0021907443,0.0023650762,0.0028955636,0.0025955788,0.0016776115,0.0010209501],"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":[0.0025420776,0.00009833166,0.00091680145,0.0005018055,0.00012253222,0.0006158117,0.0006126953,0.10523213,0.041573044,0.49569672,0.009254474,0.34283367],"study_design_scores_gemma":[0.00018284789,0.00026932207,0.0006008651,0.00026358207,0.000096345844,0.0007340389,0.0001650941,0.5249636,0.07692774,0.38139802,0.014305436,0.00009303546],"about_ca_topic_score_codex":0.0011115125,"about_ca_topic_score_gemma":0.00093266746,"teacher_disagreement_score":0.005557494,"about_ca_system_score_codex":0.0011730962,"about_ca_system_score_gemma":0.0009344314,"threshold_uncertainty_score":0.018591702},"labels":[],"label_agreement":null},{"id":"W1972680079","doi":"10.1142/s0129054107004930","title":"REDUCING SIMPLE GRAMMARS: EXPONENTIAL AGAINST HIGHLY-POLYNOMIAL TIME IN PRACTICE","year":2007,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"Université du Québec en Outaouais","funders":"","keywords":"Deterministic context-free grammar; Computer science; Concatenation (mathematics); Time complexity; Embedded pushdown automaton; Stateless protocol; Context-free grammar; Reduction (mathematics); Theoretical computer science; Simple (philosophy); Regular expression; Automaton; Algorithm; Rule-based machine translation; Artificial intelligence; State (computer science); Mathematics; Tree-adjoining grammar; Programming language; Arithmetic","score_opus":0.012144565599661167,"score_gpt":0.30976415250553546,"score_spread":0.2976195869058743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972680079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26132545,0.0026739188,0.6745232,0.0057706516,0.0004208707,0.00070458045,0.002026065,0.025964392,0.026590884],"genre_scores_gemma":[0.5926849,0.00094527495,0.38960248,0.0009200949,0.00016726748,0.0005199598,0.0027213378,0.003401825,0.0090368865],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883221,0.0033837375,0.000692481,0.0017980648,0.0047041085,0.0010995303],"domain_scores_gemma":[0.9522758,0.031319182,0.0012742546,0.012529532,0.002115806,0.0004854033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037982622,0.0012332204,0.0011548062,0.0011534118,0.0011446871,0.0038228398,0.0024025,0.0019295913,0.011355412],"category_scores_gemma":[0.032750286,0.00065436505,0.0014730849,0.002476068,0.0028706016,0.0074875336,0.0030724867,0.0027629975,0.0036207598],"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":[0.0028116826,0.0010608578,0.0049023563,0.0021028416,0.00021069174,0.00063374056,0.0017209349,0.19495346,0.039897256,0.14177664,0.036730703,0.57319885],"study_design_scores_gemma":[0.0004658788,0.00029637697,0.0010702314,0.000112504225,0.0001459753,0.0006034459,0.00059179706,0.5541814,0.046133026,0.3765655,0.01975612,0.000077737895],"about_ca_topic_score_codex":0.0028548748,"about_ca_topic_score_gemma":0.004500813,"teacher_disagreement_score":0.011355412,"about_ca_system_score_codex":0.0025880334,"about_ca_system_score_gemma":0.0052984105,"threshold_uncertainty_score":0.03798759},"labels":[],"label_agreement":null},{"id":"W1973228454","doi":"10.1007/s00453-012-9726-3","title":"Efficient Fully-Compressed Sequence Representations","year":2012,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Disjoint sets; Substring; Mathematics; Amortized analysis; Redundancy (engineering); Data structure; Binary logarithm; Compressed suffix array; Subsequence; Algorithm; Sequence (biology); Discrete mathematics; Suffix tree; Computer science","score_opus":0.030796802325430674,"score_gpt":0.2926913199302248,"score_spread":0.2618945176047941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973228454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029627737,0.00081158703,0.9623908,0.00058455527,0.00031804037,0.000104529994,0.0010838264,0.0016107721,0.003468188],"genre_scores_gemma":[0.29520375,0.0012871465,0.68631256,0.00043135864,0.000531397,0.00041004515,0.004614764,0.00038178987,0.010827289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874485,0.000250496,0.0000989518,0.00019987574,0.0005754146,0.00013040056],"domain_scores_gemma":[0.99750715,0.00091107766,0.0001396024,0.00091398775,0.00045848795,0.00006965807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070379034,0.0011808363,0.0010173441,0.0015433362,0.0004400545,0.0017433588,0.0013744268,0.0015563826,0.0057559167],"category_scores_gemma":[0.006186249,0.00048316785,0.00056786125,0.0023975142,0.0007018791,0.0036094668,0.0021308437,0.001674044,0.0023283507],"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":[0.0009083133,0.0002542275,0.00059987593,0.00027550352,0.000063479645,0.00038795502,0.00017557522,0.109047115,0.03244301,0.09212741,0.017337,0.74638057],"study_design_scores_gemma":[0.00008401243,0.00017069958,0.0003383961,0.000057651207,0.00003170966,0.00058120524,0.00008781894,0.8715865,0.024885522,0.094349295,0.0077906293,0.000036601676],"about_ca_topic_score_codex":0.00090152747,"about_ca_topic_score_gemma":0.0014227931,"teacher_disagreement_score":0.0057559167,"about_ca_system_score_codex":0.00043979808,"about_ca_system_score_gemma":0.0012874532,"threshold_uncertainty_score":0.019255519},"labels":[],"label_agreement":null},{"id":"W1973442596","doi":"10.1145/568438.568441","title":"Review of <b>Data Structures and Algorithms in Java (2nd ed)</b>","year":2001,"lang":"en","type":"article","venue":"ACM SIGACT News","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Computer science; Java; Object (grammar); Class (philosophy); Set (abstract data type); Algorithm; Garbage collection; Data structure; Sequence (biology); Linked list; Programming language; Information retrieval; Artificial intelligence; Garbage","score_opus":0.05217211995221574,"score_gpt":0.3271956880794476,"score_spread":0.27502356812723183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973442596","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014253993,0.7443246,0.127493,0.019068966,0.03008274,0.00013191096,0.0016816208,0.0025864635,0.07320522],"genre_scores_gemma":[0.0076457555,0.66728127,0.11725136,0.011780504,0.01565681,0.00024559692,0.004563474,0.0029379628,0.17263731],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998475,0.00011048399,0.0001473431,0.0002196164,0.0009584558,0.00008915334],"domain_scores_gemma":[0.9967397,0.0011253285,0.00017929183,0.00016660533,0.0015868623,0.00020219781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014338605,0.000831863,0.001242502,0.003500904,0.00086002087,0.004200911,0.0018374972,0.0011152857,0.017931212],"category_scores_gemma":[0.004533867,0.0010259476,0.0010236966,0.009584611,0.0012877188,0.0053940527,0.0009064884,0.0032513584,0.021010917],"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":[0.00002244538,0.000036112473,0.00016256774,0.0017692964,0.000021435737,0.00004733216,0.00006985374,0.001127872,0.0012000863,0.016034583,0.5115037,0.46800476],"study_design_scores_gemma":[0.0000039489614,0.000021208312,0.00046142793,0.00052258244,0.000008592935,0.00025882883,0.000029051786,0.0007157829,0.00036154446,0.0058740117,0.9917257,0.000017346489],"about_ca_topic_score_codex":0.0045203306,"about_ca_topic_score_gemma":0.0065227216,"teacher_disagreement_score":0.017931212,"about_ca_system_score_codex":0.0018171187,"about_ca_system_score_gemma":0.002861942,"threshold_uncertainty_score":0.059985936},"labels":[],"label_agreement":null},{"id":"W1973767581","doi":"10.1145/1721837.1721859","title":"Periodicity testing with sublinear samples and space","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Sublinear function; Property testing; Mathematics; Space (punctuation); Combinatorics; Binary logarithm; Constant (computer programming); Streaming algorithm; Discrete mathematics; Order (exchange); Sample space; Sample (material); Property (philosophy); Statistics; Computer science; Upper and lower bounds; Mathematical analysis; Physics","score_opus":0.03292281120173705,"score_gpt":0.24999791139832664,"score_spread":0.2170751001965896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973767581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15336055,0.0018642497,0.8220466,0.0029468206,0.0002263228,0.00033503366,0.0014477968,0.012405573,0.005367051],"genre_scores_gemma":[0.67798835,0.00029224402,0.31463677,0.00067984476,0.00024487372,0.00050463027,0.0018839771,0.000682841,0.0030864822],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992273,0.0018841857,0.0006749134,0.0020488838,0.0024463253,0.0006727013],"domain_scores_gemma":[0.9459424,0.035304967,0.0037136448,0.012074487,0.0019069957,0.0010574892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045530093,0.0016855242,0.0019702353,0.001695549,0.0011316484,0.0035263612,0.0043142824,0.0020684632,0.006036583],"category_scores_gemma":[0.037322037,0.00090652815,0.0017176095,0.0025381674,0.0024455797,0.011258714,0.0039582714,0.0030437736,0.0025014624],"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":[0.0073965434,0.0012369844,0.025942082,0.0011160083,0.0005133266,0.00093466375,0.0010473074,0.4024591,0.022721224,0.056652665,0.015929695,0.4640504],"study_design_scores_gemma":[0.00020098232,0.00026613113,0.0009972473,0.00003480957,0.000055496035,0.00023293443,0.000118508455,0.9378298,0.0062256935,0.052383553,0.0016270666,0.000027753642],"about_ca_topic_score_codex":0.0025595387,"about_ca_topic_score_gemma":0.0039723455,"teacher_disagreement_score":0.006036583,"about_ca_system_score_codex":0.002052244,"about_ca_system_score_gemma":0.0033661968,"threshold_uncertainty_score":0.024078906},"labels":[],"label_agreement":null},{"id":"W1974033543","doi":"10.1145/1290672.1290680","title":"Succinct indexable dictionaries with applications to encoding <i>k</i> -ary trees, prefix sums and multisets","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":378,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Prefix; Encoding (memory); Trie; Computer science; Prefix code; Theoretical computer science; Tree (set theory); Combinatorics; Mathematics; Data structure; Algorithm; Decoding methods; Artificial intelligence; Programming language","score_opus":0.016770324426887896,"score_gpt":0.2608292871613097,"score_spread":0.24405896273442182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974033543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14099723,0.0014697098,0.83882993,0.0020535218,0.0002689703,0.00020948467,0.0019494852,0.0032300563,0.010991626],"genre_scores_gemma":[0.38660398,0.0009689777,0.6023071,0.00048647693,0.00014784462,0.00025392772,0.0022694103,0.0003606101,0.0066015995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929464,0.000118653305,0.00011193659,0.0001353348,0.00025374023,0.00008565549],"domain_scores_gemma":[0.9976215,0.00082601147,0.00020530017,0.00096335047,0.0002830609,0.000100867466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063844625,0.00042887352,0.0008815259,0.00074310496,0.00064441847,0.0018192452,0.0013603282,0.0009118584,0.0045913956],"category_scores_gemma":[0.0041511077,0.0004217413,0.0005690484,0.0027198547,0.001234524,0.005531064,0.0022234472,0.0019609893,0.001260577],"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":[0.0008690734,0.0003108799,0.0019954776,0.0005548705,0.000043691813,0.0005333515,0.0013471992,0.11766466,0.028893255,0.49464113,0.015884008,0.33726245],"study_design_scores_gemma":[0.000128855,0.000336973,0.000580102,0.00018453649,0.000049688308,0.0007025794,0.00055767194,0.4574439,0.047231317,0.44763157,0.045042817,0.000110017674],"about_ca_topic_score_codex":0.0012214925,"about_ca_topic_score_gemma":0.0022265573,"teacher_disagreement_score":0.0045913956,"about_ca_system_score_codex":0.001253064,"about_ca_system_score_gemma":0.00075938,"threshold_uncertainty_score":0.015359759},"labels":[],"label_agreement":null},{"id":"W1975687894","doi":"10.1016/j.tcs.2012.11.024","title":"Generating bracelets with fixed content","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amortized analysis; Mathematics; Combinatorics; Constant (computer programming); Content (measure theory); Fixed point; Discrete mathematics; Computer science; Algorithm; Data structure; Programming language","score_opus":0.02246921449861843,"score_gpt":0.24451280825694888,"score_spread":0.22204359375833044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975687894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10464867,0.00031923817,0.864875,0.0005752349,0.0004273452,0.00031607866,0.0009270205,0.0033951986,0.024516212],"genre_scores_gemma":[0.5745846,0.00035987367,0.38468426,0.0004360302,0.00016866843,0.00046356782,0.0032239663,0.0022003476,0.033878755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913484,0.00013906286,0.000047690486,0.00015528164,0.0003619601,0.00016123454],"domain_scores_gemma":[0.99713206,0.0013668773,0.00013395002,0.00081594486,0.0004301825,0.0001209758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005905379,0.00091440155,0.0010396463,0.0017110198,0.00078702485,0.0012938307,0.0017493266,0.0014290777,0.01519973],"category_scores_gemma":[0.005416353,0.0006701883,0.00072684383,0.0020437439,0.0011554438,0.0024796852,0.002620415,0.0015194756,0.0043430543],"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":[0.0013155958,0.00040328168,0.001318501,0.0005746404,0.00009244433,0.0008594817,0.0004138346,0.095940635,0.03954856,0.36260307,0.03857047,0.45835948],"study_design_scores_gemma":[0.00029641917,0.00030774518,0.00041193774,0.000118651995,0.000062735206,0.0004732439,0.00023191774,0.52790785,0.040770896,0.40673304,0.022623524,0.000062021354],"about_ca_topic_score_codex":0.0006829258,"about_ca_topic_score_gemma":0.001099655,"teacher_disagreement_score":0.01519973,"about_ca_system_score_codex":0.0005827456,"about_ca_system_score_gemma":0.00062002655,"threshold_uncertainty_score":0.050848126},"labels":[],"label_agreement":null},{"id":"W1975859913","doi":"10.1007/s00224-013-9455-2","title":"Linear-Space Data Structures for Range Mode Query in Arrays","year":2013,"lang":"en","type":"article","venue":"Theory of Computing Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Waterloo","funders":"","keywords":"Range (aeronautics); Mode (computer interface); Space (punctuation); Range query (database); Computer science; Information retrieval; Web search query; Sargable; Engineering; Aerospace engineering; Search engine","score_opus":0.0389336755502249,"score_gpt":0.29434127082161676,"score_spread":0.25540759527139184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975859913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02962,0.001697306,0.95172447,0.00133195,0.00019862251,0.0001872978,0.0013099345,0.006959034,0.0069713825],"genre_scores_gemma":[0.39484206,0.0010216206,0.5876059,0.0010522058,0.00037271803,0.0006714187,0.00288458,0.0012001822,0.0103493165],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976279,0.00045563112,0.00028675847,0.00026924777,0.0010872582,0.00027322714],"domain_scores_gemma":[0.99296606,0.0026574223,0.00040872808,0.002745682,0.0010576445,0.00016443609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001563429,0.00062719587,0.0010693856,0.0016471604,0.0010490417,0.0031085338,0.001900144,0.0010656299,0.011503442],"category_scores_gemma":[0.010749016,0.00051758834,0.0006905168,0.00412854,0.0014475542,0.0067440188,0.0033083807,0.001996042,0.0030240389],"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":[0.0018693528,0.00045883044,0.0032201377,0.0007805437,0.00011160835,0.00018567602,0.0011424738,0.037148446,0.022458006,0.33996257,0.06224879,0.53041357],"study_design_scores_gemma":[0.0003048484,0.00050270924,0.0009500705,0.00019755079,0.000107074935,0.0004859223,0.00063347636,0.3464732,0.045812663,0.57041055,0.033984672,0.00013730886],"about_ca_topic_score_codex":0.0016589897,"about_ca_topic_score_gemma":0.0023895327,"teacher_disagreement_score":0.011503442,"about_ca_system_score_codex":0.0013416512,"about_ca_system_score_gemma":0.001660068,"threshold_uncertainty_score":0.038482785},"labels":[],"label_agreement":null},{"id":"W1976679120","doi":"10.1145/1473195.1473219","title":"Introducing recursion by parking cars","year":2008,"lang":"en","type":"article","venue":"ACM SIGCSE Bulletin","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Recursion (computer science); Mutual recursion; Fibonacci number; Focus (optics); Computer science; Theoretical computer science; Algorithm; Mathematics; Algebra over a field; Discrete mathematics; Pure mathematics","score_opus":0.013665859829799518,"score_gpt":0.21969003151232547,"score_spread":0.20602417168252596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976679120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014808768,0.003618211,0.74575996,0.010901847,0.001395065,0.000105686275,0.00012173631,0.0020014462,0.22128734],"genre_scores_gemma":[0.32529536,0.004766188,0.5459571,0.0054136305,0.0006564511,0.00034647947,0.00019158014,0.0010619621,0.116311364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984108,0.00089320407,0.000049626207,0.0002503979,0.00027578702,0.000120108554],"domain_scores_gemma":[0.9979114,0.0014756803,0.00006856051,0.00023871347,0.00018827038,0.000117374504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013607887,0.000835257,0.0003917371,0.0007145903,0.0015359969,0.0029233731,0.0013012345,0.0018150753,0.019162303],"category_scores_gemma":[0.006395701,0.00042951727,0.00077973306,0.00072001247,0.00484258,0.006713717,0.0027343754,0.003766185,0.0049887556],"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":[0.000023210914,0.000024980836,0.00018779274,0.00007763869,0.000005209207,0.000073829935,0.0018370998,0.0022792495,0.0008608958,0.92818445,0.009848054,0.05659761],"study_design_scores_gemma":[0.000025788493,0.000087325585,0.00014236862,0.00016494573,0.000012130855,0.00047224067,0.0006409269,0.009344407,0.00231966,0.44415277,0.54259515,0.00004222262],"about_ca_topic_score_codex":0.0018369595,"about_ca_topic_score_gemma":0.0029717179,"teacher_disagreement_score":0.019162303,"about_ca_system_score_codex":0.0015892559,"about_ca_system_score_gemma":0.0014152782,"threshold_uncertainty_score":0.06410426},"labels":[],"label_agreement":null},{"id":"W1976682045","doi":"10.1145/1242471.1242472","title":"A taxonomy of suffix array construction algorithms","year":2014,"lang":"en","type":"review","venue":"Minerva Access (University of Melbourne)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":307,"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; Suffix array; Suffix; Algorithm; Implementation; Compressed suffix array; Suffix tree; Generalized suffix tree; Data structure; Theoretical computer science; Programming language","score_opus":0.07356066266408752,"score_gpt":0.28701972048415897,"score_spread":0.21345905782007146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976682045","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058274018,0.57179886,0.37517002,0.0024070148,0.0011753989,0.0005568641,0.0012690962,0.0027389927,0.039056316],"genre_scores_gemma":[0.020542994,0.5449899,0.4151386,0.0015242628,0.0010781283,0.00074962934,0.004045807,0.0005585673,0.011372182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983053,0.00025832056,0.00024793242,0.0003716235,0.0007042147,0.00011269122],"domain_scores_gemma":[0.99564517,0.0024249465,0.0002491011,0.00042532838,0.0011707038,0.00008472216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016665212,0.001439439,0.0014275903,0.0066902456,0.0008310988,0.0026396222,0.002715476,0.0017412811,0.0048921006],"category_scores_gemma":[0.008266757,0.00088226626,0.001037949,0.01429329,0.0009972426,0.0056339637,0.0014250326,0.0021885128,0.007496295],"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":[0.000043654112,0.00006816702,0.00045704746,0.0035452826,0.000032117077,0.000063103864,0.000112611575,0.0021180795,0.0020945314,0.026798362,0.01705674,0.9476104],"study_design_scores_gemma":[0.000038316208,0.00020847034,0.0010318767,0.0024895528,0.000083920546,0.0028763833,0.00024254352,0.015516519,0.0109239565,0.05630221,0.9101684,0.00011792029],"about_ca_topic_score_codex":0.00093885954,"about_ca_topic_score_gemma":0.00082578737,"teacher_disagreement_score":0.0066902456,"about_ca_system_score_codex":0.00093099975,"about_ca_system_score_gemma":0.0022068426,"threshold_uncertainty_score":0.016365767},"labels":[],"label_agreement":null},{"id":"W1977168723","doi":"10.5555/338219.338594","title":"Restructuring ordered binary trees","year":2000,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Restructuring; Displacement (psychology); Binary tree; Node (physics); Binary number; Tree (set theory); Sequence (biology); Order (exchange); Mathematics; Value (mathematics); Combinatorics; Computer science; Algorithm; Engineering; Structural engineering; Statistics; Arithmetic; Business; Chemistry","score_opus":0.00995584618535748,"score_gpt":0.22520593945361544,"score_spread":0.21525009326825797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977168723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16755264,0.0011743156,0.8201513,0.0006087489,0.00012280581,0.00015905188,0.00032510603,0.001214489,0.008691564],"genre_scores_gemma":[0.45899016,0.00092843146,0.53140825,0.0002590662,0.00010220941,0.00014571856,0.0010502324,0.00029295636,0.006822918],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993875,0.0001393713,0.00004973339,0.000101910526,0.00022834026,0.00009314469],"domain_scores_gemma":[0.9983746,0.0008405335,0.00014587663,0.00037573403,0.00019339434,0.000069836286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006254206,0.0004711301,0.0005913754,0.0006355219,0.000571764,0.0006942443,0.00092696096,0.00077447126,0.0027757594],"category_scores_gemma":[0.0042730053,0.00033974767,0.00035648112,0.0011612141,0.0006686998,0.0021259107,0.0011185952,0.00079717534,0.0008724116],"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":[0.00043504164,0.00022338952,0.0021417965,0.0007094962,0.000051775598,0.00066211104,0.00093472237,0.20986043,0.07684155,0.0985998,0.009368692,0.60017127],"study_design_scores_gemma":[0.00010482019,0.00029324635,0.0010254512,0.000078018566,0.000053164582,0.00074170955,0.00048540873,0.6554241,0.05055123,0.26203206,0.029176617,0.00003413688],"about_ca_topic_score_codex":0.00076265685,"about_ca_topic_score_gemma":0.0012608195,"teacher_disagreement_score":0.0027757594,"about_ca_system_score_codex":0.00041776276,"about_ca_system_score_gemma":0.0004372377,"threshold_uncertainty_score":0.009285808},"labels":[],"label_agreement":null},{"id":"W1977261082","doi":"10.1007/s00453-014-9947-8","title":"Linear-Space Data Structures for Range Frequency Queries on Arrays and Trees","year":2014,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Combinatorics; Data structure; Path (computing); Multiset; Binary logarithm; Rank (graph theory); Tree (set theory); Linear space; Element (criminal law); Mathematics; Order (exchange); Space (punctuation); Range (aeronautics); Time complexity; Discrete mathematics; Computer science","score_opus":0.029155084635691452,"score_gpt":0.2760695025497986,"score_spread":0.24691441791410718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977261082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041306343,0.0026653786,0.9385325,0.0024433269,0.000249088,0.00021466218,0.0015101169,0.0040790094,0.008999648],"genre_scores_gemma":[0.3646217,0.002020261,0.61180174,0.0011303537,0.00070653774,0.00086727954,0.004090042,0.0010224319,0.013739605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99629384,0.00070804486,0.00040460366,0.00051400973,0.0016642546,0.00041510214],"domain_scores_gemma":[0.9877364,0.0059940093,0.0007250611,0.0041323393,0.0011887479,0.00022338341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020401059,0.00093298126,0.0015748319,0.002549241,0.0015222823,0.0045668464,0.002643875,0.0017503542,0.012418357],"category_scores_gemma":[0.018454403,0.00071733526,0.0010420614,0.008346558,0.0021543568,0.011697315,0.0042146775,0.0028969431,0.003551758],"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":[0.00097516296,0.0004594765,0.0029369988,0.0007667658,0.00010439013,0.00014845973,0.00089373824,0.05660234,0.009409989,0.3918392,0.04169635,0.49416715],"study_design_scores_gemma":[0.00016808065,0.00018282952,0.00061044795,0.00012113717,0.00008300068,0.00036985977,0.00045107136,0.2534876,0.012661057,0.7136109,0.018189652,0.000064376705],"about_ca_topic_score_codex":0.0017110385,"about_ca_topic_score_gemma":0.0027882725,"teacher_disagreement_score":0.012418357,"about_ca_system_score_codex":0.002029676,"about_ca_system_score_gemma":0.0021414796,"threshold_uncertainty_score":0.041543543},"labels":[],"label_agreement":null},{"id":"W1977410585","doi":"10.1016/j.jda.2006.10.003","title":"Fast pattern-matching on indeterminate strings","year":2006,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Grantová Agentura České Republiky","keywords":"Indeterminate; String (physics); Alphabet; Pattern matching; String searching algorithm; Matching (statistics); Combinatorics; Mathematics; Integer (computer science); Position (finance); Algorithm; Computer science; Discrete mathematics; Artificial intelligence; Pure mathematics; Linguistics","score_opus":0.00796072570902388,"score_gpt":0.2421792449441994,"score_spread":0.23421851923517553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977410585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11552886,0.0008871911,0.8767895,0.00045461667,0.00025074923,0.00013017647,0.00032352135,0.0018769873,0.0037584275],"genre_scores_gemma":[0.52758205,0.00053926354,0.46314615,0.00024893024,0.0001486687,0.00016119807,0.00071733864,0.00027703622,0.0071793688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980718,0.00043989343,0.00019523615,0.00033995262,0.0007791488,0.00017389406],"domain_scores_gemma":[0.9954626,0.002341243,0.00028424256,0.0013222593,0.0004872645,0.00010246248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010493146,0.0005697957,0.0012619958,0.0016965178,0.00064364634,0.0012675425,0.0013227339,0.0012742686,0.0036748094],"category_scores_gemma":[0.009190893,0.00040721,0.00047168822,0.003994023,0.00071661366,0.003652381,0.0021645897,0.0010553236,0.0012565646],"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":[0.001265356,0.00015188302,0.0015908397,0.00030779632,0.000059803886,0.0004670441,0.00016368623,0.03658244,0.028780794,0.061713077,0.0066079865,0.86230934],"study_design_scores_gemma":[0.00014446683,0.00030853174,0.00080823875,0.00005788196,0.000043677348,0.00084446924,0.00011016661,0.7271944,0.046973445,0.21695122,0.006526851,0.000036592555],"about_ca_topic_score_codex":0.0005258284,"about_ca_topic_score_gemma":0.0006320143,"teacher_disagreement_score":0.0036748094,"about_ca_system_score_codex":0.00040890698,"about_ca_system_score_gemma":0.0006175275,"threshold_uncertainty_score":0.012293458},"labels":[],"label_agreement":null},{"id":"W1977986119","doi":"10.1016/j.tcs.2007.07.041","title":"Optimal lower bounds for rank and select indexes","year":2007,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Eidgenössische Technische Hochschule Zürich","keywords":"Rank (graph theory); Data structure; Upper and lower bounds; Computer science; Word (group theory); Combinatorics; Binary logarithm; Space (punctuation); Index (typography); Order (exchange); Algorithm; Mathematics; Discrete mathematics","score_opus":0.007316668029087797,"score_gpt":0.2601985053427479,"score_spread":0.2528818373136601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977986119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032021616,0.018362364,0.87545013,0.009395971,0.0010744487,0.00042515557,0.0034887183,0.0033022393,0.056479283],"genre_scores_gemma":[0.39988336,0.014745601,0.5270165,0.0035953883,0.0053080632,0.0017707165,0.0057595046,0.0035545041,0.03836636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97543997,0.0064198687,0.0011446294,0.0020927028,0.010584428,0.0043184236],"domain_scores_gemma":[0.89107674,0.0842495,0.0037037286,0.011787602,0.0062861596,0.002896284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016314158,0.006812792,0.0072968034,0.0108717345,0.0039616437,0.018260175,0.0090005025,0.006094439,0.025740823],"category_scores_gemma":[0.1021297,0.0030714471,0.0025464115,0.013822645,0.006767613,0.022953432,0.011350997,0.010811603,0.0077690408],"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":[0.0027058537,0.00074094476,0.001755313,0.001510445,0.00025358004,0.00019100124,0.00069868483,0.14268738,0.0059253965,0.5695769,0.04872957,0.22522497],"study_design_scores_gemma":[0.00024190672,0.00031841735,0.0007097223,0.00032014123,0.00021292511,0.00036761348,0.00029953223,0.37233904,0.006349754,0.60647535,0.012245378,0.00012017523],"about_ca_topic_score_codex":0.0022940212,"about_ca_topic_score_gemma":0.0052439906,"teacher_disagreement_score":0.025740823,"about_ca_system_score_codex":0.009002999,"about_ca_system_score_gemma":0.00962744,"threshold_uncertainty_score":0.08627856},"labels":[],"label_agreement":null},{"id":"W1978319862","doi":"10.1142/s0219720006002478","title":"CHARACTERIZATION OF THE EXISTENCE OF GALLED-TREE NETWORKS","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"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":"Simon Fraser University; Slovenská Akadémia Vied","keywords":"Mathematics; Tree (set theory); Simple (philosophy); Characterization (materials science); Root (linguistics); Convexity; Tree structure; Combinatorics; Discrete mathematics; Binary tree","score_opus":0.006882667899141399,"score_gpt":0.21145192726509057,"score_spread":0.20456925936594916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978319862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15624891,0.0009786546,0.8307549,0.0009441434,0.000052544656,0.00013546608,0.0007787516,0.00039181588,0.009714749],"genre_scores_gemma":[0.7716764,0.0011318049,0.22012694,0.00039792314,0.000086992804,0.00028381628,0.0018346915,0.00020826022,0.004253142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857175,0.00035109618,0.0001171802,0.00035754713,0.00040482898,0.00019765344],"domain_scores_gemma":[0.9847845,0.009625132,0.0014247568,0.0013136845,0.0018714675,0.0009804713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019763862,0.0004678649,0.0008621727,0.0025300088,0.0011889996,0.0020869502,0.0012530361,0.0014841851,0.0043285172],"category_scores_gemma":[0.01927651,0.00069026876,0.00076240033,0.0011687052,0.001858595,0.0061119124,0.003383301,0.0018045488,0.0008214614],"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":[0.00049407705,0.00011205106,0.009834197,0.00068128813,0.00018055698,0.0015870015,0.0014335498,0.11895861,0.032703627,0.74903095,0.0066677863,0.07831628],"study_design_scores_gemma":[0.00003295904,0.00010866153,0.0024836832,0.00014621658,0.0000836542,0.0012880227,0.00046413278,0.46161914,0.01784195,0.50483376,0.01102359,0.00007418083],"about_ca_topic_score_codex":0.0004520859,"about_ca_topic_score_gemma":0.00057106983,"teacher_disagreement_score":0.0043285172,"about_ca_system_score_codex":0.0006812146,"about_ca_system_score_gemma":0.0005599649,"threshold_uncertainty_score":0.014480352},"labels":[],"label_agreement":null},{"id":"W1979205601","doi":"10.1016/s0304-3975(00)00365-0","title":"Approximate periods of strings","year":2001,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Variety (cybernetics); Mathematics; Time complexity; Algorithm; Data compression; Computer science; Theoretical computer science; Combinatorics; Discrete mathematics; Artificial intelligence","score_opus":0.009637200902656283,"score_gpt":0.2481852492509679,"score_spread":0.23854804834831161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979205601","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.285337,0.0025701174,0.66798633,0.001104558,0.00048560873,0.00010554679,0.0010108179,0.0013147998,0.040085126],"genre_scores_gemma":[0.8729491,0.0014440761,0.105108485,0.00031301327,0.00050039706,0.0001523917,0.0013529275,0.0005557102,0.017623877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895895,0.0002883848,0.00006159197,0.00021914652,0.00032713107,0.00014479949],"domain_scores_gemma":[0.99625313,0.0019257086,0.0003412552,0.0010874294,0.00022557355,0.0001669992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078808115,0.0005951392,0.00077159464,0.001961459,0.00059103285,0.0022397488,0.0010461435,0.0010308017,0.008417848],"category_scores_gemma":[0.009688893,0.0005291407,0.00052454456,0.0022979719,0.0011076697,0.0045959987,0.0019842007,0.0016125467,0.0016330804],"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":[0.0010862221,0.00010815401,0.0027313286,0.0002738206,0.00006837835,0.00026260642,0.0004888051,0.06303256,0.011474495,0.67422986,0.01156771,0.23467606],"study_design_scores_gemma":[0.000052862506,0.00011191332,0.0010180786,0.000051358442,0.000036017685,0.00036220293,0.00017821573,0.2764552,0.0054251514,0.7043688,0.011917414,0.000022765971],"about_ca_topic_score_codex":0.00034960435,"about_ca_topic_score_gemma":0.0003693547,"teacher_disagreement_score":0.008417848,"about_ca_system_score_codex":0.00090789306,"about_ca_system_score_gemma":0.00036818438,"threshold_uncertainty_score":0.028160512},"labels":[],"label_agreement":null},{"id":"W1979256186","doi":"10.1145/1964179.1964182","title":"A new method for GPU based irregular reductions and its application to k-means clustering","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Parallel computing; Benchmark (surveying); Speedup; Cluster analysis; Scheme (mathematics); General-purpose computing on graphics processing units; GPU cluster; CUDA; Algorithm; Computational science; Computer graphics (images); Graphics; Mathematics; Artificial intelligence","score_opus":0.039921720037433696,"score_gpt":0.30405263109415565,"score_spread":0.26413091105672193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979256186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030804628,0.00008645042,0.9937098,0.00013326363,0.000093114664,0.000044042303,0.00006154392,0.0014423403,0.0013489579],"genre_scores_gemma":[0.033140264,0.00010353572,0.9626619,0.0000681584,0.00005079929,0.00013401559,0.00023725998,0.0005053354,0.0030988243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991423,0.00012635182,0.000052858217,0.0001455319,0.00048103498,0.000051884363],"domain_scores_gemma":[0.9990804,0.00020344066,0.00004914764,0.0002660045,0.00035542218,0.000045499066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005269995,0.00068775576,0.0007081776,0.0013247763,0.0010593326,0.0012294012,0.0016549582,0.00092414464,0.0039893063],"category_scores_gemma":[0.003097782,0.0005023226,0.0008580229,0.0020269454,0.0007570884,0.0011213949,0.0017052573,0.0013816825,0.0019820414],"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":[0.00027425247,0.00011654083,0.0013796522,0.00023310402,0.00013188942,0.00018013896,0.00040580265,0.12824972,0.04165289,0.038884263,0.023663566,0.7648281],"study_design_scores_gemma":[0.000047002646,0.00005636253,0.0006662046,0.00001827741,0.00001886954,0.00028996274,0.00005732572,0.9306393,0.018786058,0.014111006,0.035259094,0.000050510855],"about_ca_topic_score_codex":0.0062182653,"about_ca_topic_score_gemma":0.007002148,"teacher_disagreement_score":0.0062182653,"about_ca_system_score_codex":0.00078042253,"about_ca_system_score_gemma":0.0011609182,"threshold_uncertainty_score":0.01334554},"labels":[],"label_agreement":null},{"id":"W1979443512","doi":"10.1109/iccsit.2009.5234544","title":"Computing regularities in strings","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Computation; Theoretical computer science; Subject (documents); Algorithm","score_opus":0.008759597366078821,"score_gpt":0.2361163191533385,"score_spread":0.22735672178725969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979443512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27301016,0.0010142043,0.7141001,0.00078119646,0.0001000696,0.000115079594,0.0011189798,0.0024853414,0.00727476],"genre_scores_gemma":[0.57340795,0.00080631254,0.41834322,0.0001790247,0.00016870859,0.00016134036,0.002269076,0.0004332206,0.004231215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818975,0.0003321177,0.00025361514,0.0005799813,0.0004900729,0.00015459009],"domain_scores_gemma":[0.99333704,0.0037974557,0.00062464294,0.0014961174,0.0005837391,0.00016099955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545257,0.00043422755,0.00096567173,0.002638371,0.0010755714,0.002554262,0.0011186651,0.00087714725,0.0022661476],"category_scores_gemma":[0.013307818,0.0004669992,0.0008432211,0.004472992,0.0019925588,0.006518607,0.0016511101,0.0011464909,0.0008251294],"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":[0.0005522981,0.0001731888,0.011791179,0.00073701853,0.00013017714,0.0005142486,0.0014729719,0.09224602,0.018970225,0.44824302,0.0059689344,0.41920075],"study_design_scores_gemma":[0.000034463967,0.00010272185,0.0020652818,0.00009261826,0.00005395672,0.000518088,0.00044399148,0.26261404,0.020872971,0.7004623,0.012687276,0.000052252377],"about_ca_topic_score_codex":0.00095129316,"about_ca_topic_score_gemma":0.0009187402,"teacher_disagreement_score":0.002638371,"about_ca_system_score_codex":0.0008494719,"about_ca_system_score_gemma":0.000756705,"threshold_uncertainty_score":0.0075809956},"labels":[],"label_agreement":null},{"id":"W1979660621","doi":"10.1016/j.is.2007.03.001","title":"Indexing schemes for similarity search in datasets of short protein fragments","year":2007,"lang":"en","type":"article","venue":"Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fonterra Co-Operative Group; Victoria University; Victoria University of Wellington; University of Ottawa","keywords":"Search engine indexing; Computer science; Nearest neighbor search; Similarity (geometry); Information retrieval; Data mining; Artificial intelligence","score_opus":0.03226710671312223,"score_gpt":0.3096500319111106,"score_spread":0.2773829251979884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979660621","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10872231,0.0071375,0.8685054,0.0009641273,0.00053489505,0.00087644765,0.005114661,0.0056327684,0.002511916],"genre_scores_gemma":[0.26060247,0.0025411558,0.7215549,0.0002946273,0.00033734983,0.00089155236,0.010851454,0.00034880612,0.0025777535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959578,0.00070044736,0.0008705951,0.0005062127,0.0016729818,0.00029191835],"domain_scores_gemma":[0.9848161,0.0057486882,0.0011535074,0.0056068506,0.0022294028,0.00044538925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005105868,0.0006075951,0.0023208417,0.007284139,0.0015801777,0.0031213672,0.0026492618,0.0017340521,0.003113929],"category_scores_gemma":[0.022673484,0.00054236484,0.000907241,0.012091457,0.0012344351,0.0072798156,0.002940842,0.0014427265,0.0018913856],"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":[0.002105981,0.0006163833,0.0037742106,0.0011635179,0.00016690095,0.00018683821,0.00058453495,0.022907928,0.03455627,0.050480902,0.018655932,0.8648006],"study_design_scores_gemma":[0.0008695814,0.0014674601,0.0059817974,0.00040830416,0.00042050774,0.0020547053,0.0007453673,0.66643983,0.060695905,0.22879152,0.031838484,0.00028664456],"about_ca_topic_score_codex":0.0015773373,"about_ca_topic_score_gemma":0.0022269895,"teacher_disagreement_score":0.007284139,"about_ca_system_score_codex":0.0016005574,"about_ca_system_score_gemma":0.0026488488,"threshold_uncertainty_score":0.027002752},"labels":[],"label_agreement":null},{"id":"W1980628172","doi":"10.1109/itw.2012.6404756","title":"Compressing multisets using tries","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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":"Multiset; Sequence (biology); Encoding (memory); Cardinality (data modeling); Decoding methods; Encoder; Combinatorics; Computer science; Lossless compression; Discrete mathematics; Permutation (music); Mathematics; Algorithm; Theoretical computer science; Data compression; Artificial intelligence; Data mining","score_opus":0.08606859197094394,"score_gpt":0.32324640095503765,"score_spread":0.2371778089840937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980628172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12081347,0.0016098197,0.866961,0.0010981404,0.0002905951,0.00016260974,0.00058067363,0.0014371029,0.0070465207],"genre_scores_gemma":[0.62071836,0.001498206,0.36418167,0.0005171091,0.00033245902,0.0004361153,0.0012584118,0.00033420138,0.010723408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983785,0.00039714697,0.00015483431,0.00030234273,0.0005970565,0.00017005514],"domain_scores_gemma":[0.99505806,0.0030847613,0.0003130048,0.0010513169,0.00038909822,0.000103817765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015008113,0.00086837355,0.0013563656,0.001468882,0.00075883634,0.0019176789,0.0013853824,0.0014208353,0.003452042],"category_scores_gemma":[0.008507956,0.00067204464,0.0010524036,0.0023949814,0.001497391,0.0040912763,0.0029569326,0.0018129098,0.0012988223],"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":[0.0012486005,0.00018031914,0.0017097363,0.00079598057,0.00018419327,0.0016164335,0.0010606421,0.5107179,0.022215467,0.19925228,0.007223948,0.25379443],"study_design_scores_gemma":[0.000068141526,0.00023982274,0.00023739495,0.000108002176,0.000059059315,0.00054368493,0.00020623638,0.8523998,0.0178977,0.12235299,0.00584101,0.00004617216],"about_ca_topic_score_codex":0.00060203846,"about_ca_topic_score_gemma":0.00074924936,"teacher_disagreement_score":0.003452042,"about_ca_system_score_codex":0.0006836854,"about_ca_system_score_gemma":0.0008366904,"threshold_uncertainty_score":0.011548221},"labels":[],"label_agreement":null},{"id":"W1981541922","doi":"10.1016/s0022-0000(02)00006-5","title":"Methods for reconstructing the history of tandem repeats and their application to the human genome","year":2002,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Alberta; University of Waterloo","funders":"University of Waterloo; McMaster University","keywords":"Tandem repeat; Steiner tree problem; Combinatorics; Computer science; Heuristic; Gene duplication; Tandem exon duplication; Tree (set theory); Mathematics; Algorithm; Genome; Artificial intelligence; Biology; Genetics; Gene","score_opus":0.05563502447013171,"score_gpt":0.30498942655447414,"score_spread":0.24935440208434242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981541922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016423661,0.0010607049,0.9808945,0.00017832425,0.000049393635,0.000025077208,0.00018923666,0.00064166286,0.00053741835],"genre_scores_gemma":[0.12290521,0.0019728043,0.8719652,0.00007690369,0.00014992275,0.00015113753,0.0006745331,0.00039040897,0.0017138984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994802,0.00015371827,0.000049902825,0.00014275688,0.00014275743,0.000030674124],"domain_scores_gemma":[0.99469876,0.0038614618,0.00036718676,0.0006362796,0.000305942,0.00013030577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023354448,0.00077076786,0.0008252957,0.003845509,0.0009467017,0.0014587917,0.0019291863,0.0015581637,0.0025057576],"category_scores_gemma":[0.013625629,0.00094712485,0.0011381811,0.0035187888,0.0014102283,0.0017863102,0.0016291561,0.0018927717,0.00096138],"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":[0.00028158817,0.000095825795,0.0056281025,0.00034239976,0.00019132116,0.00027158615,0.0006187442,0.2943659,0.013827705,0.0521779,0.0024174699,0.62978137],"study_design_scores_gemma":[0.000060011902,0.000044507367,0.0016692086,0.000054501357,0.00006992649,0.00037524616,0.00011622421,0.9073428,0.004668333,0.081344,0.004187349,0.00006798716],"about_ca_topic_score_codex":0.003757516,"about_ca_topic_score_gemma":0.004811899,"teacher_disagreement_score":0.003845509,"about_ca_system_score_codex":0.0005693731,"about_ca_system_score_gemma":0.00090043986,"threshold_uncertainty_score":0.012351155},"labels":[],"label_agreement":null},{"id":"W1982231222","doi":"10.1145/777412.777427","title":"I/O-efficient topological sorting of planar DAGs","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Topological sorting; Digraph; Directed acyclic graph; Planar; Directed graph; Planar graph; Combinatorics; Sorting; sort; Path (computing); Computer science; Strongly connected component; Mathematics; Graph; Topology (electrical circuits); Algorithm; Arithmetic","score_opus":0.023495195242597633,"score_gpt":0.25953271908325637,"score_spread":0.23603752384065874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982231222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14133859,0.0010141981,0.82859015,0.0010317148,0.0001349597,0.00021696111,0.0013836997,0.0071838605,0.019105827],"genre_scores_gemma":[0.4531641,0.00096553017,0.53558457,0.00022486296,0.00006071931,0.00016004169,0.0037164171,0.00036501107,0.005758806],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99967325,0.000049098075,0.000025157351,0.00006509576,0.00008692585,0.00010059851],"domain_scores_gemma":[0.9993211,0.0002537629,0.00011059986,0.0001661048,0.000096015625,0.00005242005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028184993,0.0007714182,0.0004911398,0.0013883171,0.0005858221,0.0012408154,0.0012572681,0.0005893402,0.0044226255],"category_scores_gemma":[0.0021637988,0.00027889007,0.00048904977,0.0023320685,0.00053234113,0.0024129061,0.0012979822,0.0006626551,0.000997445],"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":[0.0005132929,0.00027897392,0.00212069,0.0007061635,0.00006270134,0.00015489722,0.00025005342,0.20745268,0.026702372,0.08172173,0.02146503,0.65857136],"study_design_scores_gemma":[0.00026330713,0.0003787792,0.000960493,0.00007757726,0.000088934634,0.00035279713,0.00047614286,0.6868471,0.054234594,0.22152697,0.034735847,0.000057425987],"about_ca_topic_score_codex":0.0018535674,"about_ca_topic_score_gemma":0.0034882445,"teacher_disagreement_score":0.0044226255,"about_ca_system_score_codex":0.0007951141,"about_ca_system_score_gemma":0.0012937819,"threshold_uncertainty_score":0.014795184},"labels":[],"label_agreement":null},{"id":"W1982358125","doi":"10.1016/j.tcs.2015.03.026","title":"On hardness of several string indexing problems","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Danmarks Grundforskningsfond","keywords":"String (physics); Search engine indexing; Computer science; Mathematics; Combinatorics; Information retrieval","score_opus":0.023988290326781455,"score_gpt":0.2594345300040363,"score_spread":0.23544623967725486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982358125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27947667,0.015731007,0.405996,0.105984986,0.002353281,0.0006094665,0.0069356537,0.002742215,0.18017076],"genre_scores_gemma":[0.83273387,0.008570186,0.09902175,0.008332612,0.0072137304,0.00086591963,0.00830647,0.0016391763,0.03331626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98885196,0.0034279202,0.00074504694,0.0021364894,0.0030719007,0.0017668592],"domain_scores_gemma":[0.8521386,0.13192174,0.0035399685,0.0074133384,0.0022698406,0.002716519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008236885,0.0025789102,0.0060278,0.0048844735,0.0067439736,0.011636585,0.008370584,0.008013817,0.026527211],"category_scores_gemma":[0.061119154,0.002235814,0.005191471,0.010842703,0.011694602,0.038745806,0.009056694,0.01940761,0.0022929092],"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":[0.0016161433,0.0008205246,0.0024816315,0.0015181601,0.00023959948,0.00041628125,0.0012089506,0.038281593,0.0015683443,0.83742297,0.052898213,0.06152772],"study_design_scores_gemma":[0.00015371206,0.0000457397,0.00040244512,0.00006133316,0.000055753695,0.00015176268,0.00017148962,0.0297026,0.0004166578,0.9660886,0.002716124,0.000033893262],"about_ca_topic_score_codex":0.0030482768,"about_ca_topic_score_gemma":0.0025517922,"teacher_disagreement_score":0.026527211,"about_ca_system_score_codex":0.0070838938,"about_ca_system_score_gemma":0.004016898,"threshold_uncertainty_score":0.088742316},"labels":[],"label_agreement":null},{"id":"W1983562473","doi":"10.1142/s0129183114500132","title":"A model of language inflection graphs","year":2013,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Algorithms and Data Compression","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":"Brock University","funders":"","keywords":"Inflection; Inflection point; Bipartite graph; Lattice (music); Mathematics; Graph; Computer science; Projection (relational algebra); Combinatorics; Artificial intelligence; Algorithm; Physics; Geometry","score_opus":0.01958174601054726,"score_gpt":0.27002914696986097,"score_spread":0.2504474009593137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983562473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22130206,0.00079682155,0.72280824,0.0046409336,0.00018685634,0.0001756825,0.001527631,0.0016250634,0.046936758],"genre_scores_gemma":[0.92331034,0.0006756367,0.049174175,0.00063923997,0.00016261723,0.00028136108,0.000812518,0.0002611557,0.024682948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99953103,0.00015800996,0.000017743721,0.00012948194,0.00008828521,0.00007545336],"domain_scores_gemma":[0.99841654,0.00077008107,0.0001826274,0.00023658977,0.00021279631,0.00018144342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043209508,0.00058193994,0.00064271066,0.001382746,0.001131959,0.0019173988,0.0020253477,0.0021142662,0.008368534],"category_scores_gemma":[0.0037302936,0.00045268162,0.0007954445,0.0018440149,0.0018253007,0.003029809,0.0015345899,0.0014371619,0.0015940791],"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":[0.00009833551,0.00007329828,0.00073277985,0.000099093726,0.000038396196,0.0007157763,0.0005299158,0.13898264,0.0048278957,0.8365183,0.0052758944,0.012107685],"study_design_scores_gemma":[0.00004417765,0.000032132477,0.00029198546,0.000014496232,0.000012511081,0.00029517917,0.00010074958,0.4627969,0.0005675629,0.5312504,0.004569798,0.000024077592],"about_ca_topic_score_codex":0.002958498,"about_ca_topic_score_gemma":0.0019715314,"teacher_disagreement_score":0.008368534,"about_ca_system_score_codex":0.0010713398,"about_ca_system_score_gemma":0.0007067665,"threshold_uncertainty_score":0.027995467},"labels":[],"label_agreement":null},{"id":"W1986085581","doi":"10.1515/integers-2011-0116","title":"A Correlation Identity for Stern's Sequence","year":2012,"lang":"en","type":"article","venue":"Integers","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Stern; Mathematics; Sequence (biology); Identity (music); Correlation; Statistics; Combinatorics; History; Geometry; Philosophy; Biology; Genetics; Aesthetics; Ancient history","score_opus":0.048193086034196586,"score_gpt":0.3222093115562386,"score_spread":0.274016225522042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986085581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14690349,0.0022443526,0.6306082,0.0030740097,0.0023940331,0.00015038103,0.00042387177,0.000530986,0.21367061],"genre_scores_gemma":[0.85937285,0.0013673179,0.09095638,0.0021108754,0.0013664275,0.00019687039,0.0003773268,0.00031924972,0.043932762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986475,0.000265313,0.00008770364,0.00025775097,0.00052998704,0.00021174354],"domain_scores_gemma":[0.9970348,0.0010169243,0.0003290944,0.0004172289,0.0008654637,0.00033640853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017633699,0.00048696483,0.0006665572,0.0016030448,0.001495718,0.0020787755,0.0006326009,0.0012855435,0.010097977],"category_scores_gemma":[0.007166136,0.00024475358,0.0005952028,0.0013393704,0.0023658415,0.0034237304,0.0024276415,0.0024172566,0.0025879906],"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":[0.000057821482,0.000011886741,0.00030574293,0.000034887526,0.000004100225,0.00009039278,0.00013830142,0.00052121613,0.0017646559,0.9838995,0.0024773588,0.010694059],"study_design_scores_gemma":[0.000030980926,0.00012552424,0.00082112115,0.00008869512,0.000013113785,0.00083670253,0.000150244,0.015988803,0.0069570616,0.948912,0.026027761,0.000047846883],"about_ca_topic_score_codex":0.00039219763,"about_ca_topic_score_gemma":0.00021347539,"teacher_disagreement_score":0.010097977,"about_ca_system_score_codex":0.0010848091,"about_ca_system_score_gemma":0.0011780462,"threshold_uncertainty_score":0.03378111},"labels":[],"label_agreement":null},{"id":"W1986302430","doi":"10.1371/journal.pone.0126409","title":"DIDA: Distributed Indexing Dispatched Alignment","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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; BC Cancer Agency; University of British Columbia","funders":"National Human Genome Research Institute; BC Cancer Agency; University of British Columbia; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Computer science; Scalability; Search engine indexing; Workflow; Software; Multiple sequence alignment; Sequence alignment; Data mining; Substring; Modular design; Preprocessor; Information retrieval; Artificial intelligence; Database; Programming language; Data structure; Biology","score_opus":0.07898714744398383,"score_gpt":0.23914406446189915,"score_spread":0.16015691701791532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986302430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032565435,0.0005348136,0.92741203,0.00032002895,0.0005991551,0.00031252514,0.0024153898,0.061513823,0.003635621],"genre_scores_gemma":[0.057389587,0.00044415126,0.91813195,0.00043698415,0.00022628914,0.0011436255,0.009555047,0.0073919287,0.005280358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972088,0.00051248574,0.00026018664,0.0010524408,0.00062133494,0.00034474162],"domain_scores_gemma":[0.99684215,0.0010686148,0.00021773652,0.0010438473,0.0004562476,0.00037151895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027774454,0.0022950952,0.0022995053,0.0017542087,0.00234743,0.0036428892,0.0062633962,0.0020571346,0.019262543],"category_scores_gemma":[0.009297649,0.0015211761,0.0022221082,0.0024780142,0.0014652684,0.0033885206,0.0065555084,0.004402894,0.015374072],"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":[0.0020098742,0.0005526156,0.0029201363,0.0018069404,0.0003528603,0.0006753324,0.00077717385,0.107929036,0.032229204,0.08981874,0.30735582,0.45357218],"study_design_scores_gemma":[0.000845725,0.00022363344,0.00064758636,0.0000962531,0.0000702065,0.0005083875,0.00018217355,0.69204336,0.01762504,0.1397417,0.14782402,0.00019194059],"about_ca_topic_score_codex":0.0042106626,"about_ca_topic_score_gemma":0.0046135667,"teacher_disagreement_score":0.019262543,"about_ca_system_score_codex":0.0018893551,"about_ca_system_score_gemma":0.0034329859,"threshold_uncertainty_score":0.064439654},"labels":[],"label_agreement":null},{"id":"W1986633843","doi":"10.1006/jcss.2002.1822","title":"Optimal Bounds for the Predecessor Problem and Related Problems","year":2002,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Matching (statistics); Set (abstract data type); Computer science; Element (criminal law); Class (philosophy); Dynamic problem; Multiplication (music); Upper and lower bounds; Mathematics; Algorithm; Mathematical optimization; Combinatorics","score_opus":0.024220483263055054,"score_gpt":0.2379167837357343,"score_spread":0.21369630047267923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986633843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039101545,0.026489,0.83367825,0.014853091,0.0017435284,0.00037981654,0.0015841802,0.0013271283,0.08084351],"genre_scores_gemma":[0.38789868,0.024187725,0.52828676,0.004502759,0.006756912,0.0015413773,0.004102891,0.0024894227,0.040233564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98971915,0.0035968455,0.00049045065,0.0015402837,0.0028376563,0.0018156775],"domain_scores_gemma":[0.88011503,0.10392275,0.0029372815,0.00586886,0.00457511,0.002580948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013886751,0.004301832,0.005248293,0.0068220035,0.0032937056,0.011677475,0.009582475,0.005806073,0.027231222],"category_scores_gemma":[0.09448473,0.0026947893,0.0027232247,0.0087476745,0.0055210222,0.026839126,0.008437512,0.013546746,0.0040426464],"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":[0.0015345678,0.00087292737,0.0012643794,0.0017163708,0.00018440427,0.00018367692,0.0005932372,0.17394865,0.0021936602,0.5973677,0.055405155,0.16473524],"study_design_scores_gemma":[0.00015103267,0.00016253897,0.00040799557,0.00031081142,0.00012354857,0.0002581633,0.00017672454,0.34162733,0.001315364,0.64757276,0.007824153,0.00006957492],"about_ca_topic_score_codex":0.00272913,"about_ca_topic_score_gemma":0.004108267,"teacher_disagreement_score":0.027231222,"about_ca_system_score_codex":0.00642968,"about_ca_system_score_gemma":0.0056341323,"threshold_uncertainty_score":0.091097474},"labels":[],"label_agreement":null},{"id":"W1987108302","doi":"10.1016/s0304-3975(00)00067-0","title":"Repetitive perhaps, but certainly not boring","year":2000,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Work (physics); Mathematical economics; Theoretical computer science; Mathematics; Calculus (dental); Algebra over a field; Engineering; Pure mathematics; Mechanical engineering","score_opus":0.008705978987782583,"score_gpt":0.23941056217111675,"score_spread":0.23070458318333417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987108302","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004913241,0.030362567,0.06006058,0.7135668,0.10419378,0.000097727214,0.00072009006,0.0017243949,0.08436086],"genre_scores_gemma":[0.07950596,0.023231408,0.08779674,0.4302195,0.09363136,0.00026305672,0.0010900024,0.0023988688,0.28186324],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99452704,0.0017189971,0.00025378505,0.0011411885,0.0020973342,0.00026151165],"domain_scores_gemma":[0.9738482,0.009226417,0.0012617611,0.005253571,0.008831938,0.0015780823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062012095,0.0012808564,0.0010495366,0.0014971165,0.0042160302,0.006112575,0.0023279495,0.0043820743,0.02408208],"category_scores_gemma":[0.04436229,0.0004623545,0.0008120764,0.0012373468,0.012539417,0.014130151,0.0034116602,0.011825969,0.01690995],"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":[0.00017860022,0.00006842331,0.0006819979,0.0005868163,0.0000836954,0.00028785388,0.0013183072,0.00036326333,0.002744673,0.25785208,0.6781475,0.05768681],"study_design_scores_gemma":[0.000035250418,0.00006567419,0.00067922403,0.00041484158,0.000025193467,0.00064181426,0.0018572133,0.0004254659,0.0009923044,0.3490834,0.64570063,0.0000790159],"about_ca_topic_score_codex":0.0019361656,"about_ca_topic_score_gemma":0.0030314168,"teacher_disagreement_score":0.02408208,"about_ca_system_score_codex":0.0021213302,"about_ca_system_score_gemma":0.0019593737,"threshold_uncertainty_score":0.08056265},"labels":[],"label_agreement":null},{"id":"W1987699222","doi":"10.1016/j.tcs.2012.03.005","title":"Succinct representations of permutations and functions","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Royal Society","keywords":"Combinatorics; Upper and lower bounds; Integer (computer science); Permutation (music); Mathematics; Constant (computer programming); Redundancy (engineering); Discrete mathematics; Binary logarithm; Time complexity; Function (biology); Computer science","score_opus":0.011512410575846524,"score_gpt":0.27473259320581783,"score_spread":0.2632201826299713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987699222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034106012,0.0011856853,0.94005394,0.0016415064,0.00034890612,0.00012688347,0.0022723284,0.0012509928,0.019013764],"genre_scores_gemma":[0.5185086,0.002609609,0.4456094,0.001035515,0.0005125237,0.0007039282,0.007764855,0.0008696656,0.022385813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975085,0.00077897427,0.00021730395,0.00030118955,0.00094528473,0.00024878595],"domain_scores_gemma":[0.99524236,0.0019372968,0.0003215599,0.0018529969,0.0005175181,0.00012831675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013205745,0.001106984,0.00082750374,0.002126097,0.0007933438,0.0040474026,0.0016657376,0.0017743153,0.0107418895],"category_scores_gemma":[0.009300206,0.00060816837,0.0007517622,0.0033640857,0.0016095096,0.0070954203,0.0026081908,0.0033866756,0.002768171],"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":[0.00021907336,0.00007003755,0.00025773083,0.00014341145,0.000015476346,0.00013089081,0.00033033855,0.022604218,0.001742043,0.8672768,0.0077765724,0.0994335],"study_design_scores_gemma":[0.000026009864,0.00003180122,0.00007821432,0.00007301509,0.000014788335,0.00013767999,0.00007805174,0.040106054,0.002158177,0.9447866,0.01249156,0.000018169296],"about_ca_topic_score_codex":0.00075106946,"about_ca_topic_score_gemma":0.0014178711,"teacher_disagreement_score":0.0107418895,"about_ca_system_score_codex":0.0010414798,"about_ca_system_score_gemma":0.0012778449,"threshold_uncertainty_score":0.035935223},"labels":[],"label_agreement":null},{"id":"W1987706313","doi":"10.1016/j.jda.2015.01.003","title":"String shuffle: Circuits and graphs","year":2015,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"String (physics); Combinatorics; Mathematics; Upper and lower bounds; Discrete mathematics; Reduction (mathematics); Computer science","score_opus":0.032039400917502854,"score_gpt":0.2727656157756264,"score_spread":0.24072621485812357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987706313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059914894,0.010950686,0.8820861,0.005143646,0.0009889442,0.0001261324,0.0009791693,0.0014234075,0.038386997],"genre_scores_gemma":[0.68680125,0.013070188,0.24692842,0.0017410048,0.001573812,0.00034623814,0.0018951336,0.0007085711,0.04693528],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993087,0.00022530332,0.000037819307,0.00013656505,0.00023448002,0.000057180656],"domain_scores_gemma":[0.9975127,0.001433337,0.00016305086,0.0005200722,0.00025120066,0.000119666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006656938,0.00059895386,0.0008734106,0.0020693266,0.000853963,0.0029494185,0.0011088342,0.0013575488,0.00921118],"category_scores_gemma":[0.006405223,0.0004671873,0.00046159135,0.0039732303,0.0019267503,0.006023439,0.0015751708,0.0024415907,0.0013092858],"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":[0.0001444614,0.0000510277,0.0003896558,0.00018092684,0.000019493269,0.00007042346,0.0001212202,0.023014754,0.0015842409,0.79609007,0.01250753,0.16582619],"study_design_scores_gemma":[0.00001684137,0.000022155686,0.00011261623,0.000028077775,0.0000090984,0.00008390561,0.00003659274,0.03835446,0.001117795,0.9494461,0.0107618645,0.000010533946],"about_ca_topic_score_codex":0.00074278703,"about_ca_topic_score_gemma":0.0008905101,"teacher_disagreement_score":0.00921118,"about_ca_system_score_codex":0.00095880823,"about_ca_system_score_gemma":0.0007342681,"threshold_uncertainty_score":0.030814469},"labels":[],"label_agreement":null},{"id":"W1988109548","doi":"10.1007/s10489-008-0144-9","title":"STNR: A suffix tree based noise resilient algorithm for periodicity detection in time series databases","year":2008,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Noise (video); Suffix tree; Algorithm; Series (stratigraphy); Suffix; Tree (set theory); Sequence (biology); Time series; Symbol (formal); Data structure; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.025423552607359325,"score_gpt":0.25390647698762403,"score_spread":0.2284829243802647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988109548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021154894,0.0007074921,0.9717657,0.00018542923,0.00017408372,0.000086609165,0.000533,0.0047507654,0.0006420274],"genre_scores_gemma":[0.11422825,0.0003972151,0.8802907,0.00019567122,0.00017595243,0.0001642737,0.0017845266,0.00031555365,0.002447958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878424,0.00024646134,0.00016990861,0.00023330374,0.0004978409,0.000068303365],"domain_scores_gemma":[0.9974842,0.0009873519,0.00022653006,0.0006448571,0.0005725797,0.00008446497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017931756,0.0007875961,0.0012397865,0.0022827706,0.0007917963,0.001153886,0.0014680513,0.0011855853,0.0031295188],"category_scores_gemma":[0.006320333,0.0004067774,0.0006556004,0.0026530053,0.0005450758,0.0019676127,0.0010714899,0.0010662153,0.0023065985],"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":[0.0011609903,0.00020903994,0.0017213344,0.00022101538,0.00012229492,0.00023930235,0.00012330533,0.025819488,0.03638722,0.0055646836,0.00960446,0.9188269],"study_design_scores_gemma":[0.00013037754,0.00046998556,0.0016293271,0.00004306281,0.0000764832,0.0008253398,0.000076823126,0.92219776,0.049019057,0.012947995,0.012527452,0.000056317465],"about_ca_topic_score_codex":0.0012943563,"about_ca_topic_score_gemma":0.0016836976,"teacher_disagreement_score":0.0031295188,"about_ca_system_score_codex":0.00035747432,"about_ca_system_score_gemma":0.0010593776,"threshold_uncertainty_score":0.010469258},"labels":[],"label_agreement":null},{"id":"W1988115395","doi":"10.1007/s00453-012-9712-9","title":"Compact Navigation and Distance Oracles for Graphs with Small Treewidth","year":2012,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Treewidth; Oracle; Combinatorics; Mathematics; Discrete mathematics; Bounded function; Adjacency list; Constant (computer programming); Computer science; Graph; Pathwidth; Line graph","score_opus":0.021067207725728593,"score_gpt":0.24593302265123274,"score_spread":0.22486581492550414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988115395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17756292,0.0031800524,0.80304325,0.003306482,0.00023383273,0.00011488731,0.001567601,0.001931763,0.009059225],"genre_scores_gemma":[0.714924,0.002296753,0.2658816,0.00089391955,0.0005330919,0.00034916436,0.0038138218,0.00076605426,0.010541649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99767643,0.00059063366,0.00017995872,0.0005810402,0.00070775434,0.00026420277],"domain_scores_gemma":[0.97189957,0.019410772,0.0018302212,0.0048114024,0.0010942171,0.0009538345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020583312,0.0012312011,0.0022866041,0.0024195702,0.0012924204,0.0039506797,0.0038642848,0.0028044975,0.007374138],"category_scores_gemma":[0.02899283,0.0010078301,0.00094907964,0.0054194536,0.0034074087,0.016156094,0.0053317025,0.0051254844,0.001457401],"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":[0.0011503543,0.00032599867,0.0030191338,0.00044606865,0.00006351118,0.00020843865,0.0006760292,0.118939094,0.0037863187,0.70343405,0.01351101,0.15443993],"study_design_scores_gemma":[0.000082654646,0.00006640677,0.0003192884,0.000045514,0.000027696191,0.00017994236,0.00011281994,0.16792127,0.0014705893,0.8273195,0.002426151,0.00002813741],"about_ca_topic_score_codex":0.002204082,"about_ca_topic_score_gemma":0.0030071249,"teacher_disagreement_score":0.007374138,"about_ca_system_score_codex":0.0018810754,"about_ca_system_score_gemma":0.0016143281,"threshold_uncertainty_score":0.024668932},"labels":[],"label_agreement":null},{"id":"W1989059628","doi":"10.1145/859670.859699","title":"Grammar-based compression of interpreted code","year":2003,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Algorithms and Data Compression","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; Grammar; Programming language; Code (set theory); Compression (physics); Natural language processing; Artificial intelligence; Linguistics","score_opus":0.04484810471989512,"score_gpt":0.3007764249463846,"score_spread":0.2559283202264895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989059628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048430692,0.000694642,0.9285722,0.0003988094,0.00020903074,0.00021622068,0.00046237095,0.0164754,0.004540699],"genre_scores_gemma":[0.3557513,0.00053875754,0.6326284,0.00033379413,0.00011038105,0.0003154378,0.0021827382,0.0032232595,0.0049159126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983577,0.00043407967,0.00015910632,0.00026931523,0.00063179905,0.0001478728],"domain_scores_gemma":[0.993718,0.0029097162,0.00038972578,0.0016797304,0.0012006747,0.00010211751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011196395,0.0009191626,0.00073456345,0.0014843576,0.000517784,0.0016682675,0.0017240971,0.0011622709,0.003027396],"category_scores_gemma":[0.009269878,0.00056858506,0.0006643305,0.0015040567,0.0015665039,0.0024915626,0.002175198,0.0014074101,0.0013734795],"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":[0.00094438146,0.00023634835,0.0032169214,0.00069669494,0.00011410731,0.00091061386,0.0016666192,0.09756268,0.12082863,0.0889433,0.0282083,0.65667146],"study_design_scores_gemma":[0.00011385396,0.00015645802,0.0007628025,0.000118529024,0.000076027245,0.00044303245,0.00029921695,0.7389216,0.15775107,0.08048677,0.020813972,0.00005666166],"about_ca_topic_score_codex":0.0016425641,"about_ca_topic_score_gemma":0.0028864956,"teacher_disagreement_score":0.003027396,"about_ca_system_score_codex":0.000814726,"about_ca_system_score_gemma":0.0013687706,"threshold_uncertainty_score":0.010127664},"labels":[],"label_agreement":null},{"id":"W1989181122","doi":"10.1016/s0166-218x(00)00196-7","title":"Fixed topology alignment with recombination","year":2000,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; City University of Hong Kong","keywords":"Merge (version control); Mathematics; Recombination; Topology (electrical circuits); Combinatorics; Node (physics); Discrete mathematics; Algorithm; Computer science; Physics; Genetics","score_opus":0.00898845320520242,"score_gpt":0.22610393493605466,"score_spread":0.21711548173085224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989181122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02403299,0.00033891614,0.96221834,0.00020751906,0.00019092463,0.00009267427,0.00022991918,0.0020914956,0.010597268],"genre_scores_gemma":[0.32584232,0.00029989798,0.66048145,0.00021460642,0.00015762767,0.00025309928,0.001688783,0.0017745922,0.009287564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997324,0.0009942445,0.00010812227,0.00080151786,0.00053925614,0.00023285068],"domain_scores_gemma":[0.9968424,0.0009844017,0.00018854604,0.0015376643,0.00031511355,0.00013186254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016149736,0.0007528569,0.0015363371,0.0020063769,0.0015032236,0.0021806373,0.0025146527,0.0023284312,0.010183649],"category_scores_gemma":[0.006822152,0.0006758174,0.001106624,0.0032423725,0.0016525147,0.003264745,0.003127596,0.0025369592,0.0051369127],"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":[0.00071559695,0.0002536461,0.0011147877,0.000309669,0.00015468727,0.00059933885,0.00071060116,0.123545475,0.031434596,0.29685956,0.015690094,0.52861196],"study_design_scores_gemma":[0.00013155966,0.00031024643,0.00056564255,0.00008077978,0.00010468465,0.0007891171,0.00029198843,0.51230985,0.03569646,0.40038264,0.04925225,0.00008486948],"about_ca_topic_score_codex":0.00050600705,"about_ca_topic_score_gemma":0.00059374014,"teacher_disagreement_score":0.010183649,"about_ca_system_score_codex":0.00065952446,"about_ca_system_score_gemma":0.0006918441,"threshold_uncertainty_score":0.03406775},"labels":[],"label_agreement":null},{"id":"W1989541071","doi":"10.5555/644108.644179","title":"On the complexity of distance-based evolutionary tree reconstruction","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":46,"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 Victoria","funders":"","keywords":"Tree (set theory); Context (archaeology); Computational complexity theory; Sequence (biology); Algorithm; Computer science; Mathematics; Theoretical computer science; Combinatorics","score_opus":0.04136532322409845,"score_gpt":0.23470920697592293,"score_spread":0.19334388375182449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989541071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1505826,0.0041588126,0.817305,0.0064110085,0.0002635536,0.00034589396,0.0019790062,0.0028975739,0.016056506],"genre_scores_gemma":[0.5298112,0.0034806684,0.45092684,0.0009557769,0.00061508565,0.0008648434,0.005047746,0.00087394286,0.007423904],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993258,0.001959881,0.0006102665,0.00094176224,0.0022803592,0.0009496936],"domain_scores_gemma":[0.8960338,0.09060607,0.002901415,0.0069703157,0.002529829,0.0009585218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004776061,0.0016892392,0.0028130421,0.0023767224,0.002051259,0.006325432,0.0038871323,0.0034329027,0.009399016],"category_scores_gemma":[0.051836915,0.0010098938,0.0020225018,0.005787515,0.0033540605,0.015144874,0.0055858633,0.0047797067,0.0022017916],"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":[0.0022575464,0.0004186341,0.0053767245,0.0010292792,0.00022564574,0.0005431661,0.0009516244,0.58581334,0.012175026,0.12430264,0.016425371,0.25048098],"study_design_scores_gemma":[0.00011725649,0.00009210355,0.0009504848,0.000058518006,0.00005929533,0.00032417823,0.00015669658,0.8556503,0.0039167195,0.13640518,0.0022258565,0.00004336679],"about_ca_topic_score_codex":0.0041553895,"about_ca_topic_score_gemma":0.0044341506,"teacher_disagreement_score":0.009399016,"about_ca_system_score_codex":0.0042865425,"about_ca_system_score_gemma":0.0031847942,"threshold_uncertainty_score":0.03144288},"labels":[],"label_agreement":null},{"id":"W1990363179","doi":"10.1016/s0012-365x(03)00294-2","title":"On the extension of a partial metric to a tree metric","year":2003,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Combinatorics; Extension (predicate logic); Metric (unit); Tree (set theory); Discrete mathematics; Polynomial; Simple (philosophy); Focus (optics); Set (abstract data type); Metric space; Computer science","score_opus":0.030633271315895584,"score_gpt":0.2725350720012243,"score_spread":0.2419018006853287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990363179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040546663,0.0025371972,0.9377918,0.0016055709,0.0003235694,0.000052587482,0.00018860163,0.00015867072,0.016795354],"genre_scores_gemma":[0.5304499,0.008667391,0.43686196,0.0011777532,0.0015760439,0.00028774742,0.00075355143,0.00037247938,0.019853108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980975,0.00078478735,0.00014900681,0.00023355302,0.00060659344,0.00012861467],"domain_scores_gemma":[0.9903706,0.0057288376,0.0005880823,0.001391714,0.0014134787,0.0005074379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027501031,0.0007671052,0.0010524096,0.00224467,0.0011059174,0.0019683598,0.0012687976,0.0012941733,0.003126147],"category_scores_gemma":[0.017377889,0.0004198942,0.00096090935,0.0032528222,0.0027179462,0.007936781,0.0039716247,0.0026502674,0.00061721454],"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":[0.000057937137,0.00001591525,0.0003541196,0.000072839095,0.000015076634,0.000115793366,0.00019096196,0.015755761,0.0012415205,0.93410766,0.0023101761,0.045762207],"study_design_scores_gemma":[0.000011148304,0.00009277633,0.0003175946,0.000042009273,0.000017973165,0.0002894187,0.000053927193,0.10958203,0.0007480708,0.8732221,0.015596257,0.000026718102],"about_ca_topic_score_codex":0.0012959309,"about_ca_topic_score_gemma":0.0010439204,"teacher_disagreement_score":0.003126147,"about_ca_system_score_codex":0.0009876875,"about_ca_system_score_gemma":0.0008107183,"threshold_uncertainty_score":0.01454407},"labels":[],"label_agreement":null},{"id":"W1991052357","doi":"10.1007/s00283-012-9340-x","title":"Walking on Real Numbers","year":2012,"lang":"en","type":"article","venue":"The Mathematical Intelligencer","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Division (mathematics); Computer science; Mathematics; Arithmetic","score_opus":0.04544934363887847,"score_gpt":0.3144804719205952,"score_spread":0.2690311282817167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991052357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121398844,0.009579586,0.5768394,0.008435182,0.0051309746,0.00011469445,0.00090272306,0.0015306032,0.27606803],"genre_scores_gemma":[0.6758808,0.0055589005,0.1619072,0.0014108886,0.0010513511,0.0001679906,0.0014005941,0.00082590064,0.15179639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996031,0.00008997143,0.000025337535,0.00011322913,0.0001254772,0.000042906082],"domain_scores_gemma":[0.9992785,0.0002694179,0.000065870365,0.00014734318,0.0001544124,0.00008456277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025431954,0.00051645096,0.0005232515,0.001593482,0.0009824571,0.0022503382,0.00062849675,0.0009988163,0.020733628],"category_scores_gemma":[0.0046098763,0.00029182906,0.0004074494,0.0014442076,0.0013036893,0.0035624888,0.0015860043,0.0015801559,0.004318877],"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":[0.000084769876,0.000020561554,0.0002901648,0.00013955092,0.00001718418,0.0001229873,0.00039167036,0.00648509,0.002378049,0.86012083,0.016832607,0.11311652],"study_design_scores_gemma":[0.000015713684,0.000036506226,0.0003695179,0.00007986448,0.000010318405,0.00024075735,0.0002535695,0.023813674,0.0011184363,0.9060455,0.067992315,0.000023724853],"about_ca_topic_score_codex":0.00092616817,"about_ca_topic_score_gemma":0.00055496924,"teacher_disagreement_score":0.020733628,"about_ca_system_score_codex":0.00044556847,"about_ca_system_score_gemma":0.000327148,"threshold_uncertainty_score":0.06936091},"labels":[],"label_agreement":null},{"id":"W1991132737","doi":"10.1142/9781860947322_0011","title":"THE USE OF FUNCTIONAL DOMAINS TO IMPROVE TRANSMEMBRANE PROTEIN TOPOLOGY PREDICTION","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Caprion (Canada); University of Calgary","funders":"","keywords":"Topology (electrical circuits); Computer science; Transmembrane protein; Engineering; Biology; Electrical engineering; Genetics","score_opus":0.02251206067277116,"score_gpt":0.22955701534728212,"score_spread":0.20704495467451095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991132737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43850178,0.0019424884,0.55298316,0.0007312493,0.00020709168,0.00008523822,0.00056995364,0.002689571,0.0022894612],"genre_scores_gemma":[0.7247313,0.000601593,0.27138537,0.00018970518,0.000111088615,0.000061016493,0.0014370625,0.00015637123,0.0013264228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996728,0.00011038595,0.00004054232,0.00005191008,0.00009317688,0.000031270138],"domain_scores_gemma":[0.9972193,0.001351212,0.00014730889,0.00060306164,0.00060700835,0.00007215586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010454276,0.00041425586,0.0004370229,0.0011919371,0.00042394578,0.000609863,0.0007157203,0.00062729896,0.0006945007],"category_scores_gemma":[0.0052448763,0.00017903003,0.00028147746,0.0011186705,0.00038838384,0.0010712623,0.0005243666,0.00068891695,0.00039098217],"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":[0.0009850367,0.00031483063,0.006303787,0.00014041277,0.00006746401,0.00025449632,0.00014943797,0.062833324,0.08038061,0.009816917,0.004275077,0.83447856],"study_design_scores_gemma":[0.00007493087,0.00023442856,0.0026354284,0.000024344154,0.000054024495,0.00042833315,0.00005316786,0.9130388,0.06876229,0.011401648,0.0032625918,0.000030013236],"about_ca_topic_score_codex":0.0009991479,"about_ca_topic_score_gemma":0.0013204537,"teacher_disagreement_score":0.0011919371,"about_ca_system_score_codex":0.00020525412,"about_ca_system_score_gemma":0.00042581558,"threshold_uncertainty_score":0.0055288076},"labels":[],"label_agreement":null},{"id":"W1991329811","doi":"10.1007/s10844-006-0242-2","title":"Genetic algorithms based approach to database vertical partition","year":2006,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Partition (number theory); Crossover; Computer science; String (physics); Cluster analysis; Algorithm; Genetic algorithm; Partition problem; Constraint (computer-aided design); Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Machine learning","score_opus":0.02254776506449425,"score_gpt":0.24721010699663734,"score_spread":0.2246623419321431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991329811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020101918,0.000248415,0.974936,0.00024397245,0.000059864244,0.000077695746,0.000060241433,0.00045684932,0.0038150374],"genre_scores_gemma":[0.3682278,0.00031545994,0.623494,0.0002047097,0.000069030415,0.0001652355,0.00022942113,0.00012145223,0.007172758],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995111,0.00013830303,0.000022146027,0.00008057088,0.00019551825,0.00005235597],"domain_scores_gemma":[0.99930716,0.00027715333,0.00003936159,0.000101622245,0.00024680965,0.000027897815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006953975,0.00038060787,0.0006520809,0.0015535236,0.000730925,0.0011548811,0.0015309084,0.0010188401,0.0028921706],"category_scores_gemma":[0.0022421062,0.0003380442,0.0006001336,0.0016956403,0.0006891694,0.0009914458,0.00076283276,0.0009125046,0.00037689504],"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":[0.000105685736,0.00014422291,0.00103942,0.000053214895,0.00007100583,0.00010056291,0.00019628029,0.6963532,0.0055828025,0.053010244,0.00261608,0.24072735],"study_design_scores_gemma":[0.000010884793,0.000021800512,0.00015834252,0.000005958064,0.000014620489,0.000027227286,0.000032663458,0.9853086,0.0010173755,0.012399821,0.0009969814,0.0000056845843],"about_ca_topic_score_codex":0.011634973,"about_ca_topic_score_gemma":0.009597778,"teacher_disagreement_score":0.011634973,"about_ca_system_score_codex":0.0012173755,"about_ca_system_score_gemma":0.0013538664,"threshold_uncertainty_score":0.02313453},"labels":[],"label_agreement":null},{"id":"W1991615886","doi":"10.1109/dcc.2007.18","title":"Bit Recycling with Prefix Codes","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Multiplicity (mathematics); Computer science; Algorithm; Gas compressor; Sequence (biology); Set (abstract data type); Task (project management); Prefix; Arithmetic; Theoretical computer science; Mathematics; Engineering","score_opus":0.011796804947878768,"score_gpt":0.2452487059259094,"score_spread":0.23345190097803062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991615886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034475032,0.0014359327,0.9449077,0.00039197915,0.00027546947,0.00021766237,0.00027222955,0.0027432789,0.015280672],"genre_scores_gemma":[0.27362552,0.0011875987,0.7023813,0.00059150625,0.00020555254,0.00047524332,0.00074108946,0.00079656014,0.01999562],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971973,0.0006675887,0.00022384827,0.0003731333,0.0011959331,0.00034226794],"domain_scores_gemma":[0.9928803,0.0024979983,0.00056664855,0.0027872447,0.0010911505,0.00017672306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016729016,0.0010228184,0.0010248994,0.002318545,0.0014501377,0.0020042802,0.0014546037,0.001451939,0.0072264695],"category_scores_gemma":[0.011527232,0.0005077116,0.00072229037,0.0029952773,0.0019992285,0.004091612,0.002969582,0.0019872824,0.00346124],"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":[0.00092230586,0.00012427628,0.0010360768,0.00041051072,0.00006692162,0.00039835332,0.00040383384,0.058219474,0.025317902,0.43144593,0.0066957846,0.47495878],"study_design_scores_gemma":[0.00014958413,0.00046847688,0.00035237864,0.0003135841,0.00010041363,0.0011150357,0.00016405938,0.40534854,0.11633276,0.4145375,0.060941353,0.00017641824],"about_ca_topic_score_codex":0.001456787,"about_ca_topic_score_gemma":0.0012759847,"teacher_disagreement_score":0.0072264695,"about_ca_system_score_codex":0.0011354722,"about_ca_system_score_gemma":0.0017998326,"threshold_uncertainty_score":0.024174929},"labels":[],"label_agreement":null},{"id":"W1992117554","doi":"10.1109/icip.2010.5651184","title":"Color maps and graphs compression","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Northern British Columbia; University of British Columbia","funders":"","keywords":"Lossless compression; Computer science; Codebook; Data compression; Wireless; Theoretical computer science; Graph; Algorithm; Telecommunications","score_opus":0.006521699402381131,"score_gpt":0.22342213111974743,"score_spread":0.2169004317173663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992117554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052914497,0.0029005315,0.9266843,0.00074693485,0.00043826783,0.000176886,0.0006408069,0.0028165125,0.012681192],"genre_scores_gemma":[0.509816,0.0035123543,0.46504778,0.00047094742,0.00031635014,0.00020932831,0.0016116564,0.00038473218,0.018630825],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995442,0.00006745115,0.000017055685,0.00005835239,0.00027064214,0.000042338856],"domain_scores_gemma":[0.9992816,0.00027237707,0.000050852508,0.00017990376,0.00019383772,0.000021507596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024550053,0.0005433241,0.00033278603,0.0016664839,0.00027589028,0.0006311433,0.0006075322,0.0004892246,0.004056599],"category_scores_gemma":[0.002025477,0.0001413015,0.00029694548,0.002275025,0.00051241025,0.0011687625,0.0006634396,0.00046703636,0.00082224107],"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":[0.00038442816,0.00007348942,0.00062885,0.00022642143,0.000042808355,0.00030311916,0.00011154407,0.070234805,0.050713312,0.042036388,0.014979981,0.8202648],"study_design_scores_gemma":[0.00007215067,0.00020897888,0.0026988327,0.00006232424,0.000049715756,0.0016787426,0.00016127828,0.71947026,0.16942976,0.052682336,0.0534147,0.000070933515],"about_ca_topic_score_codex":0.0025130145,"about_ca_topic_score_gemma":0.002228959,"teacher_disagreement_score":0.004056599,"about_ca_system_score_codex":0.0004808107,"about_ca_system_score_gemma":0.00041352084,"threshold_uncertainty_score":0.013570666},"labels":[],"label_agreement":null},{"id":"W1992151876","doi":"10.1016/j.tcs.2009.08.024","title":"Repetitions in strings: Algorithms and combinatorics","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Substring; Conjecture; Mathematics; Combinatorics on words; Combinatorics; String (physics); Compression (physics); Algorithm; Discrete mathematics; Computer science; Data structure; Word (group theory)","score_opus":0.007594207663506966,"score_gpt":0.2477842159550935,"score_spread":0.24019000829158654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992151876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071354285,0.017620178,0.86335886,0.0060987887,0.00075713434,0.00013595473,0.0006908457,0.0015000149,0.03848395],"genre_scores_gemma":[0.5472813,0.016619448,0.39785066,0.0016509197,0.003048581,0.0005103862,0.0016434307,0.0010319873,0.030363353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947733,0.0019822586,0.00046449283,0.0010362354,0.0014631585,0.00028054861],"domain_scores_gemma":[0.97504824,0.020066282,0.0011563416,0.0027190144,0.00072418,0.00028604135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030479957,0.0011070342,0.0018962881,0.0040693204,0.0021964556,0.0075235446,0.0027140845,0.003330255,0.00851416],"category_scores_gemma":[0.020909183,0.0013230754,0.0016750155,0.008522545,0.006007518,0.016244737,0.0028869307,0.0049522817,0.0023893008],"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":[0.00008104601,0.000046054338,0.0005927471,0.00024913793,0.00002920376,0.00009955083,0.0003589527,0.00679243,0.00061551365,0.92492354,0.004155209,0.06205646],"study_design_scores_gemma":[0.000011696373,0.000010920554,0.00008677458,0.000038319635,0.0000148336485,0.00016801748,0.000043076365,0.011608745,0.0005562518,0.98231125,0.005134972,0.000015107071],"about_ca_topic_score_codex":0.00060957327,"about_ca_topic_score_gemma":0.0007655031,"teacher_disagreement_score":0.00851416,"about_ca_system_score_codex":0.0019895516,"about_ca_system_score_gemma":0.0012265794,"threshold_uncertainty_score":0.028482735},"labels":[],"label_agreement":null},{"id":"W1992381397","doi":"10.1016/j.tcs.2007.03.025","title":"A note on the number of squares in a word","year":2007,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Centre National de la Recherche Scientifique","keywords":"Mathematics; Word (group theory); Combinatorics; Bounded function; String (physics); Upper and lower bounds; Word length; Least-squares function approximation; Discrete mathematics; Statistics; Computer science","score_opus":0.011050063721280442,"score_gpt":0.28660153913440206,"score_spread":0.27555147541312164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992381397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016506758,0.0364929,0.7071929,0.052683763,0.05767852,0.00009679758,0.0009824262,0.0015141746,0.12685187],"genre_scores_gemma":[0.253312,0.02505446,0.55895334,0.013801996,0.057974953,0.00045868987,0.0010238035,0.0031048283,0.08631586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918132,0.0024146563,0.0008783144,0.0019745005,0.0025185265,0.00040082328],"domain_scores_gemma":[0.9381707,0.04923726,0.0009428525,0.007304595,0.0034658394,0.0008787502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047700927,0.002216392,0.0027570417,0.0036276681,0.0032090382,0.004545402,0.004924653,0.0040999292,0.013812605],"category_scores_gemma":[0.044357818,0.0013401174,0.0022255946,0.005922333,0.013987631,0.02239667,0.0054302565,0.014244965,0.005619144],"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":[0.00033256583,0.00003475908,0.0006408528,0.00049030804,0.00003996215,0.0003635933,0.00037801324,0.0043213903,0.0020325475,0.8338708,0.058918048,0.09857699],"study_design_scores_gemma":[0.000015625403,0.000042618656,0.00024545586,0.00008713047,0.00003434628,0.00044828668,0.00008214429,0.009510547,0.0017851922,0.9238437,0.063846596,0.000058338363],"about_ca_topic_score_codex":0.001655211,"about_ca_topic_score_gemma":0.0021932037,"teacher_disagreement_score":0.013812605,"about_ca_system_score_codex":0.0020237167,"about_ca_system_score_gemma":0.0010962485,"threshold_uncertainty_score":0.046207726},"labels":[],"label_agreement":null},{"id":"W1992800733","doi":"10.1016/j.jda.2012.03.003","title":"More results on overlapping squares","year":2012,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Computer science; Least-squares function approximation; Combinatorics; Algorithm; Mathematics; Statistics; Mathematical physics","score_opus":0.02257373619451643,"score_gpt":0.29064074069788065,"score_spread":0.26806700450336424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992800733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011380413,0.0062886407,0.9217164,0.0029660482,0.0019370005,0.000049411865,0.00036032038,0.0008094971,0.054492295],"genre_scores_gemma":[0.1971853,0.0073593245,0.67162055,0.0041238666,0.005129189,0.000258708,0.0017946329,0.0028355573,0.10969284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99759775,0.00063143374,0.00012208188,0.00054741674,0.00093768135,0.00016355005],"domain_scores_gemma":[0.99347323,0.0029541953,0.00022250332,0.0021349106,0.0009542213,0.00026091287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002109768,0.0020025736,0.0022875431,0.001875589,0.0012324871,0.0015311175,0.0022690496,0.001649246,0.0322426],"category_scores_gemma":[0.011807416,0.0010220784,0.0017698937,0.0048188474,0.0020917482,0.0063658594,0.004755394,0.005767488,0.0058377855],"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":[0.00039432404,0.0002124118,0.0010269003,0.00089285424,0.00022771093,0.00027720162,0.00036045408,0.03567548,0.010024232,0.42586285,0.0497606,0.475285],"study_design_scores_gemma":[0.00007482262,0.0001282428,0.0013905703,0.00014558111,0.00016330938,0.0006247775,0.0001664248,0.12902531,0.0072737965,0.74807656,0.112844914,0.00008571276],"about_ca_topic_score_codex":0.0020954062,"about_ca_topic_score_gemma":0.0024252362,"teacher_disagreement_score":0.0322426,"about_ca_system_score_codex":0.0008616692,"about_ca_system_score_gemma":0.0006536149,"threshold_uncertainty_score":0.107862234},"labels":[],"label_agreement":null},{"id":"W1993012473","doi":"10.1007/s11538-013-9906-6","title":"A Note on Probabilistic Models over Strings: The Linear Algebra Approach","year":2013,"lang":"en","type":"preprint","venue":"Bulletin of Mathematical Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Probabilistic logic; Graphical model; Inference; Normalization (sociology); Bayesian inference; Theoretical computer science; Linear algebra; Computer science; Class (philosophy); Algebra over a field; Algorithm; Bayesian probability; Mathematics; Artificial intelligence; Pure mathematics","score_opus":0.03421594040448571,"score_gpt":0.271140982175137,"score_spread":0.23692504177065127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993012473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025102298,0.013164894,0.92749256,0.031078499,0.0035558876,0.000032127005,0.00045016073,0.0002907748,0.021424945],"genre_scores_gemma":[0.23938362,0.04489485,0.5907731,0.021726346,0.052013457,0.0005191032,0.0013078465,0.0012996783,0.04808191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935893,0.0027314178,0.00045857887,0.0010313593,0.0018752961,0.00031403097],"domain_scores_gemma":[0.9716647,0.022905007,0.0006140178,0.0031566878,0.0011493427,0.0005101131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076777376,0.0017040719,0.0030677244,0.0032909408,0.00233068,0.0072309324,0.0046304786,0.0046634558,0.0108947605],"category_scores_gemma":[0.0226693,0.0013557348,0.0047679283,0.0054455423,0.011068626,0.025564779,0.0063994955,0.01714036,0.002965626],"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":[0.000014229558,0.000016479207,0.00006367157,0.000075862714,0.000023433204,0.00004145034,0.000063114596,0.002258878,0.00014506814,0.9823988,0.005121112,0.0097778225],"study_design_scores_gemma":[0.0000025853299,0.000005563364,0.000016160177,0.000011658125,0.000004890175,0.000022763916,0.000006601317,0.005136679,0.000059774506,0.99035794,0.004363918,0.000011483525],"about_ca_topic_score_codex":0.0021801195,"about_ca_topic_score_gemma":0.0016363598,"teacher_disagreement_score":0.0108947605,"about_ca_system_score_codex":0.0023074546,"about_ca_system_score_gemma":0.0017684377,"threshold_uncertainty_score":0.040604234},"labels":[],"label_agreement":null},{"id":"W1993117718","doi":"10.1007/s00453-014-9952-y","title":"Randomized Fixed-Parameter Algorithms for the Closest String Problem","year":2014,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Randomized algorithm; Theory of computation; Algorithm; Hamming distance; Integer (computer science); Mathematics; String (physics); Context (archaeology); Set (abstract data type); Hamming code; Combinatorics; Discrete mathematics; Computer science","score_opus":0.022684086345454428,"score_gpt":0.2687700531542797,"score_spread":0.24608596680882527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993117718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027707307,0.0020344264,0.9552128,0.0037785464,0.00045599116,0.0002813248,0.0008134276,0.0024240674,0.0072920816],"genre_scores_gemma":[0.31112397,0.0013713948,0.6705637,0.0012896128,0.00093047495,0.0014336065,0.003045156,0.0013029281,0.008939194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9895503,0.0043193605,0.0006739929,0.0026150022,0.0019374128,0.00090390025],"domain_scores_gemma":[0.94558674,0.040049676,0.002001926,0.009732062,0.001590838,0.0010386811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070406664,0.0024849134,0.0042229905,0.0035191018,0.0025855629,0.005835975,0.00886225,0.006337318,0.015692893],"category_scores_gemma":[0.05517998,0.0016354892,0.0025546777,0.0069592404,0.004740178,0.016656954,0.008058682,0.009960596,0.004025033],"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":[0.0033219315,0.0013239987,0.0023075768,0.0009330912,0.00039183843,0.00020894114,0.00048856385,0.36766264,0.0036236763,0.2632047,0.038082857,0.31845018],"study_design_scores_gemma":[0.0006310727,0.00016879276,0.00025039577,0.00008409577,0.000081851555,0.00017239526,0.000107340944,0.5439091,0.0020360013,0.44952682,0.002966349,0.00006582303],"about_ca_topic_score_codex":0.0021788338,"about_ca_topic_score_gemma":0.0029639532,"teacher_disagreement_score":0.015692893,"about_ca_system_score_codex":0.004098329,"about_ca_system_score_gemma":0.0055443905,"threshold_uncertainty_score":0.052497923},"labels":[],"label_agreement":null},{"id":"W1993150073","doi":"10.1007/s00224-001-0008-8","title":"A Polynomial-Time Algorithm for Max-Min Partitioning of Ladders","year":2001,"lang":"en","type":"article","venue":"Theory of Computing Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Row; Combinatorics; Time complexity; Grid; Vertex (graph theory); Partition (number theory); Mathematics; Minimum weight; Dynamic programming; Running time; Graph; Algorithm; Discrete mathematics; Computer science","score_opus":0.015498261918100999,"score_gpt":0.24527259525212397,"score_spread":0.22977433333402297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993150073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028679797,0.00036833208,0.9597318,0.0003494949,0.00006956494,0.00024233545,0.0006428284,0.00308266,0.006833078],"genre_scores_gemma":[0.115151174,0.00018872514,0.87726283,0.00012123058,0.000030658794,0.00016638901,0.0015269449,0.0004139647,0.0051381188],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993654,0.000115110946,0.00005208903,0.00013012394,0.00019279387,0.00014451648],"domain_scores_gemma":[0.99859935,0.00057207845,0.00010122761,0.000369942,0.00021009923,0.00014733433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006863761,0.0010228378,0.0012958414,0.0014228995,0.0010238258,0.0016817973,0.0021352933,0.0009001164,0.0109538],"category_scores_gemma":[0.0029631741,0.0009078005,0.0008496613,0.0021808199,0.0007507213,0.002729017,0.0025308272,0.0014039121,0.0029425118],"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":[0.0009703039,0.00026693795,0.0009888608,0.0006865377,0.000080796264,0.00010417613,0.00043601534,0.0768435,0.028497929,0.058370173,0.027187938,0.8055669],"study_design_scores_gemma":[0.00037283116,0.00034881278,0.0010900914,0.00013719917,0.00010221362,0.00037366335,0.00047732785,0.68312705,0.024989545,0.2640815,0.024823306,0.00007652541],"about_ca_topic_score_codex":0.0023506964,"about_ca_topic_score_gemma":0.004642892,"teacher_disagreement_score":0.0109538,"about_ca_system_score_codex":0.0013155888,"about_ca_system_score_gemma":0.0014672462,"threshold_uncertainty_score":0.03664416},"labels":[],"label_agreement":null},{"id":"W1993294649","doi":"10.1016/j.tcs.2013.09.031","title":"Succinct encoding of arbitrary graphs","year":2013,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Upper and lower bounds; Mathematics; Constant (computer programming); Vertex (graph theory); Discrete mathematics; Multiplicative function; Graph; Computer science","score_opus":0.007668647300515955,"score_gpt":0.227461928451841,"score_spread":0.21979328115132504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993294649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14191024,0.0018556596,0.80035144,0.006337172,0.0006253127,0.0002532426,0.006450955,0.004318175,0.037897926],"genre_scores_gemma":[0.73228115,0.0015206657,0.2398749,0.0012317199,0.00027715784,0.00037305336,0.008138641,0.0010135374,0.015289122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871945,0.0003725681,0.000094867006,0.00018148255,0.000467499,0.00016413152],"domain_scores_gemma":[0.994163,0.0026865085,0.0002685763,0.0021190187,0.00061123696,0.00015159546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008481931,0.0007056547,0.0006849882,0.0009860233,0.0006372131,0.002060495,0.0015570429,0.0010741027,0.0056060427],"category_scores_gemma":[0.0063541676,0.00043496373,0.0005192358,0.002075113,0.0011739128,0.0049177944,0.0024029477,0.0025144778,0.0010139665],"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":[0.0009182695,0.00026461246,0.0006035267,0.00038525902,0.000036227975,0.00040084962,0.00055596465,0.06865688,0.0091003105,0.7017086,0.025409073,0.19196042],"study_design_scores_gemma":[0.000097736156,0.00005927348,0.00019038208,0.00011108797,0.0000363563,0.00018601835,0.00011910239,0.12885801,0.010382502,0.84321135,0.016719958,0.000028125603],"about_ca_topic_score_codex":0.0013793455,"about_ca_topic_score_gemma":0.0027505804,"teacher_disagreement_score":0.0056060427,"about_ca_system_score_codex":0.001374887,"about_ca_system_score_gemma":0.0015019965,"threshold_uncertainty_score":0.018754125},"labels":[],"label_agreement":null},{"id":"W1993340924","doi":"10.1002/rsa.20067","title":"Probabilistic behavior of asymmetric level compressed tries","year":2005,"lang":"en","type":"article","venue":"Random Structures and Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Combinatorics; Bernoulli's principle; Binary logarithm; Log-log plot; Entropy (arrow of time); Physics; Quantum mechanics","score_opus":0.02344448903966029,"score_gpt":0.2618566098971203,"score_spread":0.23841212085746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993340924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.857797,0.00039817617,0.12819514,0.0009983787,0.000045783207,0.00006515041,0.00042306256,0.00068353827,0.011393674],"genre_scores_gemma":[0.9940813,0.00007683158,0.0041845813,0.000085737905,0.000032915643,0.00004629383,0.00016393956,0.000062475905,0.0012658113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986492,0.00043486198,0.000057296253,0.00015818766,0.0004358086,0.0002647175],"domain_scores_gemma":[0.9822192,0.011771475,0.0021422752,0.0014328843,0.0015631769,0.0008710456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019379329,0.0002800705,0.0006885605,0.0014628578,0.0007002125,0.0014571798,0.0011440673,0.0009353394,0.003931697],"category_scores_gemma":[0.027875423,0.0004228935,0.00035588807,0.0009051278,0.0021557452,0.0027275237,0.0018000879,0.0012055575,0.0004870981],"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":[0.0007936137,0.000105091276,0.009144561,0.0001971198,0.00006904343,0.00092353404,0.0006836118,0.22175264,0.013505712,0.72879636,0.0044422676,0.019586414],"study_design_scores_gemma":[0.00003894965,0.000070091584,0.0015267222,0.00003128448,0.000017291404,0.0004346604,0.00010257375,0.79624104,0.0031053456,0.19766355,0.00073594716,0.000032470612],"about_ca_topic_score_codex":0.00070123625,"about_ca_topic_score_gemma":0.0005478577,"teacher_disagreement_score":0.003931697,"about_ca_system_score_codex":0.0011954039,"about_ca_system_score_gemma":0.00058433984,"threshold_uncertainty_score":0.013152838},"labels":[],"label_agreement":null},{"id":"W1993831977","doi":"10.1145/1242524.1242529","title":"Estimating the selectivity of approximate string queries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"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":"Substring; String (physics); Estimator; Approximate string matching; Computer science; Inverse; String searching algorithm; String metric; Algorithm; String kernel; Data structure; Mathematics; Statistics; Pattern matching; Artificial intelligence","score_opus":0.025787043361268296,"score_gpt":0.2745853299599472,"score_spread":0.24879828659867892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993831977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42199904,0.000864077,0.5711316,0.0005590445,0.00004554847,0.00014139953,0.0011007761,0.0019577881,0.00220072],"genre_scores_gemma":[0.88128126,0.00048353194,0.11513948,0.00014096241,0.00011212254,0.000121461126,0.0018350474,0.00013081155,0.00075532164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99323285,0.0016519026,0.0006822789,0.0007519881,0.0031247165,0.0005562415],"domain_scores_gemma":[0.96677446,0.023671227,0.002313762,0.0038436044,0.0030561455,0.00034081738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050851656,0.00050607964,0.001518626,0.0030925204,0.0006027263,0.0021214574,0.0012139954,0.0012437903,0.00093852007],"category_scores_gemma":[0.04692527,0.0004425911,0.00041327867,0.0035054286,0.00088486134,0.004911946,0.0021099458,0.0009016392,0.00054644205],"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":[0.0030186584,0.00030223164,0.111643985,0.00034670712,0.00017960531,0.00066019344,0.00074404513,0.27105168,0.035211578,0.030576503,0.0064391927,0.5398257],"study_design_scores_gemma":[0.000034244313,0.000108372486,0.005065416,0.00001775943,0.000018641369,0.00043627655,0.00024976436,0.96380967,0.015073764,0.013992233,0.001168167,0.000025656904],"about_ca_topic_score_codex":0.0022313942,"about_ca_topic_score_gemma":0.0017145829,"teacher_disagreement_score":0.0050851656,"about_ca_system_score_codex":0.0010693168,"about_ca_system_score_gemma":0.0013338628,"threshold_uncertainty_score":0.026893258},"labels":[],"label_agreement":null},{"id":"W1995186768","doi":"10.1016/j.tcs.2010.10.030","title":"Succinct representation of dynamic trees","year":2010,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Node (physics); Tree (set theory); Computer science; Constant (computer programming); Binary tree; Combinatorics; Enhanced Data Rates for GSM Evolution; Logarithm; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.006760893345757082,"score_gpt":0.2726541615227393,"score_spread":0.2658932681769822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995186768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044336777,0.0008943327,0.934008,0.0010740142,0.0002276512,0.00012229693,0.0040910034,0.0021347327,0.013111203],"genre_scores_gemma":[0.54674965,0.0015682462,0.42465052,0.00047591413,0.00023262142,0.00038936367,0.010583298,0.0008573361,0.014492963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903023,0.00018253029,0.00009039146,0.00014391604,0.00044074564,0.00011213933],"domain_scores_gemma":[0.9972806,0.0009995556,0.00019648002,0.00092532515,0.0004976378,0.000100376776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005714148,0.00056445977,0.0006747845,0.0015738913,0.00051903987,0.00248941,0.0014929092,0.0011288008,0.008175014],"category_scores_gemma":[0.005117015,0.00043288415,0.00043802222,0.0029205699,0.0007985876,0.004754559,0.001946054,0.0019411203,0.0017758919],"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":[0.00047104066,0.00016005516,0.00057068205,0.00035488143,0.000027559154,0.00039074075,0.00054019963,0.08332079,0.009984559,0.6435267,0.018831184,0.24182172],"study_design_scores_gemma":[0.00005881873,0.000064007465,0.00022513703,0.0001262767,0.000028247869,0.00032948676,0.00015094904,0.29116318,0.0077139777,0.6707683,0.02933673,0.000034870387],"about_ca_topic_score_codex":0.0010791112,"about_ca_topic_score_gemma":0.0020328483,"teacher_disagreement_score":0.008175014,"about_ca_system_score_codex":0.00091519376,"about_ca_system_score_gemma":0.00086734485,"threshold_uncertainty_score":0.02734816},"labels":[],"label_agreement":null},{"id":"W1995913408","doi":"10.1145/1989323.1989405","title":"Efficient diversity-aware search","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","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":"University of Toronto","funders":"","keywords":"Computer science; Diversity (politics); Political science","score_opus":0.05953039391184662,"score_gpt":0.23974329367621158,"score_spread":0.18021289976436497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995913408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062139742,0.0028549056,0.92539936,0.00053261046,0.00008241242,0.00012079694,0.0003039973,0.0010744062,0.0074916957],"genre_scores_gemma":[0.6315117,0.0012130822,0.3605227,0.0002444928,0.00023286746,0.00015150793,0.0008164775,0.00016642208,0.0051407423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978497,0.00064781593,0.00013065846,0.0003582713,0.0007699764,0.00024368253],"domain_scores_gemma":[0.99632025,0.0020341284,0.00020293899,0.00089502597,0.0004305258,0.0001170166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012892005,0.00073037256,0.0017787386,0.001927261,0.0009470563,0.0018215862,0.0016491329,0.0015363898,0.0026749237],"category_scores_gemma":[0.008033267,0.00048749565,0.00059277663,0.0033266512,0.0007810917,0.0035243845,0.0024493062,0.0009467004,0.0011561426],"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":[0.00076917605,0.0003170896,0.0024488615,0.000418714,0.00016941388,0.0003330974,0.00038988848,0.32205597,0.02642584,0.058562677,0.015178763,0.5729305],"study_design_scores_gemma":[0.00007741768,0.00016285526,0.00048187305,0.00002242259,0.00004882169,0.00044957845,0.00011073972,0.91811377,0.0047555943,0.07088101,0.0048693195,0.000026651393],"about_ca_topic_score_codex":0.001062407,"about_ca_topic_score_gemma":0.0020373894,"teacher_disagreement_score":0.0026749237,"about_ca_system_score_codex":0.0006830329,"about_ca_system_score_gemma":0.0013429072,"threshold_uncertainty_score":0.0089485645},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007639334,0.4490373,0.4988672,0.0047662444,0.0045320923,0.00042991972,0.0024528478,0.0024000013,0.029875135],"genre_scores_gemma":[0.0650301,0.57276493,0.31006396,0.0029975777,0.01037024,0.00084077806,0.0122805955,0.00058977836,0.025062056],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731183,0.0005059847,0.00030691308,0.0004640861,0.0012614591,0.00014978861],"domain_scores_gemma":[0.9958704,0.0019915982,0.00022092533,0.00041839384,0.0013665279,0.00013205296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021274185,0.0011828121,0.002000881,0.007935201,0.0009974279,0.0029176234,0.0019952045,0.001630756,0.007648352],"category_scores_gemma":[0.007987824,0.00046307655,0.0012903546,0.015224217,0.0006779229,0.005571523,0.0012108363,0.0016692892,0.007023884],"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":[0.00006768613,0.00006738979,0.0012495228,0.0010722763,0.000043310654,0.00006980303,0.000060388236,0.0037803745,0.0008701941,0.009171241,0.029544277,0.9540035],"study_design_scores_gemma":[0.000041220737,0.00034057643,0.0048810244,0.0017644265,0.00012143812,0.0019636275,0.00031133002,0.10993775,0.0054537226,0.09812224,0.77692693,0.00013581268],"about_ca_topic_score_codex":0.0036233652,"about_ca_topic_score_gemma":0.0020263956,"teacher_disagreement_score":0.007935201,"about_ca_system_score_codex":0.0010716435,"about_ca_system_score_gemma":0.0019881253,"threshold_uncertainty_score":0.025586247},"labels":[],"label_agreement":null},{"id":"W1997913214","doi":"10.1145/1283900.1283918","title":"Compressed lossless texture representation and caching","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lossy compression; Lossless compression; Texture compression; Computer science; Data compression; Image compression; Data compression ratio; Context-adaptive binary arithmetic coding; Algorithm; Random access; Artificial intelligence; Computer vision; Theoretical computer science; Image processing; Image (mathematics)","score_opus":0.0077474790938919765,"score_gpt":0.23158731630351878,"score_spread":0.2238398372096268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997913214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056571554,0.0021993183,0.9180816,0.0006177368,0.00031357163,0.00014443598,0.0009790356,0.0034835977,0.017609112],"genre_scores_gemma":[0.6504761,0.001902736,0.31710234,0.0004490523,0.00021729688,0.00019235196,0.0025526143,0.00043712664,0.026670353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964714,0.00004228793,0.00001436356,0.000040464256,0.00020032722,0.000055384146],"domain_scores_gemma":[0.99947053,0.00009612453,0.000037653645,0.00023954037,0.00013071265,0.00002549754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027206147,0.00038751212,0.00065661874,0.0008597317,0.00033187418,0.0012606069,0.0013631294,0.00070175226,0.004417579],"category_scores_gemma":[0.0014247965,0.00018445028,0.00029677426,0.002107697,0.0004592271,0.0016957604,0.00068670657,0.0005062857,0.0009634317],"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":[0.0011790199,0.0002016269,0.0011750406,0.0003709045,0.00007419455,0.0011166526,0.00023621607,0.16154484,0.10089514,0.15074594,0.036327504,0.5461329],"study_design_scores_gemma":[0.000090346824,0.000097389995,0.0006615108,0.000035066783,0.00003424525,0.00067845744,0.000055220167,0.89778256,0.04008786,0.036398344,0.024029966,0.00004904938],"about_ca_topic_score_codex":0.0024988914,"about_ca_topic_score_gemma":0.0032198676,"teacher_disagreement_score":0.004417579,"about_ca_system_score_codex":0.00073057646,"about_ca_system_score_gemma":0.00051309256,"threshold_uncertainty_score":0.014778256},"labels":[],"label_agreement":null},{"id":"W1998452243","doi":"10.1504/ijwgs.2008.018501","title":"Parallel lossless data compression using the Burrows-Wheeler Transform","year":2008,"lang":"en","type":"article","venue":"International Journal of Web and Grid Services","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Computer science; Parallel computing; Lossless compression; Speedup; Task parallelism; Data compression; Parallelism (grammar); Algorithm","score_opus":0.04884866097432334,"score_gpt":0.302503839330847,"score_spread":0.2536551783565237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998452243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02162966,0.00031964152,0.97387606,0.00013186822,0.00005435945,0.000082679515,0.00006180988,0.0017902388,0.0020536997],"genre_scores_gemma":[0.12791659,0.00046438837,0.86647725,0.00008821792,0.00004483792,0.0001434429,0.00032701922,0.00026382055,0.0042743944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995621,0.000041712232,0.000024286805,0.000048021655,0.00028111847,0.000042726013],"domain_scores_gemma":[0.9995602,0.00014905506,0.000053303153,0.00011756249,0.00010276637,0.000017186878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051702326,0.0005571465,0.00056615134,0.0010287106,0.00043652952,0.0009970198,0.000981436,0.00046517048,0.002230403],"category_scores_gemma":[0.0016406307,0.00022050562,0.00038784734,0.0013574053,0.0006080339,0.0015556336,0.0007369207,0.0006580697,0.001321181],"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":[0.00051464775,0.00019346699,0.0009800125,0.00027106598,0.00006381306,0.00025794207,0.00023730534,0.1288766,0.108369485,0.045553245,0.004645812,0.71003664],"study_design_scores_gemma":[0.00009878236,0.00015170674,0.00040715738,0.000020066442,0.000021878224,0.0003398185,0.00006548571,0.85686386,0.11537605,0.014821495,0.0118027385,0.00003103464],"about_ca_topic_score_codex":0.001962516,"about_ca_topic_score_gemma":0.001978338,"teacher_disagreement_score":0.002230403,"about_ca_system_score_codex":0.0004736466,"about_ca_system_score_gemma":0.0008357821,"threshold_uncertainty_score":0.0074614286},"labels":[],"label_agreement":null},{"id":"W1998674287","doi":"10.1016/j.tcs.2008.04.020","title":"How many runs can a string contain?","year":2008,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Combinatorics; Conjecture; String (physics); Mathematics; Upper and lower bounds; Repetition (rhetorical device); Discrete mathematics; Data structure; Computer science; Mathematical analysis; Philosophy; Mathematical physics","score_opus":0.013842654129992698,"score_gpt":0.22579789981122944,"score_spread":0.21195524568123675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998674287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5531233,0.008518019,0.35870466,0.018196499,0.0015509432,0.00019720334,0.0052770884,0.007866168,0.04656611],"genre_scores_gemma":[0.8709159,0.0028600285,0.10191161,0.00090825267,0.0008592843,0.00016057778,0.004641952,0.0018146199,0.015927749],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99621236,0.0006225216,0.00043313077,0.0009706903,0.0013302262,0.00043117025],"domain_scores_gemma":[0.9723164,0.015981387,0.0014483884,0.0065608383,0.0028151665,0.00087777845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002682886,0.00081349566,0.0016940718,0.0022102662,0.0017120145,0.0043691387,0.0017810591,0.002983297,0.007565281],"category_scores_gemma":[0.038018275,0.0008577409,0.0010214526,0.002716662,0.0021158794,0.017259067,0.0018831454,0.002009226,0.004066509],"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":[0.0031572294,0.0004536033,0.04759991,0.0010627948,0.00043567517,0.001280291,0.0014910816,0.040551033,0.023882845,0.14362563,0.030569736,0.7058902],"study_design_scores_gemma":[0.00009386181,0.00032569005,0.009323772,0.000494472,0.0004588789,0.0036872346,0.002342713,0.20933914,0.052052733,0.6644328,0.057181392,0.00026725972],"about_ca_topic_score_codex":0.0009259926,"about_ca_topic_score_gemma":0.001046472,"teacher_disagreement_score":0.007565281,"about_ca_system_score_codex":0.000886045,"about_ca_system_score_gemma":0.0011801848,"threshold_uncertainty_score":0.02530843},"labels":[],"label_agreement":null},{"id":"W1998730018","doi":"10.5555/1873601.1873616","title":"Counting inversions, offline orthogonal range counting, and related problems","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Permutation (music); Range (aeronautics); Simple (philosophy); Upper and lower bounds; Rank (graph theory); Trie; Mathematics; Counting problem; Data structure; Running time; Time complexity; Algorithm; Binary logarithm; Computer science; Discrete mathematics; Physics; Mathematical analysis","score_opus":0.00895020109406776,"score_gpt":0.21617184992002106,"score_spread":0.2072216488259533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998730018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06717703,0.0012665442,0.9039452,0.0025903573,0.00026860076,0.0003349506,0.0011867214,0.0051002176,0.018130437],"genre_scores_gemma":[0.29572055,0.0010233935,0.6803227,0.0010252672,0.0006415346,0.0006477028,0.0031521537,0.0012654614,0.016201211],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951633,0.0009613095,0.0003612375,0.001146176,0.0015513469,0.0008166281],"domain_scores_gemma":[0.98706204,0.006439657,0.001210491,0.0039917873,0.0009416055,0.000354443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001815135,0.0019040446,0.0021987536,0.0023215848,0.0016961019,0.0031222724,0.0037668594,0.002077999,0.011741097],"category_scores_gemma":[0.015315449,0.0009180221,0.0014875804,0.0056353714,0.002515058,0.012680593,0.004442342,0.0034360935,0.003619728],"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":[0.0011195161,0.000671997,0.0045026364,0.00077776576,0.00008555293,0.00040131214,0.00064506236,0.060134914,0.012972511,0.193457,0.032686166,0.69254553],"study_design_scores_gemma":[0.0002922159,0.00033534618,0.0013935198,0.00010503167,0.000110670524,0.0012083256,0.00055125577,0.42199805,0.023279594,0.53044736,0.020132083,0.00014651637],"about_ca_topic_score_codex":0.0027841309,"about_ca_topic_score_gemma":0.002992695,"teacher_disagreement_score":0.011741097,"about_ca_system_score_codex":0.001670325,"about_ca_system_score_gemma":0.0022353448,"threshold_uncertainty_score":0.03927791},"labels":[],"label_agreement":null},{"id":"W1998964210","doi":"10.1016/j.ins.2011.02.002","title":"Reordering columns for smaller indexes","year":2011,"lang":"en","type":"article","venue":"Information Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université du Québec à Montréal","funders":"","keywords":"Sorting; Column (typography); Cardinality (data modeling); Bitmap; Table (database); sort; Computer science; Projection (relational algebra); Algorithm; Mathematics; Arithmetic; Database; Computer graphics (images)","score_opus":0.09889330094511244,"score_gpt":0.2681839175362711,"score_spread":0.16929061659115863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998964210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18873054,0.0052498477,0.7346755,0.003651333,0.006779814,0.0012481342,0.008116968,0.02015158,0.031396344],"genre_scores_gemma":[0.13165064,0.0013108776,0.8224975,0.0009515088,0.00087292964,0.00023597316,0.008185465,0.0027016916,0.031593494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986506,0.0001763561,0.00024079012,0.00019264936,0.00055011566,0.0001894997],"domain_scores_gemma":[0.99302906,0.001686921,0.00031645127,0.0030942021,0.0016515274,0.0002218886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006994642,0.0015361923,0.0014083366,0.0036478823,0.0013546209,0.0031998053,0.001299883,0.00081744307,0.028816983],"category_scores_gemma":[0.0072274855,0.00058898196,0.0009119213,0.007089997,0.0008394716,0.0037108122,0.0013171692,0.0017311672,0.009513365],"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":[0.0010310068,0.00043067956,0.001379704,0.0004690512,0.00009070709,0.00045950542,0.00027959942,0.0054461355,0.09906585,0.018140351,0.048654,0.8245535],"study_design_scores_gemma":[0.00046058086,0.0012411945,0.0042646863,0.00036333626,0.00038119275,0.00230461,0.001255268,0.13094947,0.4782349,0.09274049,0.287547,0.00025731616],"about_ca_topic_score_codex":0.003059602,"about_ca_topic_score_gemma":0.007322508,"teacher_disagreement_score":0.028816983,"about_ca_system_score_codex":0.0006743171,"about_ca_system_score_gemma":0.0021398694,"threshold_uncertainty_score":0.09640235},"labels":[],"label_agreement":null},{"id":"W1999003664","doi":"10.1145/2735629","title":"A General SIMD-Based Approach to Accelerating Compression Algorithms","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"SIMD; Computer science; Data compression; Decoding methods; Algorithm; Compression ratio; Compression (physics); Parallel computing; Encoding (memory); Group (periodic table); Artificial intelligence","score_opus":0.06561336432163029,"score_gpt":0.2778084545504484,"score_spread":0.2121950902288181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999003664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017337749,0.0012097184,0.96556836,0.00047986011,0.00027190917,0.00018222297,0.0003447546,0.0053492435,0.009256084],"genre_scores_gemma":[0.16068634,0.00084020296,0.8295766,0.00054768025,0.00018671594,0.0003296504,0.0010695718,0.00036159655,0.006401673],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990621,0.000110128465,0.000081319886,0.00018884716,0.00047581556,0.00008178864],"domain_scores_gemma":[0.99905354,0.00017183517,0.000051103594,0.0003715615,0.00031635357,0.000035646197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006944527,0.0010171047,0.00058019045,0.001695532,0.0006597397,0.0014580507,0.0018619107,0.00066594064,0.004925209],"category_scores_gemma":[0.0022523776,0.0003539948,0.0006340732,0.0026376771,0.0010164818,0.002517666,0.0014955563,0.0013758261,0.0022020356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007490219,0.0002369484,0.0022461389,0.00044651193,0.00009802285,0.00023276552,0.00025620722,0.1120053,0.08621914,0.11180464,0.021067034,0.6646382],"study_design_scores_gemma":[0.00013403052,0.0003710444,0.0004812573,0.000054703378,0.000041039413,0.00046097228,0.000084473955,0.7805342,0.1288283,0.044355858,0.044590868,0.00006329016],"about_ca_topic_score_codex":0.0017173568,"about_ca_topic_score_gemma":0.0023498847,"teacher_disagreement_score":0.004925209,"about_ca_system_score_codex":0.0010834788,"about_ca_system_score_gemma":0.0014404717,"threshold_uncertainty_score":0.016476512},"labels":[],"label_agreement":null},{"id":"W1999806580","doi":"10.1145/1005813.1041511","title":"A performance study of data layout techniques for improving data locality in refinement-based pathfinding","year":2004,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Center for Advanced Study, University of Illinois at Urbana-Champaign; Natural Sciences and Engineering Research Council of Canada","keywords":"Locality; Computer science; Compiler; Locality of reference; Exploit; CAS latency; Pathfinding; Data structure; Parallel computing; Cache; Optimizing compiler; Theoretical computer science; Programming language; Memory controller; Operating system; Graph","score_opus":0.09430588576968296,"score_gpt":0.3590821632634274,"score_spread":0.26477627749374444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999806580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6191695,0.0024829127,0.3677601,0.00033160162,0.000061501574,0.00035831117,0.00022927388,0.0054226704,0.0041841054],"genre_scores_gemma":[0.67379725,0.00054109655,0.32370543,0.00006274613,0.000020363866,0.00010908869,0.00031125027,0.00032288113,0.0011298473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980585,0.00075106,0.00015194905,0.00021436856,0.0006678276,0.00015623808],"domain_scores_gemma":[0.9866946,0.008410057,0.000942233,0.0023225388,0.0014995293,0.00013097307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020678225,0.0006432238,0.00048241086,0.0012270486,0.00047948436,0.000529033,0.001180277,0.0005581189,0.0012749649],"category_scores_gemma":[0.012682282,0.000332167,0.00044345701,0.002907061,0.0007395444,0.0018383904,0.0005015016,0.00054947234,0.00036100348],"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":[0.0016432123,0.000760647,0.008450808,0.0006928845,0.00016959742,0.00014880359,0.0005764143,0.17026037,0.14615688,0.0063652582,0.0026968308,0.66207826],"study_design_scores_gemma":[0.00036426095,0.0034550298,0.0068708844,0.000034456156,0.00017365583,0.00065973325,0.0001802277,0.7223709,0.25804815,0.0027893335,0.004961078,0.00009230227],"about_ca_topic_score_codex":0.003472675,"about_ca_topic_score_gemma":0.004343186,"teacher_disagreement_score":0.003472675,"about_ca_system_score_codex":0.0009782149,"about_ca_system_score_gemma":0.000984444,"threshold_uncertainty_score":0.010935783},"labels":[],"label_agreement":null},{"id":"W2000098237","doi":"10.1007/s002360050001","title":"Querying sequence databases with transducers","year":2000,"lang":"en","type":"article","venue":"Acta Informatica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Datalog; Computer science; Ackermann function; Subroutine; Theory of computation; Theoretical computer science; Hierarchy; Programming language; Sequence (biology); Database; P; Query language; Workstation; Transducer; Time complexity; Algorithm; Mathematics","score_opus":0.026321469654806775,"score_gpt":0.25187368100628554,"score_spread":0.22555221135147877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000098237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0704647,0.0013205128,0.9087593,0.001459317,0.00021153034,0.00014917861,0.0031087045,0.010925627,0.0036010928],"genre_scores_gemma":[0.54970384,0.001711243,0.43199223,0.00081180036,0.0003010142,0.00036221056,0.00953503,0.0013815024,0.0042010886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946826,0.0013076131,0.000847019,0.0009031165,0.0020281249,0.000231546],"domain_scores_gemma":[0.98557496,0.01011354,0.00040362845,0.0024420351,0.001252808,0.000213032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028850136,0.0009708696,0.00212637,0.004277317,0.0009631425,0.0049363337,0.0020102703,0.0025796904,0.0033851792],"category_scores_gemma":[0.021847224,0.0010513954,0.001749378,0.006537326,0.001852539,0.011695066,0.0034993594,0.0020354774,0.0018100567],"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":[0.0021983138,0.0004377683,0.007917009,0.0015434622,0.00041388805,0.0016883725,0.0021676049,0.0926416,0.04412044,0.28672206,0.025404362,0.53474516],"study_design_scores_gemma":[0.00011944233,0.00016496284,0.0005637764,0.00013606339,0.00017657198,0.0009291783,0.00063169753,0.510396,0.044734467,0.42190766,0.02014661,0.00009356567],"about_ca_topic_score_codex":0.0022701079,"about_ca_topic_score_gemma":0.0019968324,"teacher_disagreement_score":0.0049363337,"about_ca_system_score_codex":0.0011234061,"about_ca_system_score_gemma":0.001574625,"threshold_uncertainty_score":0.015257597},"labels":[],"label_agreement":null},{"id":"W2001159324","doi":"10.1109/fpl.2012.6339141","title":"K-means implementation on FPGA for high-dimensional data using triangle inequality","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"MNIST database; Computer science; Cluster analysis; Triangle inequality; Benchmark (surveying); Software; Curse of dimensionality; Field-programmable gate array; Overhead (engineering); Speedup; Parallel computing; Algorithm; Computer hardware; Computer engineering; Artificial neural network; Mathematics; Artificial intelligence","score_opus":0.18680240761490535,"score_gpt":0.40290071200032146,"score_spread":0.2160983043854161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001159324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040280357,0.0002586002,0.93655854,0.00026120868,0.00011864469,0.00009446297,0.00018488674,0.00965949,0.012583867],"genre_scores_gemma":[0.42665648,0.0002173832,0.564441,0.00016319763,0.000036917027,0.0001510551,0.00053205685,0.00026448557,0.007537418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996996,0.000038833015,0.000025865727,0.000048588845,0.00013654892,0.000050590505],"domain_scores_gemma":[0.99970335,0.000077960976,0.00002115771,0.000063187734,0.00012146416,0.000012867617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002172942,0.00045130868,0.0002672269,0.0005222126,0.00032793242,0.00064580893,0.0010606243,0.0003145645,0.012323302],"category_scores_gemma":[0.0010375461,0.00017830888,0.00025076015,0.00068363885,0.00019252153,0.0006214985,0.00033419736,0.00038350397,0.0023509378],"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":[0.0007556341,0.00010548551,0.0021190098,0.00032631875,0.00008656446,0.00038067374,0.00025296694,0.06886564,0.07902463,0.022036767,0.025782397,0.8002638],"study_design_scores_gemma":[0.00015759186,0.00048210824,0.001716484,0.000049278085,0.000042547752,0.0006041862,0.00015386022,0.81242436,0.13901098,0.0073244576,0.037985776,0.000048475067],"about_ca_topic_score_codex":0.004255175,"about_ca_topic_score_gemma":0.005399238,"teacher_disagreement_score":0.012323302,"about_ca_system_score_codex":0.0005647447,"about_ca_system_score_gemma":0.00061135984,"threshold_uncertainty_score":0.041225493},"labels":[],"label_agreement":null},{"id":"W2001344605","doi":"10.1109/ccece.2013.6567789","title":"Gigabyte-scale alignment of biological sequences: A case study of IO bandwidth reconfiguration for FPGA acceleration","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Field-programmable gate array; Computer science; Bandwidth (computing); Control reconfiguration; Throughput; Speedup; Embedded system; Computer architecture; Computer hardware; Parallel computing; Operating system; Computer network","score_opus":0.06762979098733131,"score_gpt":0.2950620992223945,"score_spread":0.22743230823506322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001344605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8544331,0.00144453,0.118896976,0.0014579282,0.000101509395,0.00012687079,0.000112883514,0.0016234936,0.021802615],"genre_scores_gemma":[0.9285788,0.00044834043,0.06800705,0.000102153586,0.000022133765,0.00003426301,0.000109917084,0.00007306898,0.002624272],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961543,0.000095570795,0.000024395675,0.000045266323,0.00011879128,0.00010046144],"domain_scores_gemma":[0.9988637,0.0006281405,0.00008984119,0.00022149051,0.00011880002,0.000078064164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006147171,0.00035934383,0.00029499707,0.00036116166,0.00048252053,0.00092000805,0.00064154813,0.0005219755,0.0014730492],"category_scores_gemma":[0.0025002358,0.00015565979,0.00019067094,0.0011346093,0.0006258923,0.0008389254,0.00044164216,0.00049120374,0.0003044356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017719083,0.0005369869,0.025082288,0.0007214931,0.000093642484,0.00971152,0.001997256,0.21947147,0.28116372,0.06531687,0.009882995,0.3842498],"study_design_scores_gemma":[0.00015471443,0.0013725795,0.017091664,0.00010999245,0.00007464746,0.0051831394,0.0020583472,0.59706247,0.30811375,0.026152495,0.042542577,0.000083598716],"about_ca_topic_score_codex":0.0014783174,"about_ca_topic_score_gemma":0.0025878982,"teacher_disagreement_score":0.0014783174,"about_ca_system_score_codex":0.00062534667,"about_ca_system_score_gemma":0.00044246684,"threshold_uncertainty_score":0.004927814},"labels":[],"label_agreement":null},{"id":"W2001923775","doi":"10.1142/s0129054106004467","title":"A SIMPLE ALPHABET-INDEPENDENT FM-INDEX","year":2006,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Huffman coding; Substring; Alphabet; Algorithm; Computer science; Mathematics; Entropy (arrow of time); Simple (philosophy); Combinatorics; Order (exchange); Index (typography); Discrete mathematics; Data structure; Data compression; Physics","score_opus":0.010574547236751025,"score_gpt":0.28722827318768845,"score_spread":0.2766537259509374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001923775","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036567718,0.0011408116,0.9508692,0.00030566132,0.00022974882,0.00030173312,0.0013256092,0.004010192,0.00524927],"genre_scores_gemma":[0.17424037,0.00046267247,0.8152066,0.00033345347,0.0001911546,0.00029616756,0.0027296909,0.00025790703,0.006281927],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994099,0.00006233055,0.00008030115,0.00010069274,0.00029544652,0.00005129177],"domain_scores_gemma":[0.9981407,0.00030287702,0.00020889155,0.0007563484,0.00047235747,0.00011880939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046286779,0.0005383075,0.00083800056,0.0017816613,0.0005801533,0.0010511201,0.0017642573,0.00074597815,0.004575191],"category_scores_gemma":[0.002938642,0.00033538768,0.00040524334,0.0025804145,0.00052872347,0.003227794,0.0014894982,0.00057603937,0.002659181],"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":[0.00095109275,0.0003383084,0.0027373713,0.000731593,0.00007161537,0.00032962856,0.00021148751,0.025822679,0.12805294,0.042504236,0.019437809,0.77881134],"study_design_scores_gemma":[0.00041842804,0.0018827504,0.0028211027,0.00018668886,0.00018169273,0.0025500276,0.00017716757,0.60186744,0.25076306,0.0476859,0.09123279,0.00023303302],"about_ca_topic_score_codex":0.00070775836,"about_ca_topic_score_gemma":0.0011762364,"teacher_disagreement_score":0.004575191,"about_ca_system_score_codex":0.00057397375,"about_ca_system_score_gemma":0.0011283917,"threshold_uncertainty_score":0.015305519},"labels":[],"label_agreement":null},{"id":"W2002246332","doi":"10.1016/j.jda.2010.08.004","title":"The longest common extension problem revisited and applications to approximate string searching","year":2010,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Substring; String (physics); Extension (predicate logic); Computation; Constant (computer programming); Algorithm; String searching algorithm; Approximate string matching; Preprocessor; Mathematics; Computer science; Range (aeronautics); Pattern matching; Data structure; Artificial intelligence","score_opus":0.014157796226955652,"score_gpt":0.29080555133089003,"score_spread":0.27664775510393436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002246332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05669967,0.020840576,0.8994584,0.007355302,0.00090023916,0.00014661068,0.00039444453,0.0002652175,0.013939481],"genre_scores_gemma":[0.5148559,0.024159465,0.441655,0.0010957022,0.004233433,0.00032114016,0.00096256414,0.00036547187,0.012351276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99411833,0.0023898936,0.0005303835,0.0010679126,0.0015161318,0.00037739595],"domain_scores_gemma":[0.9505093,0.04005166,0.0019855034,0.0043624975,0.0023115242,0.00077941036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009429348,0.0009828265,0.0040017907,0.0045162863,0.0025031418,0.0070495955,0.0052876356,0.005562756,0.0055952924],"category_scores_gemma":[0.06852252,0.0010968627,0.001805304,0.01728913,0.005661457,0.017661598,0.0049664965,0.006122372,0.00078920997],"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":[0.00032365992,0.00024900486,0.0018327903,0.00052254874,0.00011876514,0.0004776079,0.00051763834,0.10811605,0.0010704328,0.7114119,0.008549554,0.16680996],"study_design_scores_gemma":[0.00003625396,0.000060597573,0.00028149987,0.00008633062,0.00004305675,0.0004492705,0.00024940007,0.23567484,0.0006100561,0.75598824,0.0064765103,0.00004398761],"about_ca_topic_score_codex":0.0023311004,"about_ca_topic_score_gemma":0.0021272271,"teacher_disagreement_score":0.009429348,"about_ca_system_score_codex":0.0022499883,"about_ca_system_score_gemma":0.0030569998,"threshold_uncertainty_score":0.04986775},"labels":[],"label_agreement":null},{"id":"W2003022262","doi":"10.1142/s0129054108005620","title":"AN ASYMPTOTIC LOWER BOUND FOR THE MAXIMAL NUMBER OF RUNS IN A STRING","year":2008,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upper and lower bounds; String (physics); Combinatorics; Mathematics; Sequence (biology); Function (biology); Discrete mathematics; Mathematical analysis; Mathematical physics","score_opus":0.026011521341616408,"score_gpt":0.32900960936328133,"score_spread":0.30299808802166495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003022262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07282528,0.007512227,0.8548208,0.0048231133,0.0005932392,0.00014123748,0.00084384263,0.0033247648,0.055115514],"genre_scores_gemma":[0.64667535,0.005619146,0.3095509,0.0032000293,0.0022162416,0.0011603164,0.0022912628,0.0027256662,0.026561016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994495,0.0011835687,0.00029480632,0.001208449,0.0017772969,0.0010408127],"domain_scores_gemma":[0.95358187,0.035007507,0.0015230442,0.005095503,0.0030546947,0.0017373932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066730264,0.0022793326,0.0023558976,0.00340741,0.0019123099,0.00347441,0.0044048554,0.002882236,0.013001239],"category_scores_gemma":[0.04451863,0.0009149052,0.0017500435,0.0027063296,0.0043272246,0.012256638,0.00454299,0.006902838,0.0040853606],"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":[0.0017408116,0.0004216231,0.0056161196,0.0012182775,0.00016340388,0.00058093143,0.0006165107,0.08621162,0.036042787,0.68531424,0.022726642,0.15934704],"study_design_scores_gemma":[0.000060949213,0.00037733084,0.0021651143,0.00042994675,0.00019014788,0.0016802406,0.00015370092,0.3551569,0.023679402,0.5932949,0.022666618,0.00014474105],"about_ca_topic_score_codex":0.0006689685,"about_ca_topic_score_gemma":0.0008828785,"teacher_disagreement_score":0.013001239,"about_ca_system_score_codex":0.0036527,"about_ca_system_score_gemma":0.0024562855,"threshold_uncertainty_score":0.04349345},"labels":[],"label_agreement":null},{"id":"W2003170440","doi":"10.1109/qbsc.2014.6841193","title":"Real-time communication of dependent messages","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Ottawa","funders":"","keywords":"Computer science; Dependency (UML); Constraint (computer-aided design); Channel code; Encoder; Channel (broadcasting); Maximization; Coding (social sciences); Utility maximization problem; Theoretical computer science; Source code; Decoding methods; Mathematical optimization; Algorithm; Utility maximization; Computer network; Mathematics; Mathematical economics; Artificial intelligence","score_opus":0.008758423591887585,"score_gpt":0.2389634638357351,"score_spread":0.23020504024384753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003170440","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058795422,0.00026749616,0.9352857,0.000523564,0.00007024713,0.000043152057,0.00014576339,0.00022090785,0.00464787],"genre_scores_gemma":[0.9498443,0.00025242943,0.045319285,0.00013213136,0.000047088455,0.00008425279,0.00014068691,0.00004101116,0.0041388078],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847466,0.0006310131,0.000058323094,0.00018140987,0.00047514544,0.00017948406],"domain_scores_gemma":[0.99098164,0.0064334087,0.00074431073,0.001049338,0.00064132793,0.0001499623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016944137,0.0005821643,0.00055698195,0.00043154598,0.00040766035,0.0010188736,0.001263495,0.0012406347,0.0021873252],"category_scores_gemma":[0.011855444,0.00036950613,0.00037119203,0.00070258847,0.0012087311,0.0024403806,0.0014015397,0.0017163352,0.00037864494],"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":[0.00038871428,0.00006040801,0.0006038367,0.00013404198,0.000041756703,0.0005230658,0.0002443322,0.6880146,0.011606392,0.2743308,0.001465471,0.022586629],"study_design_scores_gemma":[0.000018960001,0.000039261842,0.00012783615,0.000008568785,0.000009139737,0.00009225878,0.000020729789,0.95357406,0.00401425,0.04107123,0.0010082992,0.00001542474],"about_ca_topic_score_codex":0.00095063256,"about_ca_topic_score_gemma":0.00072728726,"teacher_disagreement_score":0.0021873252,"about_ca_system_score_codex":0.0011055397,"about_ca_system_score_gemma":0.00063099386,"threshold_uncertainty_score":0.008961022},"labels":[],"label_agreement":null},{"id":"W2004160229","doi":"10.1016/j.jda.2011.11.003","title":"A distribution-sensitive dictionary with low space overhead","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Overhead (engineering); Computer science; Sequence (biology); Data structure; Space (punctuation); Distribution (mathematics); Sensitivity (control systems); Algorithm; Mathematics","score_opus":0.01216150086142602,"score_gpt":0.2241221282317116,"score_spread":0.2119606273702856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004160229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01518488,0.00027490157,0.9815361,0.00031469652,0.00018831718,0.00005135771,0.00017837538,0.0007683784,0.0015030121],"genre_scores_gemma":[0.22232597,0.00061651826,0.76832104,0.0005367037,0.00038964374,0.00013347552,0.0008427685,0.0003013799,0.006532556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991246,0.00020038776,0.00006293038,0.00014419864,0.00039452763,0.00007346279],"domain_scores_gemma":[0.9980679,0.000570346,0.00010104318,0.0008313658,0.0002896348,0.00013982427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005570249,0.00055968616,0.0010124418,0.00060092687,0.00047706894,0.00097537733,0.0010571188,0.0009936052,0.0045984974],"category_scores_gemma":[0.0038201045,0.0003890056,0.00036458153,0.0013168581,0.00058458885,0.0017527705,0.0024722198,0.0012914169,0.002229728],"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":[0.0014247186,0.0002737781,0.00091021124,0.00026860874,0.000089699744,0.00030155742,0.00014226366,0.05509604,0.08461738,0.05082421,0.017344505,0.7887071],"study_design_scores_gemma":[0.00038397597,0.00050726463,0.00053504144,0.000043732132,0.0000627412,0.0015498091,0.00012559285,0.87512386,0.052317683,0.05237203,0.01690909,0.000069266156],"about_ca_topic_score_codex":0.0005858802,"about_ca_topic_score_gemma":0.0012433046,"teacher_disagreement_score":0.0045984974,"about_ca_system_score_codex":0.00023455768,"about_ca_system_score_gemma":0.00088775204,"threshold_uncertainty_score":0.015383482},"labels":[],"label_agreement":null},{"id":"W2004506767","doi":"10.2200/s00396ed1v01y201111dtm022","title":"Full-Text (Substring) Indexes in External Memory","year":2011,"lang":"en","type":"article","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Substring; Computer science; Natural language processing; Arithmetic; Mathematics; Programming language; Data structure","score_opus":0.054580631353493975,"score_gpt":0.2540086173953766,"score_spread":0.19942798604188264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004506767","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044141956,0.007681959,0.8732348,0.0012727603,0.0022670904,0.00017416399,0.0019385581,0.020339468,0.048949193],"genre_scores_gemma":[0.30306774,0.0048066927,0.56861186,0.001127719,0.0019215288,0.0004020889,0.0055055297,0.004872982,0.10968387],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989114,0.00016366565,0.00016124861,0.00020025119,0.0004143188,0.0001492037],"domain_scores_gemma":[0.9966133,0.000969128,0.00015380346,0.0015358265,0.0005909343,0.00013687588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009798981,0.0011892908,0.0011501685,0.0018133793,0.0010574693,0.0039757844,0.0021154578,0.00088920904,0.026787817],"category_scores_gemma":[0.0056106406,0.0006165078,0.0005626616,0.0044616186,0.0010238595,0.0076170205,0.0027678472,0.00110703,0.011824231],"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":[0.0009275756,0.0001655891,0.000978164,0.0005358892,0.00007913186,0.000418408,0.00034593252,0.0114324605,0.030603457,0.15961409,0.076472975,0.71842635],"study_design_scores_gemma":[0.00021777653,0.00044165342,0.0011883976,0.0004050471,0.00019535272,0.0010124531,0.00033499426,0.14403072,0.18752272,0.42372197,0.2407826,0.00014631326],"about_ca_topic_score_codex":0.0007524105,"about_ca_topic_score_gemma":0.001187725,"teacher_disagreement_score":0.026787817,"about_ca_system_score_codex":0.0009257085,"about_ca_system_score_gemma":0.0009769027,"threshold_uncertainty_score":0.08961415},"labels":[],"label_agreement":null},{"id":"W2005833134","doi":"10.1109/is.2012.6335132","title":"Periodicity data mining in time series using Suffix Arrays","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data mining; Suffix; Time series; Series (stratigraphy); Time complexity; Data structure; Algorithm; Machine learning","score_opus":0.06563591537004573,"score_gpt":0.2909855815564481,"score_spread":0.22534966618640237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005833134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06015025,0.00047837588,0.93530923,0.0001394678,0.0000788108,0.000101097365,0.00053678453,0.0017815618,0.0014244538],"genre_scores_gemma":[0.20344198,0.000677117,0.7926632,0.000055587505,0.0001001189,0.00018613173,0.0015461097,0.00013834827,0.0011914378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990421,0.00023646114,0.00016672046,0.00019605747,0.00031266347,0.000046033107],"domain_scores_gemma":[0.99658906,0.0017893297,0.0004099001,0.00073759153,0.00041733202,0.000056752848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011216993,0.0004818874,0.000740633,0.0023712711,0.00062223023,0.0011266255,0.0006460934,0.00053400197,0.0018697361],"category_scores_gemma":[0.0073290896,0.00025894903,0.00072191696,0.0045537073,0.000473095,0.002117982,0.0007615221,0.0006665219,0.0011581078],"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":[0.000548665,0.00015870926,0.007818852,0.00038310036,0.00011261945,0.0005404377,0.00048933935,0.03894498,0.04844268,0.019412123,0.0022262442,0.88092226],"study_design_scores_gemma":[0.00006692768,0.0006731305,0.0068579796,0.00012240896,0.00009434166,0.0022863236,0.0004038496,0.8364828,0.08810697,0.042430166,0.022385811,0.00008922503],"about_ca_topic_score_codex":0.0003326157,"about_ca_topic_score_gemma":0.00033237445,"teacher_disagreement_score":0.0023712711,"about_ca_system_score_codex":0.00017135197,"about_ca_system_score_gemma":0.00052269717,"threshold_uncertainty_score":0.0062549114},"labels":[],"label_agreement":null},{"id":"W2007240595","doi":"10.1016/j.tcs.2012.08.011","title":"Compressed indexes for text with wildcards","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compressed suffix array; Search engine indexing; Computer science; Suffix array; Theoretical computer science; Suffix; Word (group theory); Algorithm; Combinatorics; Data structure; Mathematics; Pattern matching; String searching algorithm; Information retrieval; Artificial intelligence","score_opus":0.010163152623136596,"score_gpt":0.25236240226923884,"score_spread":0.24219924964610223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007240595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11356419,0.0051245643,0.83306324,0.002863272,0.0033587802,0.0006043397,0.009963763,0.0110430205,0.020414887],"genre_scores_gemma":[0.3482382,0.0025894959,0.6000324,0.0007942699,0.0022245885,0.0005489797,0.016535744,0.002024268,0.027012039],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978248,0.00024532684,0.00026942676,0.00025983443,0.0011913816,0.00020919979],"domain_scores_gemma":[0.992332,0.0022050713,0.00043666223,0.0030777673,0.0017132389,0.00023523383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009287255,0.0008508227,0.0012209662,0.004606519,0.0012183163,0.0029379434,0.0012798986,0.0010650103,0.013192818],"category_scores_gemma":[0.014863412,0.0004626845,0.0005335161,0.0067204204,0.00105106,0.0053831204,0.0022666254,0.0013409435,0.005221703],"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":[0.001374702,0.0002536032,0.0011687735,0.00056554505,0.00007883178,0.0008394077,0.0004462819,0.013503952,0.04239162,0.14011961,0.0636119,0.7356458],"study_design_scores_gemma":[0.00030028322,0.00053283275,0.0021292244,0.00031870563,0.00020565584,0.0024697643,0.00045035183,0.29201284,0.12421518,0.4198508,0.15737137,0.00014299552],"about_ca_topic_score_codex":0.0015475508,"about_ca_topic_score_gemma":0.0020433296,"teacher_disagreement_score":0.013192818,"about_ca_system_score_codex":0.00100031,"about_ca_system_score_gemma":0.0017779099,"threshold_uncertainty_score":0.04413432},"labels":[],"label_agreement":null},{"id":"W2007829549","doi":"10.1117/1.oe.51.3.037010","title":"Universal lossless compression algorithm for textual images","year":2012,"lang":"en","type":"article","venue":"Optical Engineering","topic":"Algorithms and Data Compression","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":"University of Northern British Columbia","funders":"","keywords":"Huffman coding; Computer science; Lossless compression; Codebook; Algorithm; Data compression; Arithmetic coding; Volume (thermodynamics); Image compression; Theoretical computer science; Information retrieval; Artificial intelligence; Context-adaptive binary arithmetic coding; Image processing; Image (mathematics)","score_opus":0.010086941608592866,"score_gpt":0.22971472157548875,"score_spread":0.2196277799668959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007829549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031522542,0.0008311595,0.9625506,0.00026398327,0.00010113468,0.00007116982,0.00013222704,0.0010105056,0.0035167288],"genre_scores_gemma":[0.39556378,0.00089030626,0.5924419,0.00025938425,0.00011395342,0.00014984382,0.00052280637,0.00011270417,0.009945312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99978167,0.00002436885,0.00001709022,0.00004213488,0.000107059976,0.000027737151],"domain_scores_gemma":[0.9996132,0.00010477862,0.00004476382,0.00009136715,0.00012998057,0.00001584492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032520323,0.00032011818,0.0003700474,0.00071136793,0.00028512513,0.00043647893,0.0005922619,0.0004238724,0.0018398489],"category_scores_gemma":[0.0017833886,0.00011156858,0.00025797077,0.00080396445,0.00043267253,0.0008395895,0.00050160725,0.00044640453,0.00064850826],"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":[0.00032238054,0.000055274235,0.0005574902,0.0002078347,0.00002602294,0.00023668288,0.00021111364,0.06272134,0.084906325,0.045185994,0.0071602454,0.7984093],"study_design_scores_gemma":[0.000043248543,0.00013176,0.00082583306,0.000043761604,0.000024461822,0.0006928708,0.00006562876,0.8859762,0.088409744,0.012725598,0.011034128,0.00002682233],"about_ca_topic_score_codex":0.0024168922,"about_ca_topic_score_gemma":0.0019177875,"teacher_disagreement_score":0.0024168922,"about_ca_system_score_codex":0.0005353767,"about_ca_system_score_gemma":0.00059091626,"threshold_uncertainty_score":0.006154895},"labels":[],"label_agreement":null},{"id":"W2007979101","doi":"10.1016/s0022-0000(03)00075-8","title":"Solving large FPT problems on coarse-grained parallel machines","year":2003,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Dalhousie University; Carleton University","funders":"","keywords":"Computer science; Vertex cover; Parallelism (grammar); Bounded function; Vertex (graph theory); Implementation; Cover (algebra); Sequence (biology); Parallel computing; Tree (set theory); Parallel algorithm; Algorithm; Theoretical computer science; Mathematics; Graph; Combinatorics; Approximation algorithm; Programming language","score_opus":0.01946566761545364,"score_gpt":0.2503981644689971,"score_spread":0.23093249685354345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007979101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40638074,0.0022623136,0.5647924,0.0036177796,0.0006678279,0.00019546408,0.00049676676,0.0049074143,0.016679306],"genre_scores_gemma":[0.6324877,0.00044142688,0.36079648,0.00029757665,0.0002520003,0.00023085428,0.0006558288,0.00036059768,0.0044775233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989623,0.00022736391,0.00009119409,0.00023468459,0.00027492046,0.00020944126],"domain_scores_gemma":[0.9924758,0.005810309,0.0002649382,0.0008857927,0.00038095834,0.0001821682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001624984,0.0008682701,0.0015565827,0.00079893664,0.0013586722,0.0018110133,0.0016664815,0.001727907,0.0054999134],"category_scores_gemma":[0.010255691,0.00066605327,0.0008166677,0.0016815957,0.0014680449,0.0034150032,0.0012976015,0.00207283,0.0006886366],"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":[0.00054789864,0.00024152323,0.0020881623,0.0004613429,0.00010940634,0.00039848525,0.00022383053,0.79730284,0.006186997,0.037579596,0.01263789,0.14222208],"study_design_scores_gemma":[0.0001017018,0.000043773784,0.00024643957,0.000010205123,0.000014854498,0.00005358317,0.00006230189,0.93878686,0.0023492912,0.057232987,0.0010902935,0.000007719344],"about_ca_topic_score_codex":0.005860194,"about_ca_topic_score_gemma":0.007488388,"teacher_disagreement_score":0.005860194,"about_ca_system_score_codex":0.0010950676,"about_ca_system_score_gemma":0.0017607379,"threshold_uncertainty_score":0.018399},"labels":[],"label_agreement":null},{"id":"W2008451765","doi":"10.1007/s00453-006-1220-3","title":"Parallelizing Feature Selection","year":2006,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Feature selection; Classifier (UML); Theory of computation; Artificial intelligence; Machine learning; Statistical classification; Linear classifier; Data mining; Algorithm","score_opus":0.005461288633920117,"score_gpt":0.21133145313564952,"score_spread":0.2058701645017294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008451765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049630407,0.0008439538,0.935449,0.0007217082,0.0005114635,0.00015034483,0.00037151168,0.005590715,0.006730791],"genre_scores_gemma":[0.32605666,0.00043652262,0.65199035,0.0003944855,0.00052693667,0.00025884775,0.0017128709,0.00065344095,0.017969893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896955,0.00018253697,0.00006536685,0.0003051082,0.00034810076,0.00012932334],"domain_scores_gemma":[0.9983664,0.00051696185,0.0000554448,0.0006644647,0.00034179585,0.000054925462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008850435,0.0011621392,0.0014510964,0.0015076488,0.00090525066,0.001448683,0.001375549,0.00076316466,0.010958719],"category_scores_gemma":[0.0033038054,0.00052146154,0.0011575408,0.0025104233,0.00066458253,0.0016495207,0.0017576872,0.0010859579,0.003007517],"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":[0.0006103752,0.00017275239,0.0015757909,0.00009521805,0.000122956,0.00016051972,0.00006545533,0.042415094,0.02009808,0.00941943,0.015631165,0.90963316],"study_design_scores_gemma":[0.00017114096,0.00017883904,0.0020161746,0.000016569895,0.00012450936,0.0003843572,0.000068572714,0.89322335,0.032786597,0.054057922,0.016942894,0.000029086508],"about_ca_topic_score_codex":0.0036027485,"about_ca_topic_score_gemma":0.0059057837,"teacher_disagreement_score":0.010958719,"about_ca_system_score_codex":0.00065910374,"about_ca_system_score_gemma":0.0014440453,"threshold_uncertainty_score":0.03666061},"labels":[],"label_agreement":null},{"id":"W2008594023","doi":"10.1109/isita.2010.5649565","title":"Using synchronization bits to boost compression by substring enumeration","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Lossless compression; Computer science; Enumeration; Byte; Synchronization (alternating current); Binary number; Algorithm; Preprocessor; Data compression; Simple (philosophy); Data structure; Theoretical computer science; Mathematics; Arithmetic; Artificial intelligence; Discrete mathematics","score_opus":0.016999374033394105,"score_gpt":0.27409956002232777,"score_spread":0.2571001859889337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008594023","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18131319,0.0013307623,0.81195927,0.00043325225,0.00016052875,0.00007951472,0.00011290214,0.0024983091,0.0021122922],"genre_scores_gemma":[0.55986017,0.00064770755,0.4357698,0.00028953826,0.00021731868,0.00008186436,0.00043690918,0.00023011796,0.0024665357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936754,0.000103732695,0.000061031573,0.0000855574,0.00033445432,0.000047727073],"domain_scores_gemma":[0.9965765,0.0018748987,0.0003063918,0.0008124116,0.00036727064,0.000062549276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007480205,0.00057756656,0.0007165208,0.0012668811,0.00035442063,0.00060213945,0.00090405386,0.0005055192,0.001539476],"category_scores_gemma":[0.0058763176,0.0002548013,0.00023391581,0.0018892679,0.00074153236,0.002019652,0.000996575,0.0008036366,0.0005319673],"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":[0.0010681608,0.00018937269,0.0020322592,0.000270436,0.0000538104,0.00028291557,0.00022071542,0.032667678,0.22007474,0.021713318,0.0023080448,0.71911854],"study_design_scores_gemma":[0.0001568667,0.00095431553,0.0029421223,0.00005772417,0.000093418355,0.0013690721,0.000093547984,0.42885238,0.53333116,0.019667035,0.012411819,0.00007053518],"about_ca_topic_score_codex":0.00030025086,"about_ca_topic_score_gemma":0.0004269555,"teacher_disagreement_score":0.001539476,"about_ca_system_score_codex":0.0002491109,"about_ca_system_score_gemma":0.00039650904,"threshold_uncertainty_score":0.00515002},"labels":[],"label_agreement":null},{"id":"W2008903345","doi":"10.1007/s10586-007-0020-0","title":"An exact parallel algorithm to compare very long biological sequences in clusters of workstations","year":2007,"lang":"en","type":"article","venue":"Cluster Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Workstation; Algorithm; Heuristic; Sequence (biology); Smith–Waterman algorithm; Computation; Dynamic programming; Cluster (spacecraft); Quadratic equation; Time complexity; Parallel computing; Parallel algorithm; Sequence alignment; Mathematics; Artificial intelligence; Biology","score_opus":0.03297818096897284,"score_gpt":0.31452972213610314,"score_spread":0.2815515411671303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008903345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018108122,0.00031740396,0.9763282,0.00010421184,0.00012683129,0.0001143739,0.00016252384,0.0031255146,0.0016128713],"genre_scores_gemma":[0.07943055,0.00015312682,0.91650116,0.0000799522,0.000062131476,0.00030460398,0.00050487876,0.00024952338,0.0027140074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878854,0.00022109188,0.00011700383,0.00024069387,0.00052807614,0.00010460865],"domain_scores_gemma":[0.9981122,0.0007339665,0.00008479328,0.00049064035,0.00050403515,0.00007435285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015289605,0.0009590709,0.0011142227,0.0019907344,0.0014774308,0.001272293,0.002906069,0.0010746978,0.00521914],"category_scores_gemma":[0.0053360104,0.0007175482,0.00066765514,0.0035639415,0.0008888617,0.0021440806,0.0019080762,0.00093434186,0.0014421461],"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":[0.0007472371,0.00024547617,0.0016171974,0.00027072078,0.00018656152,0.0002180391,0.00024723876,0.17618793,0.024619596,0.023877872,0.010154848,0.76162714],"study_design_scores_gemma":[0.00019381077,0.00019000341,0.00087630795,0.000014763389,0.00007063763,0.00030125544,0.0000774181,0.93571997,0.01730573,0.03864811,0.0065655634,0.00003642305],"about_ca_topic_score_codex":0.003811317,"about_ca_topic_score_gemma":0.004487255,"teacher_disagreement_score":0.00521914,"about_ca_system_score_codex":0.0008904269,"about_ca_system_score_gemma":0.0017369468,"threshold_uncertainty_score":0.01745975},"labels":[],"label_agreement":null},{"id":"W2009268872","doi":"10.1109/dcc.2014.68","title":"Improving Compression via Substring Enumeration by Explicit Phase Awareness","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Lossless compression; Substring; Computer science; Compression (physics); Data compression; Byte; Algorithm; Synchronization (alternating current); Enumeration; Code (set theory); Universal code; Phase (matter); Compression ratio; Theoretical computer science; Mathematics; Data structure; Decoding methods; Block code; Discrete mathematics; Programming language; Linear code; Telecommunications","score_opus":0.011849152565688902,"score_gpt":0.26204690846189244,"score_spread":0.2501977558962035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009268872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06299341,0.0005348233,0.9321968,0.0001847914,0.000047784433,0.0000664625,0.000049450075,0.0018556728,0.0020708262],"genre_scores_gemma":[0.41537833,0.0006003077,0.579571,0.00017997545,0.00008124595,0.00007091211,0.00030047662,0.00023362074,0.0035841258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993599,0.00010294831,0.000050591065,0.000075141965,0.0003595484,0.00005188458],"domain_scores_gemma":[0.9973254,0.0013932349,0.00021843707,0.00070089835,0.00031299423,0.000048929818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006283946,0.00059010467,0.00048517084,0.0013458328,0.00034966905,0.00069637666,0.00081154605,0.00064147235,0.0014139707],"category_scores_gemma":[0.0042629745,0.0002766876,0.0003142953,0.0017037798,0.000660073,0.0023927824,0.0012079219,0.00087487436,0.00050655747],"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":[0.00032548953,0.00017007889,0.0016526933,0.00016549762,0.000035055848,0.00015645497,0.00021815249,0.053573135,0.15440276,0.023121104,0.001858602,0.7643209],"study_design_scores_gemma":[0.00006309321,0.00033328435,0.0013400086,0.000037331043,0.00004174448,0.00073276466,0.00010216982,0.65877295,0.31353754,0.01596438,0.009022021,0.00005268996],"about_ca_topic_score_codex":0.00069638365,"about_ca_topic_score_gemma":0.0010314196,"teacher_disagreement_score":0.0014139707,"about_ca_system_score_codex":0.00030516848,"about_ca_system_score_gemma":0.0005651957,"threshold_uncertainty_score":0.0047302246},"labels":[],"label_agreement":null},{"id":"W2009346361","doi":"10.1145/1060745.1060783","title":"Improving Web search efficiency via a locality based static pruning method","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":64,"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":"CYTED Ciencia y Tecnología para el Desarrollo; Fundação de Amparo à Pesquisa do Estado do Amazonas; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Locality; Pruning; Computer science; Artificial intelligence","score_opus":0.018546129483312617,"score_gpt":0.30121121869234624,"score_spread":0.2826650892090336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009346361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11913794,0.002290019,0.86795455,0.00035216898,0.000092614246,0.00016693791,0.00015158296,0.0037536882,0.00610053],"genre_scores_gemma":[0.49340853,0.0012586373,0.49819788,0.00019218311,0.0002202067,0.00027160923,0.0004998561,0.00030966997,0.005641486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885476,0.00017996055,0.00008076699,0.00011823675,0.000679087,0.000087205764],"domain_scores_gemma":[0.9980184,0.0007470439,0.0002491625,0.0004497316,0.0004822091,0.000053510415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008690018,0.0005243726,0.0010103538,0.0026152285,0.0006963106,0.0008595748,0.0016983171,0.0007218489,0.0013271879],"category_scores_gemma":[0.005009148,0.00038781704,0.00048390028,0.002588608,0.0005820592,0.002058861,0.00085919816,0.00051084725,0.00075160677],"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":[0.0002908617,0.0003033636,0.0032907266,0.00024148168,0.0000903817,0.00038096812,0.00025279084,0.043344684,0.09205977,0.013237419,0.006625925,0.8398816],"study_design_scores_gemma":[0.00015528442,0.0004903737,0.0048701447,0.00007267692,0.00027275778,0.0022427256,0.00017606202,0.87517434,0.086982794,0.013141299,0.016331917,0.00008967181],"about_ca_topic_score_codex":0.0024910423,"about_ca_topic_score_gemma":0.0036849142,"teacher_disagreement_score":0.0026152285,"about_ca_system_score_codex":0.0005551912,"about_ca_system_score_gemma":0.0012293584,"threshold_uncertainty_score":0.0049530864},"labels":[],"label_agreement":null},{"id":"W2009601525","doi":"10.1109/tc.2013.29","title":"FLOTT—A Fast, Low Memory T-TransformAlgorithm for Measuring String Complexity","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Algorithms and Data Compression","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 Victoria","funders":"","keywords":"Computer science; String (physics); Algorithm; Suffix; Time complexity; Compressed suffix array; Computational complexity theory; Suffix tree; Theoretical computer science; Measure (data warehouse); Generalized suffix tree; Data structure; Mathematics; Data mining; Programming language","score_opus":0.0322719717284187,"score_gpt":0.23951572188006498,"score_spread":0.20724375015164628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009601525","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019257655,0.00048727595,0.968037,0.00009961287,0.00012601112,0.00013508312,0.00047971896,0.007949655,0.003427939],"genre_scores_gemma":[0.1481605,0.00039174297,0.8430868,0.0001340837,0.00011362816,0.00044054992,0.002549029,0.0012398788,0.003883815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833626,0.00016688906,0.000118872675,0.00021730203,0.0010161181,0.0001445932],"domain_scores_gemma":[0.9972235,0.00096781575,0.00039220808,0.000492782,0.00079509587,0.0001286924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010436166,0.0011345709,0.0007795336,0.0028933163,0.0010363207,0.0018242395,0.0017217286,0.0010929711,0.007712521],"category_scores_gemma":[0.00884565,0.00041945852,0.0008359605,0.0025198597,0.00091360114,0.0035483642,0.0017135987,0.0012141996,0.0035614918],"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":[0.0007801297,0.0001533615,0.004163837,0.00042094372,0.00011308114,0.00018520215,0.00022135631,0.040053755,0.06562441,0.03626258,0.024422547,0.8275988],"study_design_scores_gemma":[0.0001553086,0.00064969104,0.0035263684,0.000097142845,0.00006633993,0.0007995963,0.00017535243,0.7473297,0.15594605,0.05441987,0.03666119,0.00017334406],"about_ca_topic_score_codex":0.0020599882,"about_ca_topic_score_gemma":0.0024751988,"teacher_disagreement_score":0.007712521,"about_ca_system_score_codex":0.0011813348,"about_ca_system_score_gemma":0.001704174,"threshold_uncertainty_score":0.025800943},"labels":[],"label_agreement":null},{"id":"W2010916703","doi":"10.1145/2493288.2493297","title":"Parameterized strategy pattern","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Calgary","funders":"","keywords":"Parameterized complexity; Computer science; Class (philosophy); Algorithm; Artificial intelligence","score_opus":0.014154688242336292,"score_gpt":0.25009886974616435,"score_spread":0.23594418150382807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010916703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044730427,0.00017865367,0.9387403,0.0006762114,0.0002290463,0.0004647579,0.001381143,0.020086763,0.033770002],"genre_scores_gemma":[0.14728665,0.00073232787,0.75739044,0.0021668123,0.00018344418,0.0020743015,0.007482163,0.015723687,0.066960156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954798,0.0007206514,0.0007930421,0.0009370641,0.0016069789,0.00046232203],"domain_scores_gemma":[0.99507755,0.0010123436,0.00020439559,0.002469575,0.00095511077,0.00028101794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026826272,0.0015265645,0.001069812,0.0010507341,0.0009393082,0.00500359,0.003357175,0.0029687905,0.02252287],"category_scores_gemma":[0.0091826245,0.0010525319,0.0012490703,0.0013481881,0.0018840419,0.008021,0.0036321194,0.0032554963,0.012682265],"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":[0.0005305952,0.00024681853,0.0020960306,0.000521894,0.00007153532,0.0007122858,0.00084321573,0.004492536,0.014907275,0.64682966,0.070769206,0.25797895],"study_design_scores_gemma":[0.00009421056,0.00014861033,0.0005181354,0.00013562234,0.000044289125,0.0012879815,0.00024094511,0.027740736,0.020857275,0.25068903,0.6981454,0.00009771828],"about_ca_topic_score_codex":0.0020136177,"about_ca_topic_score_gemma":0.0026277893,"teacher_disagreement_score":0.02252287,"about_ca_system_score_codex":0.0015048698,"about_ca_system_score_gemma":0.0024748682,"threshold_uncertainty_score":0.07534647},"labels":[],"label_agreement":null},{"id":"W2011273749","doi":"10.1016/j.tcs.2010.06.019","title":"The “runs” conjecture","year":2010,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Conjecture; Combinatorics; Collatz conjecture; Mathematics; Upper and lower bounds; String (physics); Lonely runner conjecture; Discrete mathematics; Mathematical analysis","score_opus":0.0038316263642889036,"score_gpt":0.23197776452990565,"score_spread":0.22814613816561674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011273749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1002669,0.008462532,0.42923638,0.11475693,0.004958329,0.00012460357,0.0023498284,0.0030135727,0.3368309],"genre_scores_gemma":[0.8231403,0.004026362,0.062953666,0.024944212,0.00812778,0.00055141695,0.0035984244,0.001990145,0.07066767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99324965,0.0021100272,0.00030427045,0.0020713331,0.001527912,0.00073683856],"domain_scores_gemma":[0.96385396,0.022455616,0.0009588996,0.00995871,0.0019800197,0.00079289026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005141123,0.001409434,0.0022660173,0.0013155399,0.0033817093,0.0061847046,0.0029495475,0.0050896597,0.021665877],"category_scores_gemma":[0.03802357,0.0010762828,0.0017348207,0.0020915233,0.010704509,0.028531265,0.007115332,0.012318393,0.0061275274],"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":[0.00031376653,0.00005344992,0.0008029915,0.00014704582,0.000060384675,0.0001285238,0.00023889117,0.0034399128,0.0008023222,0.9447317,0.033034246,0.016246775],"study_design_scores_gemma":[0.000029483337,0.000012705575,0.00015096944,0.000033736633,0.00001567728,0.000068486384,0.000047718866,0.004856734,0.00046320303,0.9865089,0.0077985106,0.0000138059695],"about_ca_topic_score_codex":0.0012622031,"about_ca_topic_score_gemma":0.001041013,"teacher_disagreement_score":0.021665877,"about_ca_system_score_codex":0.0016934549,"about_ca_system_score_gemma":0.0018845423,"threshold_uncertainty_score":0.072479546},"labels":[],"label_agreement":null},{"id":"W2011321377","doi":"10.1145/1188966.1188972","title":"A backtracking LR algorithm for parsing ambiguous context-dependent languages","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Backtracking; Computer science; Parsing; Context (archaeology); Programming language; LR parser; Bottom-up parsing; Algorithm; Theoretical computer science; Top-down parsing","score_opus":0.012551200036471985,"score_gpt":0.259961434691439,"score_spread":0.24741023465496703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011321377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005336237,0.00018021897,0.9829522,0.00012057721,0.000030790925,0.000107660664,0.00018054374,0.009784249,0.0013074785],"genre_scores_gemma":[0.034453984,0.00014058671,0.96078223,0.00014623655,0.000020099444,0.000102037004,0.00058359496,0.0012257566,0.002545557],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998566,0.0003272373,0.00018303032,0.00039709048,0.00040539994,0.000121203964],"domain_scores_gemma":[0.99720865,0.0013759135,0.00018916077,0.00059596007,0.00056847493,0.00006186059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018208215,0.0009451232,0.0008777697,0.0022285127,0.0009028195,0.0016500759,0.0016875033,0.0016917299,0.005611792],"category_scores_gemma":[0.0037490502,0.00078731176,0.0010689375,0.001902963,0.0014054987,0.0022445098,0.0015907813,0.0018513871,0.0027607058],"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":[0.00032269154,0.00014376137,0.0011978616,0.0004599458,0.00007435366,0.0006822503,0.0010567933,0.02739017,0.06341427,0.04512127,0.016762998,0.8433736],"study_design_scores_gemma":[0.00030207157,0.00034948502,0.0014761761,0.00024971116,0.00021920349,0.002205559,0.0005575043,0.6462531,0.14284779,0.12270242,0.08251179,0.00032512954],"about_ca_topic_score_codex":0.003992659,"about_ca_topic_score_gemma":0.005578663,"teacher_disagreement_score":0.005611792,"about_ca_system_score_codex":0.000773689,"about_ca_system_score_gemma":0.0019799466,"threshold_uncertainty_score":0.018773377},"labels":[],"label_agreement":null},{"id":"W2011889038","doi":"10.1016/j.jspi.2007.03.063","title":"Distribution of the length of the longest common subsequence of two multi-state biological sequences","year":2008,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Manitoba","funders":"","keywords":"Mathematics; Longest common subsequence problem; Longest increasing subsequence; Subsequence; Combinatorics; Markov chain; Distribution (mathematics); Simple (philosophy); Measure (data warehouse); Discrete mathematics; Statistics; Mathematical analysis; Computer science","score_opus":0.07802255584942563,"score_gpt":0.32770503436847503,"score_spread":0.2496824785190494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011889038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93697387,0.00039960255,0.05917306,0.00044006488,0.00007980238,0.00005032987,0.0011617858,0.000390814,0.0013307617],"genre_scores_gemma":[0.99138653,0.0001177095,0.005971192,0.00003554568,0.00004808243,0.000055284727,0.0015726872,0.000051900384,0.00076114904],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99879396,0.00020737293,0.00008883252,0.00048465654,0.00028114315,0.00014405938],"domain_scores_gemma":[0.9666172,0.023996826,0.0031146558,0.0021813433,0.0031283898,0.0009615271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032584826,0.0003898444,0.0005285119,0.0028692712,0.0006466876,0.0011828898,0.0011764555,0.0012347973,0.0038126495],"category_scores_gemma":[0.023672713,0.0004178265,0.0006055151,0.001467219,0.0018494794,0.001899511,0.00075381174,0.0012581389,0.00063384266],"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":[0.008332823,0.0010163148,0.25254595,0.0010311073,0.0006020708,0.003635664,0.0021632,0.33701867,0.110709086,0.12514532,0.006956419,0.15084335],"study_design_scores_gemma":[0.00012070466,0.0005725537,0.054221112,0.00008128821,0.00011459398,0.0014582183,0.0005090456,0.88645345,0.012936537,0.041756984,0.0016517823,0.00012380842],"about_ca_topic_score_codex":0.001474963,"about_ca_topic_score_gemma":0.0012671285,"teacher_disagreement_score":0.0038126495,"about_ca_system_score_codex":0.00093299284,"about_ca_system_score_gemma":0.0007462547,"threshold_uncertainty_score":0.017232716},"labels":[],"label_agreement":null},{"id":"W2012680439","doi":"10.1109/51.940049","title":"A compression algorithm for DNA sequences","year":2001,"lang":"en","type":"article","venue":"IEEE Engineering in Medicine and Biology Magazine","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Hong Kong; City University of Hong Kong","keywords":"Data compression; Compression (physics); Algorithm; Benchmark (surveying); Computer science; Matching (statistics); DNA sequencing; DNA; DNA computing; Mathematics; Biology; Genetics; Physics; Computation","score_opus":0.036809861240034644,"score_gpt":0.2978930809314662,"score_spread":0.26108321969143156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012680439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01095981,0.0012067127,0.9824101,0.00023536623,0.00022081994,0.00017702089,0.00028236056,0.0019974178,0.0025104377],"genre_scores_gemma":[0.055328034,0.000898138,0.9367779,0.00026069616,0.00014758538,0.00032316224,0.0010750452,0.0002082592,0.0049811564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999193,0.00008289819,0.000066991466,0.0001341918,0.00047155493,0.000051393392],"domain_scores_gemma":[0.9991628,0.00026391493,0.00006762671,0.00019681237,0.00028128532,0.000027499595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053371064,0.0009762071,0.000643562,0.0019110505,0.0006964838,0.00097509346,0.0009314274,0.0012565779,0.0041063474],"category_scores_gemma":[0.0031015908,0.00032568973,0.0005126274,0.0026465205,0.00066229305,0.0014341616,0.00092001643,0.0009654854,0.0020184289],"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":[0.00025974502,0.000058127654,0.0004766479,0.00023335965,0.000044826724,0.00020811969,0.00012919377,0.03197046,0.044996478,0.022496995,0.010392001,0.888734],"study_design_scores_gemma":[0.00017936618,0.00059690455,0.0015437895,0.00017403098,0.00009581251,0.003960522,0.00013033758,0.6654543,0.20895547,0.03963121,0.07917127,0.0001069701],"about_ca_topic_score_codex":0.0013991626,"about_ca_topic_score_gemma":0.0010865803,"teacher_disagreement_score":0.0041063474,"about_ca_system_score_codex":0.00054595113,"about_ca_system_score_gemma":0.0007675677,"threshold_uncertainty_score":0.0137370825},"labels":[],"label_agreement":null},{"id":"W2013181170","doi":"10.1109/iri.2010.5558906","title":"Sentence level fact based search engine: News Fact Finder","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Substring; Computer science; Search engine; Sentence; Information retrieval; The Internet; Matching (statistics); Suffix; Order (exchange); World Wide Web; Artificial intelligence; Data structure; Mathematics; Programming language","score_opus":0.04552391365676987,"score_gpt":0.2801020250425687,"score_spread":0.23457811138579884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013181170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08208619,0.0017312055,0.57141757,0.0016130856,0.0005441296,0.0016720388,0.10011904,0.20306586,0.037750825],"genre_scores_gemma":[0.18371755,0.00081641396,0.6808147,0.0010623297,0.00029382578,0.00083693204,0.099683985,0.0054110726,0.027363205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995346,0.0000698753,0.000098190256,0.00008534775,0.00017300293,0.000039021274],"domain_scores_gemma":[0.9974789,0.0012003925,0.0002265535,0.00024190849,0.0007624481,0.000089825444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008228708,0.0007004284,0.0006723708,0.0029123086,0.00040132552,0.0010561831,0.0008316407,0.0009679649,0.032046873],"category_scores_gemma":[0.0050625606,0.00032753058,0.00039526683,0.0023474714,0.00024844558,0.0018460662,0.00067949446,0.0005306286,0.013479716],"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":[0.0022266987,0.00044470184,0.00779583,0.0025086831,0.00024452293,0.001174057,0.00062733196,0.0035922548,0.10027295,0.01927913,0.3639317,0.49790218],"study_design_scores_gemma":[0.0006897318,0.0011433308,0.01835727,0.00032128193,0.00032026338,0.003777143,0.00078628625,0.25635582,0.29790634,0.020401767,0.3996067,0.00033400374],"about_ca_topic_score_codex":0.0014990038,"about_ca_topic_score_gemma":0.002308914,"teacher_disagreement_score":0.032046873,"about_ca_system_score_codex":0.00033597543,"about_ca_system_score_gemma":0.00063803047,"threshold_uncertainty_score":0.10720754},"labels":[],"label_agreement":null},{"id":"W2013644024","doi":"10.1145/2464576.2482748","title":"Combinatorial optimization EDA using hidden Markov models","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Hidden Markov model; Estimation of distribution algorithm; Computer science; Graphical model; EDAS; Bernoulli distribution; Estimator; Maximum-entropy Markov model; Markov model; Bayesian network; Bernoulli's principle; Algorithm; Artificial intelligence; Machine learning; Variable-order Markov model; Markov chain; Random variable; Mathematics; Statistics; Engineering","score_opus":0.02114062183170093,"score_gpt":0.23366747568479299,"score_spread":0.21252685385309206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013644024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041090394,0.0004266086,0.99260795,0.00016643656,0.000034785506,0.000037333924,0.00005536213,0.00041277328,0.0021496364],"genre_scores_gemma":[0.2077348,0.00094614207,0.78429425,0.00027623243,0.00012271226,0.00040052473,0.00053566415,0.0002971851,0.0053925575],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989127,0.0004135172,0.00007500555,0.00018574961,0.00033983646,0.00007318347],"domain_scores_gemma":[0.9966409,0.0026466644,0.00015440733,0.00029525912,0.00020437047,0.000058352274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016194454,0.00084456394,0.0014828432,0.0012010192,0.0005102937,0.0014552771,0.0013387831,0.0009409972,0.004577939],"category_scores_gemma":[0.005710059,0.00058277056,0.0010708057,0.001668965,0.00096284295,0.0020983766,0.001473682,0.0018942928,0.00068659236],"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":[0.00007014622,0.000080604324,0.00041101125,0.00014866944,0.00006939262,0.000060892264,0.000056536395,0.73343575,0.0008838978,0.07177545,0.0024357173,0.190572],"study_design_scores_gemma":[0.000012070809,0.000012292286,0.00005395083,0.000009162902,0.000005745279,0.000014636189,0.0000054298807,0.9696576,0.0003797195,0.028729968,0.0011139422,0.000005441607],"about_ca_topic_score_codex":0.0028636463,"about_ca_topic_score_gemma":0.0026820556,"teacher_disagreement_score":0.004577939,"about_ca_system_score_codex":0.0011776565,"about_ca_system_score_gemma":0.0015995633,"threshold_uncertainty_score":0.015314698},"labels":[],"label_agreement":null},{"id":"W2013662449","doi":"10.1007/3-540-47555-9_12","title":"Suffix trees and string complexity","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sequence (biology); Suffix tree; Suffix; String (physics); Mathematics; Combinatorics; Generalized suffix tree; Tree (set theory); Discrete mathematics; Shift register; Order (exchange); Computer science; Data structure","score_opus":0.0454359545678276,"score_gpt":0.27756268553565316,"score_spread":0.23212673096782557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013662449","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035319768,0.04553494,0.41404736,0.011088238,0.002065801,0.000099839555,0.0011502763,0.0012150109,0.48947883],"genre_scores_gemma":[0.5501611,0.049345087,0.15884386,0.0024357992,0.008342923,0.00038161146,0.0031221225,0.0010670099,0.22630043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920815,0.00013491244,0.00004778513,0.00012662481,0.00042504683,0.000057519723],"domain_scores_gemma":[0.99832624,0.00114653,0.00007809921,0.00023989652,0.00015463274,0.000054689044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051894935,0.0006918072,0.0010756478,0.0017450409,0.00096133107,0.0032577096,0.0009901914,0.001143723,0.015143731],"category_scores_gemma":[0.0035176591,0.00052326196,0.00067484716,0.0046829223,0.0024551642,0.00932197,0.0016697628,0.003792787,0.004362548],"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":[0.000018372182,0.000020413721,0.00013248235,0.00015528454,0.000011036116,0.00003960225,0.00011062033,0.003527646,0.0005661905,0.9174782,0.013544519,0.06439559],"study_design_scores_gemma":[0.0000027585295,0.0000051943343,0.000087776694,0.000018133484,0.0000038626868,0.000072223665,0.000016726965,0.0029519992,0.0002831924,0.97572803,0.02082465,0.0000054709753],"about_ca_topic_score_codex":0.0004860381,"about_ca_topic_score_gemma":0.0005032679,"teacher_disagreement_score":0.015143731,"about_ca_system_score_codex":0.0016275739,"about_ca_system_score_gemma":0.0006711013,"threshold_uncertainty_score":0.05066079},"labels":[],"label_agreement":null},{"id":"W2014016891","doi":"10.1007/s007990100043","title":"A fast method for determining the origins of documents based on LZW compression","year":2002,"lang":"en","type":"article","venue":"International Journal on Digital Libraries","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Copying; Computer science; Publication; Revenue; Information retrieval; World Wide Web; Database; Data mining; Advertising","score_opus":0.028264850790036267,"score_gpt":0.2944132124102884,"score_spread":0.2661483616202521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014016891","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009773999,0.0013038972,0.9789028,0.00016755988,0.00025232785,0.0002570642,0.00053815055,0.006942479,0.0018616193],"genre_scores_gemma":[0.026550243,0.0006347993,0.9685242,0.00005850483,0.00012370493,0.00020131463,0.0011810217,0.00038951496,0.0023367445],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983425,0.00018262291,0.0001348196,0.00020803788,0.0010044778,0.00012751274],"domain_scores_gemma":[0.9973911,0.00081674627,0.00022971569,0.000492349,0.0009538674,0.000116130155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010477608,0.0017664495,0.0016512203,0.007139651,0.0017296096,0.0024167418,0.001964354,0.0016944209,0.007696098],"category_scores_gemma":[0.0050583184,0.00080261956,0.0007919612,0.0042914995,0.001213389,0.0035907745,0.0024850895,0.0022390233,0.009007812],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079794833,0.00009273508,0.0010736503,0.0005374314,0.00006532498,0.00029605898,0.00036188198,0.0034843083,0.13645099,0.01275754,0.0071846144,0.83689743],"study_design_scores_gemma":[0.00054761185,0.00060230674,0.0045216344,0.00023678038,0.0002550996,0.0029200034,0.0005487261,0.32915583,0.5574166,0.032309897,0.07114298,0.00034245595],"about_ca_topic_score_codex":0.0023452935,"about_ca_topic_score_gemma":0.0031363082,"teacher_disagreement_score":0.007696098,"about_ca_system_score_codex":0.00086824986,"about_ca_system_score_gemma":0.0021972228,"threshold_uncertainty_score":0.025745988},"labels":[],"label_agreement":null},{"id":"W2014277465","doi":"10.1016/j.jcss.2007.09.003","title":"Maximal repetitions in strings","year":2007,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Conjecture; String (physics); Mathematics; Combinatorics; Upper and lower bounds; Running time; Computation; Discrete mathematics; Time complexity; Linearity; Computer science; Algorithm; Mathematical analysis; Physics","score_opus":0.015463654187503464,"score_gpt":0.2579745793370556,"score_spread":0.24251092514955214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014277465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40569797,0.0031034674,0.38751101,0.0048292456,0.000796623,0.00017321724,0.0015850462,0.0024497276,0.1938536],"genre_scores_gemma":[0.8921758,0.000998623,0.06288162,0.0008910558,0.0007011912,0.00021078208,0.0014944922,0.00083955703,0.039806888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963683,0.0011281541,0.00036921055,0.0007402039,0.00097043306,0.00042380163],"domain_scores_gemma":[0.98649406,0.009331665,0.00075772806,0.002196457,0.0007955748,0.00042452553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014909932,0.0006979164,0.0011343035,0.0022821536,0.002089146,0.0037330678,0.0013255639,0.0021121316,0.013992274],"category_scores_gemma":[0.014685697,0.00088189344,0.0012266517,0.0025768518,0.0027313319,0.0058271484,0.0032710573,0.0029448492,0.0032232963],"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":[0.00032312633,0.00006811096,0.0009976499,0.00016129529,0.000033555312,0.000401503,0.00069764844,0.0038845004,0.0047502634,0.93873906,0.005788275,0.044154935],"study_design_scores_gemma":[0.000021925483,0.00003874212,0.00031135054,0.000056674766,0.000026738935,0.00045054898,0.00009287798,0.012413646,0.004263508,0.97481245,0.0074901073,0.00002157951],"about_ca_topic_score_codex":0.00037299702,"about_ca_topic_score_gemma":0.00045247714,"teacher_disagreement_score":0.013992274,"about_ca_system_score_codex":0.0011192466,"about_ca_system_score_gemma":0.0007156296,"threshold_uncertainty_score":0.04680884},"labels":[],"label_agreement":null},{"id":"W2014643492","doi":"10.1007/s11590-009-0144-7","title":"An efficient string sorting algorithm for weighing matrices of small weight","year":2009,"lang":"en","type":"article","venue":"Optimization Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Wilfrid Laurier University","keywords":"Sorting; String (physics); Computational intelligence; Algorithm; Mathematics; Connection (principal bundle); Range (aeronautics); Combinatorics; Computer science; Artificial intelligence","score_opus":0.009961612166301382,"score_gpt":0.2369741017125232,"score_spread":0.22701248954622183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014643492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011405794,0.00017293474,0.9829434,0.00017680615,0.00016623059,0.00014263151,0.00021060884,0.0020152815,0.002766316],"genre_scores_gemma":[0.04062585,0.00012909425,0.9527642,0.00012523452,0.0000804476,0.00018104578,0.0005507653,0.00023671422,0.005306697],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99888235,0.0001420375,0.000107726235,0.00017148128,0.00059306424,0.00010329053],"domain_scores_gemma":[0.99835783,0.00057151937,0.000107638356,0.00036687215,0.0005149047,0.00008128294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068555505,0.001275167,0.0011737875,0.0017518445,0.0010673943,0.0017114452,0.0016493103,0.0012627702,0.010467031],"category_scores_gemma":[0.0044118785,0.00057430315,0.00072802237,0.00419124,0.00054203614,0.0023636827,0.0019814172,0.001452051,0.004501879],"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":[0.00031937924,0.00016159858,0.00036485406,0.00017654711,0.00003966698,0.00011653458,0.00010642985,0.025336586,0.03140592,0.031340577,0.01361236,0.8970195],"study_design_scores_gemma":[0.00025039495,0.0003557632,0.0007381053,0.000060555307,0.00006295507,0.0006236245,0.0001705475,0.7871998,0.05389024,0.12766632,0.028884819,0.00009689297],"about_ca_topic_score_codex":0.002106943,"about_ca_topic_score_gemma":0.0042419173,"teacher_disagreement_score":0.010467031,"about_ca_system_score_codex":0.00080254383,"about_ca_system_score_gemma":0.0017559688,"threshold_uncertainty_score":0.035015702},"labels":[],"label_agreement":null},{"id":"W2015431312","doi":"10.1145/1145768.1145788","title":"Succinct representation of finite abelian groups","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Abelian group; Computation; Constant (computer programming); Word (group theory); Group (periodic table); Elementary abelian group; Multiplication (music); Word problem (mathematics education); Inversion (geology); Computer science; Algebra over a field; Mathematics; Arithmetic; Discrete mathematics; Pure mathematics; Combinatorics; Algorithm; Programming language; Geometry; Physics","score_opus":0.012388662820392403,"score_gpt":0.24466737024130145,"score_spread":0.23227870742090903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015431312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14752969,0.0006463414,0.841063,0.00094862265,0.00012645985,0.00010099157,0.0004174837,0.001577017,0.0075903563],"genre_scores_gemma":[0.6791284,0.0005997171,0.31227,0.0002946851,0.00014830667,0.00017342743,0.0010585752,0.00021727919,0.006109576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984157,0.00052844995,0.00014315997,0.00020045516,0.0005126125,0.00019960722],"domain_scores_gemma":[0.9970439,0.0012548884,0.0002689003,0.0010669236,0.00028743665,0.000078068624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010875625,0.0006383583,0.0007201964,0.0007877602,0.0005917202,0.0023864396,0.0015260159,0.0009361467,0.0033612333],"category_scores_gemma":[0.0052225087,0.00026629475,0.0005182089,0.0016366608,0.0014302378,0.0070028603,0.0021179968,0.0011745996,0.0012639487],"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":[0.00063667196,0.00017375311,0.0009107476,0.00043696107,0.00004611478,0.00048590417,0.0012100125,0.109586634,0.015700972,0.69399685,0.0052217385,0.1715937],"study_design_scores_gemma":[0.000081060054,0.00014322509,0.000115794464,0.00008638102,0.000029203975,0.00016209963,0.00020849427,0.19923937,0.021677291,0.76677,0.011458489,0.000028594008],"about_ca_topic_score_codex":0.0005666145,"about_ca_topic_score_gemma":0.00086779863,"teacher_disagreement_score":0.0033612333,"about_ca_system_score_codex":0.0008239226,"about_ca_system_score_gemma":0.0008105175,"threshold_uncertainty_score":0.011244416},"labels":[],"label_agreement":null},{"id":"W2016222250","doi":"10.1007/s00453-009-9352-x","title":"Precision, Local Search and Unimodal Functions","year":2009,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics; Gray code; Combinatorics; Binary number; Theory of computation; Algorithm; Binary logarithm; Code (set theory); Constant (computer programming); Scaling; Base (topology); Distribution (mathematics); Binary code; Upper and lower bounds; Discrete mathematics; Computer science; Set (abstract data type); Geometry; Mathematical analysis","score_opus":0.010285115518313043,"score_gpt":0.2469077618712889,"score_spread":0.23662264635297586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016222250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07206536,0.019393448,0.8928977,0.0022188681,0.00028579775,0.00004748995,0.00023406067,0.0006026785,0.012254515],"genre_scores_gemma":[0.7139638,0.009055212,0.25527632,0.00059191865,0.00088782643,0.0002362701,0.00046143116,0.00031549492,0.019211814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981511,0.00063327764,0.000088047535,0.00028593454,0.00069841475,0.00014317814],"domain_scores_gemma":[0.991438,0.006386822,0.000499193,0.0010519229,0.00047411709,0.0001499624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002547434,0.0007482437,0.0017305912,0.0029716345,0.0009409008,0.002982358,0.001403,0.0018053761,0.0043490254],"category_scores_gemma":[0.023404425,0.0005668814,0.0004886681,0.0051393844,0.003727787,0.006091632,0.0021779747,0.0025379488,0.0007755613],"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":[0.0003575452,0.00007512173,0.0009613958,0.00040563042,0.00005637314,0.00011256713,0.00023168046,0.13233788,0.0024866734,0.6535373,0.0069353743,0.20250253],"study_design_scores_gemma":[0.000033521777,0.00006212184,0.00033478567,0.00005456009,0.000032747306,0.00016909897,0.000043565393,0.21370327,0.0017301756,0.78053546,0.0032728356,0.000027880465],"about_ca_topic_score_codex":0.0014242186,"about_ca_topic_score_gemma":0.0013808584,"teacher_disagreement_score":0.0043490254,"about_ca_system_score_codex":0.0017205087,"about_ca_system_score_gemma":0.0011281617,"threshold_uncertainty_score":0.014548957},"labels":[],"label_agreement":null},{"id":"W2016908520","doi":"10.1016/j.jda.2005.07.003","title":"A loop-free two-close Gray-code algorithm for listing k-ary Dyck words","year":2005,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Gray code; Combinatorics; Mathematics; Suffix; Algorithm; Gray (unit); String (physics); Computer science; Discrete mathematics","score_opus":0.017518718276061277,"score_gpt":0.2913363529879703,"score_spread":0.273817634711909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016908520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026897073,0.00019801351,0.96011966,0.00021325167,0.00011191018,0.00020893125,0.00017518298,0.004762619,0.0073133144],"genre_scores_gemma":[0.1399024,0.00010003054,0.8506575,0.00017590531,0.000033631524,0.00024975682,0.00050820824,0.00048735813,0.00788515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940705,0.00006323073,0.000044579516,0.00009821734,0.0003058106,0.00008109374],"domain_scores_gemma":[0.9991392,0.00024162026,0.00005922266,0.00023220222,0.00024174358,0.00008597023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035619165,0.0007696746,0.00081834284,0.001477981,0.00091714255,0.0014390264,0.0013095383,0.0011215786,0.011932972],"category_scores_gemma":[0.0022795224,0.00035436373,0.0004370373,0.001437943,0.00070856785,0.0014429691,0.0020950285,0.0011965352,0.0036566034],"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":[0.00061039295,0.00025966103,0.0006424834,0.00019037616,0.00003658141,0.00018388263,0.00023228896,0.025892274,0.035423435,0.04157244,0.01220783,0.8827483],"study_design_scores_gemma":[0.0007242411,0.0005698985,0.0012083371,0.00011103398,0.00007648506,0.00082766946,0.00029366932,0.7867868,0.08265976,0.09255932,0.034014426,0.00016839776],"about_ca_topic_score_codex":0.0038748682,"about_ca_topic_score_gemma":0.0067188386,"teacher_disagreement_score":0.011932972,"about_ca_system_score_codex":0.00090190815,"about_ca_system_score_gemma":0.0015115738,"threshold_uncertainty_score":0.039919734},"labels":[],"label_agreement":null},{"id":"W2018127461","doi":"10.1145/1099554.1099579","title":"Exact match search in sequence data using suffix trees","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Concordia University","funders":"","keywords":"Search engine indexing; Computer science; Suffix; Scalability; Suffix tree; Representation (politics); Compressed suffix array; Sequence (biology); Auxiliary memory; Suffix array; Computation; Theoretical computer science; Data structure; Algorithm; Artificial intelligence; Database","score_opus":0.16025357513354915,"score_gpt":0.36835448446067487,"score_spread":0.20810090932712572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018127461","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07174558,0.0012336744,0.92366993,0.00019540964,0.000044225737,0.00006250422,0.00038592276,0.0015153731,0.0011472827],"genre_scores_gemma":[0.24600248,0.0012903988,0.7497354,0.00010506762,0.000092170216,0.00014319632,0.0015273268,0.00013827867,0.0009656744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989618,0.00027285944,0.0001392503,0.00020298785,0.00036443226,0.000058749338],"domain_scores_gemma":[0.9962895,0.0020948828,0.0004889193,0.0006574443,0.00040415995,0.000065100896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012271713,0.00047755448,0.0009710477,0.00213682,0.0006286831,0.0012294065,0.0012686973,0.0008261541,0.0014127392],"category_scores_gemma":[0.008755066,0.00038215215,0.00048165937,0.005971852,0.0006540689,0.0047952808,0.00094376534,0.0006142073,0.0010525942],"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":[0.000688948,0.00033562395,0.0053543635,0.0009922137,0.00015660297,0.0005469808,0.0007011895,0.122362755,0.09335296,0.0670112,0.005226368,0.70327073],"study_design_scores_gemma":[0.000102962615,0.00054632034,0.0010792917,0.00005960332,0.00005763008,0.0008660055,0.0002166796,0.84273297,0.062355246,0.08040006,0.0115330815,0.000050091756],"about_ca_topic_score_codex":0.000757057,"about_ca_topic_score_gemma":0.0009013278,"teacher_disagreement_score":0.00213682,"about_ca_system_score_codex":0.00034895155,"about_ca_system_score_gemma":0.00070194155,"threshold_uncertainty_score":0.006489992},"labels":[],"label_agreement":null},{"id":"W2018303348","doi":"10.1109/mecbme.2014.6783270","title":"A space-efficient solution to find the maximum overlap using a compressed suffix array","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Saskatchewan","funders":"","keywords":"Compressed suffix array; Suffix; Computer science; Suffix array; Scalability; Suffix tree; String (physics); Data structure; String searching algorithm; Generalized suffix tree; Algorithm; Simple (philosophy); Matching (statistics); Space (punctuation); Theoretical computer science; Mathematics; Database","score_opus":0.021453869114542005,"score_gpt":0.2513221488608089,"score_spread":0.2298682797462669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018303348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014904473,0.00019915156,0.9803908,0.00025228568,0.00006629885,0.00010235091,0.00016424811,0.0011568483,0.0027636143],"genre_scores_gemma":[0.05425554,0.00013396253,0.94271064,0.000069319525,0.000058692305,0.0001438696,0.00036046864,0.00012532133,0.00214216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923134,0.00009883699,0.000060841376,0.00019808055,0.00031840955,0.00009246755],"domain_scores_gemma":[0.9987508,0.00050906406,0.00013159528,0.0002821274,0.00026145752,0.00006494786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064789795,0.0010815319,0.0010915092,0.0017443498,0.0009853406,0.0010975557,0.0016249988,0.0012423907,0.0070103877],"category_scores_gemma":[0.0036459262,0.0004405267,0.0008370054,0.0033014023,0.0006950721,0.0029527238,0.0015450779,0.0010957175,0.0024953303],"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":[0.0003983136,0.00031750923,0.0012235038,0.00039074742,0.00007487675,0.00032464485,0.00039931544,0.107658945,0.05366788,0.04381376,0.011262666,0.7804678],"study_design_scores_gemma":[0.00014513408,0.00034802544,0.00046387484,0.00004237776,0.000048340968,0.00077242684,0.00040309448,0.8967773,0.04011393,0.04514723,0.015688712,0.000049570284],"about_ca_topic_score_codex":0.001401523,"about_ca_topic_score_gemma":0.0023304871,"teacher_disagreement_score":0.0070103877,"about_ca_system_score_codex":0.0005534545,"about_ca_system_score_gemma":0.00202712,"threshold_uncertainty_score":0.023452103},"labels":[],"label_agreement":null},{"id":"W2018481847","doi":"10.1016/j.patrec.2014.11.013","title":"Order preserving pattern matching revisited","year":2014,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String searching algorithm; Pattern matching; Matching (statistics); 3-dimensional matching; Computer science; Perspective (graphical); Optimal matching; Order (exchange); Pattern recognition (psychology); Algorithm; Artificial intelligence; Mathematics; Blossom algorithm","score_opus":0.018638501242398343,"score_gpt":0.23391867916901593,"score_spread":0.21528017792661758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018481847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040650997,0.0032413697,0.9222768,0.0019707768,0.00048243444,0.000077658806,0.00018155223,0.0007370357,0.030381516],"genre_scores_gemma":[0.62534803,0.0042667375,0.32764238,0.0016439169,0.0007601671,0.00008157366,0.0005182737,0.00036294793,0.039376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886453,0.0001990672,0.00008490795,0.00027075125,0.0004608055,0.00011997443],"domain_scores_gemma":[0.9975163,0.0007328836,0.00014493855,0.0012489153,0.0003064755,0.000050586474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010244919,0.00041190287,0.00071779545,0.0014853397,0.00065680715,0.0016847221,0.0014821804,0.0012318229,0.0050734184],"category_scores_gemma":[0.0053228284,0.0004137651,0.0006183679,0.0025425123,0.0013721733,0.0035983934,0.0014365318,0.0015201401,0.0015188956],"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":[0.00019085086,0.000073217394,0.0007753055,0.00019130461,0.000050470328,0.0003091837,0.00014485726,0.011462077,0.013823593,0.6090684,0.0052875006,0.3586233],"study_design_scores_gemma":[0.000026975806,0.00009653343,0.0006770831,0.000028128297,0.000050098275,0.0010231765,0.00008630067,0.09917123,0.024606157,0.8557073,0.018500838,0.000026376456],"about_ca_topic_score_codex":0.0009195751,"about_ca_topic_score_gemma":0.00069624226,"teacher_disagreement_score":0.0050734184,"about_ca_system_score_codex":0.00049482536,"about_ca_system_score_gemma":0.0007320024,"threshold_uncertainty_score":0.016972303},"labels":[],"label_agreement":null},{"id":"W2019165514","doi":"10.1155/2013/793130","title":"Efficient Serial and Parallel Algorithms for Selection of Unique Oligos in EST Databases","year":2013,"lang":"en","type":"article","venue":"Advances in Bioinformatics","topic":"Algorithms and Data Compression","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":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Algorithm; Brute force; Oligonucleotide; Selection (genetic algorithm); Data mining; Database; Artificial intelligence; Gene; Biology","score_opus":0.015245693863047343,"score_gpt":0.2806853424212582,"score_spread":0.26543964855821084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019165514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01038478,0.0003205977,0.9846091,0.00011007302,0.000047186397,0.0001695007,0.0001808122,0.0032649925,0.0009130075],"genre_scores_gemma":[0.027306773,0.00021601918,0.9688639,0.000078197874,0.00003992068,0.00038211723,0.00078422413,0.00020679107,0.0021220152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981864,0.00028524303,0.00024807433,0.00039325864,0.0007176421,0.00016929176],"domain_scores_gemma":[0.9971251,0.0013730128,0.0002473872,0.00055719056,0.00061992474,0.000077411125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002409455,0.001797794,0.0013439294,0.0031287265,0.0012863575,0.0014908832,0.0024110968,0.001034695,0.003898865],"category_scores_gemma":[0.006765543,0.0007685617,0.0011275859,0.0048090154,0.001013444,0.0025414932,0.0019285906,0.0015375013,0.0029911676],"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":[0.00047719968,0.00025484603,0.0018560037,0.00023093833,0.000074100935,0.00020332925,0.0002007807,0.0929286,0.024407623,0.0166248,0.010106851,0.85263485],"study_design_scores_gemma":[0.00028289756,0.00015840324,0.0011175825,0.00003371249,0.0000711223,0.0005207661,0.00014073851,0.90328664,0.036291756,0.046150755,0.011888916,0.00005669406],"about_ca_topic_score_codex":0.0035661992,"about_ca_topic_score_gemma":0.0056789718,"teacher_disagreement_score":0.003898865,"about_ca_system_score_codex":0.0011378912,"about_ca_system_score_gemma":0.0020619428,"threshold_uncertainty_score":0.013042986},"labels":[],"label_agreement":null},{"id":"W2019406253","doi":"10.1145/2484028.2484088","title":"Faster and smaller inverted indices with treaps","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Merge (version control); Inverted index; Identifier; Computer science; ENCODE; Thresholding; Algorithm; Representation (politics); Data structure; Data compression; Theoretical computer science; Topology (electrical circuits); Mathematics; Artificial intelligence; Search engine indexing; Information retrieval; Combinatorics","score_opus":0.00908660978927224,"score_gpt":0.18672919600356194,"score_spread":0.1776425862142897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019406253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045108605,0.0013428858,0.924868,0.00046386407,0.00045785346,0.00031621923,0.003179206,0.012917184,0.0113461325],"genre_scores_gemma":[0.15977284,0.0007367948,0.8188328,0.00036359293,0.00036977648,0.0005055094,0.008788161,0.0019352181,0.008695357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970958,0.00031180654,0.00033057661,0.00042114832,0.0015930193,0.00024768186],"domain_scores_gemma":[0.9931757,0.0014874032,0.0006680668,0.0029991132,0.0014591309,0.00021064903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013175093,0.0011371527,0.001580353,0.004097946,0.0010906355,0.0039777975,0.00265416,0.0010658497,0.0077583995],"category_scores_gemma":[0.009805182,0.00068106886,0.00093910244,0.009053942,0.0011941099,0.009551701,0.002907216,0.002032831,0.004497882],"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":[0.0011475494,0.00040139502,0.0020785916,0.00050907873,0.00013504857,0.00033033415,0.000580301,0.04077029,0.052761238,0.13611259,0.044994764,0.7201788],"study_design_scores_gemma":[0.00036636752,0.0012923394,0.0017185388,0.00019808236,0.0001617352,0.0017589077,0.00060738594,0.5043657,0.17698298,0.18496664,0.1272002,0.000381084],"about_ca_topic_score_codex":0.0032985653,"about_ca_topic_score_gemma":0.0032848169,"teacher_disagreement_score":0.0077583995,"about_ca_system_score_codex":0.001170467,"about_ca_system_score_gemma":0.0019168102,"threshold_uncertainty_score":0.025954485},"labels":[],"label_agreement":null},{"id":"W2019497371","doi":"10.1016/j.jda.2009.01.002","title":"On the Ehrenfeucht–Mycielski sequence","year":2009,"lang":"pl","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Upper and lower bounds; Combinatorics; Ackermann function; Prefix; Mathematics; Sequence (biology); Suffix; Discrete mathematics; Inverse","score_opus":0.03914521642632646,"score_gpt":0.3010556464635271,"score_spread":0.26191043003720066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019497371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21632604,0.0045144605,0.7125467,0.003112743,0.00085216516,0.000083226994,0.00032128065,0.00026176937,0.06198166],"genre_scores_gemma":[0.85857016,0.0033605832,0.106010504,0.00072395784,0.00063316704,0.000106024905,0.0005382587,0.00016033195,0.029897086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993357,0.00021481713,0.000036993824,0.00008532409,0.00024252944,0.00008456423],"domain_scores_gemma":[0.99782914,0.0012913285,0.00017555317,0.00018833029,0.00035043847,0.00016514955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011898063,0.00063520763,0.00081279245,0.0020959238,0.0007803381,0.0012905563,0.0008059815,0.0014743726,0.004395411],"category_scores_gemma":[0.009380712,0.0002941377,0.0003878161,0.0015734304,0.0017464644,0.002936141,0.0019206309,0.0020428386,0.0012068902],"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":[0.0001372301,0.000028100743,0.00041908518,0.00006063558,0.000010625454,0.00012915548,0.00015304337,0.016437028,0.0023657186,0.941818,0.0019731515,0.03646836],"study_design_scores_gemma":[0.000031882668,0.000063520216,0.0003994167,0.000048273243,0.000010026223,0.0002878968,0.00006321479,0.112219825,0.001905882,0.8786758,0.0062675383,0.000026807422],"about_ca_topic_score_codex":0.0009832071,"about_ca_topic_score_gemma":0.0006468315,"teacher_disagreement_score":0.004395411,"about_ca_system_score_codex":0.000801718,"about_ca_system_score_gemma":0.00060622185,"threshold_uncertainty_score":0.014704168},"labels":[],"label_agreement":null},{"id":"W2020287344","doi":"10.1007/978-3-642-19222-7_23","title":"Skip Lift: A Probabilistic Alternative to Red-Black Trees","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Lift (data mining); Computer science; Pointer (user interface); Data structure; Probabilistic logic; Algorithm; Combinatorics; Theoretical computer science; Mathematics; Data mining; Artificial intelligence; Programming language","score_opus":0.025907399158147843,"score_gpt":0.2531766838766929,"score_spread":0.22726928471854504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020287344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007160877,0.0002677994,0.982477,0.00033279075,0.00020202168,0.000053733827,0.00025736363,0.0018228567,0.007425484],"genre_scores_gemma":[0.26790118,0.0006955604,0.70247453,0.0008083993,0.0006321534,0.00026328978,0.0011641243,0.0022953246,0.023765502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984615,0.00034441808,0.00006123002,0.00025605524,0.0006712743,0.00020555513],"domain_scores_gemma":[0.99662894,0.0012567003,0.0001387399,0.0012955533,0.00043872875,0.00024132094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019548286,0.00073051767,0.0012999343,0.001203361,0.0014752791,0.0019280877,0.0024570439,0.0015144626,0.013151753],"category_scores_gemma":[0.008200516,0.0006142623,0.0011089029,0.0020151772,0.0013967361,0.003892605,0.0045864056,0.0030925586,0.0033975616],"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":[0.0007177084,0.00015920217,0.0006642591,0.00019511867,0.00006050631,0.00016861701,0.00025160785,0.05893139,0.004246151,0.51103604,0.02460975,0.39895964],"study_design_scores_gemma":[0.000055128436,0.00007074123,0.00022456929,0.000048241283,0.000039742452,0.0001423908,0.00003901452,0.34173828,0.002145808,0.6384177,0.017043935,0.000034340672],"about_ca_topic_score_codex":0.001610158,"about_ca_topic_score_gemma":0.0029410531,"teacher_disagreement_score":0.013151753,"about_ca_system_score_codex":0.0006261372,"about_ca_system_score_gemma":0.0015108457,"threshold_uncertainty_score":0.04399705},"labels":[],"label_agreement":null},{"id":"W2020892353","doi":"10.1089/cmb.2009.0039","title":"On the Maximal Interval Subgraph of a Tree","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","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":"Trent University","funders":"","keywords":"Tree (set theory); Mathematics; Combinatorics; Interval (graph theory); Induced subgraph isomorphism problem; Interval tree; Subgraph isomorphism problem; Time complexity; Algorithm; Computational complexity theory; Discrete mathematics; Computer science; Tree structure; Graph; Binary tree; Line graph","score_opus":0.013870780396049845,"score_gpt":0.26742344192832346,"score_spread":0.2535526615322736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020892353","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23610507,0.0009037085,0.7518269,0.0009378276,0.000041128555,0.000082247585,0.00064973504,0.0005057864,0.008947628],"genre_scores_gemma":[0.5592474,0.0013096319,0.4303753,0.00024025736,0.00016247628,0.0001570052,0.0024522769,0.00028753656,0.0057682144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99952865,0.00016431417,0.000020668575,0.00011886141,0.00010514051,0.0000625019],"domain_scores_gemma":[0.997855,0.0015845376,0.00017725908,0.00017728985,0.00012779565,0.00007816552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005491367,0.00036995343,0.00079162396,0.0011115972,0.0006120717,0.0009119501,0.0006446157,0.00058604014,0.0033375763],"category_scores_gemma":[0.0042065782,0.00030258225,0.00062752137,0.0022624838,0.0008735865,0.0026319968,0.001012113,0.00071955257,0.0005165223],"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":[0.000547746,0.00017233769,0.0031892161,0.00077019626,0.000103295424,0.00076231913,0.00094555144,0.2940895,0.023260571,0.4003124,0.016098127,0.2597488],"study_design_scores_gemma":[0.00005371157,0.0000790257,0.0012154506,0.000051230778,0.000032924374,0.00039221326,0.00021383904,0.5099832,0.0042840578,0.47794235,0.005732262,0.000019712703],"about_ca_topic_score_codex":0.0014974802,"about_ca_topic_score_gemma":0.0012689135,"teacher_disagreement_score":0.0033375763,"about_ca_system_score_codex":0.00057481247,"about_ca_system_score_gemma":0.00036261562,"threshold_uncertainty_score":0.011165261},"labels":[],"label_agreement":null},{"id":"W2021216077","doi":"10.1142/s0129054105003704","title":"SORTING SUFFIXES OF TWO-PATTERN STRINGS","year":2005,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generalized suffix tree; Mathematics; Recursion (computer science); String (physics); Sorting; Generalization; Morphism; Suffix tree; Set (abstract data type); Lexicographical order; Iterated function; Time complexity; Combinatorics; Trie; Algorithm; Discrete mathematics; Data structure; Computer science","score_opus":0.017952371191051537,"score_gpt":0.3194346811573973,"score_spread":0.3014823099663458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021216077","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11344313,0.00043967777,0.87301606,0.00024521418,0.0001859142,0.00020615499,0.00030672216,0.0029642961,0.009192797],"genre_scores_gemma":[0.22070527,0.00027609442,0.76700777,0.00023900476,0.00007293239,0.00020020719,0.0013177376,0.00045062153,0.009730348],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998604,0.00024836423,0.0002124329,0.00028371494,0.0004933065,0.00015810675],"domain_scores_gemma":[0.9961804,0.0015983955,0.0002831549,0.0009907873,0.00084398064,0.00010328381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009751432,0.00056152506,0.0008752287,0.0014516134,0.00078039983,0.0015301527,0.0011051391,0.0010062851,0.0055265436],"category_scores_gemma":[0.005956025,0.0003859311,0.000821295,0.0025685912,0.0010621151,0.0034383978,0.0016839282,0.0010389051,0.0028185318],"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":[0.0006412177,0.00025825022,0.0024260597,0.00068193243,0.00008706994,0.0007677285,0.0011522936,0.018482875,0.090816274,0.23419216,0.005563226,0.64493096],"study_design_scores_gemma":[0.00018861445,0.00080067164,0.0022518428,0.00017765336,0.000093299976,0.0018377281,0.00047293882,0.35473663,0.1820614,0.3786451,0.07858685,0.00014726983],"about_ca_topic_score_codex":0.0005873266,"about_ca_topic_score_gemma":0.00090162153,"teacher_disagreement_score":0.0055265436,"about_ca_system_score_codex":0.0006943114,"about_ca_system_score_gemma":0.00095531,"threshold_uncertainty_score":0.01848811},"labels":[],"label_agreement":null},{"id":"W2021281986","doi":"10.1089/cmb.2006.13.1419","title":"Approximating Subtree Distances Between Phylogenies","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"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":"University of British Columbia; Graduate Center; National Science Foundation","keywords":"Tree (set theory); Approximation algorithm; Algorithm; Type (biology); Scheme (mathematics); Computer science; Mathematics; Combinatorics; Biology","score_opus":0.012095741316089299,"score_gpt":0.25926230497714375,"score_spread":0.24716656366105447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021281986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048840582,0.00063216675,0.94709396,0.0002511978,0.00007990082,0.000049753602,0.00024550426,0.0009832381,0.0018237821],"genre_scores_gemma":[0.22884497,0.00046877872,0.76696414,0.00011807983,0.000060470997,0.00011786729,0.0012964655,0.0002561044,0.001873188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984659,0.00030377507,0.000120705874,0.00032636835,0.00062116905,0.00016206512],"domain_scores_gemma":[0.99621385,0.0020313477,0.00030312545,0.0008933652,0.00042526503,0.00013311273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012592654,0.00077503826,0.0009736518,0.0019148808,0.0006198546,0.0013307445,0.0021499128,0.0013514766,0.0024322835],"category_scores_gemma":[0.013119925,0.00052507006,0.0009789319,0.0025603303,0.0008624804,0.0022787515,0.0023739652,0.0022490614,0.0010690312],"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":[0.00049236265,0.0001367903,0.0036962614,0.00030231668,0.00012648164,0.00024872422,0.00047799273,0.42057514,0.009772863,0.08399488,0.0062238933,0.4739522],"study_design_scores_gemma":[0.000046581597,0.000089959285,0.00062003604,0.000028713475,0.000030271445,0.0002817558,0.00007476959,0.9056756,0.0050665555,0.08370345,0.0043606474,0.000021569216],"about_ca_topic_score_codex":0.001963323,"about_ca_topic_score_gemma":0.0025511333,"teacher_disagreement_score":0.0024322835,"about_ca_system_score_codex":0.0010796562,"about_ca_system_score_gemma":0.0010013707,"threshold_uncertainty_score":0.008136809},"labels":[],"label_agreement":null},{"id":"W2021649182","doi":"10.5267/j.ijiec.2010.08.007","title":"Hat and squeeze functions, a way for making precise algorithms","year":2011,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Algorithm; Computer science; Mathematical optimization; Mathematics","score_opus":0.0587628926795012,"score_gpt":0.27735918316057284,"score_spread":0.21859629048107165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021649182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001088808,0.00014454975,0.99757284,0.000111750756,0.000056941324,0.00001582854,0.000010977166,0.00019539664,0.00080301095],"genre_scores_gemma":[0.1184644,0.00089180627,0.87358826,0.0004798512,0.00025113084,0.00018290467,0.000089515874,0.00043289943,0.0056190803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980855,0.0006729464,0.00015030334,0.0002840638,0.0007030817,0.00010414307],"domain_scores_gemma":[0.9966832,0.0016582276,0.00021546776,0.0009058469,0.00045540588,0.00008192136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028807332,0.0011454304,0.00092854013,0.0012490947,0.00090659986,0.0018654809,0.0010554062,0.0013306469,0.0046065757],"category_scores_gemma":[0.011058271,0.000720736,0.0010860375,0.0012273864,0.0027380497,0.0051925695,0.0019170409,0.0037723999,0.001709766],"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":[0.00034233677,0.00006053582,0.0008381919,0.00018874116,0.00010590631,0.00016278839,0.00034719412,0.106858276,0.014068868,0.6908565,0.0046173153,0.18155329],"study_design_scores_gemma":[0.00007966846,0.00026364875,0.00035964072,0.00007309603,0.000065442175,0.0004104367,0.000069243564,0.65015453,0.022650668,0.28484938,0.040917244,0.000106913314],"about_ca_topic_score_codex":0.00094711035,"about_ca_topic_score_gemma":0.00072171685,"teacher_disagreement_score":0.0046065757,"about_ca_system_score_codex":0.0005363886,"about_ca_system_score_gemma":0.0009056321,"threshold_uncertainty_score":0.0154105425},"labels":[],"label_agreement":null},{"id":"W2021659659","doi":"10.1109/lcomm.2012.120312.121420","title":"Variable-Length Constrained Sequence Codes","year":2012,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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":"Code word; Sequence (biology); Extension (predicate logic); Variable (mathematics); Mathematics; Set (abstract data type); Simple (philosophy); Code (set theory); Algorithm; Computer science; Discrete mathematics; Combinatorics; Decoding methods","score_opus":0.05890675649039083,"score_gpt":0.2978091330885597,"score_spread":0.23890237659816888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021659659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028408466,0.00046547828,0.96108574,0.00018045153,0.00006927181,0.00014373411,0.00039357334,0.00034646477,0.008906968],"genre_scores_gemma":[0.34583905,0.0008522014,0.6424163,0.0002533342,0.00008539884,0.00046764236,0.00083179364,0.00015741262,0.009096856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943954,0.00012073258,0.000047693204,0.00009493342,0.00024649606,0.000050562878],"domain_scores_gemma":[0.9990827,0.0002919108,0.00011606836,0.00020611423,0.00024907687,0.000054180728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041610163,0.00060540944,0.00054473407,0.00061522616,0.0004293392,0.0007646723,0.00095559127,0.0005228848,0.0037358266],"category_scores_gemma":[0.002435151,0.000260377,0.0003494186,0.0011919286,0.0006744649,0.0011138078,0.0012069213,0.00079040055,0.0011713014],"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":[0.00044241085,0.00008975008,0.00076528906,0.000488892,0.000037942824,0.0004455734,0.00019328283,0.12527688,0.103851005,0.5584436,0.0040677236,0.20589769],"study_design_scores_gemma":[0.000091236216,0.00034681844,0.0006681744,0.0001347457,0.000030432566,0.001133077,0.000068533314,0.56933177,0.11557091,0.26468652,0.047799934,0.0001379753],"about_ca_topic_score_codex":0.00062076095,"about_ca_topic_score_gemma":0.00074328383,"teacher_disagreement_score":0.0037358266,"about_ca_system_score_codex":0.00042574617,"about_ca_system_score_gemma":0.00088400644,"threshold_uncertainty_score":0.012497604},"labels":[],"label_agreement":null},{"id":"W2022117185","doi":"10.1145/509907.509950","title":"Cache-oblivious priority queue and graph algorithm applications","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Priority queue; Cache; Parallel computing; Cache-oblivious algorithm; Queue; Cache algorithms; Graph; Theoretical computer science; CPU cache; Algorithm; Computer network","score_opus":0.012986187047654944,"score_gpt":0.22292437205431814,"score_spread":0.2099381850066632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022117185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02226317,0.000645413,0.97063017,0.00067246624,0.00011011871,0.000084862426,0.00008447219,0.00097017235,0.004539156],"genre_scores_gemma":[0.31011865,0.0009256782,0.6813584,0.00038884595,0.0001903608,0.00018150502,0.0003471737,0.00026734677,0.006222126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869114,0.00029609373,0.000088990244,0.0001814904,0.00054923916,0.00019313842],"domain_scores_gemma":[0.99643695,0.0015563084,0.00025415048,0.00083066616,0.00078213937,0.00013974792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013409862,0.00052236073,0.00047068618,0.00087428687,0.0008488884,0.0017021537,0.0023019756,0.0007470887,0.0032633783],"category_scores_gemma":[0.007583458,0.0003763506,0.00039639094,0.0016258615,0.0010701739,0.004034786,0.0015507495,0.0017999515,0.0007396328],"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":[0.00038291325,0.00024695735,0.0012700121,0.00032906095,0.000050413488,0.0001471594,0.00039697246,0.17795247,0.010633022,0.5702517,0.01079989,0.22753939],"study_design_scores_gemma":[0.00006821497,0.00014261395,0.0001621284,0.000029081772,0.00003350121,0.00014022362,0.000057242723,0.75989515,0.011156692,0.21484508,0.013447391,0.000022756685],"about_ca_topic_score_codex":0.0037184197,"about_ca_topic_score_gemma":0.004904149,"teacher_disagreement_score":0.0037184197,"about_ca_system_score_codex":0.0019682439,"about_ca_system_score_gemma":0.0024960295,"threshold_uncertainty_score":0.014280736},"labels":[],"label_agreement":null},{"id":"W2023422760","doi":"10.1016/j.tcs.2015.02.009","title":"Smoothed heights of tries and patricia tries","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Zhejiang Sci-Tech University; Alberta Innovates - Technology Futures","keywords":"Trie; Bernoulli's principle; String (physics); Set (abstract data type); Mathematics; Combinatorics; Infinity; Binary number; Discrete mathematics; Algorithm; Data structure; Computer science; Physics; Mathematical analysis; Arithmetic; Mathematical physics","score_opus":0.014883339790127296,"score_gpt":0.24625883979561064,"score_spread":0.23137550000548335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023422760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54887,0.0017422775,0.34293148,0.002041281,0.0007810911,0.0000876299,0.00079589017,0.0015756686,0.10117462],"genre_scores_gemma":[0.94810295,0.00043661208,0.02605441,0.00027209427,0.0003160204,0.00005641912,0.0004386036,0.0003825284,0.023940483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99935275,0.00012374615,0.000028242413,0.000117593256,0.00019882234,0.0001788617],"domain_scores_gemma":[0.9978067,0.00094890693,0.0002515586,0.0004131906,0.00025756296,0.00032209343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007205358,0.0005961399,0.00081696146,0.0028890728,0.0012237565,0.0023439596,0.0013045401,0.001085738,0.014558321],"category_scores_gemma":[0.008120683,0.0005946446,0.00075312384,0.0017399125,0.002590585,0.0027603186,0.003011656,0.0027087384,0.0020132104],"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":[0.00015156527,0.0000178065,0.0009216789,0.000054150038,0.000018486558,0.000179028,0.00035344673,0.009104036,0.0021125404,0.9665062,0.0032425977,0.017338432],"study_design_scores_gemma":[0.00003192533,0.000058870835,0.001691304,0.000031453044,0.000025473564,0.0003940604,0.00036253693,0.05469178,0.0016155066,0.9332225,0.0078333,0.00004127865],"about_ca_topic_score_codex":0.00092836894,"about_ca_topic_score_gemma":0.001068637,"teacher_disagreement_score":0.014558321,"about_ca_system_score_codex":0.0006769626,"about_ca_system_score_gemma":0.0005174547,"threshold_uncertainty_score":0.04870242},"labels":[],"label_agreement":null},{"id":"W2023591833","doi":"10.1017/s0963548312000260","title":"Longest Path Distance in Random Circuits","year":2012,"lang":"en","type":"article","venue":"Combinatorics Probability Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Path (computing); Electronic circuit; Computer science; Mathematics; Electrical engineering; Computer network; Engineering","score_opus":0.022531646828238227,"score_gpt":0.24885589015984275,"score_spread":0.22632424333160453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023591833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43066958,0.003911766,0.54319346,0.0018602023,0.000110164154,0.00010506044,0.00081927073,0.000502688,0.018827733],"genre_scores_gemma":[0.9456387,0.0017079667,0.046238694,0.00024545734,0.0001547497,0.0001758365,0.00049521105,0.00017421773,0.005169103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893194,0.0003281546,0.00006250308,0.00027743977,0.00025847726,0.00014146215],"domain_scores_gemma":[0.9837076,0.012904984,0.0014781336,0.00069763715,0.00067814667,0.0005334955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013230004,0.00049467257,0.0007690434,0.0022123957,0.0007621424,0.0015802485,0.0012452484,0.0010353861,0.0032095492],"category_scores_gemma":[0.017873514,0.0003754291,0.0005175785,0.0018917873,0.0014722182,0.004586783,0.0011619045,0.0012961433,0.00036383572],"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":[0.00015233555,0.00004835411,0.0024667736,0.00023688818,0.000044455628,0.0002113502,0.00025836483,0.12990867,0.0036001697,0.8337404,0.0024469225,0.026885344],"study_design_scores_gemma":[0.000030151257,0.00006882972,0.0007368225,0.00003451509,0.000021109883,0.0002028228,0.000059538816,0.28886706,0.0015047011,0.7054812,0.0029690927,0.000024173996],"about_ca_topic_score_codex":0.00074087403,"about_ca_topic_score_gemma":0.0007822937,"teacher_disagreement_score":0.0032095492,"about_ca_system_score_codex":0.0017994196,"about_ca_system_score_gemma":0.00054442673,"threshold_uncertainty_score":0.013055742},"labels":[],"label_agreement":null},{"id":"W2023800056","doi":"10.1007/s00453-011-9544-z","title":"Shorthand Universal Cycles for Permutations","year":2011,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Combinatorics; Substring; Mathematics; Lexicographical order; Permutation (music); Parity of a permutation; Discrete mathematics; Symmetric group; Set (abstract data type); Cyclic permutation; Computer science; Physics","score_opus":0.04240240890345279,"score_gpt":0.25064698037265226,"score_spread":0.20824457146919947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023800056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03576677,0.016495597,0.8166552,0.00364931,0.004672651,0.00025353004,0.0020948849,0.0024009307,0.11801115],"genre_scores_gemma":[0.53542465,0.011828162,0.3303778,0.0034718085,0.0034384234,0.0012931239,0.0037196449,0.0033171822,0.1071293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987816,0.00029487442,0.00010289012,0.00034749368,0.00024918615,0.00022388985],"domain_scores_gemma":[0.9984376,0.0006838921,0.00013675488,0.00042887844,0.00020704822,0.00010575915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007860262,0.0014614522,0.0009047898,0.003077824,0.0018320732,0.003263144,0.0012165913,0.0015781553,0.020244723],"category_scores_gemma":[0.0043428377,0.0005486829,0.0008714022,0.0058580833,0.0025259855,0.0050878082,0.0024886476,0.003127593,0.005498127],"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":[0.000036217454,0.0000151944,0.00011984535,0.00010492087,0.000008913963,0.00008216851,0.0001634811,0.00088968157,0.0008095442,0.9228787,0.0105513865,0.064340025],"study_design_scores_gemma":[0.000005961155,0.00001419107,0.000052633124,0.00004290116,0.000008514784,0.00012323169,0.000038598548,0.001899897,0.0007526255,0.93894774,0.058102902,0.000010769825],"about_ca_topic_score_codex":0.0007240346,"about_ca_topic_score_gemma":0.0008206188,"teacher_disagreement_score":0.020244723,"about_ca_system_score_codex":0.0009887816,"about_ca_system_score_gemma":0.00086106354,"threshold_uncertainty_score":0.0677253},"labels":[],"label_agreement":null},{"id":"W202482776","doi":"","title":"Recycling Bits in LZ77-Based Compression","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Gas compressor; Data compression; Compression (physics); Algorithm; Physics","score_opus":0.014432180106864902,"score_gpt":0.25767258391708614,"score_spread":0.24324040381022125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W202482776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2508192,0.0040394883,0.7278031,0.00095289334,0.00023857689,0.00024115997,0.00021395848,0.0036452063,0.012046384],"genre_scores_gemma":[0.6278471,0.001012139,0.3633827,0.00028382565,0.00022429624,0.00018573117,0.00026640025,0.00021847946,0.006579266],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825174,0.00048157477,0.000114846116,0.00012600755,0.00084762735,0.00017821691],"domain_scores_gemma":[0.9973029,0.001283043,0.00030437385,0.0007801785,0.00027324155,0.00005627215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014112607,0.0006818658,0.00083032117,0.0025163742,0.0009794366,0.0011283788,0.0013563192,0.0013156859,0.0038158894],"category_scores_gemma":[0.00746798,0.00034728157,0.00046947255,0.0023821306,0.0020802766,0.0029657094,0.0022071,0.0010703951,0.0014860316],"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":[0.0023153552,0.0002020397,0.002687376,0.00050212344,0.0001172815,0.0011096516,0.000808148,0.039741147,0.10905361,0.12266932,0.005045562,0.7157485],"study_design_scores_gemma":[0.00028910275,0.0008230565,0.001903392,0.00024248015,0.00017510304,0.0046173846,0.00029060207,0.31397098,0.5726133,0.068263486,0.036597256,0.00021388168],"about_ca_topic_score_codex":0.0005401542,"about_ca_topic_score_gemma":0.00060669525,"teacher_disagreement_score":0.0038158894,"about_ca_system_score_codex":0.00092972326,"about_ca_system_score_gemma":0.00058703666,"threshold_uncertainty_score":0.012765408},"labels":[],"label_agreement":null},{"id":"W2026355363","doi":"10.1145/1871437.1871527","title":"Index structures for efficiently searching natural language text","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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; Parsing; Index (typography); Scalability; Class (philosophy); Phrase; Natural language; Construct (python library); Granularity; Information retrieval; Question answering; Parse tree; Word (group theory); Term (time); Natural language processing; Artificial intelligence; Data mining; Database; World Wide Web; Programming language","score_opus":0.006454486159736561,"score_gpt":0.27588224141304124,"score_spread":0.2694277552533047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026355363","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035651896,0.005799709,0.90853417,0.0010999821,0.00035987332,0.0010673519,0.010282696,0.02911931,0.008084986],"genre_scores_gemma":[0.09285698,0.0023396385,0.87942535,0.00035606496,0.0003279558,0.001016981,0.018293586,0.0013581987,0.004025252],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973496,0.00043559048,0.00040792546,0.00029622408,0.0013973279,0.00011324916],"domain_scores_gemma":[0.9902111,0.0040657734,0.0009627669,0.0026148201,0.0019369657,0.00020856004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020605715,0.00094806793,0.0013918616,0.0056594363,0.0013954239,0.002714468,0.0019277115,0.0010929097,0.005326321],"category_scores_gemma":[0.01691903,0.0007387791,0.000693386,0.012257712,0.0009820042,0.009206203,0.0022914698,0.0014770229,0.004221992],"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":[0.00055942615,0.00029749982,0.0033407684,0.0014125144,0.0001332961,0.00025543728,0.0010400057,0.010706318,0.022885239,0.061679874,0.08325681,0.81443286],"study_design_scores_gemma":[0.00047971267,0.00096199993,0.0043625925,0.00045219107,0.00023608311,0.002162649,0.0010716993,0.39117223,0.074182,0.3105802,0.21404615,0.00029251375],"about_ca_topic_score_codex":0.0025341855,"about_ca_topic_score_gemma":0.0030938452,"teacher_disagreement_score":0.0056594363,"about_ca_system_score_codex":0.0010036975,"about_ca_system_score_gemma":0.0020609675,"threshold_uncertainty_score":0.017818332},"labels":[],"label_agreement":null},{"id":"W2027483825","doi":"10.1016/j.disc.2007.11.048","title":"The coolest way to generate combinations","year":2008,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Combinatorics; String (physics); Prefix; Order (exchange); Discrete mathematics; Ranking (information retrieval); Position (finance); Computer science; Artificial intelligence","score_opus":0.024482692655504124,"score_gpt":0.25503089231226334,"score_spread":0.2305481996567592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027483825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029409666,0.00058447587,0.93982404,0.0013721914,0.0007241886,0.00021469207,0.0006205956,0.003799753,0.023450458],"genre_scores_gemma":[0.25721344,0.00042101232,0.71239513,0.00093829836,0.00033663595,0.00047306917,0.0011897631,0.0034110066,0.023621555],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99752766,0.0006658449,0.00018199992,0.00047033103,0.0009360913,0.0002180619],"domain_scores_gemma":[0.9953237,0.0012782041,0.00016545442,0.0023705396,0.00070395455,0.0001582081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014895606,0.0011526297,0.0010282736,0.0015672648,0.0016432069,0.0031654611,0.0015955353,0.0012886286,0.020701356],"category_scores_gemma":[0.011075,0.0008952275,0.0015466956,0.0010675326,0.002070282,0.004647851,0.004655037,0.002978184,0.0060418523],"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":[0.0012693978,0.00018526785,0.001961223,0.0006853209,0.00025812673,0.0005919995,0.00084153976,0.021703484,0.036671087,0.33354875,0.039501473,0.5627824],"study_design_scores_gemma":[0.00020324341,0.00037032,0.0007233824,0.0002923115,0.00022619405,0.0017425222,0.00032845713,0.11516207,0.05200702,0.7333719,0.095430754,0.00014176207],"about_ca_topic_score_codex":0.0002672241,"about_ca_topic_score_gemma":0.0006544402,"teacher_disagreement_score":0.020701356,"about_ca_system_score_codex":0.00054300186,"about_ca_system_score_gemma":0.00088969636,"threshold_uncertainty_score":0.06925291},"labels":[],"label_agreement":null},{"id":"W2027628524","doi":"10.3115/1599081.1599120","title":"Homotopy-based semi-supervised Hidden Markov Models for sequence labeling","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence labeling; Hidden Markov model; Pattern recognition (psychology); Computer science; Artificial intelligence; Homotopy; TRACE (psycholinguistics); Markov chain; Semi-supervised learning; Sequence (biology); Mathematics; Machine learning; Task (project management)","score_opus":0.06524728755304249,"score_gpt":0.26995655626823367,"score_spread":0.20470926871519118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027628524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031518645,0.000044426757,0.9961079,0.000033916236,0.0000063358348,0.000017036078,0.000029386816,0.00043823305,0.00017095068],"genre_scores_gemma":[0.19535825,0.00014245119,0.80202436,0.00009559817,0.000039963066,0.000276644,0.00047294775,0.00022540567,0.0013642911],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985569,0.00073320855,0.00006571618,0.00028765356,0.0002993687,0.000057140744],"domain_scores_gemma":[0.99307793,0.004735263,0.00036218317,0.0011512227,0.00057935517,0.00009405033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023084283,0.0006564545,0.0009144407,0.0010029074,0.00055659,0.00064967404,0.0018906262,0.0010766648,0.002027014],"category_scores_gemma":[0.0101994565,0.000509876,0.00075122225,0.00091307383,0.0011096679,0.002464207,0.0012015199,0.002060998,0.0012524973],"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":[0.00021187712,0.00014728738,0.00090845075,0.0001222204,0.000068914596,0.00009532161,0.00027312755,0.60206497,0.00801489,0.029661072,0.0019709156,0.35646093],"study_design_scores_gemma":[0.000004275546,0.000016676899,0.000060260285,0.0000045331362,0.0000025228683,0.000018411383,0.00000853223,0.9829164,0.0016842083,0.014944451,0.00033339392,0.000006363781],"about_ca_topic_score_codex":0.0021794995,"about_ca_topic_score_gemma":0.0037431812,"teacher_disagreement_score":0.0023084283,"about_ca_system_score_codex":0.0008093783,"about_ca_system_score_gemma":0.001064848,"threshold_uncertainty_score":0.012208283},"labels":[],"label_agreement":null},{"id":"W2028026094","doi":"10.1145/1835449.1835573","title":"Agro-Gator","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Computer science; Table (database); Statistical analysis; Data mining; Statistics; Mathematics","score_opus":0.004193626204986694,"score_gpt":0.21340409778412311,"score_spread":0.20921047157913641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028026094","genre_codex":"software","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020714542,0.0012294992,0.0804316,0.0024338944,0.0017915427,0.001058163,0.28466383,0.37137637,0.23630057],"genre_scores_gemma":[0.07368132,0.0016557226,0.18673351,0.0023739499,0.00041531675,0.002014115,0.43536642,0.102321774,0.19543782],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883145,0.00020979044,0.00008254158,0.00040816373,0.0003289481,0.00013914771],"domain_scores_gemma":[0.99703336,0.0005822089,0.00020468856,0.0011072326,0.0006459139,0.00042670913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024050602,0.0010387413,0.0014796618,0.0022105975,0.001467168,0.0032640796,0.0018229237,0.00089448184,0.13563398],"category_scores_gemma":[0.0046695797,0.0008763462,0.0011180919,0.0030965554,0.00065272884,0.0017378276,0.0022863813,0.0018373495,0.13945945],"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":[0.00268603,0.0002147819,0.008198995,0.0011154737,0.00013315574,0.0003688812,0.0006507065,0.00038514187,0.029865947,0.012544509,0.76743853,0.17639787],"study_design_scores_gemma":[0.00015558551,0.00008586833,0.0072389604,0.0001003556,0.000059272912,0.00026871593,0.000104954146,0.0012847513,0.01022745,0.0031501248,0.9772752,0.000048796297],"about_ca_topic_score_codex":0.00344032,"about_ca_topic_score_gemma":0.0034121776,"teacher_disagreement_score":0.13563398,"about_ca_system_score_codex":0.00071156933,"about_ca_system_score_gemma":0.0019496694,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2028772559","doi":"10.1145/2463372.2463454","title":"Generalizing the improved run-time complexity algorithm for non-dominated sorting","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Sorting; Algorithm; Constraint (computer-aided design); Computer science; Limiting; Sorting algorithm; Time complexity; Point (geometry); Computational complexity theory; Reduction (mathematics); Mathematical optimization; Mathematics","score_opus":0.023093439347965976,"score_gpt":0.2557412610820981,"score_spread":0.23264782173413212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028772559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050941724,0.00026341973,0.9872657,0.0002210089,0.00011248913,0.00009920506,0.00005664968,0.002281921,0.004605503],"genre_scores_gemma":[0.06867895,0.00029210257,0.92383015,0.0003202226,0.0001555385,0.00015016277,0.0004364203,0.0005371267,0.0055992524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956216,0.000721578,0.00027807668,0.00057122984,0.0023991913,0.00040835483],"domain_scores_gemma":[0.99607134,0.0013994032,0.00020624198,0.00111323,0.001098045,0.00011177767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026336722,0.0014446244,0.00120019,0.0019711966,0.0008522791,0.0018466268,0.0028268315,0.0012935158,0.004192948],"category_scores_gemma":[0.009707036,0.00050089846,0.0015238205,0.0020307687,0.0011705685,0.0026507187,0.0020446389,0.002961667,0.0019540435],"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":[0.00033923978,0.00033570203,0.0011183677,0.00030633103,0.0000927013,0.00014362295,0.00020587818,0.22874323,0.025414037,0.06928977,0.015717948,0.65829307],"study_design_scores_gemma":[0.000074471216,0.00010625556,0.00047076773,0.000028425009,0.0000343172,0.00016018563,0.00002914366,0.9455931,0.012850942,0.027934782,0.012681931,0.000035615907],"about_ca_topic_score_codex":0.009201616,"about_ca_topic_score_gemma":0.016584396,"teacher_disagreement_score":0.009201616,"about_ca_system_score_codex":0.0027772791,"about_ca_system_score_gemma":0.005006594,"threshold_uncertainty_score":0.020150661},"labels":[],"label_agreement":null},{"id":"W2029596791","doi":"","title":"Speeding up random walks with neighborhood exploration","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"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":"Combinatorics; Random walk; Hypercube; Vertex (graph theory); Mathematics; Random graph; Graph; Undirected graph; Random regular graph; Discrete mathematics; Line graph; Statistics; Pathwidth","score_opus":0.02973627052051079,"score_gpt":0.24637905122523143,"score_spread":0.21664278070472065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029596791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17018831,0.0009842247,0.8181606,0.0005432923,0.00013058678,0.00025467653,0.00014762422,0.0029552493,0.0066354447],"genre_scores_gemma":[0.6964905,0.0004273855,0.29670462,0.0001710099,0.00010367517,0.00035802487,0.0002503121,0.00024193151,0.0052524894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988933,0.0003927427,0.000049270202,0.00021565928,0.0002507895,0.00019819474],"domain_scores_gemma":[0.995118,0.0032662002,0.00030575675,0.0008555751,0.0002411581,0.00021333761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014819666,0.0010225066,0.00146374,0.0011451974,0.00068000006,0.0008958649,0.0016831453,0.0013982754,0.0027941614],"category_scores_gemma":[0.008438091,0.0005915795,0.0006828763,0.0012788537,0.0012773455,0.00337616,0.0021533936,0.001006566,0.0008935457],"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":[0.0010314274,0.00020523505,0.0015323687,0.00017817547,0.00006525788,0.00030902433,0.00024581063,0.8196054,0.010033576,0.0533497,0.0034011956,0.110042885],"study_design_scores_gemma":[0.000062507504,0.00008532054,0.000077795405,0.0000065239187,0.00001053011,0.00005820964,0.000015199872,0.9807757,0.0016661033,0.016324611,0.00090893905,0.000008401486],"about_ca_topic_score_codex":0.0016785174,"about_ca_topic_score_gemma":0.0019995596,"teacher_disagreement_score":0.0027941614,"about_ca_system_score_codex":0.00065446895,"about_ca_system_score_gemma":0.0006346965,"threshold_uncertainty_score":0.009347439},"labels":[],"label_agreement":null},{"id":"W2030393641","doi":"10.1186/1471-2105-12-s1-s55","title":"Closest string with outliers","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"String (physics); Hamming distance; Outlier; Combinatorics; Integer (computer science); String metric; Edit distance; Bounded function; Hamming code; Set (abstract data type); Discrete mathematics; Algorithm; Mathematics; String searching algorithm; Computer science; Artificial intelligence; Pattern matching","score_opus":0.04317960402421332,"score_gpt":0.2097569128317822,"score_spread":0.16657730880756888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030393641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050822787,0.001690372,0.9345255,0.0034435296,0.00029849872,0.00029323908,0.0021652828,0.002485793,0.004275045],"genre_scores_gemma":[0.39466217,0.0014439012,0.58612734,0.0014970531,0.0005819199,0.0008622445,0.0060529173,0.00075999077,0.008012457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99131155,0.0022144641,0.0009140801,0.0029368086,0.002150221,0.00047298908],"domain_scores_gemma":[0.96903676,0.019932328,0.0029231508,0.0057058553,0.0016436195,0.00075827737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036673115,0.0015303966,0.0034442327,0.002618296,0.0017714688,0.0034351677,0.0052621826,0.0041617677,0.0063837003],"category_scores_gemma":[0.039534796,0.00086409063,0.002121172,0.0059620407,0.002741758,0.008788978,0.004778843,0.005034002,0.002577749],"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":[0.0016807896,0.00045940987,0.007939424,0.0014005787,0.0002362859,0.0010488058,0.0008290714,0.4882148,0.0059219967,0.18220085,0.031767927,0.27830008],"study_design_scores_gemma":[0.00007807604,0.00015564502,0.00045998246,0.000103380495,0.000032267057,0.0006345628,0.00014543188,0.69996405,0.0035606713,0.28743634,0.007382172,0.000047399248],"about_ca_topic_score_codex":0.0020611412,"about_ca_topic_score_gemma":0.0013922567,"teacher_disagreement_score":0.0063837003,"about_ca_system_score_codex":0.0021205884,"about_ca_system_score_gemma":0.0024675345,"threshold_uncertainty_score":0.02135557},"labels":[],"label_agreement":null},{"id":"W2030934401","doi":"10.1016/j.comcom.2004.06.005","title":"A fast string search algorithm for deep packet classification","year":2004,"lang":"en","type":"article","venue":"Computer Communications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Algorithm; Time complexity; String (physics); Commentz-Walter algorithm; Set (abstract data type); String searching algorithm; Boyer–Moore string search algorithm; Network packet; Pattern matching; Artificial intelligence; Mathematics","score_opus":0.07407034828581271,"score_gpt":0.32024497699178534,"score_spread":0.24617462870597262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030934401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058639334,0.00046614604,0.98872954,0.00019147818,0.00018149927,0.0000957248,0.00033860057,0.003079056,0.0010539402],"genre_scores_gemma":[0.060336024,0.00040173047,0.9299536,0.00026155813,0.00016612776,0.00033273132,0.0015591324,0.00033876038,0.0066504115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890494,0.00023063376,0.000109635424,0.00019887714,0.00045072645,0.00010509875],"domain_scores_gemma":[0.9979504,0.00093146396,0.00009304171,0.00043940914,0.00051313743,0.000072659845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001422086,0.0011616101,0.0015782372,0.0026250079,0.0011491221,0.0016305519,0.0021710105,0.0019878054,0.010390883],"category_scores_gemma":[0.0053125126,0.00058669184,0.0008291826,0.0043161362,0.0006587527,0.0024491188,0.0020700376,0.0022685812,0.0059296107],"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":[0.00038356095,0.00013469058,0.0004617728,0.00009801127,0.00005718964,0.000069149326,0.00004769359,0.020894703,0.008498925,0.012561425,0.012804333,0.94398844],"study_design_scores_gemma":[0.0001293033,0.00015913515,0.00052423705,0.00003633423,0.000053427775,0.00022218836,0.000043820968,0.9382352,0.011625656,0.039844237,0.009089416,0.000037005975],"about_ca_topic_score_codex":0.0035258755,"about_ca_topic_score_gemma":0.004254504,"teacher_disagreement_score":0.010390883,"about_ca_system_score_codex":0.00079001614,"about_ca_system_score_gemma":0.002120734,"threshold_uncertainty_score":0.034760952},"labels":[],"label_agreement":null},{"id":"W2031626180","doi":"10.1109/tip.2014.2363411","title":"An Innovative Lossless Compression Method for Discrete-Color Images","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"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 Victoria; University of Northern British Columbia","funders":"","keywords":"Lossless compression; Artificial intelligence; Huffman coding; Binary image; Codebook; Computer vision; Arithmetic coding; Data compression; Computer science; Pattern recognition (psychology); Color depth; Mathematics; Color quantization; Color image; Image processing; Context-adaptive binary arithmetic coding; Image (mathematics)","score_opus":0.0170230023903693,"score_gpt":0.3293292704620075,"score_spread":0.3123062680716382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031626180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01937386,0.0013542686,0.9755182,0.00022097057,0.00025257326,0.00009826723,0.00014387305,0.00097282516,0.0020652062],"genre_scores_gemma":[0.19522355,0.0017201932,0.79257137,0.00031802006,0.00030160227,0.00016859478,0.0005804614,0.00020724582,0.008908968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961275,0.000028605258,0.000016831083,0.000048500642,0.00027124464,0.000022215041],"domain_scores_gemma":[0.9996222,0.00008634457,0.000036712085,0.00009335478,0.00014142902,0.00001989984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024552838,0.00049631146,0.0003831566,0.001249826,0.00025918346,0.00048509086,0.0008870795,0.00045271293,0.0019728127],"category_scores_gemma":[0.00094013737,0.00019226343,0.00037301,0.00091447384,0.00039897626,0.0010173697,0.0005091077,0.00071537966,0.0008363875],"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":[0.0002917655,0.000102850194,0.0004096714,0.0003373682,0.000040929164,0.0002784776,0.00012030611,0.012395092,0.2760273,0.009007518,0.0048077903,0.6961809],"study_design_scores_gemma":[0.0001076226,0.00038204464,0.0022614985,0.00007823329,0.00009376614,0.0034255602,0.00007684724,0.49958372,0.45071512,0.0048632226,0.03831595,0.0000964904],"about_ca_topic_score_codex":0.0009311461,"about_ca_topic_score_gemma":0.0009806004,"teacher_disagreement_score":0.0019728127,"about_ca_system_score_codex":0.00030958877,"about_ca_system_score_gemma":0.00034775815,"threshold_uncertainty_score":0.006599784},"labels":[],"label_agreement":null},{"id":"W2031663903","doi":"10.1145/1345206.1345222","title":"A case study in SIMD text processing with parallel bit streams","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"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; SIMD; Byte; Parallel computing; Transcoding; Stream processing; Search engine indexing; Decoding methods; Bitstream; Algorithm; Computer hardware; Artificial intelligence","score_opus":0.03486872640238996,"score_gpt":0.2650413089250565,"score_spread":0.23017258252266654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031663903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4599318,0.0026836249,0.48184228,0.001980024,0.0002741387,0.0004904068,0.0004940995,0.0030439065,0.04925975],"genre_scores_gemma":[0.6598576,0.0010223157,0.32562155,0.00021889468,0.00013113824,0.00018255912,0.00026668966,0.00023213551,0.012467046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911875,0.00023735955,0.00004331197,0.000110106565,0.00041489434,0.000075575386],"domain_scores_gemma":[0.9986761,0.00075058255,0.000058549213,0.00020829006,0.00024202105,0.00006434459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007115188,0.0005408943,0.00062265614,0.0005536537,0.0009967226,0.0017461384,0.0010243,0.0016115054,0.003471187],"category_scores_gemma":[0.0023176433,0.00030599735,0.00064041157,0.0019212415,0.00096042646,0.0016321804,0.0007608982,0.0007953512,0.0009329635],"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":[0.0026719843,0.00092527753,0.012632892,0.0013221744,0.00023081296,0.02568237,0.0026023206,0.30777866,0.13248853,0.106375545,0.022953795,0.3843356],"study_design_scores_gemma":[0.00025060636,0.0009895646,0.0024307745,0.00008306876,0.000069885435,0.009699167,0.0008731827,0.7156061,0.18345626,0.027669797,0.058779933,0.00009168622],"about_ca_topic_score_codex":0.0018621747,"about_ca_topic_score_gemma":0.0017952013,"teacher_disagreement_score":0.003471187,"about_ca_system_score_codex":0.00064631907,"about_ca_system_score_gemma":0.00052527105,"threshold_uncertainty_score":0.011612296},"labels":[],"label_agreement":null},{"id":"W2032287082","doi":"10.1016/j.jcss.2011.01.003","title":"A three-string approach to the closest string problem","year":2011,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"String (physics); Mathematics; Combinatorics; Computer science; Theoretical physics; Physics","score_opus":0.0543624952810548,"score_gpt":0.23728972868137221,"score_spread":0.1829272334003174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032287082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046577575,0.0006010567,0.9864053,0.0011236822,0.00027221808,0.00004451358,0.00010679099,0.00017608637,0.006612556],"genre_scores_gemma":[0.16878271,0.0021454403,0.8065449,0.0009458974,0.0012497354,0.00028443412,0.0007405037,0.0004069488,0.018899411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967064,0.0013045309,0.00022689375,0.00050367316,0.0010570277,0.0002014485],"domain_scores_gemma":[0.9942729,0.003519197,0.00026007686,0.00096171326,0.00073001144,0.0002561595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025505072,0.00083931716,0.0021196716,0.0029807081,0.0017941514,0.0034479515,0.005262809,0.005250611,0.014704579],"category_scores_gemma":[0.015971325,0.00065445487,0.0018100791,0.0052102576,0.0026790216,0.00760388,0.0046937005,0.004944895,0.0033814202],"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":[0.00018783797,0.0001689448,0.00035331812,0.00023646957,0.0000717606,0.0002492718,0.00022262106,0.11479113,0.0014157722,0.73718745,0.011399405,0.13371602],"study_design_scores_gemma":[0.000034610042,0.000045237834,0.000053883294,0.000024727091,0.000014313234,0.00013839068,0.000059151796,0.3872999,0.00054717244,0.6065929,0.005163289,0.000026478123],"about_ca_topic_score_codex":0.0016862634,"about_ca_topic_score_gemma":0.0010288149,"teacher_disagreement_score":0.014704579,"about_ca_system_score_codex":0.0011900471,"about_ca_system_score_gemma":0.0015218585,"threshold_uncertainty_score":0.049191713},"labels":[],"label_agreement":null},{"id":"W2032534941","doi":"10.2498/cit.2002.01.04","title":"The Design and Implementation of SPARK, a Toolkit for Implementing Domain-Specific Languages","year":2002,"lang":"en","type":"article","venue":"Journal of Computing and Information Technology","topic":"Algorithms and Data Compression","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 Calgary","funders":"","keywords":"SPARK (programming language); Computer science; Python (programming language); Domain (mathematical analysis); Programming language; Domain-specific language; Software engineering","score_opus":0.014221259856182644,"score_gpt":0.27354078086352496,"score_spread":0.2593195210073423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032534941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022498884,0.00014217386,0.9814036,0.00030745598,0.00016704793,0.00050720543,0.00021940013,0.012233429,0.002769826],"genre_scores_gemma":[0.024184832,0.00030238336,0.96552193,0.00037266003,0.00007661659,0.0008984092,0.0012114203,0.0036777963,0.0037539557],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9935557,0.0014351832,0.0008554445,0.001059835,0.002512993,0.00058077986],"domain_scores_gemma":[0.9937376,0.0010096343,0.00041694354,0.0016618839,0.0023230573,0.0008508796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065702563,0.00087304524,0.0010634627,0.0008752546,0.0015356065,0.0036155668,0.0047467626,0.00148955,0.0033989393],"category_scores_gemma":[0.014521359,0.0015839632,0.0018400737,0.0011675834,0.0021253282,0.00456006,0.004153929,0.005248719,0.0042271335],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009962013,0.00069827447,0.0044136634,0.0027364895,0.00048198554,0.0010363074,0.004605795,0.06763568,0.067018114,0.24292499,0.13463634,0.4728163],"study_design_scores_gemma":[0.00036412507,0.00043755872,0.0015396897,0.00032532422,0.00021128931,0.001839746,0.00056215806,0.21533391,0.092522986,0.10518186,0.5812813,0.00039995988],"about_ca_topic_score_codex":0.0021781682,"about_ca_topic_score_gemma":0.0016546588,"teacher_disagreement_score":0.0065702563,"about_ca_system_score_codex":0.0009784852,"about_ca_system_score_gemma":0.0050928867,"threshold_uncertainty_score":0.034747243},"labels":[],"label_agreement":null},{"id":"W2032553706","doi":"10.1016/j.orl.2013.04.002","title":"Game theory to a friend’s rescue","year":2013,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Game theory; Computer science; Psychology; Mathematics; Mathematical economics","score_opus":0.04051551192477621,"score_gpt":0.3415616473245901,"score_spread":0.3010461353998139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032553706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048155457,0.0040121432,0.7156404,0.03803347,0.001972448,0.00012484916,0.00020284374,0.00013969527,0.1917187],"genre_scores_gemma":[0.8748474,0.001979429,0.04272056,0.0030398306,0.0006736859,0.00016022408,0.00008866728,0.00009965889,0.07639055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988242,0.0007927135,0.000029059342,0.00011275581,0.00013705007,0.00010419699],"domain_scores_gemma":[0.9977985,0.0016405634,0.00007430269,0.0001253904,0.00019728485,0.000163809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001340676,0.0006828965,0.00089039135,0.0007439843,0.0013013211,0.002517331,0.0013177841,0.00279122,0.01138735],"category_scores_gemma":[0.007671194,0.00028412355,0.0007557138,0.0006462215,0.0041219695,0.0037722816,0.0015739774,0.0029294954,0.000977012],"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":[0.000022173874,0.000019580342,0.00007168491,0.000035941364,0.000014883371,0.00004325989,0.00015352151,0.010603709,0.00006400785,0.97880816,0.0048324834,0.005330538],"study_design_scores_gemma":[0.000010045025,0.000012907221,0.00003076405,0.0000140529955,0.0000042743295,0.000021751679,0.00011122302,0.020757584,0.0000331218,0.9732674,0.005731477,0.0000055166424],"about_ca_topic_score_codex":0.0047286227,"about_ca_topic_score_gemma":0.002396602,"teacher_disagreement_score":0.01138735,"about_ca_system_score_codex":0.0017624912,"about_ca_system_score_gemma":0.0011613087,"threshold_uncertainty_score":0.03809446},"labels":[],"label_agreement":null},{"id":"W2033323609","doi":"10.1145/2594538.2594557","title":"Categorical range maxima queries","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Division of Computing and Communication Foundations","keywords":"Linear space; Maxima; Combinatorics; Iterated function; Position (finance); Mathematics; Element (criminal law); Range (aeronautics); Generalization; Categorical variable; Logarithm; Space (punctuation); Binary logarithm; Set (abstract data type); Discrete mathematics; Computer science; Mathematical analysis; Statistics","score_opus":0.008602459522003812,"score_gpt":0.21210121108554492,"score_spread":0.2034987515635411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033323609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15086204,0.0033108855,0.7780364,0.004212425,0.00030941577,0.0007676973,0.011705567,0.01728659,0.03350891],"genre_scores_gemma":[0.6347426,0.00079745974,0.33824158,0.0015576306,0.0004201786,0.00065888633,0.011109327,0.0012917413,0.011180582],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99347925,0.0012535556,0.0006769652,0.0020215672,0.0016945199,0.00087410526],"domain_scores_gemma":[0.9892314,0.0052469578,0.00087875576,0.003238151,0.0009061759,0.0004985563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029838954,0.0010622345,0.002420179,0.0017239494,0.0014773478,0.004097113,0.004896434,0.002763461,0.016598836],"category_scores_gemma":[0.015757546,0.0007676877,0.0016136696,0.004137825,0.0019145656,0.016661523,0.006575671,0.0024206478,0.0031359356],"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":[0.0038419175,0.00091896916,0.014526388,0.0024722817,0.0003071631,0.0009113005,0.002100739,0.07281346,0.04821289,0.3127853,0.08077712,0.4603325],"study_design_scores_gemma":[0.0004701256,0.0007231949,0.0028065417,0.00020658872,0.00016518052,0.001779329,0.0019126489,0.4101068,0.02942775,0.49492866,0.05729168,0.00018153318],"about_ca_topic_score_codex":0.0018076142,"about_ca_topic_score_gemma":0.002066998,"teacher_disagreement_score":0.016598836,"about_ca_system_score_codex":0.00186035,"about_ca_system_score_gemma":0.0014459691,"threshold_uncertainty_score":0.0555287},"labels":[],"label_agreement":null},{"id":"W2034389879","doi":"10.5555/1109557.1109605","title":"Asymmetric balanced allocation with simple hash functions","year":2006,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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":"Hash function; Computer science; Simple (philosophy); Extension (predicate logic); Hash table; Double hashing; Hash chain; Function (biology); Theoretical computer science; Programming language","score_opus":0.007456395841719261,"score_gpt":0.2256655254684238,"score_spread":0.21820912962670455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034389879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06664529,0.00050358026,0.9144444,0.00037790625,0.00023152622,0.00021825591,0.00018457542,0.001084102,0.016310448],"genre_scores_gemma":[0.7694152,0.0005131195,0.21018912,0.0003171273,0.00028701941,0.00040660196,0.00033119298,0.00029742214,0.018243147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99653506,0.0007851327,0.00022319928,0.00043993403,0.0013991052,0.0006176044],"domain_scores_gemma":[0.9948139,0.0011187333,0.00040760566,0.0029024875,0.0005175184,0.00023973307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023481715,0.00078948674,0.0011357297,0.00090186344,0.001421426,0.0021859496,0.0022992746,0.0013638149,0.009160792],"category_scores_gemma":[0.007679514,0.00049194193,0.00047141587,0.0016130742,0.0019982194,0.0074965255,0.0055003986,0.0014751604,0.004190854],"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":[0.0016399014,0.00025971877,0.0010485344,0.00021330283,0.000048861853,0.00025208577,0.00033539583,0.05132722,0.030837735,0.73725903,0.0076622088,0.16911599],"study_design_scores_gemma":[0.0003102951,0.00032994672,0.00044099824,0.000058527476,0.000059230824,0.00071703346,0.000079061276,0.3951065,0.04011581,0.52801156,0.034669843,0.000101238926],"about_ca_topic_score_codex":0.00041586725,"about_ca_topic_score_gemma":0.00030409766,"teacher_disagreement_score":0.009160792,"about_ca_system_score_codex":0.0011883876,"about_ca_system_score_gemma":0.001227808,"threshold_uncertainty_score":0.030645907},"labels":[],"label_agreement":null},{"id":"W2034468591","doi":"10.1080/01966324.2000.10737507","title":"Loop Free Generation of<i>K</i>-Ary Trees","year":2000,"lang":"en","type":"article","venue":"American Journal of Mathematical and Management Sciences","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Loop (graph theory); Listing (finance); Recursion (computer science); Representation (politics); Tree (set theory); Object (grammar); String (physics); Weight-balanced tree; Computer science; Algorithm; Combinatorics; Discrete mathematics; Mathematics; Theoretical computer science; Binary tree; Binary search tree","score_opus":0.022323220746847734,"score_gpt":0.25470440518749193,"score_spread":0.2323811844406442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034468591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16344142,0.00037709152,0.81718075,0.00032078207,0.00010051359,0.00017811845,0.00072988804,0.005552926,0.012118474],"genre_scores_gemma":[0.5136606,0.00015357461,0.4749618,0.00018081849,0.000044304546,0.00013046866,0.001711055,0.00063650904,0.008520844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938285,0.00012361328,0.00006390543,0.00009509267,0.00021694416,0.00011762069],"domain_scores_gemma":[0.99827933,0.00070790044,0.00018751126,0.00043889738,0.0003233123,0.00006305754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041013025,0.00031954158,0.0004666303,0.00071847194,0.00056529563,0.001150443,0.0009321669,0.00049135805,0.004263999],"category_scores_gemma":[0.0032569573,0.00023351249,0.00038350563,0.0009074554,0.0005543544,0.0015104789,0.0010923685,0.00039868217,0.0011678933],"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":[0.001142408,0.00020186395,0.0034920247,0.000501463,0.000047890087,0.00068101863,0.00050303934,0.085076004,0.083481744,0.11680109,0.019919185,0.6881523],"study_design_scores_gemma":[0.00024168628,0.00042998296,0.001974006,0.00009589588,0.00006487,0.00090805296,0.00016571581,0.6367583,0.11234197,0.21571012,0.031229362,0.00008003558],"about_ca_topic_score_codex":0.0008064129,"about_ca_topic_score_gemma":0.001088878,"teacher_disagreement_score":0.004263999,"about_ca_system_score_codex":0.00052354287,"about_ca_system_score_gemma":0.00044275963,"threshold_uncertainty_score":0.014264464},"labels":[],"label_agreement":null},{"id":"W2034751457","doi":"10.1142/s0129054107004978","title":"THE STRUCTURE OF FACTOR ORACLES","year":2007,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Oracle; Factor (programming language); Trie; Suffix; Set (abstract data type); Computer science; String (physics); Simple (philosophy); Generalized suffix tree; Matching (statistics); Quotient; Theoretical computer science; Data structure; Mathematics; Suffix tree; Algorithm; Combinatorics; Programming language; Statistics","score_opus":0.01426481259880297,"score_gpt":0.3138316890843494,"score_spread":0.2995668764855464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034751457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056319296,0.001964045,0.9140486,0.0018931278,0.00026363824,0.00019170654,0.0015580609,0.0034229925,0.020338522],"genre_scores_gemma":[0.6761904,0.0018300324,0.29753658,0.0013625806,0.0008328724,0.00062177086,0.0038524687,0.0016373568,0.016135955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899491,0.0019927442,0.0015088737,0.0029674857,0.002549749,0.0010319898],"domain_scores_gemma":[0.9634849,0.018765088,0.0022845704,0.0098444335,0.0043069674,0.0013140565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050937906,0.0009432889,0.0020073594,0.0029920407,0.0019569257,0.008089919,0.0030717242,0.0030297225,0.013612875],"category_scores_gemma":[0.03955491,0.001124338,0.0018320376,0.003582421,0.008218181,0.024756951,0.0061961105,0.004898537,0.0033423668],"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":[0.00014811115,0.00003516855,0.00087574334,0.00014523811,0.000017671566,0.000090228044,0.00053703575,0.0034012957,0.0011341947,0.96254516,0.0018367805,0.029233472],"study_design_scores_gemma":[0.000020121424,0.00006527485,0.00017758324,0.00004958164,0.000019347799,0.00015576601,0.00007855694,0.014780649,0.0017960819,0.9759236,0.0068945144,0.00003896762],"about_ca_topic_score_codex":0.0011093502,"about_ca_topic_score_gemma":0.00056197157,"teacher_disagreement_score":0.013612875,"about_ca_system_score_codex":0.001883168,"about_ca_system_score_gemma":0.0015237232,"threshold_uncertainty_score":0.045539558},"labels":[],"label_agreement":null},{"id":"W2035512259","doi":"10.1145/333135.333137","title":"Shortest-substring retrieval and ranking","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","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 Waterloo; University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Boolean conjunctive query; Substring; Matching (statistics); Standard Boolean model; Phrase; Learning to rank; Simple (philosophy); Theoretical computer science; Data mining; Boolean expression; Algorithm; Boolean function; And-inverter graph; Search engine; Data structure; Artificial intelligence; Web search query; Mathematics; Statistics; Web query classification","score_opus":0.013760319804854381,"score_gpt":0.2269255291116297,"score_spread":0.21316520930677532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035512259","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033750837,0.00056344416,0.9890428,0.00048421303,0.000074344665,0.00019464681,0.0005252195,0.001695304,0.0040449086],"genre_scores_gemma":[0.15226388,0.0018338137,0.81724083,0.00046201277,0.0004834269,0.00085895194,0.003558653,0.00063889695,0.0226595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995939,0.0011981673,0.0003603443,0.0006736077,0.0015761512,0.00025267218],"domain_scores_gemma":[0.995965,0.0015734658,0.00027725118,0.0013792892,0.0006716146,0.00013334499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030533196,0.001060554,0.0020095587,0.0033452509,0.0014119281,0.0046874145,0.004409795,0.0024261638,0.008790111],"category_scores_gemma":[0.011460092,0.0006662733,0.0018505757,0.006578992,0.0016092483,0.010442583,0.0018036076,0.0017836901,0.0074054035],"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":[0.00028547866,0.00021064265,0.0011158399,0.0004926844,0.00011009348,0.0004128224,0.0003610577,0.1399338,0.0053081713,0.62382895,0.018844882,0.2090956],"study_design_scores_gemma":[0.000058006564,0.000144021,0.00020595535,0.00003593201,0.000055970773,0.00041065417,0.00006401873,0.65079623,0.0033654282,0.31560448,0.02918219,0.00007713698],"about_ca_topic_score_codex":0.0070970603,"about_ca_topic_score_gemma":0.005785719,"teacher_disagreement_score":0.008790111,"about_ca_system_score_codex":0.0023589334,"about_ca_system_score_gemma":0.0021430687,"threshold_uncertainty_score":0.029405832},"labels":[],"label_agreement":null},{"id":"W2037307735","doi":"10.1016/j.jcss.2007.03.007","title":"Optimal spaced seeds for faster approximate string matching","year":2007,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"String (physics); Mathematics; Matching (statistics); Mathematical optimization; Computer science; Combinatorics; Statistics","score_opus":0.02193825351894405,"score_gpt":0.27304516477516255,"score_spread":0.2511069112562185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037307735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045246698,0.00087029097,0.94686806,0.00030415112,0.00032161822,0.0001423122,0.00023394788,0.0030817029,0.0029312326],"genre_scores_gemma":[0.18838288,0.00026814002,0.8062435,0.00018335099,0.000117476986,0.00016711072,0.00062345964,0.000334411,0.003679624],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981583,0.00047155516,0.00015721812,0.0003314911,0.0007451604,0.00013641981],"domain_scores_gemma":[0.9950251,0.0021996922,0.00030814073,0.0016741591,0.00061602524,0.00017688875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014439258,0.0008650149,0.001819699,0.0020165865,0.00077835965,0.0013646173,0.0015595728,0.0020186785,0.008516471],"category_scores_gemma":[0.012469167,0.00070184964,0.0006308823,0.003492477,0.00082872645,0.0028680149,0.002283519,0.001421713,0.003461359],"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":[0.0024757588,0.0004633138,0.0016183538,0.00031289016,0.00008388173,0.00038086306,0.00027870046,0.10244175,0.05350361,0.06364508,0.015236417,0.7595594],"study_design_scores_gemma":[0.00029427154,0.00033268085,0.00046234834,0.000047982787,0.000038392598,0.0005384224,0.00011618286,0.8851247,0.034975085,0.06927939,0.008753537,0.000036981706],"about_ca_topic_score_codex":0.00095894065,"about_ca_topic_score_gemma":0.0021433777,"teacher_disagreement_score":0.008516471,"about_ca_system_score_codex":0.0008204737,"about_ca_system_score_gemma":0.0016905554,"threshold_uncertainty_score":0.028490424},"labels":[],"label_agreement":null},{"id":"W2037416325","doi":"10.1007/s00026-013-0202-9","title":"Solving Non-Homogeneous Nested Recursions Using Trees","year":2013,"lang":"en","type":"article","venue":"Annals of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recursion (computer science); Tree (set theory); Binary tree; Double recursion; Homogeneous; Interpretation (philosophy); Mathematics; Term (time); Combinatorics; Generalization; Set (abstract data type); Discrete mathematics; Algorithm; Computer science; Mathematical analysis; Physics","score_opus":0.05390717657397869,"score_gpt":0.3014080344625421,"score_spread":0.2475008578885634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037416325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073734276,0.0003598223,0.9171809,0.00031798816,0.00007633484,0.00008528022,0.00014345198,0.0013046344,0.0067972527],"genre_scores_gemma":[0.3035109,0.00028401177,0.687946,0.00018738619,0.00011007569,0.00012631391,0.00045502113,0.00066338317,0.006716947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99845946,0.00035121376,0.00013805293,0.00032619789,0.00044873758,0.00027636575],"domain_scores_gemma":[0.9929322,0.005444408,0.00024851572,0.0009020592,0.00032632428,0.000146481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014882456,0.0007168534,0.0015657367,0.000951391,0.0012598814,0.0018406695,0.0023445317,0.0012831117,0.0051696734],"category_scores_gemma":[0.009240247,0.0007922352,0.0016023741,0.0019180933,0.0019797357,0.00538632,0.003129925,0.0028112677,0.0012117473],"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":[0.00047625313,0.0005245519,0.0027007232,0.0008689798,0.0001332888,0.00056012423,0.0015020124,0.1583951,0.016361075,0.42040426,0.009814143,0.38825944],"study_design_scores_gemma":[0.00009607668,0.00007905562,0.00017911031,0.00004678547,0.000060904702,0.00014886426,0.00018247198,0.53406906,0.009014813,0.45107913,0.0050182934,0.000025505346],"about_ca_topic_score_codex":0.0022739538,"about_ca_topic_score_gemma":0.006992562,"teacher_disagreement_score":0.0051696734,"about_ca_system_score_codex":0.0009035945,"about_ca_system_score_gemma":0.001320889,"threshold_uncertainty_score":0.017294228},"labels":[],"label_agreement":null},{"id":"W2037968786","doi":"10.1016/s0022-0000(03)00078-3","title":"On the parameterized complexity of the fixed alphabet shortest common supersequence and longest common subsequence problems","year":2003,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Southeast Fisheries Science Center","keywords":"Parameterized complexity; Combinatorics; Longest common subsequence problem; Alphabet; Mathematics; Sequence (biology); Subsequence; Discrete mathematics; Biology; Genetics","score_opus":0.05730906861657043,"score_gpt":0.2577674707612815,"score_spread":0.20045840214471106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037968786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43663928,0.0046480345,0.50079787,0.014463314,0.0005997009,0.0005808231,0.0057982584,0.002166563,0.034306157],"genre_scores_gemma":[0.8142553,0.0022624368,0.1627016,0.0010550735,0.0009470225,0.0006897203,0.0073014423,0.0010696105,0.0097177075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99272376,0.0025877745,0.0005173686,0.0014918245,0.0016245055,0.0010547779],"domain_scores_gemma":[0.9297576,0.058294192,0.002782638,0.0056228577,0.0021866893,0.0013559826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051308484,0.0017674092,0.0035876369,0.0019526203,0.0026016196,0.007427807,0.005469713,0.003579617,0.015023544],"category_scores_gemma":[0.05108801,0.001196134,0.0025023357,0.005442751,0.0034736537,0.02141277,0.0038853975,0.0054890844,0.001349185],"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":[0.002381964,0.0006945009,0.0049524764,0.00086571823,0.00035934252,0.00039977528,0.0007780174,0.5859976,0.0031868548,0.28543827,0.02277924,0.09216627],"study_design_scores_gemma":[0.00019170067,0.000093520255,0.0006455039,0.00004530969,0.000074670716,0.00012658286,0.00021372974,0.6025651,0.00086898124,0.39323103,0.0019074628,0.000036392223],"about_ca_topic_score_codex":0.0060208924,"about_ca_topic_score_gemma":0.006233648,"teacher_disagreement_score":0.015023544,"about_ca_system_score_codex":0.0057405955,"about_ca_system_score_gemma":0.006525215,"threshold_uncertainty_score":0.050258815},"labels":[],"label_agreement":null},{"id":"W2039944676","doi":"10.1109/tpami.2013.28","title":"Multi-Exemplar Affinity Propagation","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"University of Illinois at Chicago; North China University of Technology; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision","score_opus":0.024803729661821736,"score_gpt":0.26688838852779473,"score_spread":0.242084658865973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039944676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00485852,0.00021686972,0.9921733,0.00012237502,0.000069512666,0.00007848025,0.00008392997,0.0008931283,0.0015038088],"genre_scores_gemma":[0.2197856,0.0005425429,0.76635736,0.0005041488,0.00018873531,0.00037667085,0.0010666684,0.00044904774,0.010729189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997017,0.00053597236,0.00018261402,0.00072077685,0.0012696517,0.000274145],"domain_scores_gemma":[0.9943772,0.0017196933,0.0003127217,0.0009984779,0.002426299,0.00016558645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002319825,0.001745021,0.0020023067,0.0028730824,0.0015813546,0.0020793215,0.005700132,0.0031115455,0.006354782],"category_scores_gemma":[0.009562515,0.0010153992,0.0016967132,0.004196075,0.0012379575,0.0032440543,0.0033537608,0.0028219956,0.0033349267],"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":[0.00020757147,0.00022357331,0.0018100572,0.0003111315,0.00024821667,0.0001834142,0.0002875725,0.3575767,0.007983476,0.023865849,0.013930768,0.5933716],"study_design_scores_gemma":[0.000013500343,0.000029167139,0.00021013702,0.000013541193,0.000020798467,0.00008382134,0.000029415978,0.9828462,0.0037829697,0.010466832,0.0024864571,0.000017099528],"about_ca_topic_score_codex":0.007304807,"about_ca_topic_score_gemma":0.008443192,"teacher_disagreement_score":0.007304807,"about_ca_system_score_codex":0.0013927447,"about_ca_system_score_gemma":0.0013764034,"threshold_uncertainty_score":0.021258831},"labels":[],"label_agreement":null},{"id":"W2040262311","doi":"10.1016/j.tcs.2012.01.013","title":"A Gray code for fixed-density necklaces and Lyndon words in constant amortized time","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Guelph","funders":"","keywords":"De Bruijn sequence; Gray code; Amortized analysis; Mathematics; Combinatorics; Constant (computer programming); Binary number; Code (set theory); Polyomino; Discrete mathematics; Algorithm; Data structure; Arithmetic; Computer science; Set (abstract data type); Geometry","score_opus":0.00957280733346831,"score_gpt":0.25514893121650056,"score_spread":0.24557612388303227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040262311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26961958,0.0022360971,0.6869753,0.0034137813,0.00061678357,0.00047174806,0.0016943563,0.0048674825,0.030104904],"genre_scores_gemma":[0.64100844,0.0010197313,0.32801753,0.0013054421,0.00034704787,0.00096650043,0.0015305921,0.0012384054,0.024566337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980763,0.00034132687,0.00014918167,0.00039430446,0.0006632746,0.0003755595],"domain_scores_gemma":[0.9926801,0.0038627228,0.0004189968,0.0018131906,0.0007204829,0.0005045713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015792842,0.0012639656,0.0018271018,0.0023500368,0.0017993598,0.0037879923,0.0025291701,0.0025787177,0.010503969],"category_scores_gemma":[0.013975042,0.0008028395,0.0011610477,0.0038997133,0.0032115013,0.006659115,0.0050087916,0.0030557865,0.0021713534],"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":[0.0013861478,0.00028086524,0.0011533658,0.00038201385,0.00009508632,0.00029650572,0.000640147,0.07618368,0.011408069,0.71921706,0.026426852,0.16253026],"study_design_scores_gemma":[0.00016975026,0.000145091,0.00025365013,0.000110009394,0.00006481023,0.00018333073,0.00011010155,0.20014969,0.0051469016,0.78680944,0.0067811944,0.000075967495],"about_ca_topic_score_codex":0.0039872588,"about_ca_topic_score_gemma":0.004253664,"teacher_disagreement_score":0.010503969,"about_ca_system_score_codex":0.0040382156,"about_ca_system_score_gemma":0.0036097686,"threshold_uncertainty_score":0.035139322},"labels":[],"label_agreement":null},{"id":"W2040469876","doi":"10.1109/sc.2010.51","title":"Size Matters: Space/Time Tradeoffs to Improve GPGPU Applications Performance","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Speedup; Parallel computing; General-purpose computing on graphics processing units; Design space exploration; Multi-core processor; Computation; CUDA; Implementation; Performance improvement; Computer architecture; Embedded system; Graphics; Algorithm; Operating system","score_opus":0.004202191834885117,"score_gpt":0.2125663009238703,"score_spread":0.20836410908898517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040469876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46440887,0.0064315046,0.4693102,0.0074496344,0.00044947615,0.00014624342,0.00044246463,0.009792014,0.041569654],"genre_scores_gemma":[0.77822775,0.0011912152,0.21419275,0.00065482984,0.00014613032,0.0001141621,0.0003059562,0.0015828139,0.0035843097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935967,0.00020434738,0.00004010139,0.000095529205,0.00021942059,0.00008084026],"domain_scores_gemma":[0.9981365,0.0012036125,0.00008752177,0.00031004165,0.00018506865,0.000077176795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000815509,0.0007789655,0.0004965814,0.00064337923,0.0005843989,0.001347565,0.0013159134,0.00074518734,0.004040748],"category_scores_gemma":[0.0069159158,0.00040595635,0.00031063418,0.0014313632,0.0005374241,0.003522645,0.001090245,0.0009231885,0.0012332662],"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":[0.0014589307,0.0003901745,0.0063093305,0.00070997095,0.00008681454,0.00039285235,0.00091115746,0.15710406,0.2544666,0.06850552,0.022265032,0.48739952],"study_design_scores_gemma":[0.0002588635,0.00064031524,0.00330124,0.00007367091,0.00011071164,0.0005192608,0.0002994116,0.66645247,0.22672945,0.062414076,0.03910941,0.00009109289],"about_ca_topic_score_codex":0.00092898525,"about_ca_topic_score_gemma":0.0023597358,"teacher_disagreement_score":0.004040748,"about_ca_system_score_codex":0.00066390296,"about_ca_system_score_gemma":0.0007680946,"threshold_uncertainty_score":0.013517678},"labels":[],"label_agreement":null},{"id":"W2040975520","doi":"10.1109/bibm.2012.6392695","title":"Efficient filtration for similarity search with spaced k-mer neighbors","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo; Western University","funders":"","keywords":"Nearest neighbor search; Similarity (geometry); Seeding; Computer science; Set (abstract data type); Heuristic; Sensitivity (control systems); Algorithm; Pattern recognition (psychology); Filtration (mathematics); Speedup; Data mining; Selection (genetic algorithm); Sequence (biology); Artificial intelligence; Mathematics; Image (mathematics); Parallel computing; Engineering","score_opus":0.027291435261625932,"score_gpt":0.2727366383145167,"score_spread":0.2454452030528908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040975520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07299726,0.00068569835,0.92422867,0.00006556362,0.000045007273,0.000088776804,0.00007122146,0.00094851427,0.0008694479],"genre_scores_gemma":[0.28651062,0.00033747876,0.7112438,0.00007673791,0.000035028526,0.00016614939,0.00037982856,0.00008777596,0.0011625503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989567,0.00024066691,0.00010353008,0.0001717253,0.0004583009,0.00006901459],"domain_scores_gemma":[0.9977519,0.0011786901,0.00019217683,0.000433173,0.00035628153,0.00008778113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012139273,0.00042517408,0.0010393427,0.0013616814,0.0008430271,0.0007414865,0.0010293154,0.0008765871,0.0009067316],"category_scores_gemma":[0.005225891,0.0003902581,0.0004623682,0.0019030663,0.00066846656,0.001536133,0.00096731394,0.00059019827,0.00055872754],"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":[0.0011840338,0.0002915449,0.0047301,0.0002582494,0.00007151384,0.00043322795,0.0005843693,0.08401175,0.14086777,0.035571735,0.0042424407,0.72775316],"study_design_scores_gemma":[0.00008697289,0.00039562286,0.0014097124,0.000031349948,0.000032007138,0.00068959565,0.000109286506,0.8873872,0.08469359,0.017780254,0.0073084743,0.00007591874],"about_ca_topic_score_codex":0.0015123722,"about_ca_topic_score_gemma":0.0020759285,"teacher_disagreement_score":0.0015123722,"about_ca_system_score_codex":0.0005750415,"about_ca_system_score_gemma":0.00090622064,"threshold_uncertainty_score":0.006419897},"labels":[],"label_agreement":null},{"id":"W2040979981","doi":"10.1016/j.tcs.2009.02.033","title":"On two open problems of 2-interval patterns","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Disjoint sets; Mathematics; Interval (graph theory); Combinatorics; Time complexity; Cardinality (data modeling); Pattern matching; Discrete mathematics; Matching (statistics); Clique; Algorithm; Computer science; Artificial intelligence","score_opus":0.016823842560171616,"score_gpt":0.2936831268212049,"score_spread":0.2768592842610333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040979981","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14322363,0.005999573,0.7680212,0.021620257,0.0017413258,0.00016404243,0.0008918564,0.00044528802,0.05789287],"genre_scores_gemma":[0.6657277,0.00517287,0.27922058,0.003469632,0.0053626536,0.0004022723,0.002036162,0.00045237536,0.038155816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99693835,0.00083424937,0.00024817657,0.00080514495,0.0008117833,0.00036233113],"domain_scores_gemma":[0.9773505,0.017933784,0.0010016153,0.0019666997,0.0011397123,0.00060774194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025141179,0.0007420672,0.0015929214,0.0016792495,0.002021271,0.0040715355,0.0028246588,0.0043255957,0.015706208],"category_scores_gemma":[0.02770561,0.000758038,0.0014980086,0.004281112,0.0043875636,0.013781697,0.004359626,0.0058432645,0.0013410873],"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":[0.00032487317,0.00015700403,0.0009792363,0.00028873578,0.000033819353,0.00034504707,0.0006871327,0.008231936,0.00079294853,0.8893915,0.013187614,0.08558011],"study_design_scores_gemma":[0.00004706156,0.000032917993,0.00026047617,0.00003601971,0.000012019774,0.00028376176,0.000227093,0.020323781,0.00043165797,0.9732728,0.0050520026,0.000020356145],"about_ca_topic_score_codex":0.0007620901,"about_ca_topic_score_gemma":0.00047794817,"teacher_disagreement_score":0.015706208,"about_ca_system_score_codex":0.0011330632,"about_ca_system_score_gemma":0.00070832035,"threshold_uncertainty_score":0.052542508},"labels":[],"label_agreement":null},{"id":"W2041118403","doi":"10.3390/e13010053","title":"A Unique Perspective on Data Coding and Decoding","year":2010,"lang":"en","type":"article","venue":"Entropy","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"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; Data compression; Decoding methods; Source code; Redundancy (engineering); Coding (social sciences); MATLAB; Algorithm; Entropy encoding; Data mining; Theoretical computer science; Distributed source coding; Compression ratio; Variable-length code; Mathematics; Programming language; Statistics","score_opus":0.02458253490733224,"score_gpt":0.30117942030893213,"score_spread":0.2765968854015999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041118403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007068911,0.00088347495,0.99247074,0.00073424267,0.00028766217,0.000027354383,0.00004416831,0.00012143141,0.004724019],"genre_scores_gemma":[0.05133787,0.004363413,0.933744,0.0009133885,0.001390023,0.00020689398,0.00016577788,0.00022733456,0.0076512536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982816,0.0005114782,0.00013955313,0.0002906485,0.00068229716,0.000094427625],"domain_scores_gemma":[0.99741024,0.0012711267,0.00010462391,0.00068891223,0.00045875128,0.00006643448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015870717,0.0011129783,0.0009423938,0.0017407617,0.0007490295,0.0036910132,0.0017069629,0.0023031838,0.0033414299],"category_scores_gemma":[0.005641416,0.00050054624,0.0007665941,0.001779295,0.0038416258,0.004758751,0.0023126383,0.0039449083,0.0020736558],"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":[0.00006161024,0.00002103723,0.00013993203,0.0002016992,0.000021608923,0.00015420587,0.0002449741,0.008437063,0.007547656,0.8536762,0.0032757425,0.12621824],"study_design_scores_gemma":[0.000024821356,0.00013450865,0.00016983796,0.00019412905,0.000028525315,0.0010870708,0.00016539847,0.11524988,0.026412547,0.7860621,0.07039768,0.00007356941],"about_ca_topic_score_codex":0.00071554875,"about_ca_topic_score_gemma":0.0005278438,"teacher_disagreement_score":0.0036910132,"about_ca_system_score_codex":0.00084864174,"about_ca_system_score_gemma":0.0009861693,"threshold_uncertainty_score":0.0111781955},"labels":[],"label_agreement":null},{"id":"W2041156108","doi":"10.1016/s0304-3975(03)00086-0","title":"Palindrome recognition using a multidimensional tape","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Palindrome; Turing machine; Computer science; Mathematics; Turing; Algorithm; Theoretical computer science; Arithmetic; Combinatorics; Algebra over a field; Pure mathematics; Programming language","score_opus":0.025244452198185517,"score_gpt":0.2659925015108236,"score_spread":0.24074804931263807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041156108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20590004,0.0014672846,0.76552683,0.000519009,0.0007777381,0.0001505454,0.0009056912,0.0046010143,0.020151779],"genre_scores_gemma":[0.59712505,0.000766573,0.38947126,0.00018488942,0.000251504,0.0001797593,0.0012556924,0.00030813858,0.010457117],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996043,0.00006282973,0.000056585402,0.000109157685,0.00010602946,0.00006110468],"domain_scores_gemma":[0.9981256,0.00048260464,0.0001274656,0.000933557,0.0002291079,0.00010159245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024864747,0.0004871661,0.00065831054,0.001054147,0.00094917277,0.0012947472,0.00095164933,0.00064936484,0.005260064],"category_scores_gemma":[0.0018067248,0.00031283795,0.00055386004,0.0013947502,0.00055254105,0.0020084516,0.0014670724,0.00094711134,0.0020603382],"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":[0.0021114398,0.00019703039,0.0016915555,0.00061363954,0.00008101692,0.0017274882,0.00059160317,0.0124845505,0.292314,0.10174373,0.0102463635,0.57619756],"study_design_scores_gemma":[0.00019346597,0.0013292392,0.0018395582,0.00020343412,0.00015493773,0.0034546677,0.000708572,0.2198821,0.6082745,0.10795804,0.055793826,0.00020760004],"about_ca_topic_score_codex":0.00037594576,"about_ca_topic_score_gemma":0.0005661484,"teacher_disagreement_score":0.005260064,"about_ca_system_score_codex":0.00033746107,"about_ca_system_score_gemma":0.00040961607,"threshold_uncertainty_score":0.017596602},"labels":[],"label_agreement":null},{"id":"W2041178136","doi":"10.1145/331605.331607","title":"Parallel RAMs with owned global memory and deterministic context-free language recognition","year":2000,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Context-free language; Computer science; Context (archaeology); Parallel computing; Class (philosophy); Binary logarithm; Programming language; Time complexity; Context switch; Crew; Theoretical computer science; Discrete mathematics; Algorithm; Mathematics; Rule-based machine translation; Artificial intelligence","score_opus":0.013753264301839065,"score_gpt":0.23691720106431194,"score_spread":0.22316393676247287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041178136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47118795,0.0009104712,0.5128376,0.00072763715,0.000075148804,0.00013938826,0.00018868693,0.0020348215,0.011898336],"genre_scores_gemma":[0.901697,0.00022429506,0.09183276,0.00016672963,0.00007884129,0.00025028508,0.00024472844,0.000090162626,0.005415263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989705,0.00017024315,0.00008993842,0.00030593105,0.00026140155,0.00020202245],"domain_scores_gemma":[0.9966983,0.0014818708,0.00041518002,0.0011383198,0.00017778168,0.00008858326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067268836,0.00034313835,0.00051491096,0.00046768034,0.0008579632,0.0015178625,0.0014955784,0.00061331724,0.0021926675],"category_scores_gemma":[0.004464695,0.00043756253,0.0005583022,0.0007353678,0.001847208,0.0041554486,0.0016675554,0.0012120543,0.00045991488],"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":[0.0010007223,0.00031868814,0.0048969947,0.000325067,0.000061949606,0.0012483061,0.00107539,0.22702727,0.04211754,0.5928267,0.004033849,0.1250676],"study_design_scores_gemma":[0.00009737224,0.00021402998,0.00078110147,0.000024871408,0.000046839406,0.00066556386,0.0001915837,0.5890542,0.032832608,0.3682566,0.007786616,0.000048615806],"about_ca_topic_score_codex":0.0013636579,"about_ca_topic_score_gemma":0.0014395919,"teacher_disagreement_score":0.0021926675,"about_ca_system_score_codex":0.0006884781,"about_ca_system_score_gemma":0.00075870147,"threshold_uncertainty_score":0.0073352456},"labels":[],"label_agreement":null},{"id":"W2042481350","doi":"10.1016/j.ins.2011.02.009","title":"New complexity results for the k-covers problem","year":2011,"lang":"en","type":"article","venue":"Information Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Vertex cover; Cover (algebra); Bounded function; Cardinality (data modeling); Combinatorics; Mathematics; Reduction (mathematics); Vertex (graph theory); Parameterized complexity; Time complexity; String (physics); Discrete mathematics; Set (abstract data type); Set cover problem; NP-complete; Graph; Computer science","score_opus":0.1345540655591279,"score_gpt":0.2963074091520994,"score_spread":0.1617533435929715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042481350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08527886,0.010481027,0.8014371,0.018151846,0.0014544888,0.00031619097,0.00237025,0.00077147817,0.07973884],"genre_scores_gemma":[0.6396126,0.012164999,0.29716262,0.0042861383,0.00800045,0.0011787089,0.0050044656,0.0011200653,0.031469878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955895,0.0009913878,0.00026912667,0.00076836284,0.0018669179,0.0005146667],"domain_scores_gemma":[0.9606086,0.032778095,0.0015042315,0.0024622176,0.0016801732,0.0009666244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034349358,0.002157962,0.002471519,0.0041931965,0.002114562,0.007401161,0.003843298,0.0033351234,0.01593795],"category_scores_gemma":[0.031899348,0.0010559929,0.0030978082,0.0053377924,0.0037541382,0.020017289,0.006083444,0.009351212,0.001916292],"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":[0.00044995442,0.0003164557,0.002192313,0.00088721176,0.00019810232,0.00035760755,0.00044354095,0.07633328,0.0024115744,0.80611604,0.03316693,0.077127025],"study_design_scores_gemma":[0.00004196145,0.00003639067,0.0005136429,0.00005387341,0.00004701154,0.00020898072,0.0000884449,0.11599463,0.0005366437,0.87729686,0.0051466553,0.0000348725],"about_ca_topic_score_codex":0.0017139096,"about_ca_topic_score_gemma":0.0020021456,"teacher_disagreement_score":0.01593795,"about_ca_system_score_codex":0.0040548462,"about_ca_system_score_gemma":0.0020875917,"threshold_uncertainty_score":0.053317785},"labels":[],"label_agreement":null},{"id":"W2042947822","doi":"10.1038/nmeth.3133","title":"DeeZ: reference-based compression by local assembly","year":2014,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Compression (physics); Computer science; Computational biology; Biology; Materials science; Composite material","score_opus":0.029790139889094607,"score_gpt":0.3618449975261702,"score_spread":0.3320548576370756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042947822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012347746,0.030685214,0.42143577,0.37216637,0.07249256,0.00032463155,0.00053396384,0.0048639155,0.085149884],"genre_scores_gemma":[0.31217656,0.016149335,0.2455261,0.1495639,0.0516357,0.00091143383,0.00077665836,0.002089395,0.22117096],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99855536,0.00026098688,0.00006415264,0.00014959156,0.0008797285,0.00009025376],"domain_scores_gemma":[0.9982937,0.0008203391,0.00007771678,0.00036487562,0.00035009708,0.0000933104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019879246,0.0007959893,0.00074354734,0.0007955199,0.001271218,0.0021774087,0.0014298504,0.0068914816,0.0069247573],"category_scores_gemma":[0.0090782875,0.00041979816,0.00035655146,0.0007802084,0.0024889105,0.0026959225,0.0020085683,0.0053719436,0.004993845],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005723117,0.00007570695,0.0004893738,0.00025315123,0.000066981615,0.0009073989,0.0001677084,0.0027970453,0.016110808,0.17596106,0.58153594,0.22106256],"study_design_scores_gemma":[0.00020728506,0.00018528395,0.0003556505,0.00015935258,0.000042459204,0.0021319208,0.00008503993,0.054845884,0.057771355,0.14397357,0.7401403,0.000101837824],"about_ca_topic_score_codex":0.0004516429,"about_ca_topic_score_gemma":0.0010444999,"teacher_disagreement_score":0.0069247573,"about_ca_system_score_codex":0.0010191726,"about_ca_system_score_gemma":0.00050913246,"threshold_uncertainty_score":0.023165584},"labels":[],"label_agreement":null},{"id":"W2042983118","doi":"10.1016/j.ipl.2006.08.003","title":"On the longest increasing subsequence of a circular list","year":2006,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Longest common subsequence problem; Longest increasing subsequence; Subsequence; Monte Carlo method; Combinatorics; Algorithm; Mathematics; Computer science; Discrete mathematics; Statistics","score_opus":0.008014596510657073,"score_gpt":0.19912213834986703,"score_spread":0.19110754183920994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042983118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3044029,0.0019676299,0.6529098,0.0012436805,0.0010573632,0.00016587625,0.0012509025,0.0016013643,0.03540051],"genre_scores_gemma":[0.6287199,0.0018802615,0.3273833,0.00059943367,0.00075404975,0.00017768145,0.0041430877,0.00064859557,0.035693746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99946433,0.00008482309,0.000050764065,0.00010499577,0.00021266683,0.000082476596],"domain_scores_gemma":[0.9974172,0.0011243292,0.00024313318,0.00044121334,0.0006132494,0.00016078922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058156427,0.0004723631,0.0005328755,0.002300802,0.0010981911,0.0011006482,0.00097161916,0.00071907474,0.006884772],"category_scores_gemma":[0.0056182244,0.00026007855,0.0004489141,0.0034099713,0.00088798936,0.0020174466,0.0009848609,0.00078361947,0.0019956934],"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":[0.0014208172,0.00019062354,0.004674622,0.00051994936,0.00006303488,0.0015655842,0.0009524685,0.04000222,0.04852887,0.47961372,0.027015088,0.395453],"study_design_scores_gemma":[0.000084582825,0.0004259487,0.0028172384,0.00019647912,0.00008038618,0.0014690906,0.00046027097,0.36631554,0.022114862,0.56146497,0.04449064,0.00007997647],"about_ca_topic_score_codex":0.0018355183,"about_ca_topic_score_gemma":0.0023052238,"teacher_disagreement_score":0.006884772,"about_ca_system_score_codex":0.00055976317,"about_ca_system_score_gemma":0.0009085875,"threshold_uncertainty_score":0.02303189},"labels":[],"label_agreement":null},{"id":"W2043277617","doi":"10.1109/dcc.2014.86","title":"Better Compression through Better List Update Algorithms","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data compression; Algorithm; Logarithm; Compression (physics); Oracle; Compression ratio; Computation; Online algorithm; Theoretical computer science; Mathematics; Programming language","score_opus":0.014031700437448348,"score_gpt":0.249262020498629,"score_spread":0.23523032006118066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043277617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07728694,0.0018397047,0.88908005,0.0018338228,0.0002988359,0.00025874082,0.00048390205,0.011589586,0.017328437],"genre_scores_gemma":[0.44806272,0.00079080806,0.5365081,0.0010862966,0.00045904733,0.00025277876,0.0012256033,0.0010280961,0.010586575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961163,0.0006582095,0.00029370238,0.0005123057,0.0019808358,0.00043874985],"domain_scores_gemma":[0.9896951,0.002901901,0.00057938776,0.0055864993,0.0010016564,0.0002354475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021910404,0.000923437,0.0012669355,0.0016444918,0.0008357135,0.0028378547,0.002844209,0.001780659,0.009013483],"category_scores_gemma":[0.012614058,0.00050243654,0.0007334432,0.0027139697,0.0015062512,0.008490842,0.0032153225,0.0028293424,0.0033641176],"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":[0.0010967439,0.00063131726,0.0021153146,0.00038262346,0.00006276987,0.00022138529,0.0005095716,0.06763922,0.035792135,0.24688995,0.02197087,0.6226881],"study_design_scores_gemma":[0.00024156117,0.00040122765,0.0008376933,0.00010955509,0.00007346117,0.00065807794,0.00015752765,0.7013045,0.058072962,0.21189089,0.02615996,0.00009256326],"about_ca_topic_score_codex":0.0009823121,"about_ca_topic_score_gemma":0.0013844696,"teacher_disagreement_score":0.009013483,"about_ca_system_score_codex":0.0013777175,"about_ca_system_score_gemma":0.0017304915,"threshold_uncertainty_score":0.030153096},"labels":[],"label_agreement":null},{"id":"W2044014345","doi":"10.5555/1109557.1109599","title":"Rank/select operations on large alphabets: a tool for text indexing","year":2006,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Rank (graph theory); Generalization; String (physics); Variety (cybernetics); Computer science; Representation (politics); Alphabet; Combinatorics; Binary number; Binary search algorithm; Theoretical computer science; Mathematics; Algorithm; Information retrieval; Search algorithm; Artificial intelligence; Arithmetic","score_opus":0.008969900852929844,"score_gpt":0.2570800764681503,"score_spread":0.24811017561522045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044014345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013793168,0.00056322536,0.97150505,0.0008138574,0.00013596985,0.0001851048,0.00069318473,0.0079316385,0.0043788888],"genre_scores_gemma":[0.13822898,0.00081719324,0.84878606,0.00054368755,0.0004914076,0.00050921086,0.0017703761,0.0009471759,0.007905838],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970132,0.0007469373,0.00029345034,0.00041423092,0.0012568071,0.0002754564],"domain_scores_gemma":[0.9888911,0.005473206,0.0008113441,0.0037830852,0.00063701754,0.00040415238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023639267,0.0010213354,0.002107982,0.0030323926,0.0018041297,0.0034342569,0.002587882,0.001668756,0.0121771665],"category_scores_gemma":[0.014116506,0.00078396156,0.0011934908,0.006319441,0.0023172903,0.010961723,0.003957884,0.0027882527,0.0064876573],"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":[0.00143034,0.00037815177,0.00093153387,0.0005660021,0.00006503077,0.00041892187,0.0007347135,0.027477596,0.027222423,0.24946056,0.04653882,0.64477587],"study_design_scores_gemma":[0.0003437469,0.00058628357,0.00035589378,0.00013388021,0.00008465488,0.0010662826,0.0003907521,0.35930958,0.04160917,0.5429303,0.05304059,0.00014886798],"about_ca_topic_score_codex":0.0010789525,"about_ca_topic_score_gemma":0.0013171153,"teacher_disagreement_score":0.0121771665,"about_ca_system_score_codex":0.0008916512,"about_ca_system_score_gemma":0.0011414976,"threshold_uncertainty_score":0.040736675},"labels":[],"label_agreement":null},{"id":"W2044804826","doi":"10.1109/tit.2012.2216975","title":"How Suboptimal Is the Shannon Code?","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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 Victoria","funders":"Isfahan University of Technology","keywords":"Huffman coding; Prefix code; Canonical Huffman code; Redundancy (engineering); Mathematics; Shannon–Fano coding; Variable-length code; Information theory; Code (set theory); Algorithm; Code word; Discrete mathematics; Computer science; Code rate; Data compression; Set (abstract data type); Statistics; Linear code; Block code; Decoding methods; Systematic code","score_opus":0.014051113463751454,"score_gpt":0.22707264983542264,"score_spread":0.21302153637167118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044804826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4354411,0.009475715,0.5045261,0.011648137,0.00063040643,0.0001163341,0.0010674995,0.00096884137,0.036125798],"genre_scores_gemma":[0.9178588,0.0023042515,0.075526275,0.0010002737,0.0002796225,0.00007349335,0.0003959651,0.0002422369,0.0023189646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923929,0.002878143,0.00036356464,0.00091915607,0.002878106,0.0005681269],"domain_scores_gemma":[0.977969,0.013099518,0.0019260304,0.002470987,0.0039817174,0.00055264385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065739867,0.0005337862,0.0015484449,0.0017701371,0.0013816409,0.0031826952,0.0009962906,0.0027054674,0.0014957628],"category_scores_gemma":[0.046415612,0.00039452314,0.00044963852,0.0019087555,0.003903405,0.003941809,0.0011115205,0.00085117295,0.000800031],"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":[0.0011565961,0.00013345057,0.030070992,0.0006565818,0.00058783527,0.00059318356,0.0009432595,0.32696232,0.01833387,0.39963236,0.015134126,0.20579532],"study_design_scores_gemma":[0.00008665723,0.0004096512,0.007950795,0.00028769646,0.00013951326,0.0023657726,0.0010691952,0.51562107,0.020190319,0.43962875,0.011978915,0.00027171845],"about_ca_topic_score_codex":0.0038725464,"about_ca_topic_score_gemma":0.0039057843,"teacher_disagreement_score":0.0065739867,"about_ca_system_score_codex":0.0022838481,"about_ca_system_score_gemma":0.0035096619,"threshold_uncertainty_score":0.034766972},"labels":[],"label_agreement":null},{"id":"W2044832252","doi":"10.1016/j.jcss.2003.11.003","title":"Implicit B-trees: a new data structure for the dictionary problem","year":2004,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data structure; Computer science; Block (permutation group theory); Combinatorics; Conjecture; Hierarchy; Theoretical computer science; B-tree; Auxiliary memory; Tree (set theory); Arithmetic; Discrete mathematics; Algorithm; Mathematics; Programming language","score_opus":0.033671350161060286,"score_gpt":0.28101301593193784,"score_spread":0.24734166577087754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044832252","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041890037,0.00055504736,0.99212426,0.00049079664,0.00019382266,0.00004459333,0.00045736,0.00066542317,0.0012796713],"genre_scores_gemma":[0.048078343,0.0010950889,0.94452244,0.00038664925,0.0004050307,0.00019633038,0.0015680471,0.00054446806,0.0032035983],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984108,0.0004371275,0.00014306318,0.0002532362,0.00064036483,0.000115422146],"domain_scores_gemma":[0.9947737,0.0019317531,0.0003567961,0.0015997685,0.0010429427,0.00029500542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013307673,0.00065153115,0.001733452,0.0023980697,0.0013350256,0.0027489902,0.0028657494,0.0024532543,0.006605379],"category_scores_gemma":[0.0134229,0.0008008761,0.0007717064,0.005543728,0.0014498181,0.006549353,0.0040168865,0.004001384,0.0040752613],"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":[0.0004863789,0.00016527629,0.0011265129,0.0004832573,0.00006387172,0.0002097417,0.00045050637,0.025706802,0.010178885,0.30217716,0.039742053,0.6192095],"study_design_scores_gemma":[0.00016856992,0.0002544973,0.00031361973,0.00014180683,0.00004888781,0.00063555344,0.00018943466,0.39566478,0.006318763,0.5248971,0.07128405,0.00008289176],"about_ca_topic_score_codex":0.0013579392,"about_ca_topic_score_gemma":0.0017918309,"teacher_disagreement_score":0.006605379,"about_ca_system_score_codex":0.00043760505,"about_ca_system_score_gemma":0.0014354693,"threshold_uncertainty_score":0.02209723},"labels":[],"label_agreement":null},{"id":"W2045095870","doi":"10.1016/j.ejc.2012.07.011","title":"Computing the Longest Previous Factor","year":2012,"lang":"en","type":"article","venue":"European Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Royal Society","keywords":"Substring; Suffix array; Combinatorics; Suffix; Factor (programming language); Mathematics; Prefix; Permutation (music); String (physics); Compressed suffix array; Discrete mathematics; Algorithm; Data structure; Suffix tree; Computer science; Physics","score_opus":0.023129639898129783,"score_gpt":0.24359221495462088,"score_spread":0.2204625750564911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045095870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4255181,0.003206909,0.5162168,0.0032786925,0.0012288545,0.00025935913,0.0042860447,0.007496983,0.03850834],"genre_scores_gemma":[0.6440767,0.00093742984,0.3233006,0.00034214233,0.00046650926,0.0001383976,0.0062171076,0.0016565733,0.022864424],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981187,0.00014715378,0.00016277288,0.0006635796,0.00047283337,0.0004348976],"domain_scores_gemma":[0.9951704,0.0016560882,0.00030812193,0.0016480412,0.00085711555,0.0003602355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010514546,0.0013829811,0.0015698321,0.0032285799,0.0016944718,0.003820418,0.001993001,0.0012543394,0.025432708],"category_scores_gemma":[0.008964866,0.00059640605,0.0017676979,0.0036248392,0.0017285362,0.0076178354,0.00210506,0.0017840364,0.00783012],"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":[0.0039452687,0.00058747036,0.012907401,0.00096614956,0.00030631357,0.00072939915,0.00081620394,0.03705762,0.04721626,0.12059319,0.039240234,0.7356345],"study_design_scores_gemma":[0.00039155636,0.00082303747,0.0052935965,0.00028017227,0.0005382453,0.001581245,0.0009486027,0.28318644,0.09332986,0.5588759,0.054512974,0.00023832828],"about_ca_topic_score_codex":0.0031741366,"about_ca_topic_score_gemma":0.0058320784,"teacher_disagreement_score":0.025432708,"about_ca_system_score_codex":0.0017811303,"about_ca_system_score_gemma":0.0020015514,"threshold_uncertainty_score":0.08508086},"labels":[],"label_agreement":null},{"id":"W2045275042","doi":"10.1109/cnsr.2008.101","title":"Keynote 3 - Distributed Pattern Matching","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Flexibility (engineering); Computer science; Matching (statistics); Bandwidth (computing); Distributed computing; Pattern matching; Theoretical computer science; Data mining; Artificial intelligence; Computer network; Mathematics","score_opus":0.01870250008502554,"score_gpt":0.23034371544640303,"score_spread":0.21164121536137748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045275042","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037365225,0.009737467,0.27354276,0.034829557,0.07021914,0.00083532813,0.003720834,0.0031842217,0.60019416],"genre_scores_gemma":[0.09570247,0.007122157,0.06619116,0.0075522135,0.020299159,0.00056869496,0.00740188,0.0012438428,0.79391843],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810314,0.0003985192,0.00013731707,0.00046871512,0.00070248457,0.00018985172],"domain_scores_gemma":[0.99790525,0.00051893893,0.000085689986,0.000506224,0.0007612872,0.00022260168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020370597,0.0008875689,0.0011085025,0.0010723609,0.0013375634,0.003095,0.0017252266,0.0021303622,0.24368352],"category_scores_gemma":[0.0056149354,0.0002901481,0.0007827612,0.0024002346,0.0006578715,0.0033138206,0.0025353995,0.0016456195,0.10422793],"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":[0.00035299195,0.00011174907,0.0003439028,0.0003741135,0.000033600096,0.00024639282,0.0000784986,0.0021283329,0.0025126245,0.09299767,0.66300005,0.23782016],"study_design_scores_gemma":[0.000047067308,0.00009108413,0.00034413315,0.00013846958,0.00002091946,0.0005019462,0.00008602341,0.0032332204,0.002022449,0.043421406,0.95007086,0.000022317421],"about_ca_topic_score_codex":0.0011619494,"about_ca_topic_score_gemma":0.0015851544,"teacher_disagreement_score":0.24368352,"about_ca_system_score_codex":0.0014972035,"about_ca_system_score_gemma":0.00093939825,"threshold_uncertainty_score":0.8152026},"labels":[],"label_agreement":null},{"id":"W2046831124","doi":"10.1016/j.ipl.2006.09.015","title":"Dynamic Shannon coding","year":2006,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Alphabet; ENCODE; Mathematics; Coding (social sciences); Entropy (arrow of time); Algorithm; Entropy encoding; Combinatorics; Variable-length code; Discrete mathematics; Decoding methods; Statistics; Physics","score_opus":0.004679726946155797,"score_gpt":0.20918922387086586,"score_spread":0.20450949692471007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046831124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022350576,0.0025984065,0.70449615,0.0031513171,0.0016125544,0.00016729218,0.0013019445,0.0011094165,0.26321232],"genre_scores_gemma":[0.69193894,0.004735615,0.15034188,0.0026264314,0.0015074676,0.00042068932,0.0019748164,0.00063784374,0.14581625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992637,0.00014569875,0.000030686733,0.000119998105,0.0003445505,0.000095325566],"domain_scores_gemma":[0.9990036,0.00030304343,0.0000648266,0.00035441213,0.00020976036,0.000064467364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052550447,0.000692853,0.00060717424,0.0016725138,0.0009986488,0.0020733953,0.00079233863,0.0013397735,0.015016892],"category_scores_gemma":[0.0031385617,0.0003424343,0.00041200596,0.001684128,0.0016344244,0.0022202937,0.0020599323,0.0017913268,0.0039946167],"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":[0.000040279632,0.000013267266,0.00008285552,0.000031943342,0.0000072507655,0.000056986726,0.000036588244,0.006737237,0.0020897156,0.9476776,0.0062949145,0.036931425],"study_design_scores_gemma":[0.000016628142,0.000030873573,0.00015921246,0.000049716804,0.00001405299,0.0003384788,0.00003306835,0.07977954,0.005472214,0.87978,0.034284167,0.000042162326],"about_ca_topic_score_codex":0.0007209789,"about_ca_topic_score_gemma":0.0006128387,"teacher_disagreement_score":0.015016892,"about_ca_system_score_codex":0.0009002137,"about_ca_system_score_gemma":0.0011123896,"threshold_uncertainty_score":0.050236464},"labels":[],"label_agreement":null},{"id":"W2047243384","doi":"10.1145/1458082.1458170","title":"A new method for indexing genomes using on-disk suffix trees","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":30,"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 Victoria","funders":"","keywords":"Computer science; Search engine indexing; Compressed suffix array; Suffix tree; Trie; Suffix; Merge (version control); sort; Generalized suffix tree; Suffix array; Binary tree; String (physics); String searching algorithm; Substring; Data structure; Theoretical computer science; Parallel computing; Algorithm; Artificial intelligence; Mathematics; Database; Programming language","score_opus":0.06883198086595334,"score_gpt":0.3371902277071298,"score_spread":0.2683582468411765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047243384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052834987,0.00042345573,0.9875777,0.00016715343,0.00018654393,0.00009074637,0.00048438116,0.0045056255,0.0012809706],"genre_scores_gemma":[0.025913147,0.00035363718,0.96868056,0.00010659163,0.000107281645,0.00016150656,0.0013372258,0.00043149196,0.0029086058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897385,0.00009440088,0.00013047102,0.00021425168,0.00053483114,0.00005222159],"domain_scores_gemma":[0.99788994,0.00040500576,0.00013424079,0.00088872603,0.0005688226,0.00011324126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067765295,0.0006613413,0.0009193636,0.0028861458,0.0010743068,0.0022818758,0.0017799583,0.0009322788,0.0042596804],"category_scores_gemma":[0.003337897,0.00060302106,0.0006412755,0.004120093,0.0008605702,0.004512735,0.0019693063,0.0014000928,0.0034120493],"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":[0.00033649747,0.00016024035,0.0012958134,0.00037251634,0.00008001216,0.0001961601,0.00037423562,0.0074946126,0.07751346,0.030112213,0.01809538,0.86396885],"study_design_scores_gemma":[0.00040320595,0.0006460121,0.0021676894,0.00014323242,0.00018380028,0.003044547,0.00046011878,0.40632716,0.21476088,0.09646088,0.27512604,0.00027655254],"about_ca_topic_score_codex":0.0011131921,"about_ca_topic_score_gemma":0.0015815247,"teacher_disagreement_score":0.0042596804,"about_ca_system_score_codex":0.0005221892,"about_ca_system_score_gemma":0.0011648679,"threshold_uncertainty_score":0.01425004},"labels":[],"label_agreement":null},{"id":"W2047386086","doi":"10.1145/506147.506150","title":"On the closest string and substring problems","year":2002,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":237,"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; University of Waterloo","funders":"","keywords":"Substring; Hamming distance; Combinatorics; String (physics); Approximate string matching; Mathematics; String searching algorithm; String metric; Edit distance; Discrete mathematics; Set (abstract data type); Computer science; Algorithm; Pattern matching; Artificial intelligence","score_opus":0.039501308139665584,"score_gpt":0.21813544475435692,"score_spread":0.17863413661469135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047386086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021924026,0.011496695,0.93403953,0.008127998,0.00090290286,0.00024021388,0.00083628716,0.0012164611,0.021215798],"genre_scores_gemma":[0.21318358,0.014104618,0.7360367,0.003697814,0.0034759918,0.00074462855,0.0041102404,0.001135226,0.023511307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99310726,0.0022629993,0.00047226486,0.001631538,0.001937905,0.0005881224],"domain_scores_gemma":[0.9790701,0.016278144,0.0008306561,0.0022885227,0.0010032045,0.0005293948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047053564,0.0027353547,0.0038589528,0.0034850454,0.0031161918,0.0044207955,0.005137142,0.0053223763,0.012278624],"category_scores_gemma":[0.033386707,0.0010953309,0.0025088142,0.010043811,0.005448339,0.019935723,0.006539696,0.008332925,0.004292056],"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":[0.00079089304,0.00038683662,0.0013096266,0.000806519,0.00015532006,0.0003299323,0.00059898203,0.16604382,0.0012500525,0.544903,0.04592346,0.2375017],"study_design_scores_gemma":[0.000105860985,0.00009279431,0.00017860475,0.00010490282,0.000036017114,0.00025327786,0.00014293654,0.15310808,0.00092277216,0.8295049,0.015510294,0.00003963572],"about_ca_topic_score_codex":0.003003068,"about_ca_topic_score_gemma":0.0017705846,"teacher_disagreement_score":0.012278624,"about_ca_system_score_codex":0.0027906427,"about_ca_system_score_gemma":0.002128113,"threshold_uncertainty_score":0.041076064},"labels":[],"label_agreement":null},{"id":"W2047643564","doi":"10.5555/2025756.2025778","title":"Discovering patterns for prognostics: a case study in prognostics of train wheels","year":2011,"lang":"en","type":"article","venue":"International Conference Industrial, Engineering & Other Applications Applied Intelligent Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Prognostics; Computer science; Data mining; Data modeling; Component (thermodynamics); Reliability engineering; Engineering; Machine learning; Artificial intelligence","score_opus":0.1462002964197826,"score_gpt":0.3003429799801005,"score_spread":0.1541426835603179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047643564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91923344,0.0006643107,0.071626656,0.0024633035,0.00008386589,0.0002739933,0.0018389346,0.00045833082,0.0033572374],"genre_scores_gemma":[0.9733199,0.0001894787,0.024572622,0.000054210508,0.000018276995,0.0000246248,0.00044162804,0.000026343807,0.0013527886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904376,0.00030497496,0.00010203385,0.00013340355,0.00031548762,0.00010031144],"domain_scores_gemma":[0.9920717,0.0058267033,0.00042023137,0.00061092974,0.00078762433,0.00028282058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017591353,0.0006410708,0.0005217862,0.0013888977,0.0011885439,0.0011780558,0.0013684897,0.0025839182,0.0021934113],"category_scores_gemma":[0.0098404335,0.0003411901,0.000569575,0.0018738991,0.0007684621,0.0013732512,0.00079000596,0.0009021801,0.00040371067],"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":[0.0022690755,0.0018286377,0.2770465,0.001643745,0.0003164284,0.039125692,0.007555154,0.24346837,0.019347226,0.008490908,0.013247062,0.3856612],"study_design_scores_gemma":[0.00029927603,0.0013069315,0.094855055,0.00036506023,0.00031579685,0.015208421,0.010829931,0.7963372,0.03279736,0.021048743,0.02642871,0.00020757326],"about_ca_topic_score_codex":0.008022806,"about_ca_topic_score_gemma":0.012101954,"teacher_disagreement_score":0.008022806,"about_ca_system_score_codex":0.00070665305,"about_ca_system_score_gemma":0.0009640951,"threshold_uncertainty_score":0.01595223},"labels":[],"label_agreement":null},{"id":"W2047848293","doi":"10.1007/s10044-006-0036-8","title":"A novel look-ahead optimization strategy for trie-based approximate string matching","year":2006,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Computer science; String (physics); String searching algorithm; Matching (statistics); Pattern recognition (psychology); Artificial intelligence; Algorithm; Pattern matching; Mathematics; Data structure; Statistics","score_opus":0.020681177201560992,"score_gpt":0.2668556260348765,"score_spread":0.24617444883331552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047848293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045985347,0.0002179444,0.99235815,0.00009591067,0.00007038039,0.00005851613,0.00008701907,0.0013747705,0.0011386666],"genre_scores_gemma":[0.09450536,0.00024276687,0.89877504,0.00018333082,0.00008649321,0.00018249927,0.00048737464,0.00031379948,0.005223287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987092,0.00018973161,0.00011116589,0.00023972846,0.00063594175,0.00011414581],"domain_scores_gemma":[0.9988292,0.00034221902,0.00008569737,0.00038497,0.00029630755,0.000061498395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007831275,0.0008805543,0.0019559443,0.0016967569,0.00076019997,0.001433034,0.0024182678,0.0013399981,0.008076281],"category_scores_gemma":[0.003347624,0.0006266002,0.0007607699,0.0031464535,0.00053487485,0.0023025319,0.0018181405,0.0013637915,0.0029438636],"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":[0.00046127845,0.00030312443,0.0003905679,0.00015593608,0.00007747244,0.00012507313,0.000089605244,0.08127119,0.029956574,0.017774776,0.011460626,0.85793376],"study_design_scores_gemma":[0.000049312053,0.00010561954,0.00018778883,0.000008990717,0.000028400123,0.00018667766,0.000037962527,0.9729341,0.01198894,0.010106488,0.0043361103,0.0000295102],"about_ca_topic_score_codex":0.0026266288,"about_ca_topic_score_gemma":0.0039343084,"teacher_disagreement_score":0.008076281,"about_ca_system_score_codex":0.0006396494,"about_ca_system_score_gemma":0.0014043615,"threshold_uncertainty_score":0.027017832},"labels":[],"label_agreement":null},{"id":"W2048065755","doi":"10.1142/s0219720009004242","title":"A TUTORIAL OF TECHNIQUES FOR IMPROVING STANDARD HIDDEN MARKOV MODEL ALGORITHMS","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Viterbi algorithm; Computer science; Hidden Markov model; Logarithm; Forward algorithm; Heuristics; Algorithm; Factor (programming language); Heuristic; Markov model; Sequence (biology); Markov chain; Space (punctuation); Parallel computing; Artificial intelligence; Mathematics; Variable-order Markov model; Machine learning; Programming language","score_opus":0.011313900673213523,"score_gpt":0.27365696638997694,"score_spread":0.2623430657167634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048065755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039756062,0.009653324,0.9788801,0.00046530037,0.00083039113,0.00007890682,0.0004092473,0.0033166802,0.00596855],"genre_scores_gemma":[0.0073784054,0.01702475,0.96089315,0.0008225787,0.0013998789,0.00039430062,0.0017514889,0.001933495,0.008401826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996608,0.0008185963,0.00034931253,0.0005089202,0.00155028,0.00016488942],"domain_scores_gemma":[0.99589586,0.0026727438,0.00014586223,0.0005326735,0.00068624294,0.00006664712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028971375,0.0033410725,0.0015713926,0.003247167,0.0007583209,0.0021655476,0.0033441957,0.002163655,0.030628715],"category_scores_gemma":[0.016708408,0.0020000364,0.0028574318,0.0048225373,0.0009956729,0.0057285675,0.0023084318,0.0052074455,0.02355619],"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":[0.00011233123,0.00020126585,0.00045775468,0.0020886604,0.0002158205,0.00025792397,0.00018646065,0.028897043,0.0050145257,0.11579044,0.09811266,0.7486651],"study_design_scores_gemma":[0.00008179383,0.00015297977,0.00069707865,0.00064595765,0.000121885,0.0010460608,0.000068476744,0.18406634,0.007849984,0.38404578,0.42106676,0.00015707732],"about_ca_topic_score_codex":0.0014896081,"about_ca_topic_score_gemma":0.0015828821,"teacher_disagreement_score":0.030628715,"about_ca_system_score_codex":0.0011526863,"about_ca_system_score_gemma":0.0012553141,"threshold_uncertainty_score":0.102463245},"labels":[],"label_agreement":null},{"id":"W2048425099","doi":"10.1016/j.jda.2011.03.009","title":"The three squares lemma revisited","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Lemma (botany); String (physics); Combinatorics; Correctness; Mathematics; Preprocessor; Computation; Computer science; Discrete mathematics; Algorithm; Artificial intelligence; Data structure","score_opus":0.03224341166779137,"score_gpt":0.2565605238204628,"score_spread":0.22431711215267142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048425099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02438544,0.015481003,0.644615,0.045458034,0.0058035706,0.00006153194,0.0004763386,0.00050585857,0.26321325],"genre_scores_gemma":[0.68647116,0.01398843,0.14808673,0.016695237,0.0068418225,0.0002937409,0.00057522045,0.000979424,0.12606835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983102,0.0006169764,0.00008346094,0.00036207927,0.0004842029,0.00014310444],"domain_scores_gemma":[0.9939075,0.0041998546,0.00021660788,0.0007978364,0.00073661597,0.00014163286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024107378,0.0007234122,0.0010403508,0.0014779106,0.0013076949,0.002961771,0.0015464615,0.0018704071,0.015969422],"category_scores_gemma":[0.0145379305,0.0005072888,0.00096016715,0.0023411189,0.0046597365,0.0063660163,0.0032805046,0.007032134,0.0027788247],"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":[0.00003452436,0.000008922217,0.00014419228,0.00004827442,0.000015781749,0.000090661146,0.000069048234,0.00075308856,0.00038408925,0.9740382,0.008949099,0.015464041],"study_design_scores_gemma":[0.000018838422,0.000013738495,0.00016855252,0.000023756265,0.00001228072,0.00020896556,0.000065983215,0.006520553,0.00064920564,0.9693071,0.02299444,0.000016504346],"about_ca_topic_score_codex":0.0014920301,"about_ca_topic_score_gemma":0.0010944881,"teacher_disagreement_score":0.015969422,"about_ca_system_score_codex":0.00096267567,"about_ca_system_score_gemma":0.00090113113,"threshold_uncertainty_score":0.053423047},"labels":[],"label_agreement":null},{"id":"W2048541619","doi":"10.1016/s0020-0190(02)00500-8","title":"Cuckoo hashing: Further analysis","year":2003,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cuckoo; Hash function; Cuckoo search; Theoretical computer science; Algorithm; Programming language","score_opus":0.00865126449561512,"score_gpt":0.22049945294107579,"score_spread":0.21184818844546066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048541619","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16540664,0.006460902,0.7277422,0.005787178,0.0010225356,0.00055536063,0.001156629,0.0013934628,0.09047517],"genre_scores_gemma":[0.8656198,0.003198602,0.07894488,0.0010584191,0.0014418638,0.0003583964,0.001411232,0.00057735306,0.0473895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861026,0.00032210388,0.00005117034,0.0001764425,0.00065704493,0.000182999],"domain_scores_gemma":[0.9935887,0.003143391,0.00035267504,0.0014727993,0.001261327,0.00018102332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001306641,0.0007424014,0.000990538,0.0018161469,0.0014099664,0.0019094661,0.0015670008,0.0010838851,0.01772729],"category_scores_gemma":[0.01510229,0.00035346352,0.000688301,0.0028604688,0.0016725757,0.004268828,0.0015837883,0.0016707511,0.0023280072],"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":[0.0002766173,0.00016923185,0.0033666878,0.00028504804,0.00003650532,0.00027076047,0.00035830174,0.033720285,0.0030667009,0.8250535,0.030026333,0.10336995],"study_design_scores_gemma":[0.000037397775,0.00008142999,0.0027904965,0.000072948766,0.000033103188,0.00064355176,0.00017637001,0.44311732,0.002562916,0.5342103,0.016203264,0.0000708305],"about_ca_topic_score_codex":0.0023545655,"about_ca_topic_score_gemma":0.0025121612,"teacher_disagreement_score":0.01772729,"about_ca_system_score_codex":0.0013480977,"about_ca_system_score_gemma":0.0012836477,"threshold_uncertainty_score":0.0593037},"labels":[],"label_agreement":null},{"id":"W2048819748","doi":"10.1142/s0129054102000947","title":"VECTOR ALGORITHMS FOR APPROXIMATE STRING MATCHING","year":2002,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Algorithm; Bit array; String (physics); String searching algorithm; Matching (statistics); Automaton; Computation; Bounded function; Computer science; Focus (optics); Mathematics; Pattern matching; Theoretical computer science; Type (biology); Artificial intelligence","score_opus":0.04030689551270782,"score_gpt":0.3145119637821279,"score_spread":0.2742050682694201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048819748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041044485,0.00065870857,0.99084103,0.00013719281,0.000074285745,0.00008377619,0.000117572155,0.0009551004,0.0030278382],"genre_scores_gemma":[0.13555014,0.0017079813,0.8536008,0.000201405,0.00015315173,0.0004932308,0.0010893241,0.00040338797,0.006800577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978005,0.0005957573,0.00027884392,0.0004571904,0.00066802604,0.00019969228],"domain_scores_gemma":[0.99667966,0.0017026038,0.0002510699,0.0008475048,0.00045920679,0.000059969214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001833566,0.00085021276,0.0011817557,0.0021988405,0.000895671,0.0029393102,0.0020000879,0.0014049882,0.007501835],"category_scores_gemma":[0.011549099,0.0005682281,0.0009782601,0.004243928,0.001345278,0.006132762,0.0024132254,0.0016273173,0.0024494438],"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":[0.00021949112,0.00007756381,0.00051131233,0.00031737203,0.00005123982,0.000051499803,0.00015661748,0.07639205,0.0029728601,0.55237013,0.006046123,0.36083373],"study_design_scores_gemma":[0.000041153307,0.00007404932,0.00011249073,0.0000549822,0.00002375437,0.00014856184,0.000060731727,0.37707555,0.0039117364,0.6039398,0.014532134,0.000025089208],"about_ca_topic_score_codex":0.00093852327,"about_ca_topic_score_gemma":0.0010129764,"teacher_disagreement_score":0.007501835,"about_ca_system_score_codex":0.0013616929,"about_ca_system_score_gemma":0.001149675,"threshold_uncertainty_score":0.025096178},"labels":[],"label_agreement":null},{"id":"W2048952423","doi":"10.1145/1739041.1739075","title":"Suffix tree construction algorithms on modern hardware","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cache; Cache algorithms; Parallel computing; Generalized suffix tree; Compressed suffix array; Suffix tree; Exploit; Algorithm; String (physics); Suffix array; Search engine indexing; Suffix; CPU cache; Data structure; Operating system; Artificial intelligence; Mathematics","score_opus":0.012323562673641278,"score_gpt":0.23859029699301362,"score_spread":0.22626673431937233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048952423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017027726,0.0010262474,0.96961695,0.00023034337,0.00011379967,0.00008851746,0.0002300266,0.005548415,0.0061180326],"genre_scores_gemma":[0.08987077,0.0008750114,0.90368795,0.00016492893,0.00009746754,0.00014847888,0.0008225696,0.00026785166,0.0040649087],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993212,0.00010334941,0.00006692394,0.000109628825,0.00034817352,0.000050623712],"domain_scores_gemma":[0.9983884,0.0005679535,0.00012722585,0.0005046755,0.000377492,0.00003420667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064990507,0.0005774169,0.00045152107,0.0011661351,0.00068044476,0.0012026901,0.0010850788,0.0007817295,0.0050269184],"category_scores_gemma":[0.0035200836,0.00035760453,0.00050343946,0.0025586209,0.00052303233,0.003165958,0.00096308475,0.0010773045,0.0034583765],"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":[0.00019913829,0.00005864423,0.00095224706,0.00028017382,0.000038476883,0.000105799285,0.00015625716,0.022910723,0.04523313,0.055102468,0.010834688,0.86412823],"study_design_scores_gemma":[0.0001551486,0.00047656032,0.0018453113,0.00017459087,0.00006675843,0.0012586042,0.00024134152,0.5831556,0.14443278,0.1572502,0.11084794,0.00009526185],"about_ca_topic_score_codex":0.00066971197,"about_ca_topic_score_gemma":0.0015215434,"teacher_disagreement_score":0.0050269184,"about_ca_system_score_codex":0.00061067234,"about_ca_system_score_gemma":0.0009534282,"threshold_uncertainty_score":0.016816676},"labels":[],"label_agreement":null},{"id":"W2049140374","doi":"10.1016/j.tcs.2006.07.021","title":"Prime normal form and equivalence of simple grammars","year":2006,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Terminal and nonterminal symbols; Context-sensitive grammar; Indexed grammar; Tree-adjoining grammar; Mathematics; Context-free grammar; Prefix; Simple (philosophy); Discrete mathematics; Definite clause grammar; L-attributed grammar; Combinatorics; Equivalence (formal languages); Concatenation (mathematics); Logical equivalence; Computer science; Rule-based machine translation; Artificial intelligence; Linguistics","score_opus":0.0058679002261748416,"score_gpt":0.22985309846033694,"score_spread":0.2239851982341621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049140374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27587062,0.0016920068,0.58213496,0.0041691833,0.00063071144,0.0001674119,0.00060920266,0.0009685113,0.13375735],"genre_scores_gemma":[0.91505456,0.0010475909,0.060914528,0.00079007784,0.0008103284,0.00015964615,0.00083517557,0.00035597134,0.020032106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99687386,0.0008850799,0.00020189359,0.0007274691,0.0009557792,0.0003558188],"domain_scores_gemma":[0.99183214,0.0054828725,0.00037465632,0.0011916896,0.00077509414,0.00034337732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002229411,0.0005699106,0.0012081757,0.0022207375,0.0015635852,0.003707378,0.0011846127,0.0013182178,0.0068844915],"category_scores_gemma":[0.0119376,0.00059790554,0.001133861,0.0022571245,0.0061971205,0.009474188,0.003054716,0.0042620436,0.00090383383],"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":[0.00004774888,0.000027862963,0.0001599034,0.000022751305,0.000005589977,0.00008610657,0.000437557,0.00088469696,0.00045939162,0.9857662,0.0007712572,0.011330851],"study_design_scores_gemma":[0.0000065605536,0.0000055194314,0.000043264736,0.0000026203263,0.0000027627007,0.00003535653,0.000020296773,0.0010059769,0.00017033887,0.9976713,0.001032376,0.000003743249],"about_ca_topic_score_codex":0.0009784745,"about_ca_topic_score_gemma":0.0006414531,"teacher_disagreement_score":0.0068844915,"about_ca_system_score_codex":0.0012854676,"about_ca_system_score_gemma":0.00093655987,"threshold_uncertainty_score":0.023030877},"labels":[],"label_agreement":null},{"id":"W2049328058","doi":"10.1006/jagm.1999.1050","title":"Some Open Problems in Computational Molecular Biology","year":2000,"lang":"en","type":"article","venue":"Journal of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Network topology; Property (philosophy); Mathematics; Consistency (knowledge bases); Tree (set theory); Set (abstract data type); Function (biology); Combinatorics; Domain (mathematical analysis); Discrete mathematics; Upper and lower bounds; Algorithm; Computer science; Biology; Mathematical analysis","score_opus":0.018205429609056824,"score_gpt":0.3037905689558141,"score_spread":0.2855851393467573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049328058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03565865,0.042200107,0.78220105,0.099837296,0.006002384,0.00017530505,0.0004815341,0.00058964477,0.032854103],"genre_scores_gemma":[0.37883765,0.038781438,0.49830905,0.009870793,0.029863559,0.00090420054,0.0022716483,0.0011120425,0.040049706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944476,0.0023462772,0.0004648924,0.0009771729,0.0014643124,0.00029970458],"domain_scores_gemma":[0.92647934,0.06487939,0.000833495,0.003819728,0.0030322408,0.0009557156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011258327,0.0012467982,0.0025254919,0.0025775845,0.005086712,0.00786347,0.004791739,0.005379871,0.012092397],"category_scores_gemma":[0.058011536,0.001349,0.0019109607,0.0059554656,0.009675985,0.027806185,0.005693333,0.0114841545,0.0016647498],"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":[0.00022420034,0.00027484316,0.00085540675,0.00048190515,0.00007843259,0.000112045724,0.00046494685,0.01809307,0.00031530717,0.78738755,0.03233137,0.15938094],"study_design_scores_gemma":[0.000023526425,0.000013810465,0.000070868526,0.00003744598,0.000009665582,0.00003849559,0.000075553995,0.02077854,0.00017287969,0.9729772,0.00579257,0.000009359933],"about_ca_topic_score_codex":0.001466675,"about_ca_topic_score_gemma":0.0010060291,"teacher_disagreement_score":0.012092397,"about_ca_system_score_codex":0.0024352889,"about_ca_system_score_gemma":0.002200423,"threshold_uncertainty_score":0.05954045},"labels":[],"label_agreement":null},{"id":"W2049349451","doi":"10.1109/dcc.2010.28","title":"Lossless Data Compression via Substring Enumeration","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Lossless compression; Lexicographical order; Compression (physics); Data compression; Enumeration; Algorithm; String (physics); Computer science; Mathematics; Compression ratio; Set (abstract data type); Combinatorics; Physics","score_opus":0.028749882350341514,"score_gpt":0.2778908061616329,"score_spread":0.2491409238112914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049349451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038551923,0.0019082922,0.9528964,0.00034314324,0.00014084211,0.00008676673,0.00035411378,0.0028554464,0.0028631673],"genre_scores_gemma":[0.30538714,0.0019267878,0.68139905,0.00035063855,0.00022448316,0.00020871138,0.0014184038,0.00025164668,0.008833183],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993949,0.000096504955,0.00004310461,0.00007334488,0.00034253678,0.00004956869],"domain_scores_gemma":[0.99877125,0.00050581887,0.00009862665,0.00041407958,0.00018287794,0.000027325617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003926969,0.00056767405,0.00063470233,0.0016079381,0.00042528554,0.00070146646,0.001058817,0.000581778,0.0024088144],"category_scores_gemma":[0.0024920506,0.00021317822,0.0002777999,0.0025328395,0.0006164993,0.002257509,0.0010086015,0.00069782627,0.0014103324],"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":[0.00054882496,0.0001353656,0.00075112085,0.0003129803,0.000046392972,0.00032577952,0.00013951148,0.028768845,0.08097194,0.02037429,0.007695593,0.8599293],"study_design_scores_gemma":[0.00013846126,0.0005276738,0.0012155795,0.00011237513,0.00008192143,0.0023795476,0.00013095004,0.5989627,0.30779326,0.056747165,0.03184218,0.00006813842],"about_ca_topic_score_codex":0.00050128915,"about_ca_topic_score_gemma":0.0005971179,"teacher_disagreement_score":0.0024088144,"about_ca_system_score_codex":0.00027874653,"about_ca_system_score_gemma":0.000382258,"threshold_uncertainty_score":0.00805825},"labels":[],"label_agreement":null},{"id":"W2049562387","doi":"10.1007/s11512-009-0118-0","title":"Long and short paths in uniform random recursive dags","year":2010,"lang":"sv","type":"article","venue":"Arkiv för matematik","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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":"Directed acyclic graph; Combinatorics; Mathematics; Path (computing); Node (physics); Binary logarithm; Random graph; Root (linguistics); Shortest path problem; Constant (computer programming); Discrete mathematics; Graph; Computer science; Physics","score_opus":0.011368079148865715,"score_gpt":0.2503085451580031,"score_spread":0.23894046600913738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049562387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49011943,0.002111064,0.49377626,0.0019787715,0.00010254187,0.00016000652,0.0017079712,0.0010227016,0.009021202],"genre_scores_gemma":[0.94067144,0.0011312362,0.04719181,0.00039678783,0.00010021054,0.00028715967,0.0011375016,0.00031797396,0.008765868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981012,0.0006502157,0.00013304949,0.00042770544,0.00029122992,0.00039666594],"domain_scores_gemma":[0.9726573,0.020433903,0.002740817,0.0017957807,0.0010633552,0.0013087827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037118807,0.0005691598,0.0010613028,0.0034955137,0.0015322807,0.0021534539,0.0018917107,0.0015133296,0.0054557547],"category_scores_gemma":[0.03513972,0.0010812377,0.00090329663,0.0027377347,0.003004833,0.0059467037,0.0027516766,0.0016795133,0.00074087374],"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":[0.00038698397,0.00007961236,0.006217264,0.00031820597,0.000057357618,0.00050156156,0.0009918549,0.15996428,0.0018077403,0.7931849,0.0043930165,0.032097355],"study_design_scores_gemma":[0.00005972787,0.000052216146,0.0011927458,0.00006746595,0.000032611584,0.000246399,0.00017560004,0.26907066,0.0007705416,0.7255554,0.0027351177,0.000041446925],"about_ca_topic_score_codex":0.003654738,"about_ca_topic_score_gemma":0.006794535,"teacher_disagreement_score":0.0054557547,"about_ca_system_score_codex":0.0027683422,"about_ca_system_score_gemma":0.0012418991,"threshold_uncertainty_score":0.020085812},"labels":[],"label_agreement":null},{"id":"W2051671786","doi":"10.1007/s00453-012-9664-0","title":"A Uniform Paradigm to Succinctly Encode Various Families of Trees","year":2012,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"ENCODE; Computer science; Theory of computation; Combinatorics; Weight-balanced tree; Theoretical computer science; Mathematics; Set (abstract data type); Encoding (memory); Tree (set theory); Node (physics); Discrete mathematics; Algorithm; Binary tree; Artificial intelligence; Binary search tree","score_opus":0.012633158404860765,"score_gpt":0.24547229230012121,"score_spread":0.23283913389526045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051671786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007867626,0.00040145163,0.9831685,0.0010394707,0.00024380058,0.00011305993,0.0003667966,0.00059552863,0.0062037134],"genre_scores_gemma":[0.14065649,0.001155138,0.843537,0.0015919028,0.00037318835,0.0006716186,0.0014593598,0.0007811357,0.009774259],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99749786,0.00072146393,0.0003152967,0.00046330894,0.00079644367,0.00020554387],"domain_scores_gemma":[0.99305576,0.0018893479,0.00023640836,0.0035451704,0.0010654897,0.00020788527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026221403,0.0006580856,0.00066986197,0.0017410584,0.0015137079,0.003610938,0.002506654,0.0015547008,0.0060942164],"category_scores_gemma":[0.011038492,0.000630903,0.0011080581,0.002867509,0.0024345939,0.012186698,0.0050693406,0.0049646166,0.0019431489],"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":[0.000099759054,0.00006374516,0.0001631123,0.000103715494,0.000012683014,0.00005782136,0.00019750994,0.0045195497,0.0048926417,0.8998586,0.006242144,0.08378867],"study_design_scores_gemma":[0.00003915937,0.00008888903,0.00009818001,0.00012901136,0.00004118574,0.0003060009,0.0001334442,0.052322812,0.011349904,0.8957929,0.039662648,0.000035860612],"about_ca_topic_score_codex":0.00047602103,"about_ca_topic_score_gemma":0.000978008,"teacher_disagreement_score":0.0060942164,"about_ca_system_score_codex":0.0012586986,"about_ca_system_score_gemma":0.0014271981,"threshold_uncertainty_score":0.020387173},"labels":[],"label_agreement":null},{"id":"W2051951103","doi":"10.1007/s002240010007","title":"On Recognizing a String on an Anonymous Ring","year":2000,"lang":"en","type":"article","venue":"Theory of Computing Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Science Council","keywords":"String (physics); Kolmogorov complexity; Upper and lower bounds; Combinatorics; Mathematics; Ring (chemistry); Discrete mathematics; Binary number; Arithmetic","score_opus":0.021096749255133402,"score_gpt":0.2541077647803881,"score_spread":0.2330110155252547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051951103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13069627,0.00162244,0.82026297,0.004431249,0.0006540616,0.00015093807,0.0002521715,0.001414861,0.040515136],"genre_scores_gemma":[0.70324445,0.0033168276,0.24226497,0.001318546,0.0012983236,0.00029753946,0.0010426282,0.00051652145,0.046700176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99742836,0.0006598885,0.0002131474,0.0004446277,0.00079550163,0.00045840078],"domain_scores_gemma":[0.98815095,0.007996704,0.0005423154,0.0021688603,0.00082377123,0.0003173804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021524797,0.0009707323,0.0016348105,0.001937803,0.0021310344,0.0037317078,0.0022480728,0.0031663568,0.006553909],"category_scores_gemma":[0.011524824,0.00062882504,0.0011757829,0.0038910913,0.0050607906,0.014961866,0.0047197356,0.0029850407,0.0013791536],"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":[0.0003699146,0.00012774912,0.0011257678,0.0002004185,0.000038278235,0.0002057334,0.0008174353,0.04159377,0.0036408307,0.82373357,0.008862508,0.119284056],"study_design_scores_gemma":[0.000018378802,0.00006563399,0.00025277422,0.000035564655,0.00003085782,0.0001494399,0.00018796019,0.10741346,0.0034751159,0.8831549,0.005177184,0.000038893755],"about_ca_topic_score_codex":0.0018175902,"about_ca_topic_score_gemma":0.0014482663,"teacher_disagreement_score":0.006553909,"about_ca_system_score_codex":0.0018567472,"about_ca_system_score_gemma":0.0010862568,"threshold_uncertainty_score":0.021925032},"labels":[],"label_agreement":null},{"id":"W2053104875","doi":"10.1109/dcc.2010.102","title":"Lossless Compression of Maps, Charts, and Graphs via Color Separation","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Northern British Columbia; University of British Columbia","funders":"","keywords":"Lossless compression; Huffman coding; Codebook; Computer science; Data compression; Algorithm; Raster graphics; Image compression; Entropy encoding; Arithmetic coding; Mathematics; Artificial intelligence; Image processing; Context-adaptive binary arithmetic coding; Image (mathematics)","score_opus":0.007503817932944575,"score_gpt":0.25429729648901594,"score_spread":0.24679347855607137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053104875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16793922,0.0016314833,0.8075332,0.0006149956,0.0004375335,0.00014411684,0.0011826217,0.005986032,0.014530771],"genre_scores_gemma":[0.66385686,0.0017930116,0.31616607,0.00019444719,0.00023525555,0.000118630815,0.0017713951,0.000500052,0.015364334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998374,0.000018242352,0.0000064941964,0.000017118353,0.00010286754,0.000017860939],"domain_scores_gemma":[0.99956936,0.00012320204,0.000032258657,0.00011867314,0.00013858982,0.000017904067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014917352,0.0004094923,0.00025919086,0.0010805061,0.00018229082,0.0005032403,0.000431121,0.00018639417,0.0042750062],"category_scores_gemma":[0.0010331263,0.00009949312,0.00018689442,0.0012926586,0.00030725115,0.00075264095,0.00042034715,0.00032954582,0.0007102939],"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":[0.0006399955,0.000068429785,0.00084293424,0.00030614156,0.00003433919,0.0005668732,0.00017421959,0.041521255,0.13515952,0.015673252,0.020612672,0.7844004],"study_design_scores_gemma":[0.00008032015,0.0002786952,0.0033889704,0.00006560211,0.00007059503,0.0013318502,0.00018447428,0.4904828,0.4430059,0.012435119,0.048604034,0.00007150638],"about_ca_topic_score_codex":0.002013812,"about_ca_topic_score_gemma":0.0019062299,"teacher_disagreement_score":0.0042750062,"about_ca_system_score_codex":0.00034637412,"about_ca_system_score_gemma":0.00026208808,"threshold_uncertainty_score":0.0143013},"labels":[],"label_agreement":null},{"id":"W2053288014","doi":"10.1142/s0129054109007005","title":"AN ADAPTIVE HYBRID PATTERN-MATCHING ALGORITHM ON INDETERMINATE STRINGS","year":2009,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"Strong","keywords":"Indeterminate; Algorithm; Matching (statistics); Computer science; String searching algorithm; Pattern matching; Hybrid algorithm (constraint satisfaction); Successor cardinal; Mathematics; Artificial intelligence","score_opus":0.015010037028539204,"score_gpt":0.30523978877455843,"score_spread":0.2902297517460192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053288014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024888761,0.00013397222,0.9719203,0.000077335186,0.0000546123,0.000051701598,0.00006793597,0.0013504886,0.001454903],"genre_scores_gemma":[0.13054448,0.000082473714,0.86451024,0.000092147275,0.000026060185,0.00009392987,0.00026375987,0.00017071833,0.0042162663],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99944144,0.00006987173,0.000050987983,0.00015224464,0.00024157282,0.000043769996],"domain_scores_gemma":[0.9993292,0.00017833068,0.00004986712,0.00018342228,0.00022731471,0.000031904823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048680237,0.00036602872,0.00054768677,0.0011708495,0.0004354533,0.00080078066,0.0016529465,0.00063203473,0.0027802798],"category_scores_gemma":[0.0020084516,0.0002416566,0.00031223218,0.0016789329,0.00045863126,0.001463533,0.00096043426,0.00055820344,0.0012079127],"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":[0.0003775931,0.00007387095,0.0011042252,0.000085335996,0.00003393438,0.00016319055,0.00014540763,0.02682238,0.051593415,0.021284064,0.0040531894,0.89426345],"study_design_scores_gemma":[0.00009908651,0.00019503356,0.0008431378,0.000017932709,0.000029214565,0.00066040066,0.00007794154,0.88279617,0.06550475,0.030637896,0.019095328,0.000043080534],"about_ca_topic_score_codex":0.0011285454,"about_ca_topic_score_gemma":0.0013527413,"teacher_disagreement_score":0.0027802798,"about_ca_system_score_codex":0.00032080986,"about_ca_system_score_gemma":0.00055565813,"threshold_uncertainty_score":0.009301007},"labels":[],"label_agreement":null},{"id":"W2053500637","doi":"10.1142/s012906570900180x","title":"ADAPTIVE MACHINE LEARNING TECHNIQUE FOR PERIODICITY DETECTION IN BIOLOGICAL SEQUENCES","year":2009,"lang":"en","type":"article","venue":"International Journal of Neural Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Substring; Chromatin; Nucleosome; Computer science; Sequence (biology); Suffix tree; Histone; DNA; DNA sequencing; Algorithm; Sliding window protocol; Computational biology; Noise (video); Artificial intelligence; Pattern recognition (psychology); Biology; Genetics; Window (computing); Data structure","score_opus":0.04042864614936365,"score_gpt":0.29783529580592827,"score_spread":0.2574066496565646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053500637","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026929185,0.00047813263,0.97094697,0.000109681576,0.00008027751,0.000045838216,0.00005654486,0.0007407126,0.0006125989],"genre_scores_gemma":[0.25972822,0.00048651005,0.73736787,0.00012060369,0.00011805474,0.00019391254,0.0003360558,0.00006421005,0.0015846306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993654,0.00012682966,0.00007405631,0.00013922581,0.00024805253,0.00004641677],"domain_scores_gemma":[0.99884355,0.0006664397,0.00011605021,0.00012893023,0.0002181922,0.000026777725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010057986,0.00045834674,0.0006927645,0.0016440285,0.00041776395,0.0003994341,0.0008621242,0.00077099196,0.0012063195],"category_scores_gemma":[0.0037121524,0.00021140065,0.000508471,0.001730774,0.00039912766,0.00080837164,0.00046710134,0.00095782394,0.00058867614],"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":[0.00020226705,0.00013578623,0.0020639063,0.00011969147,0.000063705666,0.00017320298,0.00010214651,0.07471381,0.03138051,0.0050162342,0.0016000603,0.8844286],"study_design_scores_gemma":[0.000014561065,0.00009359263,0.000990559,0.000012339349,0.000014826366,0.00020396551,0.000018148536,0.98422515,0.009259006,0.0035002008,0.0016544614,0.00001317666],"about_ca_topic_score_codex":0.00080656,"about_ca_topic_score_gemma":0.00074904406,"teacher_disagreement_score":0.0016440285,"about_ca_system_score_codex":0.0003049876,"about_ca_system_score_gemma":0.0005542699,"threshold_uncertainty_score":0.0053192377},"labels":[],"label_agreement":null},{"id":"W2053550438","doi":"10.5555/338219.338634","title":"Adaptive set intersections, unions, and differences","year":2000,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":157,"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 New Brunswick; University of Waterloo","funders":"","keywords":"Set (abstract data type); Computer science; Programming language","score_opus":0.02080502840567923,"score_gpt":0.23532655073276962,"score_spread":0.21452152232709037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053550438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08274144,0.0021495037,0.90383303,0.001826551,0.00011655088,0.00021539062,0.00026644056,0.000840916,0.008010177],"genre_scores_gemma":[0.4966994,0.0012189725,0.49713624,0.00041482353,0.0003005155,0.00030186423,0.0005185099,0.0002655577,0.0031441106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99273443,0.0020934509,0.00046986446,0.001863239,0.002407435,0.00043160713],"domain_scores_gemma":[0.9602599,0.030324351,0.003321032,0.004127795,0.0013573751,0.0006094886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005237977,0.00075780763,0.0012199216,0.0025137893,0.001557132,0.004532402,0.0034608834,0.0024642106,0.004821366],"category_scores_gemma":[0.042861614,0.0009684744,0.0012817456,0.00451704,0.006094436,0.019510465,0.0053454638,0.0036700985,0.00082823733],"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":[0.0006734694,0.00020440252,0.0057263603,0.00048541382,0.00008803668,0.00016961053,0.0008798385,0.09499747,0.005500189,0.66389614,0.0052173766,0.22216165],"study_design_scores_gemma":[0.000056586923,0.00019699705,0.00096847984,0.000064561835,0.00004953386,0.000469819,0.00035393558,0.27363092,0.009045899,0.708169,0.006939049,0.000055186705],"about_ca_topic_score_codex":0.0008646449,"about_ca_topic_score_gemma":0.000699007,"teacher_disagreement_score":0.005237977,"about_ca_system_score_codex":0.0019224343,"about_ca_system_score_gemma":0.0013165427,"threshold_uncertainty_score":0.027701437},"labels":[],"label_agreement":null},{"id":"W2053647845","doi":"10.1109/ccece.2013.6567819","title":"Developing and evaluating a lossless compression scheme for scientific data from a nanosatellite","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Lossless compression; Computer science; Scheme (mathematics); Uncompressed video; Data compression; Compression (physics); Telecommunications link; Lossy compression; Computer engineering; Real-time computing; Algorithm; Computer hardware; Computer network; Artificial intelligence; Mathematics","score_opus":0.19505706020245964,"score_gpt":0.3664805478709747,"score_spread":0.1714234876685151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053647845","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8535845,0.00086155534,0.13788779,0.00033883436,0.000087593406,0.0008321536,0.00019172745,0.0009617974,0.0052539883],"genre_scores_gemma":[0.85004663,0.00061315956,0.14585955,0.000105173436,0.000021260688,0.00016458462,0.00031777823,0.00008572398,0.0027861106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924976,0.00012331015,0.00004585031,0.000059071608,0.00047137085,0.00005062931],"domain_scores_gemma":[0.99815804,0.00082255213,0.00020043956,0.00018942935,0.00056528766,0.00006414901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015872092,0.00034764447,0.00031961713,0.000619484,0.00038770484,0.00060092885,0.00077914406,0.00059975276,0.0007568417],"category_scores_gemma":[0.0044145477,0.00014107344,0.00018347432,0.0005897718,0.0005992431,0.0012115188,0.00039625584,0.00038408735,0.00015004685],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001297251,0.00092282926,0.0053965542,0.0009277421,0.00010266843,0.00030019096,0.0002947114,0.35941273,0.3801654,0.007267622,0.0019544484,0.2419578],"study_design_scores_gemma":[0.00013089796,0.0022080026,0.0018275647,0.000026324798,0.000038952083,0.00020896299,0.00010729874,0.5829868,0.4076882,0.000522964,0.0042238845,0.000030265031],"about_ca_topic_score_codex":0.002610535,"about_ca_topic_score_gemma":0.002835017,"teacher_disagreement_score":0.002610535,"about_ca_system_score_codex":0.0013332912,"about_ca_system_score_gemma":0.0006475235,"threshold_uncertainty_score":0.009673774},"labels":[],"label_agreement":null},{"id":"W2053743126","doi":"10.1006/jcss.2002.1823","title":"Finding Similar Regions in Many Sequences","year":2002,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Combinatorics; Polynomial-time approximation scheme; Mathematics; Hamming distance; Core (optical fiber); Sequence (biology); Time complexity; Approximation algorithm; Discrete mathematics; Entropy (arrow of time); Computer science; Biology; Physics; Genetics","score_opus":0.050430558016814044,"score_gpt":0.2647240296950133,"score_spread":0.21429347167819926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053743126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69982517,0.003955237,0.28890207,0.0009148869,0.0004007849,0.00025487758,0.0010022274,0.0013502899,0.0033945055],"genre_scores_gemma":[0.7731761,0.0012589603,0.21732157,0.00038150512,0.00042004243,0.00014722957,0.0029343145,0.00020416117,0.0041560936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990262,0.00010640094,0.000103032966,0.00027927302,0.00039112702,0.00009397869],"domain_scores_gemma":[0.9974246,0.0010490783,0.00041096564,0.00047664167,0.00045920615,0.00017962049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005125258,0.0007232936,0.001198863,0.0043164585,0.0013822713,0.0010371731,0.0010127482,0.0017668599,0.003174988],"category_scores_gemma":[0.004293627,0.000474742,0.0007319643,0.0038027398,0.00083175604,0.0018747438,0.0010830681,0.0010072422,0.0013270495],"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":[0.0028733355,0.00085415016,0.02799882,0.0010445603,0.0004540601,0.005900218,0.0011759677,0.02216006,0.3670491,0.012357355,0.005962624,0.55216974],"study_design_scores_gemma":[0.00044402084,0.003313964,0.048994433,0.0003734583,0.0011810996,0.021721527,0.0031786275,0.5418472,0.2659518,0.07395004,0.038818605,0.0002252262],"about_ca_topic_score_codex":0.00084457797,"about_ca_topic_score_gemma":0.001570126,"teacher_disagreement_score":0.0043164585,"about_ca_system_score_codex":0.00034551413,"about_ca_system_score_gemma":0.000679385,"threshold_uncertainty_score":0.0106214285},"labels":[],"label_agreement":null},{"id":"W2054120410","doi":"10.1109/bibe.2007.4375584","title":"Shortest Path Approaches for the Longest Common Subsequence of a Set of Strings","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Victoria","funders":"","keywords":"Longest common subsequence problem; Generalization; Computer science; Longest increasing subsequence; Shortest path problem; Set (abstract data type); Algorithm; Dynamic programming; Theoretical computer science; Approximation algorithm; Combinatorics; Subsequence; Mathematics","score_opus":0.08279382444758358,"score_gpt":0.2846085910428433,"score_spread":0.2018147665952597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054120410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0106014265,0.0013341185,0.9838536,0.0003410788,0.000085331,0.00014455793,0.00028266167,0.0005824518,0.002774824],"genre_scores_gemma":[0.088965386,0.0015523002,0.90400666,0.00015826727,0.0001423951,0.0003637333,0.0009979389,0.00019823619,0.0036150056],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798065,0.00044139923,0.00016172379,0.0005806346,0.00072263245,0.00011302001],"domain_scores_gemma":[0.99724776,0.0016201815,0.00031237467,0.00042069118,0.00032239564,0.00007655983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013056776,0.0011868033,0.001335568,0.0035010106,0.000987846,0.0012886635,0.0020912357,0.0016020584,0.0059607355],"category_scores_gemma":[0.00790771,0.0004766674,0.0009526387,0.0073101274,0.0010656045,0.004354695,0.0017258025,0.0016170817,0.0017962364],"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":[0.00021502947,0.00024146115,0.0012380645,0.00068276137,0.00016325386,0.00027700505,0.00040502127,0.22314893,0.006220637,0.1342045,0.008262489,0.6249409],"study_design_scores_gemma":[0.00007490524,0.00020633182,0.000424184,0.00008107502,0.000048917234,0.0005297556,0.0002571994,0.6922294,0.005527672,0.28076836,0.019805575,0.000046680932],"about_ca_topic_score_codex":0.0019796405,"about_ca_topic_score_gemma":0.0024640488,"teacher_disagreement_score":0.0059607355,"about_ca_system_score_codex":0.0010395765,"about_ca_system_score_gemma":0.0017861478,"threshold_uncertainty_score":0.019940615},"labels":[],"label_agreement":null},{"id":"W2054292887","doi":"10.1145/2745754.2745770","title":"Recovering Exchanged Data","year":2015,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inverse; Inversion (geology); Data exchange; Inverse problem; Simple (philosophy); Algorithm; Perspective (graphical); Theoretical computer science; Inverse method; Data mining; Data source; Artificial intelligence; Mathematics; Applied mathematics; Database","score_opus":0.2779456178029287,"score_gpt":0.3242576934228592,"score_spread":0.046312075619930504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054292887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020235574,0.00048389233,0.96773684,0.0011675343,0.00028673775,0.00013174918,0.0006765875,0.0014565992,0.007824473],"genre_scores_gemma":[0.29016253,0.0011857471,0.6913755,0.0005770557,0.0002077748,0.00021288752,0.0030655963,0.001527904,0.011685027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99407756,0.0010812265,0.00038661595,0.0008401289,0.0031957203,0.0004188117],"domain_scores_gemma":[0.9849156,0.0031560725,0.0005505359,0.00967968,0.0015457907,0.00015231161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005067354,0.0010308807,0.0011670003,0.0023367673,0.0012153919,0.0045420695,0.002600651,0.0019245782,0.004218237],"category_scores_gemma":[0.024785109,0.0007377913,0.001086009,0.0032985716,0.0020576292,0.01119396,0.0074660797,0.00414173,0.0022798846],"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":[0.0006179954,0.00016366022,0.0025323136,0.00065613404,0.0001485281,0.0013904381,0.0016319506,0.0556397,0.029226443,0.43592823,0.016325364,0.45573935],"study_design_scores_gemma":[0.00006577972,0.000156682,0.0011614333,0.0002484167,0.00010657896,0.0018006569,0.0016929404,0.25258282,0.13481319,0.48749554,0.11973569,0.00014024593],"about_ca_topic_score_codex":0.001015109,"about_ca_topic_score_gemma":0.00060567836,"teacher_disagreement_score":0.005067354,"about_ca_system_score_codex":0.0012299464,"about_ca_system_score_gemma":0.0021118561,"threshold_uncertainty_score":0.026799023},"labels":[],"label_agreement":null},{"id":"W2054300598","doi":"10.1002/spe.982","title":"Post BWT stages of the Burrows–Wheeler compression algorithm","year":2010,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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":"Lossless compression; Algorithm; Computer science; Data compression; Entropy encoding; Context (archaeology); Compression (physics); Permutation (music); Entropy (arrow of time); Image compression; Speech recognition; Artificial intelligence; Image (mathematics); History; Image processing","score_opus":0.008361186106803337,"score_gpt":0.2719656815834479,"score_spread":0.26360449547664455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054300598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14700805,0.0015190915,0.8329725,0.0005965053,0.00046819609,0.00058522285,0.00064376474,0.0070956503,0.009111069],"genre_scores_gemma":[0.24169478,0.0005767254,0.7400907,0.00022097467,0.0001931324,0.00027768646,0.0020835237,0.00079899107,0.0140635045],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991198,0.00010544376,0.00009038818,0.00013701664,0.0004484953,0.000098833116],"domain_scores_gemma":[0.998206,0.00058446,0.00015326966,0.0004624319,0.000541692,0.000052191004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008554787,0.0010167578,0.0006195194,0.001499902,0.0005653441,0.0014159591,0.0010579862,0.00078941975,0.009927828],"category_scores_gemma":[0.0043175304,0.00034573654,0.0005057985,0.0014093322,0.00069180917,0.0016212534,0.0011685704,0.001271703,0.004215594],"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":[0.00086717977,0.0001357385,0.0011756083,0.00023499252,0.00004418007,0.00023904735,0.00023592912,0.013069123,0.12345698,0.008608414,0.0061161174,0.84581673],"study_design_scores_gemma":[0.0001845113,0.0006504997,0.0071456716,0.00008779725,0.00012318561,0.0011114728,0.00024023672,0.31332168,0.6325947,0.007937992,0.036498155,0.00010401819],"about_ca_topic_score_codex":0.0036700042,"about_ca_topic_score_gemma":0.0052001146,"teacher_disagreement_score":0.009927828,"about_ca_system_score_codex":0.0004439276,"about_ca_system_score_gemma":0.0010752518,"threshold_uncertainty_score":0.033211946},"labels":[],"label_agreement":null},{"id":"W2054767096","doi":"10.1007/s10044-006-0032-z","title":"Breadth-first search strategies for trie-based syntactic pattern recognition","year":2006,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Computer science; Computation; Prefix; String (physics); Heuristic; Representation (politics); Algorithm; Element (criminal law); Dynamic programming; Data structure; Theoretical computer science; Pattern recognition (psychology); Mathematics; Artificial intelligence","score_opus":0.02461615076739881,"score_gpt":0.2738431311713298,"score_spread":0.249226980403931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054767096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01881198,0.0012135506,0.9702867,0.00033951036,0.00007125023,0.00019490984,0.00050526124,0.00389199,0.0046848725],"genre_scores_gemma":[0.12212098,0.00079179555,0.8687533,0.0002385332,0.000055847522,0.0003069501,0.0018604296,0.00067341526,0.0051987376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989807,0.00021357668,0.00014241581,0.00019067376,0.00036488986,0.00010767491],"domain_scores_gemma":[0.9970197,0.0016846356,0.00013417003,0.0005570982,0.00051667285,0.00008769881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010166982,0.0009102386,0.0015338368,0.004224204,0.0010090936,0.0018057346,0.0018710054,0.0013877149,0.010169351],"category_scores_gemma":[0.0056951423,0.0006805453,0.0009790303,0.0040889704,0.0011026647,0.0033759002,0.0019343254,0.0013460835,0.0041755033],"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":[0.00038173515,0.00023611238,0.0006631756,0.0004710609,0.00007490569,0.00028217884,0.00042938325,0.023243783,0.01892707,0.04789172,0.012521258,0.89487755],"study_design_scores_gemma":[0.00018099543,0.00023991034,0.000503132,0.00013223912,0.00011386751,0.00095927814,0.00049064524,0.7400731,0.025095057,0.21378335,0.018341856,0.000086523374],"about_ca_topic_score_codex":0.0020128607,"about_ca_topic_score_gemma":0.0038201534,"teacher_disagreement_score":0.010169351,"about_ca_system_score_codex":0.0006457397,"about_ca_system_score_gemma":0.0013318362,"threshold_uncertainty_score":0.034019887},"labels":[],"label_agreement":null},{"id":"W2055286490","doi":"10.1587/transfun.e94.a.2092","title":"Near-Optimality of the Minimum Average Redundancy Code for Almost All Monotone Sources","year":2011,"lang":"en","type":"article","venue":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Huffman coding; Universal code; Prefix code; Monotone polygon; Redundancy (engineering); Canonical Huffman code; Constant-weight code; Mathematics; Shannon–Fano coding; Source code; Code (set theory); Polynomial code; Code word; Systematic code; Algorithm; Coding (social sciences); Discrete mathematics; Computer science; Statistics; Code rate; Linear code; Decoding methods","score_opus":0.05801735668246414,"score_gpt":0.29141032603841394,"score_spread":0.2333929693559498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055286490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53683805,0.0013743503,0.45087904,0.0009074757,0.000044257995,0.00006031274,0.0002391994,0.00033142962,0.009325874],"genre_scores_gemma":[0.91770977,0.00037864497,0.08046267,0.00015334981,0.000051289782,0.000065591,0.00024601517,0.000066841436,0.00086594536],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99827325,0.00066289457,0.00007341398,0.00018171141,0.0006364728,0.00017230822],"domain_scores_gemma":[0.98891836,0.0077300915,0.0011786566,0.0006728435,0.0012856544,0.00021430926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024249684,0.00046922755,0.0009832414,0.0013173348,0.0005891737,0.0007661588,0.0008105259,0.0011637105,0.0008556014],"category_scores_gemma":[0.02188296,0.0003464324,0.0004006863,0.0007843755,0.0012789895,0.0014643805,0.0011033756,0.0007107838,0.00020040367],"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":[0.0009882945,0.000094703384,0.0041195676,0.00034270127,0.00012017258,0.0005723119,0.00029472893,0.69139427,0.029971207,0.20437938,0.0026339407,0.06508865],"study_design_scores_gemma":[0.000057437883,0.00018437128,0.0011158463,0.000040563227,0.000014455735,0.0004678295,0.000056611338,0.9167676,0.008233336,0.07229965,0.000731717,0.000030570267],"about_ca_topic_score_codex":0.00088696874,"about_ca_topic_score_gemma":0.00060447137,"teacher_disagreement_score":0.0024249684,"about_ca_system_score_codex":0.0008446175,"about_ca_system_score_gemma":0.0012610116,"threshold_uncertainty_score":0.012824595},"labels":[],"label_agreement":null},{"id":"W2055586003","doi":"10.1016/j.disc.2008.11.001","title":"Hamming distance for conjugates","year":2008,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hamming distance; Combinatorics; Mathematics; Alphabet; String (physics); Hamming code; Hamming graph; Binary number; Hamming bound; Conjugate; Discrete mathematics; Arithmetic; Algorithm; Block code","score_opus":0.02867343019447815,"score_gpt":0.2616710702256235,"score_spread":0.23299764003114537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055586003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12508377,0.0074725086,0.67026633,0.0064340034,0.002213343,0.00014610196,0.0012101742,0.00061740424,0.18655643],"genre_scores_gemma":[0.7585577,0.0058108317,0.121585056,0.0017395875,0.0020245705,0.00034175333,0.001391307,0.0005429359,0.10800627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864537,0.00031061473,0.00010326258,0.00034656748,0.0004720315,0.00012218514],"domain_scores_gemma":[0.99772996,0.0010480792,0.00023237945,0.000528846,0.00031602848,0.00014468025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009359586,0.0008106001,0.00093805796,0.003061175,0.0011026674,0.0034571143,0.000970318,0.0013228909,0.010750558],"category_scores_gemma":[0.00624821,0.00030108963,0.0005350742,0.0030174789,0.0020729464,0.006132623,0.0031641903,0.0028039587,0.003913569],"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":[0.00005046139,0.000017978,0.0001401025,0.00004067188,0.000007706335,0.000044893273,0.00008343019,0.0012013004,0.00064808934,0.95665985,0.0032502147,0.037855193],"study_design_scores_gemma":[0.0000068976374,0.000026266598,0.00013527239,0.000023427388,0.0000065384916,0.00019802625,0.000036296955,0.0049367486,0.0012376931,0.9811421,0.0122383125,0.00001243836],"about_ca_topic_score_codex":0.00019240721,"about_ca_topic_score_gemma":0.00013723406,"teacher_disagreement_score":0.010750558,"about_ca_system_score_codex":0.0011759497,"about_ca_system_score_gemma":0.00057711016,"threshold_uncertainty_score":0.03596419},"labels":[],"label_agreement":null},{"id":"W2056081579","doi":"10.1007/s10791-007-9042-8","title":"Hybrid index maintenance for contiguous inverted lists","year":2008,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Merge (version control); Computer science; Inverted index; Information retrieval; Data mining; Search engine indexing","score_opus":0.01558255272543664,"score_gpt":0.22993730688226618,"score_spread":0.21435475415682953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056081579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.115449294,0.0033665786,0.85963035,0.00047313765,0.0003775763,0.00035727723,0.0019125816,0.011709381,0.0067238086],"genre_scores_gemma":[0.33985665,0.00068728405,0.6459939,0.00026035908,0.00030997265,0.00030146312,0.0040514586,0.0008863189,0.0076525654],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846065,0.00021310018,0.00020454398,0.00024527375,0.0007285208,0.00014799286],"domain_scores_gemma":[0.9921969,0.0018394054,0.00047861433,0.0035978209,0.0017180301,0.0001693323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014459636,0.0005462507,0.0012440853,0.0038798258,0.0013295492,0.0022977097,0.0030126139,0.0009342733,0.004715884],"category_scores_gemma":[0.007664511,0.00063316827,0.0005964817,0.0057818247,0.0006857652,0.0052392767,0.002228166,0.00084223616,0.0018475034],"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":[0.0009543591,0.00033338374,0.0029622002,0.00039493796,0.00014564436,0.00020975467,0.00027629087,0.018350365,0.033902608,0.014766849,0.021392992,0.9063106],"study_design_scores_gemma":[0.00046439175,0.0011043934,0.0049557826,0.00015706141,0.0004976747,0.0019179395,0.00044600043,0.7295048,0.13187353,0.089670986,0.039198767,0.00020864008],"about_ca_topic_score_codex":0.0034357177,"about_ca_topic_score_gemma":0.0070060315,"teacher_disagreement_score":0.004715884,"about_ca_system_score_codex":0.0007723093,"about_ca_system_score_gemma":0.0015012975,"threshold_uncertainty_score":0.015776217},"labels":[],"label_agreement":null},{"id":"W2056117079","doi":"10.1016/j.tcs.2008.11.003","title":"Compressed depth sequences","year":2008,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Combinatorics; Mathematics; Redundancy (engineering); Set (abstract data type); Construct (python library); Probability distribution; Binary logarithm; Algorithm; Code (set theory); Discrete mathematics; Computer science; Statistics","score_opus":0.01978348719631589,"score_gpt":0.25570393056188034,"score_spread":0.23592044336556445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056117079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11198369,0.0032096398,0.8079473,0.002344572,0.001324085,0.0004731585,0.004357617,0.0035390065,0.06482098],"genre_scores_gemma":[0.54146487,0.0018564208,0.39962834,0.0009768774,0.00057172764,0.00041733414,0.0058769146,0.00065239135,0.048555177],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99918526,0.00008901958,0.00004189668,0.00013855836,0.00044929318,0.00009589021],"domain_scores_gemma":[0.9988048,0.00032212766,0.00008123648,0.00041503308,0.0002929908,0.00008384438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000377567,0.00075070275,0.0005788239,0.0014458941,0.00056753226,0.0011189454,0.0007936671,0.0011268922,0.01525741],"category_scores_gemma":[0.003795339,0.00036481136,0.0003206111,0.0015625613,0.00064986915,0.002353188,0.0017569436,0.0015283929,0.002789726],"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":[0.001195568,0.00015025237,0.0007332492,0.0002951569,0.000040461127,0.00042298797,0.00024048756,0.041379906,0.057954438,0.32609102,0.026154164,0.5453423],"study_design_scores_gemma":[0.00022329508,0.00040383317,0.0014476463,0.00025648533,0.00006110037,0.0015619447,0.00025611272,0.39554024,0.11072979,0.3744622,0.11495893,0.0000984222],"about_ca_topic_score_codex":0.0009632664,"about_ca_topic_score_gemma":0.001528433,"teacher_disagreement_score":0.01525741,"about_ca_system_score_codex":0.0009482599,"about_ca_system_score_gemma":0.0012044396,"threshold_uncertainty_score":0.051041126},"labels":[],"label_agreement":null},{"id":"W2056526875","doi":"10.1145/1068009.1068215","title":"Statistical analysis of heuristics for evolving sorting networks","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Heuristics; Sorting; Computer science; Sorting network; Domain (mathematical analysis); Genetic algorithm; Evolutionary algorithm; Theoretical computer science; Artificial intelligence; Mathematical optimization; Machine learning; Sorting algorithm; Algorithm; Mathematics","score_opus":0.015372373946450189,"score_gpt":0.28523354114802035,"score_spread":0.26986116720157016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056526875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5769375,0.00086893036,0.41379768,0.00077626825,0.00009296307,0.00021386654,0.0006687668,0.00074748375,0.0058965837],"genre_scores_gemma":[0.94530904,0.00030370362,0.05160642,0.00012300706,0.00004348016,0.00019257025,0.0011549541,0.00013860135,0.0011282463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841225,0.00063832797,0.000085250285,0.0003615345,0.00033057458,0.00017209539],"domain_scores_gemma":[0.95858777,0.0326398,0.0031306744,0.0026952375,0.0023376085,0.00060899206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005228589,0.00041747076,0.00069193443,0.0033475207,0.0007331909,0.0012453573,0.0015022289,0.0011154403,0.0022440602],"category_scores_gemma":[0.04556389,0.0004647242,0.0008247324,0.0018106713,0.0016827472,0.0015854585,0.00058819016,0.0012364279,0.00024195517],"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":[0.00009465917,0.00006148708,0.008232328,0.00009894015,0.000116994204,0.000072329785,0.00009954028,0.9117934,0.0014459956,0.051004093,0.001795133,0.025185073],"study_design_scores_gemma":[0.000014431815,0.000040340652,0.0020228543,0.00000961522,0.000017352002,0.000033405548,0.00003597699,0.97330225,0.000602324,0.023411179,0.00049693894,0.00001326646],"about_ca_topic_score_codex":0.0035859493,"about_ca_topic_score_gemma":0.0044844383,"teacher_disagreement_score":0.005228589,"about_ca_system_score_codex":0.0025345942,"about_ca_system_score_gemma":0.0014218667,"threshold_uncertainty_score":0.027651787},"labels":[],"label_agreement":null},{"id":"W2057760616","doi":"10.1049/el.2013.1658","title":"Tabular construction of balanced codes","year":2013,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Algorithms and Data Compression","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","score_opus":0.003624838336537467,"score_gpt":0.18975737185398697,"score_spread":0.18613253351744952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057760616","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025577983,0.00023436398,0.9539682,0.00018284936,0.00017629957,0.00014501592,0.0004757127,0.00066454476,0.018575022],"genre_scores_gemma":[0.25308537,0.00059343094,0.7280018,0.00038204336,0.000098958466,0.00059593143,0.002006772,0.00045943924,0.014776206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918014,0.00023137791,0.000071693736,0.00010521787,0.00026701653,0.0001445065],"domain_scores_gemma":[0.99840254,0.00040130116,0.00015847123,0.00030562357,0.0006481396,0.00008396797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007707469,0.00046845977,0.00048741995,0.0012523547,0.00080159766,0.0013094124,0.0007460169,0.0005242177,0.008301222],"category_scores_gemma":[0.0035542517,0.00038413054,0.00040396996,0.0014027067,0.0006686163,0.0012861211,0.0014270908,0.0008625445,0.0028295454],"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":[0.0003386991,0.00007110326,0.00055705104,0.00027987175,0.000027421718,0.00022336101,0.0003330689,0.037940197,0.04469334,0.65295404,0.008994611,0.25358722],"study_design_scores_gemma":[0.00015292106,0.0003567388,0.0004205299,0.0002352188,0.000048200447,0.00047415125,0.0001905843,0.30597526,0.088744275,0.5146938,0.0886166,0.0000917623],"about_ca_topic_score_codex":0.00049504166,"about_ca_topic_score_gemma":0.0006556254,"teacher_disagreement_score":0.008301222,"about_ca_system_score_codex":0.0007273742,"about_ca_system_score_gemma":0.001076593,"threshold_uncertainty_score":0.0277704},"labels":[],"label_agreement":null},{"id":"W2057822545","doi":"10.1007/s10115-014-0736-0","title":"Finding top- $$k\\, r$$ k r -cliques for keyword search from graphs in polynomial delay","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Clique; Substructure; Keyword search; Graph; Set (abstract data type); Theoretical computer science; Context (archaeology); Combinatorics; Mathematics; Information retrieval","score_opus":0.017632627432734232,"score_gpt":0.2689965599923172,"score_spread":0.25136393255958295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057822545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3030703,0.0042010914,0.6256744,0.012013,0.00047562012,0.0025454666,0.01606083,0.014499541,0.021459708],"genre_scores_gemma":[0.46521515,0.00090595306,0.5063624,0.0011398124,0.0002396568,0.00062338676,0.011656096,0.0017585572,0.012099048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739265,0.0005571557,0.00020288327,0.0009305328,0.00045523662,0.0004615442],"domain_scores_gemma":[0.9879848,0.008643326,0.0006473311,0.0014206932,0.00068536116,0.0006185755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015200974,0.0018416169,0.003239273,0.0030536463,0.0022958925,0.004244952,0.0047641336,0.0032835214,0.014030264],"category_scores_gemma":[0.015874432,0.0015919821,0.0027503292,0.0047224932,0.0017158565,0.008203542,0.0040204558,0.0022334335,0.00451434],"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":[0.00497056,0.0020197614,0.007929267,0.0038383019,0.0007823089,0.000834398,0.0018264509,0.24057421,0.053806897,0.06317663,0.11686241,0.50337875],"study_design_scores_gemma":[0.0005421519,0.0002175903,0.0013537864,0.0001012722,0.00021854379,0.00047745873,0.00073710654,0.84930515,0.011246721,0.12980735,0.0059118806,0.000080921076],"about_ca_topic_score_codex":0.013818193,"about_ca_topic_score_gemma":0.035113636,"teacher_disagreement_score":0.014030264,"about_ca_system_score_codex":0.0034646716,"about_ca_system_score_gemma":0.006392735,"threshold_uncertainty_score":0.046935976},"labels":[],"label_agreement":null},{"id":"W2058305583","doi":"10.1142/s0129054106004418","title":"RECONSTRUCTING A SUFFIX ARRAY","year":2006,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicographical order; Suffix array; Compressed suffix array; Suffix tree; Generalized suffix tree; Suffix; Computer science; String (physics); Data structure; Alphabet; Simple (philosophy); Construct (python library); Algorithm; Mathematics; Theoretical computer science; Combinatorics; Programming language","score_opus":0.01205037815274377,"score_gpt":0.2796258498087055,"score_spread":0.2675754716559617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058305583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033486657,0.00037679725,0.9594282,0.0002799148,0.0001986124,0.000077779,0.000593302,0.0023927258,0.003166046],"genre_scores_gemma":[0.10131246,0.0005156328,0.8905549,0.00011981688,0.00007536605,0.000084030326,0.002076361,0.00047421004,0.0047872015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999091,0.00017414734,0.00010382126,0.00024065658,0.00030991697,0.00008037151],"domain_scores_gemma":[0.99611557,0.0013408506,0.00027199768,0.0014718985,0.0007097772,0.00008990488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076390285,0.0006853499,0.0009137875,0.0012641967,0.0007603365,0.0016310432,0.0011282976,0.0013183685,0.0041430946],"category_scores_gemma":[0.0074107237,0.0005618757,0.0008251046,0.002446195,0.00071069034,0.003295461,0.0013301527,0.0013607556,0.0041107177],"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":[0.0008127522,0.000114966686,0.0028215637,0.0008337127,0.00010974499,0.00081070076,0.0007069268,0.04386954,0.14301413,0.082852356,0.008889862,0.71516377],"study_design_scores_gemma":[0.000079012134,0.00057036063,0.0011516428,0.00015640746,0.00013659561,0.003228647,0.00065786426,0.43591896,0.34095863,0.13349764,0.08353029,0.00011400491],"about_ca_topic_score_codex":0.00041210136,"about_ca_topic_score_gemma":0.00042132038,"teacher_disagreement_score":0.0041430946,"about_ca_system_score_codex":0.0003210173,"about_ca_system_score_gemma":0.0010610304,"threshold_uncertainty_score":0.013859987},"labels":[],"label_agreement":null},{"id":"W2059472642","doi":"10.2481/dsj.5.143","title":"A hashing technique using separate binary tree","year":2006,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Algorithms and Data Compression","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 Ottawa","funders":"","keywords":"Computer science; Scope (computer science); Usability; Data science; Metadata; Transparency (behavior); Data publishing; Implementation; World Wide Web; Publishing; Software engineering; Computer security; Political science","score_opus":0.05802956779394889,"score_gpt":0.3299944953690478,"score_spread":0.2719649275750989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059472642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02263773,0.0018433383,0.964668,0.0002318936,0.00080230174,0.00023851359,0.000349516,0.0025920018,0.0066367197],"genre_scores_gemma":[0.23105596,0.0012095388,0.7406788,0.0003651432,0.00039238192,0.00028674866,0.0018110988,0.00047710727,0.023723263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984341,0.00018948464,0.0001510663,0.000327001,0.000734364,0.0001639809],"domain_scores_gemma":[0.99780625,0.00043680076,0.00013857287,0.0009493836,0.00056302216,0.000106074185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095758995,0.0006172356,0.0011931361,0.002315005,0.0012410335,0.0013968665,0.0018346974,0.0012627905,0.012704835],"category_scores_gemma":[0.0038465927,0.00050746,0.0008589944,0.003310687,0.0008217053,0.004128381,0.0030084061,0.0011440995,0.008978047],"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":[0.0007375075,0.00018701713,0.0012553982,0.00042727808,0.00008238549,0.00021904107,0.0003589464,0.008193961,0.05123429,0.027969398,0.015217384,0.8941174],"study_design_scores_gemma":[0.0004442316,0.0025388119,0.0055326084,0.00034470393,0.0003886396,0.0075619044,0.0009428406,0.5053044,0.22679394,0.078072555,0.1716384,0.00043707612],"about_ca_topic_score_codex":0.0010178941,"about_ca_topic_score_gemma":0.001035648,"teacher_disagreement_score":0.012704835,"about_ca_system_score_codex":0.0004346931,"about_ca_system_score_gemma":0.0009808681,"threshold_uncertainty_score":0.042501926},"labels":[],"label_agreement":null},{"id":"W2059818323","doi":"10.1145/1064546.1180611","title":"Fast string sorting using order-preserving compression","year":2005,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","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 British Columbia; University of Waterloo","funders":"","keywords":"Algorithm; Sorting; Computer science; String (physics); Sorting algorithm; Data compression; Bounded function; Online algorithm; Compression (physics); Data structure; Theoretical computer science; Mathematics","score_opus":0.036574168632612,"score_gpt":0.31453958673888593,"score_spread":0.27796541810627395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059818323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5834325,0.0020165693,0.35193425,0.0008566729,0.00052623235,0.0005419113,0.0022973493,0.03172546,0.026669046],"genre_scores_gemma":[0.78038085,0.000787504,0.20832956,0.00024472878,0.00009997444,0.00030036113,0.0029897096,0.00090021896,0.0059670717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821764,0.00016017842,0.00019760917,0.00022441223,0.0009471311,0.00025301054],"domain_scores_gemma":[0.99347794,0.0025684624,0.00033077953,0.002227446,0.0012590161,0.00013631729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011224215,0.00072667556,0.0005714562,0.0018394897,0.0008183854,0.0013282177,0.0015098958,0.0008592956,0.005162708],"category_scores_gemma":[0.0064982055,0.000265458,0.0004860341,0.0053609107,0.00085154694,0.004294463,0.0009834999,0.0008847564,0.0011274511],"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":[0.0032342905,0.0011853157,0.004887313,0.0009465941,0.0001608343,0.00055576646,0.00057315524,0.14693068,0.14812665,0.054172102,0.020291353,0.61893606],"study_design_scores_gemma":[0.00047116156,0.0012314791,0.0027217923,0.00008144102,0.00010163434,0.0006223946,0.0001814541,0.47199738,0.4759842,0.027487423,0.019011695,0.00010791766],"about_ca_topic_score_codex":0.0031789353,"about_ca_topic_score_gemma":0.0024174592,"teacher_disagreement_score":0.005162708,"about_ca_system_score_codex":0.0012840751,"about_ca_system_score_gemma":0.0014801311,"threshold_uncertainty_score":0.017270982},"labels":[],"label_agreement":null},{"id":"W2059884147","doi":"10.5555/1070432.1070437","title":"A categorization theorem on suffix arrays with applications to space efficient text indexes","year":2005,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Suffix array; Combinatorics; String (physics); Binary number; Permutation (music); Cardinality (data modeling); Compressed suffix array; Discrete mathematics; Generalized suffix tree; Suffix tree; Mathematics; Computer science; Arithmetic; Data mining","score_opus":0.008185812719306998,"score_gpt":0.24372485196968968,"score_spread":0.2355390392503827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059884147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010370119,0.0006053845,0.9825065,0.0007510273,0.00014670118,0.000105952684,0.00020622488,0.0011502706,0.0041577783],"genre_scores_gemma":[0.14765385,0.0011584387,0.8410548,0.0011029849,0.0005433546,0.00052385434,0.00086709944,0.00047913348,0.006616568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99686337,0.00062575965,0.000436669,0.0005604987,0.001287492,0.00022619721],"domain_scores_gemma":[0.9904365,0.00403178,0.0009305961,0.002865462,0.001504899,0.00023073706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025845487,0.0007716601,0.0010414212,0.0024672963,0.0013509754,0.0031007873,0.002211482,0.0013197159,0.0068495558],"category_scores_gemma":[0.016113892,0.00072311267,0.0009291711,0.0039306735,0.0023750023,0.0120982025,0.002977554,0.0018186918,0.0031940842],"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":[0.00031571047,0.0001526759,0.0011978766,0.0004204592,0.000034075303,0.00015478054,0.00047101747,0.023040764,0.020227917,0.6349384,0.011890132,0.30715612],"study_design_scores_gemma":[0.00015966159,0.00064280693,0.00088723307,0.00027963365,0.00007483045,0.0012907712,0.0002490398,0.25623232,0.048761804,0.59115833,0.10014591,0.000117568314],"about_ca_topic_score_codex":0.00061874645,"about_ca_topic_score_gemma":0.00058756955,"teacher_disagreement_score":0.0068495558,"about_ca_system_score_codex":0.0017490559,"about_ca_system_score_gemma":0.0013656066,"threshold_uncertainty_score":0.022914052},"labels":[],"label_agreement":null},{"id":"W2062088872","doi":"10.1016/s0304-3975(03)00320-7","title":"On the complexity of finding common approximate substrings","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of New Brunswick","funders":"","keywords":"Parameterized complexity; Substring; Mathematics; Hamming distance; Combinatorics; String (physics); Alphabet; Time complexity; Class (philosophy); Set (abstract data type); Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.03818003502775003,"score_gpt":0.26858535743145007,"score_spread":0.23040532240370004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062088872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47401792,0.007134639,0.4661272,0.018041825,0.0006363578,0.00046708138,0.004678404,0.0026968222,0.026199806],"genre_scores_gemma":[0.7585545,0.0032140939,0.21844466,0.0012427686,0.001136095,0.00044766214,0.0064230557,0.0009290152,0.009608076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886497,0.002532762,0.0011152175,0.0020758044,0.0045536812,0.0010726855],"domain_scores_gemma":[0.8172253,0.16346498,0.0047398624,0.009091857,0.0038093838,0.0016687831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055331807,0.0014514682,0.0038580399,0.0037676056,0.0026446246,0.0090950355,0.005657472,0.0041899662,0.014817407],"category_scores_gemma":[0.07686041,0.001399369,0.002431808,0.009220825,0.0044569448,0.023567,0.0069135907,0.0046889964,0.0018041254],"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":[0.0061791004,0.000856752,0.017621541,0.0019674657,0.0005411471,0.0011228698,0.002321393,0.35793012,0.008853751,0.19517924,0.035073765,0.37235284],"study_design_scores_gemma":[0.00029962318,0.00016271131,0.0016029003,0.0000793158,0.00018184836,0.00062705594,0.00061479124,0.64718956,0.0027810899,0.34343582,0.0029644754,0.000060824495],"about_ca_topic_score_codex":0.006744414,"about_ca_topic_score_gemma":0.007841233,"teacher_disagreement_score":0.014817407,"about_ca_system_score_codex":0.0044560432,"about_ca_system_score_gemma":0.0038666606,"threshold_uncertainty_score":0.04956919},"labels":[],"label_agreement":null},{"id":"W2062214685","doi":"10.1007/s00224-007-1329-z","title":"A Faster FPT Algorithm for the Maximum Agreement Forest Problem","year":2007,"lang":"en","type":"article","venue":"Theory of Computing Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Disjoint sets; Partition (number theory); Combinatorics; Cardinality (data modeling); Phylogenetic tree; Mathematics; Time complexity; Order (exchange); Binary number; Running time; Set (abstract data type); Algorithm; Pairwise comparison; Computer science; Statistics; Chemistry; Data mining","score_opus":0.01855616429137116,"score_gpt":0.25570376843143866,"score_spread":0.2371476041400675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062214685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01945277,0.0011222651,0.9571615,0.0021468932,0.0006410961,0.00031715227,0.0010579146,0.005038374,0.0130620245],"genre_scores_gemma":[0.12494232,0.00038152284,0.86212337,0.0006085573,0.00049851084,0.00041835025,0.0025031331,0.0009397857,0.0075843628],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798524,0.00034838382,0.0001285736,0.00048294282,0.0007682714,0.00028648772],"domain_scores_gemma":[0.9943141,0.0031336434,0.0001914639,0.0013974422,0.00071378174,0.00024965242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017295231,0.0012223992,0.0019295657,0.0017206651,0.0014647446,0.002718903,0.002967382,0.0023702865,0.019944822],"category_scores_gemma":[0.011171876,0.0006384304,0.001541752,0.0031031673,0.0009874564,0.005887378,0.0028804482,0.0042506214,0.005304136],"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":[0.0008908182,0.00043435756,0.0007187941,0.00046959068,0.00008878247,0.00020373681,0.00020085725,0.051560264,0.009205783,0.07323705,0.054854378,0.80813557],"study_design_scores_gemma":[0.00053317857,0.00016941603,0.00054357096,0.00008711022,0.000101566904,0.000562217,0.00015800165,0.64311236,0.0072219567,0.32435396,0.02310523,0.000051404884],"about_ca_topic_score_codex":0.0034449939,"about_ca_topic_score_gemma":0.0044300896,"teacher_disagreement_score":0.019944822,"about_ca_system_score_codex":0.0015296742,"about_ca_system_score_gemma":0.0024434577,"threshold_uncertainty_score":0.066722035},"labels":[],"label_agreement":null},{"id":"W2063478894","doi":"10.1109/cec.2013.6557750","title":"Woven string kernels for DNA sequence classification","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Guelph","funders":"","keywords":"String kernel; String (physics); Kernel (algebra); Weaving; Computer science; Biological data; String searching algorithm; Synthetic data; Set (abstract data type); Algorithm; Directed acyclic graph; Graph; Kernel method; Theoretical computer science; Data structure; Graph kernel; Pattern recognition (psychology); Artificial intelligence; Pattern matching; Mathematics; Support vector machine; Combinatorics; Polynomial kernel; Engineering; Bioinformatics; Biology","score_opus":0.07363506333861959,"score_gpt":0.29337953487155494,"score_spread":0.21974447153293536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063478894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025246726,0.0003472592,0.97144663,0.00018814908,0.00005838935,0.000040523802,0.00017249878,0.0014014286,0.0010983518],"genre_scores_gemma":[0.37748593,0.0009383361,0.61559075,0.00021500305,0.0001317113,0.00014042741,0.0010038485,0.00034851875,0.00414552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999445,0.00016012536,0.00005007937,0.00010915997,0.00019086375,0.000044785833],"domain_scores_gemma":[0.99628556,0.001893527,0.0003100309,0.000885424,0.00051115017,0.00011436856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096499844,0.0004267738,0.0005803253,0.0023086215,0.00037902792,0.0010826373,0.00096790586,0.0008751624,0.0022786593],"category_scores_gemma":[0.007974992,0.00024313015,0.0005498941,0.0032317103,0.00087548565,0.0027398146,0.0008101653,0.001263223,0.001055094],"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":[0.0002920212,0.00016458354,0.002702172,0.00020145706,0.00007030708,0.00017012731,0.00018309528,0.23030637,0.02081657,0.11540264,0.0044028065,0.62528783],"study_design_scores_gemma":[0.0000068576796,0.000037435075,0.00052255974,0.000016802014,0.000008272508,0.00007837765,0.000022387896,0.9419188,0.007031076,0.04740064,0.0029394717,0.00001742557],"about_ca_topic_score_codex":0.0012677913,"about_ca_topic_score_gemma":0.0010807969,"teacher_disagreement_score":0.0023086215,"about_ca_system_score_codex":0.00064499973,"about_ca_system_score_gemma":0.00053738576,"threshold_uncertainty_score":0.007622838},"labels":[],"label_agreement":null},{"id":"W2063841356","doi":"10.1007/s11786-007-0024-4","title":"Lempel–Ziv Factorization Using Less Time &amp; Space","year":2008,"lang":"en","type":"article","venue":"Mathematics in Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Compressed suffix array; Generalized suffix tree; Suffix tree; Suffix array; Factorization; Suffix; String (physics); Data structure; Mathematics; Time complexity; Algorithm; Alphabet; Combinatorics; Computer science; Discrete mathematics","score_opus":0.07001208019824393,"score_gpt":0.28516992337848157,"score_spread":0.21515784318023765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063841356","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030872175,0.0014771799,0.9240168,0.0017845137,0.001012628,0.00030753386,0.00083800114,0.004212051,0.035479024],"genre_scores_gemma":[0.19498989,0.0007279757,0.7644397,0.001153571,0.00089065096,0.00040236406,0.0018526193,0.0008089749,0.03473422],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997131,0.00073280034,0.00019282456,0.0004933607,0.0010135025,0.00043656968],"domain_scores_gemma":[0.9962114,0.0012251551,0.0002308095,0.0016299462,0.00054637634,0.00015627856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013414539,0.0019740795,0.0016714201,0.001955036,0.0018008283,0.0029859545,0.0015586332,0.0014151199,0.040322237],"category_scores_gemma":[0.0075414754,0.00050275464,0.001414748,0.0022413821,0.0016203792,0.0060300143,0.0030536607,0.0021705746,0.018638244],"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":[0.0015965878,0.00044296912,0.0005790239,0.0007180255,0.00010955783,0.00046323412,0.00043831655,0.019380456,0.048272118,0.27547315,0.04911785,0.60340863],"study_design_scores_gemma":[0.00049435796,0.000727986,0.00071856665,0.00022600238,0.00015115757,0.0016848403,0.00065316673,0.24977885,0.09030858,0.52673393,0.12831533,0.00020730343],"about_ca_topic_score_codex":0.0016243019,"about_ca_topic_score_gemma":0.0035747932,"teacher_disagreement_score":0.040322237,"about_ca_system_score_codex":0.0010307707,"about_ca_system_score_gemma":0.0017867499,"threshold_uncertainty_score":0.13489133},"labels":[],"label_agreement":null},{"id":"W2064212735","doi":"10.1017/s0963548307008796","title":"An Analysis of the Height of Tries with Random Weights on the Edges","year":2007,"lang":"en","type":"article","venue":"Combinatorics Probability Computing","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Trie; Combinatorics; Mathematics; Exponent; String (physics); Enhanced Data Rates for GSM Evolution; Set (abstract data type); Alphabet; Function (biology); Discrete mathematics; Computer science; Data structure","score_opus":0.01640925999895056,"score_gpt":0.24312366649816672,"score_spread":0.22671440649921615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064212735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8521589,0.0006183028,0.1392742,0.00058480917,0.000054038857,0.00007268928,0.00034392538,0.00038814766,0.006504911],"genre_scores_gemma":[0.9835533,0.00025599945,0.012784857,0.00008654021,0.00006126702,0.000085228356,0.0002700285,0.00016993057,0.002732716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904865,0.00026010303,0.000041951804,0.00013333846,0.00021763075,0.00029835667],"domain_scores_gemma":[0.9848626,0.010629817,0.0014365274,0.0013265031,0.0008712895,0.0008732586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001843677,0.000551744,0.0008902187,0.0016886507,0.0007439807,0.0014561157,0.0019012113,0.001172459,0.0034842172],"category_scores_gemma":[0.01574256,0.00071037584,0.0008437314,0.0013972684,0.0023438793,0.0032549547,0.0016409713,0.0012563153,0.0004006262],"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":[0.000660969,0.00013052904,0.008272642,0.0002755752,0.0001477699,0.0006478034,0.00053701975,0.61852854,0.017748866,0.33192647,0.0027923125,0.018331528],"study_design_scores_gemma":[0.000036266272,0.00013769702,0.0013572205,0.00002244984,0.000039551964,0.00018539482,0.000096586926,0.88940865,0.0028932684,0.10518199,0.0006119794,0.000028927896],"about_ca_topic_score_codex":0.001107367,"about_ca_topic_score_gemma":0.0010779707,"teacher_disagreement_score":0.0034842172,"about_ca_system_score_codex":0.0012831136,"about_ca_system_score_gemma":0.0007880057,"threshold_uncertainty_score":0.011655867},"labels":[],"label_agreement":null},{"id":"W2065060855","doi":"10.1109/tit.2013.2295392","title":"A Universal Grammar-Based Code for Lossless Compression of Binary Trees","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Code word; Lossless compression; Binary tree; Computer science; Theoretical computer science; Random binary tree; K-ary tree; Binary number; Binary code; Mathematics; Algorithm; Decoding methods; Data compression; Tree structure; Arithmetic","score_opus":0.01103379855174834,"score_gpt":0.23154011697648408,"score_spread":0.22050631842473573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065060855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030155694,0.0006889895,0.9657736,0.00031826893,0.000067382636,0.000056031142,0.00016512896,0.00047990627,0.002295031],"genre_scores_gemma":[0.5684643,0.0013075998,0.4237118,0.00048784865,0.00019040737,0.00026750247,0.0006104665,0.00033655151,0.0046235076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930036,0.00012378322,0.00003821935,0.00012260413,0.00034685121,0.00006808788],"domain_scores_gemma":[0.9983901,0.00076836394,0.0001429522,0.0003498899,0.0002845738,0.00006423194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006005275,0.0003763147,0.0005349954,0.0008728415,0.00041766063,0.00075783505,0.0009364831,0.0010101988,0.0009893912],"category_scores_gemma":[0.0043973774,0.00021032784,0.00036122397,0.0011329293,0.0013822516,0.0013956943,0.0013365503,0.0010871446,0.00032347965],"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":[0.0002119918,0.00006931799,0.00073524757,0.00033883934,0.000040836,0.0006335202,0.00039359636,0.21741381,0.040060658,0.5287042,0.0042178626,0.20718007],"study_design_scores_gemma":[0.000027594464,0.000079378166,0.00019567732,0.00005578734,0.000023700439,0.0005418935,0.000030975236,0.83375937,0.018246539,0.1408184,0.0061892048,0.00003151444],"about_ca_topic_score_codex":0.0012864647,"about_ca_topic_score_gemma":0.0011275241,"teacher_disagreement_score":0.0012864647,"about_ca_system_score_codex":0.0007316735,"about_ca_system_score_gemma":0.0011739095,"threshold_uncertainty_score":0.0053086877},"labels":[],"label_agreement":null},{"id":"W2065457428","doi":"10.5555/365411.365526","title":"Representing dynamic binary trees succinctly","year":2001,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Binary number; Representation (politics); Amortized analysis; Binary tree; Computer science; Constant (computer programming); Binary search tree; Weight-balanced tree; Contrast (vision); Binary decision diagram; Theoretical computer science; Data structure; Binary expression tree; Discrete mathematics; Combinatorics; Mathematics; Algorithm; Arithmetic; Programming language; Artificial intelligence","score_opus":0.011674444197509347,"score_gpt":0.26678274107081956,"score_spread":0.2551082968733102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065457428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03394069,0.0008186998,0.95354694,0.0005252912,0.0002116448,0.00011424035,0.0021012952,0.0019637262,0.006777428],"genre_scores_gemma":[0.41572466,0.0021688894,0.5619731,0.00046377012,0.00020594498,0.00042864654,0.0058093527,0.00062794547,0.012597657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993864,0.00010994329,0.00006872541,0.000099604644,0.0002511733,0.000084105326],"domain_scores_gemma":[0.99832445,0.00052221277,0.00020450106,0.00063042075,0.00026646897,0.000051956427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004599627,0.00051212363,0.00067438843,0.0011851647,0.00043784626,0.0020526582,0.0011492518,0.00077652343,0.005304078],"category_scores_gemma":[0.004316065,0.00044833528,0.00037078225,0.0023890894,0.00062698725,0.005570316,0.00155849,0.0011691304,0.0014029719],"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":[0.0005159394,0.00018165247,0.0008664461,0.000458428,0.00003723698,0.00048058468,0.0005526115,0.10999774,0.026982091,0.30714354,0.016783308,0.53600043],"study_design_scores_gemma":[0.000107072476,0.0002249418,0.00040945635,0.00023591027,0.000076780896,0.00064289884,0.0002183641,0.5073244,0.037961885,0.37456715,0.07813842,0.00009271141],"about_ca_topic_score_codex":0.00083829847,"about_ca_topic_score_gemma":0.0015076409,"teacher_disagreement_score":0.005304078,"about_ca_system_score_codex":0.00050272327,"about_ca_system_score_gemma":0.00062499335,"threshold_uncertainty_score":0.017743886},"labels":[],"label_agreement":null},{"id":"W2065566607","doi":"10.1155/2014/194202","title":"On Coalescence Analysis Using Genealogy Rooted Trees","year":2014,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Algorithms and Data Compression","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":"Actua; Western University","funders":"","keywords":"Coalescent theory; Inference; Recursion (computer science); Approximate Bayesian computation; Coalescence (physics); Population; Computer science; Limit (mathematics); Computation; Sequence (biology); Simple (philosophy); Mathematics; Theoretical computer science; Algorithm; Biology; Artificial intelligence; Phylogenetic tree; Genetics; Demography","score_opus":0.0658706901583375,"score_gpt":0.42496956367212096,"score_spread":0.35909887351378345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065566607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011110622,0.00091633486,0.98657596,0.00027297492,0.000032716795,0.000025278807,0.00005180186,0.00012036841,0.00089397683],"genre_scores_gemma":[0.29688412,0.0047397297,0.6928126,0.00047114573,0.0005259044,0.00028502278,0.00059107563,0.0004722938,0.0032179956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980198,0.001093491,0.00010501433,0.00020675838,0.00050134957,0.000073549156],"domain_scores_gemma":[0.9787274,0.018846948,0.00065382523,0.0008895556,0.0006957395,0.00018657392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059807524,0.00068958924,0.0010287768,0.0037600796,0.0010116912,0.0016748753,0.0019470897,0.0011234869,0.0015881517],"category_scores_gemma":[0.039760463,0.0005424127,0.001052562,0.003447955,0.0031207989,0.0034330315,0.0024503632,0.0022269906,0.00046729128],"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":[0.000091286536,0.00005144794,0.0022583243,0.00017590019,0.00011615775,0.00031464812,0.00047656934,0.3496515,0.0026395423,0.54273057,0.0016431593,0.09985091],"study_design_scores_gemma":[0.000014037948,0.000011913101,0.00043104673,0.00003292709,0.000015797596,0.000068185014,0.000024205994,0.68123734,0.0005626241,0.31602758,0.0015576946,0.000016722575],"about_ca_topic_score_codex":0.003304812,"about_ca_topic_score_gemma":0.0020016513,"teacher_disagreement_score":0.0059807524,"about_ca_system_score_codex":0.0011240381,"about_ca_system_score_gemma":0.001068686,"threshold_uncertainty_score":0.031629562},"labels":[],"label_agreement":null},{"id":"W2066180679","doi":"10.1139/p02-005","title":"On spin irreps of (1 I<sub><i>i</i></sub> 3) 12-fold uniform NMR spin systems as invariant-based dual tensorial sets: Roles in spin physics for weight sets and their -partitional frequency catalogues","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Physics; Invariant (physics); Lattice (music); Spin (aerodynamics); Quantum mechanics; Theoretical physics; Mathematical physics","score_opus":0.02126100355071181,"score_gpt":0.22229579901880178,"score_spread":0.20103479546808997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066180679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53500664,0.00050408405,0.33624431,0.0007780848,0.00059791596,0.00014967799,0.000402118,0.00067876925,0.12563844],"genre_scores_gemma":[0.91244036,0.0004881631,0.06671384,0.00045912352,0.00032306515,0.00022754393,0.00047555775,0.0003925339,0.018479774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940705,0.00014855374,0.000039693805,0.00008868882,0.00020246724,0.000113612616],"domain_scores_gemma":[0.99942636,0.00015417964,0.0001020486,0.00015425567,0.00006935537,0.000093748364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009872966,0.0006368516,0.0005432635,0.0016799242,0.0014465104,0.0022590808,0.0010174938,0.0009277743,0.008414028],"category_scores_gemma":[0.0015856548,0.00037870198,0.00063375325,0.00073625945,0.0035593943,0.0023877101,0.001428809,0.0014467356,0.0014693456],"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":[0.000012788681,0.000010932459,0.00006197849,0.000018232593,0.0000014208952,0.00004330689,0.00010290994,0.0012997533,0.0018103687,0.9921409,0.00040032412,0.004097107],"study_design_scores_gemma":[0.0000076573415,0.000041524727,0.00022705627,0.000031864718,0.000004235881,0.00010545954,0.00011574515,0.022062397,0.00367225,0.9684872,0.0052152867,0.000029390956],"about_ca_topic_score_codex":0.00060163805,"about_ca_topic_score_gemma":0.0007416762,"teacher_disagreement_score":0.008414028,"about_ca_system_score_codex":0.00091420417,"about_ca_system_score_gemma":0.0005592579,"threshold_uncertainty_score":0.028147757},"labels":[],"label_agreement":null},{"id":"W2066342920","doi":"10.1016/j.jda.2014.06.003","title":"The lexicographically smallest universal cycle for binary strings with minimum specified weight","year":2014,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicographical order; Aperiodic graph; Mathematics; Binary number; Combinatorics; Discrete mathematics; Prefix; Simple (philosophy); Amortized analysis; Set (abstract data type); Order (exchange); Arithmetic; Computer science; Data structure","score_opus":0.008251096188583884,"score_gpt":0.22370187750932216,"score_spread":0.21545078132073828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066342920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6272511,0.0016253205,0.33096164,0.0019616126,0.00040419094,0.00038098122,0.0026358468,0.0012850529,0.033494346],"genre_scores_gemma":[0.8101431,0.0008494693,0.17257342,0.00047474026,0.000091627335,0.0003814916,0.0021466345,0.0006649877,0.012674508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943787,0.000107193744,0.000053096745,0.00012690542,0.00015169439,0.00012325941],"domain_scores_gemma":[0.9982855,0.0007618638,0.00013526586,0.0003571579,0.00028272977,0.00017738494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039142225,0.00043344204,0.00084750727,0.0017625517,0.0014828708,0.0018826132,0.0009440311,0.0011605213,0.0069971723],"category_scores_gemma":[0.006155585,0.0004172708,0.0005349108,0.0019400064,0.0011458063,0.0026742087,0.001647642,0.0008858707,0.0010326161],"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":[0.0019363431,0.00022437138,0.0040739533,0.00090983097,0.00007000708,0.00043332853,0.0012547862,0.030934732,0.04268998,0.49927714,0.017117355,0.40107822],"study_design_scores_gemma":[0.000118261494,0.0003327123,0.0012849205,0.00033959578,0.000065769855,0.0005183556,0.0006985086,0.10095294,0.0314953,0.8434088,0.020707477,0.00007737228],"about_ca_topic_score_codex":0.0013244672,"about_ca_topic_score_gemma":0.0023634206,"teacher_disagreement_score":0.0069971723,"about_ca_system_score_codex":0.0010209943,"about_ca_system_score_gemma":0.0017150849,"threshold_uncertainty_score":0.023407876},"labels":[],"label_agreement":null},{"id":"W2066574146","doi":"10.1002/rsa.10006","title":"Analysis of random LC tries","year":2001,"lang":"en","type":"article","venue":"Random Structures and Algorithms","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Trie; Node (physics); Combinatorics; Binary logarithm; Mathematics; Discrete mathematics; Computer science; Physics; Data structure; Quantum mechanics","score_opus":0.010305402516997797,"score_gpt":0.2496198197540519,"score_spread":0.2393144172370541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066574146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44179887,0.0020137252,0.5259132,0.0014654151,0.00009743804,0.00026989286,0.0012488374,0.0018540559,0.025338529],"genre_scores_gemma":[0.95927507,0.000600416,0.031875145,0.0003901657,0.00014432937,0.00030767897,0.0010374613,0.0003469858,0.00602285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705887,0.000927318,0.00014962228,0.00036845868,0.0009276603,0.0005680292],"domain_scores_gemma":[0.9712569,0.017780999,0.002750123,0.0037768367,0.0033291378,0.0011061212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034617963,0.0005164586,0.0011548338,0.0029457803,0.0010512227,0.0019302911,0.0017879545,0.0012483781,0.00618203],"category_scores_gemma":[0.0325048,0.00063177885,0.00088429917,0.0023962418,0.0026496097,0.0041241837,0.0031074954,0.0016722678,0.0009437689],"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":[0.0006117856,0.00011124276,0.009855498,0.00032294652,0.00012685944,0.0007311424,0.0005597068,0.27165487,0.00625391,0.65831083,0.011253194,0.04020797],"study_design_scores_gemma":[0.000042375457,0.00009166884,0.0012137068,0.00005346104,0.000040620314,0.00046589965,0.00011224038,0.79727715,0.0027770093,0.19513,0.002765704,0.000030215024],"about_ca_topic_score_codex":0.0010649698,"about_ca_topic_score_gemma":0.0009754666,"teacher_disagreement_score":0.00618203,"about_ca_system_score_codex":0.002002828,"about_ca_system_score_gemma":0.0012925828,"threshold_uncertainty_score":0.020681024},"labels":[],"label_agreement":null},{"id":"W2066632851","doi":"10.1109/icip.2012.6467554","title":"A new context-sensitive grammars learning algorithm and its application in trajectory classification","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Computer science; Trajectory; Rule-based machine translation; Context (archaeology); Context-free grammar; Algorithm; Series (stratigraphy); Scheme (mathematics); Artificial intelligence; Machine learning; Mathematics","score_opus":0.021609884470583495,"score_gpt":0.2540731033229909,"score_spread":0.2324632188524074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066632851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034336613,0.000094818315,0.99553347,0.00009607141,0.000027241502,0.000025556095,0.000050250695,0.00050728663,0.00023168065],"genre_scores_gemma":[0.12287715,0.00025733616,0.8736257,0.00022289203,0.000084264015,0.00019642408,0.0005581712,0.00029088845,0.001887221],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890196,0.00024312362,0.00007526715,0.0003864063,0.00032309955,0.0000702158],"domain_scores_gemma":[0.9982451,0.000935206,0.000120048535,0.00028896032,0.0003405096,0.000070178656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013943725,0.0007698166,0.0010927785,0.0019214033,0.000984106,0.0008747894,0.0023519222,0.0014737148,0.0021398622],"category_scores_gemma":[0.0053095147,0.00047054174,0.0009986602,0.002556423,0.0011372643,0.002407032,0.001493859,0.0021632737,0.0008258117],"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":[0.00008151055,0.000105230196,0.0018227071,0.00009967575,0.00007718581,0.00015172092,0.00018341414,0.32969952,0.005818784,0.042330123,0.0046827644,0.6149473],"study_design_scores_gemma":[0.000008308265,0.000011465996,0.00014272066,0.000005919585,0.0000071074996,0.000045179895,0.000014151664,0.979726,0.0013429165,0.01711555,0.0015698816,0.000010748322],"about_ca_topic_score_codex":0.008242379,"about_ca_topic_score_gemma":0.007645556,"teacher_disagreement_score":0.008242379,"about_ca_system_score_codex":0.00095435424,"about_ca_system_score_gemma":0.0021959248,"threshold_uncertainty_score":0.016388774},"labels":[],"label_agreement":null},{"id":"W2067149955","doi":"10.1142/s0129054104002297","title":"WORD COMPLEXITY AND REPETITIONS IN WORDS","year":2004,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Repetition (rhetorical device); Word (group theory); De Bruijn sequence; Mathematics; Combinatorics on words; Prefix; Iterated function; Logarithm; Complexity class; Time complexity; Morphism; Computational complexity theory; Combinatorics; Discrete mathematics; Arithmetic; Algorithm","score_opus":0.027779165371465343,"score_gpt":0.3161795475744101,"score_spread":0.2884003822029447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067149955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4408273,0.004634791,0.49425003,0.0024217798,0.00034173307,0.00018144737,0.00100672,0.00083383365,0.055502422],"genre_scores_gemma":[0.88233715,0.0016554197,0.09707962,0.00042067736,0.0008018908,0.000374919,0.0008064244,0.0003949931,0.01612888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970324,0.00045225566,0.0002866562,0.0006737906,0.0012131591,0.00034167164],"domain_scores_gemma":[0.9899644,0.005997177,0.0012924738,0.0013155293,0.0010078537,0.0004225243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009024424,0.0006757373,0.0008589603,0.0028069909,0.0010710653,0.0032463968,0.0010552865,0.0009580618,0.0064683203],"category_scores_gemma":[0.010130842,0.00042613578,0.001152537,0.002535139,0.003744652,0.009257765,0.0028156734,0.0020848757,0.0009493975],"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":[0.00014971112,0.00005196144,0.0014132581,0.00018448374,0.000037134814,0.00030038366,0.00086466817,0.018837279,0.005144198,0.93420166,0.0016027712,0.03721244],"study_design_scores_gemma":[0.00001602485,0.00007808461,0.00072406593,0.00003293659,0.000021811402,0.00032503234,0.00011761136,0.03840224,0.0035485239,0.9499152,0.0067694965,0.00004902359],"about_ca_topic_score_codex":0.000827372,"about_ca_topic_score_gemma":0.00063698506,"teacher_disagreement_score":0.0064683203,"about_ca_system_score_codex":0.0015455745,"about_ca_system_score_gemma":0.00064137205,"threshold_uncertainty_score":0.021638691},"labels":[],"label_agreement":null},{"id":"W2067201268","doi":"10.1142/s0219720004000788","title":"IDENTIFYING UNIFORMLY MUTATED SEGMENTS WITHIN REPEATS","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","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":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"","keywords":"Mathematics; String (physics); Coin flipping; Combinatorics; Set (abstract data type); Mutation; Prior probability; Algorithm; Mutation rate; Shuffling; Discrete mathematics; Statistics; Computer science; Genetics; Biology; Bayesian probability","score_opus":0.017156221096612675,"score_gpt":0.2722669738252626,"score_spread":0.2551107527286499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067201268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24484745,0.00015640576,0.74912816,0.0001536642,0.000025743098,0.00017309417,0.0004439963,0.0032096247,0.0018618795],"genre_scores_gemma":[0.47429213,0.00008319754,0.5215225,0.000095256444,0.000018078143,0.0001652228,0.0011571308,0.0003338221,0.0023327377],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984819,0.0003028771,0.00009269864,0.0006037238,0.00034841764,0.00017032078],"domain_scores_gemma":[0.9955094,0.002475505,0.00084870594,0.000497071,0.00048751725,0.00018179632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013159517,0.0005599692,0.0011054886,0.0017877606,0.00055456103,0.001421001,0.0017466698,0.0018637904,0.0022516993],"category_scores_gemma":[0.010870622,0.0005894596,0.0007587383,0.0010279528,0.0007311748,0.0010509478,0.0012364195,0.0008353481,0.0011722624],"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":[0.0021356987,0.0002833189,0.05975987,0.00038051928,0.00027434164,0.0018824778,0.00093315437,0.25612676,0.17751276,0.03187162,0.0030798514,0.46575966],"study_design_scores_gemma":[0.000041207113,0.0001017135,0.0041830274,0.000026556183,0.000033185483,0.0004527557,0.000117766904,0.93449265,0.03791112,0.021046756,0.0015521317,0.000041061885],"about_ca_topic_score_codex":0.0020781495,"about_ca_topic_score_gemma":0.0022364522,"teacher_disagreement_score":0.0022516993,"about_ca_system_score_codex":0.0009995907,"about_ca_system_score_gemma":0.0011236425,"threshold_uncertainty_score":0.007532656},"labels":[],"label_agreement":null},{"id":"W2067300659","doi":"10.1016/j.jda.2014.12.006","title":"Inferring an indeterminate string from a prefix graph","year":2014,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Prefix; Lexicographical order; String (physics); Graph; Alphabet; Indeterminate; Simple graph","score_opus":0.013818488217496715,"score_gpt":0.2617633147738582,"score_spread":0.24794482655636152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067300659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19724132,0.0005618461,0.7899968,0.0017433662,0.00027185638,0.00015203003,0.003522639,0.0033585217,0.0031516333],"genre_scores_gemma":[0.60667837,0.0004750238,0.38517395,0.00028266147,0.0001842844,0.00011512565,0.0040927106,0.0004137208,0.0025841799],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987159,0.00025530427,0.00012021287,0.00038498358,0.00042440576,0.00009916809],"domain_scores_gemma":[0.9904233,0.0066287047,0.00035082418,0.001592865,0.0008259908,0.00017834757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008617087,0.0006380301,0.0009986483,0.0025112317,0.0008022047,0.0015931126,0.0016401691,0.0022605194,0.0037321511],"category_scores_gemma":[0.013377396,0.00048792057,0.0008662534,0.0028335308,0.0010550809,0.00481615,0.0015809061,0.0019110835,0.0010959186],"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":[0.0020339657,0.0004870341,0.01471916,0.0008565193,0.00019416447,0.0030356953,0.0006185145,0.18875186,0.04179466,0.16782862,0.013317284,0.56636244],"study_design_scores_gemma":[0.00003591316,0.000113059614,0.0008412789,0.00005482509,0.00006710191,0.00047134646,0.00015199464,0.78974956,0.012548756,0.19173093,0.0042047286,0.000030449612],"about_ca_topic_score_codex":0.0019284666,"about_ca_topic_score_gemma":0.0023954029,"teacher_disagreement_score":0.0037321511,"about_ca_system_score_codex":0.0006798468,"about_ca_system_score_gemma":0.001106253,"threshold_uncertainty_score":0.012485266},"labels":[],"label_agreement":null},{"id":"W2067662418","doi":"10.1145/1344411.1344415","title":"Locality-Based pruning methods for web search","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"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":"Fundação para a Ciência e a Tecnologia; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pruning; Computer science; Locality; Search engine; Simple (philosophy); Reduction (mathematics); Data mining; Artificial intelligence; Phrase; Information retrieval; Machine learning; Mathematics","score_opus":0.0624142167311531,"score_gpt":0.34392714943000924,"score_spread":0.28151293269885613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067662418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023591658,0.0042655757,0.9671649,0.00023538093,0.00008216256,0.000156405,0.00015405127,0.0015902682,0.002759665],"genre_scores_gemma":[0.22578208,0.0023803995,0.765236,0.0001788744,0.00027728622,0.00042681163,0.0006296634,0.00036908136,0.0047198464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978167,0.00048067977,0.00015253907,0.00020662916,0.001236699,0.00010684763],"domain_scores_gemma":[0.99611974,0.002174235,0.00029880152,0.0007603745,0.00058636494,0.00006049785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014936841,0.0006104015,0.0011430085,0.0031964171,0.00088274386,0.0010720877,0.001475164,0.0008994366,0.0017758716],"category_scores_gemma":[0.009582659,0.00041338467,0.0006276796,0.0035962549,0.0008079034,0.0024643992,0.0012421813,0.0009222531,0.00090599793],"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":[0.00025770455,0.00014729482,0.0016999487,0.000457982,0.00011414694,0.00033178463,0.0004467225,0.052921083,0.028931197,0.04168283,0.007419673,0.8655897],"study_design_scores_gemma":[0.00013978439,0.00034123615,0.0029041816,0.00013886279,0.00018798727,0.0020106675,0.00022583119,0.8187744,0.044447232,0.08799371,0.042731658,0.00010448689],"about_ca_topic_score_codex":0.0021078675,"about_ca_topic_score_gemma":0.0028650027,"teacher_disagreement_score":0.0031964171,"about_ca_system_score_codex":0.00072147965,"about_ca_system_score_gemma":0.000891291,"threshold_uncertainty_score":0.007899404},"labels":[],"label_agreement":null},{"id":"W2067675443","doi":"10.1007/s11786-010-0033-6","title":"Fast, Practical Algorithms for Computing All the Repeats in a String","year":2010,"lang":"en","type":"article","venue":"Mathematics in Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Suffix array; Algorithm; Byte; Suffix tree; String searching algorithm; Computer science; Suffix; String (physics); Generalized suffix tree; Pattern matching; Compressed suffix array; Data structure; Mathematics","score_opus":0.05655433533544037,"score_gpt":0.3537429007534002,"score_spread":0.29718856541795985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067675443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006562877,0.00059717876,0.9870207,0.0002570953,0.0001368792,0.00010480298,0.00021335426,0.0031620173,0.0019451191],"genre_scores_gemma":[0.049006697,0.00045679417,0.94584954,0.000115431896,0.00014740722,0.0002688437,0.000755902,0.00036186812,0.0030375195],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970805,0.00059849187,0.00027303578,0.0006494932,0.0011699132,0.00022856439],"domain_scores_gemma":[0.9918384,0.0040515326,0.00042546398,0.0024895368,0.000984629,0.00021046573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023637714,0.0026356508,0.0019274501,0.0028069562,0.0017806744,0.003470712,0.0037091605,0.002338184,0.011431938],"category_scores_gemma":[0.015316097,0.0010073291,0.0015895019,0.004006229,0.0018084723,0.007095273,0.0035296215,0.0042551425,0.0063281753],"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":[0.0006632417,0.00020236606,0.0011238436,0.0005160226,0.00011831125,0.0001066027,0.00033062726,0.03697527,0.012501964,0.07392929,0.018594204,0.85493827],"study_design_scores_gemma":[0.0004675537,0.00032527556,0.0007365121,0.0001096301,0.0001307954,0.0006273654,0.00035930696,0.53538764,0.021588767,0.41983688,0.020323155,0.00010718258],"about_ca_topic_score_codex":0.001732995,"about_ca_topic_score_gemma":0.004471669,"teacher_disagreement_score":0.011431938,"about_ca_system_score_codex":0.001552368,"about_ca_system_score_gemma":0.0030586876,"threshold_uncertainty_score":0.03824365},"labels":[],"label_agreement":null},{"id":"W2070295459","doi":"10.3390/e17031379","title":"The Optimal Fix-Free Code for Anti-Uniform Sources","year":2015,"lang":"en","type":"article","venue":"Entropy","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Huffman coding; Code (set theory); Canonical Huffman code; Source code; Symbol (formal); Class (philosophy); Prefix code; Universal code; Computer science; Mathematics; Combinatorics; Programming language; Algorithm; Code rate; Linear code; Decoding methods; Systematic code; Block code","score_opus":0.025722405660340248,"score_gpt":0.262229856858203,"score_spread":0.23650745119786273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070295459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16163498,0.00079716614,0.82822365,0.0005765169,0.000080322345,0.00003509478,0.00021908818,0.00028905168,0.008144085],"genre_scores_gemma":[0.8455862,0.0005983233,0.14706163,0.00027523475,0.00011668898,0.0000926142,0.00043060648,0.0001419863,0.005696735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99928564,0.00016587334,0.000037773018,0.00012053338,0.00029182062,0.00009840744],"domain_scores_gemma":[0.998145,0.0009342458,0.000214364,0.0002834856,0.00033844626,0.00008448281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078093505,0.0004707111,0.00047713993,0.0010263827,0.00047120627,0.00070637057,0.0005359435,0.0006353517,0.0013380802],"category_scores_gemma":[0.004293087,0.00025549292,0.00027152896,0.0007397569,0.0010734326,0.001439241,0.001233177,0.00078415766,0.00031749334],"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":[0.00069244974,0.00004495197,0.0013357264,0.00015457998,0.00005693338,0.00026829648,0.00021070063,0.17939584,0.029296383,0.6777437,0.0036198448,0.10718068],"study_design_scores_gemma":[0.000047327434,0.00007956009,0.000557626,0.000046898174,0.00002460967,0.00034451016,0.00004966366,0.75053656,0.02637513,0.21837436,0.0035032777,0.000060520586],"about_ca_topic_score_codex":0.0010205271,"about_ca_topic_score_gemma":0.000861393,"teacher_disagreement_score":0.0013380802,"about_ca_system_score_codex":0.0007710782,"about_ca_system_score_gemma":0.0010438662,"threshold_uncertainty_score":0.0055945516},"labels":[],"label_agreement":null},{"id":"W2070346129","doi":"10.1007/s00453-010-9452-7","title":"Succinct Representation of Labeled Graphs","year":2010,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Computer science; Planar graph; Adjacency list; Representation (politics); Graph; Pathwidth; Mathematics; Discrete mathematics; Theoretical computer science; Line graph","score_opus":0.009785539630708481,"score_gpt":0.25809857849414464,"score_spread":0.24831303886343614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070346129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030443903,0.00047440344,0.9546358,0.0012923224,0.00015920102,0.00015101337,0.0042890245,0.002243592,0.006310683],"genre_scores_gemma":[0.3519621,0.0010061642,0.61894244,0.0005949203,0.00021416497,0.000555538,0.01581758,0.00095051446,0.009956549],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832946,0.0004912372,0.00013211444,0.0003072403,0.00058430154,0.0001556825],"domain_scores_gemma":[0.9935703,0.0025380403,0.0004241604,0.0023061896,0.0009895121,0.00017178735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009174896,0.00084574777,0.0008351806,0.0021633427,0.00067933253,0.003027321,0.002203135,0.0013291371,0.00719884],"category_scores_gemma":[0.008896463,0.0005628738,0.00069407857,0.0037753596,0.0009555471,0.005685325,0.0021497398,0.002406841,0.0020351335],"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":[0.00074529875,0.00030604852,0.0010468891,0.0005134646,0.000058832076,0.00032661695,0.000558023,0.1653117,0.007968898,0.43761554,0.030566653,0.35498202],"study_design_scores_gemma":[0.00005455062,0.00004742813,0.00018123846,0.00009057124,0.000030926803,0.00014574507,0.00011039261,0.34831604,0.005570803,0.6343234,0.011106285,0.000022651167],"about_ca_topic_score_codex":0.0017460895,"about_ca_topic_score_gemma":0.003382682,"teacher_disagreement_score":0.00719884,"about_ca_system_score_codex":0.001280068,"about_ca_system_score_gemma":0.0015253912,"threshold_uncertainty_score":0.024082541},"labels":[],"label_agreement":null},{"id":"W2070567176","doi":"10.5555/365411.365445","title":"A probabilistic analysis of a greedy algorithm arising from computational biology","year":2001,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Greedy algorithm; Probabilistic analysis of algorithms; Probabilistic logic; Computer science; Theoretical computer science; Algorithm; Computational complexity theory; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.019355306410043974,"score_gpt":0.2753138278994173,"score_spread":0.2559585214893733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070567176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009229517,0.0006801766,0.9847702,0.0011795694,0.000081679704,0.000049226266,0.0000830266,0.00016658528,0.0037600913],"genre_scores_gemma":[0.44394395,0.0034893663,0.53576565,0.0013565538,0.0012724971,0.00053575175,0.0006717145,0.0008017701,0.012162754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957624,0.0015665815,0.00018627556,0.00061956694,0.0015381313,0.00032701233],"domain_scores_gemma":[0.9684742,0.025799874,0.0013266645,0.0020133143,0.0017825922,0.0006033299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059706294,0.0013038204,0.0017411346,0.0035891335,0.0018888488,0.0037266286,0.0043399273,0.003600916,0.0057988497],"category_scores_gemma":[0.043763403,0.0013130809,0.0019792214,0.0042517837,0.00521744,0.007961595,0.0043591443,0.003953495,0.0010189736],"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":[0.000085532294,0.000046302106,0.00083178043,0.00015880258,0.000052566877,0.000070526374,0.00016863452,0.10608666,0.00106641,0.8613429,0.003027737,0.027062146],"study_design_scores_gemma":[0.000016569542,0.000029966448,0.00026504492,0.000035462752,0.000027603699,0.000119823846,0.000026734528,0.4085779,0.00047052524,0.5888122,0.0015947642,0.000023478216],"about_ca_topic_score_codex":0.0019471544,"about_ca_topic_score_gemma":0.001721945,"teacher_disagreement_score":0.0059706294,"about_ca_system_score_codex":0.0024973145,"about_ca_system_score_gemma":0.0022355032,"threshold_uncertainty_score":0.031576097},"labels":[],"label_agreement":null},{"id":"W2070641109","doi":"10.1145/1777432.1777433","title":"Dynamic lightweight text compression","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"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":"Agencia Española de Cooperación Internacional para el Desarrollo; Fondo Nacional de Desarrollo Científico y Tecnológico; Xunta de Galicia; Mountain Equipment Co-operative","keywords":"Computer science; Uncompressed video; Communication source; Novelty; Lossless compression; Gas compressor; Compression (physics); Compression ratio; Natural language; Data compression; Semantic compression; Artificial intelligence; Telecommunications; Video processing","score_opus":0.008293689010632505,"score_gpt":0.23601764425665225,"score_spread":0.22772395524601974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070641109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03636772,0.0014290917,0.951376,0.0007183749,0.00024587757,0.00018499729,0.00024817305,0.0020435927,0.0073861154],"genre_scores_gemma":[0.4522831,0.0021600549,0.5249498,0.0006779355,0.0008545179,0.00033329433,0.00079116184,0.00041298347,0.017537147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991246,0.000111081536,0.000052536598,0.00016200262,0.0004802328,0.00006962611],"domain_scores_gemma":[0.9969445,0.0011551006,0.00027366192,0.001138779,0.00040648706,0.000081444305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005862818,0.00054771523,0.0005777635,0.0013789429,0.0006375411,0.0010723926,0.0014215432,0.00080153573,0.0041874205],"category_scores_gemma":[0.004413724,0.000223176,0.00033690527,0.0015409023,0.0010184704,0.0028221055,0.0017905573,0.0010095946,0.0020387608],"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":[0.0004215559,0.00016186442,0.0008267781,0.00048509173,0.000044063952,0.0005333702,0.00036621344,0.01865732,0.16220401,0.047698304,0.009539738,0.7590617],"study_design_scores_gemma":[0.00014494068,0.0005299193,0.002193959,0.00017409112,0.00012065818,0.0044075223,0.0003688065,0.49384803,0.34627914,0.07996229,0.07186128,0.00010938736],"about_ca_topic_score_codex":0.00039088918,"about_ca_topic_score_gemma":0.0005486766,"teacher_disagreement_score":0.0041874205,"about_ca_system_score_codex":0.00039441316,"about_ca_system_score_gemma":0.00061581837,"threshold_uncertainty_score":0.014008343},"labels":[],"label_agreement":null},{"id":"W2072234624","doi":"10.1109/isit.2013.6620505","title":"Optimal DNA shotgun sequencing: Noisy reads are as good as noiseless reads","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; DNA sequencing; Computer science; Shotgun; Noise (video); Sequence (biology); DNA; Channel (broadcasting); Algorithm; Computational biology; Biology; Genetics; Artificial intelligence; Computer network; Gene","score_opus":0.02801162172109875,"score_gpt":0.26917315752950816,"score_spread":0.2411615358084094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072234624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17030936,0.004899999,0.8040449,0.0027679028,0.00039459034,0.00008327519,0.00052579644,0.0007490752,0.016225083],"genre_scores_gemma":[0.87325853,0.0030235872,0.11693351,0.002167291,0.0005147257,0.00029077232,0.0005145465,0.00042206477,0.002874818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894001,0.0030820507,0.00055553654,0.002148318,0.0039906045,0.00082345126],"domain_scores_gemma":[0.9456411,0.043876085,0.0029142753,0.0044981837,0.0020359184,0.0010345486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01040226,0.0010651889,0.0023800342,0.001775378,0.001022193,0.004102527,0.0020368728,0.0038258554,0.0023227402],"category_scores_gemma":[0.06387004,0.001154699,0.0008915497,0.0016241396,0.008211701,0.009243697,0.004610148,0.004184717,0.0007716979],"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":[0.0008777285,0.00013675602,0.0026847136,0.00082027435,0.00011841975,0.00038179185,0.00056443794,0.12595485,0.039677456,0.7866334,0.0026793142,0.039471004],"study_design_scores_gemma":[0.00004026271,0.0001661584,0.000783986,0.00010052808,0.000036941572,0.00034583945,0.000102176535,0.1844322,0.02197188,0.78933185,0.0026214293,0.00006674471],"about_ca_topic_score_codex":0.0004754467,"about_ca_topic_score_gemma":0.00027870692,"teacher_disagreement_score":0.01040226,"about_ca_system_score_codex":0.0015672282,"about_ca_system_score_gemma":0.0010515492,"threshold_uncertainty_score":0.05501306},"labels":[],"label_agreement":null},{"id":"W2072721374","doi":"10.1145/2611462.2611486","title":"The amortized complexity of non-blocking binary search trees","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"European Social Fund","keywords":"Optimal binary search tree; Blocking (statistics); Binary tree; Computer science; Amortized analysis; Self-balancing binary search tree; Swap (finance); Binary search tree; Search tree; Tree (set theory); Binary number; Combinatorics; Mathematics; Algorithm; Theoretical computer science; Data structure; Tree structure; Interval tree; Search algorithm; Arithmetic; Operating system","score_opus":0.04037716498594415,"score_gpt":0.28937455789739097,"score_spread":0.24899739291144682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072721374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09860279,0.0023794349,0.8687894,0.0019245037,0.00035010502,0.00038899094,0.00049586577,0.0061728,0.02089616],"genre_scores_gemma":[0.39870477,0.0013062758,0.58257073,0.0006819159,0.00024162844,0.00055509654,0.0011400889,0.0013562331,0.0134433415],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944522,0.0009735788,0.00035673997,0.00051235856,0.0026286426,0.0010764383],"domain_scores_gemma":[0.98717713,0.0070285327,0.0008329612,0.0032198722,0.001360013,0.00038142363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024537025,0.001414622,0.0010103375,0.0011647514,0.0012097395,0.0029090494,0.0041321116,0.0010526212,0.0098067885],"category_scores_gemma":[0.009838056,0.00075313536,0.0013646472,0.0026745484,0.0016485332,0.008788616,0.0026133908,0.0026940552,0.002735478],"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":[0.0025883003,0.0008635038,0.002747289,0.000974999,0.00024878018,0.00022837105,0.00042266297,0.18197934,0.061116286,0.17062984,0.029821884,0.5483787],"study_design_scores_gemma":[0.00023670877,0.00041962092,0.000895995,0.000077821904,0.00018513511,0.00035575664,0.000103532264,0.84740597,0.034844026,0.10636053,0.009036685,0.000078136545],"about_ca_topic_score_codex":0.0040821703,"about_ca_topic_score_gemma":0.0071990583,"teacher_disagreement_score":0.0098067885,"about_ca_system_score_codex":0.0030665086,"about_ca_system_score_gemma":0.0050848373,"threshold_uncertainty_score":0.032806933},"labels":[],"label_agreement":null},{"id":"W2073984053","doi":"10.1016/j.is.2010.11.001","title":"Suffix trees for inputs larger than main memory","year":2010,"lang":"en","type":"article","venue":"Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Generalized suffix tree; Compressed suffix array; Suffix tree; Suffix; Computer science; String (physics); String searching algorithm; Auxiliary memory; Algorithm; Data structure; Tree (set theory); Theoretical computer science; Construct (python library); Mathematics; Combinatorics; Programming language","score_opus":0.010174569598353925,"score_gpt":0.23446209226044487,"score_spread":0.22428752266209095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073984053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15935305,0.0038447385,0.77115124,0.00515351,0.0012820134,0.0004624957,0.00956334,0.0127947945,0.03639489],"genre_scores_gemma":[0.46845323,0.0022291364,0.48164672,0.0009910755,0.0007907649,0.0004993488,0.011930246,0.0025186937,0.030940741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871373,0.00017781646,0.0002081468,0.00025162307,0.00045545545,0.00019325149],"domain_scores_gemma":[0.98950106,0.006014266,0.00030267524,0.0025912146,0.0014490213,0.00014182937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010720933,0.0008068533,0.0011148396,0.0011172822,0.0010452913,0.0026780537,0.0009422123,0.0015908404,0.01594142],"category_scores_gemma":[0.016597692,0.00044638684,0.0006615922,0.002823147,0.00072201644,0.007163558,0.0017340761,0.0018214136,0.005745178],"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":[0.002044137,0.00020904305,0.0028921613,0.0014603811,0.0000771652,0.0013153724,0.00068330456,0.027127126,0.04701823,0.15578468,0.05761214,0.70377624],"study_design_scores_gemma":[0.00013311017,0.00032419563,0.0015410084,0.00040178737,0.000121705154,0.0019901965,0.000492499,0.24572064,0.116207495,0.56463116,0.06837243,0.000063695545],"about_ca_topic_score_codex":0.00042387203,"about_ca_topic_score_gemma":0.0008422121,"teacher_disagreement_score":0.01594142,"about_ca_system_score_codex":0.00079727406,"about_ca_system_score_gemma":0.0011477848,"threshold_uncertainty_score":0.05332935},"labels":[],"label_agreement":null},{"id":"W2074931698","doi":"10.1109/tcomm.2012.082812.110817","title":"LDGM-Based Multiple Description Coding for Finite Alphabet Sources","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Binary number; Mathematics; Algorithm; Coding (social sciences); Rate–distortion theory; Distortion (music); Upper and lower bounds; Rate distortion; Computer science; Statistics; Arithmetic; Bandwidth (computing); Telecommunications; Mathematical analysis","score_opus":0.08652453606989656,"score_gpt":0.2955598895495641,"score_spread":0.2090353534796675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074931698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009599841,0.00026104294,0.988893,0.00011242413,0.00001696564,0.000031460488,0.00004652694,0.00017018948,0.0008684386],"genre_scores_gemma":[0.51319283,0.0004728274,0.4833558,0.00021291035,0.000045340268,0.00015761069,0.00030828733,0.00005436776,0.002200123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902654,0.00036421823,0.00005343946,0.0000878244,0.00040200603,0.00006585319],"domain_scores_gemma":[0.9984174,0.0008977575,0.00015968086,0.0002812744,0.00020552489,0.000038339418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014796618,0.00050909416,0.000671013,0.0006168322,0.00034547184,0.00055340386,0.0013962766,0.0008192678,0.0010605424],"category_scores_gemma":[0.0044848407,0.00020866272,0.00043465185,0.00096669764,0.00067069783,0.0015061242,0.0014935903,0.00105216,0.00035225085],"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":[0.00048900873,0.000074823685,0.00057219184,0.0003543457,0.0000550414,0.00032200408,0.00034829444,0.5191197,0.03085059,0.16123362,0.0019193867,0.28466094],"study_design_scores_gemma":[0.000031420695,0.00007223387,0.00006380225,0.00001885266,0.000009189227,0.00013866212,0.000012146899,0.9691872,0.008866386,0.020158492,0.0014202467,0.00002131831],"about_ca_topic_score_codex":0.001412795,"about_ca_topic_score_gemma":0.0011608801,"teacher_disagreement_score":0.0014796618,"about_ca_system_score_codex":0.00087377225,"about_ca_system_score_gemma":0.00096777175,"threshold_uncertainty_score":0.007825255},"labels":[],"label_agreement":null},{"id":"W2075849239","doi":"10.1109/ccece.2008.4564782","title":"Side effect machines for sequence classification","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Randomness; Computer science; Finite-state machine; Cluster analysis; Feature (linguistics); Artificial intelligence; State (computer science); Algorithm; Population; Bounded function; Set (abstract data type); Sequence (biology); Machine learning; Mathematics","score_opus":0.033712463685797965,"score_gpt":0.2315977494858657,"score_spread":0.19788528580006773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075849239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032609801,0.0014141584,0.98718876,0.00031851674,0.00022527427,0.00012108281,0.0003627017,0.0028391879,0.0042693834],"genre_scores_gemma":[0.16420297,0.0024417427,0.81702435,0.00044739613,0.0006724213,0.0007577205,0.002060409,0.00052068953,0.01187232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984504,0.00046701438,0.00011854051,0.00030742466,0.00057789305,0.00007874234],"domain_scores_gemma":[0.99683553,0.0017025347,0.00018978084,0.0007204783,0.0004955984,0.00005610879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014620954,0.0010000732,0.0011774887,0.0016327766,0.0006799472,0.0015120403,0.001459754,0.0013418436,0.009614128],"category_scores_gemma":[0.007489575,0.0004164683,0.0009689581,0.0020566883,0.00092231674,0.002453985,0.0011358996,0.0029665725,0.0055934433],"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":[0.00021897796,0.00011910077,0.001291553,0.00038440683,0.00007496842,0.00022080069,0.00014027546,0.12582108,0.008458177,0.15881044,0.018908959,0.6855513],"study_design_scores_gemma":[0.000017025734,0.00008168792,0.00046848107,0.000066387685,0.000015785083,0.00023948494,0.000024013365,0.78537244,0.00516497,0.18231381,0.026203591,0.000032310585],"about_ca_topic_score_codex":0.0009728511,"about_ca_topic_score_gemma":0.00094680453,"teacher_disagreement_score":0.009614128,"about_ca_system_score_codex":0.0006955028,"about_ca_system_score_gemma":0.00068219757,"threshold_uncertainty_score":0.032162488},"labels":[],"label_agreement":null},{"id":"W2076501806","doi":"10.1016/j.tcs.2007.01.011","title":"Equivalence of simple functions","year":2007,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Terminal and nonterminal symbols; Mathematics; Simple (philosophy); Equivalence (formal languages); Alphabet; Combinatorics; Deterministic pushdown automaton; Discrete mathematics; Function (biology); Rule-based machine translation; Automaton; Computer science; Automata theory; Theoretical computer science","score_opus":0.012277130162784426,"score_gpt":0.27347997903692145,"score_spread":0.26120284887413703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076501806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29349616,0.0023744474,0.4221476,0.00297981,0.0012449428,0.00015610339,0.0007116026,0.00080207945,0.27608722],"genre_scores_gemma":[0.90984863,0.0012662323,0.038662937,0.0011662609,0.0010558962,0.00017729616,0.0009969319,0.0003705968,0.046455186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977245,0.0004654938,0.0001508002,0.0005498231,0.0008043679,0.0003049867],"domain_scores_gemma":[0.9963529,0.0017978487,0.0002610764,0.0005588022,0.00069223996,0.0003371306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013030544,0.00081228185,0.0012004342,0.0030797382,0.001702853,0.0036063897,0.0010982895,0.0014487506,0.0111766355],"category_scores_gemma":[0.0058746655,0.0005763708,0.0014869184,0.0020023326,0.0033892372,0.008683658,0.00360356,0.004106913,0.0016410601],"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":[0.000033971493,0.000022509508,0.00011236297,0.000018784669,0.0000065208224,0.00003557314,0.00016808475,0.00019887346,0.00047788615,0.9897001,0.000919095,0.0083061],"study_design_scores_gemma":[0.000010356566,0.000015190014,0.00016409534,0.000006138163,0.0000064982837,0.000062893945,0.000029613722,0.0011511862,0.00039308696,0.9947194,0.0034350555,0.0000065836925],"about_ca_topic_score_codex":0.00052205287,"about_ca_topic_score_gemma":0.00035423433,"teacher_disagreement_score":0.0111766355,"about_ca_system_score_codex":0.0013185367,"about_ca_system_score_gemma":0.0005784384,"threshold_uncertainty_score":0.037389576},"labels":[],"label_agreement":null},{"id":"W2076953942","doi":"10.1142/s0129054112400199","title":"CROCHEMORE'S REPETITIONS ALGORITHM REVISITED: COMPUTING RUNS","year":2012,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Algorithm; Computer science; Suffix; Time complexity; Extension (predicate logic); Suffix array; Factorization; Suffix tree; Parallel algorithm; Compressed suffix array; Running time; Mathematics; Data structure","score_opus":0.015845256807878592,"score_gpt":0.31258860627660084,"score_spread":0.2967433494687223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076953942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01613957,0.0007172017,0.97231513,0.00042046348,0.00013963651,0.00013651779,0.00020863657,0.0031805395,0.0067423396],"genre_scores_gemma":[0.07376803,0.0004591353,0.9179328,0.00026958322,0.00016689023,0.00017823988,0.0004482177,0.000727881,0.0060491846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959734,0.0008593703,0.00038938705,0.0011090167,0.0013087795,0.00035997207],"domain_scores_gemma":[0.99325424,0.0023848591,0.0003580024,0.002545432,0.0013031542,0.00015422144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028430016,0.0014197134,0.0015779187,0.0025052119,0.0012031411,0.0028043932,0.0037798083,0.0017778202,0.004802874],"category_scores_gemma":[0.012725529,0.00085821666,0.0016662143,0.0038515178,0.0025446087,0.0075377896,0.0022756022,0.0028213393,0.0024217153],"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":[0.00091240247,0.000114166694,0.0026514153,0.00039969047,0.00014092932,0.00023390558,0.0005105955,0.0783617,0.017007438,0.23226206,0.015219309,0.65218633],"study_design_scores_gemma":[0.00020514915,0.0004514405,0.0017310178,0.0002627651,0.00012171469,0.0010988401,0.00024034372,0.6118893,0.055999443,0.25483522,0.0729499,0.00021487023],"about_ca_topic_score_codex":0.0047767046,"about_ca_topic_score_gemma":0.006581449,"teacher_disagreement_score":0.004802874,"about_ca_system_score_codex":0.0015778225,"about_ca_system_score_gemma":0.0027589025,"threshold_uncertainty_score":0.016067266},"labels":[],"label_agreement":null},{"id":"W2077167828","doi":"10.1016/j.disopt.2010.10.003","title":"Charge and reduce: A fixed-parameter algorithm for String-to-String Correction","year":2010,"lang":"en","type":"article","venue":"Discrete Optimization","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"String (physics); String searching algorithm; String metric; Algorithm; Boyer–Moore string search algorithm; Mathematics; Approximate string matching; Character (mathematics); Commentz-Walter algorithm; Computer science; Discrete mathematics; Pattern matching; Artificial intelligence","score_opus":0.010305201646056453,"score_gpt":0.26270929347325445,"score_spread":0.252404091827198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077167828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036516837,0.000253385,0.98564076,0.0002176069,0.0002139123,0.000090546186,0.00017500672,0.0075968215,0.002160394],"genre_scores_gemma":[0.05715771,0.00017904575,0.93273777,0.00019769117,0.00013703726,0.00019633576,0.00045169692,0.001889155,0.0070536337],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986822,0.00024137483,0.00007593501,0.00022897609,0.0006630131,0.00010843455],"domain_scores_gemma":[0.9981231,0.0006049723,0.00007053803,0.0007731775,0.000357553,0.00007058297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009993503,0.0016513144,0.0016852643,0.0021240928,0.001059367,0.0018809858,0.0032736592,0.001949469,0.016356232],"category_scores_gemma":[0.0061242613,0.0006615269,0.0010576788,0.0026007832,0.0013147533,0.0022803685,0.003122378,0.0025034144,0.0068126502],"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":[0.0006474525,0.00013764683,0.00038479333,0.00016541455,0.000099473924,0.00012574022,0.00010707603,0.05464084,0.009656232,0.03617456,0.03353797,0.8643229],"study_design_scores_gemma":[0.00024215438,0.0001546705,0.0004014804,0.00004157798,0.00006969033,0.00034702037,0.00007683019,0.8379079,0.036637962,0.09617268,0.027842477,0.000105597086],"about_ca_topic_score_codex":0.003499331,"about_ca_topic_score_gemma":0.005146152,"teacher_disagreement_score":0.016356232,"about_ca_system_score_codex":0.0009709098,"about_ca_system_score_gemma":0.0018517605,"threshold_uncertainty_score":0.054717064},"labels":[],"label_agreement":null},{"id":"W2077484872","doi":"10.1016/j.tcs.2004.03.057","title":"Longest increasing subsequences in sliding windows","year":2004,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"University of Waterloo","keywords":"Subsequence; Sliding window protocol; Longest increasing subsequence; Sequence (biology); Generalization; Longest common subsequence problem; Algorithm; Combinatorics; Mathematics; Window (computing); Computer science; Mathematical analysis","score_opus":0.012254478362827302,"score_gpt":0.25266471317457145,"score_spread":0.24041023481174414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077484872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19397455,0.0025094314,0.7978244,0.0002242531,0.00022019958,0.00008542548,0.00035825974,0.0007411529,0.0040623196],"genre_scores_gemma":[0.68719757,0.0018393224,0.30061257,0.00012255924,0.00027931473,0.00019060058,0.0012576017,0.00027697594,0.008223586],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912995,0.00014805536,0.00012987028,0.00020335027,0.00030578178,0.00008310469],"domain_scores_gemma":[0.99677366,0.0018696474,0.00040439318,0.00042929218,0.00037912623,0.00014387416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093640195,0.00046719596,0.00074230024,0.0022066284,0.00065664185,0.0011165262,0.0008297624,0.00061478827,0.0030195813],"category_scores_gemma":[0.0073741805,0.00048541924,0.0004939646,0.0033045402,0.00074039167,0.0023863045,0.0009485391,0.00089149916,0.0006634741],"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":[0.0013288689,0.00020596838,0.007072339,0.0005476286,0.00012762695,0.0015589877,0.0009219311,0.088193074,0.048397854,0.35886997,0.004483457,0.4882922],"study_design_scores_gemma":[0.000069573296,0.00030899845,0.0037517918,0.00012461873,0.00011243879,0.0011743535,0.0002616958,0.593795,0.019882489,0.3655175,0.014956253,0.00004528844],"about_ca_topic_score_codex":0.0008252803,"about_ca_topic_score_gemma":0.00081775663,"teacher_disagreement_score":0.0030195813,"about_ca_system_score_codex":0.0004413941,"about_ca_system_score_gemma":0.00052075,"threshold_uncertainty_score":0.010101497},"labels":[],"label_agreement":null},{"id":"W2077513533","doi":"10.3390/a1020043","title":"A PTAS For The k-Consensus Structures Problem Under Squared Euclidean Distance","year":2008,"lang":"en","type":"article","venue":"Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Mathematics; Euclidean distance; Fragment (logic); Sequence (biology); Euclidean space; Simple (philosophy); Euclidean geometry; Polynomial; Translation (biology); Square (algebra); Set (abstract data type); Space (punctuation); Discrete mathematics; Algorithm; Computer science; Geometry; Mathematical analysis","score_opus":0.03394619564574629,"score_gpt":0.2649064998975932,"score_spread":0.23096030425184688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077513533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009582908,0.0005130149,0.9835864,0.0009363729,0.00013100175,0.00021906114,0.00036908354,0.001473039,0.0031891102],"genre_scores_gemma":[0.15955654,0.0007470224,0.82960755,0.00052782416,0.00032932332,0.0009204955,0.0019219329,0.00039818438,0.0059911157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653256,0.0009683417,0.00028232404,0.0008921956,0.0010492592,0.00027532672],"domain_scores_gemma":[0.99336183,0.0037997658,0.0005482216,0.001339373,0.0006763696,0.00027432878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002812657,0.0017549595,0.0027671906,0.0011929526,0.0011698401,0.0022317201,0.0039880048,0.0032542478,0.009837071],"category_scores_gemma":[0.017036147,0.00072351354,0.0015338659,0.0040411684,0.0013672782,0.0071002427,0.0028940043,0.003719941,0.0037059656],"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":[0.0009702731,0.0004573317,0.0011582113,0.00073275965,0.00015955754,0.0002514286,0.000354396,0.5033935,0.005156176,0.10844808,0.030336577,0.3485818],"study_design_scores_gemma":[0.00013398415,0.00013572095,0.00015777619,0.000022419867,0.000022795808,0.00019668663,0.000075167045,0.9116369,0.0012371087,0.08295157,0.003411681,0.000018243343],"about_ca_topic_score_codex":0.0025739265,"about_ca_topic_score_gemma":0.0024509672,"teacher_disagreement_score":0.009837071,"about_ca_system_score_codex":0.0018926564,"about_ca_system_score_gemma":0.0026587965,"threshold_uncertainty_score":0.03290826},"labels":[],"label_agreement":null},{"id":"W2077583313","doi":"10.1006/jagm.2000.1108","title":"Fast Algorithms to Generate Necklaces, Unlabeled Necklaces, and Irreducible Polynomials over GF(2)","year":2000,"lang":"en","type":"article","venue":"Journal of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics; Combinatorics; Necklace; Alphabet; Permutation (music); Algorithm; Discrete mathematics","score_opus":0.011280661338109824,"score_gpt":0.25752807666333566,"score_spread":0.24624741532522584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077583313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06912894,0.00054387783,0.9179324,0.0004990304,0.00014833611,0.00043452444,0.0004328353,0.0039987457,0.0068812296],"genre_scores_gemma":[0.2607482,0.00036181248,0.72936386,0.00021135171,0.00009238197,0.00042858155,0.001465799,0.0003796687,0.0069483006],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895287,0.00020142712,0.00007215347,0.00015391948,0.000422865,0.00019667797],"domain_scores_gemma":[0.99714017,0.001295128,0.00026848962,0.0006914715,0.00048481018,0.00011981003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011525265,0.0010980295,0.0007375249,0.0014710888,0.0011171263,0.0010397963,0.0011572107,0.00097260467,0.007803902],"category_scores_gemma":[0.005723136,0.00048694955,0.00075980526,0.0018227849,0.0008536145,0.002204729,0.0025350873,0.0014753824,0.0020038767],"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":[0.0012422113,0.00038259357,0.0015419035,0.0004735614,0.000080444224,0.00029626364,0.00063278835,0.044630207,0.025918344,0.11784107,0.021719508,0.7852412],"study_design_scores_gemma":[0.0009496759,0.00072812574,0.00088355946,0.0001677561,0.00013784877,0.00079162687,0.0004927582,0.6070118,0.093972534,0.27161002,0.02313145,0.00012287515],"about_ca_topic_score_codex":0.001452986,"about_ca_topic_score_gemma":0.0049145077,"teacher_disagreement_score":0.007803902,"about_ca_system_score_codex":0.0010048002,"about_ca_system_score_gemma":0.0018231232,"threshold_uncertainty_score":0.026106596},"labels":[],"label_agreement":null},{"id":"W2077590131","doi":"10.1142/s0219024902001493","title":"PORTFOLIO OPTIMIZATION, HIDDEN MARKOV MODELS, AND TECHNICAL ANALYSIS OF P&amp;F-CHARTS","year":2002,"lang":"en","type":"article","venue":"International Journal of Theoretical and Applied Finance","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"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 Calgary","funders":"","keywords":"Portfolio; Portfolio optimization; Hidden Markov model; Computer science; Markov chain; Mathematical optimization; Black–Litterman model; Stock price; Markov model; Replicating portfolio; Econometrics; Mathematics; Economics; Series (stratigraphy); Artificial intelligence; Financial economics; Machine learning","score_opus":0.01065136928420984,"score_gpt":0.23476499794149136,"score_spread":0.22411362865728152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077590131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017136155,0.0019009347,0.9754489,0.00063347694,0.00006232675,0.000016861017,0.00007153754,0.0001386831,0.004591076],"genre_scores_gemma":[0.7848918,0.0049430816,0.1998577,0.00023174893,0.00044457937,0.00014064557,0.0003357177,0.00018733123,0.008967356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903405,0.00039359805,0.00004450664,0.00014302626,0.00031163992,0.00007319411],"domain_scores_gemma":[0.99673754,0.0021059196,0.0004948418,0.00023026219,0.00031648044,0.00011483388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025906072,0.0008267904,0.00090931717,0.0015960498,0.0005979711,0.0018676842,0.0010227398,0.0012816399,0.0026079759],"category_scores_gemma":[0.012544093,0.00041927263,0.00074646744,0.0013835239,0.0018051448,0.0032146515,0.0012414409,0.0016695784,0.00036444011],"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":[0.000025476627,0.000023478944,0.0012822041,0.00007014359,0.00003354849,0.00012428868,0.000060237733,0.34992123,0.0005910264,0.6153518,0.0012447997,0.03127179],"study_design_scores_gemma":[0.000003396639,0.000011810308,0.00027058402,0.000015010691,0.0000063009206,0.000033703076,0.000007882247,0.7301176,0.0003076851,0.26826796,0.00094669,0.000011329282],"about_ca_topic_score_codex":0.0018752795,"about_ca_topic_score_gemma":0.0009823875,"teacher_disagreement_score":0.0026079759,"about_ca_system_score_codex":0.0011303913,"about_ca_system_score_gemma":0.00079672044,"threshold_uncertainty_score":0.013700604},"labels":[],"label_agreement":null},{"id":"W2077831311","doi":"10.1145/584792.584832","title":"On the efficient evaluation of relaxed queries in biological databases","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Database; Query language; Equivalence (formal languages); Biological database; Domain (mathematical analysis); Fuzzy logic; Relaxation (psychology); Database theory; Theoretical computer science; Data mining; Information retrieval; Database design; Artificial intelligence; Mathematics; Bioinformatics","score_opus":0.17309011031889704,"score_gpt":0.30887036447505734,"score_spread":0.1357802541561603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077831311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083793715,0.0005981213,0.91140765,0.00055504753,0.000050456983,0.00023430766,0.00022369629,0.0015216833,0.0016153096],"genre_scores_gemma":[0.43988407,0.00040484857,0.5558385,0.0003623243,0.00011370756,0.00028617974,0.00100191,0.00030612104,0.0018022395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98640037,0.0048429794,0.0011036338,0.0011646274,0.0057050036,0.00078332983],"domain_scores_gemma":[0.97150975,0.01889181,0.0010722622,0.0050443425,0.0030341123,0.00044771962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009391871,0.0007334282,0.0022036708,0.0017576389,0.0009968327,0.0030914007,0.0031694751,0.00093961257,0.0021193246],"category_scores_gemma":[0.03215774,0.00056249835,0.0009689758,0.002740319,0.0023732088,0.0069057606,0.0038371102,0.0021213323,0.00059563725],"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":[0.0041256817,0.0005907138,0.0032924535,0.00063443463,0.00019337743,0.00067816797,0.0028683704,0.18041833,0.052228693,0.18763663,0.008323356,0.5590098],"study_design_scores_gemma":[0.00014728085,0.0003329176,0.00068812276,0.000044644585,0.00007006526,0.00027646203,0.0004003178,0.89362663,0.024432719,0.074296646,0.0056273635,0.00005687835],"about_ca_topic_score_codex":0.0032675301,"about_ca_topic_score_gemma":0.002020974,"teacher_disagreement_score":0.009391871,"about_ca_system_score_codex":0.0011758114,"about_ca_system_score_gemma":0.0018110237,"threshold_uncertainty_score":0.049669564},"labels":[],"label_agreement":null},{"id":"W2078605119","doi":"10.1145/1113439.1113442","title":"The nearest polynomial with a given zero, revisited","year":2005,"lang":"en","type":"article","venue":"ACM SIGSAM Bulletin","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"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":"Monic polynomial; Zero (linguistics); Polynomial; Generalization; Mathematics; Matrix polynomial; Minor (academic); Reciprocal polynomial; Stable polynomial; Square-free polynomial; Combinatorics; Discrete mathematics; Mathematical analysis","score_opus":0.00958647146113312,"score_gpt":0.22279406614126593,"score_spread":0.2132075946801328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078605119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10900974,0.0025988466,0.8335355,0.0064215763,0.0008745303,0.0000822474,0.00028335562,0.0012958172,0.045898397],"genre_scores_gemma":[0.71702707,0.0013177465,0.25727084,0.0011998618,0.00049993524,0.000057115365,0.0003915949,0.00045705974,0.021778798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969668,0.0006203974,0.00018346011,0.0007173732,0.0010723472,0.00043958495],"domain_scores_gemma":[0.9965834,0.0014373219,0.00023144111,0.0009982388,0.0005804803,0.00016912291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002383432,0.0004423245,0.0011178225,0.0013741094,0.0021017513,0.0022295318,0.0018095701,0.0013559893,0.00732927],"category_scores_gemma":[0.016855847,0.00039132318,0.00059979194,0.0019262166,0.0042304886,0.007448849,0.0036892882,0.003620271,0.0019797224],"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":[0.0003759258,0.00007223085,0.0015577212,0.00026179707,0.000016475904,0.00024238262,0.00062916527,0.009526841,0.0038057517,0.8212648,0.008170921,0.15407601],"study_design_scores_gemma":[0.00008106519,0.00026630872,0.0007295391,0.00015228454,0.000046290228,0.00095328176,0.00069974735,0.07153144,0.015486615,0.8666187,0.043355256,0.00007956779],"about_ca_topic_score_codex":0.0028835426,"about_ca_topic_score_gemma":0.0039439173,"teacher_disagreement_score":0.00732927,"about_ca_system_score_codex":0.0020365072,"about_ca_system_score_gemma":0.0018455714,"threshold_uncertainty_score":0.024518788},"labels":[],"label_agreement":null},{"id":"W2078778545","doi":"10.1007/s00453-014-9894-4","title":"A Framework for Succinct Labeled Ordinal Trees over Large Alphabets","year":2014,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"","keywords":"Theory of computation; Computer science; Combinatorics; Ordinal optimization; Mathematics; Discrete mathematics; Ordinal data; Theoretical computer science; Algorithm; Statistics","score_opus":0.01274002575439995,"score_gpt":0.2812125145245694,"score_spread":0.26847248877016944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078778545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035955107,0.0004210049,0.99139905,0.00056093495,0.00010068478,0.00006953417,0.0004807942,0.0011849575,0.0021875475],"genre_scores_gemma":[0.099382214,0.0010022359,0.89007396,0.00059612066,0.00036683396,0.00043372755,0.0018882914,0.00065593544,0.0056006736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952028,0.0012699037,0.00048925035,0.00078515976,0.0018422191,0.00041064032],"domain_scores_gemma":[0.98792434,0.0061324,0.00059166,0.0037080771,0.0012452804,0.00039820594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037239918,0.0010289478,0.0017300121,0.003548811,0.0020649668,0.005336299,0.0045939772,0.002338045,0.009141773],"category_scores_gemma":[0.01963612,0.001130983,0.001830744,0.007012367,0.0028860483,0.013849971,0.0068907146,0.005758717,0.002813636],"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":[0.00016200551,0.00011153851,0.0003448703,0.00022646693,0.000030547533,0.0001612833,0.00040378753,0.04802998,0.002757809,0.8126411,0.009315077,0.12581551],"study_design_scores_gemma":[0.000031039806,0.000041678617,0.00006190187,0.00007826518,0.000022314423,0.0001444126,0.00009456712,0.15975358,0.0021528355,0.82440615,0.013180871,0.000032412536],"about_ca_topic_score_codex":0.0023411813,"about_ca_topic_score_gemma":0.0046356022,"teacher_disagreement_score":0.009141773,"about_ca_system_score_codex":0.002604447,"about_ca_system_score_gemma":0.003137479,"threshold_uncertainty_score":0.03058225},"labels":[],"label_agreement":null},{"id":"W2079307253","doi":"10.1016/s1570-8667(03)00080-7","title":"The longest common subsequence problem for arc-annotated sequences","year":2004,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Alberta","funders":"","keywords":"Longest common subsequence problem; Sequence (biology); Subsequence; Arc (geometry); Longest increasing subsequence; Computer science; Matching (statistics); Combinatorics; Algorithm; Similarity (geometry); Artificial intelligence; Mathematics; Biology; Genetics; Statistics","score_opus":0.018082766195424867,"score_gpt":0.2840613365543329,"score_spread":0.26597857035890804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079307253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06659449,0.0022534437,0.92351866,0.0014585357,0.0002781671,0.00022242779,0.0025031746,0.0012634576,0.0019076301],"genre_scores_gemma":[0.33759683,0.0025810387,0.6363041,0.00033777382,0.00072773645,0.00055339275,0.015094445,0.00073145964,0.0060732765],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956802,0.0009231013,0.0006586634,0.0012540147,0.0011875972,0.00029632222],"domain_scores_gemma":[0.9801831,0.013623043,0.0016009595,0.0022129393,0.0019090099,0.00047089177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003806481,0.0012229314,0.0031662032,0.0040791724,0.0016726722,0.0028477018,0.0032092885,0.0036366745,0.003753056],"category_scores_gemma":[0.023717737,0.001110935,0.0014585026,0.008082368,0.0016642252,0.007633507,0.0020696477,0.0028834655,0.0014856834],"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":[0.002019015,0.0006524173,0.004543444,0.0016820681,0.00035059013,0.0013731598,0.00073479104,0.4003227,0.011084102,0.06610705,0.018346306,0.49278435],"study_design_scores_gemma":[0.00010209754,0.00017032857,0.00062637444,0.00008139972,0.0000595795,0.00041745015,0.0003404545,0.849076,0.004620054,0.1408074,0.0036610968,0.00003782267],"about_ca_topic_score_codex":0.0030494612,"about_ca_topic_score_gemma":0.0024928497,"teacher_disagreement_score":0.0040791724,"about_ca_system_score_codex":0.0012555711,"about_ca_system_score_gemma":0.002932861,"threshold_uncertainty_score":0.020130873},"labels":[],"label_agreement":null},{"id":"W2079685570","doi":"10.1016/j.ipl.2005.11.022","title":"A new tree inclusion algorithm","year":2006,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Combinatorics; Tree (set theory); Mathematics; Matching (statistics); Algorithm; Node (physics); Space (punctuation); Time complexity; Discrete mathematics; Computer science; Physics; Statistics","score_opus":0.004709152392638082,"score_gpt":0.20485827849132324,"score_spread":0.20014912609868515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079685570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005569203,0.00053319556,0.983631,0.00032827773,0.00036982755,0.00013068265,0.0001924308,0.00187029,0.007375044],"genre_scores_gemma":[0.042194925,0.0004693333,0.94088405,0.00036027955,0.00035379123,0.00022308057,0.0007737622,0.0008208198,0.013919897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808216,0.00031841,0.00014773487,0.00034012008,0.0009439909,0.00016753026],"domain_scores_gemma":[0.997097,0.00072137796,0.0000940524,0.00089290785,0.0010205199,0.00017410038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012411465,0.00090670784,0.0014990031,0.0025982896,0.0015745327,0.0027783753,0.0025442275,0.0017059378,0.012244412],"category_scores_gemma":[0.0052106306,0.0005628459,0.0010708618,0.0036044095,0.0008005397,0.004965901,0.0040406347,0.0022852677,0.007588717],"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":[0.0003197582,0.00024554244,0.00037623258,0.00019250545,0.000055331177,0.00012819984,0.00014727551,0.012203475,0.012042182,0.08790998,0.023073802,0.86330575],"study_design_scores_gemma":[0.00016237498,0.0003190773,0.000520517,0.0001217424,0.00014045899,0.0009247195,0.00009706808,0.64612716,0.033988316,0.19311865,0.12439629,0.00008361441],"about_ca_topic_score_codex":0.0010735047,"about_ca_topic_score_gemma":0.0017695911,"teacher_disagreement_score":0.012244412,"about_ca_system_score_codex":0.00068583805,"about_ca_system_score_gemma":0.001757218,"threshold_uncertainty_score":0.040961623},"labels":[],"label_agreement":null},{"id":"W2079850117","doi":"10.1007/s00453-011-9528-z","title":"Succinct and I/O Efficient Data Structures for Traversal in Trees","year":2011,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Carleton University","funders":"","keywords":"Tree traversal; Combinatorics; Tree (set theory); Path (computing); Constant (computer programming); Mathematics; Binary tree; Binary logarithm; Data structure; Theory of computation; Discrete mathematics; Binary number; Node (physics); Physics; Algorithm; Computer science; Arithmetic","score_opus":0.05772345621798793,"score_gpt":0.2688078761154939,"score_spread":0.21108441989750595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079850117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07749564,0.0017405002,0.90417135,0.0016462837,0.00028303746,0.0002179492,0.0021299173,0.0034579353,0.008857314],"genre_scores_gemma":[0.38491523,0.0013658566,0.59293467,0.0006854663,0.0002545057,0.00049711205,0.0060226563,0.0013859997,0.011938463],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980122,0.00030228827,0.00027331227,0.00022378523,0.00095719687,0.00023122122],"domain_scores_gemma":[0.9932388,0.0025541973,0.00056945556,0.0026349921,0.0007966627,0.00020593221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011532722,0.00094630447,0.0009284649,0.0018493896,0.0010504118,0.0032034575,0.0020610502,0.0012756955,0.005980968],"category_scores_gemma":[0.010420894,0.00080565317,0.00097380765,0.0051070163,0.0017054887,0.00724615,0.002793347,0.00272424,0.0019473687],"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":[0.0013393363,0.00057188544,0.00377946,0.00089932815,0.000082714505,0.00033124856,0.0011244346,0.086146764,0.025939897,0.30287927,0.042374432,0.53453124],"study_design_scores_gemma":[0.00026790166,0.00032226995,0.001042493,0.00028504946,0.0001297249,0.00048496822,0.0005020568,0.3631288,0.04252267,0.56644684,0.024770582,0.00009665485],"about_ca_topic_score_codex":0.0016829545,"about_ca_topic_score_gemma":0.003657682,"teacher_disagreement_score":0.005980968,"about_ca_system_score_codex":0.0015802446,"about_ca_system_score_gemma":0.0021097981,"threshold_uncertainty_score":0.020008326},"labels":[],"label_agreement":null},{"id":"W2080616298","doi":"10.1016/j.tcs.2012.02.001","title":"A linear partitioning algorithm for Hybrid Lyndons using<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>V</mml:mi></mml:math>-order","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Lexicographical order; Factorization; Algorithm; Concatenation (mathematics); Order (exchange); String (physics); Computer science; Generalization; Mathematics; Edit distance; Discrete mathematics; Combinatorics","score_opus":0.019122432015830432,"score_gpt":0.26413282971905006,"score_spread":0.2450103977032196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080616298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01336958,0.0001783612,0.9796243,0.000111655725,0.000051244868,0.0000904182,0.000197702,0.0023811883,0.0039955056],"genre_scores_gemma":[0.07649239,0.00013156145,0.91262865,0.00009710396,0.00003974913,0.00021142972,0.0012861064,0.00076874037,0.008344225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999453,0.00008494663,0.000059984526,0.0001267223,0.00020613067,0.00006921825],"domain_scores_gemma":[0.99916446,0.00033147453,0.000046697256,0.0001743742,0.00022401646,0.000059019716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072493457,0.0006876188,0.00077593833,0.0014894699,0.0010315434,0.0016565701,0.0015729376,0.0007984632,0.014729707],"category_scores_gemma":[0.0025699853,0.00056184625,0.0007884616,0.0014682092,0.0007051522,0.0017268634,0.0021268437,0.0012770297,0.004837883],"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":[0.0005882401,0.00015296433,0.0008211922,0.0002758841,0.000055615463,0.00014338212,0.0004174572,0.04862024,0.026272807,0.054160435,0.018581947,0.8499098],"study_design_scores_gemma":[0.000236754,0.00031596114,0.0006520177,0.00009231533,0.0000478013,0.00034651227,0.0004192917,0.86434656,0.031800743,0.070200786,0.031457677,0.000083596235],"about_ca_topic_score_codex":0.0055248723,"about_ca_topic_score_gemma":0.009449497,"teacher_disagreement_score":0.014729707,"about_ca_system_score_codex":0.0009855039,"about_ca_system_score_gemma":0.0012909496,"threshold_uncertainty_score":0.049275756},"labels":[],"label_agreement":null},{"id":"W2082347500","doi":"10.1098/rsta.2013.0138","title":"Large-scale detection of repetitions","year":2014,"lang":"en","type":"article","venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"String (physics); Prefix; Computation; Suffix tree; Factorization; Suffix; Generalized suffix tree; Mathematics; Fraction (chemistry); Combinatorics; Trie; Computer science; Algorithm; Data structure","score_opus":0.010440853142862307,"score_gpt":0.21772975214751034,"score_spread":0.20728889900464803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082347500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4156517,0.0016119186,0.5631048,0.0012927073,0.00033130267,0.0001214491,0.0014409508,0.0056985435,0.010746674],"genre_scores_gemma":[0.8253076,0.00038422568,0.16847062,0.00026318117,0.00022144416,0.00012443778,0.0016007298,0.00037894852,0.003248771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972434,0.00047759924,0.00016673628,0.0009277085,0.00094091654,0.00024361673],"domain_scores_gemma":[0.988704,0.0059430613,0.0011899206,0.0027451573,0.0011057799,0.00031197717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012651634,0.0005779116,0.0012314422,0.0020560229,0.00084041554,0.0017954534,0.001618669,0.001272742,0.0024134654],"category_scores_gemma":[0.018989606,0.00062750315,0.0006279519,0.0021689753,0.0012484334,0.003900656,0.00222978,0.0013405642,0.0016317748],"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":[0.0022217378,0.00028226917,0.037288025,0.00073622214,0.0002749626,0.002689698,0.0017144878,0.08277328,0.20846498,0.12559636,0.021479527,0.5164785],"study_design_scores_gemma":[0.00006761852,0.0002687004,0.009824918,0.00010886565,0.00006160261,0.0022280656,0.00047611774,0.6943821,0.10026018,0.17738156,0.014830356,0.0001099188],"about_ca_topic_score_codex":0.0005301188,"about_ca_topic_score_gemma":0.0006160922,"teacher_disagreement_score":0.0024134654,"about_ca_system_score_codex":0.0006258833,"about_ca_system_score_gemma":0.0006412168,"threshold_uncertainty_score":0.008073807},"labels":[],"label_agreement":null},{"id":"W2082831697","doi":"10.1109/tit.2011.2145930","title":"Rate-Constrained Simulation and Source Coding i.i.d. Sources","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Tsinghua University; University of Kansas; John Simon Guggenheim Memorial Foundation; Simons Foundation","keywords":"Source code; Variable-length code; Computer science; Coding (social sciences); Asymptotically optimal algorithm; Algorithm; Shannon–Fano coding; Alphabet; Block code; Theoretical computer science; Code rate; Decoding methods; Mathematics; Statistics","score_opus":0.01999778273778776,"score_gpt":0.2306318751298479,"score_spread":0.21063409239206013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082831697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006355675,0.00014882704,0.99043614,0.00015765238,0.000023017248,0.00003529703,0.000075498014,0.00013058876,0.0026372964],"genre_scores_gemma":[0.7651293,0.0010025741,0.2242288,0.00028271106,0.000087293534,0.0004532309,0.00045329746,0.00017017957,0.008192617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982564,0.00078448426,0.00008705866,0.0002374686,0.00049593486,0.00013870468],"domain_scores_gemma":[0.98933524,0.008244451,0.00082836085,0.00072556356,0.00073978334,0.00012653715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021045932,0.0013062218,0.0012624898,0.00077223126,0.0004120297,0.0014058,0.0011531322,0.001690899,0.0030507979],"category_scores_gemma":[0.01546303,0.00075177837,0.0007532825,0.0009516979,0.0020184885,0.0019251818,0.0016657615,0.0017604588,0.00076558435],"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":[0.00013893934,0.000018728713,0.00023512417,0.000078719786,0.00002915417,0.00009926612,0.00005668281,0.7018458,0.0038894624,0.28257126,0.00050252903,0.010534314],"study_design_scores_gemma":[0.000014271878,0.000023325045,0.000040629744,0.000014850203,0.000005763523,0.0000449317,0.0000050422836,0.9580213,0.002236972,0.039166547,0.00041102892,0.00001527299],"about_ca_topic_score_codex":0.0014664459,"about_ca_topic_score_gemma":0.00091723923,"teacher_disagreement_score":0.0030507979,"about_ca_system_score_codex":0.0015314886,"about_ca_system_score_gemma":0.0013444588,"threshold_uncertainty_score":0.011130273},"labels":[],"label_agreement":null},{"id":"W2083073659","doi":"10.1147/rd.492.0465","title":"Custom math functions for molecular dynamics","year":2005,"lang":"en","type":"article","venue":"IBM Journal of Research and Development","topic":"Algorithms and Data Compression","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":"IBM (Canada)","funders":"","keywords":"Compiler; IBM; Fortran; Computer science; Parallel computing; Supercomputer; Folding (DSP implementation); Implementation; Throughput; Point (geometry); Programming language; Computational science; Computer architecture; Operating system; Mathematics; Engineering","score_opus":0.04394402384357644,"score_gpt":0.345994106838011,"score_spread":0.3020500829944346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083073659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056992923,0.0010327508,0.6529572,0.0007588407,0.0008350862,0.0004146371,0.015930163,0.25580475,0.06656727],"genre_scores_gemma":[0.057511445,0.002095536,0.70754987,0.0012853662,0.00028769264,0.0021044782,0.03182788,0.10585585,0.09148187],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923015,0.00009387487,0.00007364684,0.000106504296,0.0003915267,0.000104293125],"domain_scores_gemma":[0.9985569,0.0004004288,0.000107037486,0.0003088796,0.00053933094,0.00008739137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013923005,0.00184324,0.0011267719,0.0014206303,0.0010519631,0.0017016707,0.0035636213,0.0012783415,0.11203611],"category_scores_gemma":[0.004855933,0.0010968476,0.0014250855,0.0018597204,0.00050672627,0.0024572893,0.0019160439,0.0032960137,0.06613291],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006160833,0.00019858265,0.0022262037,0.0015206155,0.00017013746,0.0005278085,0.0005788895,0.022090448,0.020147193,0.121245354,0.5564457,0.27423304],"study_design_scores_gemma":[0.00021451827,0.000060254173,0.0009228775,0.00016781432,0.00004394354,0.0005249454,0.000058332822,0.08732992,0.031153884,0.021367166,0.85802126,0.0001350382],"about_ca_topic_score_codex":0.0027289286,"about_ca_topic_score_gemma":0.0038427026,"teacher_disagreement_score":0.11203611,"about_ca_system_score_codex":0.0014796808,"about_ca_system_score_gemma":0.0016080032,"threshold_uncertainty_score":0.37479812},"labels":[],"label_agreement":null},{"id":"W2083101719","doi":"10.1016/j.comgeo.2013.08.007","title":"Space efficient data structures for dynamic orthogonal range counting","year":2013,"lang":"en","type":"article","venue":"Computational Geometry","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"Canada Research Chairs","keywords":"Range (aeronautics); Space (punctuation); Computer science; Dynamic range; Data structure; Mathematics; Algorithm; Computer vision; Engineering; Aerospace engineering","score_opus":0.021831948257065168,"score_gpt":0.2821673451106919,"score_spread":0.2603353968536267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083101719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031482086,0.0013037326,0.94960594,0.0006396667,0.00023776203,0.00016362243,0.001165023,0.003963865,0.011438233],"genre_scores_gemma":[0.3269632,0.0010729529,0.65660244,0.00047166614,0.00032210635,0.0006615827,0.0036617012,0.00091488025,0.009329509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997191,0.0003884665,0.00032295857,0.0003988134,0.0013410149,0.0003576742],"domain_scores_gemma":[0.9952803,0.001144583,0.00033845496,0.002320561,0.0007830687,0.00013293282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057482,0.00091455836,0.0014359643,0.00283323,0.0013179139,0.0036505992,0.0023477348,0.00085788395,0.008733211],"category_scores_gemma":[0.008308632,0.00056669745,0.00080576533,0.0071049645,0.0013796096,0.0071743075,0.004967142,0.0020955508,0.0028862734],"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":[0.000577987,0.0002676158,0.0011547802,0.00027865602,0.00004768034,0.00011652659,0.00032530705,0.027408792,0.011234527,0.3946849,0.02546993,0.53843325],"study_design_scores_gemma":[0.00013873808,0.00026213977,0.00048247518,0.00014209466,0.00006459449,0.00044805082,0.00033000845,0.27506694,0.030632315,0.65144473,0.040884364,0.0001035129],"about_ca_topic_score_codex":0.0012826396,"about_ca_topic_score_gemma":0.0021049578,"teacher_disagreement_score":0.008733211,"about_ca_system_score_codex":0.0011726527,"about_ca_system_score_gemma":0.0018447338,"threshold_uncertainty_score":0.029215515},"labels":[],"label_agreement":null},{"id":"W2084921767","doi":"10.5555/1109557.1109644","title":"Oblivious string embeddings and edit distance approximations","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Edit distance; Embedding; Combinatorics; String (physics); Distortion (music); Mathematics; Discrete mathematics; Algorithm; Physics; Computer science; Artificial intelligence","score_opus":0.004087049705773005,"score_gpt":0.196324152313122,"score_spread":0.192237102607349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084921767","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033589978,0.0009785546,0.957187,0.000824918,0.00010524738,0.0000638217,0.00035664235,0.0019949002,0.0048988103],"genre_scores_gemma":[0.5571134,0.001066447,0.42874154,0.00044816892,0.00022084411,0.0002993914,0.0011406628,0.00058818544,0.01038142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653876,0.0009089388,0.00025637526,0.0005917633,0.0013806222,0.0003235483],"domain_scores_gemma":[0.99074507,0.0033678997,0.0007645694,0.004547126,0.00041695332,0.00015838385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013437867,0.0010328119,0.0012358656,0.0012197654,0.0006570043,0.0023979112,0.0028845351,0.0020517518,0.004924816],"category_scores_gemma":[0.016034443,0.00069466385,0.0006136529,0.0026684972,0.0017344747,0.011444938,0.0039832536,0.0028777379,0.0017830067],"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":[0.00084038737,0.00028671132,0.0010492157,0.0003262122,0.00010980507,0.00028362856,0.00041843217,0.41985768,0.010304229,0.33318213,0.008140369,0.22520116],"study_design_scores_gemma":[0.000069257265,0.00013603797,0.00019824768,0.000033150518,0.00003303983,0.00029686574,0.00007286033,0.65935045,0.012299535,0.31936124,0.0081111025,0.00003810739],"about_ca_topic_score_codex":0.00092721585,"about_ca_topic_score_gemma":0.0011265884,"teacher_disagreement_score":0.004924816,"about_ca_system_score_codex":0.0016478349,"about_ca_system_score_gemma":0.00096005923,"threshold_uncertainty_score":0.016475081},"labels":[],"label_agreement":null},{"id":"W2084965869","doi":"10.1145/2600428.2609609","title":"Skewed partial bitvectors for list intersection","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Intersection (aeronautics); Ranking (information retrieval); Information retrieval; Identifier; Point (geometry); Space (punctuation); Data mining; Theoretical computer science; Mathematics","score_opus":0.011753117408133628,"score_gpt":0.24282622673560494,"score_spread":0.23107310932747133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084965869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21422464,0.0068669696,0.7365172,0.0013572401,0.00052303466,0.0006629526,0.0040652384,0.021498017,0.014284785],"genre_scores_gemma":[0.38478383,0.0013182454,0.5995132,0.00044710704,0.00016004038,0.00056977855,0.0067326818,0.0009779906,0.005497149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968829,0.0006250258,0.00035925838,0.00035978487,0.0014870382,0.00028602287],"domain_scores_gemma":[0.9912986,0.0032981937,0.0006453403,0.002811006,0.0017241815,0.00022268125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018401553,0.0009435567,0.0016170248,0.0028014572,0.0013825038,0.0033787282,0.002884121,0.0007912295,0.009791834],"category_scores_gemma":[0.012989116,0.0004483177,0.0006727983,0.0079670055,0.0011073078,0.008392048,0.0030242829,0.0012286883,0.0038267784],"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":[0.0016714497,0.00036837094,0.0051903166,0.000549655,0.000114298906,0.00013318722,0.00048502506,0.04375406,0.015599242,0.044832386,0.023973694,0.8633284],"study_design_scores_gemma":[0.00035049146,0.0014359046,0.0023471157,0.00020544771,0.00013000311,0.00072705775,0.0010137886,0.7467411,0.084996745,0.10555441,0.056330975,0.0001669687],"about_ca_topic_score_codex":0.0053178924,"about_ca_topic_score_gemma":0.0061365683,"teacher_disagreement_score":0.009791834,"about_ca_system_score_codex":0.0021210315,"about_ca_system_score_gemma":0.0028897088,"threshold_uncertainty_score":0.032756925},"labels":[],"label_agreement":null},{"id":"W2085662310","doi":"10.1016/s0965-9978(00)00038-7","title":"On multikey sorting","year":2000,"lang":"en","type":"article","venue":"Advances in Engineering Software","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of New Brunswick","funders":"","keywords":"Computer science","score_opus":0.003940293042391474,"score_gpt":0.2237701916555714,"score_spread":0.21982989861317995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085662310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06545855,0.012597116,0.62343025,0.009305529,0.006722456,0.0002882798,0.0022499214,0.0059202425,0.27402765],"genre_scores_gemma":[0.40833476,0.008899898,0.2669453,0.006519895,0.0032198331,0.0004345407,0.00437352,0.0037886132,0.2974836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979401,0.0003049069,0.00016807867,0.0005058049,0.0006606232,0.00042038687],"domain_scores_gemma":[0.9970823,0.0007591096,0.00012458737,0.0013772238,0.00047485722,0.00018197575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001564607,0.0019680096,0.0023094248,0.0046590357,0.0046257996,0.0060288403,0.0024342637,0.002041076,0.03998052],"category_scores_gemma":[0.0049833287,0.0009558402,0.0017009871,0.0097142225,0.0034147857,0.01349655,0.0073516592,0.00416485,0.010879074],"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":[0.00073277694,0.00011940542,0.0006505232,0.00025655,0.00006599471,0.00009190385,0.00023801027,0.007954226,0.0031876308,0.6653758,0.058046483,0.2632807],"study_design_scores_gemma":[0.00003955104,0.00006441975,0.00031986783,0.000102833656,0.000049085513,0.00017874199,0.00011512243,0.013494399,0.0033922796,0.90940046,0.0728049,0.000038294354],"about_ca_topic_score_codex":0.0028322602,"about_ca_topic_score_gemma":0.0043801046,"teacher_disagreement_score":0.03998052,"about_ca_system_score_codex":0.0033919106,"about_ca_system_score_gemma":0.0023566822,"threshold_uncertainty_score":0.13374817},"labels":[],"label_agreement":null},{"id":"W2086340885","doi":"10.1016/j.jda.2011.08.005","title":"On the structure of run-maximal strings","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Property (philosophy); Combinatorics; Cover (algebra); Mathematics; Compression (physics); String searching algorithm; Computer science; Algorithm; Data structure; Discrete mathematics; Physics; Engineering","score_opus":0.02079478762518111,"score_gpt":0.23601376440565444,"score_spread":0.21521897678047333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086340885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4698735,0.0027897854,0.46638954,0.004801463,0.0003315601,0.00010295907,0.0018578493,0.001801921,0.05205147],"genre_scores_gemma":[0.9069439,0.0013488245,0.07326076,0.00068341085,0.00048643426,0.000160461,0.0022369914,0.00077327975,0.014105993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984989,0.00043822406,0.00012521807,0.0003154205,0.00037977356,0.00024235155],"domain_scores_gemma":[0.97733194,0.015968956,0.0018228244,0.002500947,0.0014276532,0.00094763737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019882028,0.00059686013,0.0012594734,0.002791694,0.0020640336,0.0039793015,0.0019946177,0.0016812619,0.00743998],"category_scores_gemma":[0.022361357,0.0007634989,0.0006096677,0.0037517708,0.004130195,0.009139161,0.0035697897,0.003133693,0.0013175161],"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":[0.00049074535,0.00008956812,0.0018156444,0.00014646974,0.000022713224,0.00021032667,0.0007594853,0.018515285,0.002663664,0.9314306,0.004798758,0.03905681],"study_design_scores_gemma":[0.000019872932,0.000043367327,0.00027636037,0.000044591114,0.000011921479,0.00007511368,0.000097343196,0.033090845,0.0010146417,0.96304244,0.0022668852,0.000016626513],"about_ca_topic_score_codex":0.0006821293,"about_ca_topic_score_gemma":0.00085682067,"teacher_disagreement_score":0.00743998,"about_ca_system_score_codex":0.0013042731,"about_ca_system_score_gemma":0.0012122045,"threshold_uncertainty_score":0.024889171},"labels":[],"label_agreement":null},{"id":"W2086354937","doi":"10.1145/1227161.1370601","title":"A graph approach to the threshold all-against-all substring matching problem","year":2008,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Substring; Graph; Matching (statistics); Computer science; Upper and lower bounds; Mathematics; Algorithm; Running time; Combinatorics; Theoretical computer science; Data structure; Statistics","score_opus":0.04409935035977574,"score_gpt":0.2762889576835892,"score_spread":0.23218960732381344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086354937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008863348,0.00020447836,0.98707354,0.00053834636,0.000048203652,0.00010254546,0.00024850783,0.0005092125,0.0024117867],"genre_scores_gemma":[0.1669865,0.0007569353,0.82451266,0.00057203206,0.00017690012,0.00025231406,0.0013440666,0.00029460152,0.005103995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813217,0.0004676917,0.000101558246,0.0006508942,0.00049204094,0.00015567936],"domain_scores_gemma":[0.99716187,0.0013803641,0.000319483,0.00069157616,0.00027893612,0.00016775246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009827442,0.0011055666,0.0014320504,0.0020788081,0.0011484972,0.0017929776,0.0037025567,0.0023947626,0.006212946],"category_scores_gemma":[0.0051425523,0.00058124645,0.0011824499,0.003637419,0.0018040369,0.007516992,0.0024443248,0.0025757807,0.0014437552],"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":[0.00035568493,0.00040071222,0.0012833031,0.0005991646,0.00012839127,0.0004753618,0.00039906453,0.3700523,0.013641085,0.39180294,0.016634366,0.20422761],"study_design_scores_gemma":[0.000046378835,0.0001171596,0.00021187506,0.000023999031,0.000047527967,0.0003657291,0.0001224716,0.64912194,0.0033855408,0.33616942,0.01035721,0.00003082389],"about_ca_topic_score_codex":0.002291968,"about_ca_topic_score_gemma":0.0025457018,"teacher_disagreement_score":0.006212946,"about_ca_system_score_codex":0.0013156747,"about_ca_system_score_gemma":0.0016390121,"threshold_uncertainty_score":0.020784378},"labels":[],"label_agreement":null},{"id":"W2086423153","doi":"10.1016/j.dam.2009.10.001","title":"On end-vertices of Lexicographic Breadth First Searches","year":2009,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Vertex (graph theory); Lexicographical order; Combinatorics; Mathematics; Set (abstract data type); Computer science; Graph; Programming language","score_opus":0.01951648551427771,"score_gpt":0.2548718604261763,"score_spread":0.23535537491189862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086423153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14944871,0.0030422453,0.76743585,0.0014710503,0.00019880003,0.00033550052,0.0011693519,0.0019647148,0.07493385],"genre_scores_gemma":[0.41947263,0.0015922918,0.5476708,0.00054771715,0.00014944044,0.00030416923,0.0017316312,0.0011546663,0.02737668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829966,0.0006173871,0.0000884193,0.00020801705,0.0005201406,0.00026635104],"domain_scores_gemma":[0.9936465,0.00465286,0.0002744283,0.0007753451,0.00046530532,0.00018558554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013485606,0.000928772,0.0016821673,0.0028331762,0.0015203138,0.0028495425,0.0018449472,0.0017787693,0.011577308],"category_scores_gemma":[0.013695068,0.0008649856,0.00082123914,0.004425234,0.002004057,0.0044702217,0.0030501322,0.0018195092,0.0026556777],"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":[0.0018346336,0.0002574222,0.0019005768,0.0007454743,0.00010095481,0.00035661226,0.0008674075,0.12852131,0.0072382293,0.49038666,0.021250214,0.3465406],"study_design_scores_gemma":[0.00012139032,0.00009900609,0.00036260177,0.00017885932,0.000059698432,0.0001999894,0.00025659098,0.24930647,0.004601564,0.73588496,0.008897293,0.000031561936],"about_ca_topic_score_codex":0.0022730983,"about_ca_topic_score_gemma":0.0036709758,"teacher_disagreement_score":0.011577308,"about_ca_system_score_codex":0.001387668,"about_ca_system_score_gemma":0.0012506727,"threshold_uncertainty_score":0.038729966},"labels":[],"label_agreement":null},{"id":"W2086959852","doi":"10.1007/s10994-009-5103-0","title":"NP-hardness of Euclidean sum-of-squares clustering","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":863,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal; Polytechnique Montréal","funders":"","keywords":"Cluster analysis; Mathematics; Euclidean distance; Explained sum of squares; Euclidean geometry; Combinatorics; Pattern recognition (psychology); Artificial intelligence; Computer science; Statistics","score_opus":0.012571535375825917,"score_gpt":0.2570000966085654,"score_spread":0.24442856123273946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086959852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09082035,0.0052133026,0.8392804,0.017828146,0.00077861355,0.00032658988,0.0043866676,0.002989387,0.038376547],"genre_scores_gemma":[0.63023615,0.002875429,0.33510074,0.0028688665,0.0009604881,0.0007316512,0.0053928313,0.0014302989,0.02040365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99413294,0.0019964434,0.00038309162,0.0012902736,0.0016599816,0.0005372186],"domain_scores_gemma":[0.97650456,0.017888442,0.00092086504,0.0027715145,0.0013928218,0.0005217586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025371208,0.0014115169,0.0036811926,0.0010096085,0.0021406137,0.0046279933,0.005001582,0.003719729,0.007659008],"category_scores_gemma":[0.026150323,0.0012452044,0.0015418004,0.003963928,0.003144532,0.008856873,0.0037228246,0.0050543146,0.0018369692],"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":[0.0017483112,0.0004490148,0.0021090587,0.0015221972,0.00033593609,0.00038472808,0.0008351782,0.53109294,0.003592115,0.17188105,0.08371957,0.20232986],"study_design_scores_gemma":[0.00021526411,0.000058342084,0.00047437527,0.00005793379,0.000048261034,0.00029165955,0.0002854683,0.526195,0.0018168307,0.46410444,0.006420189,0.000032294065],"about_ca_topic_score_codex":0.005403852,"about_ca_topic_score_gemma":0.0055088955,"teacher_disagreement_score":0.007659008,"about_ca_system_score_codex":0.0030603283,"about_ca_system_score_gemma":0.0036142543,"threshold_uncertainty_score":0.02562195},"labels":[],"label_agreement":null},{"id":"W2086997424","doi":"10.1145/1854776.1854846","title":"Genomics information retrieval using a Bayesian model for learning and re-ranking","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Ranking (information retrieval); Computer science; Genomics; Bernoulli distribution; Bayesian probability; Pace; Property (philosophy); Bernoulli's principle; Machine learning; Bayesian inference; Artificial intelligence; Data mining; Mathematics; Statistics; Engineering; Genome; Biology","score_opus":0.018253436412090308,"score_gpt":0.26249335052253947,"score_spread":0.24423991411044915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086997424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011853162,0.000606347,0.9848487,0.0006524881,0.000045572535,0.0001145204,0.00020240297,0.00066486053,0.0010120102],"genre_scores_gemma":[0.42123133,0.0018051774,0.56164634,0.00086721795,0.00053694873,0.0009949666,0.0017573923,0.00027535317,0.010885222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687564,0.0013526161,0.00019567336,0.00051439425,0.00085970835,0.000201893],"domain_scores_gemma":[0.9934644,0.004284572,0.0003998626,0.0006750446,0.0010322361,0.00014393138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045731217,0.0008595958,0.0021087795,0.002638559,0.00096771034,0.0022440262,0.0038361277,0.0023014073,0.0024840154],"category_scores_gemma":[0.017862536,0.0010236508,0.0012012452,0.0032247934,0.001257125,0.0056507406,0.0011626064,0.0025629152,0.002183185],"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":[0.00037083193,0.00029101057,0.0032407015,0.00028153122,0.00017350739,0.00018791368,0.00044233797,0.57793605,0.0047339746,0.066172495,0.009627412,0.33654216],"study_design_scores_gemma":[0.000032198735,0.000047853187,0.00038090398,0.000013728591,0.00001968485,0.00007193726,0.000016491664,0.9696842,0.0007359091,0.027776046,0.0011857087,0.000035451183],"about_ca_topic_score_codex":0.015552334,"about_ca_topic_score_gemma":0.020303607,"teacher_disagreement_score":0.015552334,"about_ca_system_score_codex":0.0025648605,"about_ca_system_score_gemma":0.001984231,"threshold_uncertainty_score":0.030923605},"labels":[],"label_agreement":null},{"id":"W2087005166","doi":"10.1016/s0895-7177(02)00274-1","title":"Fast searches in a recommendation session","year":2002,"lang":"en","type":"article","venue":"Mathematical and Computer Modelling","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Session (web analytics); Computer science; Recommender system; Information retrieval; World Wide Web","score_opus":0.07205196009618924,"score_gpt":0.25066085874031113,"score_spread":0.17860889864412188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087005166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2267588,0.0064685117,0.6243733,0.014163388,0.00420112,0.0024776093,0.0098891845,0.0335332,0.07813486],"genre_scores_gemma":[0.57598925,0.001260196,0.2920593,0.0020754207,0.0019491678,0.00063305086,0.010122812,0.0017489615,0.11416172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956006,0.0011806618,0.00027030983,0.0006625873,0.001681269,0.0006044813],"domain_scores_gemma":[0.9883504,0.0043126093,0.000321557,0.004084916,0.0020380681,0.0008925224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031313375,0.0015180323,0.0043865433,0.0019263295,0.0029016165,0.0038092085,0.002957671,0.0066378387,0.04797711],"category_scores_gemma":[0.017055418,0.0014478671,0.0016470718,0.0033769077,0.0006038783,0.008656544,0.0027374967,0.0038656986,0.027080765],"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":[0.0108912615,0.0031019629,0.009174997,0.00077960576,0.0008776966,0.0011196369,0.00067508937,0.028519005,0.039413203,0.025943343,0.271948,0.6075562],"study_design_scores_gemma":[0.001549022,0.0020335722,0.007048709,0.00015843149,0.00063326437,0.0021538553,0.00090441643,0.729014,0.0321949,0.122998536,0.10091217,0.00039912085],"about_ca_topic_score_codex":0.004100371,"about_ca_topic_score_gemma":0.0084457025,"teacher_disagreement_score":0.04797711,"about_ca_system_score_codex":0.0007845141,"about_ca_system_score_gemma":0.0018748323,"threshold_uncertainty_score":0.16049945},"labels":[],"label_agreement":null},{"id":"W2087359492","doi":"10.1134/s0001434610090166","title":"Reducing character sums to Kloosterman sums","year":2010,"lang":"en","type":"article","venue":"Mathematical Notes","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Kloosterman sum; Mathematics; Character (mathematics); Pure mathematics; Geometry","score_opus":0.017265997799914907,"score_gpt":0.2701696812581035,"score_spread":0.2529036834581886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087359492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22219904,0.0056482013,0.6805769,0.001827789,0.0014823551,0.000072016344,0.0002829838,0.00060908,0.08730167],"genre_scores_gemma":[0.86257935,0.002937326,0.09204373,0.0010046286,0.0019560286,0.00020042469,0.0004028193,0.0007673552,0.03810852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796104,0.0003904273,0.00013952202,0.00033954604,0.0008540299,0.0003153673],"domain_scores_gemma":[0.99562705,0.0023434528,0.00032262615,0.0006414695,0.0006971059,0.00036838354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016233131,0.00096542976,0.0010278568,0.0028969834,0.0015466596,0.0036189144,0.0016483072,0.0012170643,0.0069606667],"category_scores_gemma":[0.013118987,0.0004914372,0.001179443,0.0021558222,0.0024703415,0.0075449594,0.004384053,0.0040951893,0.0020609128],"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":[0.0000672256,0.00003630321,0.00041169362,0.0001463237,0.000026447768,0.00016246262,0.0003326806,0.005177353,0.00384642,0.96158403,0.0021495447,0.026059508],"study_design_scores_gemma":[0.0000033532947,0.000021011949,0.00020618406,0.000027057486,0.000013164914,0.0001841229,0.000044717122,0.015492096,0.0027561234,0.97747326,0.003757757,0.000021131436],"about_ca_topic_score_codex":0.0002993291,"about_ca_topic_score_gemma":0.0004933724,"teacher_disagreement_score":0.0069606667,"about_ca_system_score_codex":0.001181579,"about_ca_system_score_gemma":0.00044374925,"threshold_uncertainty_score":0.023285747},"labels":[],"label_agreement":null},{"id":"W2087601184","doi":"10.1016/j.jda.2006.11.004","title":"A simple fast hybrid pattern-matching algorithm","year":2007,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University","funders":"","keywords":"Simple (philosophy); Algorithm; Alphabet; Pattern matching; Matching (statistics); Computer science; String searching algorithm; SIMPLE algorithm; Independence (probability theory); Mathematics; Artificial intelligence; Statistics","score_opus":0.010511051524354267,"score_gpt":0.26868393093719184,"score_spread":0.25817287941283756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087601184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007480626,0.00021679136,0.98757136,0.00008986768,0.00015987846,0.0001160145,0.00012541408,0.0023112858,0.0019287185],"genre_scores_gemma":[0.0564942,0.00014039864,0.93477166,0.00013999353,0.00007232735,0.0001913397,0.00047010096,0.00023359072,0.0074862745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990963,0.000102367594,0.00006800306,0.0001982764,0.00046163425,0.00007348677],"domain_scores_gemma":[0.99917847,0.00017131501,0.00004042404,0.0002963651,0.00026624583,0.000047277666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063426147,0.00082969555,0.0013086213,0.001516976,0.00074867374,0.0012281728,0.0024485665,0.0013689701,0.014620622],"category_scores_gemma":[0.0019998776,0.0005203615,0.0006896851,0.0025678826,0.0003964858,0.0020908825,0.0020314152,0.0008849023,0.0070426227],"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":[0.0004444283,0.00013921272,0.0005068188,0.00013980982,0.00008112357,0.000103515784,0.00002726483,0.01147698,0.035186347,0.008921738,0.007638179,0.93533456],"study_design_scores_gemma":[0.00034529497,0.00043214756,0.0014183047,0.000033045402,0.00014654589,0.0013881339,0.000059730475,0.8594705,0.068109825,0.03567264,0.032841112,0.00008276472],"about_ca_topic_score_codex":0.0011095976,"about_ca_topic_score_gemma":0.0016676068,"teacher_disagreement_score":0.014620622,"about_ca_system_score_codex":0.0003677266,"about_ca_system_score_gemma":0.0009874997,"threshold_uncertainty_score":0.048910916},"labels":[],"label_agreement":null},{"id":"W2088906714","doi":"10.1016/j.tcs.2013.08.013","title":"Enhanced string covering","year":2013,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Cover (algebra); Mathematics; Prefix; Suffix; Cardinality (data modeling); Combinatorics; Computation; String searching algorithm; Computer science; Discrete mathematics; Algorithm; Data structure; Linguistics","score_opus":0.006813118042016994,"score_gpt":0.2286797062139488,"score_spread":0.22186658817193183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088906714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15335533,0.0024920008,0.77001655,0.0011080297,0.00089016266,0.00018900077,0.0017974853,0.004132564,0.066018976],"genre_scores_gemma":[0.75969946,0.001228441,0.20294611,0.000598786,0.0005247217,0.00019013096,0.0035414614,0.0007454243,0.030525498],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853027,0.00031452626,0.000078741876,0.00029078554,0.00059551105,0.00019006143],"domain_scores_gemma":[0.9974794,0.00077528815,0.00010687579,0.0012408592,0.00029846613,0.00009911978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063494314,0.00058736914,0.0009526069,0.0013591135,0.0005955762,0.0012144112,0.00088035833,0.00118641,0.01111514],"category_scores_gemma":[0.003984489,0.00029975205,0.0006688709,0.002017944,0.00062929874,0.0025083155,0.0022781738,0.0011248356,0.0026366462],"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":[0.0010622502,0.00021479532,0.0013679328,0.00043147238,0.000104659724,0.0008028555,0.00024964858,0.0771701,0.04305564,0.27760357,0.030420676,0.5675164],"study_design_scores_gemma":[0.00009477288,0.00032143848,0.0018542706,0.000101732505,0.000103717335,0.0018918312,0.00009195728,0.59472346,0.049865387,0.2820074,0.06887871,0.00006532063],"about_ca_topic_score_codex":0.000367755,"about_ca_topic_score_gemma":0.00035113937,"teacher_disagreement_score":0.01111514,"about_ca_system_score_codex":0.00063000986,"about_ca_system_score_gemma":0.0005723122,"threshold_uncertainty_score":0.03718382},"labels":[],"label_agreement":null},{"id":"W2090557973","doi":"10.1016/j.aml.2011.12.009","title":"Implication of regular expressions","year":2011,"lang":"en","type":"article","venue":"Applied Mathematics Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"P; Disjoint sets; Mathematics; Combinatorics; String (physics); Simple (philosophy); Set (abstract data type); Jump; Expression (computer science); Discrete mathematics; Time complexity; Computer science","score_opus":0.02584478879633238,"score_gpt":0.22230469892940824,"score_spread":0.19645991013307587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090557973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18522762,0.0018762979,0.67104864,0.0053502438,0.0010268246,0.00022189261,0.0012927997,0.001915932,0.1320397],"genre_scores_gemma":[0.8438375,0.0009118051,0.119931534,0.0016657554,0.00073345506,0.00021759851,0.0017714886,0.0005387544,0.030392049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967174,0.0007747447,0.00029245653,0.0009399656,0.00091127097,0.0003642479],"domain_scores_gemma":[0.9934716,0.0041157166,0.0003737099,0.0006851815,0.0011432272,0.00021050812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017038796,0.0005273751,0.0007484483,0.0016799035,0.0016072369,0.0028058977,0.0011926754,0.0009674388,0.0076200813],"category_scores_gemma":[0.008972539,0.00071549864,0.0011918175,0.0017057632,0.0022860516,0.0067041586,0.002276371,0.0031098493,0.001358709],"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":[0.00026942763,0.000066835724,0.0010060399,0.00017006726,0.000040767554,0.0007474322,0.00069425727,0.0013436106,0.0035448002,0.93935573,0.0050792173,0.047681753],"study_design_scores_gemma":[0.000020488755,0.000023715227,0.00026877323,0.000022676195,0.000035801855,0.00032973694,0.00013795958,0.00587284,0.0023283954,0.98028046,0.010665459,0.000013646201],"about_ca_topic_score_codex":0.00078323204,"about_ca_topic_score_gemma":0.0007182614,"teacher_disagreement_score":0.0076200813,"about_ca_system_score_codex":0.0011130441,"about_ca_system_score_gemma":0.0008688523,"threshold_uncertainty_score":0.025491655},"labels":[],"label_agreement":null},{"id":"W2091012176","doi":"10.1109/dcc.2010.68","title":"Data Compression Based on a Dictionary Method Using Recursive Construction of T-Codes","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"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; Scheme (mathematics); Unix; Data compression; Compression (physics); Algorithm; Theoretical computer science; Programming language; Mathematics","score_opus":0.051063314287036386,"score_gpt":0.3427659540919978,"score_spread":0.2917026398049614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091012176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012453032,0.00044722215,0.9824722,0.00021060286,0.0001739381,0.00015058515,0.00019443838,0.001631306,0.0022667067],"genre_scores_gemma":[0.09083125,0.00060766295,0.9023737,0.00022618612,0.00021886089,0.0003440715,0.0007134058,0.00036122746,0.0043236525],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990048,0.00019645967,0.00011561897,0.0001657208,0.00042056435,0.00009691775],"domain_scores_gemma":[0.9975394,0.0006777043,0.00017321916,0.00090353325,0.0006313799,0.00007476526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006079195,0.0007118369,0.0008693923,0.0021833377,0.0010003118,0.0011676262,0.0013516182,0.0009918436,0.0041246032],"category_scores_gemma":[0.0040502544,0.0003017425,0.00063973083,0.0030155287,0.0016131519,0.0025419453,0.0020405506,0.0016818399,0.0026001947],"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":[0.0005786727,0.00010966087,0.00085586414,0.00040392487,0.000057232573,0.00034267278,0.000622278,0.021774234,0.095515385,0.11466497,0.011465935,0.75360924],"study_design_scores_gemma":[0.00036418627,0.00094116904,0.0009139207,0.00017620371,0.00011798684,0.0023721491,0.00032229442,0.42775354,0.39543307,0.06939467,0.101990186,0.00022064718],"about_ca_topic_score_codex":0.0011385027,"about_ca_topic_score_gemma":0.0011228642,"teacher_disagreement_score":0.0041246032,"about_ca_system_score_codex":0.00056665123,"about_ca_system_score_gemma":0.0009475373,"threshold_uncertainty_score":0.013798177},"labels":[],"label_agreement":null},{"id":"W2094085768","doi":"10.5539/ijsp.v2n3p50","title":"Counting Runs of Ones with Overlapping Parts in Binary Strings Ordered Linearly and Circularly","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Combinatorics; Binary number; String (physics); Generating function; Simple (philosophy); Function (biology); Expected value; Discrete mathematics; Arithmetic; Statistics","score_opus":0.01217121648178126,"score_gpt":0.23848369374813067,"score_spread":0.2263124772663494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094085768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3834186,0.0015959849,0.59328985,0.00068111846,0.0003090708,0.0003241939,0.0009875535,0.0006190728,0.018774625],"genre_scores_gemma":[0.64653957,0.00087600044,0.33715203,0.0002714709,0.0001969435,0.000906061,0.0014595351,0.00036183058,0.012236568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99566287,0.0012917793,0.0005038442,0.0010196187,0.0010564962,0.0004654379],"domain_scores_gemma":[0.9825446,0.011219415,0.002123617,0.0021917666,0.0013451234,0.00057553046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003160288,0.0008324943,0.0011554076,0.0024203507,0.0017014878,0.0025511393,0.0018393918,0.0010875029,0.0043583885],"category_scores_gemma":[0.022307042,0.00039815882,0.00078129006,0.003382444,0.0032680954,0.005029922,0.0021259077,0.0011235902,0.0009503038],"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":[0.0017391975,0.00021125922,0.019905128,0.0006887807,0.0001348115,0.0011914691,0.0014366612,0.05792566,0.026961925,0.7252348,0.0043617785,0.16020854],"study_design_scores_gemma":[0.00007289773,0.00053006696,0.00644966,0.0003760183,0.00016469609,0.0021224185,0.0006002566,0.30876943,0.038262904,0.62239987,0.019998595,0.0002531316],"about_ca_topic_score_codex":0.00075844483,"about_ca_topic_score_gemma":0.0011664656,"teacher_disagreement_score":0.0043583885,"about_ca_system_score_codex":0.0012576729,"about_ca_system_score_gemma":0.0013231011,"threshold_uncertainty_score":0.01671338},"labels":[],"label_agreement":null},{"id":"W2094154930","doi":"10.1145/1498698.1564507","title":"An experimental investigation of set intersection algorithms for text searching","year":2009,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","field":"Computer Science","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":"University of Waterloo","funders":"","keywords":"Intersection (aeronautics); Context (archaeology); Set (abstract data type); Computer science; Algorithm; Theoretical computer science; Randomized algorithm; Information retrieval; Mathematics","score_opus":0.0479229736013965,"score_gpt":0.34821905341615517,"score_spread":0.30029607981475864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094154930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79716235,0.008279687,0.14713073,0.0018814311,0.00077019626,0.0015662191,0.0057492396,0.015096114,0.022363953],"genre_scores_gemma":[0.6515135,0.0014265499,0.33000892,0.00035079455,0.00023316109,0.0012733254,0.010410073,0.0012210048,0.0035626118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9735156,0.011003322,0.003365615,0.0028097685,0.008079876,0.0012257445],"domain_scores_gemma":[0.90793586,0.065476865,0.002809742,0.014480516,0.008281083,0.0010158893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013577845,0.0020030912,0.002437027,0.0043478487,0.002110477,0.0031804089,0.004360543,0.002915689,0.005356369],"category_scores_gemma":[0.07633378,0.000828636,0.0012299827,0.010356249,0.0018585348,0.010023804,0.0029669192,0.0025045876,0.0020533488],"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":[0.017640185,0.0067677023,0.015474038,0.0031421606,0.0010376321,0.00028031718,0.0010161912,0.15802579,0.024679542,0.02127401,0.033048604,0.71761376],"study_design_scores_gemma":[0.0023854473,0.0059872163,0.00850171,0.00014811373,0.00039156567,0.00087638356,0.001230593,0.8830354,0.059111137,0.02395898,0.014185342,0.00018802349],"about_ca_topic_score_codex":0.00566234,"about_ca_topic_score_gemma":0.004351618,"teacher_disagreement_score":0.013577845,"about_ca_system_score_codex":0.0031628294,"about_ca_system_score_gemma":0.0030327113,"threshold_uncertainty_score":0.071807384},"labels":[],"label_agreement":null},{"id":"W2094270516","doi":"10.1016/j.tcs.2014.03.014","title":"A bijective variant of the Burrows–Wheeler Transform using V -order","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicographical order; Bijection; String (physics); Factorization; Order (exchange); Combinatorics; Mathematics; Sorting; Suffix; Algorithm; Extension (predicate logic); Suffix array; Discrete mathematics; Data structure; Computer science","score_opus":0.008812748346585018,"score_gpt":0.23876803994743095,"score_spread":0.22995529160084593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094270516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019407678,0.000931712,0.9485382,0.00040983703,0.00070184586,0.000073652875,0.00019833926,0.0005924084,0.02914634],"genre_scores_gemma":[0.36685714,0.0021018593,0.5797764,0.00068258826,0.0008013792,0.00017914589,0.0006571264,0.0010570174,0.047887325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992105,0.00014855937,0.000046435165,0.00014606536,0.00036848095,0.00008000691],"domain_scores_gemma":[0.99927837,0.000212941,0.000050052637,0.0002615607,0.00014698652,0.000050067196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005528592,0.00049778254,0.0005757893,0.0013809287,0.0005544857,0.0017579786,0.0008976404,0.0007449016,0.006871098],"category_scores_gemma":[0.0027402434,0.00028001762,0.0005412857,0.001439376,0.0012796103,0.002312161,0.0015380504,0.0018789798,0.0029406687],"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":[0.000111278976,0.00006540507,0.00017443362,0.00010781332,0.000018912004,0.00013641547,0.00014399664,0.0068061342,0.017074168,0.792282,0.005288333,0.17779106],"study_design_scores_gemma":[0.00006485921,0.00017492376,0.0003952082,0.00007827171,0.00003205951,0.0010200435,0.00014053588,0.11153233,0.031470172,0.7636806,0.09131618,0.00009483044],"about_ca_topic_score_codex":0.00074823794,"about_ca_topic_score_gemma":0.0007828343,"teacher_disagreement_score":0.006871098,"about_ca_system_score_codex":0.0003774763,"about_ca_system_score_gemma":0.00065166835,"threshold_uncertainty_score":0.022986114},"labels":[],"label_agreement":null},{"id":"W2094392848","doi":"10.1145/2379776.2379781","title":"A comparison of index-based lempel-Ziv LZ77 factorization algorithms","year":2012,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"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; McMaster University","funders":"Engineering and Physical Sciences Research Council; RMIT University","keywords":"Factorization; Computer science; Algorithm; Data compression; String (physics); Index (typography); Mathematics","score_opus":0.15953346682345704,"score_gpt":0.4072939967836119,"score_spread":0.24776052996015485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094392848","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03526581,0.3715595,0.5334006,0.0025638398,0.0015770508,0.0004908518,0.0009824458,0.0036983318,0.050461605],"genre_scores_gemma":[0.16403829,0.2198877,0.58898854,0.0011614861,0.001761389,0.00070027506,0.004675596,0.00093754445,0.017849147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970606,0.00048783523,0.00024375679,0.00033301304,0.0016639043,0.00021083787],"domain_scores_gemma":[0.99633163,0.0016715897,0.00020300577,0.0004471968,0.0012453122,0.00010127494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002288415,0.0012929462,0.0016210752,0.0053396686,0.0009407354,0.0023350082,0.0028813921,0.0015575391,0.0066244705],"category_scores_gemma":[0.010195543,0.00044745064,0.0009853833,0.007200759,0.0009069817,0.005615029,0.0016050562,0.0018129814,0.0053917123],"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":[0.0005225106,0.00016642697,0.00053585746,0.0011907546,0.00007336406,0.000058803078,0.00014639164,0.0067860642,0.0035103718,0.03280581,0.015653227,0.93855035],"study_design_scores_gemma":[0.00070381357,0.0019739014,0.0050539393,0.0024984195,0.0003988054,0.0055621252,0.0012531921,0.26210994,0.075227655,0.1612538,0.48349416,0.00047019048],"about_ca_topic_score_codex":0.0013777543,"about_ca_topic_score_gemma":0.0014640521,"teacher_disagreement_score":0.0066244705,"about_ca_system_score_codex":0.0014484547,"about_ca_system_score_gemma":0.0020803786,"threshold_uncertainty_score":0.022161007},"labels":[],"label_agreement":null},{"id":"W2095207794","doi":"10.1088/1742-6596/341/1/012034","title":"Bioinformatics algorithm based on a parallel implementation of a machine learning approach using transducers","year":2012,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Algorithms and Data Compression","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":"University of Manitoba","funders":"National Institute on Minority Health and Health Disparities","keywords":"Computer science; Speedup; Algorithm; Normalization (sociology); Scalability; Parallel algorithm; Computation; Smith–Waterman algorithm; Transducer; Sequence alignment; Parallel computing","score_opus":0.03870449187761333,"score_gpt":0.2864940019788102,"score_spread":0.24778951010119687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095207794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004527599,0.000066649365,0.9801357,0.00015165268,0.00006648571,0.00010188269,0.0001884891,0.012543796,0.0022177685],"genre_scores_gemma":[0.070438094,0.00009484895,0.9226734,0.0001562775,0.000047910038,0.0004550531,0.0010437518,0.0006633178,0.0044274214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993604,0.00009134726,0.00005644501,0.00025383968,0.00017324433,0.00006471575],"domain_scores_gemma":[0.9994311,0.00018551663,0.00003216168,0.000120833494,0.00019630877,0.00003407586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005300642,0.0009196071,0.00067536125,0.00092846714,0.0008251356,0.0010860602,0.0015147842,0.0008810335,0.008557914],"category_scores_gemma":[0.001513888,0.0004902366,0.0009614977,0.000965871,0.000564222,0.0012826616,0.00088690623,0.0013329496,0.00386465],"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":[0.0010096611,0.0004387357,0.0036573624,0.0005518941,0.00021829383,0.00056385953,0.00042662444,0.20319565,0.04825477,0.0821384,0.03839026,0.62115455],"study_design_scores_gemma":[0.00012722796,0.000104220424,0.0003591908,0.000018025226,0.000042951993,0.00024294984,0.000038683218,0.9245967,0.020351404,0.030698268,0.023386797,0.000033508582],"about_ca_topic_score_codex":0.003235711,"about_ca_topic_score_gemma":0.0027040732,"teacher_disagreement_score":0.008557914,"about_ca_system_score_codex":0.00088869623,"about_ca_system_score_gemma":0.0018372018,"threshold_uncertainty_score":0.028629065},"labels":[],"label_agreement":null},{"id":"W2095439426","doi":"10.1145/1551950.1551980","title":"Pairwise sequence alignment algorithms","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":57,"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 Northern British Columbia","funders":"","keywords":"Pairwise comparison; Alignment-free sequence analysis; Sequence (biology); Multiple sequence alignment; Computer science; Sequence alignment; Algorithm; Sequence database; Smith–Waterman algorithm; Data mining; Artificial intelligence; Biology; Gene; Peptide sequence; Genetics","score_opus":0.03001452707153884,"score_gpt":0.2766715539780855,"score_spread":0.24665702690654667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095439426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018352867,0.0024813805,0.9827145,0.0002520335,0.00034490923,0.00046448765,0.0015768169,0.004490599,0.0058400654],"genre_scores_gemma":[0.01895733,0.0021954735,0.9682013,0.00024224346,0.00024126288,0.00074705377,0.0053808754,0.0008607188,0.0031737268],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926018,0.0024972965,0.00094905257,0.0015242072,0.0021047061,0.00032286503],"domain_scores_gemma":[0.9940209,0.002256412,0.00068402826,0.0013820058,0.0014793609,0.00017723833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004190424,0.0032344146,0.003733703,0.0057288664,0.002608785,0.0035296115,0.0052252985,0.002574535,0.017994095],"category_scores_gemma":[0.017203439,0.001086333,0.0024089047,0.01099294,0.001088683,0.0059065036,0.003870095,0.0031751974,0.02129767],"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":[0.000349073,0.00033986702,0.0016913046,0.0018644215,0.00066884863,0.00038496815,0.00045384193,0.06066058,0.008660941,0.09200479,0.08003292,0.75288844],"study_design_scores_gemma":[0.0001903424,0.0003450609,0.0010276128,0.0005357569,0.00028167132,0.0019308485,0.0004971294,0.37127385,0.017319394,0.30459347,0.301835,0.00016997886],"about_ca_topic_score_codex":0.0010401024,"about_ca_topic_score_gemma":0.0012505768,"teacher_disagreement_score":0.017994095,"about_ca_system_score_codex":0.0010700006,"about_ca_system_score_gemma":0.0026042962,"threshold_uncertainty_score":0.06019628},"labels":[],"label_agreement":null},{"id":"W2096000848","doi":"10.1109/tip.2006.877414","title":"Lossless compression of VLSI layout image data","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Algorithms and Data Compression","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":"Advanced Micro Devices (Canada)","funders":"","keywords":"Lossless compression; Huffman coding; Arithmetic coding; Data compression; Image compression; Entropy encoding; Computer science; Context-adaptive binary arithmetic coding; Lossy compression; Adaptive coding; Tunstall coding; Color Cell Compression; Texture compression; Algorithm; Artificial intelligence; Image processing; Image (mathematics)","score_opus":0.024748417399133294,"score_gpt":0.28222875517186863,"score_spread":0.2574803377727353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096000848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1364809,0.0009375143,0.85206354,0.00042525455,0.00018450455,0.00008895685,0.00046218015,0.002604919,0.0067523075],"genre_scores_gemma":[0.6016776,0.0006701634,0.38951486,0.00032926144,0.00014920275,0.00011130121,0.0011112012,0.00026264007,0.006173773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997222,0.000023188159,0.000014199046,0.000029049817,0.0001852697,0.000026082264],"domain_scores_gemma":[0.99950325,0.00014701372,0.000056333953,0.00014029352,0.000130108,0.00002293457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018841674,0.00039421994,0.00033517307,0.00089845585,0.00024077576,0.0006517283,0.00076051516,0.0003536651,0.0017039671],"category_scores_gemma":[0.0012504256,0.00012991359,0.00018879691,0.0013069198,0.0004454812,0.00084262184,0.0005503178,0.00046009972,0.00066556816],"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":[0.0004623961,0.00012542527,0.0010363238,0.00019284482,0.000030207259,0.0005913823,0.00013848163,0.07505432,0.26537684,0.032617092,0.0076291976,0.61674553],"study_design_scores_gemma":[0.00007498456,0.0002918382,0.0012708065,0.00003032211,0.000033189073,0.0010508018,0.000056700508,0.58662516,0.38607907,0.009375408,0.015065613,0.00004602023],"about_ca_topic_score_codex":0.0006913695,"about_ca_topic_score_gemma":0.0010562828,"teacher_disagreement_score":0.0017039671,"about_ca_system_score_codex":0.00044263792,"about_ca_system_score_gemma":0.00039467908,"threshold_uncertainty_score":0.00570035},"labels":[],"label_agreement":null},{"id":"W2096352571","doi":"10.1109/tsp.2004.831128","title":"Efficient Adaptive Algorithms and Minimax Bounds for Zero-Delay Lossy Source Coding","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics; Minimax; Bounded function; Upper and lower bounds; Algorithm; Redundancy (engineering); Rate–distortion theory; Discrete mathematics; Distortion (music); Combinatorics; Data compression; Computer science; Mathematical optimization; Mathematical analysis","score_opus":0.024775833374553607,"score_gpt":0.2605651538793277,"score_spread":0.2357893205047741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096352571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076434896,0.00030130465,0.9897333,0.0001225515,0.000019858682,0.000050637133,0.000022222692,0.00019275388,0.001914013],"genre_scores_gemma":[0.39497015,0.0009799431,0.59880257,0.0001847841,0.00009059894,0.00046759233,0.00014624697,0.00010466711,0.004253463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987048,0.00039772503,0.000073668234,0.00025153995,0.0004575585,0.000114759605],"domain_scores_gemma":[0.9954667,0.003162707,0.0004985999,0.0004638464,0.00034596302,0.00006219984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015065015,0.0010510955,0.00078293873,0.0008119224,0.0004941049,0.0011919877,0.0019584768,0.0012012166,0.0017695711],"category_scores_gemma":[0.009837289,0.0004385564,0.0005311628,0.0011531201,0.0016388623,0.0026343097,0.0015699584,0.0020597607,0.000515473],"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":[0.00019139069,0.00006211922,0.00047843312,0.000142249,0.000039739847,0.00006299206,0.00015412897,0.54856694,0.0096734725,0.32838422,0.0013472446,0.11089702],"study_design_scores_gemma":[0.000022720307,0.00004771512,0.0000873647,0.000018962664,0.0000071493164,0.000042519932,0.000011886297,0.9239301,0.0038185567,0.07093035,0.0010674555,0.000015224598],"about_ca_topic_score_codex":0.0008512715,"about_ca_topic_score_gemma":0.0007915281,"teacher_disagreement_score":0.0020862303,"about_ca_system_score_codex":0.0020862303,"about_ca_system_score_gemma":0.0010763023,"threshold_uncertainty_score":0.015136778},"labels":[],"label_agreement":null},{"id":"W2096574248","doi":"10.1109/tit.2003.820019","title":"Context-dependent multilevel pattern matching for lossless image compression","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Redundancy (engineering); Arithmetic coding; Lossless compression; Data compression; Computer science; Algorithm; Code (set theory); Systematic code; Context (archaeology); Theoretical computer science; Prefix code; Coding (social sciences); Constant-weight code; Pixel; Universal code; Context model; Code rate; Mathematics; Artificial intelligence; Decoding methods; Linear code; Context-adaptive binary arithmetic coding; Block code; Statistics; Programming language","score_opus":0.014007275567787537,"score_gpt":0.24919450634582072,"score_spread":0.2351872307780332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096574248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062981986,0.0016471894,0.9305983,0.00016295057,0.000101058926,0.00007883104,0.00010195339,0.0008485233,0.0034792058],"genre_scores_gemma":[0.52861357,0.0010622955,0.46692663,0.00025323368,0.0000814569,0.00015429701,0.00027221473,0.00009671641,0.0025395695],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99970824,0.000039212202,0.0000166938,0.000041056897,0.00017489224,0.00001989157],"domain_scores_gemma":[0.99959177,0.00012553816,0.000055542136,0.00012284379,0.00008803975,0.000016312128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016516147,0.00030870634,0.00028974452,0.00045859127,0.00022365018,0.00037420244,0.00061590935,0.00047959818,0.0013587071],"category_scores_gemma":[0.0015679103,0.00013008565,0.00021526855,0.00072449463,0.0002601388,0.000722677,0.0005853617,0.00060539646,0.00044380824],"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":[0.0002635836,0.000058596906,0.0007360859,0.000299748,0.000036090245,0.00035750732,0.00013794267,0.060971033,0.23352984,0.041039463,0.0028015322,0.65976846],"study_design_scores_gemma":[0.000026965214,0.00027395305,0.0010816696,0.000067045185,0.000030496232,0.0009676467,0.000037453923,0.79253227,0.17270589,0.017593235,0.014646316,0.000037051297],"about_ca_topic_score_codex":0.0006187756,"about_ca_topic_score_gemma":0.0008500111,"teacher_disagreement_score":0.0013587071,"about_ca_system_score_codex":0.00030639058,"about_ca_system_score_gemma":0.00032971048,"threshold_uncertainty_score":0.0045453906},"labels":[],"label_agreement":null},{"id":"W2096724800","doi":"10.1007/978-3-319-02786-9_2","title":"A True Random Generator Using Human Gameplay","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Generator (circuit theory); Theoretical computer science; Programming language; Power (physics); Physics","score_opus":0.023723392996917118,"score_gpt":0.2605503918274431,"score_spread":0.236826998830526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096724800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013354362,0.000058965117,0.974376,0.00031010254,0.000119144504,0.00016644546,0.000045607925,0.0011803093,0.010388963],"genre_scores_gemma":[0.59149855,0.00011125576,0.38206324,0.0002883958,0.00008326784,0.00049283495,0.0001389056,0.00047383932,0.024849739],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826294,0.0009705275,0.000051094623,0.00024269691,0.00037165466,0.00010115781],"domain_scores_gemma":[0.9955249,0.0032437916,0.00010275562,0.00068903976,0.00027116115,0.00016832267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021699527,0.0006946235,0.00059415394,0.0004260848,0.0005584102,0.0015399313,0.0016919973,0.0011252761,0.013869296],"category_scores_gemma":[0.010554333,0.00039346397,0.00037807034,0.00024130021,0.0015119726,0.0021594472,0.001962289,0.001088089,0.0021828606],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010163495,0.0002879735,0.0015173823,0.00028397137,0.00009809179,0.0004445263,0.00074878166,0.13021548,0.017357709,0.6160221,0.01351889,0.21848883],"study_design_scores_gemma":[0.00014838473,0.00018278946,0.00013769121,0.00003371454,0.000026612797,0.0002880455,0.00006967558,0.80146265,0.006073898,0.18300328,0.008543045,0.000030232415],"about_ca_topic_score_codex":0.00046743386,"about_ca_topic_score_gemma":0.0005486432,"teacher_disagreement_score":0.013869296,"about_ca_system_score_codex":0.00042881485,"about_ca_system_score_gemma":0.0007533395,"threshold_uncertainty_score":0.046397388},"labels":[],"label_agreement":null},{"id":"W2096960653","doi":"","title":"Selecting Query Term Alternations for Web Search by Exploiting Query Contexts","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Query expansion; Computer science; Bigram; Web query classification; Web search query; Information retrieval; Query optimization; Query language; Sargable; Selection (genetic algorithm); Term (time); RDF query language; Context (archaeology); Search engine; Word (group theory); Natural language processing; Artificial intelligence","score_opus":0.02470986278797762,"score_gpt":0.2848725438985707,"score_spread":0.2601626811105931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096960653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65075463,0.005428444,0.3318554,0.0006286401,0.0001276106,0.0008941311,0.0005953457,0.00466634,0.005049529],"genre_scores_gemma":[0.7845204,0.0010299041,0.21045333,0.0002108848,0.00028137115,0.00032593464,0.00110019,0.00040192207,0.0016760846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988952,0.0003553624,0.00013316765,0.00023389778,0.00028464638,0.00009778423],"domain_scores_gemma":[0.99722433,0.0017118352,0.00022528281,0.00028421957,0.00041921847,0.0001351521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012514467,0.0010649003,0.0014510688,0.0038920785,0.00070718996,0.0009618033,0.0008228598,0.0006048866,0.0016443634],"category_scores_gemma":[0.0067106364,0.00044235383,0.0005431543,0.0028083299,0.0005072027,0.0021296619,0.0010706787,0.0007898942,0.001021419],"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":[0.0020878445,0.0005831356,0.011521622,0.0005008046,0.00012284267,0.00048214436,0.0005999417,0.011101766,0.21683824,0.0027015419,0.004274617,0.7491856],"study_design_scores_gemma":[0.0007564157,0.002103671,0.030383635,0.00013079886,0.0010560667,0.0029879855,0.0010860366,0.7874183,0.13960384,0.013562615,0.020594187,0.00031636198],"about_ca_topic_score_codex":0.0022346876,"about_ca_topic_score_gemma":0.00660232,"teacher_disagreement_score":0.0038920785,"about_ca_system_score_codex":0.00039476523,"about_ca_system_score_gemma":0.0010271261,"threshold_uncertainty_score":0.006618321},"labels":[],"label_agreement":null},{"id":"W2097984521","doi":"10.1109/tai.1990.130417","title":"A massively parallel knowledge-base server using a hypercube multiprocessor","year":2002,"lang":"en","type":"article","venue":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Massively parallel; Computer science; Hypercube; Multiprocessing; Parallel computing; Frame (networking); Base (topology); Knowledge base; Recursion (computer science); Representation (politics); Theoretical computer science; Architecture; Programming language; Artificial intelligence","score_opus":0.20404213269606833,"score_gpt":0.33013087970059013,"score_spread":0.1260887470045218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097984521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07929857,0.0007090461,0.8831669,0.001018188,0.00022015681,0.00044009674,0.00062095386,0.018425278,0.016100828],"genre_scores_gemma":[0.3645601,0.0006108726,0.61631024,0.00024371051,0.000108167646,0.00040462436,0.002212381,0.000465261,0.015084595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950325,0.000115534654,0.000038578328,0.00012782753,0.00015520384,0.00005955717],"domain_scores_gemma":[0.9992525,0.0002092124,0.000036440048,0.00021478656,0.00018498197,0.000102029495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073037733,0.0005397404,0.0007628869,0.0008637058,0.0010347541,0.0023445932,0.002270095,0.0010344485,0.006967849],"category_scores_gemma":[0.0019604315,0.00049814896,0.00036929868,0.0020717108,0.00053682335,0.0032556215,0.0010029548,0.00085023185,0.0033828395],"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":[0.0022799869,0.0010248979,0.0041763284,0.0005410916,0.00028228323,0.0010848937,0.0008059082,0.1836491,0.053613607,0.08006172,0.05933909,0.61314106],"study_design_scores_gemma":[0.00028370708,0.0002618165,0.0007864396,0.000032126936,0.00008509808,0.00031786185,0.00020652887,0.906179,0.024160137,0.02957569,0.038059246,0.00005220095],"about_ca_topic_score_codex":0.006234053,"about_ca_topic_score_gemma":0.0050502256,"teacher_disagreement_score":0.006967849,"about_ca_system_score_codex":0.0011216219,"about_ca_system_score_gemma":0.0018481647,"threshold_uncertainty_score":0.023309767},"labels":[],"label_agreement":null},{"id":"W2098163860","doi":"10.1109/isit.2002.1023562","title":"The compression performance of grammar-based codes revisited","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Lossless compression; Computer science; Redundancy (engineering); Grammar; Arithmetic coding; Data compression; Coding (social sciences); Benchmark (surveying); Encoding (memory); Theoretical computer science; Algorithm; Context-adaptive binary arithmetic coding; Artificial intelligence; Mathematics; Linguistics","score_opus":0.012449054345169056,"score_gpt":0.23338164145757992,"score_spread":0.22093258711241087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098163860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80162966,0.017588904,0.15774733,0.0033898195,0.0004195442,0.00007887341,0.00047589713,0.0016582096,0.01701181],"genre_scores_gemma":[0.96068805,0.002259678,0.034571473,0.00030014524,0.0001450911,0.00004198744,0.00030906836,0.00013363919,0.0015507764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845636,0.00043336104,0.0000797916,0.0001709742,0.0007127809,0.00014689138],"domain_scores_gemma":[0.98965853,0.007125214,0.00046742332,0.0011093954,0.0015136328,0.00012579485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016436599,0.0005595866,0.00082607893,0.001228061,0.0003527467,0.0009823546,0.0009013557,0.0019430362,0.0012493143],"category_scores_gemma":[0.01772038,0.0002226576,0.00021667087,0.0020450125,0.00152141,0.0023349803,0.00095563853,0.0011779867,0.00037825547],"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":[0.0026435095,0.00019724069,0.0057774126,0.0005930935,0.00018574925,0.0005304742,0.0005929957,0.4337517,0.09394762,0.13745077,0.007049342,0.31728005],"study_design_scores_gemma":[0.00009200421,0.0007184382,0.0018321816,0.00009591123,0.000059920254,0.0006882531,0.00012494791,0.8381427,0.08991282,0.06423184,0.004027589,0.00007334928],"about_ca_topic_score_codex":0.0014086873,"about_ca_topic_score_gemma":0.0009796171,"teacher_disagreement_score":0.0019430362,"about_ca_system_score_codex":0.0010776299,"about_ca_system_score_gemma":0.0006106212,"threshold_uncertainty_score":0.008692622},"labels":[],"label_agreement":null},{"id":"W2098235950","doi":"10.1109/wcnc.2007.100","title":"A New Approach for Constructing FSSM Modeled Encoders to Satisfy Spectral Constraints","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Alberta","funders":"","keywords":"Encoder; Code word; Computer science; Encoding (memory); Transmission (telecommunications); State (computer science); Algorithm; Power (physics); Theoretical computer science; Decoding methods; Telecommunications; Artificial intelligence","score_opus":0.027795826776105627,"score_gpt":0.27936495954716783,"score_spread":0.2515691327710622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098235950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004237814,0.00002057637,0.99473757,0.00003064099,0.000011057982,0.000018080924,0.000017816468,0.00015576588,0.0007706498],"genre_scores_gemma":[0.21852705,0.0000984092,0.7787423,0.00009338927,0.00002394319,0.00013704626,0.00012240962,0.00006744403,0.0021879182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995453,0.00013354067,0.000032783057,0.00007562122,0.00018476954,0.000027941825],"domain_scores_gemma":[0.9992797,0.00032595257,0.00006218114,0.00016992417,0.00014009101,0.00002216695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046750536,0.0004338428,0.00040772426,0.00027096414,0.0002712239,0.00045195298,0.00057840947,0.0005591516,0.0014956973],"category_scores_gemma":[0.0021999625,0.00025064085,0.000484112,0.00024512442,0.00054426875,0.0008595351,0.0006266724,0.0008026605,0.00037185752],"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":[0.00014258681,0.000101188,0.000613575,0.00015513458,0.00005256322,0.00026640893,0.00023394842,0.49477673,0.048798837,0.2906214,0.0017906511,0.16244699],"study_design_scores_gemma":[0.000016827998,0.000089791916,0.00006561003,0.000014645958,0.000009425952,0.000100026846,0.000014259799,0.9458908,0.0135759795,0.03581323,0.0043956297,0.000013780876],"about_ca_topic_score_codex":0.00075551437,"about_ca_topic_score_gemma":0.001012656,"teacher_disagreement_score":0.0014956973,"about_ca_system_score_codex":0.0004060384,"about_ca_system_score_gemma":0.0008435779,"threshold_uncertainty_score":0.0050035715},"labels":[],"label_agreement":null},{"id":"W2098402986","doi":"10.1142/s0129054105003091","title":"FORMAL MODELLING OF VIRAL GENE COMPRESSION","year":2005,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","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":"University of Saskatchewan; Western University","funders":"","keywords":"Genome; sort; Gene; Computer science; Computational biology; Formal language; Human genome; Biology; Theoretical computer science; Artificial intelligence; Genetics; Programming language; Information retrieval","score_opus":0.028339105833077364,"score_gpt":0.297394017972588,"score_spread":0.26905491213951066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098402986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030114755,0.0006557678,0.94463766,0.0015416851,0.00010307121,0.00008922818,0.00032775087,0.0003158753,0.022214161],"genre_scores_gemma":[0.6511424,0.0014514123,0.32871643,0.0004956817,0.00024871228,0.0005618792,0.0008193159,0.00027731655,0.016286802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866176,0.0004399264,0.00010602246,0.0001816442,0.0004502005,0.00016035838],"domain_scores_gemma":[0.99579346,0.0026278615,0.00038446006,0.00057904306,0.0004369979,0.00017813749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001987571,0.000590783,0.0005144758,0.0013102107,0.0011947094,0.0033543601,0.0019554957,0.0016237367,0.003698436],"category_scores_gemma":[0.00708435,0.00045565024,0.0015991331,0.0010178079,0.0046457625,0.004221986,0.002012626,0.0017063876,0.000676901],"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":[0.00001215469,0.0000118856115,0.00013788872,0.000025777113,0.0000052374226,0.000086139415,0.00018029932,0.03204,0.0007346141,0.96460366,0.0002639093,0.001898545],"study_design_scores_gemma":[0.000018922936,0.000016644324,0.000060364102,0.000023783214,0.000008454309,0.000114669194,0.00007195469,0.18067409,0.0008155693,0.8117807,0.0063978843,0.000016951913],"about_ca_topic_score_codex":0.0038884417,"about_ca_topic_score_gemma":0.0030803208,"teacher_disagreement_score":0.0038884417,"about_ca_system_score_codex":0.0027709603,"about_ca_system_score_gemma":0.001689417,"threshold_uncertainty_score":0.020104825},"labels":[],"label_agreement":null},{"id":"W2099804009","doi":"10.1007/s11416-006-0011-3","title":"Anti-disassembly using Cryptographic Hash Functions","year":2006,"lang":"en","type":"article","venue":"Journal in Computer Virology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Hash function; Cryptography; Cryptographic primitive; Encryption; Cryptographic hash function; Code (set theory); Coding (social sciences); Theoretical computer science; Cryptographic protocol; Computer security; Programming language","score_opus":0.016535366470649543,"score_gpt":0.2511821929079612,"score_spread":0.23464682643731163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099804009","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32568634,0.0009154657,0.6520884,0.0006004724,0.0004892762,0.00010993138,0.00011321976,0.004626039,0.015370924],"genre_scores_gemma":[0.89540535,0.00026550557,0.089298025,0.00020429405,0.00012023487,0.000043381795,0.0002170501,0.00025697288,0.014189293],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990152,0.00013784236,0.00006474574,0.00015814575,0.00046921166,0.00015478213],"domain_scores_gemma":[0.9947249,0.0013297192,0.0007005988,0.0023323814,0.000736089,0.00017617858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001056158,0.00076055067,0.00064627716,0.0010467866,0.0010244391,0.0011879135,0.0011643748,0.00089077104,0.0043418915],"category_scores_gemma":[0.0028981722,0.00046781698,0.00035769574,0.0008649316,0.0010030168,0.0025505521,0.0019276353,0.000809644,0.0016886492],"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":[0.0027764384,0.0005260149,0.008050814,0.00031220398,0.00010162086,0.00086311897,0.00037494052,0.039647095,0.27700272,0.12608199,0.008264094,0.535999],"study_design_scores_gemma":[0.000109723784,0.0010145853,0.0024211837,0.000040158055,0.000069223715,0.002129236,0.0002018855,0.3723844,0.5573019,0.047812972,0.016426245,0.00008854388],"about_ca_topic_score_codex":0.0001520961,"about_ca_topic_score_gemma":0.00026939463,"teacher_disagreement_score":0.0043418915,"about_ca_system_score_codex":0.00041800458,"about_ca_system_score_gemma":0.00056292955,"threshold_uncertainty_score":0.0145251155},"labels":[],"label_agreement":null},{"id":"W2099854771","doi":"10.1109/dcc.1992.227477","title":"Textual image compression","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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 Calgary","funders":"","keywords":"Typeface; Computer science; Variety (cybernetics); Flemish; Hebrew; Information retrieval; Lossless compression; Computer graphics (images); Artificial intelligence; Data compression; Linguistics; Art; Literature","score_opus":0.011685423020102585,"score_gpt":0.24539637254893973,"score_spread":0.23371094952883714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099854771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011430008,0.0024541782,0.9195239,0.0007207502,0.0015952076,0.0008519193,0.002126646,0.016632529,0.044664834],"genre_scores_gemma":[0.083755046,0.003013852,0.7933484,0.0010962002,0.0010408777,0.0007348486,0.0051082307,0.0027696423,0.109132916],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912184,0.00006393573,0.000071843344,0.00012474676,0.0005508712,0.00006677316],"domain_scores_gemma":[0.998252,0.00032813175,0.000108767956,0.0005758408,0.0006692713,0.00006603568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047746362,0.0012075135,0.0005283346,0.003394442,0.000741525,0.0019073035,0.0016260281,0.0011046865,0.04389743],"category_scores_gemma":[0.0033530134,0.000408384,0.0007352077,0.002944589,0.0006341738,0.0021029126,0.0014193362,0.0010636284,0.021605866],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004963176,0.00014732756,0.0004120189,0.00067735655,0.000049832546,0.00045292094,0.00020215892,0.003045787,0.08516251,0.012603175,0.054731917,0.8420186],"study_design_scores_gemma":[0.00017609858,0.0003854096,0.0023795923,0.00023424042,0.00012432065,0.0047677276,0.0002433755,0.102381535,0.4472997,0.012740643,0.4291174,0.00014997763],"about_ca_topic_score_codex":0.0010332844,"about_ca_topic_score_gemma":0.0011675656,"teacher_disagreement_score":0.04389743,"about_ca_system_score_codex":0.00046978882,"about_ca_system_score_gemma":0.0003613118,"threshold_uncertainty_score":0.14685148},"labels":[],"label_agreement":null},{"id":"W2100178828","doi":"10.1109/isit.2003.1228065","title":"Context-dependent vs. context-free: performance comparison of grammar-based codes","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Lossless compression; Computer science; Data compression; Redundancy (engineering); Context (archaeology); Ergodic theory; Theoretical computer science; Discrete mathematics; Mathematics; Algorithm","score_opus":0.024763140055883943,"score_gpt":0.26468807349067397,"score_spread":0.23992493343479002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100178828","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79011357,0.0071902582,0.19344224,0.0004026624,0.00022073014,0.00028142286,0.0003497856,0.0032664652,0.004732906],"genre_scores_gemma":[0.9291162,0.0011024034,0.068160005,0.00013985777,0.00007233299,0.0001111457,0.000394911,0.00011676777,0.0007863546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672747,0.000856191,0.00025310382,0.00045018035,0.0013991571,0.00031383775],"domain_scores_gemma":[0.98606676,0.007923657,0.00070579455,0.0022089477,0.0025969,0.0004980524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029660745,0.0008281213,0.00094043073,0.002678577,0.00069907564,0.001054478,0.0013922612,0.0016325511,0.0010319174],"category_scores_gemma":[0.020692527,0.00024322521,0.0003848288,0.0019162428,0.0010887645,0.002573349,0.0019407017,0.0008902738,0.000288368],"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":[0.006291787,0.0005809711,0.01653843,0.00081178587,0.00049780274,0.00034331833,0.0005258722,0.3686745,0.047865406,0.021484887,0.0023058315,0.5340795],"study_design_scores_gemma":[0.00021311309,0.0018341466,0.0040355627,0.00007846021,0.0001871145,0.0006634589,0.00017608116,0.8788838,0.10069464,0.010327317,0.0027808389,0.0001255188],"about_ca_topic_score_codex":0.0024780156,"about_ca_topic_score_gemma":0.0027014215,"teacher_disagreement_score":0.0029660745,"about_ca_system_score_codex":0.0011220445,"about_ca_system_score_gemma":0.0023557853,"threshold_uncertainty_score":0.015686274},"labels":[],"label_agreement":null},{"id":"W2100204172","doi":"10.1109/dcc.2008.101","title":"All-Match LZ77 Bit Recycling","year":2008,"lang":"en","type":"article","venue":"DCC","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Computer science; Redundancy (engineering); Multiplicity (mathematics); Exploit; Data compression; Algorithm; Computer hardware; Theoretical computer science; Arithmetic; Mathematics; Operating system; Computer security","score_opus":0.04280842797380473,"score_gpt":0.263671605095359,"score_spread":0.22086317712155423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100204172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019907067,0.020881092,0.445205,0.00519955,0.014707388,0.0019035096,0.01191379,0.03616818,0.44411448],"genre_scores_gemma":[0.1580198,0.01076863,0.3342485,0.0027448563,0.0034616084,0.0009931009,0.026097503,0.0064108996,0.45725498],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99863094,0.00016813424,0.000111588415,0.00022281645,0.00070940773,0.00015710275],"domain_scores_gemma":[0.9985682,0.0002862947,0.000113777365,0.00043505963,0.0005150792,0.00008159313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077984115,0.0012015611,0.001571921,0.0016930794,0.0010159004,0.0023238931,0.0021503607,0.00091561937,0.2513225],"category_scores_gemma":[0.005432789,0.00038470828,0.0005995187,0.0028034202,0.00088819,0.0027770745,0.00187224,0.0012194599,0.14197084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010431783,0.00010462484,0.0005125803,0.0017987498,0.000085021755,0.00039783493,0.0001384281,0.002820386,0.01805186,0.06664742,0.24292423,0.6654757],"study_design_scores_gemma":[0.0001067624,0.00018571918,0.0004225546,0.00023940559,0.000052435884,0.0006344286,0.000076602446,0.008494646,0.027736295,0.018242136,0.9437462,0.000062713865],"about_ca_topic_score_codex":0.0011488682,"about_ca_topic_score_gemma":0.0014155727,"teacher_disagreement_score":0.2513225,"about_ca_system_score_codex":0.0012072559,"about_ca_system_score_gemma":0.0013256845,"threshold_uncertainty_score":0.84075755},"labels":[],"label_agreement":null},{"id":"W2101436724","doi":"10.20381/ruor-4947","title":"ModuleInducer: Automating the Extraction of Knowledge from Biological Sequences","year":2011,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Bottleneck; Data mining; Knowledge extraction; Set (abstract data type); Biological data; Java; Information retrieval; Artificial intelligence; Machine learning; Bioinformatics; Biology; Programming language","score_opus":0.010411552380357104,"score_gpt":0.18439191043338318,"score_spread":0.17398035805302609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101436724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053299214,0.00017111466,0.9148913,0.00016974514,0.000041663385,0.00022616882,0.0022794823,0.07524672,0.0016439521],"genre_scores_gemma":[0.033466205,0.0003574714,0.9491629,0.00033937686,0.000049759303,0.0005630926,0.008894397,0.0034565784,0.0037101519],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984409,0.00029946727,0.00012665,0.0005079803,0.00053123257,0.000093759234],"domain_scores_gemma":[0.99785846,0.0014115552,0.00013774316,0.00025377987,0.00028039457,0.000058094643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021185593,0.0018582729,0.0009661217,0.0022817783,0.0005113271,0.0017360671,0.0027493525,0.0009243459,0.012344492],"category_scores_gemma":[0.0049593947,0.00088855095,0.00228933,0.0011402266,0.0007679716,0.0027220622,0.00213718,0.0016221915,0.008607515],"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":[0.00048989843,0.00041151364,0.0038659198,0.0025483286,0.00029502576,0.000785556,0.0007415773,0.013709234,0.08659604,0.015932092,0.043902293,0.8307226],"study_design_scores_gemma":[0.00020181578,0.00038414155,0.0048280507,0.00042197498,0.0002478653,0.0012970665,0.00023917879,0.46338466,0.299208,0.062088914,0.1675175,0.00018088614],"about_ca_topic_score_codex":0.0015845418,"about_ca_topic_score_gemma":0.0022440027,"teacher_disagreement_score":0.012344492,"about_ca_system_score_codex":0.00075117854,"about_ca_system_score_gemma":0.0020016723,"threshold_uncertainty_score":0.041296422},"labels":[],"label_agreement":null},{"id":"W2101637789","doi":"10.1109/26.939851","title":"Single parity check product codes","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Algorithms and Data Compression","field":"Computer Science","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":"University of Victoria","funders":"","keywords":"Computer science","score_opus":0.06367548601671887,"score_gpt":0.29474189126887845,"score_spread":0.2310664052521596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101637789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.155909,0.0028295624,0.821845,0.00039683608,0.0001943672,0.00010715648,0.00033611374,0.0008802431,0.017501686],"genre_scores_gemma":[0.9012874,0.0008722052,0.09410259,0.0001410311,0.00008956116,0.000083730694,0.00023807657,0.000065914806,0.0031195008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985777,0.0003859706,0.000047506015,0.00020054584,0.0006149263,0.00017325747],"domain_scores_gemma":[0.995749,0.0021726214,0.00033959304,0.0005607418,0.0010846312,0.00009340876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011943813,0.00072151463,0.0006986594,0.00079300144,0.00052539597,0.0013407359,0.00095086725,0.00081116107,0.0021313427],"category_scores_gemma":[0.006423314,0.00023410968,0.00031790437,0.0009885546,0.000896124,0.001421414,0.0008561082,0.00067246467,0.00077098166],"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":[0.0006994433,0.000085450825,0.0029945374,0.0003837409,0.0001313274,0.00084312976,0.00015745105,0.48102143,0.025454197,0.307894,0.0036754168,0.17665976],"study_design_scores_gemma":[0.000043561693,0.0002843422,0.00043167782,0.00004402477,0.000038363807,0.0009216766,0.000023441127,0.9014005,0.017217468,0.07529222,0.004260328,0.000042400963],"about_ca_topic_score_codex":0.00087172684,"about_ca_topic_score_gemma":0.0005416782,"teacher_disagreement_score":0.0021313427,"about_ca_system_score_codex":0.0005899382,"about_ca_system_score_gemma":0.00086374325,"threshold_uncertainty_score":0.007130027},"labels":[],"label_agreement":null},{"id":"W2101649702","doi":"10.1109/tcbb.2008.99","title":"Finding the Nearest Neighbors in Biological Databases Using Less Distance Computations","year":2008,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Science and Technology of China; University of Alberta","keywords":"Nearest neighbor search; Computer science; Pruning; Speedup; Computation; Similarity (geometry); k-nearest neighbors algorithm; Tree (set theory); Pairwise comparison; Sequence (biology); Preprocessor; k-d tree; Data mining; Sequence database; Algorithm; Artificial intelligence; Mathematics; Image (mathematics); Gene; Combinatorics","score_opus":0.10977135957460901,"score_gpt":0.3209844104495188,"score_spread":0.2112130508749098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101649702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23634014,0.0028476834,0.75100565,0.0006072445,0.00016415377,0.00018445394,0.0007045728,0.004383573,0.0037624585],"genre_scores_gemma":[0.26760265,0.0008023288,0.727045,0.00010878925,0.00005890709,0.00017248034,0.0016469652,0.0001359758,0.0024269014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760544,0.000559699,0.00023088201,0.00047402157,0.0010205935,0.000109403976],"domain_scores_gemma":[0.99600655,0.0019189354,0.00035208324,0.0011211865,0.0004935748,0.00010769355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014796723,0.0006898045,0.0015156022,0.0032722934,0.0011034302,0.0017354335,0.00178484,0.0010587167,0.0025277536],"category_scores_gemma":[0.010553506,0.00057768525,0.00069278426,0.0039718207,0.0006084771,0.0047380663,0.0016590379,0.00073952187,0.0016806673],"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":[0.0012160073,0.00041804972,0.0070029125,0.0004581928,0.00018597742,0.00032473326,0.0006013435,0.1392228,0.029199243,0.017287638,0.0068221935,0.7972608],"study_design_scores_gemma":[0.00023252364,0.00023555597,0.0030762719,0.0000475264,0.00007869133,0.0007372502,0.00038320766,0.9364331,0.02064535,0.028904587,0.009174645,0.00005123141],"about_ca_topic_score_codex":0.005796591,"about_ca_topic_score_gemma":0.00885406,"teacher_disagreement_score":0.005796591,"about_ca_system_score_codex":0.0006963753,"about_ca_system_score_gemma":0.001382902,"threshold_uncertainty_score":0.011525691},"labels":[],"label_agreement":null},{"id":"W2101882219","doi":"10.1007/978-3-540-70600-7_7","title":"Searching for Supermaximal Repeats in Large DNA Sequences","year":2008,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Suffix; Suffix tree; Computer science; Index (typography); Tree (set theory); Algorithm; Generalized suffix tree; Computational biology; Biology; Mathematics; Data structure; Combinatorics; Programming language; Linguistics","score_opus":0.055909415260263,"score_gpt":0.31741569062001623,"score_spread":0.26150627535975324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101882219","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46232033,0.003441143,0.52112466,0.0005627458,0.00014046926,0.00010776769,0.0014252054,0.0029440648,0.007933616],"genre_scores_gemma":[0.4837619,0.0013374512,0.5043687,0.00023099399,0.00012293506,0.00010579327,0.0033902326,0.00039296492,0.0062889648],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99967206,0.000052832354,0.000031269316,0.00010950961,0.00011048319,0.000023976021],"domain_scores_gemma":[0.998616,0.0008284214,0.0001876577,0.00020115306,0.00009295091,0.00007386886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048399897,0.00041380635,0.0006959431,0.0011597229,0.0005294313,0.00060134765,0.0011402202,0.0007839735,0.0044642924],"category_scores_gemma":[0.002865523,0.00044343484,0.0004637058,0.0018756462,0.0004169724,0.0017112276,0.00075705914,0.00068868685,0.001360233],"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":[0.0011332114,0.00016774025,0.010062659,0.0013055872,0.0001653917,0.0014722754,0.0008749729,0.023226107,0.26944178,0.04747844,0.008669605,0.6360022],"study_design_scores_gemma":[0.00015441792,0.00066279713,0.008408703,0.00024182191,0.00022865868,0.005529262,0.0009787065,0.44823822,0.26815528,0.2288877,0.038399626,0.000114759016],"about_ca_topic_score_codex":0.00025758022,"about_ca_topic_score_gemma":0.0008707025,"teacher_disagreement_score":0.0044642924,"about_ca_system_score_codex":0.00022692564,"about_ca_system_score_gemma":0.00047045652,"threshold_uncertainty_score":0.01493454},"labels":[],"label_agreement":null},{"id":"W2102292102","doi":"10.1109/lcomm.2011.011811.102279","title":"Improved Algorithm for Constructing Constrained Codes with State-Independent Decoding","year":2011,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Algorithms and Data Compression","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":"Decoding methods; Computer science; Algorithm; Sequential decoding; BCJR algorithm; Sequence (biology); State (computer science); List decoding; Berlekamp–Welch algorithm; Block code; Concatenated error correction code","score_opus":0.04387124985788549,"score_gpt":0.26809577302622856,"score_spread":0.22422452316834307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102292102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029653092,0.00005616528,0.9949969,0.00006157406,0.00002595349,0.000051077557,0.000056368222,0.00034507996,0.0014415616],"genre_scores_gemma":[0.047305632,0.00013309286,0.94942474,0.00008816555,0.000025318215,0.00020502896,0.00029767453,0.00013879662,0.0023814994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904245,0.00020365072,0.0000738768,0.00014312885,0.00046514376,0.000071703886],"domain_scores_gemma":[0.9983909,0.00068955147,0.00008637188,0.00033707067,0.00045011102,0.00004597814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008080751,0.00097047526,0.00067628967,0.0010473487,0.000606087,0.0007452065,0.0010134773,0.0010597802,0.0035903428],"category_scores_gemma":[0.0040127547,0.00037435978,0.0006008281,0.0010639897,0.0007176607,0.0012186911,0.0017424942,0.0017403623,0.001499046],"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":[0.00032422048,0.00016211062,0.0007319899,0.00027874514,0.00009039196,0.00029670933,0.0002921015,0.1984067,0.05004801,0.19898541,0.0072271,0.5431565],"study_design_scores_gemma":[0.00013168257,0.00012187871,0.0002843535,0.00005389398,0.000042047475,0.0003874997,0.000031450953,0.8526833,0.04971107,0.076869905,0.019591318,0.00009166259],"about_ca_topic_score_codex":0.0015141936,"about_ca_topic_score_gemma":0.0022909958,"teacher_disagreement_score":0.0035903428,"about_ca_system_score_codex":0.000582544,"about_ca_system_score_gemma":0.0018362402,"threshold_uncertainty_score":0.012010872},"labels":[],"label_agreement":null},{"id":"W2102525660","doi":"10.1109/isit.2008.4595134","title":"Improving LZ77 bit recycling using all matches","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Lossless compression; Redundancy (engineering); Computer science; Bit (key); Exploit; Algorithm; Data compression; Multiplicity (mathematics); Mathematics; Computer network; Operating system","score_opus":0.07083278689956192,"score_gpt":0.2698876164155146,"score_spread":0.1990548295159527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102525660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2224542,0.0031496964,0.7496923,0.0005959056,0.00031804008,0.00030534205,0.0003970121,0.012429106,0.01065842],"genre_scores_gemma":[0.4405605,0.0014229931,0.5405183,0.00047401944,0.00020850322,0.00021111153,0.0012989521,0.0011605849,0.014145097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969903,0.00045830893,0.00030069047,0.0002923205,0.0015859373,0.00037233613],"domain_scores_gemma":[0.9947305,0.0013157516,0.00056747283,0.0021318651,0.001125341,0.00012900664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021440824,0.0014306764,0.0015558241,0.003119387,0.0013221358,0.0018001077,0.0020153238,0.001363976,0.005651721],"category_scores_gemma":[0.011722185,0.00044185692,0.0011175026,0.0034689312,0.0010997317,0.004723547,0.002612045,0.0013599045,0.0041348655],"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":[0.0018209107,0.00033791328,0.003073923,0.00043429312,0.00011475516,0.00042222365,0.00053960865,0.023984417,0.099216856,0.024989316,0.0071962196,0.8378696],"study_design_scores_gemma":[0.00026428924,0.0012344162,0.0021629976,0.00017902361,0.00030322679,0.0025976077,0.0004328684,0.29272565,0.62716407,0.019240752,0.053495605,0.00019941857],"about_ca_topic_score_codex":0.0017589395,"about_ca_topic_score_gemma":0.0014573919,"teacher_disagreement_score":0.005651721,"about_ca_system_score_codex":0.0008428776,"about_ca_system_score_gemma":0.0016493173,"threshold_uncertainty_score":0.018906891},"labels":[],"label_agreement":null},{"id":"W2102679851","doi":"10.14778/2350229.2350249","title":"Efficient indexing and querying over syntactically annotated trees","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Search engine indexing; Parsing; Coding (social sciences); Set (abstract data type); Natural language; Index (typography); Tree (set theory); Information retrieval; Artificial intelligence; Natural language processing; Mathematics","score_opus":0.010587261327778642,"score_gpt":0.2312921184450198,"score_spread":0.22070485711724114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102679851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11353021,0.0011881496,0.8592727,0.0007572629,0.0001095689,0.00032449767,0.0058009336,0.013534096,0.0054825633],"genre_scores_gemma":[0.3335313,0.0010165971,0.6451883,0.00026311463,0.00016155775,0.00036473142,0.015297513,0.0010240956,0.003152873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740285,0.00045977012,0.00038221118,0.0003520517,0.0011952457,0.00020774416],"domain_scores_gemma":[0.9907721,0.0045509753,0.00069332734,0.0022760888,0.001503553,0.0002039472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016302887,0.000713146,0.0014848433,0.003568674,0.0010268644,0.0023199033,0.002282323,0.0010804661,0.002330263],"category_scores_gemma":[0.014498284,0.00053044,0.0008374597,0.007581635,0.0009992346,0.0072433134,0.0022357192,0.0011876498,0.0014507109],"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":[0.0009635679,0.00045700773,0.0074449885,0.0011357936,0.00013607995,0.0009163016,0.0018173632,0.062579766,0.12035946,0.08398446,0.046746112,0.6734591],"study_design_scores_gemma":[0.0001298993,0.00023238955,0.0029967981,0.00010295067,0.00010363994,0.0008591226,0.0008231554,0.76114273,0.076853864,0.13577974,0.020854203,0.00012151475],"about_ca_topic_score_codex":0.00316393,"about_ca_topic_score_gemma":0.00525225,"teacher_disagreement_score":0.003568674,"about_ca_system_score_codex":0.00094007957,"about_ca_system_score_gemma":0.002475032,"threshold_uncertainty_score":0.008621931},"labels":[],"label_agreement":null},{"id":"W2102779471","doi":"10.1109/icdar.2003.1227757","title":"An evolutionary algorithm for general symbol segmentation","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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; University of Guelph","funders":"","keywords":"Symbol (formal); Computer science; Segmentation; Artificial intelligence; Algorithm design; Algorithm; Programming language","score_opus":0.012879412091901063,"score_gpt":0.2813944508348324,"score_spread":0.2685150387429313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102779471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024401865,0.00010396921,0.99562895,0.000041482654,0.000031622385,0.000024466832,0.000017626327,0.00026028082,0.0014513187],"genre_scores_gemma":[0.057324234,0.00018979918,0.93730825,0.000076995486,0.000045409106,0.00020492829,0.00013793037,0.00014943811,0.0045630676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993968,0.00014384162,0.000044274086,0.00017036404,0.00019569829,0.000048881666],"domain_scores_gemma":[0.9994543,0.00024581188,0.000032528358,0.000072845796,0.00016608293,0.000028426637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008809449,0.00067777437,0.00086803845,0.0011409584,0.0007679529,0.00090700336,0.0013073375,0.0014875238,0.004714741],"category_scores_gemma":[0.002687626,0.0003350146,0.0006148319,0.0011936375,0.0010058671,0.0013187301,0.0012287229,0.0011804833,0.0011827743],"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":[0.00009365009,0.00005165826,0.00070432294,0.00014360371,0.00006355213,0.00019671608,0.00024568298,0.31148854,0.013271979,0.118778735,0.0051692184,0.5497924],"study_design_scores_gemma":[0.000026332713,0.000050117465,0.00020808743,0.000022257016,0.000021790276,0.00015306866,0.000020171785,0.94874984,0.0023935076,0.03779714,0.010536281,0.000021371055],"about_ca_topic_score_codex":0.0016297355,"about_ca_topic_score_gemma":0.0014822904,"teacher_disagreement_score":0.004714741,"about_ca_system_score_codex":0.0006789445,"about_ca_system_score_gemma":0.0007200749,"threshold_uncertainty_score":0.015772343},"labels":[],"label_agreement":null},{"id":"W2102842712","doi":"10.1109/icassp.1989.266392","title":"Combined source-channel coding","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Encoder; Binary number; Binary symmetric channel; Computer science; Coding (social sciences); Algorithm; Channel code; BCH code; Channel (broadcasting); Source code; Variable-length code; Decoding methods; Binary code; Theoretical computer science; Mathematics; Arithmetic; Telecommunications; Statistics; Programming language","score_opus":0.03677596805324048,"score_gpt":0.2750517574361826,"score_spread":0.2382757893829421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102842712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014422594,0.0003024194,0.9929603,0.00008068144,0.00012614147,0.000060225786,0.000096474956,0.00048639547,0.0044451864],"genre_scores_gemma":[0.13678272,0.0009445001,0.84133035,0.0002470497,0.00027623354,0.0003521435,0.0005905995,0.00019710648,0.019279245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796164,0.00039941038,0.00006850841,0.00028577694,0.0011266387,0.00015800504],"domain_scores_gemma":[0.9985274,0.00041485328,0.00006549082,0.0004204907,0.00052627194,0.000045501645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010642603,0.0009686476,0.0010892214,0.0016849859,0.00063092227,0.0016074673,0.001579515,0.0011896612,0.006818315],"category_scores_gemma":[0.0022589893,0.00043643007,0.000911666,0.0017890357,0.0008266498,0.0017507317,0.0028207465,0.0016470036,0.0032783411],"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":[0.0004502428,0.0001502275,0.00052802224,0.00044003956,0.00019852491,0.0004272198,0.00019472705,0.11352978,0.043892972,0.2076381,0.013183006,0.6193672],"study_design_scores_gemma":[0.00007820887,0.00024068465,0.00032654352,0.000121197554,0.00010218723,0.00093417335,0.000059001264,0.7973484,0.045431055,0.113790445,0.041476987,0.00009111353],"about_ca_topic_score_codex":0.0010405484,"about_ca_topic_score_gemma":0.002062189,"teacher_disagreement_score":0.006818315,"about_ca_system_score_codex":0.0006418172,"about_ca_system_score_gemma":0.0011683796,"threshold_uncertainty_score":0.022809565},"labels":[],"label_agreement":null},{"id":"W2103291633","doi":"10.1109/dcc.1991.213370","title":"Models for compression in full-text retrieval systems","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Calgary","funders":"","keywords":"Lexicon; Computer science; Word (group theory); Natural language processing; Coding (social sciences); Artificial intelligence; Compression (physics); Information retrieval; Data compression; Mathematics; Statistics","score_opus":0.049789430890541074,"score_gpt":0.25274677520017247,"score_spread":0.2029573443096314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103291633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024574537,0.0018909372,0.9562918,0.0017921998,0.00018137589,0.0002639303,0.00060096016,0.0014463437,0.012957889],"genre_scores_gemma":[0.73304456,0.004146353,0.22031756,0.0007537895,0.00040865742,0.0013796833,0.0016547785,0.0006021954,0.03769242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833375,0.00060117594,0.00011473097,0.00021668604,0.00056407705,0.00016960877],"domain_scores_gemma":[0.9950413,0.0034837744,0.00023764063,0.00046502711,0.0006854962,0.000086881446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001887413,0.0010094354,0.0012513519,0.0013735828,0.00081402564,0.0031764447,0.0019506856,0.002400599,0.008009781],"category_scores_gemma":[0.011928716,0.00067198894,0.001035693,0.0013993204,0.0016820488,0.0060707224,0.0013672307,0.0017194157,0.0030173627],"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":[0.00020387047,0.00007434496,0.00050836545,0.00020660911,0.000042809927,0.00019977498,0.00033833305,0.7113449,0.0016864834,0.2406499,0.004317751,0.04042684],"study_design_scores_gemma":[0.000026001468,0.000029532248,0.00007387939,0.000018652525,0.000012076628,0.00006669904,0.000028785253,0.9179722,0.00060493086,0.07843195,0.0027179336,0.000017305421],"about_ca_topic_score_codex":0.0066216285,"about_ca_topic_score_gemma":0.00425345,"teacher_disagreement_score":0.008009781,"about_ca_system_score_codex":0.0023778002,"about_ca_system_score_gemma":0.0012919534,"threshold_uncertainty_score":0.026795447},"labels":[],"label_agreement":null},{"id":"W2103495476","doi":"10.1504/ijbra.2007.011836","title":"Efficient composite pattern finding from monad patterns","year":2006,"lang":"en","type":"article","venue":"International Journal of Bioinformatics Research and Applications","topic":"Algorithms and Data Compression","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":"Monad (category theory); Computer science; Insignificance; Task (project management); Composite number; Theoretical computer science; Algorithm; Mathematics; Discrete mathematics; Psychology; Engineering","score_opus":0.03164951129843416,"score_gpt":0.33691061368342184,"score_spread":0.3052611023849877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103495476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11117355,0.0006131219,0.87800676,0.0003131661,0.000083869585,0.00018681979,0.0010406484,0.0064032753,0.0021787742],"genre_scores_gemma":[0.2226003,0.00029029473,0.76909083,0.00010927167,0.000058149366,0.00014449304,0.0040503987,0.000328416,0.0033279676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883825,0.0001722079,0.00015082091,0.00030422324,0.0003985817,0.00013598],"domain_scores_gemma":[0.99603784,0.0016364041,0.0004747821,0.0010750529,0.000566397,0.00020947459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009194867,0.0008381599,0.001307495,0.0043187155,0.0008226599,0.0018059055,0.0014353127,0.0008251974,0.0036423095],"category_scores_gemma":[0.0057802163,0.0004911199,0.0011780468,0.0040432434,0.00053691235,0.00316504,0.0020116447,0.0010025969,0.001522689],"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":[0.00081802154,0.00025020321,0.0110043455,0.0005702471,0.0001664492,0.00060482154,0.00041253664,0.013213522,0.039859794,0.016315922,0.007010862,0.90977323],"study_design_scores_gemma":[0.00014803343,0.00034848307,0.007844546,0.00008348015,0.0001512869,0.0032293487,0.0007489069,0.8206453,0.05708776,0.09317746,0.016435102,0.000100360536],"about_ca_topic_score_codex":0.0015450617,"about_ca_topic_score_gemma":0.0027633049,"teacher_disagreement_score":0.0043187155,"about_ca_system_score_codex":0.00038671817,"about_ca_system_score_gemma":0.0012473328,"threshold_uncertainty_score":0.012184799},"labels":[],"label_agreement":null},{"id":"W2104409964","doi":"10.1007/11527954_18","title":"Search Engines and Web Information Retrieval","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Search engine; Human–computer information retrieval; World Wide Web; Web search engine; Adversarial information retrieval; Web crawler; Metasearch engine; Web intelligence; Cognitive models of information retrieval; Web modeling; Web search query; Web page","score_opus":0.012759789983990123,"score_gpt":0.2401844063563452,"score_spread":0.22742461637235506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104409964","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014053654,0.40468872,0.2275549,0.011165176,0.002569146,0.000121833364,0.0012928245,0.0025317317,0.336022],"genre_scores_gemma":[0.17293034,0.266209,0.10944232,0.0026418357,0.0053572864,0.00023864592,0.0036425549,0.00076632295,0.43877164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99949646,0.00013982973,0.000031075957,0.00005465309,0.00023775724,0.00004027173],"domain_scores_gemma":[0.9992379,0.00047881508,0.000050714392,0.0000912819,0.00011670413,0.000024595218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005404024,0.000695779,0.0009540057,0.0027525537,0.0005889761,0.0038973265,0.0009150883,0.0016201239,0.023505265],"category_scores_gemma":[0.003009681,0.00055945705,0.00038278569,0.0072577256,0.0010142298,0.0081011485,0.00085808703,0.001271534,0.010231199],"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":[0.000077620374,0.00007262431,0.000318436,0.00080636295,0.000045415072,0.00015305575,0.00020918065,0.004826873,0.0018433977,0.46714112,0.112020925,0.41248497],"study_design_scores_gemma":[0.000023419958,0.000039065268,0.0005823015,0.00031594458,0.000056621382,0.00067432236,0.00020609258,0.021899967,0.0017348545,0.6378201,0.33661184,0.000035497455],"about_ca_topic_score_codex":0.0022859897,"about_ca_topic_score_gemma":0.0028495926,"teacher_disagreement_score":0.023505265,"about_ca_system_score_codex":0.0008883965,"about_ca_system_score_gemma":0.0006792147,"threshold_uncertainty_score":0.07863295},"labels":[],"label_agreement":null},{"id":"W2104971205","doi":"10.1109/tsmcb.2005.861860","title":"On optimizing syntactic pattern recognition using tries and AI-based heuristic-search strategies","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Benchmark (surveying); Beam search; Heuristic; A priori and a posteriori; String (physics); String searching algorithm; Algorithm; Computer science; Search tree; Matching (statistics); Search algorithm; Levenshtein distance; Tree (set theory); Mathematics; Combinatorics; Artificial intelligence; Pattern matching; Data structure; Statistics","score_opus":0.03161134660042626,"score_gpt":0.25953851493120134,"score_spread":0.2279271683307751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104971205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03490215,0.00054842955,0.95902294,0.00017799817,0.000032017324,0.0000939551,0.000052167423,0.001007638,0.004162749],"genre_scores_gemma":[0.26608932,0.00047826327,0.72954035,0.00026816537,0.000046554513,0.00033023162,0.00023747885,0.0002406575,0.0027689578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923396,0.00029183726,0.000058050082,0.00011901498,0.00022320097,0.0000739207],"domain_scores_gemma":[0.99805295,0.0013642864,0.00015036152,0.00015706051,0.00023607344,0.000039258317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013949244,0.0010417025,0.0011150052,0.0011909764,0.00032449185,0.0011031628,0.0013935334,0.0011357745,0.0025015634],"category_scores_gemma":[0.0044292314,0.0005283426,0.00061231264,0.0014764891,0.0010531618,0.001633152,0.0009680137,0.0006515203,0.0007960474],"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":[0.00022268706,0.00009646429,0.0013975281,0.00026144978,0.000110697525,0.000111198526,0.00015601565,0.7421343,0.004874746,0.025961714,0.0015268968,0.22314623],"study_design_scores_gemma":[0.00002416831,0.00007799119,0.00012856378,0.000016322963,0.000017121823,0.00004478837,0.000037004906,0.9909018,0.0012885439,0.00665529,0.0008014635,0.0000069223825],"about_ca_topic_score_codex":0.0028246455,"about_ca_topic_score_gemma":0.0035040877,"teacher_disagreement_score":0.0028246455,"about_ca_system_score_codex":0.0006213537,"about_ca_system_score_gemma":0.001403201,"threshold_uncertainty_score":0.008368611},"labels":[],"label_agreement":null},{"id":"W2105013340","doi":"10.1109/icsmc.1995.537926","title":"Pattern recognition of strings containing traditional and generalized transposition errors","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"String (physics); Transposition (logic); Alphabet; Substitution (logic); Scheme (mathematics); Computer science; String searching algorithm; Edit distance; Algorithm; Artificial intelligence; Pattern matching; Mathematics; Programming language","score_opus":0.06457796811252833,"score_gpt":0.22804036429280422,"score_spread":0.1634623961802759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105013340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31264788,0.00039565947,0.6847408,0.00019954027,0.00008148854,0.000028875582,0.00012386002,0.0008018751,0.0009800738],"genre_scores_gemma":[0.6531181,0.00041092758,0.34244958,0.00008168967,0.00007073677,0.000042986958,0.0004845081,0.00012473793,0.003216754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993637,0.00011715464,0.00006850137,0.0001901261,0.00020653392,0.000053873686],"domain_scores_gemma":[0.99731135,0.0013661399,0.00044749273,0.00044897644,0.00037482526,0.000051165276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055267615,0.00036514018,0.0008670689,0.0005071278,0.00022077111,0.00062352436,0.0007388699,0.0007232822,0.00082402775],"category_scores_gemma":[0.0053893146,0.00020182804,0.00029359976,0.0009907864,0.0006646041,0.0012739835,0.00050419726,0.00046417673,0.000495547],"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":[0.00079021323,0.00007848548,0.005222948,0.0004305999,0.00008649424,0.001455494,0.00055082055,0.09866621,0.17206234,0.016997047,0.0021646544,0.7014947],"study_design_scores_gemma":[0.000032340973,0.000294175,0.0036955622,0.000026516938,0.00005429255,0.001467199,0.00030886297,0.79586464,0.16249736,0.030366922,0.0053548864,0.000037257258],"about_ca_topic_score_codex":0.00032603333,"about_ca_topic_score_gemma":0.00041865,"teacher_disagreement_score":0.0008670689,"about_ca_system_score_codex":0.00019728074,"about_ca_system_score_gemma":0.00020773766,"threshold_uncertainty_score":0.002922833},"labels":[],"label_agreement":null},{"id":"W2105689451","doi":"10.1109/icpr.1988.28218","title":"Signature verification from position, velocity and acceleration signals: a comparative study","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Acceleration; Signature (topology); Representation (politics); SIGNAL (programming language); Computer science; Dynamic time warping; Position (finance); Matching (statistics); Pattern recognition (psychology); Artificial intelligence; Biometrics; Algorithm; Mathematics; Statistics; Physics; Programming language; Geometry","score_opus":0.035710051397647234,"score_gpt":0.2874479886251043,"score_spread":0.2517379372274571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105689451","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357688,0.0060598743,0.34769517,0.00041239124,0.00022026282,0.000119824275,0.00028385717,0.0027359303,0.0067039956],"genre_scores_gemma":[0.90860075,0.0013782504,0.08645653,0.00006109033,0.00012489624,0.000040227114,0.00063824997,0.00019238853,0.0025076896],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99535394,0.0014237185,0.00026269534,0.00030480867,0.0024137832,0.0002410051],"domain_scores_gemma":[0.98782164,0.00869639,0.00047727922,0.0006475966,0.0021680095,0.00018907992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005177148,0.0005555636,0.0008642631,0.003622749,0.00032651826,0.0014460076,0.0007503998,0.0011491189,0.0023730858],"category_scores_gemma":[0.015649958,0.00023456305,0.00044706202,0.0019597895,0.00042443283,0.0018584118,0.0005218434,0.00034308818,0.0013543403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028086086,0.0001500373,0.010468979,0.00032017817,0.00016436091,0.000249321,0.00015490987,0.017523812,0.060933545,0.001764225,0.0014411495,0.904021],"study_design_scores_gemma":[0.00025323525,0.0039294716,0.043384567,0.00010571245,0.0003118663,0.0045973007,0.0004478151,0.6848169,0.25049168,0.0025881429,0.008898515,0.0001747864],"about_ca_topic_score_codex":0.00080076815,"about_ca_topic_score_gemma":0.0006679104,"teacher_disagreement_score":0.005177148,"about_ca_system_score_codex":0.00031744404,"about_ca_system_score_gemma":0.00039518546,"threshold_uncertainty_score":0.027379751},"labels":[],"label_agreement":null},{"id":"W2105768287","doi":"10.1109/dcc.2008.25","title":"List Update Algorithms for Data Compression","year":2008,"lang":"en","type":"article","venue":"DCC","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Computer science; Algorithm; Data compression; Locality of reference; Compression (physics); Locality; Subroutine; Construct (python library); Compression ratio; Parallel computing; Cache; Programming language","score_opus":0.1267360926996233,"score_gpt":0.32464320323652107,"score_spread":0.19790711053689777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105768287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004248885,0.0034694914,0.97686267,0.00072017335,0.0003030495,0.00035423084,0.0006253398,0.005670264,0.007745927],"genre_scores_gemma":[0.06774476,0.0029747463,0.9152485,0.0006149379,0.0005103181,0.00083817996,0.0021173912,0.001133854,0.0088173],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958352,0.0007798952,0.00046620352,0.0004985775,0.0021967746,0.00022335371],"domain_scores_gemma":[0.99087536,0.003023828,0.0005167507,0.003557509,0.0019023152,0.00012421983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026947202,0.0013594908,0.0010293699,0.0041723894,0.00131602,0.0038567171,0.002882983,0.0018471306,0.01303574],"category_scores_gemma":[0.016569797,0.00057317695,0.000914027,0.0068435897,0.0015105818,0.0066662375,0.002987157,0.002572321,0.008135371],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028706255,0.00011477252,0.00086599856,0.00049904664,0.00006249626,0.00007743053,0.0002153726,0.017350305,0.0068215784,0.14871341,0.034905203,0.7900872],"study_design_scores_gemma":[0.00021073599,0.0003267112,0.0010716952,0.00033198766,0.00012362683,0.0014466563,0.00023775373,0.42358637,0.05659315,0.32971987,0.18619402,0.00015743244],"about_ca_topic_score_codex":0.0016311031,"about_ca_topic_score_gemma":0.0016794205,"teacher_disagreement_score":0.01303574,"about_ca_system_score_codex":0.0016784471,"about_ca_system_score_gemma":0.0015713538,"threshold_uncertainty_score":0.043608904},"labels":[],"label_agreement":null},{"id":"W2105932777","doi":"10.13034/cysj-2013-006","title":"Linear Convection Sort<sup>1</sup>","year":2013,"lang":"en","type":"article","venue":"Journal of Student Science and Technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"sort; Sorting; Sorting algorithm; Computer science; Set (abstract data type); Algorithm; Time complexity; Data structure; Code (set theory); Data set; Theoretical computer science; Artificial intelligence; Database","score_opus":0.01046605087057701,"score_gpt":0.2701577135285104,"score_spread":0.2596916626579334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105932777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023799594,0.005426197,0.7896441,0.006481969,0.0035458219,0.0011009857,0.012836626,0.035967868,0.121196866],"genre_scores_gemma":[0.16080117,0.005169139,0.57094437,0.005079035,0.0017188693,0.0010590383,0.024586437,0.0077944743,0.22284745],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866915,0.00012050222,0.00013481047,0.00017330887,0.00072348444,0.00017877617],"domain_scores_gemma":[0.9965462,0.0011496567,0.00032389496,0.0008230361,0.0009960581,0.00016126464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012825785,0.0010282148,0.0010914915,0.0013746403,0.0013559368,0.0038550687,0.0021944153,0.0010062059,0.06802391],"category_scores_gemma":[0.0042998083,0.00056142925,0.0012356485,0.003737014,0.0014036809,0.0042841295,0.0017995661,0.0017323244,0.033036817],"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":[0.0012464473,0.000090589354,0.0020484454,0.0014299907,0.00008108746,0.00038883992,0.0002780451,0.0069255405,0.013080539,0.08120761,0.22562996,0.6675929],"study_design_scores_gemma":[0.0001341718,0.00042427063,0.0017954352,0.0002808257,0.00012847957,0.001545663,0.00040751405,0.06605857,0.0802198,0.085726194,0.76314557,0.00013358858],"about_ca_topic_score_codex":0.0030047728,"about_ca_topic_score_gemma":0.004207751,"teacher_disagreement_score":0.06802391,"about_ca_system_score_codex":0.0019082095,"about_ca_system_score_gemma":0.0026280757,"threshold_uncertainty_score":0.22756267},"labels":[],"label_agreement":null},{"id":"W2106159865","doi":"10.1109/tmm.2003.822793","title":"Globally Optimal Uneven Error-Protected Packetization of Scalable Code Streams","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Erasure; Network packet; Algorithm; Scalability; Payload (computing); Binary logarithm; Discrete mathematics; Mathematics; Computer network","score_opus":0.01642296285742713,"score_gpt":0.2544252547356321,"score_spread":0.23800229187820499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106159865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016826078,0.000081836486,0.98183674,0.000057924048,0.000014170471,0.000035564208,0.000024264735,0.00039041744,0.0007329856],"genre_scores_gemma":[0.45138097,0.00022775502,0.5453911,0.00009750985,0.000039415845,0.00014183366,0.00022749322,0.00018931454,0.002304614],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993562,0.00015138125,0.000040333987,0.00011943957,0.00023584126,0.000096668766],"domain_scores_gemma":[0.99886996,0.0005622035,0.00012818062,0.0002559109,0.00013782916,0.000045855442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010152922,0.00077074656,0.00092416664,0.00048045703,0.00039242505,0.00076697406,0.0011045166,0.00055204914,0.0015832627],"category_scores_gemma":[0.004254486,0.00029260747,0.00043739946,0.00058484194,0.0008066238,0.0019627437,0.0018230833,0.0011310951,0.00028069064],"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":[0.0003002759,0.000059108097,0.00063823664,0.000094034294,0.00003534835,0.00010626174,0.00016521972,0.70002365,0.014186018,0.0437157,0.002024075,0.23865208],"study_design_scores_gemma":[0.000013885388,0.0000420456,0.000064642954,0.0000062195313,0.0000043532596,0.000032664182,0.000027098054,0.9788399,0.008332672,0.011834296,0.0007953988,0.000006780143],"about_ca_topic_score_codex":0.0010305223,"about_ca_topic_score_gemma":0.0006656218,"teacher_disagreement_score":0.0015832627,"about_ca_system_score_codex":0.00079620397,"about_ca_system_score_gemma":0.0008405253,"threshold_uncertainty_score":0.005776882},"labels":[],"label_agreement":null},{"id":"W2106579389","doi":"10.1109/synasc.2009.48","title":"A Depth-first Algorithm to Reduce Graphs in Linear Time","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Time complexity; Vertex (graph theory); Combinatorics; Reduction (mathematics); Algorithm; Graph; Graph algorithms; Computer science; Discrete mathematics; Mathematics; Geometry","score_opus":0.01251942052605064,"score_gpt":0.2610468861688211,"score_spread":0.24852746564277045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106579389","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012425831,0.0011785388,0.9647227,0.00079851603,0.00015889105,0.00062162074,0.0009493045,0.010636441,0.008508092],"genre_scores_gemma":[0.040655583,0.00032776318,0.9489821,0.0002620353,0.00005524546,0.00042417386,0.0019370209,0.00060327695,0.006752845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99869066,0.00016725427,0.00009713736,0.00028167976,0.00054517837,0.00021807871],"domain_scores_gemma":[0.9986854,0.0005303692,0.00008635963,0.00037626814,0.00024808667,0.00007348941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069021084,0.0021306034,0.0015678178,0.0028712444,0.0017308334,0.0018112028,0.0028206715,0.0013187961,0.015054714],"category_scores_gemma":[0.0025952996,0.0011122725,0.0019234411,0.0028605938,0.0010564785,0.003024838,0.0028315359,0.0019513478,0.0048272493],"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":[0.00033077388,0.00041791808,0.00070456625,0.0007089541,0.00012186014,0.00016112084,0.0003732683,0.03448155,0.014541406,0.023498543,0.056508657,0.8681514],"study_design_scores_gemma":[0.00081003027,0.00050002756,0.0014635358,0.00020342643,0.00030169598,0.0012433465,0.0006945162,0.61601686,0.036222916,0.24413995,0.098229304,0.00017431889],"about_ca_topic_score_codex":0.005807788,"about_ca_topic_score_gemma":0.014278154,"teacher_disagreement_score":0.015054714,"about_ca_system_score_codex":0.001725787,"about_ca_system_score_gemma":0.0028384875,"threshold_uncertainty_score":0.050363004},"labels":[],"label_agreement":null},{"id":"W2107313055","doi":"10.1109/dcc.2003.1194051","title":"Speeding up arithmetic coding using greedy re-normalization","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Normalization (sociology); Arithmetic coding; Coding (social sciences); ENCODE; Computer science; Algorithm; Greedy algorithm; Computational complexity theory; Arithmetic; Context-adaptive binary arithmetic coding; Theoretical computer science; Mathematics; Data compression; Statistics","score_opus":0.059167962490816094,"score_gpt":0.28579922399912444,"score_spread":0.22663126150830834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107313055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014887802,0.0007674916,0.97616166,0.00018120992,0.00024779775,0.00008156678,0.00007124104,0.0027369594,0.0048643],"genre_scores_gemma":[0.18241295,0.00075774,0.80792123,0.00022638231,0.00022472364,0.00017405902,0.00041836657,0.0005209808,0.007343571],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993788,0.00011406428,0.000037521615,0.00010228772,0.0002984669,0.000068901805],"domain_scores_gemma":[0.9986279,0.00052486174,0.00009313375,0.00039884355,0.00031471305,0.0000405732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005431895,0.001180277,0.0007741329,0.0009768356,0.0005295037,0.00093120337,0.0011390027,0.0005284267,0.0061334777],"category_scores_gemma":[0.002783465,0.00028415388,0.00045613325,0.0016091925,0.00080452237,0.0017869115,0.0009960433,0.0010957458,0.0026336447],"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":[0.00039938843,0.00007637349,0.00034204373,0.00016850735,0.000042033535,0.00017440105,0.00010019767,0.056362823,0.105463676,0.028648643,0.009227047,0.79899496],"study_design_scores_gemma":[0.00006918143,0.00019005824,0.00047502897,0.00006390284,0.000055433826,0.0007513595,0.000056567063,0.7310822,0.21732536,0.023095788,0.02675132,0.00008377294],"about_ca_topic_score_codex":0.0018758249,"about_ca_topic_score_gemma":0.0030718588,"teacher_disagreement_score":0.0061334777,"about_ca_system_score_codex":0.0005850992,"about_ca_system_score_gemma":0.00081914914,"threshold_uncertainty_score":0.020518482},"labels":[],"label_agreement":null},{"id":"W2107791851","doi":"","title":"An Exact A* Method for Deciphering Letter-Substitution Ciphers","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Toronto","funders":"","keywords":"Computer science; Generalization; Encoding (memory); Relation (database); Decipherment; Theoretical computer science; Set (abstract data type); ENCODE; Substitution (logic); Algorithm; Artificial intelligence; Programming language; Data mining; Mathematics","score_opus":0.018439120161289707,"score_gpt":0.31563457729948835,"score_spread":0.2971954571381986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107791851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009234826,0.00020796082,0.9872513,0.00008780818,0.00007126626,0.000042896234,0.000040046958,0.00049551006,0.0025683835],"genre_scores_gemma":[0.13485187,0.00026403382,0.8575334,0.00014025698,0.00006238787,0.00011486724,0.0001360573,0.000108096574,0.006789028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904305,0.00021173309,0.00007820316,0.00015435158,0.00044888488,0.00006373686],"domain_scores_gemma":[0.9987047,0.0004334715,0.00009488895,0.0004446711,0.00028089285,0.00004149188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008250047,0.00048226668,0.0006003341,0.00089698844,0.0005981734,0.00083301717,0.0012212895,0.0010182224,0.0036865883],"category_scores_gemma":[0.0035593756,0.000306698,0.0004292768,0.00087555696,0.0008536604,0.0020414258,0.0011701649,0.0011006104,0.0015464585],"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":[0.00023809783,0.00012637951,0.00053873373,0.00015666477,0.000039464943,0.00012651795,0.0001583246,0.12006316,0.030692328,0.13851728,0.0043985895,0.70494455],"study_design_scores_gemma":[0.000058070804,0.00013772909,0.0002388312,0.000028774042,0.000013023801,0.00045206078,0.000036495894,0.9008778,0.024568424,0.06362846,0.00993273,0.00002757838],"about_ca_topic_score_codex":0.0010842687,"about_ca_topic_score_gemma":0.0012897293,"teacher_disagreement_score":0.0036865883,"about_ca_system_score_codex":0.0006357869,"about_ca_system_score_gemma":0.0013731709,"threshold_uncertainty_score":0.012332857},"labels":[],"label_agreement":null},{"id":"W2109262879","doi":"10.1016/j.jda.2010.09.004","title":"String matching with alphabet sampling","year":2010,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Subsequence; Longest common subsequence problem; String (physics); Alphabet; String searching algorithm; Computer science; Matching (statistics); Sampling (signal processing); Space (punctuation); Generalized suffix tree; Spamming; Suffix array; Suffix tree; Range (aeronautics); Substring; Longest increasing subsequence; Mathematics; Combinatorics; Algorithm; Artificial intelligence; Pattern matching; Data structure; Statistics; The Internet","score_opus":0.013350417132978727,"score_gpt":0.2691607421952065,"score_spread":0.2558103250622278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109262879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032899782,0.00067251886,0.95910615,0.0003643073,0.00026548622,0.00012152016,0.00033077717,0.001933194,0.004306301],"genre_scores_gemma":[0.44042122,0.0006723174,0.54513997,0.00044039162,0.00036121963,0.0003359366,0.0014184179,0.00044573096,0.010764754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971016,0.0009920578,0.00021711321,0.0005652305,0.0009148081,0.00020910459],"domain_scores_gemma":[0.9947531,0.002425533,0.00019785929,0.0020195,0.00045346413,0.00015044735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019099552,0.0005611511,0.001708209,0.0023817567,0.00087120297,0.001578558,0.0016035265,0.0014843513,0.0057193167],"category_scores_gemma":[0.010691084,0.0005919916,0.0009741627,0.003991082,0.001040883,0.0030850044,0.002644052,0.0013568721,0.0021316814],"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":[0.0012765991,0.00035084155,0.002550717,0.0002755389,0.00016555979,0.00027923685,0.00014905319,0.11684503,0.016840959,0.10137787,0.010794171,0.74909437],"study_design_scores_gemma":[0.000095700816,0.00017732619,0.00054601766,0.000031446983,0.000057264384,0.00037496514,0.00004432609,0.8325185,0.015846536,0.14455499,0.0057269493,0.000025968928],"about_ca_topic_score_codex":0.0009299802,"about_ca_topic_score_gemma":0.0011473246,"teacher_disagreement_score":0.0057193167,"about_ca_system_score_codex":0.0006200986,"about_ca_system_score_gemma":0.0013653961,"threshold_uncertainty_score":0.019132972},"labels":[],"label_agreement":null},{"id":"W2109526741","doi":"10.1109/pacrim.2011.6032965","title":"Design and implementation of an Inflate acceleration core","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of New Brunswick","funders":"","keywords":"Computer science; Graphics; Latency (audio); Acceleration; Interface (matter); User interface; Core (optical fiber); Transfer (computing); Human–computer interaction; Operating system; Telecommunications","score_opus":0.09537701142439758,"score_gpt":0.31712755229635065,"score_spread":0.22175054087195306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109526741","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05612599,0.0005854897,0.9130415,0.00045939133,0.0002788686,0.0011801528,0.00022115343,0.0085283965,0.019579044],"genre_scores_gemma":[0.37230226,0.00041681874,0.6017755,0.0005016759,0.00009648946,0.0006409811,0.0006105561,0.0005364755,0.023119258],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999567,0.00003615912,0.000035181845,0.0000700051,0.00021574175,0.000075879165],"domain_scores_gemma":[0.99908066,0.000075690354,0.0000767976,0.00009625984,0.0005917084,0.000078863755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057119835,0.0005547075,0.0003685074,0.0007036542,0.0004447853,0.001011445,0.0018297518,0.0005573279,0.0039044637],"category_scores_gemma":[0.0009594799,0.00028180052,0.00021750876,0.0003153449,0.00026724473,0.00063682056,0.00056315714,0.0007789815,0.0019776612],"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":[0.0009781746,0.0004045962,0.004839926,0.00064565346,0.00010021916,0.0005691702,0.0005406372,0.02373612,0.44246647,0.024670577,0.016434945,0.48461348],"study_design_scores_gemma":[0.00022481752,0.0025150361,0.004316688,0.00011353857,0.00015425115,0.0010812184,0.00012884133,0.2666562,0.56069374,0.0026846605,0.16131112,0.000119836375],"about_ca_topic_score_codex":0.0012244985,"about_ca_topic_score_gemma":0.0011768709,"teacher_disagreement_score":0.0039044637,"about_ca_system_score_codex":0.00063691346,"about_ca_system_score_gemma":0.0011653329,"threshold_uncertainty_score":0.013061702},"labels":[],"label_agreement":null},{"id":"W2109612762","doi":"10.1016/j.dam.2015.09.024","title":"A note on easy and efficient computation of full abelian periods of a word","year":2015,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Abelian group; Mathematics; Word (group theory); Computation; Alphabet; Constant (computer programming); Arithmetic of abelian varieties; Combinatorics; Simple (philosophy); Period length; Rank of an abelian group; Algorithm; Discrete mathematics; Elementary abelian group; Arithmetic; Computer science; Linguistics","score_opus":0.021681295995195048,"score_gpt":0.2721986936672689,"score_spread":0.25051739767207387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109612762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05551619,0.002904688,0.887333,0.0021155141,0.001697202,0.00017742772,0.0007416581,0.0035927715,0.045921586],"genre_scores_gemma":[0.44240683,0.0020923843,0.52305925,0.0011418144,0.002227821,0.00037406705,0.0015206118,0.0019936871,0.025183542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99786025,0.0004325958,0.00018955389,0.000457317,0.00079724,0.000263023],"domain_scores_gemma":[0.9953106,0.0024923144,0.00013637404,0.0016215442,0.00024076054,0.0001984893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001429874,0.0017800456,0.0017978256,0.0018547924,0.0013556909,0.004415686,0.0027159553,0.0012039068,0.016677313],"category_scores_gemma":[0.008268407,0.0007485342,0.0018159524,0.0026021802,0.0023901365,0.009561107,0.006470978,0.0038581481,0.0043947767],"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":[0.0008515462,0.00015904584,0.0011295063,0.0006312215,0.00016148422,0.0005211656,0.0007627316,0.011838878,0.019505667,0.64434505,0.028151656,0.29194197],"study_design_scores_gemma":[0.00012009634,0.000109126326,0.00047759563,0.00006297842,0.000080534184,0.00033834353,0.00014455746,0.044706028,0.0100392345,0.91794187,0.025884712,0.00009490432],"about_ca_topic_score_codex":0.0008950773,"about_ca_topic_score_gemma":0.0013289896,"teacher_disagreement_score":0.016677313,"about_ca_system_score_codex":0.0011898244,"about_ca_system_score_gemma":0.0010218862,"threshold_uncertainty_score":0.0557912},"labels":[],"label_agreement":null},{"id":"W2109692166","doi":"10.1016/s0166-218x(03)00382-2","title":"On spaced seeds for similarity search","year":2003,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Similarity (geometry); Mathematics; Sensitivity (control systems); Combinatorics; Nearest neighbor search; Algorithm; Computer science; Data mining; Artificial intelligence","score_opus":0.02766122019691645,"score_gpt":0.2810312807924654,"score_spread":0.25337006059554895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109692166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011354031,0.0006953711,0.9850773,0.00021635837,0.000101961945,0.000055695673,0.000053125823,0.00035267213,0.0020934248],"genre_scores_gemma":[0.2690101,0.00084814336,0.7224017,0.00028412932,0.00031445568,0.00020439379,0.00046044248,0.00034214096,0.006134434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718684,0.0010558629,0.00017046557,0.0004622711,0.0009745427,0.00015006193],"domain_scores_gemma":[0.98767275,0.007969343,0.00053889334,0.002373751,0.0010403234,0.0004048739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003113815,0.0008985958,0.0022874768,0.003116174,0.0012531684,0.0018898273,0.0026481536,0.0031155117,0.0061473926],"category_scores_gemma":[0.029361162,0.00088590157,0.0007806519,0.0046027987,0.0026584363,0.0058803298,0.004109342,0.002017531,0.0019776018],"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":[0.0011353431,0.0001904674,0.0010166586,0.00027224075,0.00007719654,0.00025018744,0.00036533154,0.1922906,0.010817232,0.43861288,0.00857016,0.34640166],"study_design_scores_gemma":[0.00009602825,0.00012489282,0.00018109517,0.00004221769,0.00002048121,0.00019685592,0.000051764684,0.6872347,0.0028167951,0.30548888,0.0037204258,0.000025774738],"about_ca_topic_score_codex":0.0013531148,"about_ca_topic_score_gemma":0.0013770747,"teacher_disagreement_score":0.0061473926,"about_ca_system_score_codex":0.0009531021,"about_ca_system_score_gemma":0.0011217234,"threshold_uncertainty_score":0.020565033},"labels":[],"label_agreement":null},{"id":"W2109698133","doi":"10.1109/pcs.2012.6213322","title":"Prediction with Partial Match using two-dimensional approximate contexts","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Pixel; Raster graphics; Lossless compression; Context (archaeology); Raster scan; Computer science; Artificial intelligence; Computer vision; Data compression; Sequence (biology); Raster data; Compression (physics); Algorithm; Physics; Geography","score_opus":0.030325870782950314,"score_gpt":0.2603107350712672,"score_spread":0.22998486428831685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109698133","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17123635,0.0014972538,0.8219312,0.00026991105,0.00022480986,0.00012621302,0.0002705133,0.0018959092,0.0025479337],"genre_scores_gemma":[0.7219252,0.00053200836,0.2745563,0.00014224803,0.00011725758,0.00010596785,0.0005858626,0.000083770334,0.0019513022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990709,0.00016924053,0.000056616835,0.00019042692,0.00042220028,0.00009060115],"domain_scores_gemma":[0.9985708,0.0005534823,0.00010723381,0.00048698546,0.00022862283,0.000052775664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006397219,0.0006210592,0.00086457934,0.0008007704,0.00059147325,0.00088430126,0.0009832474,0.000732679,0.001833992],"category_scores_gemma":[0.0045718024,0.0003629326,0.0003926297,0.0011410068,0.00047809127,0.0023882668,0.0018126122,0.000801128,0.00057630264],"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":[0.0017374046,0.00024474558,0.004850258,0.00018673355,0.00007588556,0.00062888965,0.0003770523,0.16986726,0.0370267,0.019191094,0.00584939,0.7599645],"study_design_scores_gemma":[0.0000502925,0.00028743403,0.0007635148,0.000019392704,0.00003306902,0.00031853997,0.000087063214,0.9660247,0.020474559,0.008295067,0.003612816,0.0000335877],"about_ca_topic_score_codex":0.0028925173,"about_ca_topic_score_gemma":0.0032751893,"teacher_disagreement_score":0.0028925173,"about_ca_system_score_codex":0.0003327321,"about_ca_system_score_gemma":0.00081589294,"threshold_uncertainty_score":0.0061353445},"labels":[],"label_agreement":null},{"id":"W2109929425","doi":"10.82308/45910","title":"Two-way hashing with separate chaining and linear probing","year":2004,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Chaining; Hash function; Dynamic perfect hashing; Combinatorics; Hash table; K-independent hashing; Bounded function; Mathematics; Linear hashing; Asymptotically optimal algorithm; Perfect hash function; Discrete mathematics; Binary logarithm; Constant (computer programming); Computer science; Double hashing; Algorithm","score_opus":0.01797479363825379,"score_gpt":0.23672678081599222,"score_spread":0.21875198717773842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109929425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042131912,0.00035910823,0.9533126,0.00023079503,0.000036130485,0.00024534384,0.00007611487,0.00094179856,0.0026662734],"genre_scores_gemma":[0.70363903,0.0002625936,0.2900906,0.00021005016,0.000084007115,0.0005511928,0.00027797933,0.00013273772,0.004751794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948042,0.0014171806,0.00036203404,0.0010524539,0.0016624297,0.00070170156],"domain_scores_gemma":[0.9840756,0.006325983,0.0012065972,0.006810299,0.0011504234,0.00043105322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032833964,0.0010884259,0.0016160297,0.0010486391,0.0010838185,0.0019242595,0.0039804187,0.0021095935,0.0029132972],"category_scores_gemma":[0.01642727,0.0011322432,0.0012667653,0.002234895,0.0028498094,0.010269412,0.0075796978,0.0023668017,0.0012042772],"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":[0.0017819287,0.00072826765,0.00873188,0.00080477,0.0001857618,0.0005052415,0.00073563785,0.426659,0.053536925,0.29231107,0.004357498,0.20966206],"study_design_scores_gemma":[0.00007625757,0.00028167947,0.00031985866,0.00001775501,0.000021222724,0.00032049255,0.00003867993,0.9501259,0.01042919,0.036628384,0.0016893653,0.00005138621],"about_ca_topic_score_codex":0.0008649597,"about_ca_topic_score_gemma":0.0006363762,"teacher_disagreement_score":0.0039804187,"about_ca_system_score_codex":0.001634749,"about_ca_system_score_gemma":0.0016108074,"threshold_uncertainty_score":0.017364442},"labels":[],"label_agreement":null},{"id":"W2110015277","doi":"10.1145/1645953.1646134","title":"Suffix trees for very large genomic sequences","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Generalized suffix tree; Suffix tree; Compressed suffix array; Suffix; Computer science; String (physics); Theoretical computer science; Data structure; String searching algorithm; Suffix array; Tree (set theory); Algorithm; Mathematics; Programming language; Combinatorics","score_opus":0.017167537308336596,"score_gpt":0.26312993669134527,"score_spread":0.24596239938300868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110015277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064485096,0.0053178472,0.96935904,0.0012392479,0.00060342695,0.00014888876,0.0036447288,0.006911403,0.0063268756],"genre_scores_gemma":[0.062458336,0.006280638,0.9119214,0.0006600982,0.00060164474,0.00048175984,0.010403761,0.0013035273,0.0058889515],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998708,0.00026606896,0.00018128502,0.00021110428,0.0005640004,0.00006947062],"domain_scores_gemma":[0.99676585,0.0015478875,0.0002945845,0.0007727829,0.0005048837,0.000114004346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009768645,0.0007140573,0.0009340851,0.0018883097,0.0010524573,0.00215345,0.0014699453,0.0014327433,0.008451243],"category_scores_gemma":[0.010095642,0.00061615766,0.00083525386,0.0045348117,0.001006706,0.004321119,0.001779583,0.0026620734,0.009145329],"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":[0.00039421566,0.00009222038,0.001119376,0.0018363448,0.000111104804,0.0013451255,0.0007484752,0.025784941,0.043354988,0.3282919,0.075615905,0.52130526],"study_design_scores_gemma":[0.00007317259,0.000103233986,0.000631039,0.00030187567,0.000039328723,0.0015102732,0.0001581757,0.10308441,0.01434448,0.7084318,0.17126223,0.000060055616],"about_ca_topic_score_codex":0.000450996,"about_ca_topic_score_gemma":0.0008070716,"teacher_disagreement_score":0.008451243,"about_ca_system_score_codex":0.0005712049,"about_ca_system_score_gemma":0.00085242896,"threshold_uncertainty_score":0.028272271},"labels":[],"label_agreement":null},{"id":"W2110694272","doi":"10.1109/ccece.1998.685553","title":"On the analysis and design of variable rate trellis source codes","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Algorithm; Rate–distortion theory; Mathematics; Trellis (graph); Decoding methods; Coding gain; Lossy compression; Computer science; Data compression; Statistics","score_opus":0.02611606809782869,"score_gpt":0.21140481643674897,"score_spread":0.18528874833892028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110694272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062044407,0.00079160766,0.98989433,0.00012044155,0.000022694227,0.00003934265,0.000053327498,0.00014721358,0.0027265635],"genre_scores_gemma":[0.5163989,0.005670872,0.46897945,0.00030709023,0.00023729823,0.00053491787,0.00058477465,0.00029406644,0.0069926884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984938,0.00048735001,0.00006258038,0.00012865888,0.0007010967,0.00012654637],"domain_scores_gemma":[0.9956715,0.0029197964,0.00043282914,0.00023742676,0.00068950286,0.000048963364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018057972,0.00084217434,0.00070509675,0.001105957,0.0003808033,0.0010473462,0.0009862323,0.0008064355,0.0023421359],"category_scores_gemma":[0.008802301,0.0005527565,0.0005225694,0.0012981886,0.0011578618,0.0012384616,0.0006574052,0.0010577202,0.0007379488],"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":[0.00014660874,0.000022591204,0.00035956662,0.00020155722,0.000043858097,0.00009522561,0.00010862491,0.8101882,0.010101847,0.111673385,0.0011805464,0.065878116],"study_design_scores_gemma":[0.000020120733,0.00009432166,0.00012781622,0.000045644785,0.000017281689,0.000092996255,0.000011949528,0.9568358,0.0057829963,0.03478199,0.0021664293,0.000022680892],"about_ca_topic_score_codex":0.0017657914,"about_ca_topic_score_gemma":0.0015414862,"teacher_disagreement_score":0.0023421359,"about_ca_system_score_codex":0.0013763302,"about_ca_system_score_gemma":0.0012668853,"threshold_uncertainty_score":0.009986043},"labels":[],"label_agreement":null},{"id":"W2110922051","doi":"10.1186/1748-7188-7-32","title":"Towards a practical O(n logn) phylogeny algorithm","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Phylogenetics; Algorithm; Biology","score_opus":0.03332692126473845,"score_gpt":0.3493959329378441,"score_spread":0.31606901167310564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110922051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01342851,0.00042664117,0.97477573,0.001148787,0.000119310746,0.00011526834,0.00030097846,0.006327308,0.003357491],"genre_scores_gemma":[0.07903437,0.0002539037,0.9147625,0.00047395623,0.000102637656,0.00021163041,0.0012851069,0.0006540452,0.0032218324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976439,0.0005671125,0.00015573547,0.0006652991,0.0006987705,0.00026913476],"domain_scores_gemma":[0.9939839,0.0021973015,0.00031461174,0.0022465542,0.0010381632,0.0002194786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025072931,0.0009875656,0.0011864608,0.0011805625,0.0011010413,0.0022859473,0.003628804,0.0024836077,0.012358628],"category_scores_gemma":[0.012380274,0.0007528992,0.00072915613,0.002784581,0.0010085482,0.005787378,0.002954961,0.0025767968,0.009857686],"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":[0.0011028085,0.00032453806,0.002510292,0.00070748525,0.00007605806,0.00024745535,0.00047041927,0.064167276,0.0225781,0.07555318,0.04582485,0.7864376],"study_design_scores_gemma":[0.0005421766,0.00019525665,0.0009539848,0.00009169448,0.000041325013,0.00074947457,0.00020191791,0.77948684,0.012123653,0.17373951,0.031824734,0.00004933143],"about_ca_topic_score_codex":0.0017807964,"about_ca_topic_score_gemma":0.0024140691,"teacher_disagreement_score":0.012358628,"about_ca_system_score_codex":0.0011353651,"about_ca_system_score_gemma":0.002340284,"threshold_uncertainty_score":0.04134375},"labels":[],"label_agreement":null},{"id":"W2110940943","doi":"10.1109/isit.2009.5205704","title":"Structural complexity of random binary trees","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Tree (set theory); Binary number; Computer science; Discrete mathematics; Mathematics; Arithmetic","score_opus":0.036706415643025125,"score_gpt":0.2715687901565743,"score_spread":0.2348623745135492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110940943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7640323,0.0016594671,0.19257767,0.0053213416,0.00010425915,0.00010428739,0.0030730253,0.00044695337,0.0326807],"genre_scores_gemma":[0.9760183,0.0006133691,0.01488722,0.0003567723,0.00018320212,0.0001830048,0.0017300071,0.00013983055,0.0058883047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977781,0.0005820201,0.00011428719,0.0004441334,0.0007158328,0.00036565293],"domain_scores_gemma":[0.98525476,0.009910733,0.0016588041,0.0011885918,0.0008915871,0.0010956067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015275759,0.00044364328,0.0010700317,0.002282016,0.0012665583,0.003347115,0.00156983,0.0015720609,0.0060337624],"category_scores_gemma":[0.017204342,0.00066035433,0.000914805,0.0013973794,0.002370871,0.0058239424,0.0022164846,0.0019350933,0.0007441598],"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":[0.00026016094,0.00006460201,0.0050686803,0.0002361374,0.000062326246,0.00020441231,0.0006180027,0.071773894,0.0033322282,0.89824563,0.00477748,0.01535657],"study_design_scores_gemma":[0.00002310841,0.000030410067,0.0023156693,0.000030174393,0.000015061342,0.00016254852,0.00008658356,0.17540398,0.0008408493,0.81956065,0.0015044677,0.00002657092],"about_ca_topic_score_codex":0.0013786684,"about_ca_topic_score_gemma":0.0015062239,"teacher_disagreement_score":0.0060337624,"about_ca_system_score_codex":0.0028797938,"about_ca_system_score_gemma":0.0009918413,"threshold_uncertainty_score":0.020894527},"labels":[],"label_agreement":null},{"id":"W2111044311","doi":"10.1093/bioinformatics/bts593","title":"SCALCE: boosting sequence compression algorithms using locally consistent encoding","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":158,"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":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; ExxonMobil Research and Engineering Company","keywords":"Boosting (machine learning); Encoding (memory); Computer science; Algorithm; Sequence (biology); Data compression; Compression (physics); Artificial intelligence","score_opus":0.08296651646590367,"score_gpt":0.3066863161757942,"score_spread":0.22371979970989056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111044311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028151931,0.00075192685,0.96184486,0.00025357504,0.00015312049,0.00015015787,0.00023823326,0.0062063974,0.0022497263],"genre_scores_gemma":[0.21090308,0.0005344778,0.77990866,0.00061365444,0.0001737837,0.00031019066,0.0016163932,0.00075844454,0.0051813056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993893,0.000105966225,0.00003702645,0.000091916954,0.00030899353,0.00006666286],"domain_scores_gemma":[0.9986547,0.00055283617,0.00011054203,0.00029210706,0.0003269042,0.000062757346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011360662,0.0007434042,0.0007818696,0.0011437774,0.00053256424,0.00082305825,0.0017111396,0.0009251098,0.0029771521],"category_scores_gemma":[0.003878002,0.00027316794,0.00053964136,0.0013739335,0.0008825218,0.0013260893,0.0012438234,0.0016453085,0.0018355786],"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":[0.00080255774,0.000223342,0.002414393,0.0002858059,0.00007268279,0.00033287256,0.00031011662,0.17430414,0.05288671,0.029117415,0.018803982,0.72044593],"study_design_scores_gemma":[0.00007370277,0.00023161626,0.0005238502,0.0000343046,0.000020617561,0.00021216633,0.000052855557,0.93806344,0.03338635,0.017943224,0.009420172,0.000037749025],"about_ca_topic_score_codex":0.0025228902,"about_ca_topic_score_gemma":0.002297467,"teacher_disagreement_score":0.0029771521,"about_ca_system_score_codex":0.0007019218,"about_ca_system_score_gemma":0.0010077399,"threshold_uncertainty_score":0.0099595785},"labels":[],"label_agreement":null},{"id":"W2111271567","doi":"10.1109/dcc.1994.305917","title":"Adaptive variable-to-variable length codes","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Bell (Canada)","funders":"","keywords":"Computer science; Variable (mathematics); Tree (set theory); Source code; Algorithm; Code (set theory); Variable-length code; Theoretical computer science; Mathematics; Programming language; Combinatorics; Decoding methods","score_opus":0.026209990386325162,"score_gpt":0.22164261882692424,"score_spread":0.19543262844059908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111271567","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01488498,0.0011122242,0.97828764,0.00017655904,0.0001380001,0.00009394416,0.00008956814,0.0010196002,0.0041976026],"genre_scores_gemma":[0.24705772,0.0013587583,0.7411067,0.00034836726,0.0002130733,0.00024844104,0.00036949987,0.00040778788,0.008889696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815613,0.00038620282,0.00015037363,0.00033676007,0.00082459784,0.00014589647],"domain_scores_gemma":[0.9947277,0.0020811723,0.00060017785,0.0010342923,0.0014404042,0.00011631117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010726864,0.0005638645,0.00047498738,0.0013875696,0.0005674325,0.0010365103,0.0016142274,0.00076804956,0.00430959],"category_scores_gemma":[0.007166052,0.00028945794,0.0004520555,0.0015688227,0.001270599,0.0018192787,0.0013428433,0.0013151804,0.0015129008],"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":[0.0007110882,0.000086126514,0.0014553865,0.0003872418,0.000060694565,0.00015180437,0.00025272227,0.08738045,0.03503631,0.23319332,0.005722908,0.63556194],"study_design_scores_gemma":[0.00015225567,0.000518954,0.0007736747,0.00021274532,0.00009880573,0.0009184995,0.0000854336,0.6405325,0.12096779,0.14340885,0.09212791,0.00020255976],"about_ca_topic_score_codex":0.0011242449,"about_ca_topic_score_gemma":0.0017587678,"teacher_disagreement_score":0.00430959,"about_ca_system_score_codex":0.0010020168,"about_ca_system_score_gemma":0.00087029865,"threshold_uncertainty_score":0.014417052},"labels":[],"label_agreement":null},{"id":"W2111454628","doi":"10.1109/tit.2003.815803","title":"Almost all complete binary prefix codes have a self-synchronizing string","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Communications Security Establishment","funders":"","keywords":"Prefix code; Synchronizing; Computer science; Binary number; Discrete mathematics; Theoretical computer science; Mathematics; Algorithm; Linear code; Block code; Arithmetic; Combinatorics; Decoding methods; Topology (electrical circuits)","score_opus":0.01931613686756095,"score_gpt":0.23613473927993242,"score_spread":0.21681860241237147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111454628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6634348,0.00068696437,0.31026068,0.0010657527,0.00023465775,0.00011935505,0.0004853639,0.00089013943,0.022822324],"genre_scores_gemma":[0.95041907,0.0004215076,0.041580725,0.00045863085,0.0002674249,0.00026231195,0.000658955,0.00019207616,0.005739256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974485,0.00062252115,0.00020906806,0.00049765164,0.0008487986,0.0003734801],"domain_scores_gemma":[0.9714145,0.014940944,0.0035021713,0.0053936155,0.0031800475,0.0015686835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018335065,0.00065681775,0.0010781834,0.001841821,0.0016385254,0.0019126729,0.00089018425,0.0021146033,0.003598908],"category_scores_gemma":[0.022041114,0.00074543775,0.0007711841,0.0016808033,0.0026092005,0.003953501,0.0023200733,0.001683009,0.001065156],"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":[0.0016030503,0.0002379574,0.012347612,0.00042772983,0.00016577651,0.0014952734,0.0011304572,0.033166513,0.0348661,0.8201042,0.005109881,0.089345396],"study_design_scores_gemma":[0.00023291241,0.0007355884,0.0052632163,0.00015673519,0.0001055573,0.004521501,0.00059093,0.14456488,0.055181894,0.7735801,0.014891831,0.00017479106],"about_ca_topic_score_codex":0.00017703947,"about_ca_topic_score_gemma":0.00013553126,"teacher_disagreement_score":0.003598908,"about_ca_system_score_codex":0.00037221255,"about_ca_system_score_gemma":0.0006831305,"threshold_uncertainty_score":0.012039542},"labels":[],"label_agreement":null},{"id":"W2111681107","doi":"10.1109/iscas.2006.1693520","title":"A systolic array technique for determining common approximate substrings","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of New Brunswick","funders":"","keywords":"Substring; Systolic array; Computation; Computer science; Algorithm; Edit distance; Theoretical computer science; Data structure; Very-large-scale integration","score_opus":0.013600769195554831,"score_gpt":0.24668222540718848,"score_spread":0.23308145621163365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111681107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065769204,0.00014238787,0.9911747,0.000054068518,0.00006769493,0.000032126412,0.000040470586,0.00091891637,0.0009925439],"genre_scores_gemma":[0.080288015,0.00026291114,0.9158846,0.000078549216,0.00010351522,0.00012264775,0.00026473348,0.00010372383,0.0028912935],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993523,0.00006933026,0.000061817285,0.00012355554,0.00034119934,0.000051768133],"domain_scores_gemma":[0.9990283,0.0002903969,0.00009920745,0.00021643827,0.00031850793,0.000047189216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056743034,0.0006377298,0.00076907413,0.001288677,0.0006476019,0.0009928212,0.0014626593,0.0005686111,0.0033000503],"category_scores_gemma":[0.0023227402,0.00030393302,0.00047970426,0.0020101757,0.00055084156,0.0016999219,0.0010175612,0.0009293748,0.0014036648],"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":[0.0003030769,0.000114117494,0.0011314172,0.00020115878,0.00005755298,0.00028493756,0.00029512728,0.04104125,0.103374936,0.050109357,0.0047344207,0.7983526],"study_design_scores_gemma":[0.00013375848,0.0009273387,0.0011031224,0.000064248685,0.00012115504,0.0013112051,0.00022955037,0.74003136,0.15410616,0.056078643,0.045796677,0.000096765725],"about_ca_topic_score_codex":0.00063714205,"about_ca_topic_score_gemma":0.0010838056,"teacher_disagreement_score":0.0033000503,"about_ca_system_score_codex":0.00038206036,"about_ca_system_score_gemma":0.0011970146,"threshold_uncertainty_score":0.011039734},"labels":[],"label_agreement":null},{"id":"W2111741778","doi":"10.1007/978-3-540-31856-9_31","title":"Approximate Range Mode and Range Median Queries","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Combinatorics; Rank (graph theory); Data structure; Binary logarithm; Range (aeronautics); Sequence (biology); Space (punctuation); Mathematics; Element (criminal law); Algorithm; Discrete mathematics; Computer science","score_opus":0.014519397415170937,"score_gpt":0.24254774722105643,"score_spread":0.2280283498058855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111741778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019736553,0.0020450072,0.9579664,0.00058504764,0.0002088969,0.00013399219,0.00068822736,0.0024891119,0.016146775],"genre_scores_gemma":[0.31646475,0.0020493516,0.64969957,0.0006270666,0.0007059099,0.0004481372,0.0028768347,0.0009726026,0.026155837],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711084,0.00045274003,0.00017906087,0.00040046562,0.0015790475,0.00027794682],"domain_scores_gemma":[0.99544036,0.0018967958,0.00022974465,0.0017470861,0.0005758969,0.0001100812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017483982,0.0011244976,0.0023899546,0.0021683038,0.00083098124,0.003233394,0.0026365097,0.0018495375,0.012599279],"category_scores_gemma":[0.01155316,0.0006410485,0.0010740095,0.0045888275,0.0011400454,0.007387686,0.004789886,0.0021137693,0.003769546],"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":[0.0020453313,0.00027399606,0.001692899,0.00050722883,0.000104019186,0.00025122592,0.00039535717,0.056519102,0.013253454,0.22806284,0.037792016,0.6591025],"study_design_scores_gemma":[0.00015527291,0.00022600501,0.0006706066,0.00009714581,0.000077256635,0.0012200892,0.00026963366,0.5202148,0.017444002,0.42780867,0.031747047,0.00006936139],"about_ca_topic_score_codex":0.0008884041,"about_ca_topic_score_gemma":0.0009931898,"teacher_disagreement_score":0.012599279,"about_ca_system_score_codex":0.0010162537,"about_ca_system_score_gemma":0.0008520384,"threshold_uncertainty_score":0.04214883},"labels":[],"label_agreement":null},{"id":"W2111953579","doi":"10.1016/j.tcs.2009.09.014","title":"Why greed works for shortest common superstring problem","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Tsinghua University; National Science Foundation","keywords":"Greedy algorithm; Mathematics; Algorithm; Combinatorics; Superstring theory; Asymptotically optimal algorithm; Approximation algorithm; Sequence (biology); Biology; Supersymmetry; Genetics","score_opus":0.012502913709073315,"score_gpt":0.2567674646483736,"score_spread":0.24426455093930027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111953579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18281576,0.007971285,0.6464126,0.052245144,0.004475812,0.0003426769,0.0011580257,0.0062044794,0.098374225],"genre_scores_gemma":[0.6962422,0.0023564969,0.25539368,0.0062163924,0.0017094705,0.00024383716,0.0013796411,0.0024646255,0.03399372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99610597,0.0013580755,0.00020026589,0.00087584945,0.0008973215,0.0005623515],"domain_scores_gemma":[0.98463076,0.008275791,0.00039401243,0.0045800232,0.0016008789,0.0005185139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038842608,0.0006533817,0.0020277046,0.0016709467,0.002505797,0.0046839137,0.0026051633,0.0048485403,0.015477897],"category_scores_gemma":[0.030453209,0.0006267787,0.0015847447,0.0020365268,0.004538977,0.020229876,0.0029394552,0.004975226,0.0040724324],"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":[0.00055994134,0.00018481474,0.0016271524,0.00043776093,0.00009708423,0.000288732,0.00037876848,0.016708883,0.0030620412,0.8287592,0.043665405,0.10423008],"study_design_scores_gemma":[0.000065760454,0.000042756514,0.00012977181,0.00005501717,0.000029435316,0.00024962914,0.00015023146,0.032093,0.0020937661,0.95557994,0.00948569,0.000025102894],"about_ca_topic_score_codex":0.0014239107,"about_ca_topic_score_gemma":0.0010714149,"teacher_disagreement_score":0.015477897,"about_ca_system_score_codex":0.0015633933,"about_ca_system_score_gemma":0.0017603742,"threshold_uncertainty_score":0.051778734},"labels":[],"label_agreement":null},{"id":"W2112595202","doi":"10.1109/iwfhr.2004.18","title":"An Optimized Hill Climbing Algorithm for Feature Subset Selection: Evaluation on Handwritten Character Recognition","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Pattern recognition (psychology); Feature selection; Artificial intelligence; NIST; Handwriting recognition; Classifier (UML); Feature extraction; Character recognition; Character (mathematics); Word error rate; Intelligent word recognition; Feature (linguistics); Speech recognition; Intelligent character recognition; Mathematics","score_opus":0.03525880353323428,"score_gpt":0.2981009102945676,"score_spread":0.2628421067613333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112595202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35048094,0.002424625,0.63304955,0.00020941306,0.00016561436,0.0010514648,0.0006880041,0.0058151386,0.0061151925],"genre_scores_gemma":[0.5303399,0.0007664447,0.46180978,0.0001591398,0.00004294847,0.0006825455,0.0017090134,0.00043166618,0.004058564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992016,0.00024732645,0.000064462365,0.00009679476,0.00030296418,0.000086924454],"domain_scores_gemma":[0.99914455,0.00035216936,0.00004550416,0.00008890134,0.00032509517,0.000043780787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012408497,0.0012455104,0.0015705252,0.00084952364,0.0005055522,0.0005341328,0.0013346729,0.0010656492,0.001744883],"category_scores_gemma":[0.0021437593,0.0003713564,0.0006747568,0.0011468432,0.00023387435,0.0005440571,0.00037184617,0.0005173987,0.00065897877],"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":[0.00095276156,0.0005726309,0.0027027614,0.00048903003,0.00046061818,0.00027595332,0.00012849359,0.491261,0.01601014,0.0006357191,0.0059689544,0.48054197],"study_design_scores_gemma":[0.000119830474,0.0003376483,0.0018142243,0.000014779198,0.000051860254,0.000116938565,0.00003453307,0.9898078,0.0062421234,0.0002606724,0.0011787545,0.000020872323],"about_ca_topic_score_codex":0.008380188,"about_ca_topic_score_gemma":0.008290783,"teacher_disagreement_score":0.008380188,"about_ca_system_score_codex":0.00044991248,"about_ca_system_score_gemma":0.0008114258,"threshold_uncertainty_score":0.016662776},"labels":[],"label_agreement":null},{"id":"W2112908352","doi":"10.1016/j.tcs.2014.05.005","title":"New space/time tradeoffs for top- k document retrieval on sequences","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico","keywords":"Document retrieval; Computer science; Space (punctuation); Information retrieval; Combinatorics; Mathematics","score_opus":0.008556120600705158,"score_gpt":0.25402016309942393,"score_spread":0.24546404249871878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112908352","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08620887,0.0140672885,0.8785967,0.0031704826,0.0006522165,0.00027757479,0.0011112075,0.0030482367,0.012867264],"genre_scores_gemma":[0.40849552,0.0045084255,0.5719308,0.000649229,0.001545547,0.00035314888,0.0013487806,0.001256038,0.009912517],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98955476,0.003368799,0.0010119517,0.0009299397,0.004138984,0.0009955752],"domain_scores_gemma":[0.95231426,0.03506189,0.0017098738,0.005751139,0.0036008386,0.0015619126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008816387,0.0020717543,0.0026806605,0.0046393834,0.0017622354,0.0061360705,0.0038545723,0.003580687,0.014607446],"category_scores_gemma":[0.06420129,0.0012143505,0.0010059414,0.007002582,0.0024942185,0.018502397,0.0041369353,0.0034404409,0.003891533],"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":[0.0042815,0.0007983999,0.0024553125,0.00124605,0.00017457352,0.00022550378,0.00068210054,0.1717075,0.038025297,0.15908383,0.02398112,0.5973388],"study_design_scores_gemma":[0.00015202345,0.00033243344,0.00066096237,0.000080662845,0.00009556149,0.00045988956,0.00022081869,0.8687865,0.010119878,0.115023576,0.003976028,0.000091638474],"about_ca_topic_score_codex":0.0026129186,"about_ca_topic_score_gemma":0.004451335,"teacher_disagreement_score":0.014607446,"about_ca_system_score_codex":0.004198353,"about_ca_system_score_gemma":0.0029484215,"threshold_uncertainty_score":0.04886681},"labels":[],"label_agreement":null},{"id":"W2113001271","doi":"10.1007/978-3-540-73814-5_5","title":"New Algorithms for the Spaced Seeds","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Running time; Algorithm; Combinatorics; Exponential function; Set (abstract data type); Monte Carlo method; Mathematics; Computer science; Statistics","score_opus":0.035057950650731536,"score_gpt":0.2858264778234328,"score_spread":0.25076852717270126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113001271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017173057,0.0003845073,0.99299663,0.00015788877,0.00024921348,0.00003616046,0.000046033565,0.00042324455,0.0039889943],"genre_scores_gemma":[0.029773135,0.0006765374,0.9552056,0.00016964968,0.00036994935,0.00017826162,0.00020554508,0.0004908758,0.012930395],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854666,0.00033273455,0.00009151344,0.0003001274,0.000645064,0.000083799125],"domain_scores_gemma":[0.99693066,0.0015925854,0.0001876446,0.0007362238,0.00040503725,0.00014794347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017159365,0.0017097847,0.0014587458,0.0022338012,0.0010062319,0.0024264636,0.0031239514,0.002019721,0.01474282],"category_scores_gemma":[0.0111667365,0.001040494,0.0014394966,0.0028931869,0.0020416442,0.0052059046,0.0037182926,0.003967976,0.005951964],"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":[0.00018592103,0.00007831119,0.00031392806,0.00018346589,0.000039880848,0.00010928087,0.0001768245,0.034721855,0.005974414,0.6228045,0.014887723,0.3205239],"study_design_scores_gemma":[0.000088101326,0.00005816665,0.0001318725,0.000050367176,0.00003682963,0.00039493915,0.000053157564,0.37081015,0.0036442222,0.59896654,0.025724573,0.00004102691],"about_ca_topic_score_codex":0.0006374618,"about_ca_topic_score_gemma":0.0012984995,"teacher_disagreement_score":0.01474282,"about_ca_system_score_codex":0.0010734638,"about_ca_system_score_gemma":0.00099017,"threshold_uncertainty_score":0.049319625},"labels":[],"label_agreement":null},{"id":"W2113844580","doi":"10.1109/ccece.2007.315","title":"FPGA-Based Lossless Data Compression using Huffman and LZ77 Algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Huffman coding; Encoder; Lossless compression; Field-programmable gate array; Data compression; VHDL; Computer hardware; Application-specific integrated circuit; Embedded system; Algorithm; Operating system","score_opus":0.09297801264256336,"score_gpt":0.34063051159560753,"score_spread":0.24765249895304417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113844580","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1586507,0.0011286183,0.8163224,0.0002698385,0.00017375838,0.0002805593,0.00034322788,0.009630642,0.013200261],"genre_scores_gemma":[0.5289974,0.000735912,0.46116954,0.00014505099,0.000077617464,0.00013898863,0.0007154928,0.00020270614,0.007817306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997434,0.000043740405,0.000020464146,0.000027511272,0.00013350959,0.000031354983],"domain_scores_gemma":[0.9996209,0.00014261258,0.000045521163,0.00006761296,0.0001100569,0.000013263747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003375951,0.0004834844,0.00030267343,0.0007859066,0.0003455173,0.0006539754,0.00066158996,0.00029877684,0.0025113798],"category_scores_gemma":[0.0010974355,0.00012725886,0.0001483256,0.0007282034,0.00037743436,0.0009113898,0.0002556223,0.00031152632,0.00080014305],"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":[0.0013457309,0.00016821241,0.0015182334,0.0005170492,0.00006216332,0.00062525977,0.00024989634,0.04894843,0.19245729,0.036188763,0.008597712,0.7093212],"study_design_scores_gemma":[0.00019599205,0.0008466788,0.001293681,0.000066437475,0.00006212268,0.00090230745,0.000088432,0.30490845,0.66097236,0.0058811805,0.024723072,0.000059327755],"about_ca_topic_score_codex":0.0011674245,"about_ca_topic_score_gemma":0.0012965896,"teacher_disagreement_score":0.0025113798,"about_ca_system_score_codex":0.00048630728,"about_ca_system_score_gemma":0.0004235461,"threshold_uncertainty_score":0.008401394},"labels":[],"label_agreement":null},{"id":"W2114206928","doi":"10.14778/2536206.2536214","title":"RACE","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Computer science; Speedup; Cache; Cloud computing; Parallel computing; Sequence (biology); Representation (politics); Multi-core processor; Contrast (vision); Scaling; Artificial intelligence; Operating system; Mathematics","score_opus":0.006947487662152172,"score_gpt":0.19577461303583504,"score_spread":0.18882712537368287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114206928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010011141,0.0025416687,0.40761036,0.0017539295,0.002598414,0.00091083214,0.05837656,0.35516146,0.16103561],"genre_scores_gemma":[0.085743695,0.0026418988,0.45338675,0.004722238,0.0010709119,0.002517344,0.18914764,0.0688385,0.19193101],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665713,0.0004999171,0.00026303428,0.0011565299,0.0009979099,0.00042552646],"domain_scores_gemma":[0.9967409,0.0007601096,0.00025361584,0.0012725338,0.00078164414,0.00019128251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021707201,0.001869461,0.0016425633,0.0016340245,0.0017866811,0.0036572686,0.003750796,0.0020778812,0.1181336],"category_scores_gemma":[0.0073691383,0.0012273215,0.0023449243,0.00216683,0.0007137096,0.0040007913,0.0034108334,0.0024266127,0.11139626],"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":[0.0014496258,0.00023957397,0.0034216589,0.0013508688,0.000209281,0.00031911788,0.00033458037,0.0056217695,0.020816408,0.05013237,0.668868,0.24723671],"study_design_scores_gemma":[0.00021166571,0.0001989789,0.0012962068,0.00013631245,0.00011101533,0.00052484986,0.00007459738,0.024553634,0.01734051,0.024581965,0.9308477,0.00012254584],"about_ca_topic_score_codex":0.0023260743,"about_ca_topic_score_gemma":0.002943098,"teacher_disagreement_score":0.1181336,"about_ca_system_score_codex":0.0009541815,"about_ca_system_score_gemma":0.0025164522,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2114358253","doi":"10.1109/ccece.1993.332371","title":"An object-oriented And/Or graph inference engine","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Lakehead University","funders":"Javna Agencija za Raziskovalno Dejavnost RS","keywords":"Computer science; Inference; Graph; Backtracking; Prolog; Inference engine; Theoretical computer science; Programming language; Artificial intelligence","score_opus":0.02043279706407538,"score_gpt":0.256316197823969,"score_spread":0.23588340075989364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114358253","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001859756,0.00014489527,0.9875471,0.00021923313,0.000050138926,0.00017793298,0.00031085053,0.0061177504,0.003572458],"genre_scores_gemma":[0.02320155,0.00026830594,0.97003156,0.00029524518,0.00003172968,0.00011367908,0.00072726555,0.00036606926,0.0049646804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862146,0.00021532073,0.00014545048,0.00028721712,0.00062447233,0.000105967854],"domain_scores_gemma":[0.9988675,0.00046763965,0.00007500001,0.000261631,0.00027838312,0.0000498361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024793528,0.00062639057,0.00090085383,0.0020744877,0.0008815764,0.0030897697,0.0035738,0.0013105808,0.006305921],"category_scores_gemma":[0.0047277454,0.0007488707,0.0017714376,0.0014875209,0.00096645724,0.0041598296,0.0014494874,0.0013928887,0.0025507899],"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":[0.00020820383,0.00021683039,0.0015931815,0.00059237075,0.00022851978,0.0003978753,0.00037535653,0.05574771,0.009800851,0.4493318,0.019361421,0.46214584],"study_design_scores_gemma":[0.00010722513,0.000051202147,0.00041698548,0.00010711698,0.00022597835,0.0003085362,0.00013316059,0.56313246,0.020291455,0.29832393,0.11683262,0.000069326525],"about_ca_topic_score_codex":0.008098566,"about_ca_topic_score_gemma":0.012897293,"teacher_disagreement_score":0.008098566,"about_ca_system_score_codex":0.0013596598,"about_ca_system_score_gemma":0.00285367,"threshold_uncertainty_score":0.021095455},"labels":[],"label_agreement":null},{"id":"W2114590489","doi":"10.1109/aero.2002.1036115","title":"Greedy adaptive Fano coding","year":2003,"lang":"en","type":"article","venue":"Proceedings - IEEE Aerospace Conference","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Huffman coding; Computer science; Algorithm; Decoding methods; Greedy algorithm; Adaptive coding; Binary number; Binary code; Theoretical computer science; Coding (social sciences); Shannon–Fano coding; Data compression; Lossless compression; Mathematics","score_opus":0.03740021934181804,"score_gpt":0.24360750396902078,"score_spread":0.20620728462720275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114590489","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01157611,0.00033625436,0.9803342,0.00015561402,0.00007484779,0.0000790208,0.00007017238,0.00030790575,0.007065871],"genre_scores_gemma":[0.32130536,0.0005893308,0.6696572,0.00030613804,0.00009163817,0.00027870835,0.00026539265,0.00012756062,0.0073786722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99944764,0.00013842132,0.000022414482,0.00007731842,0.00023871688,0.00007547975],"domain_scores_gemma":[0.999321,0.00032433003,0.00004665146,0.00016756587,0.00011322233,0.000027275886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053137465,0.0004754689,0.0004716275,0.00090251415,0.0007260688,0.00055167486,0.0009792098,0.000542984,0.002448364],"category_scores_gemma":[0.0025754746,0.00020608245,0.00032864945,0.0008622421,0.000960978,0.0010735722,0.0007802017,0.0006303035,0.00064452935],"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":[0.0002685885,0.000051741823,0.00078949064,0.00013071975,0.00003083767,0.00017394064,0.00018907557,0.16986611,0.029569985,0.44101962,0.0066665043,0.35124338],"study_design_scores_gemma":[0.000052230014,0.00010344207,0.00032422176,0.00005294708,0.00001801305,0.00040335854,0.00005105564,0.798505,0.020376578,0.15330435,0.026759176,0.000049640472],"about_ca_topic_score_codex":0.0014305646,"about_ca_topic_score_gemma":0.0023821194,"teacher_disagreement_score":0.002448364,"about_ca_system_score_codex":0.00059508736,"about_ca_system_score_gemma":0.0007896824,"threshold_uncertainty_score":0.008190572},"labels":[],"label_agreement":null},{"id":"W2114670894","doi":"10.1109/aina.2008.97","title":"Parallel Computation of Similarity Measures Using an FPGA-Based Processor Array","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Field-programmable gate array; Computation; Similarity (geometry); Parallel computing; Computer engineering; Computer architecture; Vector processor; Software; Set (abstract data type); Data mining; Computer hardware; Algorithm; Artificial intelligence","score_opus":0.09628933308418298,"score_gpt":0.30126841127032306,"score_spread":0.20497907818614008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114670894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104460455,0.00028780632,0.88848865,0.00018712667,0.00009216729,0.00008700207,0.00009021669,0.002498439,0.0038081245],"genre_scores_gemma":[0.35616252,0.00021419332,0.6407278,0.00007870795,0.00004808018,0.00012478759,0.00024913013,0.000039167906,0.0023555574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966586,0.00006957951,0.00003553265,0.00007196045,0.00012320101,0.000033893626],"domain_scores_gemma":[0.9994184,0.0002415599,0.00004211981,0.00009580671,0.00017845634,0.000023627232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040227635,0.00037509872,0.00050697406,0.00081388484,0.000303743,0.00073421525,0.0006916651,0.0002991699,0.0021749362],"category_scores_gemma":[0.0014198167,0.00019716981,0.0002209737,0.000977315,0.0002418839,0.0007999022,0.00037449846,0.00031722497,0.00064383197],"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":[0.0010057818,0.0001735931,0.002816457,0.00019427476,0.00012531482,0.00042213852,0.00017333536,0.15974766,0.12270801,0.017063715,0.005112028,0.6904577],"study_design_scores_gemma":[0.00011306605,0.00042531698,0.0012424197,0.000021435295,0.00004471348,0.00037887,0.00007926239,0.91503906,0.06927406,0.0063442127,0.0070105097,0.000026945616],"about_ca_topic_score_codex":0.0011193223,"about_ca_topic_score_gemma":0.0014371393,"teacher_disagreement_score":0.0021749362,"about_ca_system_score_codex":0.0003824656,"about_ca_system_score_gemma":0.00051624223,"threshold_uncertainty_score":0.007275939},"labels":[],"label_agreement":null},{"id":"W2114790712","doi":"10.1006/jagm.2000.1151","title":"Space Efficient Suffix Trees","year":2001,"lang":"en","type":"article","venue":"Journal of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Space (punctuation); Computer science; Suffix tree; Artificial intelligence; Mathematics; Combinatorics; Linguistics; Philosophy","score_opus":0.014614309316282275,"score_gpt":0.2550175803153401,"score_spread":0.24040327099905784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114790712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10423997,0.004424814,0.82062536,0.0033561303,0.0011909201,0.00034450233,0.0038007093,0.012514461,0.049503084],"genre_scores_gemma":[0.35551605,0.0020740193,0.58675104,0.00088095356,0.0007027655,0.0003725487,0.009819175,0.0015402195,0.042343136],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982029,0.0003337337,0.00021831506,0.00029476793,0.00077896507,0.00017127478],"domain_scores_gemma":[0.9951782,0.0016779638,0.0002082096,0.0019203618,0.0008759894,0.00013925442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008241601,0.000697427,0.0012686332,0.001747667,0.0014424723,0.0028423502,0.0014597574,0.0013471434,0.017462796],"category_scores_gemma":[0.0058754063,0.00061386405,0.00084314874,0.004259832,0.0009091084,0.0062706717,0.0024984884,0.0017472769,0.006416777],"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":[0.00096751726,0.0004886262,0.0012106932,0.00041058235,0.00010187127,0.00022576422,0.00037524215,0.029160986,0.03391625,0.14771736,0.06560559,0.7198195],"study_design_scores_gemma":[0.00025890034,0.00054134865,0.00081148115,0.0001549269,0.000168377,0.0011735787,0.00039916282,0.3190011,0.0679945,0.5031661,0.10625884,0.00007174397],"about_ca_topic_score_codex":0.0006067025,"about_ca_topic_score_gemma":0.0013806912,"teacher_disagreement_score":0.017462796,"about_ca_system_score_codex":0.0007540916,"about_ca_system_score_gemma":0.0016732655,"threshold_uncertainty_score":0.05841887},"labels":[],"label_agreement":null},{"id":"W2114931329","doi":"10.1093/bib/bbu029","title":"Correcting Illumina data","year":2014,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Scalability; Data mining; Database","score_opus":0.026524684076357094,"score_gpt":0.25320954403913576,"score_spread":0.22668485996277865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114931329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020747025,0.0031358493,0.83993316,0.001207767,0.005039038,0.0012042809,0.04563978,0.06682842,0.016264718],"genre_scores_gemma":[0.029970558,0.0016658144,0.87919545,0.0009403785,0.0004111214,0.0012221694,0.05793546,0.010187204,0.018471776],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99243426,0.001028317,0.0006931737,0.0014650498,0.004003965,0.00037519206],"domain_scores_gemma":[0.98164684,0.003242859,0.0008577836,0.0068753664,0.007213126,0.00016410604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050132163,0.0027044206,0.0021142513,0.0060350783,0.0018945896,0.0030322124,0.0027410213,0.0017135091,0.024032125],"category_scores_gemma":[0.030723058,0.0010371128,0.001978208,0.008662373,0.00074417045,0.0017999302,0.0022911048,0.0027424581,0.030622024],"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":[0.00072869833,0.00010933755,0.00759336,0.0018668496,0.00027275004,0.0005457545,0.00056575035,0.01299562,0.06699471,0.013373704,0.2262376,0.6687159],"study_design_scores_gemma":[0.0000967442,0.0001636269,0.0073415623,0.00039288754,0.00027282583,0.001568403,0.00037887582,0.055763684,0.3160478,0.023216728,0.5944254,0.0003314445],"about_ca_topic_score_codex":0.0031284883,"about_ca_topic_score_gemma":0.0035135613,"teacher_disagreement_score":0.024032125,"about_ca_system_score_codex":0.0009837736,"about_ca_system_score_gemma":0.0022106394,"threshold_uncertainty_score":0.08039546},"labels":[],"label_agreement":null},{"id":"W2115926180","doi":"10.1112/plms/pdl018","title":"Universal finitary codes with exponential tails","year":2006,"lang":"en","type":"article","venue":"Proceedings of the London Mathematical Society","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Finitary; Mathematics; Homomorphism; Bernoulli process; Alphabet; Discrete mathematics; Bernoulli's principle; Markov chain; Entropy (arrow of time); Kullback–Leibler divergence; Exponential function; Combinatorics; Exponential family; Statistics","score_opus":0.006549534070358664,"score_gpt":0.1917919735641207,"score_spread":0.18524243949376204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115926180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21231847,0.00080261665,0.7705802,0.0009144591,0.00011570181,0.000076219316,0.00029858848,0.0011414634,0.013752436],"genre_scores_gemma":[0.9506251,0.00038777266,0.042626288,0.00035188542,0.00011627744,0.00014008813,0.0002453889,0.00015646333,0.00535065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99836856,0.00029513446,0.000089943554,0.00032950664,0.00054967793,0.0003670885],"domain_scores_gemma":[0.98812985,0.006690562,0.0008467427,0.0025873743,0.0012372753,0.00050815346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017704497,0.0005033135,0.00058940623,0.0013284525,0.0010264154,0.001276902,0.0009855378,0.0008370218,0.002188162],"category_scores_gemma":[0.016225165,0.00051873666,0.00053021783,0.0010566013,0.0026215569,0.003310128,0.0037778802,0.0020321414,0.00049623504],"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":[0.0002019783,0.000050560153,0.0014778859,0.000093444556,0.000022489252,0.00033834,0.00059275137,0.03320807,0.0072320555,0.9266876,0.0010942955,0.02900041],"study_design_scores_gemma":[0.000035714038,0.000064311826,0.0005874298,0.000060183047,0.000018658067,0.00036717058,0.00006417838,0.17190674,0.011392007,0.8119659,0.003495493,0.000042267082],"about_ca_topic_score_codex":0.0006631745,"about_ca_topic_score_gemma":0.00078408554,"teacher_disagreement_score":0.002188162,"about_ca_system_score_codex":0.0011681292,"about_ca_system_score_gemma":0.0010465552,"threshold_uncertainty_score":0.009363174},"labels":[],"label_agreement":null},{"id":"W2116441444","doi":"","title":"On The Practice of B-ing Earley","year":2007,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Computer science","score_opus":0.012495973227861154,"score_gpt":0.23890579344620244,"score_spread":0.22640982021834127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116441444","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043471856,0.0013328564,0.94358647,0.0052114977,0.00039525723,0.00012698262,0.00011494976,0.003162563,0.041722193],"genre_scores_gemma":[0.0632557,0.0016756558,0.9002597,0.0023190756,0.00026164,0.00023339043,0.00021735011,0.002216705,0.029560857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923719,0.0029127856,0.00050027977,0.0014976715,0.0023430297,0.00037425794],"domain_scores_gemma":[0.9853476,0.008514262,0.00048058308,0.0035866215,0.0017762991,0.00029467637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006885212,0.0010139128,0.00077155157,0.0027225153,0.0031015084,0.004651751,0.0025741826,0.0020119462,0.017540617],"category_scores_gemma":[0.027562667,0.0011936778,0.00095306395,0.0037908722,0.0077091716,0.011784287,0.0044430783,0.0048950054,0.01179222],"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":[0.0001334473,0.000050154737,0.0005756175,0.00015788579,0.000020244679,0.00008457379,0.0006613506,0.0029401334,0.0024098174,0.6619088,0.027726496,0.30333146],"study_design_scores_gemma":[0.00007496241,0.000084555424,0.0003710436,0.000256313,0.000030595806,0.0004401376,0.00036064012,0.029058496,0.010123565,0.6459023,0.31316647,0.00013099748],"about_ca_topic_score_codex":0.0061910325,"about_ca_topic_score_gemma":0.00509358,"teacher_disagreement_score":0.017540617,"about_ca_system_score_codex":0.002212581,"about_ca_system_score_gemma":0.0040156012,"threshold_uncertainty_score":0.058679163},"labels":[],"label_agreement":null},{"id":"W2118531336","doi":"10.1109/itw.2002.1115457","title":"Lossy universal source coding for individual sequences","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Ergodic theory; Distortion function; Mathematics; Measure (data warehouse); Distortion (music); Convexity; Sequence (biology); Rate–distortion theory; Algorithm; Discrete mathematics; Computer science; Data compression; Decoding methods; Pure mathematics","score_opus":0.030420847912175277,"score_gpt":0.2546141070338537,"score_spread":0.2241932591216784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118531336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02008628,0.0008493843,0.9731357,0.00029037116,0.000058381866,0.000030257394,0.000168707,0.00028346785,0.005097468],"genre_scores_gemma":[0.7517607,0.0020975396,0.23262128,0.00028266222,0.00018402605,0.00017962532,0.0005392371,0.00013832453,0.012196467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907196,0.00020677254,0.000052069117,0.00015750948,0.00041211263,0.00009960892],"domain_scores_gemma":[0.9981989,0.00072876544,0.00024337758,0.000530917,0.00024133695,0.000056763696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001125013,0.00048875523,0.00077776687,0.0009445745,0.00030528227,0.0011932896,0.0009703272,0.0006048627,0.0017007021],"category_scores_gemma":[0.0065817665,0.0002803622,0.0003709585,0.0015299743,0.001148314,0.0020089573,0.0019658222,0.0010441119,0.0005560928],"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":[0.00020716376,0.00002833977,0.00035626855,0.00021414422,0.000035154095,0.00017278403,0.00018573813,0.14821206,0.010020102,0.708882,0.002830775,0.1288555],"study_design_scores_gemma":[0.000019418836,0.00005875624,0.00030026227,0.00007163866,0.000022990653,0.00027366242,0.000030083022,0.72289556,0.009016734,0.26045516,0.006833384,0.000022362201],"about_ca_topic_score_codex":0.0012146345,"about_ca_topic_score_gemma":0.0010545081,"teacher_disagreement_score":0.0017007021,"about_ca_system_score_codex":0.0014313883,"about_ca_system_score_gemma":0.0008506998,"threshold_uncertainty_score":0.010385513},"labels":[],"label_agreement":null},{"id":"W2119232608","doi":"10.1109/infcom.2005.1498371","title":"Delayed-dictionary compression for packet networks","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Israel Science Foundation","keywords":"Computer science; Data compression; Network packet; Packet analyzer; Compression ratio; Stateless protocol; Compression (physics); Computer network; Latency (audio); Decoding methods; Data compression ratio; Processing delay; Real-time computing; Algorithm; Transmission delay; Image compression; Artificial intelligence; Telecommunications","score_opus":0.01266738600533073,"score_gpt":0.2537165124759618,"score_spread":0.24104912647063104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119232608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01764269,0.0021545067,0.9740838,0.0003868233,0.0002508138,0.00012774291,0.00021123904,0.0008822367,0.0042601973],"genre_scores_gemma":[0.26402298,0.00366545,0.72113806,0.00025144525,0.00047810326,0.00026688568,0.0010646934,0.00021927379,0.008893149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996092,0.00006842768,0.000025936477,0.000060676663,0.0002100942,0.000025726686],"domain_scores_gemma":[0.9991394,0.00038040426,0.00005838152,0.0002089937,0.00019386744,0.00001886113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038093966,0.0004988755,0.00037611942,0.0007329506,0.00041878552,0.00069884013,0.0007959767,0.0005122923,0.001969207],"category_scores_gemma":[0.0021818194,0.0001484402,0.00023951233,0.0012820227,0.00055181974,0.0013301838,0.0006268651,0.0007536059,0.00061503035],"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":[0.00024006209,0.00006191749,0.000865819,0.0003098722,0.000035212128,0.000332713,0.00011901833,0.08638271,0.04188254,0.09931723,0.008682521,0.7617705],"study_design_scores_gemma":[0.00004173001,0.0001802275,0.0008432915,0.000060006,0.000032697524,0.0008743383,0.00006368214,0.82402354,0.07208525,0.05202017,0.04973728,0.00003780217],"about_ca_topic_score_codex":0.0015945786,"about_ca_topic_score_gemma":0.0013872286,"teacher_disagreement_score":0.001969207,"about_ca_system_score_codex":0.0006002363,"about_ca_system_score_gemma":0.00047562507,"threshold_uncertainty_score":0.006587684},"labels":[],"label_agreement":null},{"id":"W2119670115","doi":"10.1109/bibe.2003.1188947","title":"An algorithm to reconstruct a target DNA sequence from its spectrum connected at a given level","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Substring; Sequence (biology); Algorithm; DNA; Sequencing by hybridization; DNA sequencing; Sequence logo; Set (abstract data type); Combinatorics; Computer science; Mathematics; Biology; Genetics; Consensus sequence; Base sequence","score_opus":0.043979272708935875,"score_gpt":0.2689294272750023,"score_spread":0.22495015456606643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119670115","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015881496,0.0002932551,0.9781546,0.00030266188,0.00006375422,0.00022958117,0.00036265308,0.00251167,0.0022003953],"genre_scores_gemma":[0.045152053,0.00017661658,0.94953233,0.00015537725,0.00003086986,0.00036700375,0.0016267098,0.00013648717,0.0028226278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994867,0.00007729268,0.00004998202,0.00019735497,0.00012916775,0.000059545506],"domain_scores_gemma":[0.9989924,0.00047186867,0.00010277501,0.0002608843,0.0001321312,0.00003984721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008041024,0.001025184,0.00089006685,0.0018276776,0.00082707213,0.0012243924,0.0017267468,0.0019266905,0.005406597],"category_scores_gemma":[0.0023895032,0.0005546485,0.0011555039,0.0017141292,0.00097521755,0.0022486462,0.0014050651,0.0014790869,0.0026621304],"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":[0.0005390472,0.00033978696,0.0022680673,0.00054983684,0.00016569482,0.00027767773,0.00036327023,0.062804215,0.036362648,0.0281925,0.015342502,0.8527947],"study_design_scores_gemma":[0.00029389584,0.00034675727,0.0017114275,0.000105837215,0.00013910075,0.0014444307,0.0004254178,0.8438467,0.046462614,0.08043594,0.024710942,0.000076965545],"about_ca_topic_score_codex":0.0013828685,"about_ca_topic_score_gemma":0.0020629636,"teacher_disagreement_score":0.005406597,"about_ca_system_score_codex":0.0008193518,"about_ca_system_score_gemma":0.0015934024,"threshold_uncertainty_score":0.01808685},"labels":[],"label_agreement":null},{"id":"W2119878143","doi":"10.1109/dcc.1997.582019","title":"A corpus for the evaluation of lossless compression algorithms","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":201,"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":"Lossless compression; Computer science; Data compression; Compression (physics); Algorithm; Lossy compression; Natural language processing; Compression ratio; The Internet; Artificial intelligence; Information retrieval; World Wide Web","score_opus":0.125841513504027,"score_gpt":0.32627074923196603,"score_spread":0.20042923572793903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119878143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36264104,0.015562064,0.21158768,0.004254941,0.0026842384,0.013239466,0.27180368,0.016372876,0.10185397],"genre_scores_gemma":[0.2563574,0.00392528,0.2779827,0.0007410576,0.000758428,0.013706927,0.4103568,0.003941732,0.03222965],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98941237,0.0032018535,0.001412732,0.001002439,0.0046808384,0.0002897019],"domain_scores_gemma":[0.93138164,0.033406407,0.0019355608,0.011622733,0.02038937,0.0012643681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052491147,0.0013395438,0.0013514766,0.008991401,0.003543436,0.0021519843,0.002712629,0.0017852613,0.016276194],"category_scores_gemma":[0.046883922,0.00065898284,0.0007654684,0.010915911,0.002545881,0.0030414532,0.0029824688,0.0020327053,0.006437319],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009882909,0.0014881144,0.004758611,0.006948742,0.00016883173,0.0015020996,0.004133499,0.011069611,0.023946969,0.016440524,0.42781895,0.50073576],"study_design_scores_gemma":[0.00094929244,0.0012641093,0.054413248,0.0016142258,0.00020213271,0.0045393133,0.0040146303,0.045227386,0.06345784,0.013392123,0.8104768,0.00044890627],"about_ca_topic_score_codex":0.011609438,"about_ca_topic_score_gemma":0.016743165,"teacher_disagreement_score":0.016276194,"about_ca_system_score_codex":0.0025987222,"about_ca_system_score_gemma":0.0023983584,"threshold_uncertainty_score":0.05444926},"labels":[],"label_agreement":null},{"id":"W2120049702","doi":"10.1109/ccece.2009.5090220","title":"Modeling tryptic digestion on the Cell BE processor","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; SIMD; Parallel computing; String searching algorithm; String (physics); Algorithm; Data structure; Programming language","score_opus":0.027123754146308295,"score_gpt":0.24120118915746408,"score_spread":0.21407743501115578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120049702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81905186,0.000430508,0.15295164,0.00047359717,0.00007935584,0.00015039158,0.0005356185,0.00067498477,0.025651976],"genre_scores_gemma":[0.95974135,0.00044157947,0.030556528,0.00010636505,0.000009505896,0.00013469314,0.00032237056,0.00008335474,0.008604169],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990845,0.000016726246,0.0000032544704,0.000015719046,0.00003009998,0.00002575575],"domain_scores_gemma":[0.99973994,0.00014047403,0.00002523027,0.000023171218,0.000050098446,0.000021058537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014582516,0.00036427876,0.0003759255,0.00017503633,0.00031021662,0.00069078006,0.00081946613,0.00078841986,0.0030359656],"category_scores_gemma":[0.0008571093,0.00021770399,0.00026329205,0.00037969337,0.0003292748,0.00072688295,0.0003270803,0.0005185123,0.00049909524],"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":[0.00015874393,0.00004455968,0.00114294,0.00004443255,0.000008408716,0.00014555152,0.000055788547,0.98280185,0.007845411,0.004227435,0.0003776057,0.003147244],"study_design_scores_gemma":[0.000012460216,0.000029618379,0.0001907786,0.000001695673,0.000003225257,0.000011745982,0.000010837894,0.9970337,0.0018208798,0.00048354943,0.0003984416,0.000003048488],"about_ca_topic_score_codex":0.0075522857,"about_ca_topic_score_gemma":0.003259508,"teacher_disagreement_score":0.0075522857,"about_ca_system_score_codex":0.00047832346,"about_ca_system_score_gemma":0.0006821228,"threshold_uncertainty_score":0.015016675},"labels":[],"label_agreement":null},{"id":"W2121102942","doi":"10.1016/j.tcs.2015.03.011","title":"Low space data structures for geometric range mode query","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Manitoba","funders":"Canada Research Chairs","keywords":"Multiset; Range (aeronautics); Data structure; Set (abstract data type); Space (punctuation); Range query (database); Mode (computer interface); Combinatorics; Point (geometry); Mathematics; Word (group theory); Computer science; Sargable; Web search query; Geometry; Information retrieval; Search engine","score_opus":0.04144772785392008,"score_gpt":0.30845009617466385,"score_spread":0.26700236832074375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121102942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14310095,0.0029685278,0.8270153,0.0022883334,0.00028564446,0.00029185473,0.0027411333,0.007133234,0.014174986],"genre_scores_gemma":[0.66859335,0.00080780406,0.313999,0.0007799501,0.00030912046,0.0005276823,0.0042574513,0.00070966384,0.010016052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981066,0.00024486525,0.0001562021,0.00018816862,0.001097355,0.00020671681],"domain_scores_gemma":[0.99507684,0.0013781748,0.00033536213,0.0024768435,0.0005983924,0.00013434503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001088806,0.0005715567,0.0011729448,0.0020933542,0.00095317425,0.0027692914,0.0019309251,0.001022717,0.009826645],"category_scores_gemma":[0.0077995984,0.00039841622,0.00046389963,0.0041672788,0.0012343099,0.0054711998,0.0039289063,0.0017783949,0.0021359164],"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":[0.0027985687,0.0005237949,0.004955366,0.0006831124,0.00009882323,0.00023171086,0.000899065,0.04989031,0.034538046,0.31839666,0.05616566,0.5308189],"study_design_scores_gemma":[0.0003547822,0.0006730176,0.0015416577,0.00012404929,0.000105122446,0.0006446649,0.00055848673,0.38232,0.03391991,0.5487845,0.03086716,0.000106600644],"about_ca_topic_score_codex":0.0012572974,"about_ca_topic_score_gemma":0.0021467162,"teacher_disagreement_score":0.009826645,"about_ca_system_score_codex":0.0013596197,"about_ca_system_score_gemma":0.0014133777,"threshold_uncertainty_score":0.032873333},"labels":[],"label_agreement":null},{"id":"W2121104041","doi":"10.1109/dcc.1994.305933","title":"Architectural advances in the VLSI implementation of arithmetic coding for binary image compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Toronto","funders":"","keywords":"Very-large-scale integration; Arithmetic; Computer science; Arithmetic coding; Data compression; Image compression; Binary number; Coding (social sciences); Context-adaptive binary arithmetic coding; Computer architecture; Parallel computing; Image processing; Algorithm; Artificial intelligence; Image (mathematics); Mathematics; Embedded system","score_opus":0.023085141879503505,"score_gpt":0.31458277109734656,"score_spread":0.29149762921784306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121104041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042531766,0.02407623,0.87676376,0.0020418488,0.0008193863,0.00012696658,0.00009490314,0.0016956767,0.051849492],"genre_scores_gemma":[0.31549868,0.032337952,0.6298068,0.0007346398,0.00081890385,0.0000993952,0.00041913698,0.00025041445,0.020034065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974877,0.000040437742,0.00002307774,0.00002169856,0.00014320832,0.000022763177],"domain_scores_gemma":[0.99944013,0.00016387866,0.00003700408,0.00008103056,0.00026271332,0.000015175673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046784774,0.00037690476,0.00018428678,0.00067816913,0.00027714888,0.00084230275,0.0008298525,0.00040842977,0.0039681233],"category_scores_gemma":[0.0017918276,0.00032130972,0.00027685915,0.0008992168,0.00047484817,0.0018292449,0.0004215008,0.00097033236,0.001367652],"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":[0.00015499596,0.000076237324,0.0010360166,0.00082852086,0.000036293335,0.00025766416,0.00023512148,0.031017412,0.12242395,0.14847307,0.00576726,0.68969345],"study_design_scores_gemma":[0.000115252216,0.001190994,0.0022922882,0.0004052642,0.0001809409,0.0023050883,0.00020299041,0.23435275,0.20858763,0.07897081,0.47127202,0.0001239198],"about_ca_topic_score_codex":0.001007109,"about_ca_topic_score_gemma":0.0018778383,"teacher_disagreement_score":0.0039681233,"about_ca_system_score_codex":0.0005195955,"about_ca_system_score_gemma":0.00055051956,"threshold_uncertainty_score":0.01327467},"labels":[],"label_agreement":null},{"id":"W2121339777","doi":"10.1109/isit.2003.1228492","title":"Lossless image compression using context-dependent multilevel 2D pattern matching","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Lossless compression; Code (set theory); Computer science; Compression (physics); Data compression; Lossy compression; Context (archaeology); Image compression; Matching (statistics); Algorithm; Image (mathematics); Theoretical computer science; Artificial intelligence; Image processing; Mathematics; Programming language; Geography; Statistics","score_opus":0.03354885884228522,"score_gpt":0.28293942151878254,"score_spread":0.2493905626764973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121339777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19923306,0.0006314195,0.79533136,0.00022964868,0.00007979568,0.00007451549,0.00012673673,0.0005612714,0.0037321546],"genre_scores_gemma":[0.70821404,0.00040489912,0.28853354,0.00020891534,0.00005370601,0.00009546998,0.0001534236,0.000059681515,0.0022763123],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997285,0.00003362264,0.000011340658,0.00003253222,0.00017161132,0.000022401204],"domain_scores_gemma":[0.9994796,0.00020290876,0.00006480716,0.00014139347,0.00009443723,0.00001680437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002241713,0.00028639717,0.00031852175,0.0005035825,0.00017499327,0.00050230534,0.00045390922,0.0005883216,0.0010086216],"category_scores_gemma":[0.001863533,0.0001308374,0.00019801383,0.00067273295,0.0003080366,0.0008955409,0.0005695158,0.00044263285,0.00033044902],"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":[0.0005014829,0.00011035222,0.0017835018,0.0002402869,0.000055755085,0.0005308622,0.0001676878,0.08938663,0.43791652,0.040133454,0.0015370613,0.42763636],"study_design_scores_gemma":[0.00003501231,0.00021121225,0.0016978859,0.000028142704,0.000017959135,0.0010268019,0.00003113462,0.7810534,0.20118918,0.010700558,0.003972742,0.00003589038],"about_ca_topic_score_codex":0.00040881423,"about_ca_topic_score_gemma":0.00065001997,"teacher_disagreement_score":0.0010086216,"about_ca_system_score_codex":0.00025973335,"about_ca_system_score_gemma":0.00021414264,"threshold_uncertainty_score":0.003374219},"labels":[],"label_agreement":null},{"id":"W2121404865","doi":"10.1007/s13389-015-0110-5","title":"Faster 64-bit universal hashing using carry-less multiplications","year":2015,"lang":"en","type":"article","venue":"Journal of Cryptographic Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hash function; Byte; Computer science; Carry (investment); Arithmetic; Parallel computing; Universal hashing; Bit (key); Set (abstract data type); Double hashing; Multiplication (music); Cryptographic hash function; Mathematics; Computer hardware; Computer network; Combinatorics; Computer security; Programming language","score_opus":0.0391017793814229,"score_gpt":0.24650318069680693,"score_spread":0.20740140131538404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121404865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19109088,0.00569172,0.76857364,0.00074710295,0.0010547582,0.0003971002,0.00052696513,0.010897947,0.02101979],"genre_scores_gemma":[0.5872691,0.00071487203,0.39445397,0.0004421358,0.00025333863,0.00017434539,0.001038731,0.00032690543,0.015326517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987276,0.00017394294,0.00009324321,0.00020501978,0.0006114497,0.0001886736],"domain_scores_gemma":[0.9987016,0.00039161343,0.00010368206,0.0005234368,0.00021450501,0.000065183376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009890081,0.00087306526,0.0011286164,0.0013482955,0.0007311305,0.0012540127,0.0010546101,0.00060220977,0.013929967],"category_scores_gemma":[0.0025230483,0.0005101033,0.0005773814,0.001669808,0.0006610929,0.0034207806,0.001882968,0.0007751391,0.0044117086],"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":[0.001789177,0.00029249574,0.0018856494,0.00046422967,0.00015232702,0.0002048924,0.00032690653,0.008832847,0.07773141,0.048256706,0.013360498,0.84670293],"study_design_scores_gemma":[0.001762179,0.002582035,0.007252275,0.0004988051,0.00060667965,0.0030944804,0.000722585,0.40585166,0.32903183,0.12749572,0.12055064,0.00055114884],"about_ca_topic_score_codex":0.0013600069,"about_ca_topic_score_gemma":0.0024498517,"teacher_disagreement_score":0.013929967,"about_ca_system_score_codex":0.0007758544,"about_ca_system_score_gemma":0.0016686607,"threshold_uncertainty_score":0.04660034},"labels":[],"label_agreement":null},{"id":"W2121925658","doi":"10.1109/ccece.1993.332432","title":"A parallel computer for digital signal processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Uniprocessor system; Computer science; Synchronization (alternating current); Signal processing; Viterbi decoder; Simple (philosophy); Parallel computing; Digital signal processing; Viterbi algorithm; Fast Fourier transform; Computer hardware; Decoding methods; Algorithm; Multiprocessing; Telecommunications; Channel (broadcasting)","score_opus":0.028982343210232693,"score_gpt":0.2373961332742753,"score_spread":0.20841379006404262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121925658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056158225,0.025103893,0.8853419,0.002726497,0.0021547028,0.00019586104,0.00020495722,0.0024265395,0.0762298],"genre_scores_gemma":[0.14555535,0.021930696,0.7174553,0.0017544562,0.0026521932,0.0009049383,0.0007462196,0.0005235336,0.10847728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951625,0.00015882753,0.000023738097,0.00008208977,0.00019304137,0.00002612476],"domain_scores_gemma":[0.9996815,0.00012006797,0.000015383743,0.000076718716,0.00008610077,0.000020366237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003901089,0.0006226654,0.00046649596,0.0006716554,0.0005915603,0.0013058193,0.00061291637,0.00095486094,0.014450731],"category_scores_gemma":[0.0010303579,0.00019201133,0.00026791927,0.0010535482,0.0010550438,0.0018997787,0.0007426353,0.0016093818,0.0064015156],"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":[0.00011161591,0.000051949555,0.0002753546,0.0004839117,0.000038812803,0.0002794186,0.00020396257,0.010029495,0.013158635,0.5807249,0.04940905,0.34523284],"study_design_scores_gemma":[0.000060300557,0.00015589129,0.0003398387,0.00018007452,0.000025795898,0.0008811131,0.000045568715,0.056666993,0.008338299,0.25524545,0.67801696,0.000043700726],"about_ca_topic_score_codex":0.0005317699,"about_ca_topic_score_gemma":0.00046077013,"teacher_disagreement_score":0.014450731,"about_ca_system_score_codex":0.00066224317,"about_ca_system_score_gemma":0.00055067224,"threshold_uncertainty_score":0.048342526},"labels":[],"label_agreement":null},{"id":"W2122131968","doi":"10.1109/ccece.2000.849758","title":"Multithreaded implementation of a biomolecular sequence alignment algorithm-software/information technology","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Alignment-free sequence analysis; Multiple sequence alignment; Dynamic programming; Computer science; Sequence alignment; Smith–Waterman algorithm; Structural alignment; Sequence (biology); Tree (set theory); Algorithm; Heuristic; Pairwise comparison; Software; Artificial intelligence; Mathematics; Peptide sequence; Biology","score_opus":0.020364890493841426,"score_gpt":0.2750032255253125,"score_spread":0.25463833503147104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122131968","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047737737,0.00019253044,0.9717458,0.00007623602,0.00010457252,0.00014007142,0.00018450026,0.0180168,0.0047656856],"genre_scores_gemma":[0.05110071,0.00020417818,0.93964404,0.000119792196,0.000040739014,0.00037836944,0.0012150088,0.0018658771,0.005431203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989968,0.00017030933,0.00012805492,0.00020081703,0.00037644792,0.00012760043],"domain_scores_gemma":[0.9991122,0.00017789367,0.000058934285,0.00029630755,0.00028200026,0.00007261523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011870532,0.00065580977,0.00073231733,0.00078398315,0.000630518,0.0014658008,0.001789246,0.00068852934,0.008156071],"category_scores_gemma":[0.0023097808,0.00057302014,0.0009115396,0.0009515202,0.00039186486,0.0013234231,0.0009198275,0.001732172,0.00481447],"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":[0.00071151566,0.0005767505,0.003219173,0.0005145227,0.00030912476,0.00051687704,0.00047602138,0.04423631,0.11212259,0.0752738,0.03925416,0.7227891],"study_design_scores_gemma":[0.0002482562,0.00039727945,0.0016195667,0.000093943534,0.00014780436,0.00065498403,0.00007279159,0.6426514,0.12812786,0.034098595,0.19176593,0.0001215227],"about_ca_topic_score_codex":0.0013543623,"about_ca_topic_score_gemma":0.0014051562,"teacher_disagreement_score":0.008156071,"about_ca_system_score_codex":0.00075188075,"about_ca_system_score_gemma":0.0013350504,"threshold_uncertainty_score":0.027284741},"labels":[],"label_agreement":null},{"id":"W2124602574","doi":"10.1145/502512.502558","title":"Induction of semantic classes from natural language text","year":2001,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Set (abstract data type); Task (project management); Space (punctuation); Natural language; Unsupervised learning; Information retrieval","score_opus":0.011606899307252857,"score_gpt":0.2518886837407619,"score_spread":0.24028178443350903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124602574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05537136,0.0008557125,0.92278,0.001192693,0.00027736233,0.00081989676,0.0044212546,0.0055949627,0.008686723],"genre_scores_gemma":[0.14451647,0.0005455428,0.8332618,0.00028499556,0.0002250358,0.0008640752,0.016787693,0.00042277327,0.0030916585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772495,0.0005281327,0.00020312746,0.0007042468,0.0006990386,0.00014053169],"domain_scores_gemma":[0.9941854,0.003513986,0.00048640126,0.0005615124,0.0010916609,0.00016107237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016725622,0.0009821595,0.00074979395,0.0067853807,0.0017425342,0.0013802929,0.0013521172,0.00088718557,0.0029527028],"category_scores_gemma":[0.008946538,0.00041159475,0.0012786466,0.0031226256,0.0013522009,0.003660142,0.001872757,0.0018863074,0.0018499021],"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":[0.00029482794,0.0004482083,0.0065777353,0.00065128773,0.00008358462,0.00028453878,0.0010290035,0.006236929,0.016681049,0.039778914,0.02406508,0.90386885],"study_design_scores_gemma":[0.00016887004,0.0002520733,0.014784674,0.00047914873,0.00020633798,0.0009713718,0.0021960302,0.46435267,0.061309997,0.3263514,0.12875858,0.00016888205],"about_ca_topic_score_codex":0.0019936764,"about_ca_topic_score_gemma":0.004000432,"teacher_disagreement_score":0.0067853807,"about_ca_system_score_codex":0.0012041487,"about_ca_system_score_gemma":0.002346931,"threshold_uncertainty_score":0.009877741},"labels":[],"label_agreement":null},{"id":"W2125099185","doi":"10.1109/cyberc.2010.60","title":"A New Top-Down Algorithm for Tree Inclusion","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Tree (set theory); Combinatorics; Matching (statistics); Computer science; Algorithm; Node (physics); XML; Mathematics; Discrete mathematics; Physics; World Wide Web; Statistics","score_opus":0.009271043576254736,"score_gpt":0.2549714707387515,"score_spread":0.24570042716249674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125099185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002378529,0.00052321644,0.9840357,0.0004142476,0.00025313525,0.00030532424,0.0007292253,0.00618032,0.0051803873],"genre_scores_gemma":[0.02199289,0.00034966297,0.96648514,0.00029524477,0.00012453803,0.00029126956,0.0020510626,0.0007674139,0.007642868],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99731547,0.00029809566,0.00021699187,0.00078514934,0.0010465515,0.00033767987],"domain_scores_gemma":[0.99769044,0.00069219095,0.000089295674,0.0007986178,0.000593796,0.00013556685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011024998,0.0020331792,0.0020726584,0.0023342986,0.0018476677,0.0038340676,0.0045415694,0.002032973,0.02096023],"category_scores_gemma":[0.0049265972,0.0010589128,0.0026719347,0.0032814262,0.00088207086,0.008145694,0.0052299653,0.0038036704,0.011122118],"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":[0.0002698716,0.0003473927,0.00045290403,0.0006122911,0.00008948637,0.00023063296,0.00019054812,0.024168734,0.0086590275,0.04226066,0.046363667,0.87635475],"study_design_scores_gemma":[0.00021956359,0.00023771139,0.00037641777,0.00016951373,0.00017749307,0.00069833023,0.00024807436,0.6543171,0.018278206,0.20774949,0.117432654,0.000095484786],"about_ca_topic_score_codex":0.005084618,"about_ca_topic_score_gemma":0.008873104,"teacher_disagreement_score":0.02096023,"about_ca_system_score_codex":0.001414263,"about_ca_system_score_gemma":0.003032609,"threshold_uncertainty_score":0.07011896},"labels":[],"label_agreement":null},{"id":"W2125423885","doi":"10.5120/16377-5867","title":"Compressing the Data Densely by New Geflochtener to Accelerate Web","year":2014,"lang":"en","type":"article","venue":"International Journal of Computer Applications","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science; Parsing; Bandwidth (computing); Data compression; The Internet; Compression ratio; Path (computing); Data mining; Algorithm; Artificial intelligence; World Wide Web; Computer network","score_opus":0.030493252029889346,"score_gpt":0.3077510108885582,"score_spread":0.2772577588586689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125423885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16516921,0.0032781097,0.80472445,0.0011083652,0.00049530366,0.0002484225,0.0012305726,0.013178217,0.010567405],"genre_scores_gemma":[0.33180326,0.001970341,0.64433455,0.0003440554,0.00020288103,0.00024112464,0.0024441862,0.0006999211,0.017959576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961793,0.00003780677,0.000032519754,0.000046920755,0.00022154911,0.000043217886],"domain_scores_gemma":[0.99958223,0.000105941916,0.000039759107,0.000113309834,0.0001418433,0.000016957367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036444777,0.0006355249,0.00044525872,0.0019646653,0.000550767,0.0009952855,0.00080649083,0.00063460186,0.0055598686],"category_scores_gemma":[0.001552331,0.00016792714,0.00044161943,0.0022636896,0.0005524099,0.0020171816,0.0007524007,0.00068956194,0.002150374],"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":[0.0006635611,0.00011151099,0.0018742062,0.0003355132,0.000041401396,0.0006534991,0.00048705444,0.014699314,0.15017545,0.014816101,0.011251798,0.8048906],"study_design_scores_gemma":[0.00011643825,0.0004201252,0.004114474,0.000118827455,0.000085146465,0.0022525557,0.0005401722,0.29497263,0.5923403,0.011285121,0.09361539,0.00013885462],"about_ca_topic_score_codex":0.0019894815,"about_ca_topic_score_gemma":0.0025728226,"teacher_disagreement_score":0.0055598686,"about_ca_system_score_codex":0.0005233433,"about_ca_system_score_gemma":0.00053405465,"threshold_uncertainty_score":0.01859957},"labels":[],"label_agreement":null},{"id":"W2125604134","doi":"10.1093/bioinformatics/16.1.41","title":"The early introduction of dynamic programming into computational biology","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Research Council Canada; American Mathematical Society","keywords":"Theme (computing); Field (mathematics); Sentence; Computer science; Mathematical economics; Mathematics; Artificial intelligence; World Wide Web","score_opus":0.0061490985847550295,"score_gpt":0.24222906463850982,"score_spread":0.23607996605375478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125604134","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031999613,0.08598342,0.7514456,0.053439997,0.0067934594,0.000111242785,0.00036794678,0.00062010397,0.09803836],"genre_scores_gemma":[0.29277351,0.1232373,0.4626629,0.029434131,0.024240794,0.0011827598,0.00072444696,0.0016220801,0.06412205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99335337,0.003170149,0.00033868363,0.0016890692,0.0011017076,0.0003469707],"domain_scores_gemma":[0.9819956,0.015403968,0.00032967643,0.0011160363,0.00076200324,0.00039282438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056943703,0.0014968286,0.001894557,0.0027534897,0.0018408947,0.005752147,0.002366635,0.0034553097,0.009683408],"category_scores_gemma":[0.018502446,0.0018415949,0.0018131853,0.003952179,0.015660973,0.01191199,0.0057966947,0.014727381,0.0027893996],"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":[0.000029041894,0.000012798649,0.00008513401,0.00020734544,0.000021390066,0.00004219522,0.00029925446,0.0024920825,0.00010218244,0.9566984,0.005782496,0.034227725],"study_design_scores_gemma":[0.000021037888,0.000024197909,0.000095413605,0.0002656618,0.000007715022,0.000095129035,0.000068020345,0.006211637,0.0002797997,0.81269157,0.18021227,0.000027550093],"about_ca_topic_score_codex":0.0029476814,"about_ca_topic_score_gemma":0.0014179022,"teacher_disagreement_score":0.009683408,"about_ca_system_score_codex":0.005775729,"about_ca_system_score_gemma":0.002929491,"threshold_uncertainty_score":0.04190606},"labels":[],"label_agreement":null},{"id":"W2125673305","doi":"10.1109/4234.901808","title":"An improved hashing function for IS-2000 quick paging channel","year":2001,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Paging; Computer science; Hash function; Channel (broadcasting); Function (biology); Algorithm; Computer network; Computer security","score_opus":0.04138638801021296,"score_gpt":0.29202286080559026,"score_spread":0.2506364727953773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125673305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03570526,0.0005096877,0.9546249,0.00036677203,0.00021141216,0.00014746707,0.00010024532,0.0007299805,0.007604275],"genre_scores_gemma":[0.6809337,0.00053536566,0.30727735,0.00037715826,0.00018402626,0.00021769082,0.00018931695,0.00014786319,0.010137554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990509,0.00022329506,0.00004753437,0.00007132624,0.00046055886,0.00014644509],"domain_scores_gemma":[0.99869066,0.00044688614,0.000094906805,0.00024288519,0.00045664792,0.00006802532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013552726,0.00041112571,0.0007341005,0.000866378,0.00057480205,0.001117254,0.0010522718,0.00086636766,0.004137454],"category_scores_gemma":[0.0042161644,0.00021738,0.00042777296,0.0010179145,0.0009416708,0.0022124387,0.0011254374,0.0011895808,0.0010222426],"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":[0.00058221695,0.00017676652,0.0018847986,0.0003108201,0.000054635406,0.00021289421,0.00024519005,0.27523035,0.049585827,0.425381,0.009992427,0.23634306],"study_design_scores_gemma":[0.00006609838,0.00018828957,0.0004340664,0.000024319203,0.00002162384,0.0002762401,0.000038238246,0.942754,0.015022122,0.033912096,0.007209759,0.00005308784],"about_ca_topic_score_codex":0.0010691691,"about_ca_topic_score_gemma":0.0005485247,"teacher_disagreement_score":0.004137454,"about_ca_system_score_codex":0.0011770535,"about_ca_system_score_gemma":0.0014002203,"threshold_uncertainty_score":0.013841152},"labels":[],"label_agreement":null},{"id":"W2125673533","doi":"10.1109/dcc.1991.213348","title":"Semantic data compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; IBM (Canada)","funders":"","keywords":"Computer science; USable; Representation (politics); Object (grammar); Process (computing); Channel (broadcasting); Limit (mathematics); Space (punctuation); Theoretical computer science; Information retrieval; Programming language; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.0946497546882956,"score_gpt":0.27337629560052157,"score_spread":0.17872654091222595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125673533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0101731,0.0054576257,0.9044063,0.0028484226,0.0017392781,0.000644068,0.005978019,0.008284854,0.060468253],"genre_scores_gemma":[0.17789,0.008479104,0.7420589,0.002232513,0.0010765927,0.0010038881,0.021162948,0.0018561397,0.044239935],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975496,0.0004368263,0.00028373994,0.0003621027,0.001201199,0.00016654634],"domain_scores_gemma":[0.99630606,0.00092265016,0.00015552233,0.0016622923,0.00088859495,0.00006490974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021205521,0.001015283,0.0011112541,0.005040665,0.0011897082,0.004094133,0.002026359,0.0012286021,0.014938635],"category_scores_gemma":[0.009251149,0.00046065068,0.0012459897,0.007727644,0.0018102721,0.0070175785,0.0035816007,0.0017272333,0.0073254965],"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":[0.0003479807,0.00008721024,0.0008243473,0.0006520959,0.00009162541,0.00033976903,0.0003336113,0.010161863,0.004933026,0.3105535,0.056630556,0.61504436],"study_design_scores_gemma":[0.00009846668,0.00010393927,0.00092761713,0.00041373275,0.00009425623,0.0012216285,0.000454716,0.08646516,0.032216087,0.47414824,0.40378088,0.00007524666],"about_ca_topic_score_codex":0.0014256287,"about_ca_topic_score_gemma":0.0015609969,"teacher_disagreement_score":0.014938635,"about_ca_system_score_codex":0.0016250955,"about_ca_system_score_gemma":0.0019266595,"threshold_uncertainty_score":0.04997468},"labels":[],"label_agreement":null},{"id":"W2126044817","doi":"10.1007/11505877_3","title":"Locally Consistent Parsing and Applications to Approximate String Comparisons","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Parsing; Computer science; String (physics); Partition (number theory); Context (archaeology); Consistency (knowledge bases); Algorithm; Block (permutation group theory); Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.02532809756415999,"score_gpt":0.26341016933158784,"score_spread":0.23808207176742785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126044817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024843598,0.00091762823,0.9912646,0.00017831344,0.00011306837,0.000047506037,0.000096606964,0.002264873,0.0026330096],"genre_scores_gemma":[0.065338165,0.0009996775,0.9242793,0.00027493798,0.0003185983,0.00024630615,0.0005447506,0.0017392877,0.0062590507],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946503,0.0018700047,0.00042316853,0.00087728567,0.0019432283,0.00023596965],"domain_scores_gemma":[0.9850691,0.008608262,0.000570215,0.0041655623,0.0014281496,0.00015868539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038286918,0.0014627255,0.0035236164,0.003763375,0.0020251223,0.0040832483,0.004642787,0.003040469,0.013481048],"category_scores_gemma":[0.027611295,0.0018855525,0.0016091657,0.012431709,0.0030878787,0.008049913,0.0040068873,0.004373628,0.0042655296],"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":[0.0002575637,0.0001262368,0.0005001836,0.00035677507,0.00006238825,0.00022136662,0.0003586428,0.04630626,0.0063156425,0.3481698,0.015723854,0.5816013],"study_design_scores_gemma":[0.000046218564,0.000066950306,0.0002595949,0.000083851904,0.000067797664,0.0003668807,0.00011675239,0.3058954,0.009734392,0.66372067,0.019566752,0.000074783406],"about_ca_topic_score_codex":0.0021161947,"about_ca_topic_score_gemma":0.00306374,"teacher_disagreement_score":0.013481048,"about_ca_system_score_codex":0.0015799241,"about_ca_system_score_gemma":0.0018554307,"threshold_uncertainty_score":0.045098603},"labels":[],"label_agreement":null},{"id":"W2126358107","doi":"10.1007/978-3-642-04241-6_32","title":"A Unifying View on Approximation and FPT of Agreement Forests","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Bisection; Tree (set theory); Time complexity; Combinatorics; Computer science; Physics; Mathematics; Geometry","score_opus":0.021241457129045623,"score_gpt":0.25593671734083606,"score_spread":0.23469526021179044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126358107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012909365,0.003627549,0.9347997,0.00567796,0.00091883214,0.00007369036,0.00044123418,0.0005387214,0.04101303],"genre_scores_gemma":[0.44777963,0.009044221,0.47574678,0.0036996885,0.007249485,0.00046143946,0.0015642939,0.0014062382,0.05304832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99569017,0.0009577717,0.00028257325,0.0009141266,0.0016292199,0.000526115],"domain_scores_gemma":[0.989588,0.0066933488,0.0002973344,0.0023886955,0.00065133284,0.00038140858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041006496,0.001495416,0.0031774926,0.0029394708,0.0025149765,0.006987617,0.0058489954,0.0031655112,0.011847403],"category_scores_gemma":[0.013733812,0.0012637832,0.003221495,0.006598027,0.0071642506,0.029442023,0.006553161,0.013386425,0.0020736656],"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":[0.000035904173,0.000018274473,0.00009019011,0.00006173426,0.0000080191685,0.000032454165,0.00010134373,0.002965502,0.00021430764,0.97714466,0.002436507,0.016891014],"study_design_scores_gemma":[0.000007942271,0.000007957935,0.000034032193,0.000014291548,0.000010321922,0.00005067456,0.000019679499,0.009455569,0.00016787376,0.9867003,0.0035248103,0.00000655896],"about_ca_topic_score_codex":0.00300778,"about_ca_topic_score_gemma":0.002189496,"teacher_disagreement_score":0.011847403,"about_ca_system_score_codex":0.0035327175,"about_ca_system_score_gemma":0.0017310624,"threshold_uncertainty_score":0.039633512},"labels":[],"label_agreement":null},{"id":"W2126903293","doi":"10.1023/a:1026524328760","title":"Probabilistic Pattern Matching and the Evolution of Stochastic Regular Expressions","year":2000,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regular expression; String (physics); Prefix; Syntax; Semantics (computer science); Expression (computer science); Programming language; Interpretation (philosophy); Probabilistic logic; Theoretical computer science; Artificial intelligence; Algorithm; Mathematics","score_opus":0.008895213492103067,"score_gpt":0.22092134861415694,"score_spread":0.21202613512205387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126903293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1269121,0.00085632235,0.8680297,0.0008821431,0.000074770905,0.000047284768,0.00020415967,0.00034779674,0.0026456092],"genre_scores_gemma":[0.7841754,0.0007210034,0.208574,0.00026608346,0.00012711038,0.00010451846,0.0005891453,0.00022188747,0.005220825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968663,0.0010123303,0.00022621578,0.00081412756,0.00087687455,0.00020406707],"domain_scores_gemma":[0.9795386,0.015367375,0.0018141236,0.001657674,0.0013125591,0.00030964773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037205066,0.0002894949,0.00095632806,0.002139854,0.00065642165,0.0018207785,0.0019425766,0.0014410932,0.0017549612],"category_scores_gemma":[0.03426149,0.0006217832,0.00090961094,0.0026657816,0.0019757035,0.005045967,0.00155247,0.0014520261,0.00034620357],"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":[0.0003273358,0.000109471264,0.006058772,0.00020699172,0.00013602419,0.0004976944,0.00057870604,0.25751573,0.0070458376,0.56740874,0.0018254513,0.15828924],"study_design_scores_gemma":[0.000012269756,0.000020930536,0.0005150764,0.000012876302,0.00001928026,0.00013455113,0.000030255922,0.6753132,0.0012089489,0.32161254,0.0011061152,0.000014041985],"about_ca_topic_score_codex":0.0024051117,"about_ca_topic_score_gemma":0.0020559034,"teacher_disagreement_score":0.0037205066,"about_ca_system_score_codex":0.0012858529,"about_ca_system_score_gemma":0.00086679996,"threshold_uncertainty_score":0.019676149},"labels":[],"label_agreement":null},{"id":"W2127632365","doi":"10.5120/13846-1678","title":"Semi-Adaptive Substitution Coder for Lossless Text Compression","year":2013,"lang":"en","type":"article","venue":"International Journal of Computer Applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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; Lossless compression; Substitution (logic); Compression (physics); Data compression; Theoretical computer science; Algorithm; Programming language; Thermodynamics","score_opus":0.016991866400793556,"score_gpt":0.2812501279464959,"score_spread":0.26425826154570237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127632365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041389726,0.0012531983,0.94803154,0.00024171479,0.00023239899,0.00014136513,0.0003096324,0.0053061103,0.0030943211],"genre_scores_gemma":[0.2754101,0.0011093948,0.70747375,0.00036616126,0.00018440149,0.00031163057,0.0014853033,0.0006746754,0.012984598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933857,0.00010597216,0.000048302543,0.00007816208,0.000393648,0.000035409572],"domain_scores_gemma":[0.99892384,0.00025657358,0.00008858011,0.00026679682,0.00043510066,0.000029082757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003477492,0.00046217823,0.00045996858,0.0010048365,0.00032434217,0.0005757174,0.0009840337,0.0005331163,0.0031345272],"category_scores_gemma":[0.0017026908,0.00014425849,0.00028012256,0.0012850576,0.0004509602,0.0009333023,0.0005535951,0.0006982337,0.0021693478],"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":[0.0006749156,0.00006909521,0.00060119154,0.00026420978,0.000046702422,0.00053399336,0.0001879756,0.009430542,0.33826423,0.010122263,0.008619181,0.6311858],"study_design_scores_gemma":[0.000101269434,0.0004645756,0.0015179069,0.00007506452,0.0000669866,0.0026436397,0.00010076712,0.38702187,0.5450681,0.0051498385,0.057697583,0.00009233577],"about_ca_topic_score_codex":0.0007210827,"about_ca_topic_score_gemma":0.000902869,"teacher_disagreement_score":0.0031345272,"about_ca_system_score_codex":0.00026661588,"about_ca_system_score_gemma":0.00042159157,"threshold_uncertainty_score":0.010486007},"labels":[],"label_agreement":null},{"id":"W2128020980","doi":"10.1145/1132516.1132540","title":"Optimal phylogenetic reconstruction","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":90,"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":"Natural Sciences and Engineering Research Council of Canada; Harvard University; National Science Foundation","keywords":"Tree (set theory); Phylogenetic tree; Markov chain; Mathematics; Combinatorics; Algorithm; Tree rearrangement; Sequence (biology); Discrete mathematics; Biology; Statistics; Genetics","score_opus":0.007480600463049214,"score_gpt":0.20684240453919886,"score_spread":0.19936180407614965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128020980","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033293296,0.0007365197,0.95834744,0.00058001943,0.00008530971,0.000070092785,0.000577439,0.0014232564,0.004886576],"genre_scores_gemma":[0.24960817,0.00072850176,0.7406767,0.0003048582,0.00011870217,0.00016208223,0.0026227005,0.00046746037,0.0053108116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984642,0.00037179078,0.00011428074,0.000490933,0.00034617944,0.00021265958],"domain_scores_gemma":[0.9957813,0.0021289876,0.00025010383,0.0012167721,0.00048226106,0.00014046956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012501398,0.0008301265,0.0014055114,0.0017257254,0.0010503558,0.0014863809,0.0014668495,0.0019274455,0.0063075647],"category_scores_gemma":[0.011221882,0.00080403034,0.0010160587,0.0018625126,0.0013093381,0.0038717368,0.0022452413,0.0019103896,0.00229227],"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":[0.0006789261,0.00018766725,0.0030546624,0.00060165336,0.0001167378,0.00031644801,0.0004990181,0.20929185,0.016864067,0.19041243,0.020709086,0.5572674],"study_design_scores_gemma":[0.00008980847,0.00009461533,0.0007993107,0.00006873179,0.000045569002,0.00035405022,0.00021222096,0.6167569,0.010264733,0.3589853,0.012287926,0.00004091243],"about_ca_topic_score_codex":0.0010404538,"about_ca_topic_score_gemma":0.0013196517,"teacher_disagreement_score":0.0063075647,"about_ca_system_score_codex":0.0010411454,"about_ca_system_score_gemma":0.0014161661,"threshold_uncertainty_score":0.021100938},"labels":[],"label_agreement":null},{"id":"W2128464835","doi":"10.1109/isit.1993.748476","title":"Selection and Square-Law Combining for Ncfsk with Correlated Branch Diversity","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Diversity (politics); Selection (genetic algorithm); Square (algebra); Computer science; Mathematics; Law; Artificial intelligence; Political science; Geometry","score_opus":0.012038906934957749,"score_gpt":0.21773760122693547,"score_spread":0.20569869429197774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128464835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03155625,0.0005489428,0.9609298,0.00029452913,0.0000973229,0.0000616343,0.000062871215,0.0005040671,0.0059445365],"genre_scores_gemma":[0.4571709,0.0006010254,0.53239864,0.00040039406,0.00028172357,0.00018826089,0.00028825417,0.00011994971,0.008550815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856806,0.00046825933,0.00006289533,0.00015588048,0.00062730035,0.0001176136],"domain_scores_gemma":[0.99719405,0.0016197427,0.00015374624,0.00039951026,0.00055628474,0.00007662298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013764749,0.000892949,0.0008504729,0.0010972406,0.0010986871,0.001306264,0.0009433432,0.0009578728,0.0035034167],"category_scores_gemma":[0.0048996294,0.00036589443,0.00046719532,0.0020706386,0.00089061656,0.0014307902,0.001121358,0.0008348957,0.0011001985],"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":[0.00097258756,0.00023712241,0.0027762833,0.00015475105,0.00019719989,0.0003155368,0.00029144116,0.18920209,0.051290624,0.05698492,0.0056225127,0.69195503],"study_design_scores_gemma":[0.000041970427,0.00012500967,0.000698822,0.000021075957,0.000054439,0.00035092377,0.000037464084,0.95534515,0.017793223,0.021684824,0.0038091799,0.000037931044],"about_ca_topic_score_codex":0.0015168223,"about_ca_topic_score_gemma":0.004869792,"teacher_disagreement_score":0.0035034167,"about_ca_system_score_codex":0.0007916432,"about_ca_system_score_gemma":0.0010246827,"threshold_uncertainty_score":0.011720061},"labels":[],"label_agreement":null},{"id":"W2128931238","doi":"10.1109/itw.2005.1531904","title":"Estimation and decoding strategies for channels with abruptly changing statistics","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Crossover; Decoding methods; Channel (broadcasting); Algorithm; Binary symmetric channel; Code word; Piecewise; Computer science; Bounded function; Binary number; Mathematics; Statistics; Channel code; Artificial intelligence; Telecommunications","score_opus":0.01675613296194047,"score_gpt":0.27055181889361984,"score_spread":0.2537956859316794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128931238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077080666,0.000119088974,0.9917631,0.00003573671,0.000005202952,0.00001049745,0.000010033859,0.00009179255,0.00025645547],"genre_scores_gemma":[0.47269312,0.0006791208,0.5240406,0.000116272546,0.00007642682,0.00011603959,0.0001299888,0.000103058155,0.0020453844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913615,0.0002618374,0.000059986218,0.00014185777,0.0002925839,0.00010767955],"domain_scores_gemma":[0.995883,0.0029503629,0.00041659927,0.00033779012,0.0003473921,0.00006499172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011348055,0.00075760763,0.0008243879,0.00067215104,0.00049196754,0.00081664586,0.0011871228,0.00091455836,0.0006272003],"category_scores_gemma":[0.006689891,0.0005501271,0.00047597158,0.00063430343,0.0011585994,0.0019524957,0.0012727269,0.0013264883,0.00038663723],"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":[0.00025145276,0.000060776812,0.0013714853,0.00014212217,0.00008155943,0.00028202924,0.00068732904,0.69810677,0.026825791,0.05044155,0.0007580406,0.22099116],"study_design_scores_gemma":[0.0000139488875,0.000053958403,0.000299543,0.000013887894,0.000017823468,0.0001638481,0.00004186468,0.9739395,0.010405171,0.014378435,0.0006421588,0.00002994069],"about_ca_topic_score_codex":0.0016237667,"about_ca_topic_score_gemma":0.0014578986,"teacher_disagreement_score":0.0016237667,"about_ca_system_score_codex":0.00056349405,"about_ca_system_score_gemma":0.00093160453,"threshold_uncertainty_score":0.006001532},"labels":[],"label_agreement":null},{"id":"W2129029222","doi":"10.1145/2483699.2483702","title":"Persistent Predecessor Search and Orthogonal Point Location on the Word RAM","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Point location; Data structure; Combinatorics; Mathematics; Binary search tree; Linear space; Binary logarithm; Sequence (biology); Space (punctuation); Amortized analysis; Recursion (computer science); Set (abstract data type); Subdivision; Computational geometry; Discrete mathematics; Point (geometry); Algorithm; Binary tree; Computer science; Geometry","score_opus":0.029189455842332738,"score_gpt":0.254282221392127,"score_spread":0.22509276554979424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129029222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13396697,0.0017454455,0.84862167,0.0016060915,0.00019900705,0.00014456631,0.0007402758,0.004548035,0.008427984],"genre_scores_gemma":[0.39553306,0.00083778077,0.59278077,0.0006290628,0.0002914772,0.00035992148,0.0011045715,0.0008276568,0.007635712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969553,0.0005427911,0.00036274837,0.0008699985,0.0007865514,0.0004826938],"domain_scores_gemma":[0.98508745,0.0041917465,0.0011625215,0.008225181,0.0009885879,0.00034449142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022609453,0.0007254041,0.0016686185,0.0016147846,0.0015397451,0.00335827,0.0037215955,0.0015145937,0.0045749582],"category_scores_gemma":[0.013019805,0.00096559856,0.0011828211,0.0043224692,0.003996412,0.016920632,0.0057355957,0.0023909006,0.0021187621],"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":[0.0013755462,0.00025121827,0.004776175,0.000470502,0.00007276743,0.00025118794,0.0018132405,0.0390422,0.024791269,0.53579515,0.013628536,0.37773225],"study_design_scores_gemma":[0.00025199197,0.0009009496,0.0012078254,0.0001652911,0.00015752132,0.0009034228,0.0007649152,0.24893,0.046668,0.6435924,0.056253556,0.00020406597],"about_ca_topic_score_codex":0.0026068515,"about_ca_topic_score_gemma":0.0030557648,"teacher_disagreement_score":0.0045749582,"about_ca_system_score_codex":0.0014024362,"about_ca_system_score_gemma":0.0019775399,"threshold_uncertainty_score":0.015304744},"labels":[],"label_agreement":null},{"id":"W2129107669","doi":"10.1109/iembs.2008.4649419","title":"An efficient algorithm for local sequence alignment","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Substring; Smith–Waterman algorithm; Pairwise comparison; Algorithm; Computer science; Multiple sequence alignment; Sequence (biology); Sensitivity (control systems); String searching algorithm; Suffix tree; Matching (statistics); Tree (set theory); Algorithm design; Pattern matching; Sequence alignment; Mathematics; Data structure; Artificial intelligence; Combinatorics","score_opus":0.032548385939449816,"score_gpt":0.28057299693471893,"score_spread":0.24802461099526912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129107669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013886851,0.00043724533,0.98298115,0.00010611907,0.00014970983,0.00022125088,0.000740667,0.011472194,0.0025029194],"genre_scores_gemma":[0.01155518,0.00020555378,0.98106474,0.00011074496,0.00006205556,0.00050795975,0.0026799692,0.00082026655,0.002993445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742645,0.0005389763,0.00029966066,0.00070212747,0.0008500253,0.00018269526],"domain_scores_gemma":[0.998278,0.00045907468,0.00014540531,0.00061981735,0.0004427924,0.00005490138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017649973,0.0025390754,0.0023366595,0.0033691768,0.002009993,0.0025046363,0.004080852,0.0020124756,0.019584654],"category_scores_gemma":[0.005608305,0.0013582795,0.0017987269,0.004763794,0.0009887216,0.0035256657,0.0033793654,0.0029264856,0.026299682],"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":[0.00030110453,0.00020342204,0.0009624128,0.00073209836,0.0002821729,0.00032447468,0.0003498268,0.027888956,0.022268001,0.04150371,0.10058132,0.8046025],"study_design_scores_gemma":[0.00038444062,0.00032107098,0.0012457065,0.00018817247,0.00018142353,0.0016210063,0.00033746092,0.51588905,0.044462167,0.14705427,0.28812566,0.00018958785],"about_ca_topic_score_codex":0.0017734466,"about_ca_topic_score_gemma":0.003001575,"teacher_disagreement_score":0.019584654,"about_ca_system_score_codex":0.0010186261,"about_ca_system_score_gemma":0.0017356582,"threshold_uncertainty_score":0.06551719},"labels":[],"label_agreement":null},{"id":"W2129268159","doi":"10.1109/iai.1996.493742","title":"An analysis-compression technique for black and white documents","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lossless compression; Lossy compression; Computer science; Algorithm; Data compression; Data compression ratio; Adaptive coding; Image compression; Artificial intelligence; Image processing; Image (mathematics)","score_opus":0.015331726361325702,"score_gpt":0.27469670718245165,"score_spread":0.25936498082112597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129268159","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025202792,0.00056576554,0.9666453,0.00030408296,0.00016032225,0.00009622889,0.000117951815,0.0020202082,0.0048873355],"genre_scores_gemma":[0.29138932,0.0008823933,0.6920825,0.00027870035,0.00021257019,0.00016075936,0.0003114653,0.00036826354,0.014313948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956614,0.00005185373,0.000020767113,0.00006468681,0.0002597099,0.000036797937],"domain_scores_gemma":[0.9995801,0.0001223807,0.000054154996,0.000090370246,0.00013441867,0.000018695859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034365678,0.0006449675,0.00041960928,0.0015571387,0.0006929715,0.0007621029,0.0005492043,0.0005627627,0.002597993],"category_scores_gemma":[0.0012826885,0.00024566794,0.0005086479,0.0010255865,0.00053292426,0.0010066878,0.0007063433,0.0008217006,0.001338762],"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":[0.00037022232,0.00007188561,0.00049143407,0.00016328722,0.00005396001,0.00035708633,0.0002579047,0.018772274,0.21045278,0.028654765,0.006892021,0.7334624],"study_design_scores_gemma":[0.000054738743,0.00015207456,0.0015700714,0.00006250747,0.0000803288,0.0014233243,0.000121210636,0.5440739,0.3956548,0.020844024,0.035894774,0.00006833677],"about_ca_topic_score_codex":0.0014067695,"about_ca_topic_score_gemma":0.0019751056,"teacher_disagreement_score":0.002597993,"about_ca_system_score_codex":0.00039016546,"about_ca_system_score_gemma":0.0006398802,"threshold_uncertainty_score":0.008691132},"labels":[],"label_agreement":null},{"id":"W2129623613","doi":"10.1109/isit.2013.6620559","title":"Redundancy analysis in lossless compression of a binary tree via its minimal DAG representation","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Encoder; Binary number; Lossless compression; Binary tree; Discrete mathematics; Tree (set theory); Redundancy (engineering); Mathematics; Computer science; Algorithm; Data compression; Arithmetic; Statistics","score_opus":0.021652549440030266,"score_gpt":0.28186989881991215,"score_spread":0.2602173493798819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129623613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18376186,0.0011325999,0.80802137,0.00062380865,0.000064785614,0.00008080058,0.0009692626,0.0012869637,0.004058536],"genre_scores_gemma":[0.7967806,0.00091414555,0.19577134,0.00019344443,0.000104127495,0.00019619153,0.0021152708,0.00013882374,0.003786095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922025,0.00018357624,0.000047961665,0.000091108006,0.00036077204,0.00009626695],"domain_scores_gemma":[0.99854845,0.0006842901,0.00016647464,0.0002788154,0.00026577158,0.000056086283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083455053,0.0005269872,0.0005429234,0.0015124356,0.00027924182,0.0008470547,0.0008961043,0.00046413625,0.0012216903],"category_scores_gemma":[0.0051825643,0.00022591768,0.00037462972,0.0013149111,0.0004616248,0.0014314341,0.00072873867,0.00053274597,0.0003704666],"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":[0.0013081107,0.00016475211,0.0027564832,0.00042196474,0.000076891454,0.00081022136,0.0004243107,0.33920977,0.03862867,0.15917376,0.008620305,0.44840476],"study_design_scores_gemma":[0.00002190884,0.00009812308,0.00061840494,0.000028762533,0.000027392865,0.00019537492,0.00004315968,0.9407383,0.008745059,0.047602613,0.0018650328,0.000015776643],"about_ca_topic_score_codex":0.0020363494,"about_ca_topic_score_gemma":0.001879988,"teacher_disagreement_score":0.0020363494,"about_ca_system_score_codex":0.000878612,"about_ca_system_score_gemma":0.0009358721,"threshold_uncertainty_score":0.006374836},"labels":[],"label_agreement":null},{"id":"W2129677775","doi":"10.1007/s11222-011-9232-5","title":"Decrypting classical cipher text using Markov chain Monte Carlo","year":2011,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Markov chain; Algorithm; Transposition (logic); Cipher; Theoretical computer science; Mathematics; Artificial intelligence; Machine learning; Bayesian probability; Encryption","score_opus":0.03401946711079033,"score_gpt":0.2587742742807753,"score_spread":0.22475480716998497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129677775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03626567,0.0002373247,0.95948243,0.0003122825,0.00010185465,0.0000970933,0.000083058214,0.00066149083,0.0027588797],"genre_scores_gemma":[0.7251074,0.00048734166,0.26595116,0.00027508123,0.00016104353,0.00024739883,0.00028482705,0.00023475556,0.007251041],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836,0.0004701541,0.00008908162,0.00018984533,0.00069463305,0.00019627894],"domain_scores_gemma":[0.9917282,0.00608936,0.00033553888,0.0011730805,0.0005313932,0.00014241917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023250056,0.000651452,0.0013708149,0.0013103018,0.001007894,0.0018744593,0.0010554483,0.0014163974,0.004022163],"category_scores_gemma":[0.010647592,0.0007313566,0.00097466627,0.0011705513,0.0021628723,0.0035474724,0.0017609006,0.0018906918,0.0008467372],"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":[0.0004634318,0.00013651872,0.0014716937,0.00010983416,0.000089815854,0.00028304767,0.00014283576,0.6571258,0.004129095,0.2882664,0.0018590933,0.045922466],"study_design_scores_gemma":[0.00001419934,0.000012969695,0.00004976232,0.000007123444,0.0000059796703,0.000049549177,0.000004580236,0.94968593,0.0017511302,0.048171222,0.00023843606,0.000009127147],"about_ca_topic_score_codex":0.0016231849,"about_ca_topic_score_gemma":0.0018747537,"teacher_disagreement_score":0.004022163,"about_ca_system_score_codex":0.0012329674,"about_ca_system_score_gemma":0.0017054545,"threshold_uncertainty_score":0.013455451},"labels":[],"label_agreement":null},{"id":"W2130384369","doi":"10.1016/j.jda.2012.12.004","title":"A computational framework for determining run-maximal strings","year":2012,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"String (physics); Computation; Combinatorics; Mathematics; Function (biology); Binary number; Key (lock); Element (criminal law); Cover (algebra); Discrete mathematics; Algorithm; Computer science; Arithmetic; Mathematical physics","score_opus":0.025830563042006628,"score_gpt":0.3077244475159101,"score_spread":0.28189388447390346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130384369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008335424,0.00013405425,0.98725885,0.00029825282,0.00004293835,0.00008430486,0.00027700872,0.0009682309,0.002600848],"genre_scores_gemma":[0.15213536,0.00024436487,0.84264183,0.00021196417,0.00015914963,0.00030717466,0.0012822183,0.00057123124,0.002446728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937736,0.0013831173,0.0006291308,0.0017208644,0.0017344041,0.0007589005],"domain_scores_gemma":[0.97389627,0.018083988,0.0011947473,0.003917524,0.002286831,0.0006205699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005436039,0.0013372406,0.0024347792,0.005197567,0.0035013466,0.007447523,0.006379274,0.0032850886,0.0095809],"category_scores_gemma":[0.0359218,0.001365279,0.0031027442,0.0053139166,0.0054010055,0.012629806,0.006984723,0.0052138944,0.0024913775],"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":[0.0005101724,0.000275654,0.0015468427,0.0003494283,0.00008659092,0.00019820916,0.00046511574,0.12654822,0.0049875444,0.67882055,0.0072080456,0.17900367],"study_design_scores_gemma":[0.000034478133,0.000064964224,0.00016168325,0.00007126268,0.00003899183,0.00008451087,0.000114712595,0.31411028,0.0036926512,0.67802095,0.0035584124,0.000047077774],"about_ca_topic_score_codex":0.003059611,"about_ca_topic_score_gemma":0.004216058,"teacher_disagreement_score":0.0095809,"about_ca_system_score_codex":0.0023197588,"about_ca_system_score_gemma":0.004715466,"threshold_uncertainty_score":0.032051325},"labels":[],"label_agreement":null},{"id":"W2130419021","doi":"10.1109/dcc.2005.20","title":"AXECHOP: A Grammar-based Compressor for XML","year":2005,"lang":"en","type":"article","venue":"Data Compression Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; XML validation; Document Structure Description; XML Encryption; Streaming XML; Efficient XML Interchange; XML Schema (W3C); Information retrieval; XML database; Programming language; Well-formed document; XML; XML framework; Database; World Wide Web","score_opus":0.12585986575161315,"score_gpt":0.3360986455891776,"score_spread":0.21023877983756448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130419021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008144746,0.00047362418,0.9264295,0.00043117636,0.00035505756,0.00040441853,0.0025119362,0.051576544,0.00967288],"genre_scores_gemma":[0.08429204,0.001190625,0.86067593,0.0006504629,0.00035965285,0.0008732541,0.013307862,0.009844396,0.028805798],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907994,0.00009792233,0.00009611025,0.00009523108,0.0005773328,0.000053546286],"domain_scores_gemma":[0.9990262,0.00031024904,0.000069899856,0.00030026495,0.00025090232,0.000042435648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069170067,0.0007884424,0.00048650414,0.001370728,0.0005317676,0.0012741401,0.0013025661,0.0006840865,0.015941182],"category_scores_gemma":[0.003797003,0.0003677841,0.00051426544,0.0015815129,0.00070865365,0.0015294425,0.0015848374,0.0014321697,0.005440436],"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":[0.0005066281,0.00006198321,0.0006316619,0.00046942005,0.000048204947,0.0008012848,0.00038622908,0.0120119,0.050795246,0.078176565,0.106497094,0.7496138],"study_design_scores_gemma":[0.00023184219,0.00031890982,0.00119282,0.00017261309,0.00006998738,0.0021644884,0.00012801998,0.28203547,0.17625374,0.049541622,0.48776534,0.00012518183],"about_ca_topic_score_codex":0.0010472559,"about_ca_topic_score_gemma":0.0009099767,"teacher_disagreement_score":0.015941182,"about_ca_system_score_codex":0.0004354288,"about_ca_system_score_gemma":0.0007017208,"threshold_uncertainty_score":0.053328514},"labels":[],"label_agreement":null},{"id":"W2130433404","doi":"10.1109/tit.2003.818411","title":"Efficient universal lossless data compression algorithms based on a greedy sequential grammar transform-part two: with context models","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Algorithm; Data compression; Lossless compression; Mathematics; Countable set; Entropy encoding; Arithmetic coding; Discrete mathematics; Theoretical computer science; Computer science; Context-adaptive binary arithmetic coding","score_opus":0.026234722003755918,"score_gpt":0.242439027781114,"score_spread":0.21620430577735808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130433404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011455381,0.0004440444,0.98662287,0.00011722246,0.000029407745,0.000051847077,0.000049092036,0.0004448514,0.0007853],"genre_scores_gemma":[0.20165028,0.0005173312,0.795517,0.00015832002,0.000059619655,0.00020662334,0.00024542768,0.000096819334,0.0015485112],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995431,0.00010451351,0.000033138815,0.00010804842,0.00016660772,0.000044662094],"domain_scores_gemma":[0.9992993,0.00036533186,0.0000661368,0.00015337607,0.000089753,0.00002618106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068594,0.00078086293,0.00075276435,0.0009214964,0.00041772713,0.00071659154,0.0013019701,0.000888231,0.0010237357],"category_scores_gemma":[0.0027801648,0.0003190463,0.0006072923,0.0015014546,0.0009607244,0.0016541745,0.0016002518,0.0012324507,0.0005362043],"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":[0.0002191813,0.00010945867,0.000743768,0.00018170074,0.000059611903,0.00021652738,0.0003066789,0.19795135,0.032250367,0.14226204,0.0042352644,0.621464],"study_design_scores_gemma":[0.000022130647,0.000059127167,0.00012107349,0.000013733711,0.000012559077,0.00021288796,0.000028985758,0.9460542,0.013241894,0.038113803,0.0021055848,0.0000140235625],"about_ca_topic_score_codex":0.0010353206,"about_ca_topic_score_gemma":0.0012464479,"teacher_disagreement_score":0.0013019701,"about_ca_system_score_codex":0.00070565776,"about_ca_system_score_gemma":0.0008620404,"threshold_uncertainty_score":0.00511992},"labels":[],"label_agreement":null},{"id":"W2130436162","doi":"10.1016/j.dam.2011.12.020","title":"The interval ordering problem","year":2012,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Mathematics; Interval (graph theory); Bottleneck; Time complexity; Combinatorics; Cover (algebra); Real line; Function (biology); Set (abstract data type); Discrete mathematics; Constant (computer programming); Polynomial; Computer science; Mathematical analysis","score_opus":0.016370403418607012,"score_gpt":0.2497104297630086,"score_spread":0.2333400263444016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130436162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061670285,0.0063192905,0.7744578,0.010001966,0.0010263073,0.00014014872,0.001613875,0.0003727795,0.14439754],"genre_scores_gemma":[0.6213217,0.0096535785,0.2892361,0.0016363087,0.0029563494,0.00039275212,0.0047249175,0.00043104784,0.06964729],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865556,0.00039390865,0.000090366346,0.00033620108,0.00039447594,0.00012945985],"domain_scores_gemma":[0.99606425,0.0026254721,0.000248196,0.00051645545,0.00031239667,0.00023322443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012265168,0.00067611405,0.0012008237,0.0011534056,0.0010886374,0.0037969023,0.001301822,0.0016544154,0.015345068],"category_scores_gemma":[0.008873162,0.0005428414,0.0008283818,0.0029325946,0.0017720197,0.0068383445,0.0018256457,0.004245119,0.0016933172],"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":[0.00009876545,0.000058309637,0.00028311714,0.00013779277,0.000021614787,0.00008186343,0.00012746848,0.010642877,0.0005258428,0.9208474,0.011975201,0.055199765],"study_design_scores_gemma":[0.000019463032,0.000014052574,0.00011036374,0.000025042727,0.000008677212,0.00008024693,0.00006186831,0.021245504,0.00027434074,0.96774787,0.010404278,0.000008256749],"about_ca_topic_score_codex":0.0009185672,"about_ca_topic_score_gemma":0.00065284077,"teacher_disagreement_score":0.015345068,"about_ca_system_score_codex":0.0011437769,"about_ca_system_score_gemma":0.0012068794,"threshold_uncertainty_score":0.05133438},"labels":[],"label_agreement":null},{"id":"W2132630274","doi":"","title":"York University at TREC 2012: Medical Records Track","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Medical record; Work (physics); Artificial intelligence; Medicine; Engineering","score_opus":0.03818721144490055,"score_gpt":0.2545070467609054,"score_spread":0.21631983531600485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132630274","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016463615,0.015457493,0.011152468,0.0227003,0.008755158,0.0037275837,0.846627,0.02893306,0.0461833],"genre_scores_gemma":[0.0120920325,0.002769531,0.014241668,0.0023645887,0.0011882134,0.0016273463,0.9285212,0.0010026678,0.036192656],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862541,0.0040778727,0.0012572231,0.0013995582,0.005976236,0.0010350011],"domain_scores_gemma":[0.96151483,0.0067528985,0.0021585855,0.005678092,0.01964117,0.004254486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02224003,0.004561493,0.0044159372,0.009036218,0.0040735663,0.0057571204,0.0045549246,0.004161833,0.05565176],"category_scores_gemma":[0.0326659,0.0011269234,0.0018670512,0.008430782,0.0011978677,0.0066741174,0.003105791,0.0047088126,0.046427347],"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":[0.00020643655,0.00016831017,0.00044234897,0.00050558033,0.000059704922,0.000034186556,0.000028849012,0.00039236728,0.0010605283,0.0002931753,0.98086697,0.015941504],"study_design_scores_gemma":[0.0016303954,0.0010416599,0.02624767,0.0006141818,0.00033559772,0.00043964057,0.0003129735,0.018501543,0.009926459,0.0032305946,0.93732196,0.00039723577],"about_ca_topic_score_codex":0.10271128,"about_ca_topic_score_gemma":0.15404584,"teacher_disagreement_score":0.10271128,"about_ca_system_score_codex":0.0069420626,"about_ca_system_score_gemma":0.011715938,"threshold_uncertainty_score":0.20422691},"labels":[],"label_agreement":null},{"id":"W2132943603","doi":"10.1007/978-1-4757-6048-4_36","title":"Universal Lossless Coding of Sources with Large and Unbounded Alphabets","year":2000,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adaptive coding; Algorithm; Huffman coding; Arithmetic coding; Lossless compression; Data compression; ENCODE; Computer science; Mathematics; Coding (social sciences); Theoretical computer science; Context-adaptive binary arithmetic coding","score_opus":0.00975808768726935,"score_gpt":0.19777595112951213,"score_spread":0.18801786344224278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132943603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007449915,0.010408043,0.9431485,0.0006619573,0.00027148388,0.000032255484,0.000215544,0.00064541487,0.037166905],"genre_scores_gemma":[0.38986814,0.030533437,0.47854236,0.00086655084,0.0013548898,0.0003228154,0.001400426,0.0009448271,0.09616652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99957603,0.00009313509,0.000024621993,0.000055657274,0.00021023172,0.00004032632],"domain_scores_gemma":[0.99858177,0.0009602931,0.00004460672,0.00026399246,0.00012184597,0.000027374159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054312503,0.00072153873,0.0008096834,0.0010705849,0.00034182143,0.0015204867,0.0011754407,0.00081461115,0.0035674179],"category_scores_gemma":[0.0030448646,0.0005075422,0.00034378062,0.0018777436,0.0014447924,0.0028579521,0.0013618122,0.0021445754,0.0013967183],"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":[0.00006581256,0.00002712615,0.00008228634,0.00038083192,0.000019834506,0.00009498724,0.00019722192,0.037530445,0.007915332,0.68770003,0.0122335795,0.25375247],"study_design_scores_gemma":[0.000015611671,0.000026414722,0.0001221628,0.00017137067,0.000016464226,0.0002937628,0.000033332984,0.14665267,0.012129869,0.8111857,0.029325029,0.00002751678],"about_ca_topic_score_codex":0.00039804514,"about_ca_topic_score_gemma":0.00035922189,"teacher_disagreement_score":0.0035674179,"about_ca_system_score_codex":0.00066381943,"about_ca_system_score_gemma":0.00046443232,"threshold_uncertainty_score":0.011934221},"labels":[],"label_agreement":null},{"id":"W2133114708","doi":"10.1109/phycmp.1994.363676","title":"A fast algorithm for entropy estimation of grey-level images","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Entropy (arrow of time); Pixel; Algorithm; Mathematics; Computer science; Artificial intelligence; Binary number; Data compression; Histogram; Pattern recognition (psychology); Image (mathematics); Physics; Arithmetic","score_opus":0.03013754039726744,"score_gpt":0.25802031885300325,"score_spread":0.22788277845573582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133114708","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067078264,0.0001360298,0.99779665,0.000029155879,0.000036408237,0.000052182888,0.000045870078,0.0008454801,0.00038732035],"genre_scores_gemma":[0.015724845,0.00020538559,0.9818741,0.00004009948,0.00006562409,0.00019808538,0.00024781062,0.00019032543,0.0014537425],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904245,0.00016056874,0.000080420345,0.00015444499,0.00050255074,0.000059490383],"domain_scores_gemma":[0.9986737,0.0006291225,0.000111387126,0.00016476729,0.00038007757,0.00004091596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012555113,0.0013177866,0.0010483154,0.0031180468,0.000846177,0.0019808514,0.0014367569,0.0012773108,0.0065756217],"category_scores_gemma":[0.004397749,0.00078605005,0.00086741755,0.0023447415,0.00082066486,0.00221981,0.0016455397,0.0017277859,0.0041479035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013421984,0.000052456035,0.00042532632,0.00020358102,0.00006933388,0.00016146983,0.00015329118,0.028286424,0.02825117,0.027890507,0.007121456,0.9072508],"study_design_scores_gemma":[0.00010786163,0.00018646453,0.0015347834,0.00009233033,0.0000621672,0.001158427,0.00008016115,0.83294356,0.06321834,0.062069643,0.03841752,0.00012883397],"about_ca_topic_score_codex":0.0012483472,"about_ca_topic_score_gemma":0.0015687615,"teacher_disagreement_score":0.0065756217,"about_ca_system_score_codex":0.00070871064,"about_ca_system_score_gemma":0.0010541219,"threshold_uncertainty_score":0.02199763},"labels":[],"label_agreement":null},{"id":"W2133151651","doi":"10.1109/cnsr.2005.22","title":"An Integrated Error Control and Constrained Sequence Code Based on Multimode Coding","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Alberta","funders":"","keywords":"Encoder; Computer science; Decoding methods; Algorithm; Coding (social sciences); Error detection and correction; Constant-weight code; Code (set theory); Sequence (biology); Code rate; Electronic engineering; Set (abstract data type); Theoretical computer science; Concatenated error correction code; Block code; Mathematics; Engineering","score_opus":0.02868870995950557,"score_gpt":0.29209930424900954,"score_spread":0.263410594289504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133151651","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05565228,0.00033748712,0.93923,0.00016624408,0.00010683321,0.00007495953,0.000056581284,0.00043611086,0.0039394526],"genre_scores_gemma":[0.33965996,0.0001900358,0.6539938,0.0001516565,0.0000683523,0.00013641425,0.00008083897,0.000050950515,0.0056680944],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945694,0.00008188646,0.000022068718,0.000074859425,0.00033178442,0.00003239699],"domain_scores_gemma":[0.99945897,0.00017732286,0.00006830918,0.00011659932,0.0001486095,0.000030258696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003225767,0.0003459888,0.0002828187,0.0005311501,0.00024833402,0.00039591378,0.0005697398,0.0005706737,0.001178315],"category_scores_gemma":[0.0012124839,0.00016111968,0.00018107229,0.00052512944,0.00046713406,0.0007609588,0.00063823996,0.0005292857,0.0003000683],"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":[0.00054248155,0.00018015278,0.0014963982,0.00017327751,0.00007294911,0.00048241465,0.00023329005,0.08085701,0.37136325,0.16272108,0.0018507823,0.3800269],"study_design_scores_gemma":[0.000063562715,0.00055609725,0.0007184293,0.0000461971,0.00004015921,0.0009633001,0.000022766362,0.680363,0.28665245,0.013482373,0.017016763,0.00007485734],"about_ca_topic_score_codex":0.00069916924,"about_ca_topic_score_gemma":0.0012878329,"teacher_disagreement_score":0.001178315,"about_ca_system_score_codex":0.00033715845,"about_ca_system_score_gemma":0.00042533505,"threshold_uncertainty_score":0.0039418936},"labels":[],"label_agreement":null},{"id":"W2133601898","doi":"10.1145/780542.780590","title":"A sublinear algorithm for weakly approximating edit distance","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":79,"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":"Edit distance; Substring; Sublinear function; Character (mathematics); Computer science; Upper and lower bounds; Algorithm; Time complexity; Combinatorics; Mathematics; Data structure","score_opus":0.014912925700245539,"score_gpt":0.24820379331236384,"score_spread":0.23329086761211829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133601898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024511399,0.0005234668,0.96098155,0.0007048995,0.00014357756,0.00029423783,0.00064778986,0.007913107,0.004279986],"genre_scores_gemma":[0.21393426,0.00020942862,0.776901,0.0004515258,0.00017573673,0.0008319745,0.0025074135,0.00078738,0.0042012306],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99269956,0.0016686653,0.0007645261,0.0016474673,0.0026222416,0.0005975723],"domain_scores_gemma":[0.9784461,0.012351936,0.0011019385,0.005728724,0.0018921212,0.0004792109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029895555,0.0019783906,0.0027305344,0.0028051923,0.001342748,0.0034620531,0.0044276193,0.0023127077,0.008640673],"category_scores_gemma":[0.031029709,0.0007908398,0.0017825502,0.0038095738,0.0015645102,0.007437896,0.0040833727,0.003688976,0.0049916324],"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":[0.0014823693,0.0005634854,0.006145979,0.00062290166,0.00023094601,0.00023365898,0.0005764993,0.111373045,0.016420022,0.058478646,0.021475414,0.78239703],"study_design_scores_gemma":[0.00020191229,0.00024758803,0.0008840585,0.000035650988,0.00005973242,0.0004003785,0.00013689471,0.8696034,0.009901935,0.11224646,0.006232316,0.000049789604],"about_ca_topic_score_codex":0.0048674564,"about_ca_topic_score_gemma":0.0059056776,"teacher_disagreement_score":0.008640673,"about_ca_system_score_codex":0.0029512036,"about_ca_system_score_gemma":0.0038654397,"threshold_uncertainty_score":0.028905928},"labels":[],"label_agreement":null},{"id":"W2133943430","doi":"10.1016/j.dam.2014.08.016","title":"How many double squares can a string contain?","year":2014,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Bounding overwatch; String (physics); Mathematics; Combinatorics; Upper and lower bounds; Least-squares function approximation; Discrete mathematics; Computer science; Statistics; Mathematical analysis; Mathematical physics","score_opus":0.015293524775743722,"score_gpt":0.23041399782368463,"score_spread":0.2151204730479409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133943430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42058066,0.0049173534,0.46190894,0.018549474,0.0030277285,0.000133134,0.0037435032,0.0029715877,0.084167644],"genre_scores_gemma":[0.8021005,0.002303482,0.15989184,0.0015393374,0.00071208173,0.00013276891,0.0028761309,0.0011138752,0.029330114],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864036,0.00019699577,0.00014216772,0.0004060923,0.00046819853,0.00014614261],"domain_scores_gemma":[0.99155504,0.0037406797,0.0007219658,0.0020558555,0.0014852721,0.0004412127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007686664,0.00062542356,0.0012570873,0.0013050155,0.0013092727,0.0028204622,0.00095112313,0.0023680632,0.013208259],"category_scores_gemma":[0.020134348,0.00060186005,0.00051997305,0.0029901252,0.0017696316,0.010151444,0.0019467542,0.0016637937,0.0073651457],"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":[0.0017906425,0.00022374015,0.015592274,0.00079847913,0.000117761294,0.0015727703,0.00077407935,0.019882401,0.026452234,0.1888186,0.03615367,0.7078234],"study_design_scores_gemma":[0.0000768639,0.0002402564,0.0046680775,0.0003810851,0.00012979699,0.004381754,0.0031662683,0.09070622,0.045184664,0.75545126,0.09543385,0.00017991249],"about_ca_topic_score_codex":0.00056023296,"about_ca_topic_score_gemma":0.00052275375,"teacher_disagreement_score":0.013208259,"about_ca_system_score_codex":0.00045568906,"about_ca_system_score_gemma":0.0006150189,"threshold_uncertainty_score":0.044186056},"labels":[],"label_agreement":null},{"id":"W2134216061","doi":"10.14288/1.0067287","title":"Improving hash join performance by exploiting intrinsic data skew","year":2009,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Skew; Computer science; Join (topology); Hash function; Hash join; Mathematics; Computer security","score_opus":0.014006478576918488,"score_gpt":0.1807874491164766,"score_spread":0.1667809705395581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134216061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49878198,0.0015956142,0.48391914,0.0004434824,0.00023399608,0.0001657586,0.00037165842,0.010725056,0.0037633753],"genre_scores_gemma":[0.8016285,0.0007974372,0.19379392,0.0001301335,0.00024688404,0.00009025964,0.0011779763,0.0006068585,0.0015280856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966544,0.00048457494,0.00035618758,0.0004075377,0.0018171915,0.00028006267],"domain_scores_gemma":[0.9845856,0.0072213192,0.0012844513,0.0036289576,0.002852732,0.0004270722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047129644,0.0009342435,0.0013524655,0.0017461327,0.0012738433,0.0031386795,0.0017255642,0.0006572589,0.0011426182],"category_scores_gemma":[0.0166615,0.0006698696,0.00041178745,0.0027480074,0.0008338582,0.0060230847,0.002679246,0.00096168555,0.0012177646],"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":[0.0034288575,0.00070216495,0.049249746,0.00034570243,0.00019230679,0.0002949354,0.0010989088,0.092242055,0.16318534,0.011914383,0.008813528,0.6685321],"study_design_scores_gemma":[0.00021492965,0.0010335679,0.005476675,0.000026750658,0.000106856794,0.00071917445,0.00050080894,0.7764101,0.19498911,0.013185374,0.0072276494,0.00010894421],"about_ca_topic_score_codex":0.0007790787,"about_ca_topic_score_gemma":0.0009730871,"teacher_disagreement_score":0.0047129644,"about_ca_system_score_codex":0.0005867041,"about_ca_system_score_gemma":0.0020569349,"threshold_uncertainty_score":0.024924874},"labels":[],"label_agreement":null},{"id":"W213460862","doi":"10.5220/0002716800450052","title":"ON USING SIMULATION AND STOCHASTIC LEARNING FOR PATTERN RECOGNITION WHEN TRAINING DATA IS UNAVAILABLE - The Case of Disease Outbreak","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Training (meteorology); Outbreak; Machine learning; Artificial intelligence; Training set; Data modeling; Disease; Pattern recognition (psychology); Medicine; Database; Geography","score_opus":0.12576590046116803,"score_gpt":0.3308350851122124,"score_spread":0.20506918465104435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W213460862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051623095,0.00055691804,0.9442473,0.0014723066,0.000062111365,0.00005117085,0.00004337139,0.00031322814,0.001630515],"genre_scores_gemma":[0.79672956,0.0007639202,0.19982518,0.00037267548,0.00014880153,0.00012838998,0.0001657783,0.00010969792,0.001755987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998412,0.0009305095,0.000118524535,0.0001812382,0.00025238204,0.00010520017],"domain_scores_gemma":[0.94322264,0.051498868,0.0011915975,0.0021643157,0.0015556308,0.0003669278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064024557,0.00063580176,0.0015302212,0.0013522434,0.00068150455,0.0015821672,0.0015105832,0.002330731,0.0016579396],"category_scores_gemma":[0.046032213,0.0006046544,0.00086579996,0.0010676226,0.002555386,0.003860489,0.0017812611,0.0016276962,0.00023258146],"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":[0.0001554792,0.00005310572,0.0024147544,0.000041321127,0.00005210097,0.000091430884,0.00007526927,0.94153935,0.00039632662,0.024185086,0.00052248035,0.03047334],"study_design_scores_gemma":[0.0000038520952,0.000006106678,0.00006630307,0.0000032307391,0.0000023280552,0.000015429716,0.0000043485998,0.9911595,0.00011853226,0.008547131,0.000070274335,0.000003054223],"about_ca_topic_score_codex":0.0075412574,"about_ca_topic_score_gemma":0.0048251767,"teacher_disagreement_score":0.0075412574,"about_ca_system_score_codex":0.001111168,"about_ca_system_score_gemma":0.0012335142,"threshold_uncertainty_score":0.03385985},"labels":[],"label_agreement":null},{"id":"W2134683937","doi":"10.1016/j.dam.2004.01.003","title":"Fun-Sort—or the chaos of unordered binary search","year":2004,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"sort; Binary number; Permutation (music); Mathematics; Binary search algorithm; Random permutation; Combinatorics; Point (geometry); Binary search tree; CHAOS (operating system); Algorithm; Element (criminal law); Discrete mathematics; Search algorithm; Binary tree; Computer science; Arithmetic; Block (permutation group theory)","score_opus":0.027464717399487384,"score_gpt":0.2710111488748926,"score_spread":0.2435464314754052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134683937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100523524,0.0070630605,0.8260198,0.0028950677,0.0014123885,0.00015489834,0.0007775215,0.0020985084,0.05905521],"genre_scores_gemma":[0.75436133,0.0032964356,0.20466472,0.0015897657,0.000753856,0.00019852245,0.00042764336,0.00054494094,0.0341628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995214,0.00011833101,0.000028978273,0.00007400898,0.00018207573,0.00007523772],"domain_scores_gemma":[0.99859387,0.0007241733,0.000119801414,0.00033998338,0.00014222403,0.0000799985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077552773,0.0003155154,0.0008766062,0.0016034937,0.0011500261,0.0023523073,0.00079367316,0.0008908279,0.0051285443],"category_scores_gemma":[0.0059184427,0.0002493504,0.00046498337,0.0015971586,0.0027353482,0.004403609,0.0015760642,0.0012336634,0.00093287416],"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":[0.00020023959,0.000012281565,0.00047533392,0.00008858833,0.000022354974,0.000064440595,0.00013792695,0.008021933,0.0015743742,0.92606866,0.004306662,0.05902714],"study_design_scores_gemma":[0.000028144477,0.000050229253,0.00019373056,0.000048538386,0.0000137700235,0.00023906928,0.00006496269,0.04720279,0.0021960975,0.92891634,0.021019233,0.000027071519],"about_ca_topic_score_codex":0.0010071013,"about_ca_topic_score_gemma":0.0010532581,"teacher_disagreement_score":0.0051285443,"about_ca_system_score_codex":0.0008394047,"about_ca_system_score_gemma":0.0010003372,"threshold_uncertainty_score":0.01715666},"labels":[],"label_agreement":null},{"id":"W2134890818","doi":"10.1016/j/ipl.2003.07.005","title":"Depth-first discovery algorithm for incremental topological sorting of directed acyclic graphs","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Alberta","funders":"","keywords":"Cover (algebra); Topological sorting; Sorting; Algorithm; Directed acyclic graph; Node (physics); Bounded function; Computer science; Mathematics; Computational complexity theory; Combinatorics; Discrete mathematics","score_opus":0.022651483000039885,"score_gpt":0.26807085928123653,"score_spread":0.24541937628119664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134890818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09206726,0.001204164,0.89965546,0.0007021827,0.00007253532,0.0003556099,0.00074801163,0.0026539604,0.0025408454],"genre_scores_gemma":[0.18791562,0.00045189413,0.80765206,0.00012215094,0.000045775032,0.00023222218,0.0017691047,0.0001570332,0.001654115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986959,0.0003024576,0.00011681303,0.00027301328,0.00040933848,0.00020248975],"domain_scores_gemma":[0.99291354,0.004627481,0.00071732135,0.0010019265,0.00047753088,0.00026226777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021472964,0.0009107123,0.001396373,0.0029349683,0.001385786,0.001462837,0.0027809807,0.0013412941,0.002170586],"category_scores_gemma":[0.009521685,0.0007548224,0.0010658279,0.0042880718,0.0012172984,0.0049763704,0.0018652403,0.0013532902,0.0006167176],"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":[0.00070522894,0.00045084706,0.004760691,0.0008256654,0.0001486006,0.00026484954,0.0007659259,0.3265214,0.009701005,0.057071604,0.011068347,0.58771586],"study_design_scores_gemma":[0.0001740016,0.0002695149,0.00056541496,0.00003578624,0.000072764546,0.0003479179,0.00016908038,0.90978867,0.00815656,0.07314647,0.0072294474,0.000044368735],"about_ca_topic_score_codex":0.0046947883,"about_ca_topic_score_gemma":0.0067320927,"teacher_disagreement_score":0.0046947883,"about_ca_system_score_codex":0.0016593088,"about_ca_system_score_gemma":0.0030975523,"threshold_uncertainty_score":0.012039125},"labels":[],"label_agreement":null},{"id":"W2135427994","doi":"10.1109/icsmc.2008.4811311","title":"An evolutionary approach for accent classification in IVR systems","year":2008,"lang":"en","type":"article","venue":"Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Computer science; Pronunciation; Stress (linguistics); Variation (astronomy); Artificial intelligence; Cluster analysis; Euclidean distance; Speech recognition; Natural language; Natural language processing; Speaker recognition; Speaker diarisation; Word error rate; Linguistics","score_opus":0.12133280092244766,"score_gpt":0.30893997724570754,"score_spread":0.18760717632325988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135427994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011730227,0.00028627928,0.98502326,0.00016557515,0.000036311623,0.00005782297,0.000018899804,0.00026561407,0.0024158652],"genre_scores_gemma":[0.33830428,0.00033238446,0.65472215,0.00022112511,0.00009715462,0.00017765394,0.00012499337,0.000112808644,0.005907505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984363,0.00046565177,0.00011026687,0.0003586217,0.0005009485,0.00012824991],"domain_scores_gemma":[0.9991041,0.00027576674,0.00008744142,0.00013102361,0.00036643908,0.000035207835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016431804,0.00065169105,0.00084847765,0.0014724167,0.000846999,0.001211618,0.0016690023,0.0011115125,0.001493746],"category_scores_gemma":[0.0034536927,0.0004466201,0.0006283913,0.0010558672,0.0008503797,0.001325639,0.000984239,0.0009079791,0.0005052793],"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":[0.00006584435,0.00010827135,0.002518896,0.000077427576,0.000086979475,0.00017623266,0.00033598367,0.42460516,0.011682532,0.03742246,0.0013530016,0.5215672],"study_design_scores_gemma":[0.0000058066053,0.000046767356,0.0005769996,0.000009420836,0.000011114377,0.00006689723,0.000038919534,0.9856984,0.0021178878,0.009222763,0.0021893524,0.000015654095],"about_ca_topic_score_codex":0.0036946093,"about_ca_topic_score_gemma":0.0033646133,"teacher_disagreement_score":0.0036946093,"about_ca_system_score_codex":0.0012069254,"about_ca_system_score_gemma":0.0006045313,"threshold_uncertainty_score":0.008756876},"labels":[],"label_agreement":null},{"id":"W2136065708","doi":"","title":"Skip Context Tree Switching","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"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":"Generalized suffix tree; Computer science; Suffix tree; Suffix; Class (philosophy); Context (archaeology); Tree (set theory); Set (abstract data type); Artificial intelligence; Weighting; Probabilistic logic; Sequence (biology); Regret; Bounded function; Machine learning; Pattern recognition (psychology); Algorithm; Mathematics; Data structure; Combinatorics; Geography","score_opus":0.009160082819927709,"score_gpt":0.21744090412426825,"score_spread":0.20828082130434056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136065708","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06394618,0.0014622313,0.9217163,0.0003850294,0.0002833616,0.00022763491,0.0012338047,0.0050169216,0.005728605],"genre_scores_gemma":[0.6764601,0.0006818815,0.30888692,0.000670357,0.00033162953,0.0004228048,0.003420324,0.00074721174,0.00837884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980428,0.0005991346,0.000113644004,0.00051437214,0.0005339878,0.00019606974],"domain_scores_gemma":[0.9955302,0.0022519887,0.00021869465,0.0011890942,0.00064154406,0.00016844754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020307146,0.00086009013,0.0015173092,0.001332612,0.0009353029,0.0010526252,0.002114542,0.0014375706,0.0065021864],"category_scores_gemma":[0.010208274,0.00043495957,0.0009600935,0.0020908962,0.00080623996,0.0030642177,0.0020926043,0.0019989442,0.0022451025],"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":[0.0006964732,0.0003340778,0.007408724,0.0002451603,0.00018290928,0.00042162635,0.0003234871,0.13571733,0.014068615,0.034813218,0.01766422,0.7881242],"study_design_scores_gemma":[0.000037724254,0.00011406654,0.0012846238,0.000030908323,0.000051955216,0.00021872189,0.000049001428,0.9356464,0.007939273,0.04805154,0.0065398887,0.000035902078],"about_ca_topic_score_codex":0.0035761455,"about_ca_topic_score_gemma":0.008071343,"teacher_disagreement_score":0.0065021864,"about_ca_system_score_codex":0.0006716051,"about_ca_system_score_gemma":0.0015260029,"threshold_uncertainty_score":0.02175194},"labels":[],"label_agreement":null},{"id":"W2136171005","doi":"10.5281/zenodo.1416837","title":"Jaudio: Additions And Improvements.","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":37,"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; Variety (cybernetics); Software deployment; Dependency (UML); Feature (linguistics); Feature extraction; Distributed computing; Data mining; Artificial intelligence; Software engineering","score_opus":0.004533756751627927,"score_gpt":0.19744206776726522,"score_spread":0.1929083110156373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136171005","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010015967,0.018926302,0.63230497,0.017951561,0.046438567,0.0014224709,0.011282572,0.15406477,0.10759277],"genre_scores_gemma":[0.03758999,0.0067363395,0.7113101,0.009447054,0.013029408,0.0011045727,0.027438395,0.034784228,0.15855986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920896,0.001821259,0.00082472333,0.00090585556,0.0034714367,0.00088706746],"domain_scores_gemma":[0.9790421,0.0026211853,0.0005289734,0.0065084854,0.009408219,0.0018911426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051867324,0.0031847898,0.0026537322,0.007182915,0.0020987482,0.0050964225,0.007541279,0.0028276113,0.05934589],"category_scores_gemma":[0.036720756,0.002051707,0.0018940016,0.006065624,0.0016139668,0.008941563,0.00783616,0.0060789366,0.088528894],"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":[0.0010443552,0.0003679573,0.0011161211,0.0006052037,0.00009508958,0.00023801012,0.00015602478,0.00091061054,0.0062731365,0.01800661,0.5770111,0.39417583],"study_design_scores_gemma":[0.00020022184,0.00021715209,0.0011217645,0.00020679912,0.00011851918,0.0011293126,0.00012617433,0.012189635,0.014726197,0.021447983,0.94830465,0.0002116025],"about_ca_topic_score_codex":0.002810761,"about_ca_topic_score_gemma":0.0045060073,"teacher_disagreement_score":0.05934589,"about_ca_system_score_codex":0.0012873895,"about_ca_system_score_gemma":0.0020003268,"threshold_uncertainty_score":0.19853175},"labels":[],"label_agreement":null},{"id":"W2136351840","doi":"10.1109/itw.2003.1216752","title":"Serial turbo coding for data compression and the Slepian-Wolf problem","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"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":"Distributed source coding; Computer science; Turbo code; Tunstall coding; Decoding methods; Variable-length code; Algorithm; Context-adaptive binary arithmetic coding; Encoder; Data compression; Shannon–Fano coding; Adaptive coding; Arithmetic coding; Theoretical computer science; Coding (social sciences); Serial concatenated convolutional codes; Encoding (memory); Entropy encoding; Lossless compression; Concatenated error correction code; Mathematics; Block code; Artificial intelligence; Statistics","score_opus":0.03647783093793736,"score_gpt":0.27694872301557844,"score_spread":0.24047089207764108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136351840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031484548,0.0013352957,0.96012026,0.0004149236,0.00011173717,0.000047669473,0.00003161952,0.00019437305,0.0062596677],"genre_scores_gemma":[0.5753608,0.0021593007,0.41220504,0.0002551659,0.00022824526,0.00016901438,0.00014185188,0.000074809235,0.009405768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995765,0.00016030426,0.000025143669,0.000031745738,0.00017784077,0.000028511024],"domain_scores_gemma":[0.9990553,0.0006182494,0.000071654234,0.00012162019,0.00011291977,0.000020191661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080228,0.00049647724,0.00036352422,0.0006401922,0.0003257748,0.00055518455,0.0005132809,0.00084612664,0.0013264075],"category_scores_gemma":[0.0031946946,0.00017094074,0.00026637348,0.0009795929,0.0011129339,0.001371889,0.0005652148,0.0007047823,0.000385214],"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":[0.00031460848,0.000050153063,0.00046953125,0.00027354207,0.000038977756,0.00045631823,0.00020736922,0.21280591,0.018878166,0.54540735,0.003402509,0.21769567],"study_design_scores_gemma":[0.000047624613,0.00015306089,0.00015945517,0.00005282575,0.00001697975,0.00052656047,0.000027926078,0.8032598,0.021867245,0.16846398,0.0053950166,0.000029568537],"about_ca_topic_score_codex":0.00038369265,"about_ca_topic_score_gemma":0.0004299421,"teacher_disagreement_score":0.0013264075,"about_ca_system_score_codex":0.00044852955,"about_ca_system_score_gemma":0.00050372217,"threshold_uncertainty_score":0.004437268},"labels":[],"label_agreement":null},{"id":"W2136611242","doi":"10.1109/cec.2006.1688666","title":"Symmetric Comparator Pairs In The Initialization Of Genetic Algorithm Populations For Sorting Networks","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Initialization; Sorting; Sorting network; Comparator; Computer science; Genetic algorithm; Algorithm; Simple (philosophy); Sorting algorithm; sort; Permutation (music); Theoretical computer science; Mathematical optimization; Mathematics; Machine learning; Engineering; Physics","score_opus":0.03587855261627935,"score_gpt":0.2831978605290503,"score_spread":0.24731930791277099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136611242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07272278,0.00017654747,0.92027235,0.00014624454,0.00005719628,0.00016791085,0.00006266298,0.00036667514,0.0060276827],"genre_scores_gemma":[0.5261011,0.00012914915,0.47017276,0.00014969209,0.00002280529,0.00033079888,0.00016756952,0.00013680682,0.002789239],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986798,0.00061819213,0.00008150223,0.00020037268,0.0003238744,0.0000962036],"domain_scores_gemma":[0.9972178,0.0014615094,0.00031198212,0.0004959772,0.0003799805,0.00013282742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024631312,0.00046707326,0.0005362705,0.0008808114,0.0006504618,0.0010504824,0.0011394834,0.0010196471,0.0034283623],"category_scores_gemma":[0.01000583,0.00033151684,0.00032895067,0.00096621015,0.0010032314,0.0017055073,0.001160713,0.0010373702,0.0005763428],"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":[0.00052129617,0.0002624103,0.0038997561,0.00016077852,0.000060003134,0.0002762356,0.00048971246,0.4866419,0.031277604,0.24468671,0.002102804,0.22962071],"study_design_scores_gemma":[0.00014627914,0.0004894224,0.0009252412,0.000055794553,0.0000370196,0.00022349066,0.000114402654,0.8735861,0.0317695,0.0856797,0.006926053,0.00004696428],"about_ca_topic_score_codex":0.00051850633,"about_ca_topic_score_gemma":0.0008099044,"teacher_disagreement_score":0.0034283623,"about_ca_system_score_codex":0.0011862862,"about_ca_system_score_gemma":0.0009151978,"threshold_uncertainty_score":0.013026416},"labels":[],"label_agreement":null},{"id":"W2136702169","doi":"10.1109/aina.2007.109","title":"Parallel Lossless Data Compression Based on the Burrows-Wheeler Transform","year":2007,"lang":"en","type":"article","venue":"Proceedings","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Computer science; Parallel computing; Lossless compression; Speedup; Task parallelism; Distributed memory; Data parallelism; Data compression; Parallelism (grammar); Algorithm; Shared memory","score_opus":0.047555876127906634,"score_gpt":0.2806979466130523,"score_spread":0.23314207048514568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136702169","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022155933,0.0003246088,0.9739575,0.0001163311,0.000052914165,0.0000915485,0.0000525967,0.0013970226,0.0018515346],"genre_scores_gemma":[0.123212315,0.0005049625,0.87124985,0.000086900254,0.00004748608,0.00015425216,0.00029709612,0.00021964208,0.0042274008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996062,0.00003526647,0.00002001879,0.000041258212,0.000259598,0.0000376046],"domain_scores_gemma":[0.99961483,0.00013087512,0.0000482819,0.00009371142,0.00009611477,0.000016167785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047093548,0.0005283522,0.0005772859,0.0009504334,0.00038411937,0.0008149108,0.0009652738,0.0004028885,0.0019388085],"category_scores_gemma":[0.0014729355,0.00022267501,0.00034631515,0.001172384,0.0005712588,0.0013443179,0.00062021305,0.0006199335,0.0010863722],"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":[0.0004922601,0.00019785961,0.000886917,0.00026838452,0.000057376245,0.0002315553,0.00020423578,0.13429105,0.11157566,0.04553105,0.004242524,0.7020212],"study_design_scores_gemma":[0.00009540809,0.00015769487,0.00038798669,0.000016119964,0.000022301692,0.00033288312,0.00004654557,0.87428415,0.10146654,0.012668512,0.0104940655,0.000027792199],"about_ca_topic_score_codex":0.001690318,"about_ca_topic_score_gemma":0.001875141,"teacher_disagreement_score":0.0019388085,"about_ca_system_score_codex":0.00045885582,"about_ca_system_score_gemma":0.0007552771,"threshold_uncertainty_score":0.0064859986},"labels":[],"label_agreement":null},{"id":"W2136792657","doi":"10.1093/nar/gkp662","title":"HMMConverter 1.0: a toolbox for hidden Markov models","year":2009,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hidden Markov model; Computer science; Software; Toolbox; Task (project management); Machine learning; Data mining; Probabilistic logic; XML; Markov model; Artificial intelligence; Set (abstract data type); Markov chain; Algorithm; Programming language","score_opus":0.072584701986076,"score_gpt":0.3487133995037021,"score_spread":0.27612869751762614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136792657","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013655769,0.00061295094,0.72577596,0.00013214543,0.00015138501,0.000132243,0.017116308,0.25204927,0.0026641265],"genre_scores_gemma":[0.019274728,0.0012103685,0.86628824,0.0004164179,0.000117720025,0.0015108729,0.047539484,0.054351214,0.009291013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992506,0.00020053002,0.00009531023,0.00017696308,0.00021644245,0.000060119663],"domain_scores_gemma":[0.998063,0.0012046384,0.00013915967,0.00031559207,0.00020532914,0.0000721663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018040437,0.0018058221,0.0016156305,0.0022492798,0.0006718122,0.0014469995,0.0031761047,0.0014727273,0.076666094],"category_scores_gemma":[0.0070735984,0.0023221779,0.001543303,0.0017593338,0.00041769407,0.0021017382,0.0025055276,0.0028753441,0.044756364],"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":[0.0006441982,0.00017586879,0.0020784417,0.0022269534,0.00044243524,0.00078329304,0.0005215043,0.032638047,0.015264427,0.015135059,0.46371254,0.46637723],"study_design_scores_gemma":[0.00034754758,0.00013548962,0.0040096017,0.0005475771,0.00018268514,0.0016984977,0.0001413601,0.33903027,0.038370643,0.082556605,0.5325855,0.000394185],"about_ca_topic_score_codex":0.0015344956,"about_ca_topic_score_gemma":0.002347114,"teacher_disagreement_score":0.076666094,"about_ca_system_score_codex":0.00058594806,"about_ca_system_score_gemma":0.001221396,"threshold_uncertainty_score":0.2564736},"labels":[],"label_agreement":null},{"id":"W2137339254","doi":"10.1145/1321440.1321546","title":"Index compression is good, especially for random access","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random access; Uncompressed video; Index (typography); Computer science; Overhead (engineering); Compression (physics); Data compression; Inverted index; Data access; Information retrieval; Data mining; Database; Search engine indexing; Computer network; World Wide Web; Artificial intelligence; Operating system","score_opus":0.02805789760268694,"score_gpt":0.3251836736894811,"score_spread":0.29712577608679414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137339254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053126644,0.048490707,0.7228062,0.012105775,0.0037725347,0.00084177434,0.00548726,0.037061416,0.11630766],"genre_scores_gemma":[0.3627079,0.022920936,0.5052341,0.0051986594,0.0064166104,0.0006172795,0.011056212,0.006880934,0.07896731],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963315,0.0004101572,0.00031082088,0.00050677126,0.0022171151,0.00022359956],"domain_scores_gemma":[0.9855439,0.0045851143,0.0009588557,0.00409195,0.004539601,0.0002805794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021545782,0.0014167663,0.0016646025,0.002871471,0.0017139389,0.003417261,0.0014836744,0.0017394802,0.022598136],"category_scores_gemma":[0.018701883,0.0006225891,0.00069268525,0.0063708895,0.0010772347,0.0061476785,0.0013021239,0.001606746,0.027732432],"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":[0.0008432279,0.00027010942,0.0039419853,0.0013167692,0.00019008269,0.00074161397,0.00024692848,0.0065129814,0.045895465,0.017785113,0.08893185,0.83332384],"study_design_scores_gemma":[0.00049349776,0.0016402281,0.018131638,0.0008834134,0.0005480815,0.015130732,0.00060861366,0.055929616,0.22425526,0.110369414,0.57160234,0.00040707784],"about_ca_topic_score_codex":0.0010061456,"about_ca_topic_score_gemma":0.0012720762,"teacher_disagreement_score":0.022598136,"about_ca_system_score_codex":0.0005866731,"about_ca_system_score_gemma":0.0009600149,"threshold_uncertainty_score":0.07559836},"labels":[],"label_agreement":null},{"id":"W2137653121","doi":"10.1109/tcbb.2005.13","title":"Optimizing Multiple Seeds for Protein Homology Search","year":2005,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Logarithm; Set (abstract data type); Computer science; Integer programming; Sensitivity (control systems); Integer (computer science); Noise (video); Algorithm; Local search (optimization); Homology (biology); Theoretical computer science; Mathematics; Artificial intelligence; Biology","score_opus":0.027872479733665922,"score_gpt":0.2897299473276345,"score_spread":0.2618574675939686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137653121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010391716,0.00027088734,0.987263,0.00009042628,0.00002885235,0.000039834584,0.000054259726,0.0011805706,0.0006804426],"genre_scores_gemma":[0.14505453,0.00027658694,0.8523165,0.00009399365,0.00003918896,0.00019716886,0.0004074978,0.00044281373,0.0011716859],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815303,0.0007234844,0.00011470386,0.0003600188,0.00054684695,0.000101858146],"domain_scores_gemma":[0.99634296,0.002102687,0.00032859392,0.00061634573,0.00046909912,0.0001402105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024124736,0.0012240006,0.0016246655,0.0017500536,0.0007858011,0.0011024588,0.001978081,0.0016615071,0.002967749],"category_scores_gemma":[0.011848001,0.00086962385,0.0008230441,0.0025575808,0.0010668616,0.0035766826,0.001917667,0.0013884129,0.001761126],"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":[0.00037409543,0.00015754488,0.0013390142,0.00019855879,0.000079682104,0.00021532766,0.00014327836,0.70546395,0.015181246,0.05525246,0.0054219677,0.21617289],"study_design_scores_gemma":[0.000034812318,0.000050522045,0.000065524386,0.000009990824,0.000008974252,0.00005773657,0.000014543079,0.9649594,0.004482328,0.028763209,0.0015405599,0.000012415651],"about_ca_topic_score_codex":0.0014880579,"about_ca_topic_score_gemma":0.0021149435,"teacher_disagreement_score":0.002967749,"about_ca_system_score_codex":0.0011929651,"about_ca_system_score_gemma":0.0013412174,"threshold_uncertainty_score":0.012758493},"labels":[],"label_agreement":null},{"id":"W2138249341","doi":"10.3233/fi-2011-538","title":"On the Regularity of Iterated Hairpin Completion of a Single Word","year":2011,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"Iterated function; Word (group theory); Mathematics; Arithmetic; Computer science; Linguistics; Natural language processing; Combinatorics; Philosophy; Geometry; Mathematical analysis","score_opus":0.06498363595602971,"score_gpt":0.22817466271495887,"score_spread":0.16319102675892916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138249341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8384648,0.00023807061,0.15282094,0.00019790408,0.000026758102,0.00005754495,0.00020264846,0.00028402678,0.0077072787],"genre_scores_gemma":[0.9629006,0.00015175574,0.03355357,0.00007287232,0.00010581819,0.00008965569,0.00044583442,0.000120116136,0.002559814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839336,0.00039970587,0.00012123377,0.00045263252,0.0004106138,0.00022237585],"domain_scores_gemma":[0.9861043,0.009650188,0.0013361592,0.0012090461,0.0010286141,0.00067173486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015364586,0.00035549485,0.00076651847,0.0013216673,0.0008360187,0.0012538951,0.0007272554,0.00064251496,0.0018264002],"category_scores_gemma":[0.013923851,0.00036509265,0.00069222896,0.00063073944,0.0033936407,0.0022817347,0.0013628165,0.0012911409,0.00038782292],"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":[0.0009944795,0.00027257172,0.010317958,0.00031922892,0.00006974359,0.001772717,0.0024179984,0.092296444,0.05715648,0.78704786,0.0020520757,0.045282487],"study_design_scores_gemma":[0.00008390723,0.0005456634,0.0032153535,0.000055243912,0.000037324724,0.0008989761,0.00041929173,0.40379032,0.026870852,0.56015086,0.0038278098,0.00010429365],"about_ca_topic_score_codex":0.0006688113,"about_ca_topic_score_gemma":0.00043951644,"teacher_disagreement_score":0.0018264002,"about_ca_system_score_codex":0.00051267404,"about_ca_system_score_gemma":0.0005370045,"threshold_uncertainty_score":0.008125663},"labels":[],"label_agreement":null},{"id":"W2138523425","doi":"10.1109/dcc.1992.227475","title":"Constructing word-based text compression algorithms","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":86,"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; University of Victoria","funders":"","keywords":"Huffman coding; Word (group theory); ASCII; Computer science; Context (archaeology); Algorithm; Compression (physics); Data compression; Alphanumeric; Sigma; Alphabet; Word problem (mathematics education); Compression ratio; Lossless compression; Theoretical computer science; Natural language processing; Artificial intelligence; Arithmetic; Mathematics; Programming language; Linguistics","score_opus":0.01936819052923327,"score_gpt":0.2530895295810157,"score_spread":0.23372133905178244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138523425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010642518,0.00033417268,0.9819518,0.00013426194,0.000118598,0.00029216855,0.00023615806,0.0028094775,0.0034809406],"genre_scores_gemma":[0.042597428,0.00043903457,0.9516012,0.00015399649,0.000094395975,0.0003440141,0.0009950468,0.00032575976,0.0034491061],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897456,0.00014858635,0.00013861187,0.00019099272,0.0004577502,0.00008944165],"domain_scores_gemma":[0.99808645,0.0004301163,0.00009669725,0.0003046874,0.00102936,0.00005278227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008133821,0.00083609147,0.00070247427,0.0028169546,0.0006625699,0.0015601766,0.0015965764,0.0011204756,0.0056684753],"category_scores_gemma":[0.0054987343,0.00040034726,0.00066743727,0.0026165482,0.000674311,0.0020756007,0.0015544416,0.0009549614,0.00543822],"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":[0.00021341091,0.000109735156,0.00094629114,0.00034423286,0.00004957556,0.00023425129,0.00028572875,0.033462085,0.0365651,0.062217765,0.011052825,0.854519],"study_design_scores_gemma":[0.00012516088,0.0002831467,0.00073770835,0.00013845778,0.000091656846,0.00074840715,0.00024262538,0.6728899,0.18801813,0.0736453,0.06300986,0.00006969183],"about_ca_topic_score_codex":0.0007732165,"about_ca_topic_score_gemma":0.00063257833,"teacher_disagreement_score":0.0056684753,"about_ca_system_score_codex":0.00063602295,"about_ca_system_score_gemma":0.0010043316,"threshold_uncertainty_score":0.01896292},"labels":[],"label_agreement":null},{"id":"W2138630447","doi":"10.1109/dcc.2012.44","title":"A Machine Learning Perspective on Predictive Coding with PAQ8","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 British Columbia","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Perspective (graphical); Online machine learning; Lossy compression; Unsupervised learning; Computational learning theory; Coding (social sciences); Predictive coding","score_opus":0.013366151810793729,"score_gpt":0.24781236669835485,"score_spread":0.23444621488756112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138630447","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002532972,0.0006842648,0.9919437,0.00095573073,0.00011317023,0.00002596598,0.000039630526,0.0001863724,0.003518201],"genre_scores_gemma":[0.26512572,0.002865336,0.7207097,0.0012689709,0.0010697547,0.0003431329,0.00026688733,0.00019685569,0.008153662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987966,0.00049004774,0.000061528306,0.00012939815,0.00044369636,0.00007875274],"domain_scores_gemma":[0.9952378,0.0032244115,0.00017469728,0.0007631054,0.0005346645,0.00006525938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021954463,0.0008136732,0.00063068897,0.0009610751,0.0007233449,0.0018888382,0.0018465654,0.0017343285,0.0036136277],"category_scores_gemma":[0.011400408,0.00038817248,0.00048177326,0.0014578501,0.002266041,0.0031591856,0.0016462872,0.004035938,0.00127481],"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":[0.00010009033,0.000046048903,0.00054230134,0.0000891628,0.000026111142,0.000118770455,0.00014194183,0.1337766,0.0036018277,0.71029395,0.0044812667,0.14678188],"study_design_scores_gemma":[0.000016072441,0.00006676706,0.0001102038,0.00005274285,0.000008544122,0.00016257286,0.000029616263,0.6841021,0.0041116504,0.3031913,0.008122281,0.000026223819],"about_ca_topic_score_codex":0.0024514007,"about_ca_topic_score_gemma":0.001855921,"teacher_disagreement_score":0.0036136277,"about_ca_system_score_codex":0.0009334165,"about_ca_system_score_gemma":0.0010758466,"threshold_uncertainty_score":0.012088776},"labels":[],"label_agreement":null},{"id":"W2139928429","doi":"10.1109/itw.1998.706446","title":"Design of context-free grammars for lossless data compression","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"University of Arizona","keywords":"Lossless compression; Rule-based machine translation; Computer science; Redundancy (engineering); String (physics); Grammar; L-attributed grammar; Context-free grammar; Data compression; Tree-adjoining grammar; Indexed grammar; Context (archaeology); Extended Affix Grammar; Natural language processing; Alphabet; Compression (physics); Algorithm; Artificial intelligence; Mathematics; Linguistics; Physics","score_opus":0.14203147393803534,"score_gpt":0.28866056051241035,"score_spread":0.146629086574375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139928429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015065847,0.00045705287,0.9811087,0.00021887536,0.0000617603,0.0001917021,0.0000757334,0.0016051732,0.0012151111],"genre_scores_gemma":[0.1909073,0.0005738302,0.8049567,0.00030505436,0.000098886965,0.00064484857,0.00032767298,0.00030888905,0.0018768465],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998524,0.0004778009,0.00014472511,0.0002643319,0.0004713075,0.00011792535],"domain_scores_gemma":[0.99716467,0.0013154283,0.00022308208,0.000589287,0.0005940516,0.000113449634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017542504,0.00054296694,0.00064257317,0.00089510117,0.0005679931,0.0010319946,0.0018117807,0.00087314844,0.0011405466],"category_scores_gemma":[0.0058340365,0.00055403454,0.0006169307,0.0007822601,0.001473484,0.0012427068,0.0010979829,0.0011695536,0.000650336],"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":[0.00056686153,0.0002644052,0.0014398643,0.0007774914,0.00014977346,0.0011671735,0.0010295575,0.2154193,0.15533589,0.25257516,0.008186477,0.36308807],"study_design_scores_gemma":[0.00023169757,0.00028134213,0.0003016582,0.00011589535,0.0001172682,0.00081207906,0.0001246471,0.7015173,0.116116114,0.14957553,0.030730987,0.00007552258],"about_ca_topic_score_codex":0.0005577748,"about_ca_topic_score_gemma":0.0008882674,"teacher_disagreement_score":0.0018117807,"about_ca_system_score_codex":0.000712684,"about_ca_system_score_gemma":0.0012539936,"threshold_uncertainty_score":0.009277523},"labels":[],"label_agreement":null},{"id":"W2140065054","doi":"","title":"Adaptive Range Counting and Other Frequency-Based Range Query Problems","year":2012,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Range query (database); Range (aeronautics); Data structure; Counting problem; Mathematics; Binary logarithm; Function (biology); Log-log plot; Combinatorics; Discrete mathematics; Algorithm; Computer science; Sargable; Search engine; Web search query","score_opus":0.016258606629158696,"score_gpt":0.2008370117836284,"score_spread":0.1845784051544697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140065054","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06705506,0.0033935437,0.9027789,0.0031564827,0.00020405446,0.00032421233,0.0007689142,0.0008783964,0.021440428],"genre_scores_gemma":[0.47235745,0.002976711,0.5051865,0.0012100574,0.0010052414,0.0007457884,0.0022458127,0.0006446731,0.013627669],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99248147,0.0017977866,0.00050708535,0.0014891252,0.0029538139,0.00077071815],"domain_scores_gemma":[0.9673758,0.023792446,0.001936917,0.004742456,0.001626777,0.0005255015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038324671,0.001154555,0.001999121,0.0023446353,0.0014919122,0.0041101696,0.004396488,0.0026787312,0.008682066],"category_scores_gemma":[0.030497584,0.00062438846,0.0016969645,0.007223467,0.0024923626,0.014897936,0.003944024,0.0040511084,0.0014218139],"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":[0.00074688485,0.00047867704,0.003432508,0.00083383976,0.00013213861,0.0003278808,0.00075387425,0.1250501,0.00742023,0.59856504,0.020676719,0.24158221],"study_design_scores_gemma":[0.00009482343,0.0001635542,0.0009988247,0.000096276,0.000048349757,0.00068871496,0.0002913131,0.48950097,0.0050429553,0.49183813,0.0111770015,0.000059123435],"about_ca_topic_score_codex":0.0014893075,"about_ca_topic_score_gemma":0.0009322784,"teacher_disagreement_score":0.008682066,"about_ca_system_score_codex":0.0022133884,"about_ca_system_score_gemma":0.0012407291,"threshold_uncertainty_score":0.02904445},"labels":[],"label_agreement":null},{"id":"W2140307187","doi":"","title":"Neighbourhood Thresholding for Projection-Based Motif Discovery","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Thresholding; Computer science; Projection (relational algebra); Artificial intelligence; Motif (music); Neighbourhood (mathematics); Algorithm; Mathematics; Data mining; Theoretical computer science","score_opus":0.017457635757114752,"score_gpt":0.26193588574197274,"score_spread":0.24447824998485798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140307187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009441362,0.0003128577,0.9888911,0.000080616606,0.000028009437,0.000037108173,0.00007412924,0.0006294414,0.00050536107],"genre_scores_gemma":[0.1262254,0.0003801951,0.87129474,0.00006630963,0.000057242833,0.0003034439,0.0005030502,0.00019006064,0.0009796373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974049,0.0009568252,0.00016964128,0.0004752372,0.00089090713,0.000102494625],"domain_scores_gemma":[0.99510646,0.0029279517,0.0002450756,0.00087736413,0.00067470357,0.00016840282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023893304,0.00049021794,0.0015158167,0.0016895618,0.0008636671,0.0011138995,0.0014043942,0.0009360799,0.0020645375],"category_scores_gemma":[0.013755745,0.00067916454,0.0007178413,0.002812399,0.0012871792,0.0016668838,0.002364651,0.0018458071,0.0011851105],"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":[0.0006998396,0.000120181576,0.002707386,0.0004792539,0.00013062207,0.00022763909,0.00038039644,0.14510982,0.04001154,0.05595533,0.0053885714,0.7487894],"study_design_scores_gemma":[0.000052228326,0.00007484602,0.0006861053,0.000024678255,0.000021503502,0.00019858823,0.000037594156,0.9035184,0.014415423,0.07659207,0.004340079,0.000038420512],"about_ca_topic_score_codex":0.0009357057,"about_ca_topic_score_gemma":0.0011556625,"teacher_disagreement_score":0.0023893304,"about_ca_system_score_codex":0.0005521057,"about_ca_system_score_gemma":0.0008865492,"threshold_uncertainty_score":0.012636125},"labels":[],"label_agreement":null},{"id":"W2140883685","doi":"10.1016/s0166-218x(02)00217-2","title":"An external memory data structure for shortest path queries","year":2002,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Combinatorics; Mathematics; Shortest path problem; Distance; sort; Planar graph; Data structure; Path (computing); Graph; Spanning tree; Binary logarithm; Binary tree; Discrete mathematics; Computer science; Arithmetic","score_opus":0.03890792014784756,"score_gpt":0.27609379526152195,"score_spread":0.2371858751136744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140883685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064683,0.0019912375,0.88275874,0.0018364164,0.0007796794,0.0005947325,0.0062386105,0.02535287,0.015764708],"genre_scores_gemma":[0.38752466,0.0011399795,0.56408685,0.0011690051,0.00048577721,0.0013653112,0.01647097,0.0034697338,0.024287635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986255,0.00020812325,0.00022850827,0.00020074986,0.00055072206,0.00018639989],"domain_scores_gemma":[0.99387217,0.0013618974,0.0003725366,0.0032653743,0.0008381282,0.00028998186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014150088,0.00096245226,0.0013130571,0.0022517487,0.0013733179,0.002726507,0.002864398,0.0010739788,0.01391497],"category_scores_gemma":[0.007925829,0.00069430313,0.00063349906,0.0049239686,0.0011054687,0.0058236797,0.0054665287,0.0017957108,0.004135741],"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":[0.0031534946,0.00044808997,0.0032075932,0.00075138983,0.00011210018,0.00036922516,0.0006244819,0.019951684,0.025822727,0.14735568,0.10237594,0.69582766],"study_design_scores_gemma":[0.0012282628,0.0012091914,0.0019144033,0.00042229448,0.000300088,0.001046002,0.00069872034,0.32481185,0.090010755,0.3553251,0.22278081,0.00025255102],"about_ca_topic_score_codex":0.0013921394,"about_ca_topic_score_gemma":0.0018726508,"teacher_disagreement_score":0.01391497,"about_ca_system_score_codex":0.0012982003,"about_ca_system_score_gemma":0.0015453722,"threshold_uncertainty_score":0.046550214},"labels":[],"label_agreement":null},{"id":"W2140944908","doi":"10.14778/1687627.1687722","title":"Improving the performance of list intersection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"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; Intersection (aeronautics); Identifier; Overhead (engineering); Hash function; Sorting; Cache; Parallel computing; Hash table; Data structure; Algorithm; Theoretical computer science; Operating system; Programming language","score_opus":0.0073209096403227154,"score_gpt":0.2025471456109298,"score_spread":0.19522623597060706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140944908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20298858,0.0029505051,0.7704503,0.00062391435,0.00017193369,0.00015516112,0.00031774267,0.015892424,0.006449464],"genre_scores_gemma":[0.5777852,0.0007589205,0.41635042,0.00016238619,0.00014023884,0.00015626149,0.0010718214,0.00069686206,0.0028778876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965609,0.00060615246,0.00029305075,0.000468936,0.0015713314,0.0004996203],"domain_scores_gemma":[0.9885107,0.0057624183,0.00058908935,0.0024516566,0.002463617,0.00022236843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022639127,0.0010212585,0.0011762041,0.0026875495,0.001187651,0.0025911606,0.0025167824,0.0008814541,0.0032800275],"category_scores_gemma":[0.016847821,0.0004556359,0.00049439445,0.0049963547,0.000808825,0.005817433,0.0029808895,0.0011214195,0.0018600479],"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":[0.0016934623,0.0002827146,0.01163524,0.00026682572,0.000115038536,0.0001392042,0.0005880866,0.07680458,0.040203374,0.01560503,0.010648329,0.8420182],"study_design_scores_gemma":[0.000095728814,0.00042753233,0.0019229227,0.00002684196,0.0000611903,0.0003179142,0.00023422997,0.8979215,0.078125015,0.012138858,0.008673761,0.000054519467],"about_ca_topic_score_codex":0.0025779747,"about_ca_topic_score_gemma":0.002447515,"teacher_disagreement_score":0.0032800275,"about_ca_system_score_codex":0.001406499,"about_ca_system_score_gemma":0.0024809663,"threshold_uncertainty_score":0.011972904},"labels":[],"label_agreement":null},{"id":"W2141385938","doi":"10.1109/icdar.1995.602070","title":"A Markovian random field approach to information retrieval","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Markov process; Analogy; Markov chain; Theoretical computer science; Random field; Set (abstract data type); Matching (statistics); Field (mathematics); Information retrieval; Algorithm; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.013615399523665079,"score_gpt":0.20693306512186585,"score_spread":0.19331766559820077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141385938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003553357,0.0044902256,0.9851164,0.0014601379,0.00018356276,0.00015477464,0.00015346915,0.0003085441,0.0045794686],"genre_scores_gemma":[0.3691484,0.012576701,0.58878905,0.0016636071,0.0021425108,0.0011307426,0.0006257738,0.000216683,0.02370646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813086,0.00074251636,0.00010810578,0.0003430407,0.0005439336,0.00013150218],"domain_scores_gemma":[0.9966614,0.0024400754,0.00020375407,0.00025757172,0.0003496517,0.00008748689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027606967,0.00081957824,0.0014895933,0.0031281535,0.00078812765,0.0018080065,0.0025721008,0.002626495,0.004973918],"category_scores_gemma":[0.007364131,0.0005350209,0.0015236398,0.0028904495,0.0021622179,0.0043486664,0.0011387641,0.0021104286,0.0012724446],"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":[0.00006072472,0.000110919216,0.00057080126,0.00036131684,0.00010533929,0.00022789922,0.00018644797,0.16411911,0.0021993227,0.7304864,0.0066146636,0.09495703],"study_design_scores_gemma":[0.00003430486,0.000112760026,0.00032394106,0.00006197021,0.000042411215,0.0002130276,0.000020516352,0.5547135,0.0007593905,0.4319221,0.011729969,0.0000661439],"about_ca_topic_score_codex":0.004111071,"about_ca_topic_score_gemma":0.0027870648,"teacher_disagreement_score":0.004973918,"about_ca_system_score_codex":0.0022605956,"about_ca_system_score_gemma":0.0015499155,"threshold_uncertainty_score":0.016639411},"labels":[],"label_agreement":null},{"id":"W2141999856","doi":"10.1145/1031171.1031259","title":"Approximating the top-m passages in a parallel question answering system","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Merge (version control); Computer science; Question answering; Computation; Information retrieval; Node (physics); Data mining; Algorithm","score_opus":0.009827592412512267,"score_gpt":0.23488746644961161,"score_spread":0.22505987403709934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141999856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2736126,0.000977644,0.72028655,0.0007360933,0.00004810724,0.00016804451,0.00046502327,0.0019314212,0.0017745002],"genre_scores_gemma":[0.64485705,0.0005340011,0.34835988,0.00020394738,0.00014955271,0.00020291933,0.0014393802,0.00021807969,0.004035219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987985,0.00033003138,0.000116298135,0.0003281161,0.00030255705,0.0001244899],"domain_scores_gemma":[0.99595296,0.002621571,0.00030797868,0.00046406014,0.00047722372,0.00017612107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022532244,0.000756235,0.001602687,0.0016750045,0.0012441942,0.0017374643,0.0024315743,0.0018473751,0.0022274472],"category_scores_gemma":[0.01295928,0.00058600673,0.00077924423,0.0027296634,0.0011290014,0.003645545,0.0013760463,0.00092089956,0.0010093927],"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":[0.0013187862,0.00036467187,0.009515539,0.0004459909,0.00014756969,0.0009478084,0.0011615875,0.74387926,0.024933582,0.015264393,0.0039535635,0.19806726],"study_design_scores_gemma":[0.000035000066,0.000083342136,0.00055420207,0.000005318604,0.000024102865,0.0001452188,0.00007632268,0.98387223,0.0039135055,0.010661636,0.0006196826,0.000009420266],"about_ca_topic_score_codex":0.008500871,"about_ca_topic_score_gemma":0.0066341143,"teacher_disagreement_score":0.008500871,"about_ca_system_score_codex":0.0012316264,"about_ca_system_score_gemma":0.0012836152,"threshold_uncertainty_score":0.016902804},"labels":[],"label_agreement":null},{"id":"W2142543306","doi":"10.1016/j.ipl.2006.05.013","title":"A polynomial time algorithm for the minimum quartet inconsistency problem with quartet errors","year":2006,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Time complexity; Polynomial; Mathematics; Algorithm; Combinatorics; Discrete mathematics; Mathematical analysis","score_opus":0.004749491763813111,"score_gpt":0.19647819872110153,"score_spread":0.19172870695728841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142543306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023325589,0.00041699404,0.9670291,0.00089517346,0.00019068287,0.00028796843,0.00033474408,0.0028576748,0.00466198],"genre_scores_gemma":[0.1366133,0.0001874135,0.85743314,0.00029377514,0.00011562596,0.00024933895,0.001316563,0.00065217906,0.003138653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816954,0.00028854658,0.0001620575,0.0005814388,0.00053530897,0.0002630729],"domain_scores_gemma":[0.9949987,0.0027297589,0.00037004377,0.0011629673,0.00054817897,0.00019024474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001654944,0.0014540511,0.0022850067,0.0015051514,0.0016232762,0.002629716,0.0038217013,0.0023503038,0.012343097],"category_scores_gemma":[0.008546715,0.0010695588,0.0015016418,0.0030703433,0.0010854019,0.004627209,0.0040406846,0.0030940499,0.0019931954],"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":[0.0011611533,0.00054372795,0.0013236225,0.000774826,0.00016092331,0.00034568724,0.0005031958,0.1072642,0.012989129,0.05436725,0.0348938,0.7856724],"study_design_scores_gemma":[0.00078820647,0.00030631453,0.0006720382,0.00007924925,0.00012063054,0.00069957,0.0003572115,0.7397814,0.009690913,0.23798068,0.009455596,0.00006820958],"about_ca_topic_score_codex":0.002372343,"about_ca_topic_score_gemma":0.0035367685,"teacher_disagreement_score":0.012343097,"about_ca_system_score_codex":0.0012832737,"about_ca_system_score_gemma":0.0023055628,"threshold_uncertainty_score":0.041291833},"labels":[],"label_agreement":null},{"id":"W2142590039","doi":"10.1145/2063576.2063646","title":"Indexes for highly repetitive document collections","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Computer science; Compression (physics); Data compression; Encoding (memory); Software versioning; Grammar; Inverted index; Space (punctuation); Information retrieval; Data mining; Algorithm; Artificial intelligence; Programming language; Software; Search engine indexing","score_opus":0.02842593801195017,"score_gpt":0.2432859569559241,"score_spread":0.2148600189439739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142590039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048982687,0.002786168,0.9271458,0.0006156914,0.000403295,0.00042497518,0.0027468621,0.007421806,0.009472839],"genre_scores_gemma":[0.14422335,0.0019102416,0.83657193,0.00031728088,0.00053665246,0.00034212327,0.007029464,0.0009202453,0.00814875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984365,0.00014693287,0.00016060394,0.00017636335,0.0009809011,0.00009872484],"domain_scores_gemma":[0.9955485,0.000935244,0.00040292263,0.0018764671,0.0010946976,0.00014214488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006880659,0.00056727295,0.0007480012,0.0032546485,0.0008311297,0.0018347619,0.0017240035,0.0005719971,0.0036957911],"category_scores_gemma":[0.0061658267,0.00036724296,0.0004357579,0.0051336046,0.000789246,0.004502088,0.0020411129,0.0012359128,0.0020917552],"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":[0.0003386117,0.00021091691,0.0014471093,0.0007457723,0.00008243375,0.00068281224,0.00044093616,0.015689773,0.07131166,0.08046609,0.025951082,0.80263287],"study_design_scores_gemma":[0.00022307497,0.0006053614,0.0038670853,0.0002796192,0.0002283069,0.004421038,0.00045198604,0.33834526,0.24410857,0.1804104,0.22682494,0.00023433681],"about_ca_topic_score_codex":0.001008799,"about_ca_topic_score_gemma":0.0020830927,"teacher_disagreement_score":0.0036957911,"about_ca_system_score_codex":0.00081249786,"about_ca_system_score_gemma":0.0012374712,"threshold_uncertainty_score":0.012363613},"labels":[],"label_agreement":null},{"id":"W2142857718","doi":"10.1287/opre.50.6.1073.358","title":"An Object-Oriented Random-Number Package with Many Long Streams and Substreams","year":2002,"lang":"en","type":"article","venue":"Operations Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":343,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Disjoint sets; Generator (circuit theory); Random number generation; Reduction (mathematics); Implementation; Variance reduction; Sequence (biology); Set (abstract data type); Java; Variance (accounting); Algorithm; Parallel computing; Mathematics; Discrete mathematics; Programming language; Statistics; Power (physics)","score_opus":0.03584947236627194,"score_gpt":0.33157427079349944,"score_spread":0.2957247984272275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142857718","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006121069,0.00009749547,0.8818346,0.000115176445,0.00016228949,0.00031377055,0.0033573282,0.109506406,0.0040007746],"genre_scores_gemma":[0.017651161,0.0005104912,0.88263,0.000483993,0.00027935018,0.0035052132,0.012325714,0.0621554,0.02045873],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982162,0.00041782725,0.00023655695,0.00021922053,0.0007573993,0.00015277928],"domain_scores_gemma":[0.99406826,0.0028978265,0.00042887894,0.0012352526,0.0011529896,0.00021681075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045020645,0.0018646013,0.0018004546,0.0021159651,0.0007020931,0.0021878122,0.0036406212,0.0016147862,0.08680658],"category_scores_gemma":[0.01483436,0.001629837,0.0015320341,0.0020740998,0.0006272362,0.0025541345,0.0021673641,0.0026404823,0.04573571],"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":[0.00077896984,0.00042786976,0.0032657841,0.0015341042,0.00030405592,0.0007871981,0.0003304045,0.04739293,0.010631701,0.09541203,0.4232705,0.41586447],"study_design_scores_gemma":[0.0010157302,0.00024636724,0.0016286406,0.0002822707,0.00016425533,0.0010799237,0.000032080097,0.29634058,0.018148517,0.090340905,0.5904532,0.00026756752],"about_ca_topic_score_codex":0.0009585771,"about_ca_topic_score_gemma":0.0013430767,"teacher_disagreement_score":0.08680658,"about_ca_system_score_codex":0.0006206817,"about_ca_system_score_gemma":0.0014533673,"threshold_uncertainty_score":0.29039693},"labels":[],"label_agreement":null},{"id":"W2142905080","doi":"10.1145/2094072.2094073","title":"Word-based self-indexes for natural language text","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":79,"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":"Fondo Nacional de Desarrollo Científico y Tecnológico; Xunta de Galicia; Ministerio de Ciencia e Innovación","keywords":"Computer science; Word (group theory); Phrase; Search engine indexing; Inverted index; Natural language processing; Space (punctuation); Artificial intelligence; Natural language; Index (typography); Sequence (biology); Full text search; Information retrieval; Search engine; Linguistics; World Wide Web","score_opus":0.01209488053201561,"score_gpt":0.2518274829218977,"score_spread":0.23973260238988212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142905080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037386417,0.0029244309,0.9331111,0.00032632923,0.00037497314,0.0005629993,0.0027102144,0.013173218,0.009430313],"genre_scores_gemma":[0.12112075,0.0015591297,0.8613623,0.00018489969,0.00028336377,0.0006134513,0.0056300573,0.0012959021,0.007950197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852693,0.00021264981,0.0003198749,0.00017522601,0.0006836397,0.000081702194],"domain_scores_gemma":[0.9955047,0.0013559884,0.0004379973,0.0014085969,0.001158451,0.00013430655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087164383,0.000644444,0.00073551043,0.0044225063,0.0008684902,0.0021299548,0.001207211,0.00055460574,0.0054549193],"category_scores_gemma":[0.007670279,0.00038543952,0.00056723563,0.0053335354,0.00090429286,0.006394855,0.0019375539,0.00063001673,0.0046342756],"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":[0.00040803762,0.00011288225,0.0019602547,0.0010331477,0.00007019085,0.0003387892,0.0008259866,0.0048754252,0.058098823,0.08866899,0.018876562,0.82473093],"study_design_scores_gemma":[0.00016358196,0.00093336334,0.004137134,0.00036908648,0.00019115278,0.002469921,0.0007588504,0.18876165,0.29003736,0.21393175,0.29798394,0.00026209094],"about_ca_topic_score_codex":0.0011957568,"about_ca_topic_score_gemma":0.001451055,"teacher_disagreement_score":0.0054549193,"about_ca_system_score_codex":0.0009085741,"about_ca_system_score_gemma":0.001184312,"threshold_uncertainty_score":0.018248558},"labels":[],"label_agreement":null},{"id":"W2143461819","doi":"10.1109/isita.2008.4895395","title":"On the capability of the Harada-Kobayashi algorithm in finding fix-free codewords","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Simple (philosophy); Algorithm; Combinatorics; Kraft paper; Mathematics; Computer science; Discrete mathematics; Engineering","score_opus":0.026723136301342505,"score_gpt":0.23353081456374403,"score_spread":0.2068076782624015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143461819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39215684,0.002453329,0.5926974,0.0005874515,0.00010397013,0.0001314723,0.00021183911,0.0020146866,0.00964306],"genre_scores_gemma":[0.6861583,0.00087348116,0.30897835,0.00016937903,0.0000610468,0.00012674101,0.00040097503,0.00025016515,0.002981533],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967884,0.00071204704,0.00044057998,0.00046934574,0.0012009151,0.00038877063],"domain_scores_gemma":[0.9802751,0.012860064,0.0011835208,0.0029765617,0.0022956622,0.0004090786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045359703,0.00077462924,0.0009988125,0.0026261902,0.0014633951,0.0015666956,0.0013785345,0.00136754,0.0026005544],"category_scores_gemma":[0.035075724,0.00039988058,0.0006533263,0.0019620555,0.0019641407,0.003637806,0.0018004469,0.000937245,0.0013164461],"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":[0.004677466,0.0003105194,0.025780085,0.0006981551,0.0003847197,0.00043588382,0.0011830853,0.17012489,0.056266688,0.09997364,0.0052364483,0.6349284],"study_design_scores_gemma":[0.00028123584,0.0011963773,0.0064701084,0.0002421447,0.00022201551,0.002312052,0.000604499,0.7966375,0.10752689,0.07264297,0.011605151,0.00025896975],"about_ca_topic_score_codex":0.0029507873,"about_ca_topic_score_gemma":0.003200496,"teacher_disagreement_score":0.0045359703,"about_ca_system_score_codex":0.0005165974,"about_ca_system_score_gemma":0.0018267723,"threshold_uncertainty_score":0.023988783},"labels":[],"label_agreement":null},{"id":"W2144085454","doi":"10.1109/dcc.1993.253138","title":"Minimizing error and VLSI complexity in the multiplication free approximation of arithmetic coding","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Arithmetic; Alphabet; Binary number; Arithmetic coding; Multiplication (music); Multiplication algorithm; Coding (social sciences); Computer science; Algorithm; Very-large-scale integration; Arbitrary-precision arithmetic; Saturation arithmetic; Reduction (mathematics); Mathematics; Context-adaptive binary arithmetic coding; Data compression; Combinatorics","score_opus":0.10810765796701213,"score_gpt":0.2796426647168135,"score_spread":0.17153500674980135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144085454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04731196,0.000642966,0.9455006,0.00021164525,0.000050942534,0.000031515672,0.00003138152,0.00065238966,0.0055665914],"genre_scores_gemma":[0.28205281,0.00061577366,0.7095385,0.0000959513,0.00009125087,0.000080279555,0.00015976494,0.00017332548,0.007192228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999086,0.0001987831,0.000045820372,0.00008076366,0.0005044966,0.00008410883],"domain_scores_gemma":[0.99825555,0.0010168231,0.00011467506,0.00035656305,0.00023211371,0.000024129044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007430139,0.0004927736,0.0003256767,0.0006783692,0.00031691394,0.0010714454,0.00085186266,0.00043811637,0.0020153834],"category_scores_gemma":[0.0051836604,0.00019297676,0.00024406149,0.0009885668,0.0006709612,0.0017158623,0.0007805151,0.0005364975,0.00071234314],"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":[0.00063265045,0.0000665992,0.0012224523,0.00020219355,0.000039590235,0.00020430943,0.00017152187,0.1657841,0.05885689,0.1361575,0.0035247898,0.63313735],"study_design_scores_gemma":[0.000077609584,0.00029419758,0.000832943,0.000044200286,0.000045548804,0.00055866834,0.00005278999,0.8672414,0.076458305,0.044874612,0.009493318,0.000026563013],"about_ca_topic_score_codex":0.000778215,"about_ca_topic_score_gemma":0.0021556765,"teacher_disagreement_score":0.0020153834,"about_ca_system_score_codex":0.0006767868,"about_ca_system_score_gemma":0.0008299367,"threshold_uncertainty_score":0.00674212},"labels":[],"label_agreement":null},{"id":"W2144480290","doi":"10.1109/csmr.2011.27","title":"Pattern Recognition Techniques Applied to the Abstraction of Traces of Inter-Process Communication","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Abstraction; Process (computing); Message passing; Distributed computing; Message Passing Interface; Theoretical computer science; Programming language","score_opus":0.04919094170969973,"score_gpt":0.2724200054440495,"score_spread":0.22322906373434975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144480290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01709669,0.00030005164,0.97889906,0.000147016,0.00004243455,0.000121619174,0.00030421052,0.0024116717,0.0006771959],"genre_scores_gemma":[0.17630087,0.0006762182,0.8194037,0.000092435504,0.00006839285,0.00037423175,0.0013782462,0.00020839964,0.0014974553],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990387,0.00017122604,0.00013311059,0.00021618264,0.00037632047,0.000064378386],"domain_scores_gemma":[0.99638003,0.0015990284,0.0005362478,0.00078567636,0.0006193059,0.00007971745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912424,0.0010810235,0.000768402,0.0036977492,0.0005656583,0.00096902833,0.0012401864,0.00085044693,0.0013714652],"category_scores_gemma":[0.0053607197,0.00035033355,0.00073708955,0.0044302875,0.0009376875,0.0016231849,0.0008112504,0.0011908181,0.00077773316],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024775814,0.00018208567,0.0057066632,0.00060414325,0.00012124975,0.0009678741,0.00075327803,0.030170212,0.08397836,0.015858421,0.003089182,0.8583207],"study_design_scores_gemma":[0.000062848994,0.00035023878,0.011614432,0.00012829842,0.00011203084,0.0032237475,0.00061081856,0.80121976,0.08860695,0.07188308,0.022080734,0.000107131826],"about_ca_topic_score_codex":0.0019811464,"about_ca_topic_score_gemma":0.0018552771,"teacher_disagreement_score":0.0036977492,"about_ca_system_score_codex":0.00039589015,"about_ca_system_score_gemma":0.0007184083,"threshold_uncertainty_score":0.004588008},"labels":[],"label_agreement":null},{"id":"W2144697110","doi":"10.1007/978-3-642-15369-3_41","title":"Periodicity in Streams","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; STREAMS; Operating system","score_opus":0.01191302391728481,"score_gpt":0.23794899230911204,"score_spread":0.22603596839182724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144697110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08925427,0.0101119215,0.75802654,0.0015202747,0.0017261473,0.00011783122,0.0006720095,0.0014094261,0.1371616],"genre_scores_gemma":[0.79790944,0.006445388,0.11649681,0.00047219679,0.0024680884,0.00025312082,0.0013092684,0.00072840176,0.07391721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99941754,0.00012434534,0.000049694445,0.00013013606,0.00022097913,0.000057308574],"domain_scores_gemma":[0.9986526,0.00065016525,0.00013219754,0.00028303018,0.00018347212,0.00009858277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061470125,0.0004973531,0.00079257495,0.0015524898,0.0007926003,0.0019631146,0.0005469835,0.00060593855,0.0067176674],"category_scores_gemma":[0.004401713,0.00046910215,0.00055013713,0.001672243,0.001099861,0.0024982851,0.0012204342,0.0015047101,0.001665936],"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":[0.000081062266,0.000015515625,0.00044753106,0.00010448391,0.000012743855,0.00012407711,0.00020173017,0.0029903657,0.0019916834,0.9375111,0.00562828,0.050891466],"study_design_scores_gemma":[0.000017149498,0.000036076242,0.00040578077,0.00003375058,0.00001643807,0.00038196068,0.00006755683,0.03612478,0.0017614524,0.9437031,0.01743296,0.000019005625],"about_ca_topic_score_codex":0.00033892208,"about_ca_topic_score_gemma":0.00023997613,"teacher_disagreement_score":0.0067176674,"about_ca_system_score_codex":0.0005779711,"about_ca_system_score_gemma":0.00037960216,"threshold_uncertainty_score":0.022472858},"labels":[],"label_agreement":null},{"id":"W2145195191","doi":"10.1002/spe.2325","title":"Better bitmap performance with Roaring bitmaps","year":2015,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital; Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bitmap; Computer science; Encoding (memory); Compression (physics); Oracle; Data compression; Compression ratio; Parallel computing; Algorithm; Computer graphics (images); Artificial intelligence; Engineering; Programming language","score_opus":0.0231628126247053,"score_gpt":0.26177811216115016,"score_spread":0.23861529953644486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145195191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7573051,0.0069330903,0.16183986,0.0024527756,0.0009619512,0.00022684259,0.003112277,0.035937913,0.031230144],"genre_scores_gemma":[0.8389448,0.0011397052,0.14444908,0.0006381925,0.00016193303,0.00013438477,0.0061305435,0.0014668009,0.0069346232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986644,0.00017993517,0.0001445132,0.0001904346,0.0006330838,0.00018763477],"domain_scores_gemma":[0.99312395,0.0026136818,0.00038608524,0.0021854683,0.001509833,0.00018097385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010910279,0.000593595,0.0006722545,0.0016605154,0.00044179545,0.0021021762,0.0013541547,0.00083776546,0.010858149],"category_scores_gemma":[0.010731952,0.0002486899,0.00033334296,0.00448532,0.00064031576,0.0058713807,0.001306755,0.00091405964,0.002738688],"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":[0.0035749401,0.0005969531,0.005478791,0.0007147207,0.00014831343,0.0005448783,0.00075226167,0.077881806,0.100626156,0.026060494,0.048181117,0.7354396],"study_design_scores_gemma":[0.00033564577,0.0016859956,0.005172495,0.00023381194,0.00010705426,0.0012721989,0.0009000192,0.5373897,0.36215636,0.020674372,0.06979262,0.00027972215],"about_ca_topic_score_codex":0.0021717895,"about_ca_topic_score_gemma":0.0014920158,"teacher_disagreement_score":0.010858149,"about_ca_system_score_codex":0.00067155715,"about_ca_system_score_gemma":0.0006412764,"threshold_uncertainty_score":0.036324143},"labels":[],"label_agreement":null},{"id":"W2145635616","doi":"10.1109/ccece.2006.277302","title":"Survey of Biological High Performance Computing: Algorithms, Implementations and Outlook Research","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Implementation; Massively parallel; Biological data; Field-programmable gate array; Supercomputer; Field (mathematics); Algorithm; Matching (statistics); Throughput; Parallel computing; Bioinformatics; Embedded system","score_opus":0.13373667378320905,"score_gpt":0.3762713188462085,"score_spread":0.24253464506299946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145635616","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009113876,0.47156805,0.47159505,0.0064801625,0.0017192244,0.00024411405,0.00033932566,0.0027075482,0.03623264],"genre_scores_gemma":[0.062045645,0.5224823,0.3978107,0.0017625578,0.0026392618,0.0004924139,0.0014230243,0.0007221977,0.010621935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813133,0.0004442995,0.00015346236,0.00020543016,0.0009457306,0.00011978202],"domain_scores_gemma":[0.99654466,0.0017946588,0.00011730042,0.00039540368,0.0010278453,0.000120160126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020142435,0.0012492392,0.0013160419,0.0026389994,0.0007093114,0.0036048258,0.00244331,0.0018113669,0.0063086944],"category_scores_gemma":[0.0072053964,0.0007544236,0.00070577406,0.007745262,0.00089986005,0.00452543,0.0011383161,0.0020397187,0.004817848],"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":[0.00016292634,0.00012517409,0.00089434907,0.002607095,0.00006411853,0.00008557201,0.00008279035,0.014217759,0.002731161,0.038241122,0.018446337,0.92234164],"study_design_scores_gemma":[0.00013378297,0.0004743502,0.0018670815,0.0023126672,0.00014225431,0.0012224916,0.00030189598,0.175799,0.013798406,0.1575668,0.6462306,0.00015068687],"about_ca_topic_score_codex":0.0010080348,"about_ca_topic_score_gemma":0.00070239493,"teacher_disagreement_score":0.0063086944,"about_ca_system_score_codex":0.0010187528,"about_ca_system_score_gemma":0.0017135303,"threshold_uncertainty_score":0.021104693},"labels":[],"label_agreement":null},{"id":"W2145838433","doi":"10.1007/11496656_2","title":"On the Longest Common Rigid Subsequence Problem","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Longest common subsequence problem; Substring; Subsequence; Time complexity; Longest increasing subsequence; Combinatorics; Computer science; Similarity (geometry); Algorithm; Mathematics; Artificial intelligence; Data structure","score_opus":0.018614437664633728,"score_gpt":0.24358034591822328,"score_spread":0.22496590825358956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145838433","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025739027,0.004912957,0.9183976,0.0041020312,0.0010837865,0.00013745305,0.00077908335,0.00077490637,0.044073187],"genre_scores_gemma":[0.2819195,0.0122173205,0.6382513,0.0016785628,0.004483627,0.0005209843,0.007203334,0.001254988,0.05247028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979925,0.00051947497,0.00016167191,0.0005069262,0.00060347223,0.00021601393],"domain_scores_gemma":[0.99448085,0.0035263167,0.00031042643,0.0010206923,0.0005056556,0.00015613539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022024016,0.0013133154,0.002417053,0.0023301945,0.001971631,0.0027112658,0.0031433946,0.0027433266,0.012940436],"category_scores_gemma":[0.012426652,0.0008083878,0.001448378,0.006879834,0.0026523354,0.010053194,0.0040601934,0.003983725,0.003705078],"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":[0.0003077371,0.00016567389,0.000487196,0.0005288808,0.00009606921,0.00034989693,0.0002744117,0.064386375,0.0022646901,0.6246374,0.041076288,0.26542538],"study_design_scores_gemma":[0.000033979424,0.00003953277,0.0001492882,0.000048832335,0.000020248057,0.00018739514,0.00008353324,0.08086205,0.00087208935,0.9064388,0.011243194,0.000021026915],"about_ca_topic_score_codex":0.0017481003,"about_ca_topic_score_gemma":0.0011809837,"teacher_disagreement_score":0.012940436,"about_ca_system_score_codex":0.0010283142,"about_ca_system_score_gemma":0.0014463753,"threshold_uncertainty_score":0.04329008},"labels":[],"label_agreement":null},{"id":"W2146094628","doi":"10.1007/978-0-387-30162-4_122","title":"Edit Distance Under Block Operations","year":2008,"lang":"en","type":"article","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Edit distance; Combinatorics; Substring; Character (mathematics); Block (permutation group theory); Alphabet; Mathematics; Permutation (music); Discrete mathematics; Computer science; Algorithm; Physics; Data structure; Geometry","score_opus":0.01426117440055015,"score_gpt":0.2400185813164199,"score_spread":0.22575740691586976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146094628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051634472,0.0026975365,0.9073832,0.0016183127,0.0008986799,0.00009562229,0.0014348632,0.0010699816,0.03316736],"genre_scores_gemma":[0.5828079,0.004703689,0.3261576,0.00090790447,0.0020841314,0.00045087747,0.004340214,0.0009962473,0.077551484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737144,0.0005754712,0.0002515105,0.000604251,0.0010416354,0.0001557519],"domain_scores_gemma":[0.9936521,0.00279481,0.00045427386,0.0018504321,0.00101471,0.00023372623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014286144,0.00060680683,0.0012170462,0.0024956854,0.00084424776,0.0025269517,0.001240491,0.0014261153,0.009571289],"category_scores_gemma":[0.010194489,0.00037788603,0.00060744485,0.0035965217,0.0013651359,0.007871785,0.0027652436,0.0020426004,0.0032905168],"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":[0.00017404252,0.00005970293,0.0003796024,0.00013736579,0.00003489219,0.00017636803,0.00019542148,0.008103325,0.0035830352,0.8355449,0.009877465,0.14173399],"study_design_scores_gemma":[0.000022649976,0.00014193356,0.00040007007,0.00003216415,0.000029027671,0.00059837097,0.000062156265,0.059687875,0.0069514434,0.901226,0.030815175,0.000033142645],"about_ca_topic_score_codex":0.00061320886,"about_ca_topic_score_gemma":0.000433917,"teacher_disagreement_score":0.009571289,"about_ca_system_score_codex":0.00075156416,"about_ca_system_score_gemma":0.00092128926,"threshold_uncertainty_score":0.03201914},"labels":[],"label_agreement":null},{"id":"W2146254066","doi":"10.1109/hpcsa.2002.1019170","title":"Concurrent and distributed data structures for multikey sorting on computer clusters","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Lethbridge","funders":"","keywords":"Computer science; Sorting; Sorting network; Supercomputer; Distributed computing; Parallel computing; Sorting algorithm; Load balancing (electrical power); Data structure; sort; Range (aeronautics); Computer cluster; Cluster (spacecraft); Operating system; Database; Algorithm","score_opus":0.051779993138675005,"score_gpt":0.30488688228817507,"score_spread":0.2531068891495001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146254066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053069595,0.001494527,0.9295652,0.0010528832,0.00038732836,0.00024553027,0.00017617147,0.0018993776,0.01210937],"genre_scores_gemma":[0.4261607,0.0014313882,0.5480274,0.0002821183,0.00037215633,0.00065859273,0.00086000207,0.0006016142,0.021606028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989465,0.0002260206,0.00009472186,0.00013413171,0.00048464228,0.00011407748],"domain_scores_gemma":[0.9959448,0.0015541539,0.00021263541,0.0012896676,0.00077234703,0.00022646667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016501868,0.00043891603,0.0006906327,0.0008856901,0.0020215828,0.002509466,0.002222322,0.00078748696,0.0066459905],"category_scores_gemma":[0.006599637,0.00040238185,0.00048500625,0.0024607014,0.0013943161,0.0037994788,0.0023271923,0.0012089182,0.0012322976],"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":[0.00077423966,0.0002484798,0.0019192353,0.0005913863,0.0000744563,0.00024740878,0.0005693612,0.13566034,0.012134256,0.52208906,0.023481952,0.30220988],"study_design_scores_gemma":[0.00029188488,0.00027177087,0.000822383,0.00008710397,0.00007621588,0.00027263703,0.00028469425,0.5389729,0.0141299665,0.3898062,0.054915335,0.0000689362],"about_ca_topic_score_codex":0.0014605939,"about_ca_topic_score_gemma":0.0029660352,"teacher_disagreement_score":0.0066459905,"about_ca_system_score_codex":0.0016800937,"about_ca_system_score_gemma":0.002135323,"threshold_uncertainty_score":0.02223301},"labels":[],"label_agreement":null},{"id":"W2147175228","doi":"10.1109/isspa.2010.5605599","title":"Efficient data encoder for low-power capsule endoscopy application","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Encoder; Computer science; Bandwidth (computing); Compression ratio; Frame (networking); Frame rate; Encoding (memory); Energy consumption; Data compression; Data set; Algorithm; Real-time computing; Computer vision; Artificial intelligence; Engineering","score_opus":0.014979405361988033,"score_gpt":0.2828348037528378,"score_spread":0.26785539839084976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147175228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03827868,0.00083777145,0.9564929,0.000118547345,0.000052396183,0.00006982744,0.0001639677,0.001554659,0.0024313065],"genre_scores_gemma":[0.37566307,0.0006626517,0.61509156,0.00012660759,0.00007988042,0.000124932,0.00069875456,0.00017711702,0.00737544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998036,0.000033827444,0.000012477898,0.000020197227,0.000113137525,0.000016802012],"domain_scores_gemma":[0.99958545,0.00018705029,0.000044942317,0.000045426958,0.000120136945,0.000017064653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029340724,0.0004192089,0.00033475153,0.00062124565,0.00023664543,0.00045471863,0.00066524505,0.0004023554,0.0030457277],"category_scores_gemma":[0.0007224789,0.00012147944,0.00019433096,0.00058899936,0.00018843722,0.00093219,0.00033848503,0.00036334546,0.0010616002],"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":[0.0009209774,0.00015256315,0.0012334444,0.0006686054,0.000053813917,0.00056890206,0.00017922393,0.032951236,0.35133898,0.015082544,0.0061743986,0.59067535],"study_design_scores_gemma":[0.00011684527,0.00046197383,0.0009795856,0.000049586928,0.00006374348,0.0009781003,0.000047340505,0.39204553,0.5763651,0.0024515516,0.026390664,0.000049881135],"about_ca_topic_score_codex":0.0004934709,"about_ca_topic_score_gemma":0.00061776064,"teacher_disagreement_score":0.0030457277,"about_ca_system_score_codex":0.00032476048,"about_ca_system_score_gemma":0.00033251202,"threshold_uncertainty_score":0.010188997},"labels":[],"label_agreement":null},{"id":"W2147175297","doi":"10.1109/icsmc.1997.625803","title":"On using parametric string distances and vector quantization in designing syntactic pattern recognition systems","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Edit distance; Computer science; Vector quantization; Pattern recognition (psychology); Parametric statistics; Quantization (signal processing); Classifier (UML); Artificial intelligence; String (physics); Algorithm; Speech recognition; Mathematics","score_opus":0.07561650716031804,"score_gpt":0.257541309560092,"score_spread":0.181924802399774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147175297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007191005,0.00045224238,0.99134105,0.00016614822,0.000024212342,0.000053092062,0.000016513777,0.0002549034,0.0005008107],"genre_scores_gemma":[0.2142642,0.00067835255,0.7835473,0.00017627087,0.0000868526,0.0002363958,0.00011150606,0.00010438207,0.0007946973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99565506,0.0019117867,0.00046604895,0.0005508711,0.0012725368,0.00014368747],"domain_scores_gemma":[0.9924062,0.004572987,0.00063733174,0.0010372942,0.001245693,0.00010044508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005346442,0.000943324,0.0011968263,0.0017141812,0.00065946346,0.0017370178,0.0018540121,0.0012387206,0.0010309814],"category_scores_gemma":[0.02073361,0.0004987196,0.00046796747,0.002310816,0.0024095764,0.007471258,0.0018775781,0.0013309428,0.00058722496],"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":[0.00018184508,0.00007064182,0.0011378436,0.00021492527,0.000040212744,0.00006619959,0.00034333894,0.27177247,0.0068588657,0.10067702,0.0013029992,0.61733365],"study_design_scores_gemma":[0.000034495057,0.00021776966,0.00031157763,0.000053794232,0.000020248586,0.00013874318,0.00010194965,0.8745186,0.008743329,0.112171516,0.0036367462,0.000051189298],"about_ca_topic_score_codex":0.0016595521,"about_ca_topic_score_gemma":0.0018448146,"teacher_disagreement_score":0.005346442,"about_ca_system_score_codex":0.0012611864,"about_ca_system_score_gemma":0.0011070906,"threshold_uncertainty_score":0.028275073},"labels":[],"label_agreement":null},{"id":"W2147344024","doi":"10.1145/1841909.1841913","title":"Fast and Compact Web Graph Representations","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":103,"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":"Fondo Nacional de Desarrollo Científico y Tecnológico","keywords":"Computer science; Theoretical computer science; Graph","score_opus":0.01849260082025904,"score_gpt":0.2626085176005849,"score_spread":0.24411591678032585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147344024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07016766,0.0014022889,0.9055863,0.0007895556,0.00024068973,0.00016208085,0.0024547612,0.010589222,0.008607442],"genre_scores_gemma":[0.38480517,0.0014522455,0.5948659,0.00030887834,0.00020601455,0.00028697794,0.0077532614,0.00122426,0.009097269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928373,0.00011172143,0.000041700572,0.000102388265,0.00039438752,0.00006610406],"domain_scores_gemma":[0.9980781,0.00052932726,0.00012769761,0.0008791671,0.00033703606,0.00004864512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032275572,0.0006558992,0.0007662595,0.0025730724,0.00035792068,0.0016754909,0.0011068338,0.00095618406,0.005722493],"category_scores_gemma":[0.0049750363,0.00037392467,0.0004440581,0.003398582,0.0004387592,0.0036787344,0.0016074659,0.0011720647,0.0023182197],"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":[0.00043135145,0.00015309101,0.0009525148,0.0003869289,0.00006125337,0.0005992664,0.0003588146,0.12743653,0.028922452,0.06014583,0.037616704,0.7429352],"study_design_scores_gemma":[0.00007695084,0.0000869341,0.00074456073,0.000053328018,0.000031462092,0.0007456287,0.00028875453,0.8553949,0.028406844,0.09006534,0.024068812,0.00003645854],"about_ca_topic_score_codex":0.0012974056,"about_ca_topic_score_gemma":0.002249394,"teacher_disagreement_score":0.005722493,"about_ca_system_score_codex":0.00047209059,"about_ca_system_score_gemma":0.00046595375,"threshold_uncertainty_score":0.019143641},"labels":[],"label_agreement":null},{"id":"W2147425931","doi":"10.1007/3-540-44674-5_3","title":"Fast Implementations of Automata Computations","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Automaton; Edit distance; Sequence (biology); Computation; Algorithm; Implementation; Theoretical computer science; Class (philosophy); Parallel computing; Bit array; Programming language; Artificial intelligence; Type (biology)","score_opus":0.022314547805681227,"score_gpt":0.28873630459525357,"score_spread":0.26642175678957236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147425931","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020850625,0.001296032,0.94099665,0.00045451743,0.00054322067,0.000108909495,0.00043226886,0.009880397,0.025437344],"genre_scores_gemma":[0.38413948,0.0010958696,0.5899381,0.00036757305,0.00029598048,0.0005436202,0.0013152536,0.0021791891,0.020125011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978282,0.0005701271,0.0001680018,0.00039592845,0.0007388873,0.00029887757],"domain_scores_gemma":[0.9955836,0.0019680178,0.000113261754,0.0016076593,0.0005982816,0.00012921558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011400203,0.0013561635,0.0013177489,0.0012897066,0.0013041575,0.0040925667,0.002976439,0.0015308886,0.02472009],"category_scores_gemma":[0.006975891,0.0011172881,0.0013437592,0.0023556151,0.0013063698,0.006393559,0.0026827087,0.0027793637,0.0066448664],"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":[0.00072753814,0.00014619519,0.0004827679,0.0004887678,0.000098011806,0.00012324496,0.00034327162,0.03171922,0.012252122,0.531893,0.02650733,0.39521852],"study_design_scores_gemma":[0.00017654206,0.00009176515,0.0001942974,0.000097841905,0.00007350691,0.00013653384,0.00011315685,0.24889928,0.018275985,0.7021964,0.029692017,0.000052671876],"about_ca_topic_score_codex":0.0015941375,"about_ca_topic_score_gemma":0.0032603785,"teacher_disagreement_score":0.02472009,"about_ca_system_score_codex":0.0016859415,"about_ca_system_score_gemma":0.0015049938,"threshold_uncertainty_score":0.082696974},"labels":[],"label_agreement":null},{"id":"W2147440220","doi":"10.1007/s007780000029","title":"One-dimensional and multi-dimensional substring selectivity estimation","year":2000,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Substring; Computer science; String (physics); Context (archaeology); Matching (statistics); String searching algorithm; Constraint (computer-aided design); Theoretical computer science; Algorithm; Data structure; Mathematics; Pattern matching; Artificial intelligence; Statistics","score_opus":0.02152338838573285,"score_gpt":0.24920143496609998,"score_spread":0.22767804658036714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147440220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1274479,0.0012408312,0.86792886,0.00027945056,0.00006943396,0.00003256906,0.0005910651,0.0007558807,0.0016539547],"genre_scores_gemma":[0.6536906,0.0014257557,0.337769,0.00015078756,0.00023700637,0.0000690936,0.001930933,0.00010324687,0.0046235537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920875,0.000133289,0.000059802187,0.00013936871,0.00034172458,0.00011709973],"domain_scores_gemma":[0.996612,0.0018168864,0.0002627646,0.0007149627,0.00046485325,0.00012838261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011392876,0.00038683743,0.00088625285,0.0014824662,0.00037735436,0.00083671557,0.00088229525,0.0008137988,0.0018467341],"category_scores_gemma":[0.0055311816,0.00026514535,0.00043967378,0.0018548719,0.0003719233,0.0015237486,0.0012042744,0.000601887,0.0011197046],"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":[0.0011336076,0.00019596783,0.01881465,0.00023909759,0.00010906129,0.000413215,0.00011634053,0.071089774,0.06565055,0.011799026,0.0030969793,0.82734174],"study_design_scores_gemma":[0.000020641235,0.00008449229,0.009883365,0.000015868834,0.000046566787,0.0007437708,0.00009802698,0.9378821,0.04223669,0.0068453187,0.0021047615,0.0000383318],"about_ca_topic_score_codex":0.001488841,"about_ca_topic_score_gemma":0.002593106,"teacher_disagreement_score":0.0018467341,"about_ca_system_score_codex":0.00032357496,"about_ca_system_score_gemma":0.0006268462,"threshold_uncertainty_score":0.006177902},"labels":[],"label_agreement":null},{"id":"W2147492358","doi":"10.1093/bioinformatics/18.12.1696","title":"DNACompress: fast and effective DNA sequence compression","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":210,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada); Western University","funders":"National Science Foundation","keywords":"Compression (physics); Sequence (biology); DNA; Computer science; DNA sequencing; Data compression; Computational biology; Algorithm; Genetics; Biology; Materials science; Composite material","score_opus":0.021486470274000594,"score_gpt":0.23858404324737703,"score_spread":0.21709757297337645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147492358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03246675,0.0020878066,0.8701677,0.00077987515,0.00047597173,0.0003362939,0.005522962,0.077695474,0.01046714],"genre_scores_gemma":[0.118822075,0.0009165324,0.84883064,0.0003600698,0.00024098397,0.00072024367,0.012414291,0.0037377423,0.01395739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994324,0.00007205144,0.000045570516,0.000103910235,0.00030528073,0.00004085179],"domain_scores_gemma":[0.99912006,0.00035457566,0.000087373126,0.00016591104,0.00021379702,0.000058201775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007324831,0.0011686556,0.00055818196,0.0020201239,0.00055097125,0.0008478376,0.0012513102,0.00078450405,0.014409398],"category_scores_gemma":[0.0027052835,0.00054530863,0.00040753194,0.0018175566,0.000492989,0.0010320103,0.0012072697,0.0011707062,0.0073053464],"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":[0.0007889232,0.0001256345,0.0008934613,0.00056272355,0.00007034222,0.0004213182,0.00016181634,0.012756411,0.08729523,0.014869772,0.10966554,0.7723889],"study_design_scores_gemma":[0.00050999183,0.00031925965,0.001916713,0.00015087707,0.00007012073,0.0013295701,0.00009356661,0.3799454,0.47183505,0.023258809,0.12046427,0.000106424195],"about_ca_topic_score_codex":0.0009566056,"about_ca_topic_score_gemma":0.001350841,"teacher_disagreement_score":0.014409398,"about_ca_system_score_codex":0.00045018297,"about_ca_system_score_gemma":0.00070343126,"threshold_uncertainty_score":0.048204243},"labels":[],"label_agreement":null},{"id":"W2147614729","doi":"10.1109/sies.2008.4577680","title":"An embedded decryption/decompression engine using Handel-C","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; CMC Microsystems","keywords":"Computer science; Encryption; Field-programmable gate array; Throughput; Data stream mining; Key (lock); Data security; Embedded system; Data compression; Computer hardware; Computer network; Algorithm; Wireless; Data mining; Computer security; Operating system","score_opus":0.041564886361011105,"score_gpt":0.29241139998127513,"score_spread":0.250846513620264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147614729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055558484,0.00034425317,0.89380723,0.00015268904,0.00013063535,0.0004163371,0.00036878773,0.034237362,0.014984156],"genre_scores_gemma":[0.45875582,0.00039715928,0.51532954,0.0004777352,0.00006177493,0.00023468291,0.00094705477,0.0011514038,0.022644801],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996567,0.000021741364,0.000030088615,0.00007699446,0.00014611844,0.00006849728],"domain_scores_gemma":[0.999647,0.00011345819,0.00004307566,0.00006464566,0.00010695219,0.000024951329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003213287,0.000731211,0.0004728855,0.0004482594,0.00033707652,0.00082958245,0.0012754052,0.00057046115,0.005568256],"category_scores_gemma":[0.0006720181,0.00030753424,0.0003862361,0.0003859545,0.00038260987,0.00082599,0.00038114583,0.0006491527,0.0015500424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019864123,0.00043823043,0.0022165496,0.0009517105,0.00016310389,0.0014017423,0.00023905655,0.05140887,0.4299052,0.035788354,0.017236833,0.4582639],"study_design_scores_gemma":[0.00029964247,0.00077257183,0.0011092912,0.00008407211,0.00011935186,0.0017490388,0.000035596877,0.3627651,0.57985574,0.0039111506,0.04917646,0.00012190845],"about_ca_topic_score_codex":0.0024891614,"about_ca_topic_score_gemma":0.0021477358,"teacher_disagreement_score":0.005568256,"about_ca_system_score_codex":0.00046994936,"about_ca_system_score_gemma":0.0010544509,"threshold_uncertainty_score":0.018627703},"labels":[],"label_agreement":null},{"id":"W2147671191","doi":"10.1145/1148170.1148233","title":"Hybrid index maintenance for growing text collections","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","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 Waterloo","funders":"","keywords":"Search engine indexing; Computer science; Merge (version control); Index (typography); Monotonic function; Auxiliary memory; Information retrieval; Zipf's law; Data mining; World Wide Web; Mathematics; Statistics","score_opus":0.008690065081308028,"score_gpt":0.22291227247964,"score_spread":0.21422220739833195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147671191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04547602,0.00059561455,0.9492392,0.00009293568,0.000028683005,0.00011291041,0.00014916061,0.0026194924,0.0016860118],"genre_scores_gemma":[0.24260697,0.00032906912,0.75304615,0.000089416535,0.000089177236,0.000245169,0.000625082,0.00043010042,0.0025388997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998774,0.00023375143,0.00012846665,0.00018191234,0.0005988489,0.000082983235],"domain_scores_gemma":[0.9934157,0.0021089867,0.0006972824,0.0025904463,0.0010020747,0.00018546211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001290673,0.0005998445,0.0009195072,0.00242704,0.00075678836,0.0014516313,0.0023212954,0.0006678817,0.0015667903],"category_scores_gemma":[0.00839185,0.00042949643,0.0005607174,0.0027344066,0.00064515375,0.0033326217,0.0019146403,0.00080385985,0.00097643223],"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":[0.00031342448,0.00020358589,0.0031655533,0.00030792222,0.000103363265,0.00023242946,0.0005229898,0.043303076,0.059240885,0.016575813,0.00646615,0.8695649],"study_design_scores_gemma":[0.00011053714,0.000448224,0.0025083919,0.00004406884,0.00013751323,0.0013567205,0.00020869474,0.8680118,0.08405605,0.025981126,0.017054787,0.00008212935],"about_ca_topic_score_codex":0.0010936648,"about_ca_topic_score_gemma":0.001521412,"teacher_disagreement_score":0.00242704,"about_ca_system_score_codex":0.0005295635,"about_ca_system_score_gemma":0.0006485364,"threshold_uncertainty_score":0.0068258643},"labels":[],"label_agreement":null},{"id":"W2148029210","doi":"10.1109/dcc.2013.40","title":"Partition Tree Weighting","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Weighting; Computer science; Partition (number theory); Piecewise; Algorithm; Entropy (arrow of time); Tree (set theory); k-d tree; Huffman coding; Redundancy (engineering); Data mining; Theoretical computer science; Tree traversal; Data compression; Mathematics","score_opus":0.009474460688097647,"score_gpt":0.20453992869986662,"score_spread":0.19506546801176897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148029210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018060704,0.00014188574,0.9968754,0.000042798387,0.000028536939,0.000039354505,0.000054220825,0.00027571266,0.0007361191],"genre_scores_gemma":[0.06388357,0.0003499419,0.9310545,0.00012574815,0.0000887932,0.00023215273,0.00060599105,0.00041709092,0.0032422307],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864036,0.0003425845,0.00006563623,0.00023493898,0.0006038185,0.00011275689],"domain_scores_gemma":[0.99804306,0.0008533974,0.00012938947,0.00041778426,0.00047992938,0.000076373864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014578681,0.0009688986,0.0012880616,0.0027915162,0.00085164513,0.0016515433,0.0022433023,0.001385063,0.0073856097],"category_scores_gemma":[0.008029461,0.0005808787,0.0010948719,0.0029170173,0.0006374199,0.0030648676,0.0024297647,0.001703749,0.0023386176],"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":[0.00023312238,0.00008320411,0.0010332074,0.00020104456,0.00011885079,0.000112393645,0.00022895484,0.11463923,0.013266461,0.10224028,0.007462684,0.7603805],"study_design_scores_gemma":[0.000038663366,0.0000944754,0.00034923828,0.000057168603,0.000057433914,0.00028419122,0.00006980185,0.856622,0.009509854,0.1134994,0.01938528,0.00003251568],"about_ca_topic_score_codex":0.0014325154,"about_ca_topic_score_gemma":0.0019546407,"teacher_disagreement_score":0.0073856097,"about_ca_system_score_codex":0.0008329307,"about_ca_system_score_gemma":0.0012530533,"threshold_uncertainty_score":0.024707317},"labels":[],"label_agreement":null},{"id":"W2148545105","doi":"10.1109/wi-iat.2009.114","title":"Query Suggestion by Query Search: A New Approach to User Support in Web Search","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Alberta","funders":"","keywords":"Web query classification; Web search query; Computer science; Information retrieval; Query expansion; Query optimization; Set (abstract data type); Sargable; Rank (graph theory); Query language; Search engine; Range (aeronautics); Result set; Mathematics; Programming language; Combinatorics; Engineering","score_opus":0.037119172220794985,"score_gpt":0.2887133720485981,"score_spread":0.2515941998278031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148545105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009770533,0.0021306449,0.9800598,0.0012646866,0.00009530859,0.00025230058,0.00007446144,0.0017351648,0.004617186],"genre_scores_gemma":[0.20679727,0.0016470213,0.78292036,0.0008505537,0.00069369003,0.0005144454,0.00022758271,0.00044011115,0.0059089777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.984929,0.006567821,0.0006530063,0.0011031311,0.0061952234,0.0005517347],"domain_scores_gemma":[0.9747278,0.017153015,0.0008327815,0.004804149,0.0021155647,0.00036667436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068368777,0.0010198457,0.0019682522,0.0031379918,0.0013384261,0.0038085098,0.0037617665,0.0030075768,0.0045775347],"category_scores_gemma":[0.028098933,0.0009388792,0.0012519283,0.0038573088,0.003999913,0.0125133395,0.0031915968,0.0026686697,0.0023480856],"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":[0.0016435853,0.0007590517,0.0045032734,0.00096429,0.00025636583,0.0006201054,0.005721886,0.028258016,0.028296307,0.26780498,0.01982459,0.6413476],"study_design_scores_gemma":[0.0004296148,0.001005458,0.0018952666,0.0002091223,0.00032400122,0.002758116,0.0012172251,0.6102202,0.029824322,0.22307763,0.12867634,0.00036273737],"about_ca_topic_score_codex":0.0028387348,"about_ca_topic_score_gemma":0.001955422,"teacher_disagreement_score":0.0068368777,"about_ca_system_score_codex":0.001226247,"about_ca_system_score_gemma":0.0015273097,"threshold_uncertainty_score":0.03615731},"labels":[],"label_agreement":null},{"id":"W2148659572","doi":"10.5555/1283383.1283456","title":"Succinct indexes for strings, binary relations and multi-labeled trees","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Encoding (memory); String (physics); Set (abstract data type); Binary number; Rank (graph theory); Bit array; Type (biology); String searching algorithm; Data structure; Theoretical computer science; Combinatorics; Mathematics; Arithmetic","score_opus":0.022843810786979935,"score_gpt":0.28122349483335096,"score_spread":0.258379684046371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148659572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067832083,0.0002920712,0.98712385,0.00024827645,0.00008417588,0.00014159596,0.00071515696,0.0020060276,0.0026057232],"genre_scores_gemma":[0.09138945,0.0006905411,0.8971453,0.00046718022,0.0001245856,0.00049092545,0.0025806848,0.0010478931,0.0060634245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99622464,0.0006111893,0.00063135923,0.0004966683,0.0017715344,0.00026464785],"domain_scores_gemma":[0.9911431,0.0028469812,0.0010908095,0.0035267733,0.0011346253,0.0002576941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020956635,0.00091027765,0.0009598666,0.0017208224,0.0008966262,0.003807002,0.0022307637,0.0011393896,0.0065026702],"category_scores_gemma":[0.01078527,0.0007997246,0.0012926747,0.0036371532,0.0025342577,0.014115451,0.0033625287,0.0025123165,0.0027199592],"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":[0.00061033096,0.00016139081,0.001531183,0.00079426315,0.00004938481,0.00030642588,0.0009041621,0.03713982,0.03500147,0.6542045,0.013816521,0.25548065],"study_design_scores_gemma":[0.00012652442,0.00042463452,0.0005287568,0.0003852392,0.0000933568,0.0006358508,0.00031490411,0.24252088,0.12133691,0.5121619,0.12127504,0.00019607627],"about_ca_topic_score_codex":0.0010300649,"about_ca_topic_score_gemma":0.0016264112,"teacher_disagreement_score":0.0065026702,"about_ca_system_score_codex":0.0019041544,"about_ca_system_score_gemma":0.0019942038,"threshold_uncertainty_score":0.02175355},"labels":[],"label_agreement":null},{"id":"W2148837681","doi":"10.1016/s0304-3975(03)00049-5","title":"A fast algorithm to generate necklaces with fixed content","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Alphabet; Amortized analysis; Algorithm; Mathematics; Fixed point; Constant (computer programming); Simple (philosophy); Symbol (formal); Construct (python library); Bounding overwatch; Listing (finance); Combinatorics; Content (measure theory); Computer science; Data structure; Artificial intelligence","score_opus":0.015390357915986018,"score_gpt":0.23220576042524038,"score_spread":0.21681540250925435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148837681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009111247,0.00017490942,0.9846795,0.000110203786,0.000115514056,0.0002523283,0.00021057698,0.0025053527,0.0028403017],"genre_scores_gemma":[0.036849957,0.000120171615,0.9575428,0.000049684422,0.00003712691,0.00024872887,0.0004472208,0.00043088227,0.0042734137],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990754,0.000093067945,0.00006911421,0.0001370146,0.0005454139,0.00008000678],"domain_scores_gemma":[0.9976852,0.00069911673,0.00015096522,0.0007644751,0.00059228676,0.00010801136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097123004,0.0014586402,0.0008009097,0.0021737786,0.0010151032,0.0010961132,0.001293017,0.001461345,0.01202235],"category_scores_gemma":[0.0045694634,0.0006233622,0.0008900075,0.0018419526,0.0010350568,0.0016752811,0.0029547152,0.0014272437,0.00484326],"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":[0.0006797907,0.00014610095,0.0005070459,0.00035687487,0.00006911681,0.00032060622,0.00036534696,0.017606346,0.08201431,0.055165395,0.017459888,0.8253092],"study_design_scores_gemma":[0.00049616594,0.00068376283,0.0009196381,0.00016846828,0.00017442214,0.0020666053,0.00028729608,0.5491254,0.2752033,0.09510413,0.07559809,0.00017276793],"about_ca_topic_score_codex":0.0010843049,"about_ca_topic_score_gemma":0.0018483636,"teacher_disagreement_score":0.01202235,"about_ca_system_score_codex":0.00070924446,"about_ca_system_score_gemma":0.0010718763,"threshold_uncertainty_score":0.04021877},"labels":[],"label_agreement":null},{"id":"W2149332866","doi":"10.1093/database/baq029","title":"Damming the genomic data flood using a comprehensive analysis and storage data structure","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"","keywords":"Computer science; Data mining; Data structure; Search engine indexing; Database; Redundancy (engineering); Data management; Data redundancy; Computer data storage; Data set; Data processing; Software; Normalization (sociology); Big data; Table (database); Information retrieval; Operating system","score_opus":0.05690010147651383,"score_gpt":0.3044548854189972,"score_spread":0.24755478394248334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149332866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047950674,0.0009407764,0.9186536,0.004775042,0.00047778003,0.0004760521,0.003576275,0.018052157,0.0050977375],"genre_scores_gemma":[0.1056184,0.00092688244,0.8785253,0.001000907,0.00025893244,0.00044591242,0.007648743,0.001049454,0.0045253984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789006,0.00038390257,0.0002755346,0.00036359022,0.0009958653,0.00009108717],"domain_scores_gemma":[0.98805064,0.0028842564,0.0006784444,0.006319857,0.0017716553,0.00029522867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004228822,0.00059487845,0.0010895411,0.003040823,0.0011998696,0.0049608466,0.0021708163,0.0010523775,0.0035057983],"category_scores_gemma":[0.014251824,0.000720195,0.0009560676,0.0051384238,0.0012831753,0.005876242,0.0039697615,0.0022973958,0.0028402319],"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":[0.00079695735,0.00029019773,0.011564689,0.00046421695,0.00018032143,0.0008751236,0.0011538849,0.01961543,0.04019037,0.077301644,0.0736514,0.7739157],"study_design_scores_gemma":[0.0005685475,0.00071831123,0.013671922,0.0004437986,0.00029417817,0.0029677968,0.0010922813,0.34459254,0.14216755,0.19735491,0.29578623,0.00034181125],"about_ca_topic_score_codex":0.0015464915,"about_ca_topic_score_gemma":0.0016881435,"teacher_disagreement_score":0.0049608466,"about_ca_system_score_codex":0.0011227172,"about_ca_system_score_gemma":0.0032714286,"threshold_uncertainty_score":0.022364378},"labels":[],"label_agreement":null},{"id":"W2149356828","doi":"10.1007/s00453-013-9840-x","title":"Explicit and Efficient Hash Families Suffice for Cuckoo Hashing with a Stash","year":2013,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Universal hashing; Dynamic perfect hashing; K-independent hashing; Double hashing; Hash function; Perfect hash function; Computer science; Hash table; Mathematical proof; Constant (computer programming); Theoretical computer science; Theory of computation; Mathematics; Discrete mathematics; Combinatorics; Algorithm; Programming language","score_opus":0.007133839550742515,"score_gpt":0.20254706877188305,"score_spread":0.19541322922114054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149356828","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08477406,0.001015023,0.8820239,0.0018432632,0.0004754684,0.00036652145,0.00076054054,0.0021705502,0.02657079],"genre_scores_gemma":[0.8583038,0.00066535146,0.119687036,0.0008829555,0.000427366,0.00047916613,0.0009352553,0.00077380415,0.017845338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99678695,0.0006664631,0.00023014277,0.00056200125,0.0011943044,0.0005601589],"domain_scores_gemma":[0.9838612,0.0044488763,0.0006067375,0.009431172,0.0013490818,0.000302887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002358699,0.001047665,0.0018544472,0.0011422074,0.0029234958,0.0032784396,0.0018569989,0.0042541646,0.010998679],"category_scores_gemma":[0.023002056,0.0012254051,0.0012036642,0.0022087302,0.0045573832,0.014691838,0.006028074,0.0042987,0.0046700626],"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":[0.0009198595,0.00019648415,0.0016218402,0.00040726093,0.000067083725,0.00034933828,0.00052105665,0.022179909,0.009322865,0.8771643,0.009520129,0.077729896],"study_design_scores_gemma":[0.00010984082,0.00013772225,0.0003258013,0.000085489555,0.000044156965,0.00048522916,0.00014911305,0.059992608,0.009737597,0.9167967,0.012059611,0.00007618754],"about_ca_topic_score_codex":0.00038099944,"about_ca_topic_score_gemma":0.0006201471,"teacher_disagreement_score":0.010998679,"about_ca_system_score_codex":0.0010828463,"about_ca_system_score_gemma":0.0019541327,"threshold_uncertainty_score":0.036794186},"labels":[],"label_agreement":null},{"id":"W2149499527","doi":"10.1109/dcc.2002.999945","title":"Globally optimal uneven error-protected packetization of scalable code streams","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"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":"Scalability; Algorithm; Computer science; Redundancy (engineering); Convex function; Network packet; Monotonic function; Binary logarithm; Function (biology); Regular polygon; Discrete mathematics; Mathematics","score_opus":0.015237382643186956,"score_gpt":0.24737265341627723,"score_spread":0.23213527077309026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149499527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013314989,0.00006497046,0.98535687,0.00004847069,0.000012792162,0.000027649074,0.00002234265,0.00033896664,0.00081293285],"genre_scores_gemma":[0.36678532,0.0002061059,0.629855,0.00008753529,0.00003576191,0.0001340961,0.00021751234,0.00018729968,0.0024914152],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994134,0.00013791533,0.000036623613,0.000109555534,0.0002233635,0.00007920876],"domain_scores_gemma":[0.9991146,0.00041699875,0.000095592804,0.0002203909,0.00012258717,0.000029886061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008786002,0.0007255552,0.00082422997,0.0004974014,0.0003230901,0.0007299178,0.000867651,0.00050719036,0.0017215565],"category_scores_gemma":[0.003708574,0.00023742624,0.00040642484,0.00063344144,0.000692921,0.0016199287,0.0014799831,0.00097578176,0.0003217775],"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":[0.00022996329,0.000052931773,0.0006371442,0.00010824135,0.000037916143,0.00013399398,0.00018210133,0.5966226,0.020906113,0.06819956,0.0023912983,0.31049818],"study_design_scores_gemma":[0.000013341605,0.0000483617,0.00009280227,0.000008250357,0.0000056217173,0.000054110442,0.000030542327,0.96645,0.01349319,0.018467695,0.0013283876,0.000007632378],"about_ca_topic_score_codex":0.0007342817,"about_ca_topic_score_gemma":0.0005377864,"teacher_disagreement_score":0.0017215565,"about_ca_system_score_codex":0.00064373075,"about_ca_system_score_gemma":0.0006354138,"threshold_uncertainty_score":0.0057591796},"labels":[],"label_agreement":null},{"id":"W2149740174","doi":"10.1109/icfhr.2010.112","title":"Digital ink compression via functional approximation","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Legendre polynomials; Legendre function; Legendre wavelet; Mathematics; Chebyshev polynomials; Representation (politics); Sobolev space; Chebyshev filter; Algorithm; Computer science; Mathematical analysis; Artificial intelligence; Wavelet; Wavelet transform","score_opus":0.010249224543618714,"score_gpt":0.21202380725306968,"score_spread":0.20177458270945098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149740174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075338736,0.0007959678,0.9118397,0.00022050078,0.00010497681,0.000039774615,0.000070518436,0.000824042,0.010765713],"genre_scores_gemma":[0.6826377,0.0012799894,0.3064275,0.00011241081,0.00010591567,0.00006476008,0.00019568054,0.00019196382,0.008984067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999798,0.00003961847,0.000011488977,0.000025733363,0.00010390107,0.0000212524],"domain_scores_gemma":[0.9997117,0.00011684746,0.000023527033,0.000080787344,0.00005927355,0.000007969965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030560783,0.0003190378,0.00034631617,0.0006872591,0.00016432235,0.0006578263,0.00036669022,0.00035917858,0.0018322355],"category_scores_gemma":[0.001233113,0.00010703576,0.00023461269,0.00082937855,0.0005159584,0.0009077127,0.0004001359,0.00047315066,0.0005425148],"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":[0.0002642673,0.00009740578,0.00071812555,0.00020988654,0.000024252318,0.0002867853,0.00018885556,0.18206212,0.11521358,0.17241174,0.0030390911,0.5254839],"study_design_scores_gemma":[0.0000086231485,0.000051045048,0.0002812669,0.000014799231,0.000005046202,0.0002588398,0.000022844897,0.9321506,0.04860445,0.0132377185,0.0053500594,0.0000146623715],"about_ca_topic_score_codex":0.00049292465,"about_ca_topic_score_gemma":0.00026849538,"teacher_disagreement_score":0.0018322355,"about_ca_system_score_codex":0.00032607187,"about_ca_system_score_gemma":0.00019589816,"threshold_uncertainty_score":0.0061295033},"labels":[],"label_agreement":null},{"id":"W2150228548","doi":"10.1109/cwit.2013.6621583","title":"Using bit recycling to reduce Knuth's balanced codes redundancy","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Redundancy (engineering); Code word; Algorithm; Mathematics; Computer science; Arithmetic; Theoretical computer science; Decoding methods","score_opus":0.04865398646649421,"score_gpt":0.3100208142509679,"score_spread":0.2613668277844737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150228548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07154471,0.001196762,0.91739815,0.00049977645,0.00024031392,0.0002000169,0.0000986538,0.0011756453,0.0076459497],"genre_scores_gemma":[0.33049992,0.00093225355,0.6583738,0.0003683934,0.00013390242,0.0002300376,0.00024039696,0.00021001957,0.009011358],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885976,0.00021957995,0.00009870079,0.00010901847,0.0005933512,0.000119629265],"domain_scores_gemma":[0.99820304,0.0006419012,0.00013598494,0.00054670696,0.00043142991,0.00004089652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090609334,0.0008073955,0.000685316,0.0020863037,0.00096469605,0.00090522866,0.00086028397,0.0009739255,0.002132079],"category_scores_gemma":[0.0051084,0.00034183086,0.0005039201,0.0024264178,0.0011774583,0.0020702416,0.001461023,0.0010004848,0.0007909367],"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":[0.00076890556,0.00011410312,0.0009858345,0.00029750823,0.000080541,0.00058361265,0.00053048437,0.03928798,0.13269895,0.2749445,0.0046493243,0.54505825],"study_design_scores_gemma":[0.00020216664,0.0007579941,0.0008567637,0.00022695313,0.00015340607,0.0020449376,0.00017954977,0.35034865,0.40739617,0.18039207,0.05722117,0.00022010333],"about_ca_topic_score_codex":0.0006839513,"about_ca_topic_score_gemma":0.00080053625,"teacher_disagreement_score":0.002132079,"about_ca_system_score_codex":0.00072115,"about_ca_system_score_gemma":0.00092814205,"threshold_uncertainty_score":0.00713253},"labels":[],"label_agreement":null},{"id":"W2150418677","doi":"","title":"MAX-SAT 2012: ubcsat-irots","year":2012,"lang":"hu","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Software; Iterated function; Algorithm; Mathematics; Minor (academic); Computer science; Arithmetic; Programming language; Humanities","score_opus":0.027525107390001136,"score_gpt":0.26248943297407806,"score_spread":0.23496432558407693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150418677","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011578763,0.002711526,0.2234485,0.0050967773,0.008496451,0.0012515098,0.07663879,0.33704323,0.33373454],"genre_scores_gemma":[0.046186514,0.0010998083,0.31468222,0.003949167,0.0012359151,0.0015854018,0.29737842,0.1533197,0.18056288],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99371064,0.0013019183,0.00034950033,0.0010267933,0.0025612237,0.0010500193],"domain_scores_gemma":[0.9946367,0.0010549263,0.00011747994,0.0014129876,0.0021385485,0.0006393252],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006068533,0.0036805926,0.0030811953,0.0027012907,0.002211899,0.0059984275,0.0076466915,0.0030305292,0.31056854],"category_scores_gemma":[0.012368175,0.0020174936,0.003551309,0.0061815106,0.0009834578,0.005251986,0.0043878388,0.0067089424,0.22910044],"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":[0.00069259835,0.00018550409,0.00016921326,0.0002493537,0.000040646173,0.000064045315,0.000051107265,0.0051451656,0.0012953831,0.013287315,0.9189551,0.059864487],"study_design_scores_gemma":[0.00096333184,0.00025754294,0.0008301925,0.00016584179,0.000036378668,0.0002042959,0.000071691706,0.06242836,0.0073307953,0.027346062,0.90023494,0.00013053956],"about_ca_topic_score_codex":0.00948243,"about_ca_topic_score_gemma":0.014342274,"teacher_disagreement_score":0.31056854,"about_ca_system_score_codex":0.0045161764,"about_ca_system_score_gemma":0.0047429055,"threshold_uncertainty_score":0.98339033},"labels":[],"label_agreement":null},{"id":"W2150574820","doi":"10.1093/comjnl/bxt070","title":"Strongly Universal String Hashing is Fast","year":2013,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hash function; Computer science; Parallel computing; Byte; Dynamic perfect hashing; String (physics); Universal hashing; Theoretical computer science; Arithmetic; Double hashing; Hash table; Mathematics; Programming language","score_opus":0.013136950572244179,"score_gpt":0.21302345001104855,"score_spread":0.19988649943880438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150574820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14755422,0.0025410156,0.8121847,0.0015675727,0.00040002444,0.00022231425,0.00043400223,0.0065010376,0.028595122],"genre_scores_gemma":[0.8498017,0.001089434,0.13677368,0.001079312,0.0005077657,0.00031679493,0.00055372977,0.001039667,0.0088378405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965251,0.0006539154,0.0002238329,0.0006121811,0.0014755717,0.00050940324],"domain_scores_gemma":[0.98594713,0.0056715556,0.0009324611,0.0049920827,0.0021304935,0.0003261539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031299905,0.00076758536,0.0011438074,0.0013354657,0.0014819045,0.0019467727,0.0012917091,0.0012351872,0.0053973617],"category_scores_gemma":[0.015685292,0.00091676775,0.0010413512,0.0016578994,0.0031518391,0.008359399,0.0053479997,0.0020484691,0.0022128324],"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":[0.0011053624,0.00020537675,0.0043799602,0.0007962561,0.00012380931,0.00037551994,0.00081122445,0.030703953,0.038658287,0.59244144,0.016335545,0.31406322],"study_design_scores_gemma":[0.0001555557,0.000692635,0.0017212529,0.00020237928,0.00017078035,0.0014419325,0.00026351196,0.19540614,0.09258739,0.6660937,0.04107594,0.00018873488],"about_ca_topic_score_codex":0.00041238792,"about_ca_topic_score_gemma":0.0003470936,"teacher_disagreement_score":0.0053973617,"about_ca_system_score_codex":0.0009177064,"about_ca_system_score_gemma":0.0014238803,"threshold_uncertainty_score":0.018055916},"labels":[],"label_agreement":null},{"id":"W2151087881","doi":"10.1109/vtcf.2006.366","title":"Random Binning and Turbo Source Coding for Lossless Compression of Memoryless Sources","year":2006,"lang":"en","type":"article","venue":"IEEE Vehicular Technology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Turbo code; Lossless compression; Variable-length code; Algorithm; Theoretical computer science; Context-adaptive binary arithmetic coding; Entropy encoding; Data compression; Source code; Distributed source coding; Tunstall coding; Decoding methods","score_opus":0.012099935635383419,"score_gpt":0.2300457274370346,"score_spread":0.2179457918016512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151087881","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028591596,0.00045248072,0.96901727,0.00014607391,0.000044386332,0.00002913693,0.000032327272,0.0002579874,0.0014287054],"genre_scores_gemma":[0.64975,0.0009306878,0.3454676,0.00019974977,0.00006553538,0.00009311952,0.00013772649,0.000103282706,0.0032524075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996276,0.00009406817,0.000017133229,0.000030262818,0.00020522586,0.000025747166],"domain_scores_gemma":[0.99894327,0.00048343846,0.00014449815,0.00015457538,0.00023524457,0.00003910209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006956417,0.00042835643,0.00042540743,0.0005563879,0.00021042513,0.0004556628,0.00076198194,0.00063556124,0.0010615294],"category_scores_gemma":[0.0031520233,0.00020337557,0.00023280775,0.0007774464,0.00059529155,0.0012579652,0.0005831114,0.0006479007,0.00037515094],"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":[0.00042372718,0.00005876766,0.0006500463,0.00023185852,0.000050518076,0.00026638442,0.000108209795,0.6679781,0.059564713,0.14482275,0.0011780105,0.124666885],"study_design_scores_gemma":[0.000014813051,0.00005742444,0.000101054735,0.000012785721,0.000008979251,0.000091417925,0.0000060930493,0.97214365,0.015952885,0.010788659,0.0008050795,0.00001728325],"about_ca_topic_score_codex":0.00059903006,"about_ca_topic_score_gemma":0.00075579225,"teacher_disagreement_score":0.0010615294,"about_ca_system_score_codex":0.00036695512,"about_ca_system_score_gemma":0.0005289365,"threshold_uncertainty_score":0.0036789775},"labels":[],"label_agreement":null},{"id":"W2151422907","doi":"10.1145/1562090.1562094","title":"Finding optimal parameters for edit distance based sequence classification is NP-hard","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Edit distance; Parametric statistics; Sequence (biology); Computer science; Measure (data warehouse); Matching (statistics); Heuristic; Data mining; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics","score_opus":0.0852972519177814,"score_gpt":0.31378736920573264,"score_spread":0.22849011728795124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151422907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10722262,0.0019307139,0.8782236,0.0036207098,0.000121870544,0.00035861955,0.0014238446,0.0025198504,0.0045782095],"genre_scores_gemma":[0.39458668,0.0009182032,0.59708446,0.00056240894,0.00020062583,0.0009944125,0.0024539148,0.0005545663,0.0026447065],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964139,0.0012033351,0.00045505364,0.0009642553,0.0006782847,0.00028524967],"domain_scores_gemma":[0.95101136,0.044126756,0.0013401338,0.0016989368,0.0013989201,0.0004239451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041113095,0.0016579609,0.0032902886,0.0018127157,0.0009097145,0.003239007,0.002869447,0.004040917,0.0035579298],"category_scores_gemma":[0.0326412,0.001096237,0.0011648856,0.0026746388,0.001597329,0.007884949,0.0017682103,0.0039208154,0.001401236],"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":[0.0005796689,0.00060277694,0.00311168,0.0008003318,0.00017018223,0.00018982918,0.00036320827,0.50936157,0.006031398,0.016284784,0.014854228,0.44765034],"study_design_scores_gemma":[0.00013957891,0.00020287686,0.00059168995,0.000059518232,0.000060359933,0.0003201905,0.0002823608,0.8743361,0.0036706575,0.11815049,0.00213075,0.00005543526],"about_ca_topic_score_codex":0.0016344119,"about_ca_topic_score_gemma":0.0016917201,"teacher_disagreement_score":0.0041113095,"about_ca_system_score_codex":0.0018306561,"about_ca_system_score_gemma":0.00211681,"threshold_uncertainty_score":0.02174294},"labels":[],"label_agreement":null},{"id":"W2151634152","doi":"10.1109/wescan.1993.270518","title":"Real-time dynamic arithmetic coding for low bit-rate channels","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Manitoba","funders":"","keywords":"Huffman coding; Arithmetic coding; Computer science; Arithmetic; Variable-length code; Data compression; Context-adaptive binary arithmetic coding; Coding (social sciences); Algorithm; Decoding methods; Mathematics; Statistics","score_opus":0.01789781705569582,"score_gpt":0.24332962810161246,"score_spread":0.22543181104591664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151634152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027716689,0.00045469843,0.9601685,0.00024747095,0.00020605691,0.00012715119,0.000070801005,0.0020817113,0.008926882],"genre_scores_gemma":[0.40608463,0.00063834246,0.5767065,0.00019356332,0.0002759174,0.00021989393,0.00030252663,0.00028627983,0.015292327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994506,0.00009729502,0.000034523087,0.000050967494,0.00031104402,0.000055487966],"domain_scores_gemma":[0.9987888,0.0005008316,0.00010456947,0.0002310893,0.00033802344,0.000036712136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004654881,0.0005880945,0.00025142927,0.0007419763,0.0005038915,0.0010209467,0.0010068633,0.00046048537,0.0060477746],"category_scores_gemma":[0.0022402562,0.00016101878,0.00021971067,0.0007508887,0.00073326816,0.0012844849,0.0007378268,0.00079200155,0.001640975],"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":[0.0006223117,0.00012875674,0.0010993541,0.00033402102,0.00004361639,0.0005445894,0.00036673102,0.033643346,0.20512146,0.105422415,0.007955344,0.64471805],"study_design_scores_gemma":[0.00011062178,0.00047254318,0.00065680244,0.00011826227,0.000087165216,0.0014291387,0.00009023626,0.50834787,0.40879613,0.022340741,0.057439413,0.000111137815],"about_ca_topic_score_codex":0.0012579969,"about_ca_topic_score_gemma":0.0015228,"teacher_disagreement_score":0.0060477746,"about_ca_system_score_codex":0.0005100498,"about_ca_system_score_gemma":0.0005047026,"threshold_uncertainty_score":0.020231843},"labels":[],"label_agreement":null},{"id":"W2151743318","doi":"10.1093/bioinformatics/btn173","title":"Optimal pooling for genome re-sequencing with ultra-high-throughput short-read technologies","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"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; BC Cancer Agency","funders":"","keywords":"Pooling; Multiplex; DNA sequencing; Computer science; Bacterial artificial chromosome; Genome; Deep sequencing; Reference genome; Computational biology; Throughput; Algorithm; Biology; Genetics; Artificial intelligence; Gene; Telecommunications","score_opus":0.037241946335152605,"score_gpt":0.24526871172737083,"score_spread":0.20802676539221823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151743318","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01208224,0.00020116135,0.9863891,0.00007175002,0.000018316814,0.00008837338,0.000044712946,0.0007109549,0.00039334391],"genre_scores_gemma":[0.07267782,0.00016540506,0.92540044,0.00008625695,0.000021851853,0.00033501413,0.00034872352,0.0002014584,0.00076302694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587446,0.0020353931,0.00021517058,0.0007571304,0.0009308836,0.00018702904],"domain_scores_gemma":[0.9914349,0.0048657227,0.00067734625,0.002193631,0.00064397365,0.00018445405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062372587,0.0013562564,0.0018920233,0.0013012821,0.00069497275,0.0013493784,0.0025157556,0.0010401747,0.002732957],"category_scores_gemma":[0.011059752,0.00096484536,0.0013331432,0.0020277933,0.0011389002,0.002832426,0.0017105653,0.0013670335,0.0010708852],"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":[0.0010770735,0.00045416376,0.0022308843,0.00053220795,0.00019496852,0.0002585087,0.00026299537,0.34022793,0.10925559,0.03190239,0.002647197,0.51095605],"study_design_scores_gemma":[0.00008495102,0.00030162075,0.00097062276,0.000026256908,0.000064750224,0.00013100801,0.00007277841,0.8729265,0.074812695,0.04629155,0.004276923,0.000040317747],"about_ca_topic_score_codex":0.0011312901,"about_ca_topic_score_gemma":0.0017904292,"teacher_disagreement_score":0.0062372587,"about_ca_system_score_codex":0.0015816672,"about_ca_system_score_gemma":0.0012999338,"threshold_uncertainty_score":0.032986164},"labels":[],"label_agreement":null},{"id":"W2152220072","doi":"10.1109/cwit.2011.5872127","title":"Credit-based variable-to-variable length coding: Key concepts and preliminary redundancy analysis","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Variable-length code; Redundancy (engineering); Bounded function; Coding (social sciences); Computer science; Tunstall coding; Shannon–Fano coding; Source code; Algorithm; Binary number; Theoretical computer science; Alphabet; Discrete mathematics; Mathematics; Arithmetic; Statistics; Decoding methods; Programming language; Operating system; Linguistics","score_opus":0.026053914501809397,"score_gpt":0.2554649111489464,"score_spread":0.22941099664713704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152220072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010257583,0.001906178,0.9792403,0.00054223865,0.00015813835,0.00009904014,0.00017358165,0.00022386466,0.007399179],"genre_scores_gemma":[0.47044528,0.004602241,0.5128588,0.00063907186,0.00070484326,0.0005415135,0.0006866366,0.00017334984,0.009348309],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986077,0.00033771485,0.000074316085,0.00019741115,0.0006264118,0.00015656815],"domain_scores_gemma":[0.99678814,0.0014469338,0.0004160288,0.00050885195,0.0007418927,0.00009812668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013620984,0.00096686755,0.00061931164,0.0018265862,0.00068816653,0.0013912016,0.0018387756,0.0011119763,0.0030406064],"category_scores_gemma":[0.006698699,0.0004107532,0.0005587169,0.0023613821,0.0020664139,0.0025468199,0.0016132216,0.002108904,0.0007696904],"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":[0.00025628923,0.00006708525,0.00069939246,0.0003326535,0.000028277162,0.0002871478,0.00031618206,0.09094878,0.021803375,0.72417855,0.006250917,0.15483138],"study_design_scores_gemma":[0.000040643503,0.00022148473,0.00046338336,0.00015478858,0.000027800801,0.0007009507,0.00007492199,0.7484902,0.017810442,0.21332005,0.0185764,0.00011892694],"about_ca_topic_score_codex":0.0029384505,"about_ca_topic_score_gemma":0.0016763821,"teacher_disagreement_score":0.0030406064,"about_ca_system_score_codex":0.0016911036,"about_ca_system_score_gemma":0.001688138,"threshold_uncertainty_score":0.012269855},"labels":[],"label_agreement":null},{"id":"W2152844281","doi":"10.4204/eptcs.170.6","title":"Simple Balanced Binary Search Trees","year":2014,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Ternary search tree; Weight-balanced tree; Binary search tree; Simple (philosophy); Binary number; Optimal binary search tree; Implementation; Basis (linear algebra); Code (set theory)","score_opus":0.005834959949034589,"score_gpt":0.24722204912693854,"score_spread":0.24138708917790394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152844281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025943164,0.0008943925,0.92530715,0.0005808569,0.0002892827,0.00015443984,0.0009847742,0.004279096,0.04156679],"genre_scores_gemma":[0.27566382,0.0008157039,0.6888469,0.00055786344,0.00016147696,0.00037769845,0.0018250413,0.0012334817,0.030517932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991334,0.00016163892,0.00008307106,0.00012855715,0.00035089318,0.00014256344],"domain_scores_gemma":[0.99889344,0.00033063898,0.000063144245,0.00030075663,0.00035194558,0.000060132974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060521334,0.00040172337,0.00052841264,0.0008764204,0.00084858155,0.0020399943,0.0013347416,0.0010624075,0.014199413],"category_scores_gemma":[0.004988692,0.0003267596,0.00041690364,0.0015810883,0.0008296718,0.003799376,0.0015681237,0.0007472859,0.008353084],"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":[0.00037821004,0.00007644947,0.0007874944,0.0003329982,0.000027447944,0.00017639737,0.0003207423,0.015496267,0.015819917,0.58263683,0.019215148,0.364732],"study_design_scores_gemma":[0.00011458337,0.00017127061,0.00051246537,0.0001821371,0.000050587194,0.0006651176,0.00019771587,0.17733449,0.023508424,0.654385,0.14281057,0.00006768385],"about_ca_topic_score_codex":0.00074015715,"about_ca_topic_score_gemma":0.0012096836,"teacher_disagreement_score":0.014199413,"about_ca_system_score_codex":0.00052788405,"about_ca_system_score_gemma":0.00095707364,"threshold_uncertainty_score":0.047501743},"labels":[],"label_agreement":null},{"id":"W2153294698","doi":"10.1145/2344422.2344432","title":"Succinct ordinal trees based on tree covering","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"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; Dalhousie University","funders":"","keywords":"Tree traversal; Unary operation; Tree (set theory); Mathematics; Combinatorics; Sequence (biology); Set (abstract data type); Parenthesis; Representation (politics); Discrete mathematics; Computer science; Theoretical computer science; Algorithm","score_opus":0.0244141420401886,"score_gpt":0.26327157157595255,"score_spread":0.23885742953576394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153294698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036208864,0.00055011566,0.95406806,0.000328994,0.00011951329,0.00009840548,0.0013636064,0.0014023053,0.0058602835],"genre_scores_gemma":[0.388459,0.0010303792,0.5974242,0.0003354409,0.00012217194,0.0003386604,0.0039171283,0.00046382233,0.007909136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989135,0.00027140047,0.00011606244,0.00014059315,0.00044663966,0.000111682384],"domain_scores_gemma":[0.99790335,0.0007623777,0.00023321602,0.0006459876,0.00036700285,0.000088152694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067208376,0.00044714278,0.0006805939,0.0016396185,0.00054268545,0.0018287706,0.0009289016,0.00069076696,0.0053788936],"category_scores_gemma":[0.005915537,0.00033310978,0.0006181994,0.002873681,0.0008284438,0.004483806,0.0018582374,0.0012921694,0.0015407857],"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":[0.0005772926,0.00010325283,0.001361683,0.00039405155,0.000033359694,0.0003852985,0.0008800855,0.07463483,0.018764341,0.51330465,0.011795578,0.3777656],"study_design_scores_gemma":[0.00008659563,0.00024656559,0.0008187705,0.0002505005,0.000057389425,0.000786528,0.00037669385,0.4260217,0.024405776,0.48676205,0.060079046,0.00010833873],"about_ca_topic_score_codex":0.0009066323,"about_ca_topic_score_gemma":0.0012369308,"teacher_disagreement_score":0.0053788936,"about_ca_system_score_codex":0.00073901634,"about_ca_system_score_gemma":0.0006847558,"threshold_uncertainty_score":0.017994225},"labels":[],"label_agreement":null},{"id":"W2153447124","doi":"","title":"Faster Algorithm for Designing Optimal Prefix-Free Codes with Unequal Letter Costs","year":2006,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Prefix; Prefix code; Alphabet; Encoding (memory); Algorithm; Time complexity; Integer (computer science); Function (biology); Generalization; Binary logarithm; Binary number; Mathematics; Computer science; Discrete mathematics; Property (philosophy); Computational complexity theory; Combinatorics; Arithmetic; Block code; Decoding methods; Linear code","score_opus":0.012649683804712356,"score_gpt":0.2293029668300164,"score_spread":0.21665328302530407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153447124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010350945,0.00016440959,0.9875294,0.00012588421,0.00003776303,0.00007667553,0.000055986486,0.0004435881,0.0012153579],"genre_scores_gemma":[0.077119246,0.000204472,0.92053497,0.00010123942,0.000052104642,0.00029662563,0.00025500642,0.000097595075,0.0013387438],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986582,0.0003331569,0.000132838,0.00021611391,0.00052684656,0.00013285447],"domain_scores_gemma":[0.99703264,0.0017124399,0.00027269585,0.0005254671,0.00038199133,0.00007478032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011201474,0.0009059065,0.0011612627,0.0012429417,0.00053045363,0.0010816797,0.0010354941,0.0013156997,0.0034263395],"category_scores_gemma":[0.0060604364,0.0005060201,0.00083150325,0.0015655705,0.0006359169,0.0017075943,0.0013699105,0.0011949746,0.0013579302],"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":[0.0003543816,0.00021595698,0.00073122414,0.0005368197,0.00010466109,0.00024000269,0.0003331621,0.1990332,0.03864504,0.08496503,0.0055546504,0.6692858],"study_design_scores_gemma":[0.00022870887,0.00030832904,0.0002394612,0.00006236789,0.00005399839,0.0004533678,0.00007485368,0.881032,0.029361581,0.07846546,0.009662862,0.000056911143],"about_ca_topic_score_codex":0.0006543317,"about_ca_topic_score_gemma":0.0008451263,"teacher_disagreement_score":0.0034263395,"about_ca_system_score_codex":0.00061259896,"about_ca_system_score_gemma":0.0018405977,"threshold_uncertainty_score":0.011462271},"labels":[],"label_agreement":null},{"id":"W2153541768","doi":"10.1002/rsa.10103","title":"Random suffix search trees","year":2003,"lang":"en","type":"article","venue":"Random Structures and Algorithms","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Combinatorics; Mathematics; Random binary tree; Binary search tree; Self-balancing binary search tree; Independent and identically distributed random variables; Tree (set theory); Optimal binary search tree; B-tree; Suffix; Sequence (biology); Suffix tree; Binary number; Discrete mathematics; Binary tree; K-ary tree; Random variable; Statistics; Tree structure; Arithmetic","score_opus":0.013034325146850363,"score_gpt":0.2517538110391782,"score_spread":0.23871948589232786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153541768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20529664,0.0027299784,0.76095575,0.0014304752,0.00031194475,0.00033229726,0.0027231006,0.0031484638,0.023071337],"genre_scores_gemma":[0.6846106,0.0008512412,0.29426375,0.0006079907,0.00018398059,0.0003866963,0.004218103,0.00045911467,0.014418456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899715,0.0002912404,0.000090855065,0.00019552528,0.00029819223,0.00012697943],"domain_scores_gemma":[0.9964994,0.0015639181,0.00032105818,0.00086207874,0.00058650173,0.00016701882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010005526,0.00026529023,0.0006632595,0.0012319637,0.00073016196,0.0010866164,0.0008955747,0.00088174397,0.006615023],"category_scores_gemma":[0.008745578,0.00031821243,0.00042482713,0.0019528666,0.00077790994,0.0025630447,0.0015698388,0.00064812024,0.0022133011],"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":[0.0010509433,0.00020260223,0.0050308253,0.00059466244,0.0001339564,0.00068319886,0.00045966503,0.15983358,0.02495629,0.4434137,0.03723926,0.32640126],"study_design_scores_gemma":[0.00016157248,0.00018918002,0.0009858842,0.00008034686,0.000057945344,0.0011659013,0.00013486682,0.6566532,0.011753521,0.29972243,0.029052213,0.00004303562],"about_ca_topic_score_codex":0.0004735362,"about_ca_topic_score_gemma":0.0008467831,"teacher_disagreement_score":0.006615023,"about_ca_system_score_codex":0.0006144251,"about_ca_system_score_gemma":0.00074402295,"threshold_uncertainty_score":0.022129416},"labels":[],"label_agreement":null},{"id":"W2153611381","doi":"10.1007/11880561_11","title":"Inverted Files Versus Suffix Arrays for Locating Patterns in Primary Memory","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Compressed suffix array; Suffix array; Inverted index; Suffix; String searching algorithm; Pattern matching; Data structure; Word (group theory); Matching (statistics); Algorithm; Information retrieval; Artificial intelligence; Mathematics; Programming language; Search engine indexing","score_opus":0.020712010630244544,"score_gpt":0.24183024024776845,"score_spread":0.2211182296175239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153611381","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.108136386,0.0055919955,0.841226,0.000924339,0.001137426,0.00033849743,0.0028118854,0.016996041,0.022837473],"genre_scores_gemma":[0.22890525,0.002713202,0.7393513,0.00039014776,0.000440872,0.0003275753,0.0036296942,0.0018664324,0.022375638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991398,0.00012186362,0.000121101526,0.00017006006,0.00032785372,0.00011926655],"domain_scores_gemma":[0.9944377,0.002208675,0.00030393153,0.0019508103,0.00094511703,0.00015365735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006862879,0.0010214619,0.0012577729,0.003136997,0.00094230176,0.0035064332,0.0027805732,0.0017227107,0.019460548],"category_scores_gemma":[0.007867724,0.00063285575,0.00060164754,0.006563183,0.00089989125,0.007649699,0.0017415681,0.001035362,0.0070908563],"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":[0.0017833227,0.00011909033,0.0016270292,0.000780013,0.000056774712,0.00041488867,0.0004470871,0.0059150564,0.059565954,0.041940033,0.02125981,0.86609095],"study_design_scores_gemma":[0.0004248308,0.0022802674,0.002217015,0.0006734359,0.0005136915,0.006489447,0.0023238452,0.21117793,0.46932715,0.1628086,0.14147857,0.00028518992],"about_ca_topic_score_codex":0.00087247515,"about_ca_topic_score_gemma":0.0015534688,"teacher_disagreement_score":0.019460548,"about_ca_system_score_codex":0.0007282034,"about_ca_system_score_gemma":0.0008296307,"threshold_uncertainty_score":0.06510204},"labels":[],"label_agreement":null},{"id":"W2154942876","doi":"10.1109/sfcs.1991.185387","title":"Size-depth tradeoffs for algebraic formulae","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"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 Calgary","funders":"","keywords":"Algebraic number; Omega; Mathematics; Upper and lower bounds; Combinatorics; Discrete mathematics; Physics; Mathematical analysis","score_opus":0.03212410337113941,"score_gpt":0.24128654951280867,"score_spread":0.20916244614166926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154942876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3220062,0.006104162,0.60292596,0.011391683,0.00035258674,0.0003389151,0.0008316739,0.0035205146,0.05252836],"genre_scores_gemma":[0.71806496,0.0036234062,0.2649605,0.0016228203,0.0006687396,0.00034919824,0.00076259,0.00089871895,0.0090490775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944719,0.0012869464,0.00044512167,0.00065555,0.0024703087,0.0006701535],"domain_scores_gemma":[0.95032585,0.040297385,0.0025504448,0.0043682954,0.0018478736,0.0006102192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003507531,0.0008824298,0.0008482262,0.0019324061,0.0011726851,0.0041618505,0.001991664,0.0018388834,0.00930894],"category_scores_gemma":[0.04009926,0.0013280944,0.0017613793,0.002126708,0.0027512084,0.017285736,0.0045653377,0.0033672475,0.00089456874],"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":[0.0015770631,0.0002753783,0.004088598,0.00096900616,0.00012031677,0.0005048294,0.00089331757,0.060053937,0.052647896,0.6252785,0.01164772,0.2419434],"study_design_scores_gemma":[0.00019666835,0.00030832764,0.0010384629,0.00015021488,0.00018249298,0.00093046785,0.00025817455,0.22242606,0.036657546,0.7265082,0.011257894,0.000085416],"about_ca_topic_score_codex":0.0008593869,"about_ca_topic_score_gemma":0.001932591,"teacher_disagreement_score":0.00930894,"about_ca_system_score_codex":0.003001909,"about_ca_system_score_gemma":0.0016170648,"threshold_uncertainty_score":0.03114146},"labels":[],"label_agreement":null},{"id":"W2154954197","doi":"10.1109/infcom.1993.253405","title":"Parallel searching techniques for routing table lookup","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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; Alphanumeric; Lookup table; Implementation; Routing table; Robustness (evolution); Table (database); Routing (electronic design automation); Parallel computing; Algorithm; Data mining; Embedded system; Programming language; Routing protocol","score_opus":0.037071348825723854,"score_gpt":0.2757145908246598,"score_spread":0.23864324199893597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154954197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015871905,0.0045113736,0.9766367,0.00016743317,0.00026220884,0.00012492324,0.00014514863,0.0034791646,0.013085884],"genre_scores_gemma":[0.031176243,0.0054406025,0.94787174,0.00021746174,0.0002612093,0.0002942145,0.00073386374,0.0005588076,0.013445833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990361,0.00013276807,0.000079525154,0.0001677899,0.00051336945,0.00007041816],"domain_scores_gemma":[0.99908435,0.00029907352,0.000064977925,0.00030154598,0.00023138928,0.000018605804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000583603,0.0011043478,0.001053507,0.002491143,0.0009440415,0.0016793014,0.0023813331,0.00089016446,0.016603172],"category_scores_gemma":[0.0030639514,0.00062363164,0.00070027716,0.004533499,0.0007937888,0.0033257313,0.0014767218,0.0011679884,0.009211976],"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":[0.0001029059,0.0000668536,0.00019290717,0.0007443588,0.000052426334,0.00018188142,0.00012859485,0.020317523,0.016179131,0.12126104,0.02221992,0.8185525],"study_design_scores_gemma":[0.00018123386,0.00024930222,0.00049319066,0.00037764185,0.00016493908,0.004086081,0.00015400542,0.3037357,0.043919183,0.23724118,0.40925944,0.00013798666],"about_ca_topic_score_codex":0.0014039202,"about_ca_topic_score_gemma":0.0015458342,"teacher_disagreement_score":0.016603172,"about_ca_system_score_codex":0.00075306604,"about_ca_system_score_gemma":0.0010128991,"threshold_uncertainty_score":0.055543125},"labels":[],"label_agreement":null},{"id":"W2155315813","doi":"10.1109/pacrim.2007.4313247","title":"On-Chip Hardware Support for Similarity Measures","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Victoria","funders":"","keywords":"Computer science; Field-programmable gate array; Reuse; Software; Embedded system; Computer architecture; Computer hardware; Hardware architecture; System on a chip; Reconfigurable computing; Operating system; Engineering","score_opus":0.03850810946134257,"score_gpt":0.2911818596694841,"score_spread":0.25267375020814153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155315813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3287263,0.0012701105,0.63014275,0.0005685586,0.00050296326,0.00032426644,0.0004728148,0.018010477,0.019981861],"genre_scores_gemma":[0.86997086,0.00022237227,0.12332745,0.0003836542,0.00006799988,0.0001294649,0.0004870137,0.00020316782,0.005207928],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995883,0.00007353173,0.00003383303,0.000075437754,0.0001399879,0.00008883587],"domain_scores_gemma":[0.99874794,0.00045017648,0.00011895618,0.00032648328,0.00030583926,0.000050611467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029262056,0.00063546095,0.00044415717,0.00064505445,0.00021061179,0.0009346873,0.0019046067,0.0004556283,0.008964634],"category_scores_gemma":[0.0016584047,0.00026548962,0.00032102282,0.0005697743,0.00023794454,0.00086655095,0.00041565223,0.0005205398,0.0017408369],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014372969,0.0005791616,0.008505586,0.0010701276,0.00031901879,0.000867541,0.00021374444,0.041156426,0.36231712,0.016758284,0.018997544,0.5477782],"study_design_scores_gemma":[0.0004994235,0.0027280746,0.009295554,0.00012788607,0.0003492966,0.0014964711,0.00014053455,0.45381838,0.47774142,0.005516141,0.048162367,0.00012447976],"about_ca_topic_score_codex":0.0012471041,"about_ca_topic_score_gemma":0.0014380402,"teacher_disagreement_score":0.008964634,"about_ca_system_score_codex":0.00044206192,"about_ca_system_score_gemma":0.00058917346,"threshold_uncertainty_score":0.02998966},"labels":[],"label_agreement":null},{"id":"W2155322527","doi":"10.1109/arrays.1988.18046","title":"New architectures for systolic hashing","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Windsor","funders":"","keywords":"Hash function; Sorting; Computer science; Hash table; Dynamic perfect hashing; Double hashing; Constant (computer programming); Universal hashing; Theoretical computer science; Parallel computing; Linear hashing; Process (computing); Algorithm; Programming language","score_opus":0.017262238466690522,"score_gpt":0.2539850074961375,"score_spread":0.23672276902944697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155322527","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010288964,0.0018746629,0.96686995,0.0003911967,0.0007289218,0.00010926425,0.00015253123,0.0032518187,0.016332682],"genre_scores_gemma":[0.14390437,0.002265673,0.83267355,0.00047393696,0.0006950897,0.0003607524,0.0007905709,0.00025574482,0.018580422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994252,0.000074322685,0.000059190934,0.00007737385,0.00029066694,0.00007327334],"domain_scores_gemma":[0.9990569,0.00018857568,0.00006785584,0.00022720963,0.00039630898,0.00006310209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009257443,0.00060562586,0.00054343446,0.0010408727,0.00070669915,0.0017496579,0.001875781,0.0007467463,0.009167894],"category_scores_gemma":[0.0018550238,0.00048087377,0.0005750308,0.0016438641,0.00080147467,0.0029086042,0.0016027411,0.0011779475,0.0032201249],"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":[0.0003730657,0.00013433816,0.0008047275,0.000493501,0.000060751434,0.00027808372,0.00027160306,0.026982678,0.03781587,0.33247435,0.023669222,0.5766419],"study_design_scores_gemma":[0.00033344573,0.0010422457,0.00086132664,0.00019954047,0.00012266936,0.0015822126,0.00022728097,0.37380484,0.055463996,0.28333807,0.28287235,0.00015205711],"about_ca_topic_score_codex":0.00050147274,"about_ca_topic_score_gemma":0.0010798059,"teacher_disagreement_score":0.009167894,"about_ca_system_score_codex":0.00085878436,"about_ca_system_score_gemma":0.0010980117,"threshold_uncertainty_score":0.03066963},"labels":[],"label_agreement":null},{"id":"W2155575074","doi":"10.1007/11551188_1","title":"Enhancing Trie-Based Syntactic Pattern Recognition Using AI Heuristic Search Strategies","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Trie; Beam search; Computer science; Benchmark (surveying); Pruning; Heuristic; A priori and a posteriori; String (physics); Levenshtein distance; Algorithm; Quadrilateral; Search tree; Search algorithm; Tree (set theory); Artificial intelligence; Combinatorics; Mathematics; Finite element method; Data structure; Physics","score_opus":0.03541699996764469,"score_gpt":0.28766361145974956,"score_spread":0.25224661149210487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155575074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041300856,0.00031810233,0.94354016,0.0001979693,0.000099709876,0.00015890283,0.00019848766,0.0054578283,0.008727983],"genre_scores_gemma":[0.27806014,0.00036098194,0.71180135,0.00033231973,0.00007259296,0.00021212676,0.00092234573,0.00063982856,0.0075983084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994728,0.00010571959,0.000051211417,0.00011556464,0.0001983986,0.000056360932],"domain_scores_gemma":[0.9980452,0.0009703135,0.00009528345,0.0002791614,0.00055908284,0.000050968152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061435456,0.00094348117,0.00123198,0.002054856,0.000468724,0.0014716604,0.0015482154,0.0012073807,0.008513106],"category_scores_gemma":[0.0034890831,0.0004358688,0.00080473704,0.0018237949,0.0005126777,0.0023648818,0.0009162381,0.0010917531,0.0033053006],"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":[0.00030073148,0.00029926465,0.00086374424,0.0002680463,0.00009946376,0.00028273696,0.0001898905,0.05900735,0.0485196,0.011070692,0.006942651,0.87215585],"study_design_scores_gemma":[0.000035261062,0.00007432922,0.00023874796,0.00001588542,0.000049787806,0.00022600818,0.00010178073,0.9709533,0.017528493,0.008303205,0.0024536643,0.000019502948],"about_ca_topic_score_codex":0.0027758083,"about_ca_topic_score_gemma":0.00447392,"teacher_disagreement_score":0.008513106,"about_ca_system_score_codex":0.00044133136,"about_ca_system_score_gemma":0.0009602742,"threshold_uncertainty_score":0.028479159},"labels":[],"label_agreement":null},{"id":"W2155992938","doi":"10.1007/s00453-014-9881-9","title":"Linear-Space Data Structures for Range Minority Query in Arrays","year":2014,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Waterloo","funders":"","keywords":"Range query (database); Data structure; Query optimization; Range (aeronautics); Preprocessor; Linear space; Mathematics; Computer science; Combinatorics; Algorithm; Web search query; Sargable; Data mining; Search engine; Information retrieval","score_opus":0.033027681919376356,"score_gpt":0.28630230316188354,"score_spread":0.2532746212425072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155992938","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08062349,0.0020440514,0.8972471,0.0030178314,0.00026270415,0.00026020056,0.0016965753,0.005407514,0.009440459],"genre_scores_gemma":[0.5140797,0.0008436466,0.46772826,0.0009982,0.00045076196,0.00069702615,0.003109513,0.0007810239,0.011311942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997917,0.00038174758,0.0002156008,0.000283744,0.00092780986,0.00027413142],"domain_scores_gemma":[0.99304515,0.002696515,0.00045577262,0.0027816459,0.0008187107,0.00020221827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015683225,0.0005507079,0.001077734,0.001524062,0.001384943,0.0029907764,0.0020034544,0.0010402278,0.009501752],"category_scores_gemma":[0.011150406,0.00036392783,0.0007159488,0.004328221,0.0014425342,0.007426495,0.0038358308,0.0021801672,0.002336496],"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":[0.0021523908,0.00062287785,0.0058691627,0.00061516365,0.00011373578,0.00015751184,0.0013725979,0.04484847,0.017542068,0.27985662,0.05213956,0.5947098],"study_design_scores_gemma":[0.00034570857,0.000471028,0.0012843431,0.00013313706,0.000114656454,0.00046231938,0.00091884023,0.40508163,0.038641896,0.5241842,0.028268823,0.00009330371],"about_ca_topic_score_codex":0.0015587631,"about_ca_topic_score_gemma":0.0023862112,"teacher_disagreement_score":0.009501752,"about_ca_system_score_codex":0.0014274959,"about_ca_system_score_gemma":0.0018044552,"threshold_uncertainty_score":0.03178656},"labels":[],"label_agreement":null},{"id":"W2156411090","doi":"10.1007/978-3-642-12476-1_3","title":"Fast Intersection Algorithms for Sorted Sequences","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Intersection (aeronautics); Algorithm; Theoretical computer science; Cartography","score_opus":0.02275534578046922,"score_gpt":0.2680858875064642,"score_spread":0.245330541725995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156411090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018157007,0.0020857698,0.95728093,0.00026551372,0.00029119875,0.00015040649,0.00060600834,0.005479395,0.015683811],"genre_scores_gemma":[0.09709387,0.0013891994,0.8817075,0.00014246457,0.00024590472,0.00034229227,0.0031823725,0.0013859692,0.014510553],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99708706,0.0003658022,0.00027911612,0.00046438878,0.0014511321,0.0003524867],"domain_scores_gemma":[0.99551374,0.0021125348,0.00020085432,0.0008927897,0.0011166147,0.00016357645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018746493,0.0018549769,0.0024628383,0.0048465137,0.0023587663,0.0050227484,0.0032203132,0.0013356863,0.025229122],"category_scores_gemma":[0.007605787,0.0014939137,0.0018881498,0.009672431,0.0014632159,0.010957509,0.0051899813,0.0037211129,0.007435435],"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":[0.0006044635,0.00014855542,0.00060317764,0.0004421287,0.000069276866,0.000057848672,0.00046950244,0.012510522,0.005338871,0.22231385,0.020263156,0.7371786],"study_design_scores_gemma":[0.00023273332,0.00028074684,0.0005321629,0.00025691377,0.00011023201,0.00044498275,0.0005639691,0.2262967,0.02631895,0.6828001,0.062052682,0.00010974982],"about_ca_topic_score_codex":0.0021947871,"about_ca_topic_score_gemma":0.0028177036,"teacher_disagreement_score":0.025229122,"about_ca_system_score_codex":0.0024257887,"about_ca_system_score_gemma":0.0026453815,"threshold_uncertainty_score":0.08439982},"labels":[],"label_agreement":null},{"id":"W2156695057","doi":"10.1109/rsp.2006.26","title":"Parameter-Specific FPGA Implementation of Edit-Distance Calculation","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of New Brunswick","funders":"","keywords":"Field-programmable gate array; Computer science; Leverage (statistics); Edit distance; Hardware acceleration; Computation; Acceleration; Task (project management); Set (abstract data type); Computer hardware; Computer engineering; Parallel computing; Embedded system; Algorithm; Artificial intelligence; Engineering; Programming language","score_opus":0.014720842887574026,"score_gpt":0.27309277470852455,"score_spread":0.25837193182095053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156695057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073558584,0.00040471324,0.881019,0.00019376917,0.00031303,0.00020851358,0.00036025562,0.015718078,0.028224085],"genre_scores_gemma":[0.63413805,0.00023681567,0.34880883,0.00019146074,0.00006666834,0.00020422254,0.0005926549,0.00028928794,0.015471918],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99982834,0.00002306213,0.000014708993,0.00003859772,0.0000615833,0.000033693024],"domain_scores_gemma":[0.9997286,0.00007324849,0.00001939569,0.00008757956,0.000077310804,0.000013818775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018244522,0.0004641524,0.00031182703,0.0005081083,0.00026035766,0.00072795333,0.0012442032,0.00035482278,0.013049421],"category_scores_gemma":[0.00070400833,0.00019148935,0.000200849,0.0003928081,0.00015947994,0.0005082846,0.0002739078,0.00040319952,0.0020890993],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007866135,0.00021633586,0.0023264408,0.00043970393,0.00014543229,0.00072167534,0.00030791922,0.042093422,0.17428176,0.028402664,0.02301262,0.7272653],"study_design_scores_gemma":[0.00031986934,0.0009205571,0.0027847784,0.00007312326,0.00013459471,0.0018661525,0.00015161811,0.43319166,0.45321378,0.009286373,0.09795127,0.000106324325],"about_ca_topic_score_codex":0.0012941301,"about_ca_topic_score_gemma":0.002678437,"teacher_disagreement_score":0.013049421,"about_ca_system_score_codex":0.00039696362,"about_ca_system_score_gemma":0.00032338532,"threshold_uncertainty_score":0.04365468},"labels":[],"label_agreement":null},{"id":"W2156871012","doi":"10.1109/isit.2001.935940","title":"YK data compression algorithms: complexity, implementation, and experimental results","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Computer science; Data compression; Algorithm; Compression (physics); Computation","score_opus":0.15610417135075697,"score_gpt":0.3598086612990565,"score_spread":0.2037044899482995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156871012","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57665765,0.005012076,0.38853896,0.0009920447,0.00024248606,0.0010026139,0.0017988046,0.011481736,0.0142736165],"genre_scores_gemma":[0.6001299,0.0019877588,0.38977942,0.00016950596,0.00009077838,0.0006773536,0.0035009335,0.00054118154,0.0031231435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630666,0.0006396426,0.000382147,0.00028165823,0.0020781104,0.00031178983],"domain_scores_gemma":[0.98951644,0.0060569104,0.00058272295,0.0014254354,0.002232718,0.00018576128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021800667,0.0013092809,0.00080561865,0.001786505,0.00083292945,0.0011624957,0.0017290645,0.0011516338,0.003747492],"category_scores_gemma":[0.0174049,0.00037815757,0.0003307639,0.003741629,0.0007829096,0.0037216365,0.001262568,0.0009251627,0.0012446797],"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":[0.0048460728,0.0028477674,0.005366726,0.0012152072,0.00024137877,0.0003552521,0.00042421147,0.1738627,0.08012089,0.012164258,0.016659588,0.70189595],"study_design_scores_gemma":[0.0007888368,0.0016330354,0.0034462858,0.00007069398,0.00013547204,0.0006740005,0.00029056155,0.7409282,0.2404317,0.006471747,0.0050108247,0.00011870579],"about_ca_topic_score_codex":0.005058112,"about_ca_topic_score_gemma":0.002846646,"teacher_disagreement_score":0.005058112,"about_ca_system_score_codex":0.0013615243,"about_ca_system_score_gemma":0.00111268,"threshold_uncertainty_score":0.012536585},"labels":[],"label_agreement":null},{"id":"W2157474903","doi":"10.1109/iembs.2006.260286","title":"Hardware Accelerator for Genomic Sequence Alignment","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"York University; University of Toronto","funders":"","keywords":"Smith–Waterman algorithm; Field-programmable gate array; Computer science; Parallel computing; Software; Sequence (biology); Hardware acceleration; Sequence alignment; Simple (philosophy); Function (biology); Algorithm; Computer hardware; Programming language; Biology","score_opus":0.03174105521429538,"score_gpt":0.26415973570604967,"score_spread":0.2324186804917543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157474903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07392087,0.0020607186,0.82255214,0.0008864529,0.0010695859,0.00044125805,0.002297516,0.030522762,0.066248715],"genre_scores_gemma":[0.30772725,0.0009798371,0.6291901,0.00072754436,0.00019113951,0.00060909713,0.0052261124,0.00056967395,0.054779265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997434,0.00003391181,0.000019393497,0.000047400496,0.000117942196,0.000037884285],"domain_scores_gemma":[0.99960893,0.00011909325,0.000027466207,0.00007924398,0.00013892587,0.000026364516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031443586,0.000463398,0.00037617036,0.0006330244,0.00032379344,0.0006453779,0.0010806667,0.00042650578,0.040391933],"category_scores_gemma":[0.0009931442,0.00021836361,0.00025274084,0.0011521758,0.00013243199,0.0005965616,0.0004185307,0.0006712436,0.011497117],"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":[0.001529171,0.00024930984,0.0036608034,0.0007120875,0.00013186899,0.00089479174,0.00023903795,0.0173529,0.19067326,0.0398873,0.13197866,0.6126908],"study_design_scores_gemma":[0.0006168287,0.0012910058,0.006430409,0.00021398788,0.00015533113,0.0020183607,0.00020115581,0.31283078,0.20262577,0.014833289,0.4586425,0.00014066925],"about_ca_topic_score_codex":0.0012349372,"about_ca_topic_score_gemma":0.001502576,"teacher_disagreement_score":0.040391933,"about_ca_system_score_codex":0.0005548648,"about_ca_system_score_gemma":0.00056319416,"threshold_uncertainty_score":0.13512444},"labels":[],"label_agreement":null},{"id":"W2158062068","doi":"10.1109/cmpsac.1979.762609","title":"Two n-point fast walsh transform sorting algorithms","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Royal Military College of Canada","funders":"","keywords":"sort; Sorting; Sorting algorithm; Algorithm; Computer science; Point (geometry); Set (abstract data type); Mathematics; Arithmetic","score_opus":0.014387906407972226,"score_gpt":0.26545493612547866,"score_spread":0.25106702971750644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158062068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012917151,0.00021746861,0.9676627,0.00022019517,0.00015021808,0.00016718864,0.0001388163,0.0021570087,0.016369395],"genre_scores_gemma":[0.1187444,0.00030431282,0.8360436,0.0002094877,0.000099475954,0.00030521103,0.0005948651,0.00030674168,0.04339192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908054,0.00011035592,0.00007500542,0.000120083365,0.00047776866,0.0001361908],"domain_scores_gemma":[0.9992778,0.0001529731,0.000054368862,0.00022515675,0.00024948406,0.000040328247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061983307,0.0008511977,0.00068487786,0.0013749276,0.00082434074,0.0018599401,0.0013442028,0.000992728,0.017072957],"category_scores_gemma":[0.0021434613,0.00035366678,0.0006331438,0.0013690926,0.00062055036,0.001673365,0.0015545173,0.0009062406,0.0074103517],"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":[0.0005094947,0.00013549319,0.00047640863,0.00017193586,0.000026189811,0.00024179992,0.00025266982,0.021910772,0.034876797,0.13201617,0.011837287,0.7975451],"study_design_scores_gemma":[0.00031629502,0.00050649856,0.0010979461,0.00012841071,0.000051962143,0.001706693,0.0003151833,0.6028796,0.14088227,0.13552685,0.11640184,0.00018651177],"about_ca_topic_score_codex":0.0012918852,"about_ca_topic_score_gemma":0.0021751805,"teacher_disagreement_score":0.017072957,"about_ca_system_score_codex":0.0008309306,"about_ca_system_score_gemma":0.0013205619,"threshold_uncertainty_score":0.05711472},"labels":[],"label_agreement":null},{"id":"W2158086649","doi":"10.1007/s00373-014-1467-4","title":"Minimum Many-to-Many Matchings for Computing the Distance Between Two Sequences","year":2014,"lang":"en","type":"article","venue":"Graphs and Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Queen's University","funders":"","keywords":"Mathematics; Matching (statistics); Combinatorics; Real line; Line (geometry); Discrete mathematics; Algorithm; Statistics","score_opus":0.013452449097658995,"score_gpt":0.25548876252894354,"score_spread":0.24203631343128454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158086649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0853217,0.0016472636,0.9023254,0.0010213049,0.00025808805,0.00031004153,0.001887994,0.0027394516,0.0044887816],"genre_scores_gemma":[0.3399721,0.0007828365,0.64874595,0.0003954374,0.0002465944,0.0005207865,0.004482145,0.000507856,0.0043463055],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965263,0.0006217357,0.00042643986,0.0010348747,0.0011096086,0.00028098057],"domain_scores_gemma":[0.99116933,0.0048368513,0.00075947284,0.0021681606,0.0007149231,0.00035115425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020409003,0.0014690448,0.0027917137,0.0056517962,0.0017814584,0.0029866744,0.0039412975,0.0030517217,0.0068103564],"category_scores_gemma":[0.021755239,0.00087514747,0.0015906343,0.007621138,0.0019119867,0.008839072,0.0034942615,0.0032004535,0.002448209],"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":[0.0020139674,0.000751233,0.0041757203,0.001142646,0.0002582275,0.00022685263,0.0006501891,0.13259286,0.013936824,0.1773695,0.018049262,0.64883274],"study_design_scores_gemma":[0.00018801777,0.00029605126,0.0008305696,0.00013712732,0.00012339099,0.0004596972,0.0002694362,0.52253026,0.009467504,0.45976567,0.00585948,0.0000728466],"about_ca_topic_score_codex":0.0015883937,"about_ca_topic_score_gemma":0.0027986837,"teacher_disagreement_score":0.0068103564,"about_ca_system_score_codex":0.001992904,"about_ca_system_score_gemma":0.0018697743,"threshold_uncertainty_score":0.022782922},"labels":[],"label_agreement":null},{"id":"W2158725698","doi":"10.1109/itwnit.2009.5158535","title":"Constructing optimal whole-bit recycling codes","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Redundancy (engineering); Bit (key); Recipe; Computer science; Multiplicity (mathematics); Algorithm; Data compression; Mathematics; Computer network","score_opus":0.01693023982062969,"score_gpt":0.2620274085568954,"score_spread":0.2450971687362657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158725698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07945046,0.00046647846,0.91008663,0.00022742174,0.00008066087,0.000109910005,0.00018421476,0.0009822205,0.008411993],"genre_scores_gemma":[0.2952397,0.00072404416,0.6950447,0.00024416504,0.000064589345,0.0002851811,0.00056030473,0.0006260647,0.007211275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99832064,0.00038392577,0.00014079959,0.0002290598,0.0006285646,0.0002969667],"domain_scores_gemma":[0.9968575,0.0011845737,0.00022866282,0.0008073455,0.00079862744,0.00012335375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001637295,0.00078913773,0.0012841204,0.002027583,0.0008541755,0.0014106487,0.0013757645,0.0015748611,0.0027312655],"category_scores_gemma":[0.008963333,0.0007384096,0.0008492165,0.0018621384,0.0018941252,0.0021885224,0.002663817,0.0015705273,0.0013736836],"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":[0.0005755407,0.000108687644,0.0008435611,0.00046359416,0.00006200387,0.00024063258,0.00042371877,0.116811454,0.039066814,0.5515429,0.005640684,0.2842204],"study_design_scores_gemma":[0.00012063752,0.00016516514,0.0002885175,0.00014117842,0.000064858046,0.00034579053,0.00012328618,0.51560545,0.08524286,0.38458318,0.013219388,0.00009971687],"about_ca_topic_score_codex":0.00046361383,"about_ca_topic_score_gemma":0.00046810092,"teacher_disagreement_score":0.0027312655,"about_ca_system_score_codex":0.0009167722,"about_ca_system_score_gemma":0.001653499,"threshold_uncertainty_score":0.009136975},"labels":[],"label_agreement":null},{"id":"W2159041520","doi":"10.1109/tcomm.2011.081111.100300","title":"On Computation of Performance Bounds of Optimal Index Assignment","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Algorithms and Data Compression","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":"Blackberry (Canada); McMaster University","funders":"","keywords":"Quadratic assignment problem; Mathematical optimization; Assignment problem; Heuristic; Computation; Index (typography); Computer science; Resilience (materials science); Channel (broadcasting); Weapon target assignment problem; Upper and lower bounds; Quadratic equation; Optimization problem; Algorithm; Frequency assignment; Mathematics; Telecommunications","score_opus":0.053607851987623335,"score_gpt":0.27326439195972874,"score_spread":0.2196565399721054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159041520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032942574,0.002109484,0.9431233,0.0009125654,0.0001735243,0.0000978058,0.00021143103,0.00056604715,0.019863307],"genre_scores_gemma":[0.7038089,0.002652409,0.28646818,0.0005248663,0.00048534814,0.00053166796,0.00070491014,0.00077656144,0.0040472304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99491274,0.0018766026,0.00017286885,0.000584264,0.0017238674,0.0007295013],"domain_scores_gemma":[0.95298624,0.04012959,0.0014832816,0.0027410632,0.0020040262,0.0006558178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007439691,0.0030702355,0.0020497786,0.0027273654,0.0010190954,0.0037791634,0.0017177794,0.0020876375,0.005852801],"category_scores_gemma":[0.060594965,0.0007862988,0.00095298764,0.0024355925,0.0031403094,0.0037150967,0.0031610485,0.0039301454,0.0014080937],"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":[0.00026850007,0.00008706917,0.00052701624,0.00020751933,0.00003813352,0.000055575878,0.00014271999,0.8668476,0.0038524605,0.090880364,0.0025698652,0.034523223],"study_design_scores_gemma":[0.000014291397,0.0000648041,0.00016976238,0.000057866524,0.0000107435235,0.000028957182,0.00002927827,0.9519748,0.0027020206,0.044290613,0.0006421957,0.000014631659],"about_ca_topic_score_codex":0.0017012019,"about_ca_topic_score_gemma":0.0014345674,"teacher_disagreement_score":0.007439691,"about_ca_system_score_codex":0.003360005,"about_ca_system_score_gemma":0.0025184506,"threshold_uncertainty_score":0.039345324},"labels":[],"label_agreement":null},{"id":"W2159109004","doi":"10.1007/0-306-47015-2_36","title":"A Note on Coarse Grained Parallel Integer Sorting","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Sorting; Integer (computer science); Simple (philosophy); Computer science; Parallel computing; Computation; Algorithm; Sorting algorithm; Combinatorics; Mathematics","score_opus":0.026568978833162834,"score_gpt":0.2648823722166881,"score_spread":0.23831339338352525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159109004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00954461,0.020429289,0.8848913,0.007427996,0.0050643813,0.00016727102,0.00034873115,0.0046688644,0.06745753],"genre_scores_gemma":[0.08285927,0.021179019,0.81367296,0.002687039,0.003486515,0.00017240015,0.00070899684,0.0012151024,0.074018724],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99930704,0.000071248054,0.00005180095,0.00012272007,0.00038998047,0.000057203575],"domain_scores_gemma":[0.9990916,0.0004323649,0.000023057073,0.00030500963,0.000117109004,0.00003079413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008413711,0.00075093383,0.0006695936,0.0008243969,0.0007718777,0.0015210768,0.0011684725,0.0005228556,0.00934788],"category_scores_gemma":[0.0019744996,0.00041379232,0.0006831068,0.002417035,0.0014439863,0.003522215,0.0014518664,0.0022874954,0.004098882],"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":[0.00029127023,0.0000905525,0.00043085433,0.00061707885,0.00003496888,0.00023037985,0.00012698118,0.04348671,0.013983178,0.21038961,0.073764496,0.6565539],"study_design_scores_gemma":[0.0000569391,0.00014712871,0.0010982404,0.00014519761,0.000034230365,0.000511634,0.00008315818,0.103238985,0.01410642,0.40292838,0.47757605,0.00007360995],"about_ca_topic_score_codex":0.0033485705,"about_ca_topic_score_gemma":0.0037388287,"teacher_disagreement_score":0.00934788,"about_ca_system_score_codex":0.0009287051,"about_ca_system_score_gemma":0.0008640318,"threshold_uncertainty_score":0.031271815},"labels":[],"label_agreement":null},{"id":"W2159228779","doi":"10.1109/icct.2000.889351","title":"Lossless image coding via one-dimensional grammar based codes","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Arithmetic coding; Lossless compression; Context-adaptive variable-length coding; Variable-length code; Tunstall coding; Context-adaptive binary arithmetic coding; Computer science; Coding (social sciences); Algorithm; Redundancy (engineering); Theoretical computer science; Shannon–Fano coding; Artificial intelligence; Mathematics; Computer vision; Data compression; Decoding methods","score_opus":0.02705198952183068,"score_gpt":0.23174008544338298,"score_spread":0.2046880959215523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159228779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037408058,0.00051325676,0.9551914,0.0003128703,0.00006927281,0.000074147,0.000122034326,0.00051577494,0.00579321],"genre_scores_gemma":[0.61729294,0.0009813671,0.37488198,0.00036680102,0.000110574336,0.00023296486,0.0002892462,0.00010778486,0.005736311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953794,0.000096190815,0.000023310702,0.00006668416,0.00021452564,0.00006136774],"domain_scores_gemma":[0.9991353,0.00029590947,0.00011927751,0.0002361884,0.00018224039,0.00003115706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041624444,0.00043850954,0.00047031752,0.00073409354,0.00027644951,0.0009323015,0.00089234987,0.0006241749,0.0011600975],"category_scores_gemma":[0.0019435791,0.0001562074,0.0003556576,0.00097416405,0.0011178076,0.0015025695,0.00087386917,0.0008345231,0.00047721114],"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":[0.0002889694,0.00006335164,0.00071536034,0.0001968887,0.00002706888,0.00038638225,0.00031839305,0.21040711,0.050714508,0.49313337,0.003996494,0.23975207],"study_design_scores_gemma":[0.000040232775,0.00013435657,0.0003142829,0.000037056674,0.000015830687,0.00034038504,0.000039137634,0.8284285,0.026515529,0.13785794,0.0062360973,0.000040632785],"about_ca_topic_score_codex":0.0013322961,"about_ca_topic_score_gemma":0.0009994755,"teacher_disagreement_score":0.0013322961,"about_ca_system_score_codex":0.0007826907,"about_ca_system_score_gemma":0.00075350935,"threshold_uncertainty_score":0.005678773},"labels":[],"label_agreement":null},{"id":"W2160050794","doi":"10.1109/icdar.2005.93","title":"Document understanding system using stochastic context-free grammars","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Concordia University","funders":"","keywords":"Computer science; Natural language processing; Parsing; Artificial intelligence; Context-free grammar; Rule-based machine translation; Context (archaeology); Grammar; Document processing; Regular expression; Block (permutation group theory); Character (mathematics); Programming language; Linguistics; Mathematics","score_opus":0.04866331483306063,"score_gpt":0.25977071392154616,"score_spread":0.21110739908848553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160050794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013111022,0.00017143904,0.9588426,0.00021522456,0.00003494837,0.00008639244,0.0006198866,0.025022479,0.0018960572],"genre_scores_gemma":[0.2039639,0.0003441076,0.78620535,0.00025079274,0.00006443741,0.00022480487,0.002866985,0.0012686707,0.0048109996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992687,0.00013376512,0.00007135255,0.00022080573,0.000258725,0.000046632296],"domain_scores_gemma":[0.9986732,0.0006680526,0.00008260543,0.00026195633,0.00026895496,0.00004521128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009571493,0.0005723679,0.00094188075,0.0010277417,0.00063199166,0.0015226194,0.0014402693,0.0014299006,0.003798317],"category_scores_gemma":[0.0036426904,0.00043306864,0.0010252319,0.0008004168,0.00046454614,0.0024577372,0.0010285097,0.0011691906,0.0019796123],"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":[0.0004392967,0.00026357765,0.0020016404,0.0003643252,0.00017244152,0.001010405,0.00082134927,0.25709483,0.03631735,0.082222745,0.029073741,0.59021825],"study_design_scores_gemma":[0.000050529532,0.00004285953,0.0002443797,0.000024328663,0.00004112518,0.00022038631,0.000044361197,0.9307047,0.013761076,0.037982244,0.01684252,0.00004161241],"about_ca_topic_score_codex":0.0053535164,"about_ca_topic_score_gemma":0.004397523,"teacher_disagreement_score":0.0053535164,"about_ca_system_score_codex":0.00092908746,"about_ca_system_score_gemma":0.0012621195,"threshold_uncertainty_score":0.012706578},"labels":[],"label_agreement":null},{"id":"W2160802334","doi":"10.1007/3-540-44888-8_4","title":"Optimal Spaced Seeds for Hidden Markov Models, with Application to Homologous Coding Regions","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Coding (social sciences); Markov chain; Computer science; Hidden Markov model; Markov model; Computational biology; Artificial intelligence; Biology; Mathematics; Machine learning; Statistics","score_opus":0.01756825757284889,"score_gpt":0.24319839916902644,"score_spread":0.22563014159617756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160802334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065374994,0.0002147498,0.99220896,0.00006153108,0.000022856542,0.00002868138,0.000040013838,0.00036731004,0.0005184105],"genre_scores_gemma":[0.19780736,0.0006069312,0.7979114,0.000085534506,0.000102862665,0.00021534729,0.00038116673,0.0005169609,0.002372413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99919087,0.000380943,0.000038885726,0.00016650232,0.00016121008,0.00006169447],"domain_scores_gemma":[0.9907719,0.007586049,0.00038204083,0.00059687876,0.00044268658,0.00022041897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026052499,0.0010348398,0.0017587537,0.0014169101,0.0009067195,0.001440148,0.0022481445,0.0025750324,0.0028520068],"category_scores_gemma":[0.016087538,0.0010656574,0.0011200064,0.0017109253,0.0016707997,0.002755706,0.0020169597,0.0018571226,0.0010847006],"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":[0.00038046678,0.00012179145,0.0005694557,0.0001844585,0.00003218749,0.0002575484,0.00027799874,0.68479556,0.005646043,0.17348734,0.0026460048,0.13160115],"study_design_scores_gemma":[0.000014145074,0.000015334766,0.000035481913,0.000009559167,0.000005971213,0.000028902217,0.000011536904,0.9476186,0.00062514434,0.05126995,0.0003570083,0.000008340604],"about_ca_topic_score_codex":0.002435538,"about_ca_topic_score_gemma":0.0027392323,"teacher_disagreement_score":0.0028520068,"about_ca_system_score_codex":0.0011391687,"about_ca_system_score_gemma":0.0014951257,"threshold_uncertainty_score":0.013778031},"labels":[],"label_agreement":null},{"id":"W2160877678","doi":"10.1109/cibcb.2008.4675755","title":"Classifying synthetic and biological DNA sequences with side effect machines","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"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 Guelph","funders":"","keywords":"Cluster analysis; Computer science; Finite-state machine; Feature (linguistics); Artificial intelligence; Population; Algorithm; Set (abstract data type); State (computer science); Machine learning; Sequence (biology); Biological data; String (physics); Mathematics; Bioinformatics; Biology","score_opus":0.025671408595029078,"score_gpt":0.240573625183412,"score_spread":0.2149022165883829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160877678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6412971,0.00021650018,0.35474163,0.00022381415,0.00007235824,0.00013940022,0.00027262323,0.0013696804,0.0016669701],"genre_scores_gemma":[0.81390744,0.00009079116,0.1843509,0.000054493587,0.000022859173,0.00013458793,0.0004958403,0.00003413219,0.00090895564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948883,0.00014901784,0.00005464454,0.00012732297,0.00014342075,0.000036706453],"domain_scores_gemma":[0.9964228,0.0024452282,0.00026232968,0.00036795123,0.00043477482,0.000066944645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009926698,0.0003226422,0.0004868423,0.0007164672,0.00026867387,0.0004961847,0.0004848803,0.00064081146,0.0007382101],"category_scores_gemma":[0.0050164163,0.00016206296,0.00033922624,0.0005878996,0.0004923654,0.0007300169,0.0002835885,0.0005822154,0.00026267322],"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":[0.00092623715,0.00034108027,0.012657034,0.00020080572,0.00006972138,0.00034350026,0.00031650686,0.4692982,0.09460068,0.0072586257,0.0013636317,0.41262403],"study_design_scores_gemma":[0.00000600782,0.00011579123,0.0013233785,0.0000058391497,0.000005001716,0.00007423179,0.000021907015,0.97165525,0.02330801,0.0031057533,0.00036995532,0.000008877407],"about_ca_topic_score_codex":0.00054722966,"about_ca_topic_score_gemma":0.0005948679,"teacher_disagreement_score":0.0009926698,"about_ca_system_score_codex":0.00042728244,"about_ca_system_score_gemma":0.00031313841,"threshold_uncertainty_score":0.0052497983},"labels":[],"label_agreement":null},{"id":"W2160902920","doi":"10.1109/tit.2004.830781","title":"Performance Analysis of Grammar-Based Codes Revisited","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data compression; Mathematics; Combinatorics; Algorithm; Arithmetic coding; Context (archaeology); Markov chain; Discrete mathematics; Context-adaptive binary arithmetic coding","score_opus":0.008600087559121712,"score_gpt":0.22529205400680585,"score_spread":0.21669196644768415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160902920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40745068,0.0058886353,0.57314837,0.0011230954,0.00017224113,0.00018730917,0.00039578375,0.002317108,0.009316743],"genre_scores_gemma":[0.90689534,0.0010017562,0.08987256,0.00020224848,0.00007112181,0.00010685836,0.00036967266,0.00014478632,0.0013356524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995865,0.0010028178,0.00021053404,0.00041770647,0.0021112375,0.00039276318],"domain_scores_gemma":[0.9842977,0.010050458,0.00088722387,0.001751308,0.0027529984,0.0002604153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00267086,0.00077427167,0.00090006023,0.0019666315,0.0006340913,0.0014234452,0.0011136188,0.0015837958,0.0013916343],"category_scores_gemma":[0.021420212,0.0002643555,0.00039983296,0.0020655056,0.0015128944,0.002408519,0.0016313345,0.0011271756,0.00040731387],"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":[0.0013660697,0.00012974201,0.0040955073,0.00031191952,0.00013554226,0.0003276632,0.0003320645,0.6922123,0.038010802,0.063582055,0.0018351873,0.19766112],"study_design_scores_gemma":[0.000021078515,0.00025853325,0.00044351796,0.000030387295,0.000023620487,0.00021169038,0.000041482017,0.9635593,0.022255333,0.012241848,0.00088273926,0.000030504743],"about_ca_topic_score_codex":0.0029759551,"about_ca_topic_score_gemma":0.0023473173,"teacher_disagreement_score":0.0029759551,"about_ca_system_score_codex":0.0018405548,"about_ca_system_score_gemma":0.0024149443,"threshold_uncertainty_score":0.0141249895},"labels":[],"label_agreement":null},{"id":"W2161252119","doi":"10.1109/icip.2005.1530048","title":"A near minimum sparse pattern coding based scheme for binary image compression","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Northern British Columbia","funders":"","keywords":"Coding (social sciences); Computer science; Binary number; Image compression; Data compression; Scheme (mathematics); Algorithm; Context-adaptive binary arithmetic coding; Computational complexity theory; Sparse approximation; Neural coding; Image (mathematics); Binary code; Artificial intelligence; Pattern recognition (psychology); Mathematics; Image processing; Arithmetic","score_opus":0.026261810062195873,"score_gpt":0.2747040050506007,"score_spread":0.24844219498840484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161252119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011421922,0.00028488107,0.9863517,0.0002294491,0.00008178007,0.00006042778,0.00004304036,0.00022591597,0.0013008695],"genre_scores_gemma":[0.21112984,0.00042900615,0.78454494,0.00024549136,0.00011334698,0.00015965899,0.00021915755,0.000049914757,0.0031085887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995697,0.00011129956,0.00002372954,0.00004520304,0.00022492565,0.00002504282],"domain_scores_gemma":[0.9995999,0.00009691067,0.00004266081,0.00012371114,0.00011384801,0.000023043869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035899697,0.0003187292,0.0004721745,0.0006566337,0.00033416835,0.0004490408,0.0007514302,0.00067146786,0.0015937279],"category_scores_gemma":[0.001445676,0.00015834409,0.00024521092,0.00077737635,0.0004517324,0.0012365127,0.00066955783,0.0008425023,0.0005911748],"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":[0.00051195076,0.00013321057,0.0005026034,0.00023209925,0.000041924286,0.00024158384,0.00016453091,0.04757074,0.1971324,0.07825887,0.0056738267,0.6695363],"study_design_scores_gemma":[0.00010786226,0.00044656105,0.0006451176,0.000050700077,0.000032790078,0.0011870232,0.000039206727,0.87287754,0.089458264,0.019099973,0.015989019,0.000065918786],"about_ca_topic_score_codex":0.00041763653,"about_ca_topic_score_gemma":0.00061606814,"teacher_disagreement_score":0.0015937279,"about_ca_system_score_codex":0.00027570542,"about_ca_system_score_gemma":0.00033147103,"threshold_uncertainty_score":0.005331576},"labels":[],"label_agreement":null},{"id":"W2161403911","doi":"10.1016/j.tcs.2007.07.015","title":"Adaptive searching in succinctly encoded binary relations and tree-structured documents","year":2007,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Conjunctive query; Binary relation; Binary number; XML; Intersection (aeronautics); Theoretical computer science; Representation (politics); Binary tree; Information retrieval; Relation (database); Data mining; Mathematics; Algorithm; Discrete mathematics; Relational database; World Wide Web","score_opus":0.008911253992056412,"score_gpt":0.2664774614759441,"score_spread":0.2575662074838877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161403911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30967793,0.0018589683,0.6810802,0.00081191596,0.00015094147,0.00010390651,0.00080390606,0.001829578,0.0036826832],"genre_scores_gemma":[0.5967364,0.000902395,0.39379847,0.00026764147,0.00010659503,0.00011491789,0.00152975,0.00028635422,0.0062575783],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998728,0.0003104494,0.00011945913,0.00021028526,0.0005187551,0.000113098715],"domain_scores_gemma":[0.9917075,0.005622964,0.0005186466,0.0012819488,0.00071664073,0.00015230104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010450582,0.00035743735,0.001022231,0.0014804855,0.0005192635,0.0014764126,0.0014452464,0.0012952171,0.0022941455],"category_scores_gemma":[0.012698007,0.0004930085,0.00038272876,0.0037924824,0.00084597827,0.0039190357,0.0012677164,0.0010495256,0.0007205417],"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":[0.002100033,0.00041316624,0.0031746314,0.0006075021,0.00009019712,0.0007540505,0.00086217985,0.2521647,0.04198977,0.1098618,0.01076541,0.57721657],"study_design_scores_gemma":[0.00006414483,0.00011493917,0.00050149055,0.000042482337,0.00003232308,0.00038745385,0.0001515852,0.9160029,0.01748573,0.06297778,0.0022140741,0.000025108986],"about_ca_topic_score_codex":0.0020271083,"about_ca_topic_score_gemma":0.0032263417,"teacher_disagreement_score":0.0022941455,"about_ca_system_score_codex":0.00082353404,"about_ca_system_score_gemma":0.00093418034,"threshold_uncertainty_score":0.007674694},"labels":[],"label_agreement":null},{"id":"W2161615476","doi":"10.1109/hpcc.2009.100","title":"Load Scheduling Strategies for Parallel DNA Sequencing Applications","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"St. Francis Xavier University","funders":"","keywords":"Computer science; Scheduling (production processes); Computation; Parallel computing; Load distribution; Distributed computing; Load balancing (electrical power); Algorithm; Mathematical optimization; Mathematics","score_opus":0.031644127402825045,"score_gpt":0.2877861372188106,"score_spread":0.25614200981598556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161615476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14058156,0.0007944531,0.85094035,0.00027458364,0.00009939119,0.00013889952,0.000040435636,0.00050640584,0.006623881],"genre_scores_gemma":[0.8221758,0.00059907406,0.1726088,0.00008986337,0.00010272423,0.00012829085,0.00008023261,0.00012399182,0.0040913206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997309,0.00008276369,0.000014677,0.00003979112,0.00009304439,0.000038791448],"domain_scores_gemma":[0.9994672,0.00028245256,0.00007140137,0.00004404523,0.000094930074,0.000039987466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005538036,0.000552849,0.00038554537,0.00062737067,0.00071793806,0.0005721764,0.00068934314,0.00038592948,0.0016983084],"category_scores_gemma":[0.0016905796,0.0002315018,0.0001831768,0.0006226265,0.00038176964,0.0010915919,0.0004745936,0.00029657144,0.00036748304],"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":[0.00039872018,0.00023345496,0.0008071093,0.00015871946,0.000029067533,0.00020305195,0.00025405007,0.71172124,0.035255507,0.030767495,0.0019552063,0.2182164],"study_design_scores_gemma":[0.000021838601,0.00007377315,0.00014205901,0.000005236338,0.00000715911,0.000029948345,0.000042921656,0.9847098,0.0042008827,0.008603682,0.0021551605,0.000007505903],"about_ca_topic_score_codex":0.0016311768,"about_ca_topic_score_gemma":0.0016821248,"teacher_disagreement_score":0.0016983084,"about_ca_system_score_codex":0.00078309135,"about_ca_system_score_gemma":0.00055407867,"threshold_uncertainty_score":0.0056816936},"labels":[],"label_agreement":null},{"id":"W2161950782","doi":"10.1109/ccece.2004.1347647","title":"A novel way of lossless compression of digital mammograms using grammar codes","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Huffman coding; Lossless compression; Computer science; Data compression; Arithmetic coding; Artificial intelligence; Shannon–Fano coding; Grammar; Tunstall coding; Variable-length code; Algorithm; Context-adaptive binary arithmetic coding; Speech recognition; Theoretical computer science; Decoding methods; Linguistics","score_opus":0.032394286722048526,"score_gpt":0.26435043405510295,"score_spread":0.23195614733305442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161950782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10257813,0.000518233,0.89104676,0.00035454406,0.00017006643,0.00013745014,0.00022848869,0.002118969,0.002847459],"genre_scores_gemma":[0.4384439,0.00062736165,0.5540888,0.00027268284,0.0001076078,0.00015193783,0.00073056156,0.0002605874,0.0053165304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996605,0.000038468806,0.000020392823,0.000043607706,0.00021543502,0.000021659185],"domain_scores_gemma":[0.99936813,0.00023009005,0.000051770483,0.00011144077,0.00021807874,0.000020451433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025757603,0.00038082912,0.00027138402,0.00073587114,0.00020130337,0.00032639937,0.00058382074,0.0004656097,0.0010051319],"category_scores_gemma":[0.0015146444,0.00011191829,0.0002815623,0.00072584226,0.00044182537,0.0006209976,0.00046295428,0.00045124957,0.00029843292],"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":[0.0004061536,0.0001473296,0.0014716987,0.00026834846,0.00005843301,0.00148818,0.00046408444,0.053097874,0.39055073,0.02379575,0.0044412725,0.5238102],"study_design_scores_gemma":[0.000105278545,0.00042068545,0.0016999346,0.00005033911,0.000065365064,0.002883018,0.00007455278,0.59742254,0.37293658,0.0061484436,0.018122729,0.00007052554],"about_ca_topic_score_codex":0.0010873931,"about_ca_topic_score_gemma":0.00092756207,"teacher_disagreement_score":0.0010873931,"about_ca_system_score_codex":0.00024266464,"about_ca_system_score_gemma":0.0004591269,"threshold_uncertainty_score":0.0033625364},"labels":[],"label_agreement":null},{"id":"W2162457418","doi":"10.1111/j.1556-4029.2010.01614.x","title":"DNAc: A Clustering Method for Identifying Kinship Relations Between DNA Profiles Using a Novel Similarity Measure*","year":2010,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Algorithms and Data Compression","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":"Cegep Edouard Montpetit; Université de Sherbrooke","funders":"","keywords":"Kinship; Similarity (geometry); Cluster analysis; Microsatellite; Population; Computer science; Genetics; Biology; Allele; Artificial intelligence; Political science; Sociology; Gene; Law","score_opus":0.17242209966894245,"score_gpt":0.38660357275149454,"score_spread":0.2141814730825521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162457418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009357517,0.00029124055,0.9878637,0.00009381043,0.0000775786,0.00013607045,0.00038447202,0.0012334178,0.00056212203],"genre_scores_gemma":[0.047963787,0.00017205624,0.9488693,0.00007188992,0.000041300547,0.00027645272,0.0010153478,0.00018332645,0.0014066594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984676,0.00023224163,0.00012974521,0.00033734032,0.0007534201,0.00007957615],"domain_scores_gemma":[0.99770147,0.0005952109,0.0002694215,0.0005287351,0.0007863879,0.00011879336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012593702,0.0008291834,0.0010798682,0.0060422593,0.0010855147,0.0010327154,0.0019028535,0.0010795838,0.0019629924],"category_scores_gemma":[0.0047059217,0.0004027898,0.00077866303,0.0046589584,0.0010009744,0.0013988854,0.0015773261,0.0011447754,0.0020268103],"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":[0.00018555942,0.00011552552,0.0033631036,0.00031418758,0.00013971086,0.00019280704,0.0003846545,0.0198363,0.036971975,0.010343792,0.008805753,0.9193466],"study_design_scores_gemma":[0.0000885363,0.00023075302,0.010087682,0.00010639483,0.00009915123,0.0018054922,0.0003380423,0.85374004,0.061488386,0.0247027,0.047066,0.00024690427],"about_ca_topic_score_codex":0.0033818092,"about_ca_topic_score_gemma":0.0039044395,"teacher_disagreement_score":0.0060422593,"about_ca_system_score_codex":0.00080816867,"about_ca_system_score_gemma":0.0012087334,"threshold_uncertainty_score":0.006724298},"labels":[],"label_agreement":null},{"id":"W2162678883","doi":"10.1016/j.tcs.2009.07.010","title":"A new approach to the periodicity lemma on strings with holes","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Lemma (botany); Mathematics; String (physics); Combinatorics; Discrete mathematics; Computer science; Data structure","score_opus":0.012621170148108091,"score_gpt":0.2370631779968014,"score_spread":0.2244420078486933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162678883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02178528,0.0015017152,0.9385207,0.0025533114,0.0012213092,0.00007228839,0.00022733229,0.00055470626,0.03356339],"genre_scores_gemma":[0.43444195,0.0036472715,0.51249355,0.0036249966,0.00588975,0.00046532298,0.0008037209,0.0016185393,0.037014965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774545,0.0006086088,0.00016792414,0.00047872728,0.00076795573,0.00023122312],"domain_scores_gemma":[0.9935888,0.003424909,0.00036208172,0.0017511526,0.0006005877,0.0002723834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020868608,0.0009273289,0.0016313446,0.0033409533,0.0020074788,0.0036042025,0.0024367105,0.0023820389,0.0077829],"category_scores_gemma":[0.009965455,0.00086660136,0.0018030145,0.0031831644,0.004630272,0.013742393,0.0064865025,0.0054825805,0.0017250035],"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":[0.00004396252,0.000020522844,0.0001655032,0.000060307277,0.000010485643,0.00014253396,0.00014372806,0.0011972331,0.0018160398,0.9775229,0.002758346,0.016118478],"study_design_scores_gemma":[0.000017751665,0.000034474815,0.0001268095,0.000028295752,0.00001603974,0.00029955397,0.00004941314,0.02063919,0.0011803735,0.9678648,0.009719085,0.00002428013],"about_ca_topic_score_codex":0.00043828474,"about_ca_topic_score_gemma":0.00046366444,"teacher_disagreement_score":0.0077829,"about_ca_system_score_codex":0.0009928936,"about_ca_system_score_gemma":0.0007630567,"threshold_uncertainty_score":0.026036441},"labels":[],"label_agreement":null},{"id":"W2162858604","doi":"10.1109/icci.1992.227636","title":"Compression of dictionaries via extensions to front coding","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Calgary","funders":"","keywords":"Huffman coding; Computer science; Prefix; Redundancy (engineering); Natural language processing; Tunstall coding; Coding (social sciences); Artificial intelligence; Data compression; Mathematics; Linguistics","score_opus":0.016146983118303045,"score_gpt":0.24536646936255094,"score_spread":0.2292194862442479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162858604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017668204,0.00051713275,0.9738012,0.00016330727,0.0002148735,0.00017287303,0.0003226507,0.0018204192,0.0053194254],"genre_scores_gemma":[0.090218395,0.00073861686,0.8960535,0.00017824193,0.0001330037,0.00017642326,0.00127609,0.00021914642,0.011006566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993131,0.00011501495,0.00006462955,0.0000866068,0.0003577101,0.00006287339],"domain_scores_gemma":[0.9980076,0.0005738654,0.00007340796,0.00063551025,0.00067425176,0.000035382956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058384833,0.00067651435,0.00055514864,0.0019162493,0.0004999468,0.001394237,0.0007984533,0.0007714329,0.004629336],"category_scores_gemma":[0.0032796615,0.00034032323,0.0006521906,0.0023604096,0.00060078944,0.0013794065,0.0013376571,0.0009871493,0.0028208834],"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":[0.0004678242,0.000114916504,0.0004339489,0.0002706588,0.000044960256,0.0003412075,0.00028129897,0.033616565,0.07801946,0.039662953,0.008629443,0.8381167],"study_design_scores_gemma":[0.00008757913,0.0002772765,0.0009937929,0.00012122177,0.000059831862,0.0012951697,0.000129489,0.6748959,0.2377821,0.03795945,0.046303842,0.00009443309],"about_ca_topic_score_codex":0.0016005909,"about_ca_topic_score_gemma":0.0019154215,"teacher_disagreement_score":0.004629336,"about_ca_system_score_codex":0.00038750234,"about_ca_system_score_gemma":0.0004959712,"threshold_uncertainty_score":0.015486717},"labels":[],"label_agreement":null},{"id":"W2163459627","doi":"10.1145/2332432.2332438","title":"Random walks which prefer unvisited edges.","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Random walk; Vertex (graph theory); Enhanced Data Rates for GSM Evolution; Mathematics; Combinatorics; Computer science; Discrete mathematics; Artificial intelligence; Graph; Statistics","score_opus":0.020963793510455846,"score_gpt":0.24427673738261127,"score_spread":0.22331294387215542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163459627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1481505,0.0011454757,0.8295441,0.000997897,0.0004479095,0.00056481065,0.00034244778,0.00067670486,0.018130116],"genre_scores_gemma":[0.83732474,0.00082035473,0.14356074,0.0010342739,0.00032380727,0.00060474745,0.00042385678,0.00032782144,0.015579732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962799,0.00166268,0.00019950436,0.00072228204,0.00074164243,0.00039395716],"domain_scores_gemma":[0.98002464,0.0119519355,0.0017289157,0.004413884,0.0010626632,0.000817958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031882674,0.0008473485,0.00097024214,0.0010897403,0.000926132,0.001630399,0.0018140407,0.002086264,0.0052738492],"category_scores_gemma":[0.027321428,0.0005634084,0.00087661797,0.0012248486,0.001777206,0.0047405045,0.0013787504,0.002071412,0.0013672092],"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":[0.002317163,0.0005151314,0.006175404,0.0005953132,0.00039145758,0.0011620295,0.00046656936,0.2153472,0.029098762,0.6238672,0.008419962,0.111643754],"study_design_scores_gemma":[0.0003080294,0.00079729484,0.0011044416,0.00010851811,0.00014373806,0.0010731404,0.00014691798,0.5191223,0.010120964,0.45285633,0.014109546,0.00010876605],"about_ca_topic_score_codex":0.0004956094,"about_ca_topic_score_gemma":0.0011361267,"teacher_disagreement_score":0.0052738492,"about_ca_system_score_codex":0.0005765392,"about_ca_system_score_gemma":0.00056057476,"threshold_uncertainty_score":0.017642796},"labels":[],"label_agreement":null},{"id":"W2163475593","doi":"10.1109/pccc.1991.113886","title":"Keyboard optimization using genetic techniques","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Alphabet; Set (abstract data type); Power set; Computer science; Genetic algorithm; Character (mathematics); Finite set; Optimization problem; Power (physics); Theoretical computer science; Combinatorics; Artificial intelligence; Algorithm; Discrete mathematics; Mathematics; Machine learning; Programming language","score_opus":0.030638060851962884,"score_gpt":0.24259792164636654,"score_spread":0.21195986079440365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163475593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053186677,0.000694741,0.93636507,0.00029789782,0.00007184385,0.00009388184,0.00007341276,0.00070370437,0.008512757],"genre_scores_gemma":[0.45882136,0.00079114333,0.5303904,0.00023760265,0.00006151209,0.0003281075,0.00024033377,0.00024174633,0.008887798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996196,0.00010943016,0.000020400783,0.000086719985,0.00010088959,0.00006293545],"domain_scores_gemma":[0.99950826,0.00028947278,0.00005410217,0.00004360531,0.00008332619,0.000021280957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050596945,0.0009343316,0.0011169151,0.0008351619,0.00046520354,0.0010049696,0.0008626308,0.0014713752,0.002889581],"category_scores_gemma":[0.0018196668,0.00043416777,0.00074902194,0.0009825502,0.00076320645,0.00081197656,0.0007124871,0.00086097204,0.00044155208],"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":[0.00005922579,0.000062403386,0.0004337519,0.00008284483,0.000043769927,0.00007620787,0.000065782435,0.91221076,0.005071627,0.012373322,0.0012839081,0.06823636],"study_design_scores_gemma":[0.000024170231,0.00004368111,0.000096705175,0.000011421641,0.000013726336,0.000033345186,0.000024789633,0.9910987,0.001313128,0.005734657,0.0015985911,0.0000070093497],"about_ca_topic_score_codex":0.0028474377,"about_ca_topic_score_gemma":0.0020598392,"teacher_disagreement_score":0.002889581,"about_ca_system_score_codex":0.00081541686,"about_ca_system_score_gemma":0.00085149455,"threshold_uncertainty_score":0.009666562},"labels":[],"label_agreement":null},{"id":"W2163733217","doi":"10.1016/j.jcss.2013.11.002","title":"Unshuffling a square is NP-hard","year":2013,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Square (algebra); Combinatorics; Time complexity; Interleaving; Mathematics; Square tiling; Discrete mathematics; Partition (number theory); Dynamic programming; Reduction (mathematics); Computer science; Algorithm","score_opus":0.02151735836986119,"score_gpt":0.24342231982633483,"score_spread":0.22190496145647365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163733217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36850715,0.0013602322,0.56670725,0.008084007,0.0007820805,0.00056378864,0.00242427,0.0032595093,0.048311643],"genre_scores_gemma":[0.81085044,0.00064000103,0.15753752,0.0011303694,0.0004279881,0.00028381054,0.0012927956,0.0006783257,0.027158672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986809,0.00018061175,0.00008522769,0.00042387357,0.00033850042,0.0002909098],"domain_scores_gemma":[0.9832261,0.014471008,0.0006281757,0.00081492006,0.0005529114,0.0003069794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008223668,0.0010157025,0.0015179645,0.000586466,0.001337873,0.0021386803,0.0015405522,0.0020500498,0.011244084],"category_scores_gemma":[0.009753889,0.000807257,0.0012780385,0.0013562823,0.0019742919,0.004217296,0.0022252358,0.0028093543,0.0016487953],"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":[0.0013462948,0.00057425664,0.00417848,0.0013897172,0.00024715342,0.0015854238,0.00073010183,0.47111443,0.021522135,0.10103795,0.051307183,0.3449669],"study_design_scores_gemma":[0.00033389055,0.00028685975,0.0007096777,0.00008296328,0.00008163843,0.0005299666,0.0005062364,0.63179106,0.0091171535,0.34496865,0.011538624,0.000053211923],"about_ca_topic_score_codex":0.004559491,"about_ca_topic_score_gemma":0.0048671723,"teacher_disagreement_score":0.011244084,"about_ca_system_score_codex":0.0010042575,"about_ca_system_score_gemma":0.0012767883,"threshold_uncertainty_score":0.03761524},"labels":[],"label_agreement":null},{"id":"W2163758199","doi":"10.1109/icassp.1994.389234","title":"New graph search techniques for speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Graph; Phone; Speech recognition; Property (philosophy); Feature (linguistics); Artificial intelligence; Feature extraction; Pattern recognition (psychology); Theoretical computer science","score_opus":0.06268289645669711,"score_gpt":0.28400293581017094,"score_spread":0.22132003935347383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163758199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017532626,0.001101327,0.993068,0.00020777267,0.00010355442,0.000043443124,0.0001439206,0.0011710145,0.00240767],"genre_scores_gemma":[0.036162324,0.0014194723,0.95148355,0.00033356517,0.00024344133,0.00016769624,0.0006930505,0.00056416495,0.008932753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989743,0.00022834362,0.000071363305,0.0002510719,0.00041127772,0.000063669715],"domain_scores_gemma":[0.99888307,0.00053547247,0.000083785,0.00024733433,0.00020572667,0.00004454314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005620289,0.0010090263,0.0010712729,0.0024021878,0.0006707071,0.0015211195,0.0017237408,0.0014292003,0.008280243],"category_scores_gemma":[0.0030224463,0.000578974,0.0010361874,0.0027894538,0.00090292917,0.0033145547,0.0015748475,0.0019250563,0.0045602135],"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":[0.00017670641,0.000108906774,0.0002625303,0.00041188492,0.000102790196,0.00016313381,0.00021224392,0.06955785,0.01848788,0.15012258,0.02204483,0.73834866],"study_design_scores_gemma":[0.000075209195,0.00009509709,0.00027308922,0.000074996045,0.00005663515,0.00033346852,0.000082217855,0.67417103,0.010853714,0.26690534,0.04701816,0.00006103209],"about_ca_topic_score_codex":0.0023075666,"about_ca_topic_score_gemma":0.0043548746,"teacher_disagreement_score":0.008280243,"about_ca_system_score_codex":0.0008496034,"about_ca_system_score_gemma":0.00071224343,"threshold_uncertainty_score":0.027700186},"labels":[],"label_agreement":null},{"id":"W2164030956","doi":"10.1109/dcc.2007.44","title":"High Throughput Compression of Double-Precision Floating-Point Data","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":96,"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":"Department of Family and Community Medicine, University of Toronto","keywords":"Lossless compression; Throughput; Computer science; Data compression; Compression (physics); Compression ratio; Point (geometry); Floating point; Computer hardware; Algorithm; Real-time computing; Wireless; Engineering; Mathematics; Telecommunications","score_opus":0.0562830034262234,"score_gpt":0.32088302093616367,"score_spread":0.2646000175099403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164030956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24100593,0.0046261777,0.7211755,0.00092369097,0.00068089017,0.00048400043,0.00712942,0.01523023,0.008744183],"genre_scores_gemma":[0.5243355,0.0024295656,0.4444966,0.00027773765,0.00039074276,0.000520121,0.018789686,0.0010609017,0.007699154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894613,0.00006222088,0.000072691284,0.000115864066,0.0007215271,0.00008164207],"domain_scores_gemma":[0.9986192,0.00035783564,0.000093386414,0.00027095177,0.0006148603,0.00004386933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071994244,0.00082375493,0.00063601445,0.002517278,0.00046071675,0.0010485132,0.0009948338,0.00047275572,0.0021019531],"category_scores_gemma":[0.0036026305,0.00019886906,0.000258721,0.0034156018,0.00036072396,0.0017382446,0.00092255237,0.00073901925,0.0013092202],"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":[0.0010263935,0.000157576,0.0024734878,0.00046408246,0.00007978058,0.0008908573,0.000383435,0.026529651,0.14514925,0.006013861,0.032616057,0.78421557],"study_design_scores_gemma":[0.00025347606,0.0004276705,0.0066200034,0.00016450346,0.00006119321,0.0017661746,0.00027425337,0.32617977,0.5985149,0.011993058,0.053626634,0.000118310236],"about_ca_topic_score_codex":0.0014393013,"about_ca_topic_score_gemma":0.0011666085,"teacher_disagreement_score":0.002517278,"about_ca_system_score_codex":0.00048693398,"about_ca_system_score_gemma":0.00055353553,"threshold_uncertainty_score":0.0070317388},"labels":[],"label_agreement":null},{"id":"W2164426675","doi":"10.1006/jpdc.2001.1789","title":"A Genetic Algorithm for Finding the Pagenumber of Interconnection Networks","year":2002,"lang":"en","type":"article","venue":"Journal of Parallel and Distributed Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Waterloo; Nortel (Canada)","funders":"","keywords":"Computer science; Interconnection; Genetic algorithm; Parallel computing; Algorithm; Computer network; Machine learning","score_opus":0.02333325426687188,"score_gpt":0.24934095488796865,"score_spread":0.22600770062109676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164426675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02538932,0.00037227458,0.9695845,0.00024638907,0.000111052126,0.00010699893,0.00008682516,0.0010667655,0.0030358287],"genre_scores_gemma":[0.16261326,0.00019017376,0.83296806,0.00015536354,0.000069693044,0.00026131416,0.0002037251,0.00016808418,0.0033703544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995635,0.00012111199,0.000022295915,0.000096853095,0.00014863398,0.000047659647],"domain_scores_gemma":[0.99800247,0.0014161515,0.00010950169,0.0001081427,0.00030545625,0.000058339785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009833791,0.0010446039,0.0012600176,0.0023979626,0.0010364249,0.0011718192,0.0018110401,0.0027307682,0.0037332787],"category_scores_gemma":[0.0055481885,0.00081813784,0.00093299453,0.0019164736,0.0010432026,0.0014261969,0.00074119755,0.0012302774,0.000622655],"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":[0.00011371877,0.00010754363,0.0009889811,0.00006390657,0.000060568564,0.00009063036,0.00009220018,0.7841596,0.0022583532,0.010660403,0.002522788,0.1988813],"study_design_scores_gemma":[0.000035559206,0.000020897203,0.00012240527,0.000007979893,0.000014049829,0.000023135552,0.000009864542,0.99357575,0.0004425301,0.0053278212,0.00041304887,0.0000069116154],"about_ca_topic_score_codex":0.010154386,"about_ca_topic_score_gemma":0.009191088,"teacher_disagreement_score":0.010154386,"about_ca_system_score_codex":0.0013595251,"about_ca_system_score_gemma":0.0016019654,"threshold_uncertainty_score":0.020190597},"labels":[],"label_agreement":null},{"id":"W2164727016","doi":"10.1109/bsc.2006.1644616","title":"Towards a Unified Solution for Constraint-Satisfaction Problems: A Survey-Propagation Approach Based on Normal Realizations","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Ottawa","funders":"","keywords":"Constraint satisfaction problem; Formalism (music); Local consistency; Computer science; Constraint satisfaction; Mathematical optimization; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence","score_opus":0.032802854198944124,"score_gpt":0.2511795903739018,"score_spread":0.21837673617495768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164727016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002248643,0.0006562333,0.9936801,0.0005456686,0.000035591067,0.000027939266,0.000038977243,0.00009158967,0.0026752378],"genre_scores_gemma":[0.10360412,0.0049550366,0.8846182,0.00058996666,0.00048609864,0.00032822066,0.00045309527,0.00025377033,0.0047114547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997439,0.0011133067,0.00014849243,0.00039800853,0.0007358834,0.00016521713],"domain_scores_gemma":[0.99665546,0.0021552949,0.00014940991,0.00048015744,0.0004405122,0.00011904536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004342557,0.0011481451,0.0019152927,0.0027527355,0.0010363652,0.0035162102,0.003197932,0.0021741001,0.0043087923],"category_scores_gemma":[0.010012872,0.0010343194,0.0021308023,0.004200907,0.0029559361,0.008118148,0.0029893762,0.0046885777,0.001137677],"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":[0.000011963075,0.000026351277,0.0001857806,0.00013286424,0.000018620885,0.000020876372,0.00010260395,0.021401651,0.0003775543,0.9409528,0.0016901359,0.03507883],"study_design_scores_gemma":[0.000017253273,0.000039501836,0.00007810325,0.00005730992,0.000015802714,0.000059994447,0.000052109663,0.2325673,0.00047020984,0.7548653,0.011756675,0.00002042889],"about_ca_topic_score_codex":0.0015844858,"about_ca_topic_score_gemma":0.0015051957,"teacher_disagreement_score":0.004342557,"about_ca_system_score_codex":0.0016028923,"about_ca_system_score_gemma":0.002170749,"threshold_uncertainty_score":0.022965908},"labels":[],"label_agreement":null},{"id":"W2165158451","doi":"10.1145/1242572.1242796","title":"Mobile shopping assistant","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Asynchronous communication; Web service; Architecture; Mobile phone; World Wide Web; Mobile telephony; Mobile Web; Mobile computing; Multimedia; Mobile technology; Mobile device; Computer network; Telecommunications; Mobile radio","score_opus":0.013081564158399015,"score_gpt":0.2664481769113925,"score_spread":0.2533666127529935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165158451","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06339072,0.0021090384,0.5419805,0.0025328402,0.0020578732,0.0014881907,0.0024175874,0.06320284,0.32082036],"genre_scores_gemma":[0.21795982,0.0016985527,0.24994877,0.002166525,0.0005762997,0.00042325663,0.0035118219,0.0019229592,0.52179193],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995561,0.000055321987,0.000028477181,0.00009625102,0.00018857619,0.00007513292],"domain_scores_gemma":[0.99940217,0.00007264808,0.000023536082,0.00015481137,0.00023650058,0.000110301145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037459735,0.0006932446,0.00053595495,0.00049067865,0.0008872367,0.0016407353,0.0014599334,0.001242192,0.10210163],"category_scores_gemma":[0.0010329216,0.00036422806,0.00040123885,0.00044224673,0.0002177202,0.0015469283,0.0015765182,0.00065569195,0.065780215],"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":[0.0011042586,0.0005781436,0.0032302372,0.0004149497,0.000043899345,0.002124214,0.00067239575,0.00090593804,0.07200964,0.021165641,0.17681779,0.7209329],"study_design_scores_gemma":[0.00009972735,0.00040010043,0.0020871721,0.00007588543,0.000044213208,0.0026803948,0.00024447762,0.010950036,0.028197274,0.0019347952,0.9531993,0.00008660985],"about_ca_topic_score_codex":0.00086233905,"about_ca_topic_score_gemma":0.0012742807,"teacher_disagreement_score":0.10210163,"about_ca_system_score_codex":0.00030904645,"about_ca_system_score_gemma":0.00033959825,"threshold_uncertainty_score":0.34156394},"labels":[],"label_agreement":null},{"id":"W2165384045","doi":"10.1109/tcbb.2005.26","title":"Joint Classification and Pairing of Human Chromosomes","year":2005,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"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":"Pairing; Heuristic; Computer science; Function (biology); Class (philosophy); Joint (building); Algorithm; Mathematical optimization; Theoretical computer science; Artificial intelligence; Mathematics; Biology; Engineering","score_opus":0.039090901260304824,"score_gpt":0.2903729291005122,"score_spread":0.25128202784020737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165384045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11224223,0.0006824168,0.8824484,0.0008906302,0.00007778596,0.000072131996,0.00027138297,0.00044660314,0.0028683797],"genre_scores_gemma":[0.58371985,0.0005520287,0.4086562,0.00024389806,0.00014110743,0.00018953976,0.0010449811,0.0001563179,0.0052960496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973683,0.0010777186,0.00011370895,0.0007120897,0.0004963847,0.00023192422],"domain_scores_gemma":[0.9938784,0.0031152305,0.0006729103,0.0015919949,0.0005369361,0.00020449418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032178177,0.00055159733,0.0018221064,0.001706472,0.0010185975,0.0023944345,0.0011315256,0.0021330968,0.0027737934],"category_scores_gemma":[0.012979895,0.00060749927,0.00087246316,0.0031716588,0.0016977077,0.0027880578,0.0024446226,0.0013210241,0.0010127366],"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":[0.0006699826,0.0001890727,0.013512136,0.00016883436,0.00007519727,0.00031852315,0.0006207013,0.4511541,0.014784726,0.06088653,0.0055412343,0.45207897],"study_design_scores_gemma":[0.000039009887,0.00012409169,0.005079663,0.00003586203,0.000028552411,0.00030928734,0.00023228572,0.8771562,0.014897623,0.09517669,0.006877422,0.000043337062],"about_ca_topic_score_codex":0.0014631093,"about_ca_topic_score_gemma":0.001551437,"teacher_disagreement_score":0.0032178177,"about_ca_system_score_codex":0.00073370396,"about_ca_system_score_gemma":0.0011653018,"threshold_uncertainty_score":0.017017663},"labels":[],"label_agreement":null},{"id":"W2165730354","doi":"10.1016/s1701-2163(16)34423-1","title":"Plus le temps file, plus les articles s’empilent","year":2010,"lang":"fr","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SOAP; Computer science; Cluster analysis; Hypertext Transfer Protocol; XML; Huffman coding; Data mining; Information retrieval; Computer network; World Wide Web; Data compression; The Internet; Algorithm; Artificial intelligence","score_opus":0.018991436203347464,"score_gpt":0.2254253721465898,"score_spread":0.20643393594324233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165730354","genre_codex":"dataset","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010340905,0.002464887,0.018029075,0.030426491,0.0428133,0.00081533403,0.47551426,0.047510784,0.372085],"genre_scores_gemma":[0.037016172,0.0021386377,0.02450617,0.0051364643,0.011880934,0.0007542276,0.17468128,0.01881799,0.72506815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890554,0.00010478016,0.00011006481,0.00013377823,0.0006216963,0.00012413925],"domain_scores_gemma":[0.98520076,0.005029926,0.0007919643,0.0022262551,0.005703821,0.0010472558],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008956596,0.0009778873,0.0008754819,0.0051046233,0.00092807267,0.0045658667,0.00086359546,0.0014431464,0.62237686],"category_scores_gemma":[0.021078391,0.0007134441,0.00076640456,0.004557347,0.00058991736,0.0022820397,0.0017210026,0.001672779,0.39921874],"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":[0.0002282663,0.000032103562,0.000372077,0.00014459457,0.000010701273,0.00009773406,0.000019596124,0.000174736,0.0007326735,0.0009013809,0.9538962,0.043389894],"study_design_scores_gemma":[0.00017615387,0.00005843019,0.002212788,0.0001879393,0.000012950533,0.0003395309,0.000100817364,0.0011472706,0.0028916341,0.0019599076,0.99087614,0.000036394],"about_ca_topic_score_codex":0.0044511976,"about_ca_topic_score_gemma":0.0046935226,"teacher_disagreement_score":0.62237686,"about_ca_system_score_codex":0.0011074919,"about_ca_system_score_gemma":0.0015398521,"threshold_uncertainty_score":0.5386336},"labels":[],"label_agreement":null},{"id":"W2166712818","doi":"10.1109/sccc.2005.1587868","title":"Parallel Evolution Strategy for Protein Threading","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Threading (protein sequence); Computer science; Protein structure prediction; Multithreading; Parallel computing; Sequence (biology); Set (abstract data type); Protein structure; Algorithm; Biology; Thread (computing); Programming language","score_opus":0.024118676540630296,"score_gpt":0.2598037252623769,"score_spread":0.2356850487217466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166712818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06421647,0.00041746226,0.92543066,0.00041899807,0.000097282464,0.00010936166,0.0000412182,0.0005921515,0.008676313],"genre_scores_gemma":[0.51583165,0.00043638793,0.4744344,0.0002355087,0.00005357353,0.00033719788,0.0001373143,0.00017669598,0.0083573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967194,0.00008433974,0.000019309398,0.00005198742,0.00013092153,0.000041445892],"domain_scores_gemma":[0.9996779,0.0001146545,0.000025422574,0.00005566751,0.00009843932,0.000027974784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005207788,0.00042713358,0.00060240895,0.00050251774,0.0005490138,0.00044381944,0.0007779399,0.00057336903,0.0013857676],"category_scores_gemma":[0.0010716164,0.00021339969,0.00035784254,0.0004956573,0.0005929518,0.0006839292,0.0007013515,0.0007023019,0.00026776068],"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":[0.00027176368,0.0002673963,0.0013933979,0.00011391355,0.00008445484,0.00035908216,0.00018607169,0.5612894,0.047663957,0.18368049,0.004328564,0.20036153],"study_design_scores_gemma":[0.00006230771,0.00004768404,0.00012110095,0.0000030071262,0.00001224109,0.00006849934,0.000010369724,0.9692551,0.0040303324,0.023585325,0.002795458,0.000008636938],"about_ca_topic_score_codex":0.0016704092,"about_ca_topic_score_gemma":0.0012273279,"teacher_disagreement_score":0.0016704092,"about_ca_system_score_codex":0.00067746406,"about_ca_system_score_gemma":0.00071723404,"threshold_uncertainty_score":0.0049153566},"labels":[],"label_agreement":null},{"id":"W2167155938","doi":"10.1101/gr.094607.109","title":"JBrowse: A next-generation genome browser","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":776,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"JavaScript; Upload; Computer science; Web server; Genome; Genome browser; Annotation; Zoom; Panning (audio); Biology; Rendering (computer graphics); Web browser; World Wide Web; The Internet; Genomics; Genetics; Artificial intelligence","score_opus":0.20852398952379084,"score_gpt":0.37443061079622836,"score_spread":0.16590662127243752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167155938","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057833735,0.0018932376,0.7451709,0.0007279731,0.0004948317,0.00017302291,0.01368783,0.21938922,0.012679554],"genre_scores_gemma":[0.026299424,0.0025096235,0.8671907,0.00071765657,0.0001214118,0.00039554783,0.05297352,0.026445419,0.023346575],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929607,0.00007395936,0.000050776773,0.00011904315,0.00039710445,0.00006301326],"domain_scores_gemma":[0.9988624,0.00032644966,0.00006283149,0.00025486609,0.00033554016,0.00015790081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001510609,0.0008037914,0.0006523883,0.0014496288,0.00059073913,0.002097674,0.0024619878,0.0012064403,0.01744792],"category_scores_gemma":[0.0035600387,0.00097197975,0.0008006937,0.0012503285,0.00031231524,0.0025188997,0.0015128907,0.0022852763,0.014037891],"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":[0.0005904399,0.0002641205,0.0026830027,0.0009042242,0.00014798419,0.0005636583,0.00052911753,0.005866037,0.07081655,0.023745472,0.4246746,0.4692148],"study_design_scores_gemma":[0.00011885935,0.00005261862,0.0013741306,0.00012507025,0.000044132914,0.0010063907,0.00009505493,0.034333248,0.04498181,0.012332902,0.9053959,0.00013995255],"about_ca_topic_score_codex":0.0049705724,"about_ca_topic_score_gemma":0.008918373,"teacher_disagreement_score":0.01744792,"about_ca_system_score_codex":0.0004862517,"about_ca_system_score_gemma":0.0013376189,"threshold_uncertainty_score":0.0583691},"labels":[],"label_agreement":null},{"id":"W2167200109","doi":"10.1109/dcc.2010.67","title":"Optimum String Match Choices in LZSS","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"String (physics); Computer science; Set (abstract data type); Compression (physics); Data compression; String searching algorithm; Algorithm; Greedy algorithm; Compression ratio; Mathematics; Artificial intelligence; Engineering; Pattern matching","score_opus":0.009385781601101092,"score_gpt":0.24953367432161827,"score_spread":0.24014789272051718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167200109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07825129,0.0015857164,0.9002277,0.0004925096,0.000115665825,0.00029370186,0.00060141186,0.0036621715,0.014769863],"genre_scores_gemma":[0.2945114,0.0007490076,0.6929526,0.0002617845,0.00011551659,0.0004252778,0.0011780028,0.0007761658,0.009030335],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968058,0.00084435183,0.0003076245,0.00035265842,0.0013918539,0.00029778705],"domain_scores_gemma":[0.9976411,0.001123434,0.00019072814,0.00056720315,0.0003956074,0.000082030914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017578037,0.00076072715,0.0011917419,0.0023430923,0.0012670887,0.0019913039,0.0015846308,0.0015422866,0.009171733],"category_scores_gemma":[0.00965644,0.00045881275,0.0006016613,0.0029138154,0.0015197139,0.0038255777,0.0024256974,0.0010212706,0.0039960286],"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":[0.0019607656,0.00017827435,0.0019229666,0.00047712875,0.000068753834,0.0003172745,0.0006678302,0.094052374,0.033296645,0.19633797,0.014131693,0.6565883],"study_design_scores_gemma":[0.00030428448,0.00054430997,0.0007896913,0.00022187235,0.00007740466,0.0008028339,0.0005300607,0.4900669,0.11291508,0.34475815,0.048846707,0.00014276229],"about_ca_topic_score_codex":0.0006720021,"about_ca_topic_score_gemma":0.0011954852,"teacher_disagreement_score":0.009171733,"about_ca_system_score_codex":0.0010766545,"about_ca_system_score_gemma":0.0013130883,"threshold_uncertainty_score":0.030682504},"labels":[],"label_agreement":null},{"id":"W2167671877","doi":"10.1109/cec.2006.1688598","title":"Protein Threading using Parallel Evolution Strategy","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Threading (protein sequence); Computer science; Parallel computing; Protein structure prediction; Multithreading; Sequence (biology); Set (abstract data type); Protein structure; Biology; Thread (computing)","score_opus":0.025296278262436335,"score_gpt":0.25447115520093583,"score_spread":0.2291748769384995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167671877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08488296,0.0006242254,0.90459275,0.00040575952,0.00009455228,0.00014639559,0.0000421995,0.0009458589,0.008265339],"genre_scores_gemma":[0.59431565,0.0006045195,0.3985399,0.00018786026,0.00005571121,0.00037217786,0.00013358066,0.00017229936,0.00561841],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996282,0.000110045105,0.000020528165,0.000060726794,0.00013821413,0.00004228967],"domain_scores_gemma":[0.9995907,0.0001462153,0.000037273112,0.00008191265,0.00010655675,0.000037329817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007627604,0.00043360525,0.00085867714,0.00056179165,0.00061393925,0.0006373713,0.0009057545,0.000732137,0.0012677901],"category_scores_gemma":[0.0011767896,0.0002558022,0.00046101175,0.0006400147,0.00061558007,0.00083542895,0.00068402407,0.0006746343,0.00026869794],"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":[0.0002619637,0.00021856306,0.0017536121,0.00015102563,0.00012461914,0.00035428477,0.0001641226,0.6269897,0.04350553,0.15215035,0.0032202594,0.17110594],"study_design_scores_gemma":[0.00007074643,0.000047127454,0.00015471935,0.0000035568803,0.000013886442,0.00006576456,0.000008476816,0.9652165,0.0037724755,0.02856888,0.0020683252,0.000009467653],"about_ca_topic_score_codex":0.0015935942,"about_ca_topic_score_gemma":0.0010411702,"teacher_disagreement_score":0.0015935942,"about_ca_system_score_codex":0.00074120535,"about_ca_system_score_gemma":0.00068939995,"threshold_uncertainty_score":0.0053777695},"labels":[],"label_agreement":null},{"id":"W2167806346","doi":"10.1145/1508244.1508283","title":"Architectural support for SWAR text processing with parallel bit streams","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Computer science; SIMD; Operand; Instruction set; Parallel computing; Set (abstract data type); Parsing; Stream processing; Regular expression; Computer architecture; Programming language; Computer hardware","score_opus":0.01219964360160559,"score_gpt":0.25126317458021025,"score_spread":0.23906353097860467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167806346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14976871,0.00044461223,0.8081632,0.0004607511,0.00015078184,0.00016016608,0.00025097077,0.011359056,0.02924181],"genre_scores_gemma":[0.60649264,0.000646872,0.37650272,0.00044708845,0.00013480593,0.0002460184,0.0010391391,0.00075031695,0.013740305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997578,0.00003627961,0.000039628212,0.000034290457,0.00010211458,0.000029743687],"domain_scores_gemma":[0.99925596,0.00019332487,0.00008245154,0.00023876764,0.00019807032,0.000031350723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025381037,0.00038677067,0.00030269392,0.00058249565,0.00039161168,0.00093721505,0.0013169151,0.00031003388,0.004834381],"category_scores_gemma":[0.0012388616,0.000322101,0.0003646314,0.00067609124,0.00037249865,0.0015412978,0.00066804147,0.000862008,0.0017212394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071842247,0.0003208651,0.0039017845,0.00064323563,0.00007938005,0.0007817006,0.00045384225,0.053589247,0.3759937,0.16070022,0.011657156,0.3911606],"study_design_scores_gemma":[0.00015246621,0.0007227056,0.0014688328,0.00008504236,0.00011884311,0.0010010157,0.00013341467,0.5075096,0.35990715,0.058010492,0.07081307,0.000077363446],"about_ca_topic_score_codex":0.0003889891,"about_ca_topic_score_gemma":0.0012217405,"teacher_disagreement_score":0.004834381,"about_ca_system_score_codex":0.00033112994,"about_ca_system_score_gemma":0.0006731373,"threshold_uncertainty_score":0.016172647},"labels":[],"label_agreement":null},{"id":"W2168304982","doi":"10.14288/1.0167069","title":"Linear and parallel learning of Markov random fields","year":2014,"lang":"en","type":"article","venue":"Open Collections","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Embarrassingly parallel; Markov chain; Computer science; Bounded function; Log-linear model; Markov process; Mathematics; Degree (music); Markov model; Algorithm; Random field; Theoretical computer science; Parallel algorithm; Linear model; Statistics; Machine learning","score_opus":0.012332862284641928,"score_gpt":0.2532988352024782,"score_spread":0.24096597291783628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168304982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038824975,0.00009197735,0.9950599,0.00012697392,0.000019528612,0.000022633245,0.000025160129,0.0002370206,0.00053423736],"genre_scores_gemma":[0.30233875,0.00037039808,0.69107187,0.0003639305,0.00019656746,0.00031780355,0.00037297537,0.0003711636,0.004596645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773633,0.0008825323,0.00010932101,0.00064964005,0.00044867373,0.00017354738],"domain_scores_gemma":[0.99064785,0.0068022585,0.00058541686,0.0011876571,0.00059098256,0.00018583256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044415914,0.0010590365,0.0014540552,0.0009616265,0.0006843347,0.0017870935,0.0028810673,0.0015240287,0.0030143317],"category_scores_gemma":[0.020478183,0.00088148314,0.0013562475,0.0008845933,0.0022616142,0.004556222,0.003103061,0.0028780797,0.0007664308],"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":[0.00011737137,0.000057318277,0.0010563489,0.00010464115,0.00006508877,0.000077468394,0.00012303675,0.743087,0.0011967473,0.15910536,0.0012818206,0.09372781],"study_design_scores_gemma":[0.000009012035,0.000011298279,0.00004196615,0.0000050410436,0.0000035589403,0.000016865337,0.0000057699745,0.93249506,0.00036996734,0.06665058,0.00038516347,0.000005655978],"about_ca_topic_score_codex":0.0028881223,"about_ca_topic_score_gemma":0.0027782498,"teacher_disagreement_score":0.0044415914,"about_ca_system_score_codex":0.0016535288,"about_ca_system_score_gemma":0.0015364351,"threshold_uncertainty_score":0.023489654},"labels":[],"label_agreement":null},{"id":"W2168838823","doi":"10.5555/1931390.1931428","title":"Using Markov chains to exploit word relationships in information retrieval","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université de Montréal","funders":"","keywords":"Exploit; Query expansion; Computer science; Markov chain; Process (computing); Information retrieval; Term (time); Word (group theory); Markov process; Natural language processing; Mathematics; Machine learning; Statistics; Programming language","score_opus":0.06257794759449921,"score_gpt":0.2945246859432514,"score_spread":0.23194673834875218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168838823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03698978,0.0013770572,0.95880985,0.00034098423,0.00004185359,0.00010427988,0.00010326019,0.0008096568,0.0014233247],"genre_scores_gemma":[0.5274222,0.0027996674,0.46356276,0.0003468473,0.00021674133,0.00036929187,0.00076859904,0.00017267499,0.0043412643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990175,0.0004578952,0.000060471535,0.00015428405,0.00023576358,0.00007407976],"domain_scores_gemma":[0.9956671,0.0035757613,0.00022393491,0.00028351985,0.00019324309,0.000056390054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013654986,0.00054845907,0.0006441161,0.0016054796,0.0004440937,0.00075045234,0.00061912666,0.000707667,0.001463411],"category_scores_gemma":[0.0061750086,0.0004984577,0.00059011194,0.0020268634,0.00073539827,0.0031891977,0.00090883294,0.0010551814,0.0005186487],"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":[0.00051286595,0.0002597217,0.0030250377,0.00026715372,0.00014562019,0.00033355592,0.00048294186,0.37265834,0.018757032,0.05821844,0.0046140226,0.5407252],"study_design_scores_gemma":[0.000044236866,0.00006679803,0.0004151868,0.000021567677,0.00003068125,0.000118369884,0.000023827817,0.95796543,0.0036164387,0.03560898,0.0020590886,0.00002942455],"about_ca_topic_score_codex":0.0044449475,"about_ca_topic_score_gemma":0.004785601,"teacher_disagreement_score":0.0044449475,"about_ca_system_score_codex":0.0006326426,"about_ca_system_score_gemma":0.00088419515,"threshold_uncertainty_score":0.008838177},"labels":[],"label_agreement":null},{"id":"W2168961888","doi":"10.1145/1248377.1248436","title":"Using SIMD registers and instructions to enable instruction-level parallelism in sorting algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Alberta","funders":"","keywords":"Computer science; SIMD; Parallel computing; Parallelism (grammar); Sorting; Instruction-level parallelism; Sorting algorithm; Instruction set; Computer architecture; Algorithm","score_opus":0.0820414321601886,"score_gpt":0.31952960010779585,"score_spread":0.23748816794760724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168961888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09403198,0.0018217851,0.87522876,0.0003632187,0.0001451686,0.00017122993,0.00027552177,0.010788076,0.017174317],"genre_scores_gemma":[0.47981107,0.0008997684,0.511434,0.0004918269,0.00009285563,0.00021329877,0.0005401188,0.00079914567,0.0057179374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995396,0.00009649481,0.00004459733,0.00006753863,0.00019289662,0.00005892785],"domain_scores_gemma":[0.9992292,0.0002154039,0.000114904644,0.00030543734,0.00011485578,0.000020180736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046932267,0.0005245844,0.00030618382,0.00089727435,0.000502604,0.00077122933,0.0014930079,0.00036730108,0.0032570797],"category_scores_gemma":[0.0016839787,0.0004028426,0.00040756416,0.0019771766,0.0007915772,0.0016795149,0.0009920587,0.0008183776,0.0012718708],"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":[0.0011121973,0.0001753799,0.0036581727,0.00043011844,0.0000771722,0.00031429422,0.00046557482,0.07757432,0.10899393,0.15913944,0.010603894,0.63745546],"study_design_scores_gemma":[0.0003992702,0.0011320534,0.002463953,0.00015516218,0.00013085145,0.0011080564,0.00014249186,0.3283503,0.4224213,0.091691844,0.1518403,0.00016435614],"about_ca_topic_score_codex":0.0007259505,"about_ca_topic_score_gemma":0.0011416309,"teacher_disagreement_score":0.0032570797,"about_ca_system_score_codex":0.0005313167,"about_ca_system_score_gemma":0.0006634715,"threshold_uncertainty_score":0.0108959675},"labels":[],"label_agreement":null},{"id":"W2169348983","doi":"10.4230/lipics.stacs.2014.149","title":"Palindrome Recognition In The Streaming Model","year":2014,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"","keywords":"Substring; Palindrome; String (physics); Mathematics; Sublinear function; Combinatorics; Square root; Algorithm; Discrete mathematics; Computer science; Data structure","score_opus":0.02455233136888209,"score_gpt":0.25154909241749424,"score_spread":0.22699676104861213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169348983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047973353,0.00037145248,0.9450714,0.00042853114,0.000057370686,0.0001161551,0.00043231412,0.0021833829,0.0033659781],"genre_scores_gemma":[0.43655777,0.00057164184,0.5495037,0.0003112694,0.00014711931,0.0003389955,0.0018869904,0.0004079718,0.0102746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885535,0.00022639494,0.00010090884,0.00038164,0.000278051,0.00015776527],"domain_scores_gemma":[0.9970855,0.0012755914,0.00025673228,0.0010297575,0.00025502537,0.0000973414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010450045,0.000620987,0.0012150417,0.0006309274,0.0007386351,0.0015408025,0.0025517778,0.0015989168,0.004248059],"category_scores_gemma":[0.004465793,0.0004833724,0.0009577158,0.0013472935,0.0012429375,0.0048976704,0.0014425782,0.0014761398,0.0015181574],"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":[0.0010563008,0.0003877155,0.0023404057,0.00040720953,0.000072152085,0.0008361201,0.00037153522,0.33090797,0.03683178,0.39254728,0.0107672345,0.22347431],"study_design_scores_gemma":[0.0000536006,0.00009369202,0.00021502902,0.000018125631,0.00001498046,0.00036674459,0.00007888493,0.7911986,0.00914888,0.19492842,0.0038527278,0.000030225712],"about_ca_topic_score_codex":0.0034197906,"about_ca_topic_score_gemma":0.0031784049,"teacher_disagreement_score":0.004248059,"about_ca_system_score_codex":0.0012663642,"about_ca_system_score_gemma":0.0014642292,"threshold_uncertainty_score":0.014211178},"labels":[],"label_agreement":null},{"id":"W2169465650","doi":"10.1007/11880561_31","title":"A New Algorithm for Fast All-Against-All Substring Matching","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Substring; Algorithm; Matching (statistics); Computer science; Graph; String searching algorithm; Mathematics; Theoretical computer science; Pattern matching; Data structure; Artificial intelligence; Statistics","score_opus":0.018427564062573225,"score_gpt":0.2523865924585631,"score_spread":0.23395902839598987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169465650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005411331,0.00070703746,0.9800544,0.00023243554,0.000490592,0.0002554164,0.000444604,0.008629891,0.0037741368],"genre_scores_gemma":[0.024492672,0.00032154197,0.96382517,0.00022084867,0.00017596009,0.00023645409,0.00163919,0.00077669736,0.008311406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973157,0.00025434355,0.00028672453,0.0007064904,0.0011951174,0.00024158445],"domain_scores_gemma":[0.99749184,0.0006018998,0.00013388123,0.00095417025,0.0006888142,0.00012936018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013513512,0.0022147705,0.0028330914,0.00362113,0.0018741657,0.002697002,0.0045737927,0.002393701,0.01630316],"category_scores_gemma":[0.0046175276,0.0010987923,0.0015283615,0.0051540383,0.0010099823,0.0066491705,0.0048745526,0.0022707267,0.0103855105],"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":[0.00052476383,0.00019383148,0.00038408788,0.00026059605,0.000089473935,0.00013592848,0.000103893384,0.007313495,0.025525017,0.012069834,0.025819354,0.9275797],"study_design_scores_gemma":[0.0006883081,0.0008797668,0.0015029177,0.0001309325,0.00037380712,0.0031237716,0.00034176267,0.5925707,0.110011145,0.13786644,0.15224847,0.0002619723],"about_ca_topic_score_codex":0.0017080861,"about_ca_topic_score_gemma":0.0034971102,"teacher_disagreement_score":0.01630316,"about_ca_system_score_codex":0.0010447014,"about_ca_system_score_gemma":0.002212202,"threshold_uncertainty_score":0.0545395},"labels":[],"label_agreement":null},{"id":"W2169586192","doi":"10.1109/isit.2001.935941","title":"Efficient universal lossless data compression algorithms based on a greedy context-dependent sequential grammar transform","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lossless compression; Computer science; Data compression; Compression (physics); Context (archaeology); Algorithm; Theoretical computer science; Context model; Artificial intelligence","score_opus":0.05470251236435772,"score_gpt":0.261412816170819,"score_spread":0.2067103038064613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169586192","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020214465,0.000394463,0.97712654,0.00017418446,0.00005064162,0.00005800412,0.000058410904,0.0012513839,0.00067191274],"genre_scores_gemma":[0.30079535,0.00054674555,0.69547844,0.00034267557,0.00011234469,0.00021564205,0.0004489059,0.00020821404,0.0018516476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990995,0.00020715444,0.00007126308,0.00016065144,0.0003774051,0.00008405768],"domain_scores_gemma":[0.9988746,0.0006269264,0.000083574334,0.00023283115,0.00014195364,0.00004008032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011046618,0.00081805483,0.00118178,0.0012130348,0.0004921096,0.0008700279,0.001377196,0.0010074539,0.0010673444],"category_scores_gemma":[0.004442492,0.00035730514,0.00053860876,0.0017190482,0.0013172796,0.0017866556,0.001859586,0.0012002643,0.000705947],"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":[0.00045876618,0.00016385698,0.00074944354,0.00016366177,0.00006776501,0.000361904,0.00026324685,0.24307835,0.033062413,0.06781836,0.0057337545,0.64807844],"study_design_scores_gemma":[0.000050984618,0.00008211579,0.0001222134,0.000011502984,0.000014239948,0.00022743388,0.000027847966,0.94945914,0.01170102,0.036844168,0.0014451793,0.000014239582],"about_ca_topic_score_codex":0.0011084958,"about_ca_topic_score_gemma":0.0012936218,"teacher_disagreement_score":0.001377196,"about_ca_system_score_codex":0.0005401946,"about_ca_system_score_gemma":0.0010303137,"threshold_uncertainty_score":0.0058420897},"labels":[],"label_agreement":null},{"id":"W2169742131","doi":"10.1109/dcc.1996.488312","title":"Free energy coding","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Information Technology Research Centre","keywords":"Code word; Maximization; Computer science; Algorithm; Code (set theory); Parity-check matrix; Energy (signal processing); Source code; Coding (social sciences); Mathematics; Mathematical optimization; Decoding methods; Statistics","score_opus":0.023060895886557062,"score_gpt":0.20830306014456346,"score_spread":0.18524216425800638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169742131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048733423,0.0011107785,0.97973686,0.0009895414,0.0002510466,0.000051671148,0.0001341872,0.00016926492,0.012683295],"genre_scores_gemma":[0.34723365,0.0035034153,0.6175808,0.001320661,0.000669272,0.00047678011,0.0006065433,0.00041115403,0.028197749],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989236,0.0002917786,0.000051497515,0.00013206882,0.00050483766,0.000096336815],"domain_scores_gemma":[0.9982167,0.0009209416,0.00010239469,0.00045724376,0.00023891291,0.00006381875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011194907,0.00067187625,0.00084887876,0.0014789032,0.0007377853,0.0015796872,0.0016876527,0.0019865609,0.0051716496],"category_scores_gemma":[0.005691792,0.00035107913,0.0007251578,0.001519018,0.0018630923,0.0029009709,0.0022555904,0.00212345,0.0015043246],"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":[0.00003579626,0.000021288019,0.00012437439,0.00008203134,0.000022779672,0.0000835567,0.000069484384,0.06880558,0.0021641413,0.8716684,0.0034898268,0.053432707],"study_design_scores_gemma":[0.000016520387,0.000027757542,0.00008520313,0.000036485,0.000011656959,0.00012984207,0.000018748762,0.30967048,0.001905467,0.67500037,0.013065538,0.00003187697],"about_ca_topic_score_codex":0.0009899886,"about_ca_topic_score_gemma":0.00085955067,"teacher_disagreement_score":0.0051716496,"about_ca_system_score_codex":0.0008273433,"about_ca_system_score_gemma":0.0007772593,"threshold_uncertainty_score":0.017300904},"labels":[],"label_agreement":null},{"id":"W2169763171","doi":"10.1109/icassp.2011.5946841","title":"cROVER: Improving ROVER using automatic error detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Computer science; Word error rate; Trim; Word (group theory); Reduction (mathematics); Error detection and correction; Artificial intelligence; Speech recognition; Algorithm; Mathematics","score_opus":0.04782357021298726,"score_gpt":0.2495010374967477,"score_spread":0.20167746728376046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169763171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06857268,0.0014105682,0.89673287,0.00019753356,0.00020073593,0.00016325693,0.0001915463,0.029868659,0.0026620482],"genre_scores_gemma":[0.2076888,0.000567005,0.78010696,0.00035958804,0.00016025967,0.00012216145,0.0016118077,0.0018676037,0.0075158165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823123,0.00044460045,0.000098498334,0.00041753543,0.00068260316,0.00012561082],"domain_scores_gemma":[0.99775785,0.0007027199,0.00026401173,0.0006788512,0.0005401999,0.000056356323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017115673,0.0015157481,0.0014105015,0.0018347278,0.00051574677,0.0010787006,0.0018986063,0.0011628611,0.0029911948],"category_scores_gemma":[0.0050603678,0.00047914602,0.00053061015,0.00085011317,0.0006209388,0.0018236447,0.0014378964,0.0009596939,0.0030404138],"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":[0.00041471905,0.00014972675,0.0020996716,0.00014459672,0.00009303814,0.00013798317,0.00015634154,0.009840536,0.09220154,0.0012103287,0.00560923,0.8879424],"study_design_scores_gemma":[0.00022355214,0.001729691,0.007218933,0.00008260398,0.00026124585,0.0022898004,0.00027031914,0.47833157,0.449573,0.0028044202,0.05697879,0.00023611149],"about_ca_topic_score_codex":0.0016950971,"about_ca_topic_score_gemma":0.0035354127,"teacher_disagreement_score":0.0029911948,"about_ca_system_score_codex":0.00018704025,"about_ca_system_score_gemma":0.0005816097,"threshold_uncertainty_score":0.010006547},"labels":[],"label_agreement":null},{"id":"W2169875613","doi":"10.1109/isit.2001.935891","title":"Causal source coding of stationary sources with high resolution","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Source code; Encoder; Mathematics; Entropy (arrow of time); Algorithm; Quantization (signal processing); Decoding methods; Rate–distortion theory; Entropy rate; Computer science; Applied mathematics; Binary entropy function; Data compression; Statistics; Physics; Principle of maximum entropy","score_opus":0.018201865983075893,"score_gpt":0.2123028342861345,"score_spread":0.19410096830305862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169875613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025893373,0.00044384453,0.96995395,0.00019532298,0.000029304161,0.000020107122,0.000075072545,0.0001756252,0.0032133248],"genre_scores_gemma":[0.74652135,0.0007803654,0.24805509,0.00015246659,0.00009667789,0.0000633985,0.00023410795,0.000057487545,0.004039111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939096,0.00019917343,0.00003040282,0.00007736515,0.00024238399,0.000059712213],"domain_scores_gemma":[0.9983026,0.00084525323,0.00023618968,0.00028966478,0.0002791764,0.00004700148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093060825,0.00034416447,0.00041943873,0.0006246745,0.00032716856,0.0006784768,0.0007314947,0.00061799766,0.0016271307],"category_scores_gemma":[0.004946305,0.00028461398,0.00029953723,0.0009295226,0.0010184326,0.0015819368,0.0010871497,0.00081770524,0.0003366744],"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":[0.00027297283,0.000040871353,0.0005877361,0.00012574792,0.000031425592,0.00024107959,0.00016181868,0.33880502,0.028494688,0.5104941,0.0018790452,0.11886543],"study_design_scores_gemma":[0.000024953866,0.00004388353,0.00023831897,0.00001553017,0.000011048759,0.00012884932,0.000020612331,0.86164,0.0147710135,0.12053991,0.0025449446,0.00002097782],"about_ca_topic_score_codex":0.0008897129,"about_ca_topic_score_gemma":0.0008823591,"teacher_disagreement_score":0.0016271307,"about_ca_system_score_codex":0.0007110955,"about_ca_system_score_gemma":0.0005715779,"threshold_uncertainty_score":0.005443275},"labels":[],"label_agreement":null},{"id":"W2170731137","doi":"10.1109/cjece.2008.4621791","title":"Hardware acceleration for similarity computations of feature vectors","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Field-programmable gate array; Hardware acceleration; Software; Computation; Hardware architecture; Similarity (geometry); Feature (linguistics); Computer hardware; Reuse; Parallel computing; Computer architecture; Embedded system; Set (abstract data type); Artificial intelligence; Algorithm; Engineering; Operating system; Programming language","score_opus":0.0145728566659455,"score_gpt":0.20006668160474717,"score_spread":0.18549382493880168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170731137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1450975,0.0007025462,0.8437783,0.00013380469,0.00014314191,0.0001198433,0.00012719388,0.0058546495,0.004042857],"genre_scores_gemma":[0.54397833,0.00035140032,0.4516301,0.0000976261,0.000050720206,0.00012466994,0.0004400943,0.00009288712,0.0032342074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971455,0.000040768507,0.000021919044,0.00004488134,0.00013815371,0.000039696057],"domain_scores_gemma":[0.99950814,0.0001839804,0.000046244488,0.000113161695,0.00012969488,0.000018847048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025031227,0.0005256041,0.00035868038,0.0006951824,0.00021783894,0.00048489045,0.00089397875,0.00033786264,0.0036926284],"category_scores_gemma":[0.0011532832,0.00021767763,0.0003129516,0.00091707625,0.0001820912,0.00061414996,0.0003970908,0.00039500996,0.001154918],"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":[0.0007758763,0.00014399142,0.0020546995,0.00025559956,0.00008045075,0.0003094764,0.0000937695,0.031579442,0.21750809,0.0065983864,0.0044165347,0.7361837],"study_design_scores_gemma":[0.00017487834,0.0010611101,0.005360944,0.00003407873,0.00007933176,0.00084492966,0.00007076419,0.74623877,0.22599684,0.0050791455,0.015008855,0.000050322473],"about_ca_topic_score_codex":0.0013892998,"about_ca_topic_score_gemma":0.0016926426,"teacher_disagreement_score":0.0036926284,"about_ca_system_score_codex":0.000324828,"about_ca_system_score_gemma":0.000465106,"threshold_uncertainty_score":0.012353063},"labels":[],"label_agreement":null},{"id":"W2171446221","doi":"10.1109/is.2008.4670501","title":"Using suffix trees for periodicity detection in time series databases","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Suffix; Pruning; Suffix tree; Computer science; Series (stratigraphy); Time series; Data mining; Symbol (formal); Sequence (biology); Dynamic time warping; Data structure; Algorithm; Generalized suffix tree; Pattern recognition (psychology); Artificial intelligence; Machine learning","score_opus":0.06277645949789548,"score_gpt":0.28478160332807934,"score_spread":0.22200514383018385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171446221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058656342,0.0009120372,0.9365681,0.00018776114,0.00008442244,0.0000966388,0.00047403763,0.0020202566,0.0010004321],"genre_scores_gemma":[0.2198467,0.0008087705,0.7767609,0.000098190074,0.00011037807,0.0001368062,0.0014459601,0.00014648386,0.0006458245],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984113,0.0004985176,0.00029257667,0.00025788962,0.0004715164,0.00006814717],"domain_scores_gemma":[0.9928201,0.0043916516,0.0007730733,0.000994363,0.00091440656,0.0001064466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022558083,0.0005429969,0.00072944036,0.0031585116,0.0006949039,0.0011488572,0.0007810962,0.0008352351,0.0009875087],"category_scores_gemma":[0.011991641,0.00030970274,0.0004972277,0.004942474,0.0004200155,0.0021046074,0.00058375817,0.0006664971,0.0008019025],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004118656,0.00015146777,0.007337518,0.00031957988,0.00012885637,0.0004984929,0.00036936087,0.036309805,0.033806235,0.01019469,0.0041586007,0.90631366],"study_design_scores_gemma":[0.000077762415,0.00031168634,0.0042586727,0.00010279334,0.00010087823,0.0015255352,0.0002613026,0.89766276,0.04748557,0.035322513,0.0128143225,0.000076221935],"about_ca_topic_score_codex":0.0006107678,"about_ca_topic_score_gemma":0.00070687965,"teacher_disagreement_score":0.0031585116,"about_ca_system_score_codex":0.00023409163,"about_ca_system_score_gemma":0.0007034068,"threshold_uncertainty_score":0.011929989},"labels":[],"label_agreement":null},{"id":"W2171866929","doi":"10.1017/s0960129515000134","title":"Fast circular dictionary-matching algorithm","year":2015,"lang":"en","type":"article","venue":"Mathematical Structures in Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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":"String searching algorithm; Matching (statistics); Computation; Algorithm; String (physics); Pattern matching; Space (punctuation); Mathematics; Combinatorics; Approximate string matching; Computer science; Discrete mathematics; Artificial intelligence; Statistics","score_opus":0.02040349900912089,"score_gpt":0.2687050296310084,"score_spread":0.2483015306218875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171866929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017778292,0.00041755626,0.975575,0.00014963029,0.000115300594,0.00011807023,0.00033037216,0.0026092813,0.002906424],"genre_scores_gemma":[0.13186575,0.00027318063,0.85841006,0.00019494278,0.000071889786,0.0001833588,0.001654634,0.00026329467,0.007082878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870026,0.00012598591,0.00013710052,0.00037041717,0.0004687203,0.00019745938],"domain_scores_gemma":[0.9988153,0.00021536603,0.000100377874,0.00040583182,0.00040593705,0.000057254983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006332675,0.00061386434,0.0012438045,0.001690329,0.0010523018,0.0012263352,0.0017265544,0.0013237565,0.009041062],"category_scores_gemma":[0.0031723313,0.0003950075,0.00066480617,0.002612029,0.0006071407,0.0020165136,0.0020021705,0.00073203334,0.0049456055],"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":[0.00074522843,0.00015727685,0.0016298721,0.00023309386,0.00006469167,0.00024756364,0.00018222889,0.04857311,0.033944737,0.021993432,0.018371655,0.87385714],"study_design_scores_gemma":[0.00014161947,0.00019614086,0.0008286127,0.00002986947,0.000043572036,0.00090072537,0.00013609206,0.9020497,0.049878754,0.0226577,0.023085862,0.00005133835],"about_ca_topic_score_codex":0.0023606643,"about_ca_topic_score_gemma":0.0028590928,"teacher_disagreement_score":0.009041062,"about_ca_system_score_codex":0.00066534587,"about_ca_system_score_gemma":0.0021006332,"threshold_uncertainty_score":0.030245423},"labels":[],"label_agreement":null},{"id":"W2171906598","doi":"10.1145/1067309.1067322","title":"Algorithmic foundations of the internet","year":2005,"lang":"en","type":"article","venue":"ACM SIGACT News","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"The Internet; Computer science; Field (mathematics); Sample (material); Data science; Theoretical computer science; World Wide Web; Mathematics","score_opus":0.022439356031763835,"score_gpt":0.26995108654818956,"score_spread":0.24751173051642572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171906598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043652836,0.016414668,0.5919115,0.023199892,0.0010576175,0.00011822212,0.00072806445,0.00045182847,0.32246533],"genre_scores_gemma":[0.78745043,0.026086424,0.14277329,0.0035084977,0.0041286275,0.00047547897,0.0014182103,0.00024715363,0.033911932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829656,0.00055956456,0.00009369776,0.00026549684,0.0006037859,0.00018088229],"domain_scores_gemma":[0.996986,0.0018278562,0.00018086942,0.00045655825,0.00040417782,0.0001445201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015628441,0.0004217753,0.00051978027,0.0025724093,0.002108918,0.0047608675,0.001041317,0.0019473687,0.009862914],"category_scores_gemma":[0.005815632,0.00042833888,0.00083207793,0.0024226925,0.0041617975,0.010031692,0.002857595,0.0031269793,0.0017748163],"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":[0.0000020724017,0.0000042640277,0.00005194273,0.000017776394,0.0000024879707,0.000011241805,0.000026018008,0.0010908996,0.000028305512,0.994578,0.0010290995,0.0031577805],"study_design_scores_gemma":[0.00000282333,0.0000024610472,0.000042013267,0.000018241979,0.0000020782263,0.000027014847,0.000024879271,0.003527605,0.000034633937,0.9857734,0.010541546,0.0000032519176],"about_ca_topic_score_codex":0.0014155944,"about_ca_topic_score_gemma":0.0010494072,"teacher_disagreement_score":0.009862914,"about_ca_system_score_codex":0.001451402,"about_ca_system_score_gemma":0.001338131,"threshold_uncertainty_score":0.032994688},"labels":[],"label_agreement":null},{"id":"W2176225957","doi":"10.1007/978-3-319-07566-2_25","title":"On Hardness of Several String Indexing Problems","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; String (physics); Combinatorics; Search engine indexing; Upper and lower bounds; Pattern matching; Linear space; Connection (principal bundle); Space (punctuation); Integer (computer science); String searching algorithm; Simple (philosophy); Mathematics; Discrete mathematics; Data structure; Computer science; Information retrieval; Artificial intelligence","score_opus":0.016802981142046387,"score_gpt":0.23483356280543555,"score_spread":0.21803058166338915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176225957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11518323,0.02361926,0.41457278,0.06864855,0.003359857,0.00050067285,0.0053944774,0.002376143,0.3663451],"genre_scores_gemma":[0.65739244,0.021859163,0.18407616,0.009480539,0.01229873,0.0013195857,0.011001231,0.0027142751,0.09985785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936998,0.0015694448,0.00039388894,0.0012808958,0.0022530043,0.0008030608],"domain_scores_gemma":[0.9608692,0.033625185,0.000911608,0.0028522832,0.0009764819,0.000765218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004408947,0.002345829,0.004143671,0.00349837,0.0048073884,0.00933856,0.0060713673,0.0054991753,0.025947992],"category_scores_gemma":[0.024532706,0.0019364606,0.0047385544,0.008493785,0.008724072,0.02787543,0.0068399347,0.019468224,0.003457867],"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":[0.00046690335,0.00029208386,0.0005398903,0.0010301669,0.000104153296,0.00019800443,0.0004915475,0.013719847,0.0011511992,0.8630695,0.052544463,0.06639216],"study_design_scores_gemma":[0.000057974594,0.00002066974,0.00016527936,0.000060461487,0.00002908775,0.00010192708,0.00006139347,0.010106186,0.00032856214,0.9840561,0.004992763,0.000019588613],"about_ca_topic_score_codex":0.0018559756,"about_ca_topic_score_gemma":0.0015308377,"teacher_disagreement_score":0.025947992,"about_ca_system_score_codex":0.0056107654,"about_ca_system_score_gemma":0.0026600675,"threshold_uncertainty_score":0.08680469},"labels":[],"label_agreement":null},{"id":"W2176745125","doi":"10.1016/j.jda.2011.12.013","title":"Efficient chaining of seeds in ordered trees","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"","keywords":"Chaining; Extension (predicate logic); Combinatorics; Set (abstract data type); Computer science; Tree (set theory); Time complexity; Computational complexity theory; Mathematics; Forward chaining; Order (exchange); Constant (computer programming); Discrete mathematics; Theoretical computer science; Algorithm; Artificial intelligence; Expert system","score_opus":0.028365662946910574,"score_gpt":0.2556116409046778,"score_spread":0.22724597795776724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176745125","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15594904,0.000575463,0.8361914,0.00037775666,0.000131162,0.00019286352,0.00033103558,0.0012387339,0.0050125443],"genre_scores_gemma":[0.45141825,0.0004463389,0.5409073,0.0001275795,0.00008369932,0.00011846191,0.0009367584,0.00040860847,0.005552977],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991708,0.00021584368,0.0000693572,0.00012846367,0.00030594977,0.00010967401],"domain_scores_gemma":[0.99442166,0.0029244204,0.0003345622,0.0012588067,0.00068643613,0.0003740767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001006366,0.0004876886,0.0010859547,0.0015636323,0.0008123299,0.0013002588,0.0012478764,0.0010517582,0.0036971625],"category_scores_gemma":[0.007947642,0.0006484063,0.0005167331,0.0023374867,0.0010358138,0.0025500378,0.0020932127,0.0012374676,0.001057894],"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":[0.001641329,0.00042015113,0.0045689014,0.00057938125,0.00007711886,0.0008619939,0.0010501761,0.22489995,0.046227485,0.21021096,0.013253239,0.49620938],"study_design_scores_gemma":[0.00010814182,0.00022026576,0.0004001112,0.00006081568,0.000033706317,0.00024186943,0.00017299052,0.816148,0.017371811,0.16002752,0.0051895105,0.000025272015],"about_ca_topic_score_codex":0.0010137082,"about_ca_topic_score_gemma":0.0023078346,"teacher_disagreement_score":0.0036971625,"about_ca_system_score_codex":0.0006073007,"about_ca_system_score_gemma":0.0010333582,"threshold_uncertainty_score":0.012368202},"labels":[],"label_agreement":null},{"id":"W2178984881","doi":"10.1109/tit.2005.856948","title":"The Universality of Grammar-Based Codes for Sources With Countably Infinite Alphabets","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Mathematics; Alphabet; Combinatorics; Universality (dynamical systems); Discrete mathematics; Countable set; Lambda; Grammar; Physics; Linguistics","score_opus":0.008000919638424399,"score_gpt":0.2201732323105906,"score_spread":0.2121723126721662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178984881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41600654,0.0014061978,0.5786928,0.00035864522,0.000043605094,0.000045268414,0.00012860708,0.0008440337,0.002474324],"genre_scores_gemma":[0.9575151,0.00039257022,0.041022483,0.00010189661,0.00005500208,0.0000483102,0.00015246916,0.00009654979,0.0006155951],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975884,0.00060220016,0.00015553283,0.00042361062,0.00089838397,0.00033194703],"domain_scores_gemma":[0.96777225,0.02287841,0.0028387804,0.0035582047,0.002260303,0.0006921056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031183655,0.00062924053,0.0011285519,0.0011036757,0.00073716434,0.0011499467,0.0012445326,0.0010861766,0.00071143406],"category_scores_gemma":[0.0331465,0.00044158197,0.00045044525,0.0011195478,0.0024833772,0.0029820479,0.002139745,0.0011962218,0.00027849816],"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":[0.0008345458,0.000083621366,0.007826495,0.0002834067,0.0001548981,0.00057189097,0.0007690906,0.70682156,0.04369108,0.15552875,0.00094325497,0.08249135],"study_design_scores_gemma":[0.00002200746,0.00021583434,0.00091941847,0.000027073847,0.00004040078,0.00044839483,0.00006224298,0.9135169,0.024197534,0.05952787,0.0009748574,0.000047456393],"about_ca_topic_score_codex":0.00116737,"about_ca_topic_score_gemma":0.0008412111,"teacher_disagreement_score":0.0031183655,"about_ca_system_score_codex":0.0013102357,"about_ca_system_score_gemma":0.0012594309,"threshold_uncertainty_score":0.016491711},"labels":[],"label_agreement":null},{"id":"W2180616177","doi":"10.1016/j.jda.2011.12.017","title":"Skip lift: A probabilistic alternative to red–black trees","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Lift (data mining); Pointer (user interface); Computer science; Data structure; Combinatorics; Probabilistic logic; Algorithm; Mathematics; Discrete mathematics; Data mining; Artificial intelligence; Programming language","score_opus":0.03582305399091825,"score_gpt":0.27033341733777766,"score_spread":0.2345103633468594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180616177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012077898,0.00030939988,0.98175734,0.00038182657,0.00017656045,0.000057280897,0.00020804681,0.0012747566,0.0037568312],"genre_scores_gemma":[0.36611903,0.0006817306,0.6166944,0.00081677915,0.0006282889,0.00025175526,0.0009374874,0.00139937,0.012471255],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99817526,0.0004925533,0.00008011556,0.0002558842,0.0007626073,0.00023364407],"domain_scores_gemma":[0.99524456,0.0017136274,0.00020592091,0.0018720519,0.0006210308,0.00034276565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026052438,0.00075861835,0.001586283,0.0016185712,0.0014695283,0.0018191248,0.0023911053,0.0015239117,0.008731791],"category_scores_gemma":[0.011149369,0.00064015435,0.0011403343,0.0022915287,0.0014378267,0.003946329,0.005092461,0.003031028,0.0020068418],"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":[0.00131469,0.0002457925,0.0014291758,0.00020575235,0.00010573149,0.00025657113,0.00029142995,0.11950303,0.006044331,0.41210887,0.020451343,0.4380433],"study_design_scores_gemma":[0.00007663746,0.00010593613,0.0003030258,0.000043644683,0.000045151508,0.00016622251,0.000041762818,0.58282423,0.0022931555,0.40469852,0.009363947,0.000037801525],"about_ca_topic_score_codex":0.0015534697,"about_ca_topic_score_gemma":0.002687845,"teacher_disagreement_score":0.008731791,"about_ca_system_score_codex":0.0006257094,"about_ca_system_score_gemma":0.0016254034,"threshold_uncertainty_score":0.029210746},"labels":[],"label_agreement":null},{"id":"W2180828828","doi":"10.1016/j.tcs.2013.05.037","title":"On approximating string selection problems with outliers","year":2013,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Parameterized complexity; String (physics); Hamming distance; Combinatorics; Mathematics; Polynomial-time approximation scheme; Time complexity; Outlier; Edit distance; Selection (genetic algorithm); Approximation algorithm; Set (abstract data type); Randomized algorithm; Discrete mathematics; Algorithm; Computer science; Artificial intelligence; Statistics","score_opus":0.006601948988134197,"score_gpt":0.20958767853864238,"score_spread":0.20298572955050817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180828828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018228326,0.0017183712,0.97653085,0.0012769802,0.00017996672,0.000062298015,0.000105033745,0.00031107714,0.0015871297],"genre_scores_gemma":[0.3215412,0.00397651,0.6590699,0.0011852394,0.001540439,0.0005957982,0.001667861,0.0006767048,0.009746414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99224514,0.0042004157,0.00045872014,0.0007968697,0.0019306754,0.00036828843],"domain_scores_gemma":[0.9322966,0.059052687,0.0018201389,0.0034398732,0.0025687737,0.00082196126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010678695,0.0020130994,0.004359384,0.0030453163,0.0014295656,0.0029964321,0.003970244,0.0049810903,0.0038681396],"category_scores_gemma":[0.070867755,0.0012177171,0.0013570834,0.0090319365,0.0037250463,0.008200152,0.005028247,0.005202569,0.0010593019],"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":[0.0007225195,0.00025774734,0.0026563583,0.0004219719,0.00015337447,0.00026480446,0.00030401687,0.69476044,0.0014698029,0.11748773,0.007991207,0.17351],"study_design_scores_gemma":[0.00003026214,0.00006311251,0.00014616399,0.0000307753,0.000016745938,0.00006860677,0.000041702213,0.9260569,0.0005349352,0.07200523,0.0009950225,0.000010511902],"about_ca_topic_score_codex":0.0023247933,"about_ca_topic_score_gemma":0.0012082602,"teacher_disagreement_score":0.010678695,"about_ca_system_score_codex":0.0018404567,"about_ca_system_score_gemma":0.0015869191,"threshold_uncertainty_score":0.056474984},"labels":[],"label_agreement":null},{"id":"W2183729464","doi":"10.1016/j.tcs.2015.11.011","title":"Fast construction of wavelet trees","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wavelet; Computer science; Mathematics; Artificial intelligence; Algorithm","score_opus":0.014599212517948037,"score_gpt":0.2475569675169556,"score_spread":0.23295775499900756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183729464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016174383,0.00027053963,0.9801588,0.00011431555,0.000084205436,0.000036747922,0.00012832439,0.00058006524,0.0024526387],"genre_scores_gemma":[0.1476566,0.00062698603,0.8465113,0.000083738894,0.00008802004,0.00013111446,0.0006869818,0.00046468063,0.0037505038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993864,0.000126688,0.000040855917,0.000077243814,0.0002899472,0.000078732395],"domain_scores_gemma":[0.9985593,0.0005799023,0.00007786537,0.00034086275,0.0003387421,0.00010330687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006728685,0.0005983861,0.00086988154,0.0015432347,0.0005150813,0.0012246694,0.0007720304,0.00069377664,0.00449371],"category_scores_gemma":[0.00416009,0.0005528247,0.0007806486,0.0016602546,0.0004954103,0.0017309521,0.00220714,0.0017595155,0.0020195164],"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":[0.00041806372,0.00009934136,0.0008422305,0.00035258825,0.00007420406,0.00031259583,0.0003851343,0.040623184,0.057457093,0.22387144,0.0124583915,0.6631057],"study_design_scores_gemma":[0.00013937322,0.00016443132,0.0007624575,0.00009249412,0.000056356144,0.000488841,0.00016781664,0.6289946,0.03679099,0.30491698,0.027377682,0.000047862053],"about_ca_topic_score_codex":0.00037534535,"about_ca_topic_score_gemma":0.00067027,"teacher_disagreement_score":0.00449371,"about_ca_system_score_codex":0.00040418448,"about_ca_system_score_gemma":0.0005576108,"threshold_uncertainty_score":0.015032947},"labels":[],"label_agreement":null},{"id":"W2185072563","doi":"","title":"On the complexity of #nding common approximate substrings","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Memorial University of Newfoundland; University of New Brunswick","funders":"","keywords":"Parameterized complexity; Substring; Hamming distance; Mathematics; Combinatorics; Alphabet; String (physics); Class (philosophy); Set (abstract data type); Time complexity; Hamming code; Discrete mathematics; Algorithm; Computer science; Artificial intelligence","score_opus":0.06589192076454257,"score_gpt":0.2635647412571811,"score_spread":0.1976728204926385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185072563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5062068,0.0018516352,0.45760328,0.00785239,0.00012038638,0.0003944604,0.002752676,0.001974213,0.021244142],"genre_scores_gemma":[0.81625193,0.0018641962,0.16574138,0.00056520296,0.00036254423,0.0004889721,0.0045298394,0.0006840548,0.009511827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99393374,0.0019629605,0.0004888469,0.0015171063,0.0014075778,0.00068968517],"domain_scores_gemma":[0.91909677,0.069589764,0.0037206716,0.0055054394,0.001262384,0.00082491105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043690144,0.0010819513,0.0018672291,0.0015714399,0.0017815967,0.007894983,0.003443943,0.0033288018,0.011126775],"category_scores_gemma":[0.04427267,0.00097502617,0.0020261507,0.003852107,0.003628273,0.015089485,0.003927725,0.0035698155,0.0011923419],"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":[0.0016494886,0.0004946538,0.011245655,0.000977244,0.0002667297,0.000511747,0.0011289084,0.6072742,0.0064486787,0.20613201,0.012258222,0.15161245],"study_design_scores_gemma":[0.00010944314,0.000091666254,0.0013835802,0.000044541324,0.00007762657,0.00030063663,0.0003068067,0.7066418,0.0031666372,0.28528643,0.0025525151,0.00003837623],"about_ca_topic_score_codex":0.00455415,"about_ca_topic_score_gemma":0.0036998559,"teacher_disagreement_score":0.011126775,"about_ca_system_score_codex":0.004123784,"about_ca_system_score_gemma":0.0028676358,"threshold_uncertainty_score":0.037222803},"labels":[],"label_agreement":null},{"id":"W2186052691","doi":"","title":"RESEARCH INTO THE EFFICIENCY OF LOSSLESS COMPRESSION METHODS WHEN USED TOGERHER","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Lossless compression; Compression (physics); Lossy compression; Data compression; Computer science; Lossless JPEG; Data compression ratio; Natural language processing; Artificial intelligence; Image compression; Materials science","score_opus":0.08551173072371436,"score_gpt":0.42954986077277585,"score_spread":0.3440381300490615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186052691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45161837,0.041248377,0.48932904,0.0016858432,0.0007148661,0.0006280972,0.00078993686,0.0029255403,0.0110599445],"genre_scores_gemma":[0.6105107,0.014434365,0.3626429,0.00038566286,0.0006806378,0.00025588504,0.0016031986,0.00093420234,0.008552341],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99326706,0.0016957955,0.00062379777,0.000968827,0.0031387482,0.00030589232],"domain_scores_gemma":[0.9659055,0.022236336,0.0017183928,0.0050165066,0.0048678,0.00025548646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063298848,0.0015415107,0.0013594093,0.004668549,0.00083232333,0.0025761104,0.0025771188,0.0014757947,0.0033969642],"category_scores_gemma":[0.037197907,0.0006688537,0.0007459433,0.004298814,0.0013348446,0.00838517,0.0011357171,0.0012677473,0.0022017015],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091071485,0.00038156312,0.007379873,0.0009793909,0.0003947501,0.00018166756,0.00028239645,0.021156706,0.08520711,0.004973385,0.002652892,0.8754996],"study_design_scores_gemma":[0.00018601716,0.0021044754,0.01694777,0.0003383122,0.0008561238,0.0034251176,0.00069894316,0.3242744,0.6170133,0.01001879,0.023905097,0.00023172144],"about_ca_topic_score_codex":0.0014061822,"about_ca_topic_score_gemma":0.0014344335,"teacher_disagreement_score":0.0063298848,"about_ca_system_score_codex":0.0009623391,"about_ca_system_score_gemma":0.0005920883,"threshold_uncertainty_score":0.033475995},"labels":[],"label_agreement":null},{"id":"W2187873293","doi":"10.1609/socs.v3i1.18232","title":"Automatic Move Pruning Revisited","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Combinatorial Search","topic":"Algorithms and Data Compression","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":"Pruning; Simple (philosophy); Computer science; State (computer science); Algorithm; Artificial intelligence; Machine learning; Biology","score_opus":0.013765679445542732,"score_gpt":0.26114596971126736,"score_spread":0.2473802902657246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187873293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11054612,0.001669803,0.8351585,0.0029818402,0.0008210284,0.00034949425,0.0008261735,0.013749789,0.033897284],"genre_scores_gemma":[0.49294016,0.0006040017,0.4864662,0.0016482681,0.00017738609,0.00029836927,0.0014618996,0.0024601165,0.013943621],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947331,0.0013171335,0.0002793892,0.00071915897,0.0023517208,0.0005995112],"domain_scores_gemma":[0.99357575,0.002666001,0.000285921,0.0024764882,0.0008754867,0.00012035732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021230925,0.001075303,0.0010686758,0.0010948897,0.0017509302,0.0019355798,0.00324287,0.0019175091,0.0059554004],"category_scores_gemma":[0.01091935,0.00077649165,0.0011908035,0.0014567814,0.002413378,0.0035792137,0.0028604225,0.0031524221,0.0020681797],"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":[0.00095343473,0.0003079312,0.00388301,0.00095343066,0.0002020824,0.0012717028,0.0011400013,0.088886425,0.042369105,0.23743412,0.046126373,0.57647234],"study_design_scores_gemma":[0.0003246495,0.00045240863,0.0018354914,0.00031845405,0.00021571736,0.0017953976,0.00045844656,0.55332273,0.09264528,0.20167963,0.14679174,0.00015994805],"about_ca_topic_score_codex":0.004354678,"about_ca_topic_score_gemma":0.007823066,"teacher_disagreement_score":0.0059554004,"about_ca_system_score_codex":0.0013996876,"about_ca_system_score_gemma":0.0029447651,"threshold_uncertainty_score":0.019922793},"labels":[],"label_agreement":null},{"id":"W2203109677","doi":"10.1016/j.dam.2015.11.005","title":"A multiobjective optimization algorithm for the weighted LCS","year":2015,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Longest common subsequence problem; Set (abstract data type); Algorithm; Similarity (geometry); Sequence (biology); Mathematics; Task (project management); Bounded function; Computation; Computer science; Subsequence; Artificial intelligence","score_opus":0.025563864346921917,"score_gpt":0.2652240079121981,"score_spread":0.23966014356527615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2203109677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004022987,0.00009014179,0.9934189,0.00008912049,0.000033960274,0.00005135703,0.000034629848,0.0001839096,0.0020751394],"genre_scores_gemma":[0.113963485,0.00015926504,0.87880576,0.00013395099,0.00006479708,0.00036726383,0.00017141679,0.00017353204,0.006160597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999516,0.00012168184,0.000025264198,0.000087117645,0.00020158663,0.00004835445],"domain_scores_gemma":[0.99930406,0.00034235267,0.00006304508,0.000049853883,0.0002014426,0.00003929268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012401874,0.00089972967,0.0011608845,0.0013813331,0.0005912867,0.0011371353,0.0013641929,0.0015282771,0.007197157],"category_scores_gemma":[0.0028274218,0.00049705047,0.0008981589,0.0015272486,0.00065971515,0.001096857,0.0017571277,0.0011235506,0.0010501532],"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":[0.00008466721,0.00007779265,0.0003309921,0.00012287819,0.00004574201,0.000055425382,0.000050523315,0.8059119,0.003041778,0.017291158,0.0025726585,0.17041449],"study_design_scores_gemma":[0.000010046875,0.000018907313,0.000030444988,0.0000072774633,0.0000047614294,0.000012308679,0.000004986948,0.99693054,0.0003271029,0.0020508014,0.00059938023,0.0000033936494],"about_ca_topic_score_codex":0.005268124,"about_ca_topic_score_gemma":0.004648328,"teacher_disagreement_score":0.007197157,"about_ca_system_score_codex":0.0012204825,"about_ca_system_score_gemma":0.0017008756,"threshold_uncertainty_score":0.024076939},"labels":[],"label_agreement":null},{"id":"W2204143132","doi":"10.1007/978-3-0348-8211-8_20","title":"Analysis of Quickfind with Small Subfiles","year":2002,"lang":"en","type":"book-chapter","venue":"Birkhäuser Basel eBooks","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"sort; Cutoff; Recursion (computer science); Selection (genetic algorithm); Computer science; Algorithm; Element (criminal law); Mathematics; Artificial intelligence; Information retrieval; Physics; Law","score_opus":0.03444116536697843,"score_gpt":0.20783276092156996,"score_spread":0.17339159555459155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204143132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38592452,0.0018640936,0.5943182,0.0012193505,0.00010154623,0.00024388103,0.0010624274,0.0047882493,0.01047766],"genre_scores_gemma":[0.689918,0.00058499124,0.29557407,0.00027163269,0.00014453736,0.00041578137,0.0017927126,0.0018246656,0.009473691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99292445,0.0014794188,0.00023909366,0.0007618988,0.003660801,0.00093434943],"domain_scores_gemma":[0.9448696,0.041454334,0.002390497,0.0071989857,0.003364409,0.0007222029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004898695,0.00090962136,0.0011443289,0.0028190718,0.0012961921,0.0026515748,0.0047363667,0.0012072681,0.008498191],"category_scores_gemma":[0.042844158,0.0007510183,0.00086309365,0.004121574,0.002520797,0.009800326,0.0026633295,0.0018411794,0.0009987706],"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":[0.0024140782,0.0004444537,0.011686727,0.00059267617,0.000185129,0.00051875476,0.000495909,0.46314493,0.013771814,0.18467386,0.01751381,0.30455783],"study_design_scores_gemma":[0.000066011766,0.00011914763,0.0014720104,0.000028749571,0.000053262393,0.00030233606,0.000113848255,0.90111834,0.013382186,0.078194216,0.0051142266,0.000035719586],"about_ca_topic_score_codex":0.0031785031,"about_ca_topic_score_gemma":0.0032398538,"teacher_disagreement_score":0.008498191,"about_ca_system_score_codex":0.0038634334,"about_ca_system_score_gemma":0.002770992,"threshold_uncertainty_score":0.02842927},"labels":[],"label_agreement":null},{"id":"W2216625225","doi":"10.11575/prism/30326","title":"A TOOL FOR TEACHING ADVANCED DATA STRUCTURES TO COMPUTER SCIENCE STUDENTS AN OVERVIEW OF THE BDP SYSTEM","year":2000,"lang":"en","type":"article","venue":"PRISM (University of Calgary)","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Task (project management); Data structure; Code (set theory); Order (exchange); Software engineering; Mathematics education; Computer engineering; Human–computer interaction; Programming language; Systems engineering; Engineering","score_opus":0.028050386126064853,"score_gpt":0.2835678380654518,"score_spread":0.25551745193938696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2216625225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058881645,0.0003793742,0.9359176,0.00081758184,0.00015705958,0.00039738612,0.00063214026,0.032912556,0.02289807],"genre_scores_gemma":[0.01973085,0.00095045497,0.9490517,0.0004024303,0.000052006162,0.0006397038,0.0011971813,0.003053108,0.02492255],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932003,0.00015579774,0.00005700467,0.00010346665,0.00030814525,0.000055512628],"domain_scores_gemma":[0.9978517,0.0012238496,0.000061598614,0.00025411576,0.00033344707,0.00027525407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014861319,0.0010428091,0.00062537496,0.00125209,0.00061875914,0.0014465366,0.0014207859,0.0011005228,0.0384957],"category_scores_gemma":[0.00596532,0.0008831515,0.00048031533,0.0013962248,0.0005201086,0.0029261047,0.0023636592,0.00268418,0.01925957],"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":[0.00025293438,0.00063353137,0.000995652,0.00058308395,0.000015184443,0.00056377845,0.0011962585,0.004196962,0.03231171,0.026469579,0.16414347,0.7686379],"study_design_scores_gemma":[0.00037739187,0.0004938683,0.0021583957,0.00046745094,0.00003560524,0.003296397,0.00056304905,0.04882263,0.030484261,0.05387279,0.8592981,0.00013002263],"about_ca_topic_score_codex":0.0008862342,"about_ca_topic_score_gemma":0.0012402093,"teacher_disagreement_score":0.0384957,"about_ca_system_score_codex":0.00066465064,"about_ca_system_score_gemma":0.0012899959,"threshold_uncertainty_score":0.1287809},"labels":[],"label_agreement":null},{"id":"W2223854644","doi":"10.1007/978-3-642-22006-7_21","title":"Range Majority in Constant Time and Linear Space","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Manitoba","funders":"","keywords":"Range (aeronautics); Linear space; Range query (database); Constant (computer programming); Logarithm; Upper and lower bounds; Space (punctuation); Mathematics; Combinatorics; Discrete mathematics; Computer science; Mathematical analysis; Search engine; Sargable; Information retrieval; Web search query","score_opus":0.016534144034564536,"score_gpt":0.23071446030165912,"score_spread":0.21418031626709458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2223854644","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05766735,0.005410745,0.7284465,0.00754289,0.0012261313,0.00039703853,0.0021493174,0.0107945055,0.18636557],"genre_scores_gemma":[0.5380276,0.002850551,0.2975498,0.0022972766,0.0014358425,0.0007010455,0.002389462,0.003540406,0.15120795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99601233,0.00062201155,0.00021205645,0.0009141835,0.0014388298,0.0008006232],"domain_scores_gemma":[0.99280566,0.0040444145,0.00024361008,0.002035677,0.0006061428,0.0002644844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015913532,0.0016013767,0.0022639697,0.0013174157,0.0025117574,0.005606508,0.0028573724,0.0015936269,0.02907897],"category_scores_gemma":[0.008671287,0.00090879045,0.0015958118,0.0028132643,0.0025724838,0.015879633,0.005454071,0.0046376223,0.009468171],"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":[0.0012749099,0.00020472276,0.0005958226,0.00079675077,0.00009540792,0.00017002269,0.000610097,0.019113181,0.009541866,0.55503297,0.068173595,0.34439072],"study_design_scores_gemma":[0.0001826428,0.000096402255,0.00022601026,0.00009925857,0.00010318669,0.00029105577,0.00023281749,0.053139005,0.0104780225,0.90078336,0.0343147,0.000053548687],"about_ca_topic_score_codex":0.0015878372,"about_ca_topic_score_gemma":0.002946017,"teacher_disagreement_score":0.02907897,"about_ca_system_score_codex":0.0025715884,"about_ca_system_score_gemma":0.0025650226,"threshold_uncertainty_score":0.09727883},"labels":[],"label_agreement":null},{"id":"W2224651063","doi":"10.22215/etd/2007-06323","title":"On improving FPT K-VERTEX COVER with applications to some combinatorial problems","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Cover (algebra); Vertex (graph theory); Vertex cover; Combinatorics; Mathematics; Computer science; Engineering; Time complexity; Mechanical engineering","score_opus":0.00863670814053174,"score_gpt":0.2656693011958386,"score_spread":0.25703259305530685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2224651063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1656566,0.008300076,0.6732973,0.008836287,0.0017171066,0.00081713055,0.00110972,0.0056847064,0.13458115],"genre_scores_gemma":[0.4292667,0.0031018262,0.53982717,0.0016138244,0.0014255376,0.00046552956,0.0020329647,0.0011155376,0.021151004],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99746406,0.0006596255,0.00011194528,0.00041874498,0.00084602856,0.0004996692],"domain_scores_gemma":[0.99174553,0.0057945945,0.00021465852,0.0013553309,0.0006531598,0.00023670334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654655,0.0016076908,0.001822469,0.0028334456,0.0016528663,0.0028082926,0.0026146576,0.0021017953,0.01217696],"category_scores_gemma":[0.017415807,0.0004038883,0.0016586359,0.0053143348,0.0015436332,0.0048956443,0.0028451222,0.003112717,0.0020454486],"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":[0.00072248426,0.0006376941,0.002173183,0.0006405835,0.000111150985,0.0003056855,0.0003086909,0.28158888,0.0064999997,0.084690966,0.042450722,0.5798699],"study_design_scores_gemma":[0.000104061204,0.00021650214,0.0008844874,0.000080299156,0.00008983282,0.00032171287,0.000119033895,0.88376284,0.00371598,0.0960869,0.0145980315,0.000020273552],"about_ca_topic_score_codex":0.0057986192,"about_ca_topic_score_gemma":0.009326353,"teacher_disagreement_score":0.01217696,"about_ca_system_score_codex":0.0030486858,"about_ca_system_score_gemma":0.0021215645,"threshold_uncertainty_score":0.04073602},"labels":[],"label_agreement":null},{"id":"W2231051939","doi":"10.17485/ijst/2015/v8i24/80242","title":"A New Variable-Length Integer Code for Integer Representation and Its Application to Text Compression","year":2015,"lang":"en","type":"article","venue":"Indian Journal of Science and Technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"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":"Golomb coding; Lossless compression; Lossy compression; Computer science; Data compression; Systematic code; Code (set theory); Compression (physics); Algorithm; Prefix code; Universal code; Integer (computer science); Data compression ratio; Theoretical computer science; Code rate; Image compression; Linear code; Programming language; Decoding methods; Physics; Block code; Artificial intelligence","score_opus":0.022997829827299386,"score_gpt":0.3002173426676524,"score_spread":0.277219512840353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2231051939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029341226,0.002685564,0.9598679,0.00037201575,0.00040015663,0.00015085639,0.00028086337,0.0014463173,0.005455071],"genre_scores_gemma":[0.20488648,0.0020999177,0.7786391,0.00034699714,0.0002469846,0.00033593556,0.0011387748,0.00023910755,0.012066711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944264,0.00007453018,0.000047060043,0.000085660424,0.00031143628,0.00003864278],"domain_scores_gemma":[0.99906534,0.00023947477,0.00011442722,0.00013212611,0.00041641452,0.00003224233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003339712,0.00049283187,0.00036114064,0.0016425975,0.00042373547,0.00080307433,0.000587384,0.0006838493,0.0025426054],"category_scores_gemma":[0.0023976502,0.00012690392,0.00028552473,0.0020055836,0.0006729275,0.0010386746,0.00052140636,0.00081657927,0.0012084909],"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":[0.000532608,0.000083325984,0.00126929,0.00039726644,0.00003487598,0.000804257,0.0002715754,0.022432068,0.13648015,0.057915483,0.0073000644,0.77247906],"study_design_scores_gemma":[0.00015417689,0.00082689244,0.0035539707,0.00031007314,0.00009333037,0.0062920223,0.00022110318,0.54145455,0.29743075,0.019983321,0.12948786,0.00019200493],"about_ca_topic_score_codex":0.0015225998,"about_ca_topic_score_gemma":0.0012615559,"teacher_disagreement_score":0.0025426054,"about_ca_system_score_codex":0.00048081783,"about_ca_system_score_gemma":0.0008513015,"threshold_uncertainty_score":0.008505881},"labels":[],"label_agreement":null},{"id":"W2236111098","doi":"10.1007/978-3-642-31155-0_26","title":"Linear-Space Data Structures for Range Minority Query in Arrays","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Waterloo","funders":"","keywords":"Range query (database); Computer science; Query optimization; Data structure; Range (aeronautics); Preprocessor; Linear space; Algorithm; Web search query; Sargable; Theoretical computer science; Data mining; Information retrieval; Search engine; Mathematics; Combinatorics; Artificial intelligence","score_opus":0.044450573550178285,"score_gpt":0.2879214141629149,"score_spread":0.2434708406127366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2236111098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03483652,0.0031399208,0.93445426,0.0016857984,0.00031349505,0.00030250565,0.0024177006,0.008978522,0.013871313],"genre_scores_gemma":[0.34746847,0.0015628163,0.61975926,0.0011412657,0.00049841503,0.00096001296,0.0053816806,0.0015993769,0.021628698],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998538,0.00023854988,0.00018346455,0.00016560705,0.0006865184,0.0001879242],"domain_scores_gemma":[0.99669826,0.0010627006,0.00021873043,0.0013916732,0.0005232524,0.000105448125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010372897,0.0005830467,0.0010713465,0.0012210464,0.0012049989,0.0025033308,0.0019732774,0.000905699,0.014050318],"category_scores_gemma":[0.005941529,0.00042583141,0.0007205853,0.003940871,0.0011328835,0.006002688,0.0037497855,0.001933755,0.003837781],"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":[0.0013078711,0.00033933407,0.0020976937,0.0007964962,0.000079334444,0.00013678301,0.0009500239,0.01692661,0.02348559,0.26511234,0.07935839,0.60940945],"study_design_scores_gemma":[0.00041530942,0.00063584803,0.0012656497,0.0002769321,0.00012118638,0.000764064,0.0009884547,0.23027487,0.067099005,0.5843667,0.11362682,0.00016511064],"about_ca_topic_score_codex":0.0014695016,"about_ca_topic_score_gemma":0.002124685,"teacher_disagreement_score":0.014050318,"about_ca_system_score_codex":0.0013101422,"about_ca_system_score_gemma":0.0013041812,"threshold_uncertainty_score":0.04700297},"labels":[],"label_agreement":null},{"id":"W2248630842","doi":"","title":"A fixed-parameter algorithm for string-to-string correction","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"String (physics); Character (mathematics); Integer (computer science); Algorithm; Simple (philosophy); Boyer–Moore string search algorithm; String searching algorithm; Computer science; Commentz-Walter algorithm; Tree (set theory); Mathematics; Discrete mathematics; Combinatorics; Data structure; Geometry","score_opus":0.012242094454471542,"score_gpt":0.2625452371130331,"score_spread":0.2503031426585616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248630842","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017329019,0.00029567102,0.9753862,0.00018439311,0.000361858,0.00020484363,0.00040392764,0.01887589,0.00255427],"genre_scores_gemma":[0.023193313,0.0001812217,0.9633907,0.00013450849,0.00014989445,0.00026944876,0.0012770954,0.0018844965,0.009519348],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964831,0.00044101142,0.00033896268,0.00092327764,0.0015407864,0.00027289768],"domain_scores_gemma":[0.99454546,0.0011483891,0.00023358033,0.00233083,0.0015833621,0.00015844996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019324428,0.0026221655,0.0016435143,0.004368664,0.0021216655,0.002482846,0.0051923697,0.002238756,0.044125617],"category_scores_gemma":[0.010936766,0.0009240892,0.0015251632,0.0046119355,0.001283215,0.00314542,0.0039893365,0.0029682189,0.0349334],"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":[0.00039974588,0.000115197654,0.000477036,0.00019074944,0.00009524652,0.00013093476,0.000095548385,0.0090088025,0.013630716,0.012762556,0.041517526,0.921576],"study_design_scores_gemma":[0.00051354367,0.00039071133,0.001716629,0.00017618114,0.00022139009,0.0020336166,0.000236005,0.5894508,0.16034847,0.09924991,0.14533284,0.0003299272],"about_ca_topic_score_codex":0.004376719,"about_ca_topic_score_gemma":0.008191051,"teacher_disagreement_score":0.044125617,"about_ca_system_score_codex":0.0013244268,"about_ca_system_score_gemma":0.003599089,"threshold_uncertainty_score":0.1476149},"labels":[],"label_agreement":null},{"id":"W2249651582","doi":"10.1049/el.2015.3418","title":"Pseudo‐random Gaussian distribution through optimised LFSR permutations","year":2015,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Linear feedback shift register; Gaussian; Distribution (mathematics); Algorithm; Mathematics; Statistical physics; Computer science; Statistics; Shift register; Physics; Telecommunications; Chip; Mathematical analysis","score_opus":0.01729496078471695,"score_gpt":0.2515489276274223,"score_spread":0.23425396684270536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249651582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024402734,0.000124363,0.97029954,0.00014763951,0.000029491539,0.000053591357,0.000030028157,0.00060050876,0.0043120426],"genre_scores_gemma":[0.5693553,0.00023603764,0.4245299,0.00008810696,0.00003368682,0.00015808079,0.00009524,0.00016007238,0.0053436267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929297,0.00022245932,0.0000303138,0.000084234634,0.00029828987,0.000071758615],"domain_scores_gemma":[0.9992981,0.00032787785,0.000100472564,0.00014170213,0.00010932393,0.000022549772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070704205,0.00051187305,0.00039101834,0.00054544787,0.0002263297,0.0006551457,0.0005505536,0.0005241858,0.0019234564],"category_scores_gemma":[0.0023057153,0.00029357907,0.00031060222,0.0005384727,0.0006197787,0.0008266573,0.00057359773,0.0005392835,0.0009178148],"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":[0.00046048884,0.000112296526,0.00083677785,0.00015602936,0.000055091645,0.00027975204,0.00016998689,0.5431829,0.060913328,0.13228612,0.0023075605,0.2592397],"study_design_scores_gemma":[0.000048008962,0.00008262226,0.0001529794,0.000019127612,0.000014328516,0.00020423831,0.000014647953,0.9520547,0.020420605,0.023261122,0.003703977,0.00002364539],"about_ca_topic_score_codex":0.00032849406,"about_ca_topic_score_gemma":0.0006437577,"teacher_disagreement_score":0.0019234564,"about_ca_system_score_codex":0.00042967862,"about_ca_system_score_gemma":0.0007347153,"threshold_uncertainty_score":0.00643456},"labels":[],"label_agreement":null},{"id":"W2250208271","doi":"","title":"Why Letter Substitution Puzzles are Not Hard to Solve: A Case Study in Entropy and Probabilistic Search-Complexity","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"","keywords":"Probabilistic logic; Computer science; Entropy (arrow of time); Substitution (logic); Natural language; Heuristic; Upper and lower bounds; Theoretical computer science; Artificial intelligence; Algorithm; Mathematics","score_opus":0.06700991521398743,"score_gpt":0.28697938971600967,"score_spread":0.21996947450202226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250208271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42856354,0.0032834825,0.521618,0.016985627,0.00012766224,0.00015274301,0.0001664329,0.0004837406,0.028618712],"genre_scores_gemma":[0.93819773,0.0007474098,0.05886235,0.0003561122,0.00018076402,0.00008049832,0.00005375431,0.00013740489,0.001384025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953762,0.002447125,0.00019258347,0.00047937655,0.0010654681,0.00043925003],"domain_scores_gemma":[0.88901716,0.102201425,0.0025524504,0.0040122587,0.0014102532,0.00080643833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005770261,0.00043997858,0.0010771736,0.0014065505,0.0018597232,0.0031190473,0.0014289648,0.0031986253,0.003060101],"category_scores_gemma":[0.07156398,0.00057346054,0.00093588856,0.0019582906,0.007989925,0.010980343,0.0029338426,0.0039921114,0.00036775146],"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":[0.00037987562,0.00018045167,0.0045907632,0.00025093835,0.000068253335,0.00092129223,0.0015286017,0.122854576,0.0030995368,0.8057072,0.00325618,0.05716228],"study_design_scores_gemma":[0.00006745303,0.00005690759,0.0008022482,0.000026777003,0.000013555141,0.00045567311,0.00030847063,0.19422252,0.0016359371,0.80105,0.0013314295,0.000028956016],"about_ca_topic_score_codex":0.0008481022,"about_ca_topic_score_gemma":0.00081049354,"teacher_disagreement_score":0.005770261,"about_ca_system_score_codex":0.0015222781,"about_ca_system_score_gemma":0.0011997935,"threshold_uncertainty_score":0.030516446},"labels":[],"label_agreement":null},{"id":"W2258074816","doi":"10.1016/j.ic.2016.02.001","title":"Approximate matching between a context-free grammar and a finite-state automaton","year":2016,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, Science and Technology; National Research Foundation of Korea","keywords":"Edit distance; Affine transformation; Automaton; Deterministic finite automaton; Computer science; Deterministic automaton; Finite-state machine; Nondeterministic finite automaton; Context (archaeology); Matching (statistics); Context-free language; Grammar; Theoretical computer science; State (computer science); Büchi automaton; Time complexity; State diagram; Algorithm; Mathematics; Automata theory; Artificial intelligence; Rule-based machine translation; Pure mathematics","score_opus":0.012152801788875315,"score_gpt":0.23359991260595894,"score_spread":0.22144711081708363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258074816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07982592,0.00019577076,0.9155418,0.00027424408,0.0000780832,0.00006990701,0.00034282636,0.0019545762,0.0017168707],"genre_scores_gemma":[0.6845078,0.00013884957,0.31103396,0.00016722328,0.000051974275,0.00014642392,0.000894751,0.0003720667,0.002686982],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974753,0.000617101,0.00022154236,0.00068641035,0.00079192343,0.0002077357],"domain_scores_gemma":[0.99064356,0.0063446327,0.00032826056,0.0019590317,0.0005986823,0.00012570409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014801275,0.00045790043,0.0013353557,0.0014539799,0.0008549755,0.0017007086,0.0018853488,0.0019636585,0.0032715346],"category_scores_gemma":[0.016894769,0.0005397728,0.0011513069,0.0019459983,0.0014913568,0.0042484202,0.0021215566,0.0012303822,0.0007668092],"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":[0.0009832468,0.00027885608,0.0037075013,0.00039286743,0.0002115165,0.0009871289,0.0008253571,0.43156964,0.018909132,0.24328536,0.0042534615,0.29459596],"study_design_scores_gemma":[0.00003224006,0.00005712172,0.00034840556,0.000022657143,0.000038253496,0.00014740156,0.00007876665,0.7704337,0.0075653144,0.21995471,0.0013036041,0.000017718367],"about_ca_topic_score_codex":0.003932812,"about_ca_topic_score_gemma":0.0038984078,"teacher_disagreement_score":0.003932812,"about_ca_system_score_codex":0.0012603716,"about_ca_system_score_gemma":0.002011301,"threshold_uncertainty_score":0.010944307},"labels":[],"label_agreement":null},{"id":"W2261045153","doi":"10.48550/arxiv.1506.06716","title":"A model of language inflection graphs","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Brock University","funders":"","keywords":"Inflection; Inflection point; Bipartite graph; Lattice (music); Computer science; Mathematics; Graph; Projection (relational algebra); Connected component; Combinatorics; Artificial intelligence; Algorithm; Physics; Geometry","score_opus":0.10034967688036489,"score_gpt":0.20621586915199636,"score_spread":0.10586619227163147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261045153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18287641,0.0006734211,0.7832296,0.003395492,0.00013565915,0.00015095212,0.0015261736,0.0013915795,0.026620705],"genre_scores_gemma":[0.90013605,0.0006614561,0.07560828,0.0006352556,0.0001459697,0.00032783963,0.0012088764,0.00026557758,0.021010654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994803,0.00017526474,0.000020291034,0.00014772444,0.00010402438,0.000072515395],"domain_scores_gemma":[0.99821293,0.00091157143,0.00019269278,0.00030532436,0.00021523017,0.00016226189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004528586,0.00055831176,0.0006252418,0.001369555,0.0009772195,0.0016910519,0.0020647242,0.001848807,0.006692018],"category_scores_gemma":[0.004387533,0.00042667394,0.0007518618,0.0020848706,0.001719373,0.0028271016,0.0015845335,0.0014656152,0.001317272],"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":[0.00012641783,0.00008694861,0.0009364881,0.00012857135,0.000046620153,0.00077835016,0.0005487953,0.20219454,0.005944308,0.76208425,0.0066191377,0.020505574],"study_design_scores_gemma":[0.000036617912,0.000027913977,0.00027748902,0.000013577174,0.000011420551,0.0002817951,0.0000915587,0.5351269,0.0007863098,0.45907307,0.0042528394,0.000020561678],"about_ca_topic_score_codex":0.0025284763,"about_ca_topic_score_gemma":0.0017750249,"teacher_disagreement_score":0.006692018,"about_ca_system_score_codex":0.0011245753,"about_ca_system_score_gemma":0.00063534075,"threshold_uncertainty_score":0.022387028},"labels":[],"label_agreement":null},{"id":"W2264090060","doi":"10.1007/978-3-662-48350-3_74","title":"Compressed Data Structures for Dynamic Sequences","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; Symbol (formal); Computer science; String (physics); Data structure; Alphabet; Algorithm; Combinatorics; Representation (politics); Lossless compression; Entropy (arrow of time); Data compression; Mathematics; Physics","score_opus":0.05750524399227357,"score_gpt":0.3123359668703994,"score_spread":0.2548307228781258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2264090060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013126323,0.004390604,0.956395,0.0008586818,0.00084507983,0.00017293349,0.0018526922,0.0039164927,0.01844236],"genre_scores_gemma":[0.1864193,0.005405673,0.7454279,0.0008459714,0.0011202358,0.0007917715,0.008753687,0.001813462,0.04942203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992704,0.00007724752,0.000068072404,0.000091237955,0.0004363272,0.0000567605],"domain_scores_gemma":[0.99841607,0.0005484607,0.000086342596,0.000547911,0.0003580967,0.000043092958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042584524,0.0008101167,0.00064698746,0.0016357164,0.00055392977,0.0014628718,0.0012162431,0.00077410525,0.01597583],"category_scores_gemma":[0.0036171044,0.00046951752,0.00039971215,0.0029150655,0.0008678814,0.0030013497,0.0016838785,0.0015872016,0.004374415],"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":[0.00025783555,0.00006707695,0.00020853808,0.00040261165,0.000023997038,0.00023786335,0.00029042384,0.012757438,0.022795746,0.24646626,0.040313326,0.67617893],"study_design_scores_gemma":[0.000135847,0.000290188,0.00054369436,0.00045251774,0.0000568595,0.0017824639,0.0002616283,0.18889768,0.08162614,0.46024725,0.2656024,0.000103391605],"about_ca_topic_score_codex":0.0007112012,"about_ca_topic_score_gemma":0.000807552,"teacher_disagreement_score":0.01597583,"about_ca_system_score_codex":0.00072194764,"about_ca_system_score_gemma":0.0007627379,"threshold_uncertainty_score":0.053444505},"labels":[],"label_agreement":null},{"id":"W2265589577","doi":"10.32657/10356/42096","title":"Heterogeneous multi-core systems for bioinformatics","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Institute of Genetics","keywords":"Computer science; Scalability; Multi-core processor; Biological data; Supercomputer; Distributed computing; Parallel computing; Bioinformatics","score_opus":0.03285386051591242,"score_gpt":0.29477329611617714,"score_spread":0.2619194356002647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2265589577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043687757,0.10070647,0.7697326,0.003898397,0.002695496,0.0004986192,0.00053887605,0.0043502,0.07389164],"genre_scores_gemma":[0.47229633,0.031575944,0.45507798,0.0010843737,0.0012203748,0.000681928,0.0016109748,0.0006269025,0.035825234],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997242,0.00008811787,0.000014065539,0.000044531782,0.000095181684,0.000033835404],"domain_scores_gemma":[0.9996643,0.00009139988,0.000016692462,0.00008974127,0.00009572726,0.000042190288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000622477,0.0003974078,0.00033191027,0.00032786926,0.000489732,0.0010829747,0.00079385546,0.0005134918,0.0067315153],"category_scores_gemma":[0.00096174143,0.00021588313,0.00023629007,0.0007535844,0.0002574997,0.0010499526,0.0007855409,0.0008869767,0.0016959009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003712399,0.00021172229,0.0011631945,0.0012235873,0.00011957685,0.0002616217,0.00026335948,0.09842466,0.035348665,0.2128335,0.07035506,0.5794239],"study_design_scores_gemma":[0.00014405847,0.00027367965,0.0014998831,0.00028078203,0.00011029169,0.0003050553,0.0001625347,0.34825823,0.015439232,0.24290712,0.39056355,0.00005560097],"about_ca_topic_score_codex":0.0005399573,"about_ca_topic_score_gemma":0.00091248285,"teacher_disagreement_score":0.0067315153,"about_ca_system_score_codex":0.00043923623,"about_ca_system_score_gemma":0.0007075439,"threshold_uncertainty_score":0.022519171},"labels":[],"label_agreement":null},{"id":"W2284790019","doi":"10.1007/978-3-319-48472-3_53","title":"Processing Regular Path Queries on Arbitrarily Distributed Data","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Path (computing); Query optimization; Graph; Path expression; Distributed database; Theoretical computer science; Matching (statistics); Node (physics); Enhanced Data Rates for GSM Evolution; Data mining; Query language; Distributed computing; Artificial intelligence; Mathematics","score_opus":0.025579819898917777,"score_gpt":0.2560736317503194,"score_spread":0.2304938118514016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284790019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17490333,0.0010267289,0.80725616,0.00096348,0.0002769874,0.00034127675,0.00078343594,0.008404655,0.006043973],"genre_scores_gemma":[0.5596518,0.0006800102,0.42231712,0.00030228525,0.00033851148,0.0003101841,0.0031343477,0.0012026567,0.012063129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971877,0.00041175727,0.00022241913,0.000509374,0.0013063973,0.00036236472],"domain_scores_gemma":[0.99247026,0.0045306445,0.0002824961,0.002009501,0.0005286476,0.00017847348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017272203,0.0010903698,0.0020597146,0.0011155541,0.001058698,0.0022974757,0.0020875153,0.0015263212,0.0050290935],"category_scores_gemma":[0.008896429,0.0006614074,0.0007683288,0.0029811815,0.0013467086,0.005369888,0.003992697,0.0019627765,0.0017878447],"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":[0.0029726762,0.00055937585,0.003936594,0.0009425614,0.0002489358,0.0010822847,0.0013956864,0.1637667,0.07827483,0.07995824,0.035558637,0.63130355],"study_design_scores_gemma":[0.00014049612,0.00024913708,0.00045572993,0.000033413107,0.00005045228,0.00051589037,0.000413445,0.80711854,0.028031476,0.15523598,0.007724118,0.000031331285],"about_ca_topic_score_codex":0.0013573037,"about_ca_topic_score_gemma":0.0018375237,"teacher_disagreement_score":0.0050290935,"about_ca_system_score_codex":0.00078238157,"about_ca_system_score_gemma":0.0011006618,"threshold_uncertainty_score":0.016823947},"labels":[],"label_agreement":null},{"id":"W2287320187","doi":"10.1007/978-3-642-45278-9_34","title":"Circuit Complexity of Shuffle","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; String (physics); Circuit complexity; Reduction (mathematics); Computational complexity theory; Combinatorics; Discrete mathematics; Upper and lower bounds; Parity (physics); Theoretical computer science; Mathematics; Algorithm; Electronic circuit; Physics; Quantum mechanics","score_opus":0.04321056273481346,"score_gpt":0.25380700085244984,"score_spread":0.21059643811763637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287320187","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21413302,0.0056431848,0.16158205,0.0072301235,0.00068658363,0.00013533863,0.001933652,0.0005966888,0.6080594],"genre_scores_gemma":[0.89381164,0.0037085616,0.019150551,0.00074828067,0.0007177913,0.00019955626,0.0011689528,0.00031759753,0.08017704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929464,0.000109829336,0.000027047223,0.00011026151,0.00033194065,0.00012633856],"domain_scores_gemma":[0.99844104,0.0009576183,0.00007960856,0.00028501934,0.00014634801,0.00009026219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003943885,0.00046362885,0.00066152844,0.0008809499,0.00094657054,0.00307827,0.0011479914,0.0010201616,0.020957],"category_scores_gemma":[0.0028031548,0.00041312742,0.00065684406,0.0016393977,0.0013457445,0.0048466697,0.0013156672,0.002753699,0.0024110244],"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":[0.000060856237,0.000031324555,0.00016485446,0.00009464943,0.000010688076,0.000033095737,0.00006829824,0.0060933568,0.0008791986,0.9618491,0.007427502,0.023287052],"study_design_scores_gemma":[0.00001115244,0.000010736781,0.0001538085,0.0000132708055,0.000007045457,0.000050678165,0.000015599728,0.0064001502,0.0007203239,0.98681474,0.00579459,0.000007958616],"about_ca_topic_score_codex":0.00087916845,"about_ca_topic_score_gemma":0.0010106277,"teacher_disagreement_score":0.020957,"about_ca_system_score_codex":0.0021528895,"about_ca_system_score_gemma":0.0012138058,"threshold_uncertainty_score":0.070108116},"labels":[],"label_agreement":null},{"id":"W2288489406","doi":"10.1101/002881","title":"A GWAS platform built on iPlant cyber-infrastructure","year":2014,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"University of Toronto; Ontario Institute for Cancer Research","funders":"Agricultural Research Service; U.S. Department of Agriculture; National Science Foundation","keywords":"Computer science; Data science","score_opus":0.013501249577935451,"score_gpt":0.22119292677419122,"score_spread":0.20769167719625578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288489406","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0303773,0.00067731837,0.65006703,0.0023152737,0.0006911995,0.00096090196,0.03147797,0.26130065,0.02213228],"genre_scores_gemma":[0.2938033,0.0006254814,0.6059609,0.00219395,0.00038132732,0.0020365007,0.07163921,0.01489097,0.00846833],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688005,0.0005514718,0.00021711609,0.000853414,0.0011553024,0.000342634],"domain_scores_gemma":[0.99556386,0.0009974003,0.0003000476,0.0017481962,0.00075593195,0.00063463947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039628707,0.0010052957,0.0010027885,0.0023107906,0.00055468443,0.0020025622,0.0031266701,0.0006094801,0.015304701],"category_scores_gemma":[0.0077499654,0.0006759343,0.0010373396,0.0025569776,0.00076687423,0.0022002961,0.0042413394,0.001759112,0.008956859],"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":[0.0055571212,0.0007235645,0.02279731,0.000813903,0.00067947543,0.0023876755,0.0007016607,0.027563805,0.07451908,0.05709561,0.42276555,0.38439524],"study_design_scores_gemma":[0.0026884996,0.00096120423,0.023496514,0.00027499153,0.000555182,0.0029534195,0.00022172772,0.3077765,0.11368655,0.08143242,0.4653845,0.0005684496],"about_ca_topic_score_codex":0.0030310436,"about_ca_topic_score_gemma":0.0015292991,"teacher_disagreement_score":0.015304701,"about_ca_system_score_codex":0.0009203026,"about_ca_system_score_gemma":0.0025065492,"threshold_uncertainty_score":0.051199377},"labels":[],"label_agreement":null},{"id":"W2290281988","doi":"10.37236/5517","title":"Generalizing the Classic Greedy and Necklace Constructions of de Bruijn Sequences and Universal Cycles","year":2016,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Necklace; Concatenation (mathematics); Combinatorics; Mathematics; De Bruijn sequence; Lexicographical order; Morphism; Alphabet; Integer (computer science); Class (philosophy); Intersection (aeronautics); Suffix; Word (group theory); String (physics); Discrete mathematics; Computer science","score_opus":0.00749060686263108,"score_gpt":0.21755430299060532,"score_spread":0.21006369612797424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290281988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1733208,0.0016388339,0.7495059,0.0011537995,0.00021489893,0.00021883588,0.00049172,0.0017270052,0.07172819],"genre_scores_gemma":[0.74280506,0.001373595,0.22238277,0.001040968,0.00035865908,0.000366157,0.0007004977,0.00091363996,0.030058673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812883,0.00027268808,0.00013169645,0.00058621133,0.0005196398,0.00036090214],"domain_scores_gemma":[0.9976726,0.0009488116,0.00029302537,0.0006677312,0.0002445803,0.00017321024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001039363,0.00081628095,0.00072715216,0.002030016,0.0018111919,0.0028788012,0.0012353449,0.0011357717,0.0056270626],"category_scores_gemma":[0.0070853597,0.00069232757,0.0009587959,0.0028190946,0.0039138347,0.007486478,0.004019335,0.0020080425,0.0013072061],"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":[0.00009838494,0.000034226832,0.00049186085,0.00010672202,0.000011078105,0.00014018969,0.00061577436,0.0088176,0.004058948,0.94491357,0.0014817027,0.03922985],"study_design_scores_gemma":[0.000032209806,0.00008595255,0.0002630083,0.00008436487,0.000023534587,0.0006483137,0.00023392553,0.041273586,0.012307969,0.90624326,0.038738087,0.0000657253],"about_ca_topic_score_codex":0.0017109442,"about_ca_topic_score_gemma":0.0014959195,"teacher_disagreement_score":0.0056270626,"about_ca_system_score_codex":0.0020532657,"about_ca_system_score_gemma":0.0017595381,"threshold_uncertainty_score":0.018824399},"labels":[],"label_agreement":null},{"id":"W2291149938","doi":"10.1137/1.9781611973754.2","title":"A Data-Aware FM-index","year":2014,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Computer science; Code (set theory); Index (typography); Algorithm; Wavelet; Data compression; Entropy (arrow of time); Tree (set theory); Theoretical computer science; Wavelet transform; Data mining; Artificial intelligence; Mathematics","score_opus":0.10354134900068349,"score_gpt":0.2667702607326768,"score_spread":0.1632289117319933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291149938","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021369895,0.0021086233,0.94758064,0.00045920888,0.0006249086,0.00026936785,0.00176966,0.010815961,0.015001789],"genre_scores_gemma":[0.11782195,0.000745988,0.86009365,0.00050798804,0.0005130943,0.00023711688,0.0055416427,0.00078490766,0.013753682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999119,0.00006314972,0.00006725157,0.00012108999,0.0005611001,0.00006832476],"domain_scores_gemma":[0.9987263,0.00020823698,0.000061345985,0.000534971,0.0003966056,0.000072567804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005431595,0.0007217114,0.0009793465,0.002703541,0.00075480517,0.0014690225,0.002176726,0.0008609417,0.008136811],"category_scores_gemma":[0.0028902902,0.00029762997,0.00044916748,0.0034044888,0.00048455756,0.0037247173,0.0021408582,0.00089750567,0.0049431752],"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":[0.0004140312,0.00021511698,0.00085984194,0.00038342932,0.00004302421,0.00021474207,0.00014113031,0.006636557,0.07042374,0.021069083,0.03474679,0.86485255],"study_design_scores_gemma":[0.00026632423,0.0006164854,0.0029192006,0.00015627187,0.00013704295,0.0031490584,0.00022244966,0.53913444,0.19368187,0.0441242,0.21538168,0.00021103585],"about_ca_topic_score_codex":0.0012960322,"about_ca_topic_score_gemma":0.0018359203,"teacher_disagreement_score":0.008136811,"about_ca_system_score_codex":0.0006894857,"about_ca_system_score_gemma":0.001217055,"threshold_uncertainty_score":0.027220309},"labels":[],"label_agreement":null},{"id":"W2292889201","doi":"10.1007/978-3-319-27122-4_26","title":"Bitwise Data Parallelism with LLVM: The ICgrep Case Study","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; SIMD; Unicode; Parallel computing; Bitwise operation; Parallelism (grammar); Compiler; Instruction-level parallelism; Programming language; Computer architecture; Artificial intelligence","score_opus":0.07006981858183572,"score_gpt":0.3014386979558672,"score_spread":0.23136887937403147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292889201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5764013,0.0063623795,0.20190127,0.004126447,0.0003966812,0.00047865952,0.002842122,0.0075138044,0.19997737],"genre_scores_gemma":[0.8377919,0.0010769732,0.13655908,0.00039513785,0.00013498888,0.00015120256,0.0011587462,0.0010891735,0.021642813],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983082,0.00034152664,0.00007582018,0.0002401893,0.000702235,0.00033202974],"domain_scores_gemma":[0.99672616,0.0015623604,0.00017841917,0.00090809504,0.00047680055,0.00014812007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013026407,0.0005782565,0.0005238131,0.0006567924,0.001041571,0.0021735954,0.0018760667,0.0013635586,0.00544327],"category_scores_gemma":[0.00657328,0.00031250023,0.0005112538,0.0027277183,0.0013592797,0.0028580069,0.0010705333,0.0016821361,0.0012589205],"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":[0.001807268,0.0013940562,0.010275706,0.0013612526,0.00014356406,0.00510666,0.0016196076,0.11940467,0.015102588,0.24647422,0.109136194,0.48817426],"study_design_scores_gemma":[0.00040211363,0.00096218026,0.003809329,0.00029180603,0.0001548841,0.00657181,0.0014473792,0.5514948,0.061067652,0.23342983,0.1402516,0.00011662301],"about_ca_topic_score_codex":0.0043010316,"about_ca_topic_score_gemma":0.0054605254,"teacher_disagreement_score":0.00544327,"about_ca_system_score_codex":0.0010347225,"about_ca_system_score_gemma":0.0012997548,"threshold_uncertainty_score":0.018209577},"labels":[],"label_agreement":null},{"id":"W2293145487","doi":"","title":"An In-Place Priority Search Tree","year":2011,"lang":"en","type":"article","venue":"Canadian Conference on Computational Geometry","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Tree (set theory); Search tree; Data structure; Set (abstract data type); Point (geometry); Range tree; Segment tree; K-ary tree; Tree structure; Interval tree; Space (punctuation); Theoretical computer science; Data mining; Algorithm; Search algorithm; Mathematics; Combinatorics","score_opus":0.05831943655892484,"score_gpt":0.2812326171816245,"score_spread":0.22291318062269966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293145487","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042264998,0.00089295855,0.93115896,0.0008984048,0.0003746482,0.00023321336,0.0014935884,0.0038888487,0.018794363],"genre_scores_gemma":[0.32221434,0.00097561534,0.6501124,0.00061384705,0.00028636467,0.00024664303,0.0031681194,0.0006919396,0.021690791],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987985,0.00015008287,0.000119135795,0.00020865958,0.0004974939,0.00022608647],"domain_scores_gemma":[0.9978759,0.00045117253,0.00014246903,0.0005865596,0.000739438,0.00020445597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091016537,0.0004774197,0.0010573973,0.0012643026,0.0010658619,0.0023387568,0.001954769,0.0010359096,0.00843916],"category_scores_gemma":[0.0052764416,0.0004725541,0.00056384294,0.0025477007,0.00069867464,0.0047628293,0.0024192964,0.0012146119,0.0038624147],"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":[0.001621863,0.00044090234,0.0035779173,0.0009116031,0.000091817084,0.0011355834,0.0010205274,0.023516305,0.05317983,0.301602,0.05981155,0.55309016],"study_design_scores_gemma":[0.00052084774,0.0013435844,0.0017376086,0.00020075252,0.00022343446,0.0033222178,0.0008375184,0.30064052,0.06563561,0.40557113,0.21974184,0.0002249071],"about_ca_topic_score_codex":0.0021682242,"about_ca_topic_score_gemma":0.0021460666,"teacher_disagreement_score":0.00843916,"about_ca_system_score_codex":0.000767231,"about_ca_system_score_gemma":0.0016851079,"threshold_uncertainty_score":0.0282318},"labels":[],"label_agreement":null},{"id":"W2293388829","doi":"","title":"Crochemore's Repetitions Algorithm Revisited - Computing Runs.","year":2009,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Algorithm; Computer science; Suffix array; Time complexity; Suffix; Extension (predicate logic); Compressed suffix array; Factorization; Parallel algorithm; Suffix tree; Data structure","score_opus":0.01707766616431033,"score_gpt":0.2677945298609171,"score_spread":0.2507168636966068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293388829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014148284,0.0009569721,0.9668861,0.0004906652,0.00029966485,0.0002145699,0.00029962056,0.0040014684,0.012702781],"genre_scores_gemma":[0.080861524,0.0005795998,0.9026989,0.00046224098,0.00028064288,0.0002799169,0.0007105518,0.0009947666,0.01313191],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99547654,0.00091048464,0.0003804468,0.0012065787,0.0016419135,0.00038397868],"domain_scores_gemma":[0.99461854,0.0018154245,0.0002981365,0.0020259847,0.0011152554,0.00012672442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002430516,0.0015184395,0.0012640926,0.0022251839,0.0012034969,0.0027540305,0.0031805283,0.0016416846,0.0067053204],"category_scores_gemma":[0.012392051,0.00081101235,0.0017511225,0.0033727055,0.0023787213,0.007540911,0.0024103674,0.0028459125,0.0035736538],"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":[0.0009911947,0.00012014675,0.0026584247,0.00053628447,0.00017552215,0.00025988946,0.0005433511,0.042302623,0.019454723,0.24017084,0.021965496,0.67082155],"study_design_scores_gemma":[0.0002692649,0.00070943515,0.0026452518,0.00036330993,0.00020668226,0.0023954709,0.00034059968,0.41512063,0.09507167,0.31353942,0.16903813,0.0003001934],"about_ca_topic_score_codex":0.0036011229,"about_ca_topic_score_gemma":0.0053622583,"teacher_disagreement_score":0.0067053204,"about_ca_system_score_codex":0.0014167244,"about_ca_system_score_gemma":0.0023434958,"threshold_uncertainty_score":0.022431493},"labels":[],"label_agreement":null},{"id":"W2294604582","doi":"10.1007/978-3-662-48971-0_8","title":"Multidimensional Range Selection","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Range (aeronautics); Selection (genetic algorithm); Artificial intelligence; Engineering","score_opus":0.025958850772309795,"score_gpt":0.26056020804899827,"score_spread":0.23460135727668846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294604582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009264719,0.004460327,0.9268476,0.00026986474,0.00047375608,0.00007594598,0.000513775,0.0024486596,0.05564537],"genre_scores_gemma":[0.16081767,0.005682519,0.74651664,0.0005260157,0.000681822,0.0002064334,0.0028821689,0.0012123996,0.08147433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99960774,0.000044599863,0.000019876525,0.00009072733,0.00020360164,0.000033450007],"domain_scores_gemma":[0.99964774,0.0000955922,0.000020049372,0.00011806832,0.000095066185,0.000023531584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029715305,0.00066542067,0.0007487682,0.0011697036,0.00044384037,0.0011505472,0.0007196149,0.00045538033,0.022843713],"category_scores_gemma":[0.00089920004,0.00026536637,0.00050092593,0.0018588745,0.0003584809,0.0010805812,0.0015552739,0.0008110146,0.009490683],"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":[0.00015256158,0.000032877913,0.00031138505,0.00027706384,0.000029545276,0.00014101635,0.00006399552,0.004344565,0.04557021,0.030898768,0.026782108,0.8913959],"study_design_scores_gemma":[0.000079716345,0.00036471177,0.002702615,0.00029886604,0.00012335388,0.0052870116,0.00024561211,0.2238904,0.17906761,0.081064515,0.50671285,0.00016272713],"about_ca_topic_score_codex":0.00015060646,"about_ca_topic_score_gemma":0.00022726145,"teacher_disagreement_score":0.022843713,"about_ca_system_score_codex":0.00016206171,"about_ca_system_score_gemma":0.00020464207,"threshold_uncertainty_score":0.07641983},"labels":[],"label_agreement":null},{"id":"W2294639780","doi":"","title":"Reconstructing a suffix array","year":2005,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Lexicographical order; Suffix array; Compressed suffix array; Suffix tree; Suffix; Generalized suffix tree; Computer science; String (physics); Data structure; Alphabet; Simple (philosophy); Construct (python library); Algorithm; Theoretical computer science; Mathematics; Combinatorics; Programming language","score_opus":0.04307785103725692,"score_gpt":0.284097871430358,"score_spread":0.24102002039310105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294639780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05693978,0.0005278494,0.93356955,0.0004290575,0.00036320047,0.00009032687,0.0007200559,0.0026291658,0.0047310544],"genre_scores_gemma":[0.15017448,0.00044435562,0.83954185,0.00015592281,0.00010074462,0.00008709362,0.0024685564,0.00044400847,0.006582937],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991535,0.00017184301,0.00009724124,0.00020466249,0.0003012139,0.00007156539],"domain_scores_gemma":[0.99584216,0.0014805753,0.00028665192,0.0014920132,0.00080167135,0.0000968796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072107645,0.00060933194,0.0007931356,0.0013260753,0.00064697175,0.0013590441,0.0009285056,0.0010201168,0.004549704],"category_scores_gemma":[0.0073078163,0.00043984482,0.00066502544,0.002568821,0.00066661177,0.002548607,0.0010981101,0.0012935842,0.0039719115],"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":[0.00092475757,0.00012318236,0.0033981705,0.0006166329,0.0001149836,0.0008780912,0.0005722863,0.046852,0.10989167,0.07356976,0.011730313,0.7513282],"study_design_scores_gemma":[0.00009346586,0.0005198452,0.0012189451,0.00015871522,0.00012472905,0.002631719,0.00050285226,0.51127726,0.29777095,0.110304676,0.07531878,0.00007808196],"about_ca_topic_score_codex":0.00043671997,"about_ca_topic_score_gemma":0.00043740403,"teacher_disagreement_score":0.004549704,"about_ca_system_score_codex":0.0003284405,"about_ca_system_score_gemma":0.0008530607,"threshold_uncertainty_score":0.015220284},"labels":[],"label_agreement":null},{"id":"W2295102091","doi":"","title":"Two squares canonical factorization","year":2014,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Lemma (botany); Factorization; Mathematics; Conjecture; String (physics); Combinatorics; Least-squares function approximation; Canonical form; Pure mathematics; Algorithm; Statistics","score_opus":0.02014224060489709,"score_gpt":0.2683239865334741,"score_spread":0.24818174592857703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295102091","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10499192,0.0008688825,0.76293963,0.0020993017,0.0012939004,0.00020365202,0.0011925632,0.0023937868,0.124016404],"genre_scores_gemma":[0.68992037,0.00071113434,0.24627188,0.0013820201,0.0005226666,0.00033979764,0.001905506,0.00137382,0.05757278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998192,0.00023586012,0.00010540765,0.00067713816,0.00044004922,0.0003495802],"domain_scores_gemma":[0.9979961,0.00047009546,0.00014848188,0.0006444759,0.0005033694,0.00023750767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008512983,0.000869203,0.00079090305,0.001219838,0.0017377116,0.0024204808,0.0008097258,0.0013476349,0.02297935],"category_scores_gemma":[0.004522679,0.0005636528,0.0011823575,0.0014100799,0.0028530955,0.0050886944,0.0024975722,0.0025584942,0.00626026],"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":[0.00015035324,0.00004030414,0.00054353283,0.000088410445,0.000009218388,0.00036571687,0.00037202844,0.0015403315,0.004622645,0.9510365,0.0068805222,0.034350354],"study_design_scores_gemma":[0.000046474088,0.00010044752,0.0003435536,0.000050459945,0.000021480642,0.00071067765,0.00032015296,0.014035807,0.007664614,0.9236592,0.052981537,0.00006566284],"about_ca_topic_score_codex":0.0011258905,"about_ca_topic_score_gemma":0.0011767313,"teacher_disagreement_score":0.02297935,"about_ca_system_score_codex":0.0008476603,"about_ca_system_score_gemma":0.0012469016,"threshold_uncertainty_score":0.0768736},"labels":[],"label_agreement":null},{"id":"W2306065056","doi":"","title":"Boosting high throughput sequencing data compression algorithms using reordering","year":2013,"lang":"en","type":"dissertation","venue":"Summit (Simon Fraser University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Mitacs","keywords":"Boosting (machine learning); Computer science; Throughput; Algorithm; Data compression; Parallel computing; Artificial intelligence; Telecommunications","score_opus":0.04692865658826111,"score_gpt":0.26315636175134705,"score_spread":0.21622770516308593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2306065056","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0563942,0.00046124816,0.9370621,0.0003964668,0.00009459978,0.00017651264,0.00015980721,0.002839028,0.002415887],"genre_scores_gemma":[0.27447546,0.00037527207,0.72015554,0.0004387228,0.00014515429,0.00027357409,0.001034685,0.00042551715,0.0026760912],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984114,0.00041231545,0.00009293675,0.00026655776,0.00065031735,0.00016639529],"domain_scores_gemma":[0.9959313,0.0019073394,0.00027787947,0.0010643705,0.00069643365,0.00012254906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020582646,0.0008621008,0.0011547151,0.0013422027,0.0007604575,0.001052166,0.0015389791,0.0012826242,0.0015786265],"category_scores_gemma":[0.006668963,0.0003879705,0.00083837635,0.0018727116,0.0011732477,0.0017092127,0.0014600424,0.0022014189,0.0010860566],"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":[0.0005807572,0.00035388078,0.0033059672,0.00022413004,0.000071861374,0.00025744858,0.00035906644,0.3203967,0.06499525,0.03721938,0.014578997,0.5576565],"study_design_scores_gemma":[0.00003637036,0.00012827886,0.00058630644,0.000016095411,0.00001489423,0.00014240725,0.000048307124,0.9513532,0.027468214,0.016742192,0.0034455857,0.000018190754],"about_ca_topic_score_codex":0.0012871724,"about_ca_topic_score_gemma":0.0013133204,"teacher_disagreement_score":0.0020582646,"about_ca_system_score_codex":0.0010360626,"about_ca_system_score_gemma":0.0010750153,"threshold_uncertainty_score":0.010885298},"labels":[],"label_agreement":null},{"id":"W23065273","doi":"10.1007/s11033-012-2082-1","title":"Computing periodicities in strings: A new approach","year":2005,"lang":"en","type":"article","venue":"Molecular Biology Reports","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Computation; Generalized suffix tree; Suffix array; Suffix tree; Computer science; Suffix; Algorithm; Theoretical computer science; Compressed suffix array; Tree (set theory); Overhead (engineering); Mathematics; Data structure; Combinatorics; Programming language; Linguistics","score_opus":0.011546768822766859,"score_gpt":0.26741512524484745,"score_spread":0.2558683564220806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W23065273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022023022,0.00028773662,0.9751888,0.00017798426,0.000067433866,0.00010539849,0.00053917035,0.0010279741,0.0005826047],"genre_scores_gemma":[0.12897956,0.00032671553,0.86606103,0.0001678885,0.0003068386,0.0004418121,0.0023749357,0.00022952059,0.0011118242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954592,0.0012875901,0.00068459613,0.00118067,0.0011556417,0.00023232911],"domain_scores_gemma":[0.98726463,0.008258538,0.00082010124,0.0022990264,0.0010555843,0.0003021876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004197673,0.0008996992,0.0022680815,0.0065125604,0.0011215338,0.0024094481,0.00212383,0.0012309989,0.0026138893],"category_scores_gemma":[0.023524405,0.00072450464,0.001584277,0.005697468,0.0009950887,0.00267398,0.0026123594,0.001412041,0.0012470548],"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":[0.0007836416,0.0003865628,0.0290586,0.00048257722,0.0005860167,0.0008769229,0.0006827962,0.09007837,0.012058618,0.036989033,0.0053779427,0.8226389],"study_design_scores_gemma":[0.0001387894,0.00027152148,0.004919632,0.00004981455,0.00014114493,0.0008602157,0.00020089092,0.89292365,0.0030875537,0.09061451,0.0067222174,0.00006999138],"about_ca_topic_score_codex":0.0020004201,"about_ca_topic_score_gemma":0.0019446254,"teacher_disagreement_score":0.0065125604,"about_ca_system_score_codex":0.0004900738,"about_ca_system_score_gemma":0.0010395502,"threshold_uncertainty_score":0.02219969},"labels":[],"label_agreement":null},{"id":"W2314945607","doi":"10.4310/joc.2012.v3.n1.a5","title":"Chipping away at the edges: How long does it take?","year":2012,"lang":"en","type":"article","venue":"Journal of Combinatorics","topic":"Algorithms and Data Compression","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":"Toronto Metropolitan University","funders":"","keywords":"Vertex (graph theory); Combinatorics; Mathematics; TRAC; Enhanced Data Rates for GSM Evolution; Graph; Discrete mathematics; Computer science; Telecommunications","score_opus":0.021216610707188912,"score_gpt":0.24872301482640446,"score_spread":0.22750640411921555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314945607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16787674,0.06608571,0.54335076,0.13388704,0.008819839,0.00028448668,0.001195258,0.0026392103,0.075861014],"genre_scores_gemma":[0.69466466,0.024337022,0.17221265,0.02360962,0.0024752652,0.00035988286,0.0018057707,0.0015236764,0.079011455],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981084,0.0005494283,0.00008766556,0.0004137799,0.00043257794,0.00040804915],"domain_scores_gemma":[0.9890593,0.005836067,0.00056754734,0.0020390155,0.0018221568,0.000675858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002106064,0.0010527811,0.0018569378,0.0012018168,0.0023886722,0.0038878047,0.0017614806,0.003967313,0.013829811],"category_scores_gemma":[0.025695926,0.0008834415,0.0010918535,0.002256272,0.0031627975,0.010896472,0.0027911058,0.0052662524,0.0047949986],"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":[0.0016379459,0.00038724983,0.008970133,0.000729018,0.00022632393,0.0006534165,0.0006770989,0.030674249,0.008224987,0.26895544,0.14585866,0.5330054],"study_design_scores_gemma":[0.00017908469,0.000322401,0.0023946792,0.00032889715,0.00024318589,0.0008689575,0.0019553408,0.14497155,0.012404455,0.7690697,0.066976435,0.00028530395],"about_ca_topic_score_codex":0.004219517,"about_ca_topic_score_gemma":0.006178465,"teacher_disagreement_score":0.013829811,"about_ca_system_score_codex":0.0015625278,"about_ca_system_score_gemma":0.001687325,"threshold_uncertainty_score":0.046265304},"labels":[],"label_agreement":null},{"id":"W2319265692","doi":"10.1007/s10489-016-0766-2","title":"Repeated patterns detection in big data using classification and parallelism on LERP Reduced Suffix Arrays","year":2016,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Parallelism (grammar); Suffix; Parallel computing; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.1438759669707695,"score_gpt":0.3030399949651068,"score_spread":0.15916402799433732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319265692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1840275,0.00056824,0.8054119,0.00047762797,0.000198996,0.00014536882,0.0007459255,0.0054218867,0.003002587],"genre_scores_gemma":[0.46119702,0.00025939452,0.5320429,0.00016965205,0.00014327012,0.00019679138,0.0015929237,0.00026245907,0.0041355123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990683,0.000168643,0.000094924224,0.0002100334,0.0003646095,0.000093523355],"domain_scores_gemma":[0.9975375,0.00079989247,0.00020459607,0.00069535704,0.000655339,0.000107279986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005569158,0.0005149669,0.0008107369,0.0017836476,0.0008489722,0.0012436492,0.0011383498,0.0005262834,0.0020862918],"category_scores_gemma":[0.0037040063,0.0003162671,0.00062541675,0.0031801078,0.0005578809,0.0017485714,0.0010259232,0.00083619193,0.0012044109],"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":[0.0010509054,0.00035835,0.008013862,0.0001906735,0.00010391256,0.00054130756,0.00036546277,0.056918193,0.0726931,0.013330109,0.0075604995,0.83887357],"study_design_scores_gemma":[0.000039535716,0.00020523199,0.00240987,0.000017768505,0.000035021567,0.00033369657,0.00016453717,0.93446445,0.034747005,0.022506237,0.005044543,0.00003199954],"about_ca_topic_score_codex":0.0016623337,"about_ca_topic_score_gemma":0.0025104005,"teacher_disagreement_score":0.0020862918,"about_ca_system_score_codex":0.00046957147,"about_ca_system_score_gemma":0.001278878,"threshold_uncertainty_score":0.0069792867},"labels":[],"label_agreement":null},{"id":"W2323457000","doi":"10.6000/1927-5129.2012.08.02.18","title":"Evaluation of Basic Data Compression Algorithms in a Distributed Environment","year":2012,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Huffman coding; Data compression; Scalability; Compression ratio; Algorithm; Server; Compression (physics); Encoding (memory); Transfer (computing); Parallel computing; Distributed computing; Real-time computing; Database; Computer network; Artificial intelligence","score_opus":0.0932986025072772,"score_gpt":0.32105354414957576,"score_spread":0.22775494164229856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2323457000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8753113,0.0022578964,0.10863312,0.00023899559,0.00010907322,0.00038880444,0.0005251591,0.00338564,0.009150051],"genre_scores_gemma":[0.9276912,0.00068400026,0.06871674,0.000027914062,0.000028774124,0.00014825068,0.0008368407,0.00016549145,0.0017009171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778676,0.00041529306,0.00014192554,0.00025872618,0.0011890422,0.00020817644],"domain_scores_gemma":[0.992934,0.003854872,0.00040459764,0.0007275493,0.0018475719,0.00023144952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017857739,0.0008153201,0.0008122308,0.0014009092,0.0005858827,0.0008445768,0.0010638108,0.0007046228,0.0013626718],"category_scores_gemma":[0.0074374597,0.00014923241,0.0003266677,0.0022305176,0.0005848006,0.0012359493,0.00050737336,0.0005095352,0.00036008525],"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":[0.0042196345,0.0018203796,0.013146291,0.0012089075,0.00024954462,0.0006502972,0.00046591807,0.39427784,0.10146229,0.0058301413,0.004401189,0.47226766],"study_design_scores_gemma":[0.00026214172,0.0022711335,0.009867048,0.00004036108,0.00007580834,0.0004355647,0.00034192903,0.87035483,0.11119022,0.0018019201,0.0033126872,0.000046245616],"about_ca_topic_score_codex":0.002755858,"about_ca_topic_score_gemma":0.0014703016,"teacher_disagreement_score":0.002755858,"about_ca_system_score_codex":0.0010334625,"about_ca_system_score_gemma":0.00085466803,"threshold_uncertainty_score":0.009444177},"labels":[],"label_agreement":null},{"id":"W2327189209","doi":"10.2316/p.2010.676-066","title":"Stream Experiments: Toward Latency Hiding in GPGPU","year":2010,"lang":"en","type":"article","venue":"Parallel and Distributed Computing and Networks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; General-purpose computing on graphics processing units; Latency (audio); Parallel computing; Computer graphics (images); Graphics; Telecommunications","score_opus":0.013934640081271593,"score_gpt":0.25797018275291095,"score_spread":0.24403554267163935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2327189209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49800357,0.0013476853,0.46431854,0.0025548907,0.001009144,0.000253495,0.0009629723,0.012268876,0.019280871],"genre_scores_gemma":[0.8535646,0.00045204358,0.13863198,0.00053954596,0.00014778937,0.00019165424,0.00054924184,0.00090616907,0.005017002],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883074,0.00040027744,0.00003475411,0.00012797331,0.0004551119,0.00015117877],"domain_scores_gemma":[0.9968027,0.0012855507,0.00013581889,0.0011513374,0.0004689867,0.00015558115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014805059,0.0006996061,0.00065431616,0.00044855606,0.00067590084,0.0011461294,0.0018007845,0.0008492963,0.004482891],"category_scores_gemma":[0.008186021,0.00033412152,0.00029360733,0.0009821067,0.0013769862,0.0030212468,0.0015358273,0.001845258,0.00066792243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008557761,0.001994775,0.008777489,0.0007312971,0.00034646638,0.00038716712,0.0009796051,0.25087032,0.11634016,0.17314923,0.04461449,0.39325124],"study_design_scores_gemma":[0.0003728116,0.0007018129,0.0007896382,0.000033939705,0.00006241972,0.000073505005,0.00015848549,0.78906846,0.12728152,0.07356885,0.0078437915,0.000044833618],"about_ca_topic_score_codex":0.001778969,"about_ca_topic_score_gemma":0.001448165,"teacher_disagreement_score":0.004482891,"about_ca_system_score_codex":0.00055164564,"about_ca_system_score_gemma":0.0010998364,"threshold_uncertainty_score":0.014996767},"labels":[],"label_agreement":null},{"id":"W2328002359","doi":"10.1145/2893488","title":"Parallel Optimal Pairwise Biological Sequence Comparison","year":2016,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"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; Pairwise comparison; Xeon; Xeon Phi; Parallel computing; Sequence (biology); Graphics; Field (mathematics); Supercomputer; Benchmark (surveying); Resource (disambiguation); Field-programmable gate array; Artificial intelligence; Operating system","score_opus":0.19535979625243,"score_gpt":0.39282431332644263,"score_spread":0.19746451707401264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328002359","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0121454755,0.06829321,0.90461844,0.0010681349,0.0006615653,0.00020313538,0.00067283533,0.001787882,0.010549355],"genre_scores_gemma":[0.120459974,0.047425088,0.8208682,0.00061830675,0.0008187848,0.0004073262,0.0030300026,0.00054118707,0.005831091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973869,0.00049588433,0.00022014412,0.00053921604,0.0012370448,0.00012085067],"domain_scores_gemma":[0.9970005,0.001581636,0.0002620481,0.00044505685,0.00064610585,0.000064582586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023949621,0.001313391,0.0019248355,0.002959626,0.00056472776,0.0014619624,0.0024395555,0.0011751741,0.003686616],"category_scores_gemma":[0.008584126,0.0005049124,0.0011719436,0.005233211,0.00094850705,0.0025775246,0.0017090922,0.0012157689,0.0021426436],"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":[0.00017770853,0.00009185661,0.0010422352,0.0015010862,0.00015391628,0.00013031336,0.000091895956,0.025931554,0.007799752,0.023936354,0.00949399,0.92964935],"study_design_scores_gemma":[0.00023111727,0.00065240095,0.0056558545,0.0010284677,0.00044864847,0.0064732614,0.00044165386,0.46935755,0.06902345,0.26663363,0.17983662,0.00021744675],"about_ca_topic_score_codex":0.00090575975,"about_ca_topic_score_gemma":0.00083192566,"teacher_disagreement_score":0.003686616,"about_ca_system_score_codex":0.0006117623,"about_ca_system_score_gemma":0.0015093466,"threshold_uncertainty_score":0.012665927},"labels":[],"label_agreement":null},{"id":"W2335338794","doi":"10.1007/s00453-016-0146-7","title":"Biased Predecessor Search","year":2016,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Bounded function; Sublinear function; Entropy (arrow of time); Computer science; Logarithm; Mathematics; Data structure; Theory of computation; Theoretical computer science; Discrete mathematics; Algorithm; Physics","score_opus":0.017181617998753437,"score_gpt":0.24480148613027702,"score_spread":0.22761986813152357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335338794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06610137,0.0076575126,0.87186074,0.0031344327,0.0010853849,0.00031347448,0.0008960299,0.0018511803,0.047099862],"genre_scores_gemma":[0.43428132,0.0022918475,0.51102644,0.0016530614,0.0012220348,0.00040298735,0.0020852457,0.00061441207,0.04642267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970017,0.0011620029,0.00016120824,0.0005762121,0.00086706,0.00023184539],"domain_scores_gemma":[0.9927908,0.0036770655,0.00029604422,0.0021356803,0.0008325716,0.00026780766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024947016,0.00087563036,0.0017272523,0.0027813073,0.0013894466,0.002537629,0.0023974276,0.0023494756,0.019022664],"category_scores_gemma":[0.01748041,0.0006945623,0.0009766537,0.0039931354,0.0014761419,0.0043351785,0.0031867658,0.002349716,0.005372943],"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":[0.0011258947,0.0003798027,0.0022813703,0.0004833015,0.00016957261,0.00035830543,0.00022652901,0.050155655,0.0062324894,0.2739357,0.041461725,0.6231896],"study_design_scores_gemma":[0.0002615191,0.00047188418,0.0006841909,0.00018612678,0.0001426659,0.0014439014,0.00009642189,0.507667,0.010428818,0.44459432,0.033958055,0.00006508553],"about_ca_topic_score_codex":0.0006359945,"about_ca_topic_score_gemma":0.0016475485,"teacher_disagreement_score":0.019022664,"about_ca_system_score_codex":0.0009245441,"about_ca_system_score_gemma":0.002213795,"threshold_uncertainty_score":0.0636372},"labels":[],"label_agreement":null},{"id":"W2343253211","doi":"10.22215/etd/2006-06665","title":"Tries in data retrieval and syntactic pattern recognition","year":2006,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University; Canadian Heritage","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence","score_opus":0.037603577541395546,"score_gpt":0.2863093366257132,"score_spread":0.24870575908431763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343253211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011675621,0.03644615,0.90961415,0.007470929,0.0028418836,0.00029770305,0.00056687434,0.0028970907,0.028189661],"genre_scores_gemma":[0.17161998,0.027569935,0.6994836,0.0040204744,0.0058418172,0.0007208558,0.0039213826,0.0014313478,0.085390575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99463487,0.0018263173,0.000665598,0.00087932457,0.0016011752,0.00039266242],"domain_scores_gemma":[0.9921077,0.0047573475,0.0002684068,0.001809037,0.00088555034,0.00017200214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042318185,0.00095892156,0.0019526175,0.005659578,0.0011930651,0.006930714,0.002355894,0.0028191912,0.012379773],"category_scores_gemma":[0.014279565,0.0008357801,0.0015282095,0.008410133,0.0034762907,0.012783873,0.003023284,0.0025232935,0.0093145],"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":[0.00029138062,0.00013769504,0.0016180103,0.0010379078,0.00018905466,0.00047618072,0.0007066825,0.007961221,0.0051847533,0.2921418,0.047080718,0.64317465],"study_design_scores_gemma":[0.000091434355,0.00024049848,0.0013956429,0.00045256835,0.00016964598,0.0016531986,0.0006895896,0.12676467,0.019493377,0.6236686,0.22528605,0.00009473194],"about_ca_topic_score_codex":0.0015381441,"about_ca_topic_score_gemma":0.0017934922,"teacher_disagreement_score":0.012379773,"about_ca_system_score_codex":0.0012833507,"about_ca_system_score_gemma":0.0016641524,"threshold_uncertainty_score":0.04141444},"labels":[],"label_agreement":null},{"id":"W2356993399","doi":"","title":"Improvement of a Single Cycle Sorting Algorithm Based on Data Driven","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Sorting; Sorting algorithm; Algorithm","score_opus":0.014582753511773327,"score_gpt":0.2463451098631085,"score_spread":0.23176235635133519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2356993399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09266108,0.0009133139,0.8979355,0.00022120164,0.0003542598,0.00021334883,0.000102239435,0.002780828,0.004818188],"genre_scores_gemma":[0.27470648,0.0006619622,0.7173284,0.00022764057,0.000115109324,0.00012587295,0.00044327945,0.00018819838,0.006202973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99915123,0.00007321638,0.000052802512,0.00013313371,0.0005252906,0.00006432647],"domain_scores_gemma":[0.99878746,0.00027952253,0.00006926953,0.0001714578,0.00063995854,0.00005235265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055837247,0.00056525815,0.00074896414,0.0015927053,0.00072108296,0.0007898181,0.0011269393,0.000549606,0.0023345316],"category_scores_gemma":[0.0017273148,0.00025976828,0.0004675671,0.0016776721,0.00038569167,0.001334505,0.00054707815,0.0006578367,0.0006312188],"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":[0.0009305463,0.00032603007,0.0023478842,0.00029447282,0.00009130202,0.00016911926,0.00016490018,0.046125825,0.12666668,0.021447208,0.0048697963,0.79656625],"study_design_scores_gemma":[0.00018570447,0.0009567159,0.0015925091,0.000040547136,0.000112669186,0.0008065004,0.00006334126,0.77484727,0.1854412,0.009505236,0.026345525,0.000102785154],"about_ca_topic_score_codex":0.0015530703,"about_ca_topic_score_gemma":0.002048086,"teacher_disagreement_score":0.0023345316,"about_ca_system_score_codex":0.0007303457,"about_ca_system_score_gemma":0.0013686091,"threshold_uncertainty_score":0.007809818},"labels":[],"label_agreement":null},{"id":"W2359427212","doi":"","title":"Display Random Code in the C","year":2005,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Unicode; Computer science; Code (set theory); Programming language; Encoding (memory); ANSI C; Operating system; Theoretical computer science; Artificial intelligence; Software; Set (abstract data type)","score_opus":0.00904962128602122,"score_gpt":0.2527045737053329,"score_spread":0.24365495241931168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2359427212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019948872,0.0005400138,0.8855982,0.0013783015,0.0009114546,0.0001992683,0.0010267715,0.050359167,0.040037967],"genre_scores_gemma":[0.36772656,0.0010662721,0.5199152,0.0028443174,0.0005075055,0.00045654963,0.0031765655,0.019712225,0.08459475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969988,0.00041969965,0.00021424939,0.0006382443,0.0014395408,0.0002894518],"domain_scores_gemma":[0.99020255,0.0025043103,0.00060210295,0.003234251,0.0032652568,0.00019150245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001308068,0.0010356456,0.00059994514,0.0015250318,0.0011543845,0.003324843,0.001956475,0.0014116479,0.01734018],"category_scores_gemma":[0.0151124345,0.00048509918,0.00044702727,0.0017766055,0.0011922965,0.003662412,0.0014607767,0.001717284,0.009576277],"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":[0.0011785306,0.0000939447,0.0044716857,0.0007581977,0.000093722505,0.0025083178,0.00138777,0.011338786,0.07442683,0.2724232,0.20470357,0.42661542],"study_design_scores_gemma":[0.000061133556,0.00024885716,0.0016141707,0.00030745,0.00008298415,0.00390863,0.00026895714,0.11130532,0.26232395,0.05067706,0.5689538,0.0002476901],"about_ca_topic_score_codex":0.0038222969,"about_ca_topic_score_gemma":0.002296726,"teacher_disagreement_score":0.01734018,"about_ca_system_score_codex":0.0013521397,"about_ca_system_score_gemma":0.0016011968,"threshold_uncertainty_score":0.05800867},"labels":[],"label_agreement":null},{"id":"W2371742128","doi":"","title":"Adaptive joint source-channel coding and MAP decoding of error correction arithmetic codes","year":2007,"lang":"en","type":"article","venue":"Journal of Communications","topic":"Algorithms and Data Compression","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":"Advanced Micro Devices (Canada)","funders":"","keywords":"Variable-length code; Decoding methods; Computer science; Algorithm; Arithmetic coding; Shannon–Fano coding; Coding gain; Adaptive coding; List decoding; Coding (social sciences); Channel (broadcasting); Source code; Theoretical computer science; Context-adaptive binary arithmetic coding; Concatenated error correction code; Mathematics; Block code; Telecommunications; Data compression; Statistics","score_opus":0.07945490248697054,"score_gpt":0.3163771763641999,"score_spread":0.23692227387722933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2371742128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01620629,0.0002317053,0.98155516,0.00007078942,0.000045922934,0.00005584444,0.000029174891,0.00027124642,0.0015338779],"genre_scores_gemma":[0.55331904,0.0003779165,0.4410181,0.000086639644,0.00008351345,0.00016935419,0.00012824235,0.00004917126,0.004767997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901366,0.00030208618,0.000039829523,0.00013071409,0.00042309467,0.000090568836],"domain_scores_gemma":[0.9988236,0.00049268076,0.00010900329,0.00017140318,0.0003694135,0.00003391106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085563114,0.0006697505,0.0006603244,0.00080527365,0.0004681368,0.0006179455,0.00080995384,0.00073450635,0.0010305626],"category_scores_gemma":[0.0030974066,0.00026936972,0.00039627324,0.0011009586,0.0006119731,0.0010506581,0.0010287836,0.00083945674,0.00037987967],"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":[0.00073637307,0.00012406509,0.001370435,0.0002663088,0.00017372215,0.00044234938,0.00037314938,0.33554628,0.07285572,0.10827668,0.0025224371,0.4773125],"study_design_scores_gemma":[0.000030054622,0.00010161026,0.00024728515,0.0000128041665,0.000029083441,0.0002529908,0.000017557675,0.953876,0.032869034,0.009962661,0.0025707986,0.000030174551],"about_ca_topic_score_codex":0.0021367802,"about_ca_topic_score_gemma":0.0022454283,"teacher_disagreement_score":0.0021367802,"about_ca_system_score_codex":0.0004297241,"about_ca_system_score_gemma":0.0011754737,"threshold_uncertainty_score":0.004525006},"labels":[],"label_agreement":null},{"id":"W2379852994","doi":"","title":"A Modified Burrows-Wheeler Transform Compression Algorithm Based On Least Frequently Used Replacement","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lossless compression; Computer science; Algorithm; Compression (physics); Compression ratio; Data compression; Sorting; Block (permutation group theory); Mathematics","score_opus":0.020831556210158933,"score_gpt":0.2451250473243288,"score_spread":0.22429349111416985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2379852994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039233647,0.0013172217,0.9540677,0.00020349983,0.00032273654,0.00020102717,0.00029311414,0.0023285446,0.0020325226],"genre_scores_gemma":[0.15842924,0.00068020244,0.83055437,0.00013944136,0.00023208278,0.00023945628,0.0010372541,0.00020309813,0.008484987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994211,0.0000612739,0.00005042812,0.00009012497,0.0003318004,0.00004530226],"domain_scores_gemma":[0.9993709,0.00012475085,0.00006220716,0.00012494302,0.00029114992,0.000026107562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004366046,0.000658813,0.0007938766,0.0017296901,0.00052138005,0.00071001507,0.0011655982,0.00073099846,0.0026285043],"category_scores_gemma":[0.0017835237,0.00021000039,0.000466163,0.0020105047,0.00034166308,0.0013912646,0.00038606746,0.0006839904,0.001321357],"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":[0.0004396566,0.000109807486,0.00082597806,0.00013709544,0.000042890973,0.00022908337,0.0000921674,0.015156795,0.10115461,0.0077548334,0.005713035,0.8683441],"study_design_scores_gemma":[0.0002542351,0.00083101715,0.0038284287,0.00005593167,0.00011519385,0.003651829,0.000084100655,0.67670435,0.26028618,0.0044904705,0.049514335,0.00018381997],"about_ca_topic_score_codex":0.0024627645,"about_ca_topic_score_gemma":0.0030945174,"teacher_disagreement_score":0.0026285043,"about_ca_system_score_codex":0.00044351642,"about_ca_system_score_gemma":0.00095242535,"threshold_uncertainty_score":0.008793235},"labels":[],"label_agreement":null},{"id":"W2394599118","doi":"","title":"A Parameterized Formulation for the Maximum Number of Runs Problem.","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Parameterized complexity; Combinatorics; Mathematics; String (physics); Bounded function; Alphabet; Upper and lower bounds; Diagonal; Table (database); Function (biology); Discrete mathematics; Constant (computer programming); Computer science; Mathematical analysis; Geometry","score_opus":0.04923647735752655,"score_gpt":0.2761872924681522,"score_spread":0.22695081511062565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394599118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0584477,0.0014361179,0.90539044,0.0032885578,0.00018856929,0.00031410222,0.0027460188,0.000858833,0.02732977],"genre_scores_gemma":[0.5467566,0.0012574993,0.41684377,0.0011497543,0.00061328063,0.0013107262,0.004590271,0.0016678647,0.02581028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949621,0.0018384684,0.00032231509,0.0015015262,0.0008116737,0.000564037],"domain_scores_gemma":[0.98560137,0.010193134,0.0013231983,0.0014350583,0.0007540838,0.00069315423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004275995,0.0020463618,0.0022363428,0.0013315057,0.0014972534,0.0051511005,0.0046773804,0.0034687847,0.015340171],"category_scores_gemma":[0.022135263,0.0014522473,0.002655752,0.0026669824,0.002715432,0.012297491,0.0028956048,0.0048176083,0.0017689958],"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":[0.0005339453,0.00023870403,0.0014116988,0.0006624252,0.00015119405,0.00044948296,0.00040799237,0.29761785,0.0027775515,0.6483073,0.01253516,0.03490655],"study_design_scores_gemma":[0.00007358526,0.00008757445,0.0002588791,0.00008114799,0.00004033278,0.00020574623,0.00010249706,0.45945165,0.0010433858,0.5318346,0.006784418,0.000036252226],"about_ca_topic_score_codex":0.0021035112,"about_ca_topic_score_gemma":0.0021199198,"teacher_disagreement_score":0.015340171,"about_ca_system_score_codex":0.0037937097,"about_ca_system_score_gemma":0.0022191447,"threshold_uncertainty_score":0.05131799},"labels":[],"label_agreement":null},{"id":"W2394735685","doi":"","title":"An adaptive hybrid pattern-matching algorithm on indeterminate strings","year":2008,"lang":"en","type":"article","venue":"UWA Profiles and Research Repository (University of Western Australia)","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Indeterminate; Algorithm; Matching (statistics); Computer science; Pattern matching; String searching algorithm; Algorithm design; Hybrid algorithm (constraint satisfaction); Successor cardinal; Component (thermodynamics); Mathematics; Artificial intelligence","score_opus":0.07667599149036339,"score_gpt":0.3071999573066203,"score_spread":0.23052396581625692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394735685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044149946,0.00017288962,0.9511158,0.00012259827,0.00007865588,0.000077254386,0.00012363572,0.0018621559,0.00229713],"genre_scores_gemma":[0.1934991,0.00007477728,0.8001528,0.000117124444,0.000028126706,0.00010751387,0.00039787518,0.00017786479,0.0054448918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993223,0.0000936062,0.00006850689,0.00018458691,0.00028157956,0.00004939413],"domain_scores_gemma":[0.9991366,0.0002347956,0.00006603278,0.00024501252,0.00027974372,0.000037856706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054666656,0.00036383956,0.00052222185,0.0013767686,0.00045923653,0.0008735828,0.0015702567,0.000609677,0.0032437132],"category_scores_gemma":[0.0023725948,0.00021312841,0.0002948576,0.0019408717,0.00043070383,0.0014064059,0.0010101657,0.0005000698,0.001244768],"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":[0.0004754027,0.00008444304,0.0014056658,0.000081168975,0.000035693494,0.00016869107,0.00015004381,0.026305724,0.04368143,0.020140668,0.0049804845,0.90249074],"study_design_scores_gemma":[0.000100860314,0.00018617867,0.0010043242,0.000019481598,0.000025492873,0.00050133525,0.000085786916,0.9026364,0.05284084,0.026696144,0.015869189,0.00003395889],"about_ca_topic_score_codex":0.0011487768,"about_ca_topic_score_gemma":0.00137644,"teacher_disagreement_score":0.0032437132,"about_ca_system_score_codex":0.00039211317,"about_ca_system_score_gemma":0.00054084684,"threshold_uncertainty_score":0.010851324},"labels":[],"label_agreement":null},{"id":"W2395489635","doi":"10.5555/2627817.2627898","title":"Dynamic graph connectivity in polylogarithmic worst case time","year":2013,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":141,"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 Victoria","funders":"","keywords":"Combinatorics; Time complexity; Binary logarithm; Amortized analysis; Computer science; Graph; Enhanced Data Rates for GSM Evolution; Preprocessor; Upper and lower bounds; Data structure; Matching (statistics); Discrete mathematics; Path (computing); Sequence (biology); Mathematics; Algorithm","score_opus":0.0061883137897224185,"score_gpt":0.23245964126258176,"score_spread":0.22627132747285933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395489635","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21077752,0.00545556,0.68683434,0.020283883,0.00089780416,0.001075591,0.008608968,0.024105253,0.041961078],"genre_scores_gemma":[0.62149113,0.0014868889,0.3544714,0.0020251232,0.00060846703,0.0010131132,0.006820535,0.0023044366,0.00977897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9867727,0.0022076576,0.0008988484,0.0030668494,0.0046942485,0.0023597253],"domain_scores_gemma":[0.9613441,0.025901232,0.0025923532,0.00735708,0.0017955876,0.0010096396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004080792,0.0025951725,0.0023033724,0.0023479415,0.0022494167,0.007816906,0.005159807,0.003523184,0.013378687],"category_scores_gemma":[0.03013197,0.0016927128,0.0021581622,0.006499964,0.0030490565,0.016658118,0.0038320504,0.0045483825,0.0031634895],"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":[0.004730037,0.0011154205,0.008050062,0.001990333,0.00052287226,0.00094913907,0.0011489699,0.46529475,0.03721242,0.0889868,0.0668744,0.3231249],"study_design_scores_gemma":[0.0007033346,0.00028837883,0.0014128253,0.00012679929,0.0002802556,0.0010723723,0.00047958086,0.7546094,0.014282493,0.21149322,0.0151639255,0.00008742775],"about_ca_topic_score_codex":0.0065651513,"about_ca_topic_score_gemma":0.012516663,"teacher_disagreement_score":0.013378687,"about_ca_system_score_codex":0.006602376,"about_ca_system_score_gemma":0.0065852692,"threshold_uncertainty_score":0.047903836},"labels":[],"label_agreement":null},{"id":"W2396090462","doi":"","title":"Maximal Separation On 2-D Arrays.","year":2012,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Separation (statistics); Combinatorics; Statistics","score_opus":0.017611880251572173,"score_gpt":0.27098344384787426,"score_spread":0.2533715635963021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396090462","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050702192,0.002408626,0.8712729,0.001003099,0.00042520612,0.0000785795,0.0013139732,0.0028355892,0.069959775],"genre_scores_gemma":[0.5282621,0.0018182774,0.42683473,0.0009308474,0.00034009924,0.00026971992,0.0029888023,0.00080834946,0.03774712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920243,0.00019309876,0.00007362359,0.00014594887,0.00023352077,0.000151494],"domain_scores_gemma":[0.99856347,0.0006408727,0.00012209127,0.00041824416,0.00014324179,0.000112063324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004655218,0.00065322197,0.00069697754,0.0013096406,0.0007761399,0.0019472204,0.00086684333,0.0007199885,0.011293983],"category_scores_gemma":[0.003235977,0.00036121605,0.00051670696,0.0022347122,0.0008028483,0.003289843,0.003067904,0.0012075084,0.004604167],"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":[0.0006010703,0.0001384759,0.0008124581,0.00043365805,0.00005927086,0.00019731213,0.00031126218,0.022456942,0.014677445,0.6173184,0.033151247,0.3098425],"study_design_scores_gemma":[0.00007982312,0.00009445985,0.00045192052,0.00012504235,0.000028780809,0.00042441094,0.00023274016,0.08445154,0.021593867,0.8370357,0.055438913,0.000042784384],"about_ca_topic_score_codex":0.0005446331,"about_ca_topic_score_gemma":0.001064274,"teacher_disagreement_score":0.011293983,"about_ca_system_score_codex":0.00066168077,"about_ca_system_score_gemma":0.0008252988,"threshold_uncertainty_score":0.037782133},"labels":[],"label_agreement":null},{"id":"W2396953629","doi":"","title":"An Improved Deterministic #SAT Algorithm for Small De Morgan Formulas.","year":2013,"lang":"en","type":"article","venue":"Electronic colloquium on computational complexity","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics; Time complexity; Algorithm; Constructive; struct; Running time; Deterministic algorithm; Discrete mathematics; Computational complexity theory; Random variable; Combinatorics; Computer science; Statistics","score_opus":0.022861646840508044,"score_gpt":0.2770429379744798,"score_spread":0.25418129113397175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396953629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009537929,0.00016448165,0.9835597,0.00036671796,0.000074841606,0.00016738316,0.00020134539,0.0026512304,0.0032763705],"genre_scores_gemma":[0.13515869,0.00017051991,0.8581742,0.00042992877,0.00009146723,0.0003971471,0.0010653262,0.0004291034,0.0040835384],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99691474,0.0006340271,0.00023075074,0.00063321256,0.0013377883,0.0002494411],"domain_scores_gemma":[0.99338806,0.003112988,0.00033262983,0.0020630022,0.0009956486,0.00010761426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019869448,0.0008848508,0.0009824033,0.0011671503,0.00089593994,0.0013124945,0.002907715,0.0010042064,0.0064852205],"category_scores_gemma":[0.01129123,0.000852096,0.0017798158,0.001506873,0.0012795397,0.0034902275,0.003442374,0.0024690456,0.0024059422],"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":[0.0005981116,0.00029245878,0.002557239,0.0004478367,0.00020063168,0.00023139032,0.00032167122,0.090671904,0.033497427,0.1221183,0.021914274,0.7271487],"study_design_scores_gemma":[0.00023116574,0.00019904428,0.00086046645,0.00004763637,0.00015898231,0.00041399847,0.00006407601,0.82833123,0.03053601,0.118139744,0.020953864,0.00006381501],"about_ca_topic_score_codex":0.002678521,"about_ca_topic_score_gemma":0.005037392,"teacher_disagreement_score":0.0064852205,"about_ca_system_score_codex":0.0013736999,"about_ca_system_score_gemma":0.002478526,"threshold_uncertainty_score":0.021695256},"labels":[],"label_agreement":null},{"id":"W2397530947","doi":"","title":"A Relationship Between Balanced Modular Tableaux and k-Ribbon Shapes.","year":2013,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ribbon; Modular design; Mathematics; Combinatorics; Pure mathematics; Arithmetic; Geometry; Computer science; Programming language","score_opus":0.018803994930197788,"score_gpt":0.23826742004078735,"score_spread":0.21946342511058956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397530947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15677609,0.0016635116,0.7036099,0.0016300494,0.00053497317,0.00011745122,0.00095963344,0.0016998039,0.13300861],"genre_scores_gemma":[0.7712122,0.0011027141,0.18822594,0.0009556929,0.00034267217,0.00019799103,0.0009649216,0.0006314968,0.03636646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99928916,0.00014432806,0.000058066245,0.00015773885,0.00026491086,0.000085768],"domain_scores_gemma":[0.9964592,0.00191515,0.00039293777,0.0007530327,0.00030558396,0.00017403248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053237926,0.00037235484,0.0005206041,0.0012102374,0.0010096851,0.0028581207,0.0010568233,0.0010011537,0.014480084],"category_scores_gemma":[0.007869856,0.0004239795,0.00041133625,0.0022311192,0.0019019672,0.003985481,0.0021407125,0.0016984799,0.0030635027],"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":[0.00008164345,0.000022423277,0.0003205242,0.00004140102,0.00000571603,0.00015479322,0.000114182985,0.003411948,0.0017542061,0.95146704,0.0036214176,0.039004624],"study_design_scores_gemma":[0.00001499034,0.000029995452,0.00019180974,0.000031063282,0.0000075119106,0.00037516726,0.00006107516,0.017010495,0.002259693,0.9686328,0.011364417,0.000020969735],"about_ca_topic_score_codex":0.0005029893,"about_ca_topic_score_gemma":0.0008496435,"teacher_disagreement_score":0.014480084,"about_ca_system_score_codex":0.00081594585,"about_ca_system_score_gemma":0.00048017892,"threshold_uncertainty_score":0.048440695},"labels":[],"label_agreement":null},{"id":"W2398155836","doi":"","title":"Low Space Data Structures for Geometric Range Mode Query.","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo; University of Manitoba","funders":"","keywords":"Multiset; Combinatorics; Data structure; Space (punctuation); Range (aeronautics); Set (abstract data type); Range query (database); Mathematics; Point (geometry); Word (group theory); Mode (computer interface); Discrete mathematics; Computer science; Sargable; Web search query; Geometry; Information retrieval; Search engine","score_opus":0.03091431701458262,"score_gpt":0.28805398397124826,"score_spread":0.2571396669566656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398155836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09188928,0.00381291,0.8545289,0.0024904185,0.00043407892,0.0010605496,0.011297684,0.02296849,0.011517753],"genre_scores_gemma":[0.28609535,0.00074654113,0.68841237,0.0009100541,0.00027956633,0.0017624992,0.014759902,0.0012563777,0.0057774],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960821,0.0006084257,0.00060148357,0.00080761855,0.0014825288,0.0004179362],"domain_scores_gemma":[0.98594624,0.004149264,0.0013578438,0.006753476,0.0013236189,0.00046951926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001751883,0.0016998686,0.0017403035,0.0025578812,0.0014767197,0.0029268684,0.004384672,0.0018185896,0.011619816],"category_scores_gemma":[0.0137932105,0.0010377492,0.0017789156,0.006941185,0.0013173562,0.011036286,0.0058198576,0.0025611669,0.0051130913],"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":[0.004548492,0.001287638,0.0096673295,0.0017910291,0.00028265885,0.00057760754,0.0016007738,0.03784138,0.05775948,0.110823505,0.11332579,0.6604944],"study_design_scores_gemma":[0.0010756176,0.0021347404,0.004273098,0.00037288864,0.00029962556,0.0018372899,0.0014850602,0.49659613,0.06960621,0.28298858,0.1389567,0.0003740938],"about_ca_topic_score_codex":0.002507837,"about_ca_topic_score_gemma":0.0041041407,"teacher_disagreement_score":0.011619816,"about_ca_system_score_codex":0.0023279816,"about_ca_system_score_gemma":0.002199284,"threshold_uncertainty_score":0.038872123},"labels":[],"label_agreement":null},{"id":"W2398258650","doi":"","title":"Time-Windowed Closest Pair","year":2015,"lang":"en","type":"article","venue":"Canadian Conference on Computational Geometry","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Quadtree; Dimension (graph theory); Point (geometry); Interval (graph theory); Set (abstract data type); Computer science; Binary logarithm; Computational geometry; Data structure; Algorithm; Word (group theory); Combinatorics; Constant (computer programming); Mathematics; Theoretical computer science; Geometry","score_opus":0.04467829215851175,"score_gpt":0.25425152611678137,"score_spread":0.20957323395826963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398258650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042016707,0.001428601,0.94708496,0.00031991498,0.00035436818,0.0002610978,0.0019357534,0.0030921572,0.003506432],"genre_scores_gemma":[0.3009835,0.00094353507,0.68552876,0.00020880952,0.00021248223,0.00036267054,0.003976847,0.00033978958,0.007443664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982205,0.00020146726,0.00018797736,0.00060329726,0.00063577184,0.00015086756],"domain_scores_gemma":[0.9970407,0.00062966364,0.00036924414,0.0012521078,0.0005191394,0.00018907103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080294313,0.0010466365,0.0019178286,0.002853713,0.0010292081,0.0015582629,0.0032585678,0.0011621868,0.008113219],"category_scores_gemma":[0.008794039,0.0007311281,0.0006798548,0.0050206855,0.0007330928,0.00491389,0.0041448404,0.0012444473,0.004478222],"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":[0.0026158483,0.00047876648,0.0040161363,0.0006486384,0.00019163676,0.00057000614,0.0007223298,0.13836117,0.02632535,0.05249997,0.032189395,0.7413808],"study_design_scores_gemma":[0.00024468635,0.00077951467,0.0011223492,0.00010169876,0.0000753543,0.0013443563,0.00049002655,0.82145137,0.03791596,0.092809126,0.043538883,0.00012663133],"about_ca_topic_score_codex":0.0017417447,"about_ca_topic_score_gemma":0.0023989803,"teacher_disagreement_score":0.008113219,"about_ca_system_score_codex":0.0007244046,"about_ca_system_score_gemma":0.0011562967,"threshold_uncertainty_score":0.027141392},"labels":[],"label_agreement":null},{"id":"W2399734345","doi":"","title":"Improved Two-Way Bit-parallel Search","year":2014,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","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":"Sheridan College","funders":"","keywords":"String searching algorithm; Computer science; Sublinear function; String (physics); Algorithm; Bit array; Matching (statistics); Approximate string matching; Bit (key); Pattern matching; Theoretical computer science; Mathematics; Discrete mathematics; Artificial intelligence","score_opus":0.02664909317515039,"score_gpt":0.2750735642817489,"score_spread":0.24842447110659852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2399734345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01731867,0.00081961363,0.9675991,0.00024093862,0.00022400537,0.00016980205,0.00033016523,0.005070286,0.0082275085],"genre_scores_gemma":[0.11863752,0.00042400556,0.86477804,0.00030432126,0.00010695255,0.0003082483,0.0011786523,0.0005151262,0.013747198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981287,0.00022574922,0.00017729535,0.00031157906,0.0010028176,0.00015391206],"domain_scores_gemma":[0.99783915,0.00047718047,0.00013407008,0.0007080831,0.00075716624,0.000084430096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007976225,0.0010621197,0.0016187755,0.0023140074,0.0009219719,0.0016589082,0.0028871833,0.0011554324,0.011291475],"category_scores_gemma":[0.004047522,0.0005897181,0.0009718936,0.004416298,0.0007408416,0.0037252284,0.0022791917,0.0013014178,0.005132981],"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":[0.0008408947,0.00027666712,0.0009806419,0.00034301486,0.000101679245,0.000161883,0.000118663396,0.08338434,0.022044947,0.03536168,0.013492619,0.8428929],"study_design_scores_gemma":[0.00025262428,0.00025141556,0.00052209955,0.000038889735,0.00006451525,0.0004895144,0.00005019807,0.91871315,0.02251058,0.03708261,0.019966463,0.00005791256],"about_ca_topic_score_codex":0.003225834,"about_ca_topic_score_gemma":0.004674462,"teacher_disagreement_score":0.011291475,"about_ca_system_score_codex":0.0010858213,"about_ca_system_score_gemma":0.002481461,"threshold_uncertainty_score":0.03777373},"labels":[],"label_agreement":null},{"id":"W2400068012","doi":"10.1016/j.tcs.2016.05.024","title":"Document retrieval with one wildcard","year":2016,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Substring; Symbol (formal); String (physics); Computer science; Data structure; Alphabet; Extension (predicate logic); Linear space; Space (punctuation); Pattern matching; Listing (finance); Combinatorics; Mathematics; Algorithm; Theoretical computer science; Information retrieval; Artificial intelligence; Linguistics","score_opus":0.00782486814828636,"score_gpt":0.22878456495539984,"score_spread":0.22095969680711347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400068012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07474711,0.005721474,0.87296754,0.0039436948,0.0036836271,0.0007254364,0.0016700996,0.0059850104,0.030556053],"genre_scores_gemma":[0.35623544,0.0015951954,0.58551675,0.0013714117,0.0019431947,0.00033451017,0.0026743733,0.0006684658,0.049660675],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959661,0.00082410383,0.00054872606,0.00078977755,0.0014934781,0.00037776344],"domain_scores_gemma":[0.994076,0.0013009255,0.00020202357,0.0031701222,0.001075664,0.00017517865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027208778,0.000959416,0.0023890075,0.0049217236,0.0015091484,0.0049495357,0.0018502683,0.0026263962,0.021744505],"category_scores_gemma":[0.013724502,0.0005864383,0.00079726346,0.004679692,0.0021414012,0.010222742,0.0034394178,0.0017368294,0.013412553],"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":[0.0011677359,0.00027920154,0.0010810603,0.00031582272,0.0000714419,0.00033760894,0.00011327345,0.0050356598,0.02497456,0.1075382,0.032652494,0.8264329],"study_design_scores_gemma":[0.00044892277,0.0013378039,0.0017677435,0.00024045873,0.00021790169,0.00511862,0.00030373115,0.34413457,0.087404065,0.4471567,0.1116536,0.0002159521],"about_ca_topic_score_codex":0.0006483893,"about_ca_topic_score_gemma":0.000807883,"teacher_disagreement_score":0.021744505,"about_ca_system_score_codex":0.00092367595,"about_ca_system_score_gemma":0.0015891024,"threshold_uncertainty_score":0.07274264},"labels":[],"label_agreement":null},{"id":"W2401761585","doi":"","title":"TAC 2010 Summarization Track - Update Summarization with Interview Algorithm.","year":2010,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Algorithm; Data mining; Information retrieval; Artificial intelligence; Operating system","score_opus":0.00681810827578963,"score_gpt":0.22892436102194372,"score_spread":0.2221062527461541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401761585","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011451936,0.0012897647,0.91094905,0.0007830469,0.0010533782,0.0011853403,0.018614985,0.042170033,0.012502515],"genre_scores_gemma":[0.07261875,0.00051466783,0.80812955,0.00036749867,0.0003983205,0.0013622926,0.08428209,0.0020224517,0.03030432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977411,0.00070586894,0.00024704594,0.00045746475,0.000652568,0.00019592152],"domain_scores_gemma":[0.99497014,0.00095104944,0.00020735826,0.001106251,0.0026182523,0.00014697833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002536437,0.0012958859,0.0012285718,0.004998607,0.0013882014,0.0024551302,0.0022344666,0.00134937,0.016159322],"category_scores_gemma":[0.01241948,0.0004502598,0.0007996686,0.0044314694,0.0003773511,0.0030233099,0.0018339831,0.0013998976,0.013901706],"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":[0.0006181653,0.00014157362,0.00076124154,0.00039984364,0.000121414305,0.00008447002,0.00026200418,0.0050441595,0.009961334,0.005905197,0.22111312,0.75558746],"study_design_scores_gemma":[0.00042933912,0.0008115742,0.004134316,0.00017860201,0.00038159726,0.0005614501,0.00093473465,0.4007646,0.069636874,0.04001461,0.4819389,0.00021335292],"about_ca_topic_score_codex":0.0062013185,"about_ca_topic_score_gemma":0.009780661,"teacher_disagreement_score":0.016159322,"about_ca_system_score_codex":0.0008350629,"about_ca_system_score_gemma":0.0021806995,"threshold_uncertainty_score":0.054058313},"labels":[],"label_agreement":null},{"id":"W2401936767","doi":"","title":"A Computational Framework for Determining Square-maximal Strings.","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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":"Square (algebra); Computer science; Computational complexity theory; Algorithm; Mathematics; Theoretical computer science; Geometry","score_opus":0.03328067568074888,"score_gpt":0.3036181077934534,"score_spread":0.2703374321127045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401936767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07512522,0.000470969,0.9056173,0.0008069807,0.00006557832,0.00022291919,0.0006637545,0.00081102113,0.016216263],"genre_scores_gemma":[0.37301698,0.00020158177,0.620961,0.00024327487,0.00007299186,0.0003059171,0.0011568479,0.00022459525,0.0038167993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968611,0.00083706796,0.00025984802,0.0007294877,0.00097404217,0.00033836218],"domain_scores_gemma":[0.98910564,0.007999416,0.0006885476,0.0011928871,0.00071824715,0.00029525545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002803183,0.0006530704,0.0009450629,0.003356518,0.0019185815,0.0040597944,0.0024625808,0.0015405972,0.0075399266],"category_scores_gemma":[0.020886658,0.0007026185,0.0016287969,0.0030207224,0.0039885696,0.0071391044,0.0033211096,0.0016526568,0.0013491992],"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":[0.00035901624,0.00010736,0.0019490386,0.00031130563,0.000049379683,0.00017569539,0.0004936309,0.059545893,0.005213866,0.82929194,0.0043363627,0.098166525],"study_design_scores_gemma":[0.00004092291,0.000074138654,0.00037890972,0.000075142096,0.000027340155,0.00019553938,0.0001837718,0.2651311,0.0064592,0.7199533,0.0074441996,0.00003645338],"about_ca_topic_score_codex":0.0021298563,"about_ca_topic_score_gemma":0.0031404288,"teacher_disagreement_score":0.0075399266,"about_ca_system_score_codex":0.002813049,"about_ca_system_score_gemma":0.0023339852,"threshold_uncertainty_score":0.025223553},"labels":[],"label_agreement":null},{"id":"W2402207292","doi":"","title":"Réduction de la complexité spatiale et temporelle du Compact Prediction Tree pour la prédiction de séquences.","year":2015,"lang":"fr","type":"book-chapter","venue":"EGC eBooks","topic":"Algorithms and Data Compression","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":"Université de Moncton","funders":"","keywords":"Humanities; Mathematics; Forestry; Philosophy; Geography","score_opus":0.062190671040444324,"score_gpt":0.28672233175876516,"score_spread":0.22453166071832084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402207292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055674605,0.0029999416,0.9347764,0.00051417766,0.00018461289,0.00008436644,0.0008704958,0.0027391575,0.0021561228],"genre_scores_gemma":[0.3064454,0.001937732,0.6806509,0.00021340161,0.00013013367,0.00023976312,0.0032858937,0.00037394706,0.006722829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992084,0.00014381231,0.000055710923,0.00012940794,0.00041137252,0.00005130119],"domain_scores_gemma":[0.9965191,0.0022892486,0.00018225008,0.00039665768,0.00054991496,0.000062903506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001067471,0.00078074384,0.00057189236,0.0010346984,0.00037975053,0.0010172621,0.00096526096,0.0007416267,0.0032426927],"category_scores_gemma":[0.006316531,0.0003329812,0.00056138966,0.0015346593,0.0004570675,0.0021472168,0.0007598367,0.0012630046,0.0010900955],"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":[0.0003674392,0.00008480038,0.0021037895,0.0003595862,0.00005541195,0.0001678455,0.00021504241,0.20241638,0.027354559,0.014994841,0.011304297,0.74057597],"study_design_scores_gemma":[0.000015075659,0.00009054682,0.00088995305,0.000034944514,0.000021597705,0.00018389414,0.000051456944,0.97187334,0.013210921,0.0075541153,0.0060589598,0.00001527816],"about_ca_topic_score_codex":0.0068899314,"about_ca_topic_score_gemma":0.00805358,"teacher_disagreement_score":0.0068899314,"about_ca_system_score_codex":0.00089915894,"about_ca_system_score_gemma":0.0013203695,"threshold_uncertainty_score":0.013699651},"labels":[],"label_agreement":null},{"id":"W2402462786","doi":"","title":"A Sequence Representation of the Dyck Path Poset.","year":2010,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Sequence (biology); Path (computing); Partially ordered set; Representation (politics); Combinatorics; Computer science; Genetics; Computer network; Law","score_opus":0.016478758246875603,"score_gpt":0.2668124878955848,"score_spread":0.2503337296487092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402462786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03971028,0.0012929967,0.7760531,0.0010422661,0.00092480844,0.00022950115,0.0077254944,0.0029554244,0.1700663],"genre_scores_gemma":[0.4692532,0.0019499226,0.39460516,0.00057223183,0.0003946301,0.00047967816,0.01618467,0.0014263021,0.11513411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995733,0.00006889905,0.000028852237,0.000116251904,0.00015123058,0.00006152861],"domain_scores_gemma":[0.9996055,0.00010235464,0.00003327034,0.0001057554,0.000107545144,0.00004562007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030168472,0.00072605256,0.0005071536,0.001593403,0.00074798445,0.0023534847,0.0009433909,0.00076028076,0.04761989],"category_scores_gemma":[0.0015124212,0.00027113187,0.0004340184,0.0022057856,0.0008075702,0.0026661633,0.0012809309,0.0016365804,0.011092379],"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":[0.00013012001,0.000056378598,0.00017650459,0.00012067577,0.000007949084,0.00012418187,0.0002053373,0.0046667433,0.0027273141,0.88047904,0.019614475,0.09169137],"study_design_scores_gemma":[0.0000328671,0.000087756845,0.00023978634,0.00008308857,0.00001530875,0.00038741744,0.00022859199,0.024598788,0.00320337,0.85188216,0.11920727,0.000033604323],"about_ca_topic_score_codex":0.0012724197,"about_ca_topic_score_gemma":0.0017714478,"teacher_disagreement_score":0.04761989,"about_ca_system_score_codex":0.00059737806,"about_ca_system_score_gemma":0.0006420702,"threshold_uncertainty_score":0.15930438},"labels":[],"label_agreement":null},{"id":"W2402546767","doi":"","title":"Pebbling Graph Products.","year":2011,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Graph; Combinatorics","score_opus":0.028439147918434132,"score_gpt":0.22996687108919764,"score_spread":0.2015277231707635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402546767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027124295,0.0022710452,0.9051991,0.0008581853,0.0005865328,0.00014012189,0.0008341326,0.0030278238,0.05995866],"genre_scores_gemma":[0.30099878,0.0027174312,0.615327,0.00087898155,0.00041949644,0.00030808817,0.0027761946,0.0019352889,0.0746388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868435,0.00027301974,0.00010080212,0.00030913623,0.0004923423,0.00014030562],"domain_scores_gemma":[0.9968066,0.0010733606,0.00015917259,0.0013834813,0.00045742333,0.00011992379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009229124,0.0009058452,0.0008198942,0.0022358808,0.001239309,0.0025460883,0.0014202832,0.0008754548,0.0190348],"category_scores_gemma":[0.0067254417,0.0005098332,0.0008759867,0.0034979496,0.0016198494,0.004890759,0.0029410867,0.0020344316,0.0099596325],"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":[0.00018243684,0.00011258177,0.00046576417,0.00030304398,0.0000453919,0.00019440759,0.0002632209,0.009907163,0.005539432,0.62229395,0.022629734,0.33806288],"study_design_scores_gemma":[0.000023404811,0.0000727408,0.00018712647,0.00009755539,0.00003513016,0.000525571,0.00011560335,0.03687202,0.0143072475,0.8825661,0.06517082,0.000026794163],"about_ca_topic_score_codex":0.0010377478,"about_ca_topic_score_gemma":0.0021256013,"teacher_disagreement_score":0.0190348,"about_ca_system_score_codex":0.00091037474,"about_ca_system_score_gemma":0.00089530036,"threshold_uncertainty_score":0.06367779},"labels":[],"label_agreement":null},{"id":"W2402627865","doi":"10.1049/iet-com.2016.0077","title":"Simplified search and construction of capacity‐approaching variable‐length constrained sequence codes","year":2016,"lang":"en","type":"article","venue":"IET Communications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Computer science; Variable (mathematics); Algorithm; Mathematics; Mathematical optimization; Genetics; Biology","score_opus":0.08051680200167717,"score_gpt":0.29591895667195695,"score_spread":0.2154021546702798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402627865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012766159,0.00009399809,0.9842681,0.00004687409,0.000014280052,0.000058386115,0.00006263946,0.00016851137,0.0025210383],"genre_scores_gemma":[0.17431684,0.00029300654,0.8218721,0.00007429868,0.00002346818,0.00024742927,0.00031470766,0.00007855486,0.0027795853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99930644,0.00019665623,0.000035932197,0.000066500186,0.00033309063,0.00006130346],"domain_scores_gemma":[0.9987048,0.00072978524,0.00011633148,0.00018600535,0.00022425553,0.00003883376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006218798,0.00058936636,0.00068386557,0.0008428471,0.00033226673,0.00059827435,0.000827792,0.00062676653,0.0026260703],"category_scores_gemma":[0.0035557246,0.00037700395,0.00048194916,0.0010403696,0.0006463271,0.00096395,0.0010590667,0.001005062,0.00071961596],"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":[0.00028881768,0.00010128568,0.00045235266,0.00027770252,0.00004785633,0.00032168574,0.00023824892,0.45359626,0.06457776,0.2856314,0.003071446,0.19139527],"study_design_scores_gemma":[0.000051161336,0.00012226272,0.00017509419,0.00002780803,0.00001269748,0.00020034121,0.000024854178,0.92741114,0.027937405,0.037834138,0.0061676875,0.000035478726],"about_ca_topic_score_codex":0.0010211549,"about_ca_topic_score_gemma":0.0011877539,"teacher_disagreement_score":0.0026260703,"about_ca_system_score_codex":0.0004179151,"about_ca_system_score_gemma":0.001234291,"threshold_uncertainty_score":0.008785069},"labels":[],"label_agreement":null},{"id":"W2402764450","doi":"","title":"Grid Proximity Graphs: LOGs, GIGs and GIRLs.","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Computer science; Grid; Graph; Theoretical computer science; Mathematics","score_opus":0.008767690436409204,"score_gpt":0.20319046322948925,"score_spread":0.19442277279308004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402764450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27281278,0.0035444843,0.6707821,0.0052776057,0.0004901458,0.0005574135,0.004045659,0.0030461855,0.039443687],"genre_scores_gemma":[0.84296983,0.0013823897,0.14019461,0.00094081595,0.00022270353,0.00034051048,0.0035404295,0.0003303017,0.010078381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987826,0.00029024467,0.0000808423,0.00035265772,0.00033082557,0.00016281732],"domain_scores_gemma":[0.99444973,0.002687982,0.00090997753,0.0010821312,0.00043745642,0.0004327584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051726453,0.000515207,0.00068157795,0.0011176692,0.0011715797,0.0020555856,0.0010060511,0.001157165,0.003844574],"category_scores_gemma":[0.00803998,0.00041301321,0.00051183207,0.0025804464,0.0017790062,0.005345991,0.0022636037,0.0016847822,0.00058617734],"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":[0.0009670471,0.00020653398,0.02142824,0.00084807095,0.000089322624,0.0015191545,0.0020231947,0.044495367,0.006461726,0.61873466,0.04125075,0.2619759],"study_design_scores_gemma":[0.00006437302,0.00019498532,0.005948347,0.00016580384,0.00008000075,0.003956386,0.0029402778,0.1191455,0.007832814,0.78146285,0.07812183,0.00008682724],"about_ca_topic_score_codex":0.0020879505,"about_ca_topic_score_gemma":0.0027678276,"teacher_disagreement_score":0.003844574,"about_ca_system_score_codex":0.0010124197,"about_ca_system_score_gemma":0.00071458967,"threshold_uncertainty_score":0.012861431},"labels":[],"label_agreement":null},{"id":"W2405237896","doi":"10.1007/s13369-016-2162-y","title":"Reconfigurable Hardware Accelerator for Profile Hidden Markov Models","year":2016,"lang":"en","type":"article","venue":"Arabian Journal for Science and Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Deanship of Scientific Research, Prince Sattam bin Abdulaziz University; Institut national de recherche en informatique et en automatique (INRIA); Prince Sattam bin Abdulaziz University","keywords":"Field-programmable gate array; Computer science; Viterbi algorithm; Speedup; VHDL; Ranging; Parallel computing; Throughput; Computer hardware; Overhead (engineering); Embedded system; Vector processor; Hardware acceleration; Reuse; Hidden Markov model; Engineering; Operating system; Artificial intelligence","score_opus":0.026048170031870942,"score_gpt":0.24542194199868156,"score_spread":0.21937377196681063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405237896","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29550248,0.0019254885,0.66632307,0.00065747154,0.0006942747,0.00011113747,0.00088949036,0.021330848,0.012565782],"genre_scores_gemma":[0.88878757,0.00023281132,0.10381333,0.00020180352,0.000059460857,0.00005157936,0.0007128563,0.0001566482,0.005984036],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998319,0.00002013491,0.000011018909,0.000047184316,0.00004457108,0.00004518067],"domain_scores_gemma":[0.99974316,0.00008479305,0.000028702232,0.00006529045,0.00005011122,0.000028021683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019750868,0.00045878085,0.00037256506,0.0003351165,0.00025642393,0.0005255545,0.0012207406,0.00033046037,0.009155782],"category_scores_gemma":[0.0007252061,0.00024524084,0.00039203113,0.00035219712,0.00011387519,0.00067743566,0.00040638167,0.0007129782,0.0018038644],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033827918,0.0006594722,0.008016375,0.00048312912,0.00039253276,0.0011673525,0.0002151826,0.19722652,0.10146132,0.020442527,0.03182718,0.63472563],"study_design_scores_gemma":[0.00009093231,0.00023581999,0.0008932362,0.000021038739,0.000056370984,0.0001780718,0.000035326928,0.9651793,0.022857025,0.0052643223,0.0051612286,0.000027333415],"about_ca_topic_score_codex":0.001985955,"about_ca_topic_score_gemma":0.0036445651,"teacher_disagreement_score":0.009155782,"about_ca_system_score_codex":0.00037792043,"about_ca_system_score_gemma":0.00072731957,"threshold_uncertainty_score":0.030629158},"labels":[],"label_agreement":null},{"id":"W2405265970","doi":"10.1007/978-1-59745-514-5_13","title":"An Introduction to the Lagan Alignment Toolkit","year":2007,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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","score_opus":0.01809006376225506,"score_gpt":0.3937985868039047,"score_spread":0.37570852304164964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405265970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009444663,0.007668626,0.82457376,0.0015415931,0.001748724,0.00040220958,0.026630899,0.105621316,0.03086836],"genre_scores_gemma":[0.0067495215,0.008038848,0.86602294,0.0018516215,0.0006950723,0.0012023335,0.057447337,0.023604296,0.034388073],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970049,0.0007566357,0.000402057,0.00045686815,0.0011740951,0.0002053424],"domain_scores_gemma":[0.99631613,0.0015691638,0.00026252284,0.00061982963,0.0009795146,0.00025297693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002573618,0.0017200207,0.0015113982,0.0036914793,0.0017151535,0.0043999436,0.004272436,0.0015450079,0.09842651],"category_scores_gemma":[0.010383183,0.0020052267,0.001311155,0.0061474135,0.00071292755,0.004605797,0.003578143,0.0046058237,0.1246017],"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":[0.00018605047,0.00008311032,0.000590969,0.0016108169,0.00008791151,0.00036436293,0.00027874083,0.0034781038,0.005251304,0.033483673,0.61699015,0.3375948],"study_design_scores_gemma":[0.000024417574,0.000018655268,0.00033858683,0.0002385864,0.000014761274,0.0004987447,0.00005463644,0.0042863805,0.0018451824,0.028579595,0.96402055,0.00008005275],"about_ca_topic_score_codex":0.0030411961,"about_ca_topic_score_gemma":0.004347182,"teacher_disagreement_score":0.09842651,"about_ca_system_score_codex":0.001146693,"about_ca_system_score_gemma":0.0025867007,"threshold_uncertainty_score":0.32926953},"labels":[],"label_agreement":null},{"id":"W2406653127","doi":"10.1016/j.dam.2016.04.025","title":"A computational substantiation of the <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si7.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>d</mml:mi></mml:math>-step approach to the number of distinct squares problem","year":2016,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cover (algebra); String (physics); Mathematics; Ternary operation; Combinatorics; Algorithm; Discrete mathematics; Computer science","score_opus":0.015257785665206249,"score_gpt":0.2403468883504535,"score_spread":0.22508910268524726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406653127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009341815,0.00036227313,0.9308964,0.009438476,0.000573935,0.000118142285,0.00059879967,0.00032279413,0.048347376],"genre_scores_gemma":[0.2556267,0.0010930495,0.70378494,0.00446848,0.0014786201,0.0006531679,0.0020495062,0.0007775743,0.030067826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99139345,0.0041531334,0.0004297296,0.0015267045,0.0020264066,0.00047067468],"domain_scores_gemma":[0.92634,0.05925674,0.0010459647,0.0075284755,0.0049661864,0.00086259755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009830826,0.0016334793,0.0015657612,0.0020876683,0.0035188259,0.0052473224,0.006666945,0.0038690087,0.0323938],"category_scores_gemma":[0.07377249,0.0011297727,0.003064151,0.0024629883,0.009814747,0.013298918,0.010644659,0.011413458,0.0065432475],"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":[0.00011240045,0.000097135795,0.00034974542,0.00020014532,0.00003513127,0.00010643017,0.00018729772,0.014629239,0.0005210237,0.9576795,0.011496959,0.014584927],"study_design_scores_gemma":[0.0000364722,0.00004690874,0.00015831308,0.00005893558,0.000015340695,0.00008029706,0.0000710526,0.08195092,0.0010358273,0.90956926,0.0069506955,0.000025882227],"about_ca_topic_score_codex":0.0026627167,"about_ca_topic_score_gemma":0.005756133,"teacher_disagreement_score":0.0323938,"about_ca_system_score_codex":0.0027266587,"about_ca_system_score_gemma":0.0048954906,"threshold_uncertainty_score":0.10836798},"labels":[],"label_agreement":null},{"id":"W2407207612","doi":"10.1016/j.tcs.2016.02.036","title":"Permuted scaled matching","year":2016,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Substring; Permutation (music); Matching (statistics); String searching algorithm; Mathematics; Scaling; Computer science; 3-dimensional matching; Pattern matching; Algorithm; Blossom algorithm; Artificial intelligence; Set (abstract data type); Statistics","score_opus":0.007325258038249031,"score_gpt":0.23932446873999386,"score_spread":0.2319992107017448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407207612","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13697232,0.0007363405,0.7425933,0.0017965401,0.0012828963,0.00039141037,0.0020020716,0.0027018392,0.11152326],"genre_scores_gemma":[0.6274848,0.00048258217,0.29359052,0.0012732962,0.0004648201,0.00033034303,0.0027812696,0.001082329,0.072510116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980567,0.00046478852,0.00014365722,0.0006049566,0.0004998241,0.00023009689],"domain_scores_gemma":[0.99756926,0.00043529808,0.00014416019,0.0013400154,0.0003614057,0.00014990717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011468186,0.0005107453,0.0009306325,0.0014323164,0.0011205982,0.0019465477,0.001283542,0.0015413167,0.029800449],"category_scores_gemma":[0.006378703,0.00039675858,0.00088897184,0.0020132996,0.0013975211,0.0033205573,0.0030265094,0.0014759641,0.006980914],"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":[0.0006390491,0.00019965676,0.0009769747,0.00017939426,0.00007910231,0.0003523738,0.00020625207,0.013995088,0.014058551,0.7428029,0.020684566,0.20582604],"study_design_scores_gemma":[0.00010242125,0.00017842017,0.00071487785,0.000050597184,0.0000614859,0.0006345864,0.00014025331,0.08018687,0.013913371,0.8608843,0.043085013,0.000047737536],"about_ca_topic_score_codex":0.0004650009,"about_ca_topic_score_gemma":0.00047378294,"teacher_disagreement_score":0.029800449,"about_ca_system_score_codex":0.0006981053,"about_ca_system_score_gemma":0.00094743667,"threshold_uncertainty_score":0.099692404},"labels":[],"label_agreement":null},{"id":"W2407396938","doi":"10.48550/arxiv.1605.08102","title":"Finding Synchronization Codes to Boost Compression by Substring Enumeration","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Substring; Lossless compression; Computer science; Synchronization (alternating current); Enumeration; Data compression; Benchmark (surveying); Compression (physics); Byte; Algorithm; Parallel computing; Data structure; Mathematics; Telecommunications; Computer hardware; Discrete mathematics","score_opus":0.04989120929542976,"score_gpt":0.19780159155662028,"score_spread":0.14791038226119052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407396938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18476003,0.0004994874,0.80684525,0.0005948664,0.000087525674,0.000082956045,0.00013419829,0.001013828,0.005981791],"genre_scores_gemma":[0.6807745,0.00037132011,0.31511167,0.00021078356,0.00006288777,0.000112858324,0.00038248577,0.00031638605,0.0026571965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963343,0.000084975094,0.000024080846,0.000057661542,0.0001490984,0.000050783307],"domain_scores_gemma":[0.9979948,0.0012379421,0.00018167113,0.00031530423,0.00020774142,0.00006261577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054854277,0.00047197498,0.0005185399,0.0007624029,0.00043725478,0.000691411,0.00074527075,0.0007977844,0.0021887713],"category_scores_gemma":[0.006062514,0.00023423183,0.00032832,0.0012145767,0.0009838655,0.0017673798,0.0009414882,0.00097004167,0.00040766754],"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":[0.0003611039,0.00019499572,0.0031160363,0.00028590922,0.00003758327,0.00023066686,0.00025131484,0.5185113,0.04034728,0.23108369,0.0070540993,0.19852601],"study_design_scores_gemma":[0.000023788678,0.000047720518,0.00013791703,0.000016856686,0.000005656582,0.00005248421,0.000032845568,0.9296617,0.014509155,0.053877175,0.0016237934,0.000010797202],"about_ca_topic_score_codex":0.0014219703,"about_ca_topic_score_gemma":0.0023944038,"teacher_disagreement_score":0.0021887713,"about_ca_system_score_codex":0.00067738525,"about_ca_system_score_gemma":0.0010657761,"threshold_uncertainty_score":0.007322192},"labels":[],"label_agreement":null},{"id":"W2408378546","doi":"","title":"A Contribution to the characterization of Quasi-groups that are Isotopic to Abelian groups.","year":2010,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Abelian group; Mathematics; Characterization (materials science); Pure mathematics; Nanotechnology; Materials science","score_opus":0.00892940864600261,"score_gpt":0.2285353064254919,"score_spread":0.2196058977794893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408378546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12546593,0.004586497,0.7499912,0.005109522,0.002252411,0.0001598727,0.0012290283,0.0013712632,0.109834276],"genre_scores_gemma":[0.6694539,0.0034956732,0.26154897,0.002499732,0.00400413,0.00020145313,0.0028215477,0.0010073493,0.054967187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986131,0.00034230668,0.00011946567,0.0003141875,0.00045178583,0.00015903034],"domain_scores_gemma":[0.9944892,0.0024051582,0.00038099833,0.001727306,0.00058838533,0.00040891336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011764943,0.0005819985,0.00072923646,0.0017513903,0.0014370292,0.0026076671,0.0012054375,0.0009543184,0.009642332],"category_scores_gemma":[0.007456944,0.0003424581,0.0006395506,0.0022123272,0.002496786,0.007339859,0.0035216978,0.0023058404,0.0025285436],"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":[0.00015013745,0.00014628695,0.0017892586,0.00024692863,0.000033503133,0.00015649656,0.00052327436,0.0017042673,0.0050492594,0.898441,0.016547592,0.07521194],"study_design_scores_gemma":[0.000021309073,0.00008810878,0.0009445736,0.000060673334,0.00002735265,0.00063005113,0.00022570282,0.012206998,0.0038221953,0.9154756,0.066463985,0.000033465614],"about_ca_topic_score_codex":0.00050017424,"about_ca_topic_score_gemma":0.0004470554,"teacher_disagreement_score":0.009642332,"about_ca_system_score_codex":0.00067555014,"about_ca_system_score_gemma":0.0007121124,"threshold_uncertainty_score":0.03225684},"labels":[],"label_agreement":null},{"id":"W2408443083","doi":"10.1609/socs.v3i1.18227","title":"Partial-Expansion A* with Selective Node Generation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Combinatorial Search","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"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":"Node (physics); A priori and a posteriori; Computer science; Branching (polymer chemistry); Domain (mathematical analysis); Theoretical computer science; Mathematics; Algorithm; Combinatorics; Mathematical optimization; Engineering","score_opus":0.01693971839691495,"score_gpt":0.253200546666199,"score_spread":0.23626082826928407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408443083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103222996,0.001071913,0.86347896,0.0006706261,0.0001928247,0.00046338892,0.0010060889,0.008846615,0.021046713],"genre_scores_gemma":[0.41541898,0.0003702102,0.57049847,0.00058345,0.000078552,0.000484606,0.0016500772,0.0006688034,0.010246915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995486,0.00011274562,0.00003590408,0.000107491454,0.00012354551,0.00007163774],"domain_scores_gemma":[0.9982509,0.0008077615,0.00008572539,0.0006035853,0.00018789886,0.00006410764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006177041,0.00064831146,0.00055897736,0.00081734225,0.00053344213,0.0005668011,0.0016320414,0.0008068556,0.0070836726],"category_scores_gemma":[0.0025818103,0.00028021095,0.0007998427,0.0013160112,0.00073902204,0.0018669846,0.0018715141,0.00096145563,0.0015534719],"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":[0.00057612266,0.00033442446,0.0023106425,0.00048777414,0.0000814606,0.00050601974,0.00027051542,0.09043116,0.03770797,0.036320634,0.02432345,0.8066498],"study_design_scores_gemma":[0.00017892488,0.00050560455,0.0010856881,0.00006786716,0.00010348526,0.0011564235,0.00017576427,0.8373048,0.0447023,0.08087748,0.033788726,0.00005302898],"about_ca_topic_score_codex":0.001168586,"about_ca_topic_score_gemma":0.002131149,"teacher_disagreement_score":0.0070836726,"about_ca_system_score_codex":0.0003155479,"about_ca_system_score_gemma":0.00094304176,"threshold_uncertainty_score":0.023697257},"labels":[],"label_agreement":null},{"id":"W2408481389","doi":"","title":"An Improved Version of the Runs Algorithm Based on Crochemore's Partitioning Algorithm.","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Algorithm; Computer science; Running time; Extension (predicate logic); Time complexity; String (physics); Mathematics","score_opus":0.013906092562567998,"score_gpt":0.2243569673255715,"score_spread":0.2104508747630035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408481389","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025160622,0.00048287303,0.95014286,0.00024232079,0.00031456767,0.00023295941,0.00060564146,0.005966306,0.016851854],"genre_scores_gemma":[0.09132349,0.00014599545,0.8885181,0.00018894354,0.00011483515,0.00017996374,0.0016132208,0.0010428771,0.016872533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986394,0.00020738256,0.000106074905,0.00039316577,0.00051554624,0.00013839026],"domain_scores_gemma":[0.99870443,0.0002512409,0.0000663819,0.00055380195,0.000366734,0.00005742059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007393946,0.0008667376,0.0008301614,0.0014647773,0.0008376182,0.0012390575,0.0020139616,0.0009348147,0.01024321],"category_scores_gemma":[0.0027373808,0.00061170314,0.0010817858,0.0015664628,0.0007929882,0.0026697463,0.0016811858,0.0015090046,0.0052613416],"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":[0.0008885445,0.00016611068,0.0016590242,0.0002944854,0.0001280574,0.00029016487,0.00030185297,0.030123048,0.057932757,0.07657681,0.023762975,0.8078761],"study_design_scores_gemma":[0.00049387704,0.00068581605,0.0042999783,0.00018348926,0.00017941745,0.0018372223,0.0002399145,0.5503713,0.118890986,0.124173544,0.19833975,0.00030478838],"about_ca_topic_score_codex":0.0034430674,"about_ca_topic_score_gemma":0.0063765934,"teacher_disagreement_score":0.01024321,"about_ca_system_score_codex":0.00062724814,"about_ca_system_score_gemma":0.0012018553,"threshold_uncertainty_score":0.03426695},"labels":[],"label_agreement":null},{"id":"W2426990689","doi":"10.1007/s00453-021-00799-7","title":"Range Majorities and Minorities in Arrays","year":2021,"lang":"en","type":"preprint","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Academy of Finland","keywords":"Parameterized complexity; String (physics); Linear space; Combinatorics; Mathematics; Range (aeronautics); Space (punctuation); Function (biology); Time complexity; Polynomial; Constant (computer programming); Omega; Sigma; Alphabet; Discrete mathematics; Physics; Mathematical analysis; Computer science; Quantum mechanics","score_opus":0.015675739032133228,"score_gpt":0.23813348238730814,"score_spread":0.2224577433551749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2426990689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6474969,0.0020547784,0.28604183,0.0036216856,0.00022809346,0.000058567683,0.00084414665,0.0005469356,0.05910713],"genre_scores_gemma":[0.95237374,0.0006210469,0.034126036,0.00038377085,0.00030533466,0.000070688315,0.00032978045,0.00016563658,0.011624103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881065,0.0003426204,0.000071067545,0.00028546606,0.00027892957,0.00021116546],"domain_scores_gemma":[0.9919911,0.0055697067,0.0006854934,0.0008872331,0.00051771593,0.0003487282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009821338,0.0003315709,0.0006310314,0.0018742533,0.0016990361,0.003111483,0.0009102903,0.00070089113,0.006755355],"category_scores_gemma":[0.010964209,0.00038059155,0.0005086418,0.002235546,0.0027251304,0.004183023,0.002923764,0.0019920736,0.00093147706],"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":[0.00025406067,0.000043996675,0.0046049,0.00008354128,0.000017781147,0.00012737467,0.00097413885,0.006715987,0.0026863536,0.92454237,0.004632705,0.05531673],"study_design_scores_gemma":[0.000018181909,0.00002427622,0.00096649857,0.000034308825,0.000019373876,0.0002629554,0.00050991576,0.026127743,0.002987308,0.96351886,0.00551611,0.00001446546],"about_ca_topic_score_codex":0.00054318795,"about_ca_topic_score_gemma":0.0006548526,"teacher_disagreement_score":0.006755355,"about_ca_system_score_codex":0.0006782464,"about_ca_system_score_gemma":0.00037232222,"threshold_uncertainty_score":0.022598922},"labels":[],"label_agreement":null},{"id":"W2463091895","doi":"10.1093/bioinformatics/btw397","title":"ntHash: recursive nucleotide hashing","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Hash function; Computer science; Expediting; Software; Data mining; Sequence (biology); Universal hashing; Theoretical computer science; Hash table; Biology; Genetics; Programming language","score_opus":0.017284746271392315,"score_gpt":0.23445768803110562,"score_spread":0.2171729417597133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463091895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027334634,0.0015148252,0.93281287,0.0003716009,0.0004521915,0.0003314487,0.0026428127,0.025621118,0.00891849],"genre_scores_gemma":[0.25663736,0.00067356805,0.71539766,0.00042379048,0.00024335671,0.0005057827,0.009912255,0.0020704654,0.014135736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986986,0.0002309792,0.00012711108,0.00023058326,0.00060782535,0.00010494505],"domain_scores_gemma":[0.9981304,0.0005490819,0.000143654,0.000607425,0.00046153204,0.00010793246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012249296,0.0006355576,0.00072500296,0.0009525071,0.00066093827,0.0010783852,0.002021729,0.0006327538,0.011136613],"category_scores_gemma":[0.0059810868,0.00040599718,0.00058967003,0.0014617229,0.0008782407,0.0017259783,0.0024001934,0.0009290772,0.009234875],"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":[0.001615801,0.00015828894,0.0051684803,0.0009871981,0.000112095295,0.00025985282,0.000460339,0.04329789,0.045042094,0.04136975,0.07508264,0.7864456],"study_design_scores_gemma":[0.00036887793,0.0009581667,0.003337289,0.00016895735,0.00009384479,0.0015799772,0.0002537536,0.5846991,0.15500417,0.09393184,0.1593722,0.00023190223],"about_ca_topic_score_codex":0.0015493548,"about_ca_topic_score_gemma":0.0018730557,"teacher_disagreement_score":0.011136613,"about_ca_system_score_codex":0.00058308116,"about_ca_system_score_gemma":0.0014061568,"threshold_uncertainty_score":0.037255704},"labels":[],"label_agreement":null},{"id":"W2463883732","doi":"10.3906/elk-1410-124","title":"A new dictionary-based preprocessor that uses radix-190 numbering","year":2016,"lang":"en","type":"article","venue":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science; Preprocessor; Byte; Numbering; Decoding methods; Word (group theory); Natural language processing; Information retrieval; Artificial intelligence; Programming language; Algorithm; Linguistics","score_opus":0.015413401969115274,"score_gpt":0.22788006257657778,"score_spread":0.2124666606074625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463883732","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07756756,0.002106031,0.88413113,0.00030193117,0.00073423417,0.00051341415,0.002468728,0.022923835,0.009253057],"genre_scores_gemma":[0.07924202,0.000812934,0.8948009,0.00034735713,0.00020226336,0.00030090523,0.0061045284,0.001669979,0.016519096],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995695,0.00002882369,0.00006108065,0.00013600638,0.00016386315,0.000040698502],"domain_scores_gemma":[0.9990036,0.00025540288,0.00009483275,0.00025985672,0.000340724,0.0000456442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041742917,0.0010019252,0.0006890837,0.0017121638,0.0005643282,0.0012605727,0.0009230329,0.00068189955,0.013119098],"category_scores_gemma":[0.0022603353,0.00045635397,0.00063952163,0.0020460053,0.00041580302,0.0014181209,0.000857189,0.0009903031,0.007969478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088473636,0.00009222268,0.0011775724,0.00050167413,0.000052872936,0.00035400948,0.00021776473,0.0022380191,0.22774217,0.0034170118,0.009934266,0.75338775],"study_design_scores_gemma":[0.00017474644,0.0016116578,0.0064695673,0.00011841393,0.00020145714,0.002514208,0.00033123186,0.06650362,0.7369935,0.0024321862,0.18248574,0.00016363703],"about_ca_topic_score_codex":0.0015224998,"about_ca_topic_score_gemma":0.0022048939,"teacher_disagreement_score":0.013119098,"about_ca_system_score_codex":0.00036339293,"about_ca_system_score_gemma":0.0010180149,"threshold_uncertainty_score":0.043887794},"labels":[],"label_agreement":null},{"id":"W2471701653","doi":"10.48550/arxiv.1112.5636","title":"Tight lower bounds for online labeling problem","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Akademie Věd České Republiky; Grantová Agentura České Republiky; National Science Foundation","keywords":"Upper and lower bounds; Combinatorics; Integer (computer science); Order (exchange); Constant (computer programming); Range (aeronautics); Space (punctuation); Online algorithm; Binary logarithm; Mathematics; Computer science; Algorithm; Class (philosophy); Discrete mathematics; Artificial intelligence","score_opus":0.10124113931914487,"score_gpt":0.20077301964048075,"score_spread":0.09953188032133588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471701653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057594303,0.014535611,0.782486,0.016708175,0.0012477519,0.00061575166,0.0043080975,0.005700774,0.11680342],"genre_scores_gemma":[0.52909106,0.01061025,0.38666463,0.0073380726,0.0035900157,0.0023215928,0.010682764,0.005388779,0.044312797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877698,0.00268451,0.00045671585,0.0023852664,0.0032314905,0.0034722122],"domain_scores_gemma":[0.9379755,0.04928868,0.0022276107,0.0058291145,0.002540658,0.0021384552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0078037255,0.0056874705,0.00599004,0.0034444015,0.004515128,0.010410165,0.010042513,0.0067856945,0.031930085],"category_scores_gemma":[0.052978493,0.0021969706,0.0034414844,0.0067519,0.0044306954,0.029765563,0.0074399197,0.015754173,0.0080780005],"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":[0.002882612,0.0023101103,0.0051845293,0.0032585107,0.00034939268,0.0005437739,0.0011348465,0.26073235,0.009338918,0.43161097,0.09702737,0.18562664],"study_design_scores_gemma":[0.00022029,0.00025594866,0.00087971246,0.00027000986,0.00017590617,0.00035625312,0.00026160674,0.5150245,0.0027290063,0.46253332,0.017225733,0.00006764821],"about_ca_topic_score_codex":0.0042127147,"about_ca_topic_score_gemma":0.0053624567,"teacher_disagreement_score":0.031930085,"about_ca_system_score_codex":0.007267616,"about_ca_system_score_gemma":0.004353117,"threshold_uncertainty_score":0.10681677},"labels":[],"label_agreement":null},{"id":"W2472682600","doi":"10.1049/el.2016.1605","title":"Variable length integer codes based on radix number system conversion","year":2016,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"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":"Radix (gastropod); Integer (computer science); Arithmetic; Mathematics; Computer science; Discrete mathematics; Algorithm; Biology","score_opus":0.004673090901351482,"score_gpt":0.19625765264287617,"score_spread":0.1915845617415247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472682600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07086987,0.002047837,0.9109067,0.00037418125,0.0004253688,0.00016833509,0.00028175206,0.0016007159,0.013325206],"genre_scores_gemma":[0.48627394,0.0016613641,0.49440026,0.00037916034,0.00020356748,0.0003268496,0.0010865674,0.00024393282,0.015424353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995377,0.000078643214,0.000031078867,0.00007597223,0.00021859615,0.00005790658],"domain_scores_gemma":[0.9993094,0.00018441949,0.000086569235,0.00016081642,0.00023162378,0.000027099548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033202957,0.000404797,0.0003644026,0.0013453952,0.00043991924,0.0007307296,0.0006063432,0.0004933851,0.0026459391],"category_scores_gemma":[0.0016067359,0.00015016265,0.00024198585,0.0016467363,0.00082815846,0.0011112473,0.00063737924,0.0007938206,0.0009965417],"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":[0.0005870271,0.00007164652,0.00142385,0.00027588828,0.000032485314,0.00037821033,0.00035281095,0.03452027,0.16373275,0.19320472,0.006656911,0.5987634],"study_design_scores_gemma":[0.00015525147,0.0006559642,0.0022417742,0.00021310526,0.000072256495,0.0017043959,0.00018751688,0.4199942,0.43022165,0.04727354,0.09708739,0.00019305314],"about_ca_topic_score_codex":0.0010577096,"about_ca_topic_score_gemma":0.0010338962,"teacher_disagreement_score":0.0026459391,"about_ca_system_score_codex":0.00048061964,"about_ca_system_score_gemma":0.0007922333,"threshold_uncertainty_score":0.008851528},"labels":[],"label_agreement":null},{"id":"W2473775606","doi":"10.29173/cais748","title":"Scanning Compressed Full Text Files","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University; Acadia University","funders":"","keywords":"Computer science; Inverted index; Compression (physics); Data compression; Index (typography); Data file; File format; Information retrieval; Computer graphics (images); Database; World Wide Web; Search engine indexing; Artificial intelligence","score_opus":0.018604863686409866,"score_gpt":0.2325702940413815,"score_spread":0.21396543035497162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473775606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28636104,0.0063289376,0.4009243,0.0061470857,0.0031343678,0.0027985182,0.04000762,0.029413663,0.2248845],"genre_scores_gemma":[0.37131852,0.0039068917,0.32520002,0.0013760617,0.00076281605,0.00092099875,0.06475764,0.003275212,0.22848184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945134,0.000040880554,0.000033482436,0.00007484701,0.00033299156,0.000066433255],"domain_scores_gemma":[0.9975846,0.0005835424,0.00008833052,0.0004492134,0.0012054085,0.000088885026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045926872,0.0004710594,0.00040446935,0.001763866,0.0006270545,0.0013442008,0.0010392318,0.0005154575,0.05121252],"category_scores_gemma":[0.003106373,0.00023546268,0.00021863174,0.0028401804,0.00040098303,0.0011612822,0.0009296201,0.0005337091,0.011258262],"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":[0.0009428289,0.00015116959,0.0013999247,0.00056149665,0.000031257314,0.0012102284,0.0005974177,0.0025238846,0.10291607,0.0074068983,0.15649758,0.72576123],"study_design_scores_gemma":[0.00023787715,0.00071989174,0.011100836,0.0002704493,0.000067205205,0.003641869,0.0010822079,0.045005094,0.23124893,0.015460288,0.69099176,0.0001735914],"about_ca_topic_score_codex":0.004621779,"about_ca_topic_score_gemma":0.009400908,"teacher_disagreement_score":0.05121252,"about_ca_system_score_codex":0.0007004547,"about_ca_system_score_gemma":0.0012193175,"threshold_uncertainty_score":0.17132294},"labels":[],"label_agreement":null},{"id":"W2479313071","doi":"10.1017/cbo9780511546884.016","title":"The Path-Greedy Algorithm","year":2007,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Path (computing); Greedy algorithm; Computer science; Algorithm; Computer network","score_opus":0.0239906268607839,"score_gpt":0.20916272126694968,"score_spread":0.18517209440616578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479313071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003356803,0.002463774,0.94984883,0.000784279,0.00044588323,0.00022804554,0.000796189,0.003732336,0.038343847],"genre_scores_gemma":[0.056744467,0.0023554573,0.8929518,0.00056091155,0.00026447143,0.00046898663,0.0027627577,0.0015661196,0.042325083],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989452,0.00023381,0.000056332894,0.0002436255,0.00036622884,0.0001549408],"domain_scores_gemma":[0.99899775,0.0004464959,0.00003565781,0.00026136232,0.00019798231,0.00006083429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086636515,0.001775848,0.0015372735,0.0016967391,0.0010849884,0.002144258,0.0028256867,0.0018183257,0.037603024],"category_scores_gemma":[0.00454296,0.0006049307,0.0011138078,0.0030722427,0.00090367283,0.0027430712,0.0026194656,0.0023157177,0.021552095],"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":[0.00025179063,0.00013374144,0.0003004993,0.00038477939,0.00008487878,0.00010304269,0.000086267326,0.07374545,0.0019683305,0.06541234,0.110136434,0.74739236],"study_design_scores_gemma":[0.00022837748,0.00016263804,0.00037897442,0.00016693435,0.000085560336,0.00057578925,0.00012454654,0.627667,0.0043222634,0.2566845,0.10954123,0.00006216632],"about_ca_topic_score_codex":0.004288845,"about_ca_topic_score_gemma":0.0057040467,"teacher_disagreement_score":0.037603024,"about_ca_system_score_codex":0.001071836,"about_ca_system_score_gemma":0.0031799404,"threshold_uncertainty_score":0.12579465},"labels":[],"label_agreement":null},{"id":"W2484345647","doi":"10.4018/978-1-60566-661-7.ch017","title":"Communication Issues in Scalable Parallel Computing","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Computer science; Scalability; Distributed computing; Models of communication; Theoretical computer science; Limit (mathematics); Communications system; String (physics); Parallel computing; Computer network; Mathematics; Database","score_opus":0.018248964417969048,"score_gpt":0.2694645164170153,"score_spread":0.25121555199904627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484345647","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037429861,0.10591197,0.6396418,0.020894412,0.007043048,0.0002826897,0.0001680497,0.0017114027,0.22060363],"genre_scores_gemma":[0.111124866,0.123193674,0.5684181,0.006389098,0.012353321,0.0014319267,0.0006925475,0.002185932,0.17421068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980361,0.0004309916,0.00010651732,0.00019271357,0.0011057965,0.00012803062],"domain_scores_gemma":[0.9978941,0.0013749597,0.000063534244,0.00029048527,0.00031615462,0.00006070574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017158304,0.0013010671,0.000990179,0.0009484035,0.0019116693,0.0034469834,0.0019470267,0.0017812083,0.012215247],"category_scores_gemma":[0.0056417617,0.0010227725,0.0009764852,0.0036610847,0.0025473759,0.00773485,0.0021583245,0.0048450003,0.005876203],"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":[0.000028282855,0.000033411106,0.00007387032,0.0007254956,0.000023390938,0.00013677758,0.00027084208,0.015234643,0.0010199563,0.7950414,0.06864485,0.118767045],"study_design_scores_gemma":[0.000017961154,0.00003606464,0.00007351091,0.00019315972,0.000015200144,0.00022112191,0.00008009306,0.026940083,0.0014444159,0.64030665,0.33064556,0.0000262233],"about_ca_topic_score_codex":0.00084356824,"about_ca_topic_score_gemma":0.00074527046,"teacher_disagreement_score":0.012215247,"about_ca_system_score_codex":0.0019653356,"about_ca_system_score_gemma":0.0012844066,"threshold_uncertainty_score":0.04086411},"labels":[],"label_agreement":null},{"id":"W2484881710","doi":"10.48550/arxiv.1404.1347","title":"The Probability Density Function of a Transformation-based Hyperellipsoid Sampling Technique","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformation (genetics); Mathematics; Probability density function; Ball (mathematics); Unit sphere; Proof of concept; Distribution function; Distribution (mathematics); Simple random sample; Sampling (signal processing); Applied mathematics; Computer science; Discrete mathematics; Combinatorics; Statistics; Mathematical analysis; Physics; Telecommunications","score_opus":0.06622608577663963,"score_gpt":0.18971026557671886,"score_spread":0.12348417980007922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484881710","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064434884,0.00032459814,0.9910767,0.00023147244,0.000033079785,0.00007505277,0.000094130985,0.00021039497,0.0015110708],"genre_scores_gemma":[0.47668856,0.0017149854,0.51146525,0.00040768925,0.00027107037,0.00084015174,0.00096289755,0.00026297406,0.007386341],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99674976,0.001126283,0.00012800813,0.0005358307,0.0012505242,0.0002096589],"domain_scores_gemma":[0.9887007,0.0077649043,0.00050630374,0.0015510588,0.0012308455,0.00024616063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048611113,0.0010499717,0.0011029117,0.0021503177,0.00079097203,0.0017124116,0.0026288244,0.001999218,0.004105642],"category_scores_gemma":[0.027244005,0.0007187719,0.0009795383,0.0024925736,0.0026024203,0.0036424461,0.002649815,0.0027033803,0.001788811],"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":[0.0008792352,0.00011523529,0.0034851634,0.00041317398,0.00010764101,0.00026791551,0.0005263069,0.34649447,0.01550151,0.45423168,0.0068958574,0.17108177],"study_design_scores_gemma":[0.000035741297,0.00008250142,0.00070989184,0.00003769637,0.00001788452,0.00026065003,0.00004074978,0.93122715,0.0049248966,0.059255864,0.0033705875,0.000036359233],"about_ca_topic_score_codex":0.0023705922,"about_ca_topic_score_gemma":0.000826907,"teacher_disagreement_score":0.0048611113,"about_ca_system_score_codex":0.0019598438,"about_ca_system_score_gemma":0.0011890647,"threshold_uncertainty_score":0.025708377},"labels":[],"label_agreement":null},{"id":"W2488667214","doi":"10.1145/2930889.2930944","title":"Succinct Data Structures ... Potential for Symbolic Computation?","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Data structure; Theoretical computer science; Combinatorial explosion; Computation; Space (punctuation); Programming language; Mathematics","score_opus":0.031048107903936997,"score_gpt":0.3004191490718697,"score_spread":0.2693710411679327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488667214","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030273223,0.021387808,0.84353703,0.04886149,0.0023173285,0.00020118558,0.002085049,0.0029131847,0.048423678],"genre_scores_gemma":[0.51349115,0.028339172,0.4094314,0.00652204,0.0031975529,0.0007775858,0.003255984,0.0016007338,0.033384297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670047,0.0012327604,0.00022581735,0.00036903753,0.0012242991,0.0002475886],"domain_scores_gemma":[0.9777583,0.012083372,0.0009769048,0.0073333993,0.0014711268,0.00037702243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003996689,0.001030977,0.0011513173,0.0014364887,0.0010954734,0.006063657,0.002263314,0.002256391,0.01491624],"category_scores_gemma":[0.030685125,0.0009482531,0.0010534463,0.003237737,0.0061474103,0.027819324,0.003455406,0.00540212,0.0055031665],"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":[0.00015741964,0.00004986331,0.00032000247,0.0003867024,0.000026137808,0.000079233665,0.00017342389,0.01076469,0.0014289983,0.89837307,0.010187095,0.0780533],"study_design_scores_gemma":[0.000023987868,0.00003602946,0.000042679152,0.0001452159,0.000013607333,0.000100593876,0.00006987432,0.018687015,0.0022813287,0.95548797,0.02309185,0.000020025056],"about_ca_topic_score_codex":0.000796446,"about_ca_topic_score_gemma":0.0010523259,"teacher_disagreement_score":0.01491624,"about_ca_system_score_codex":0.0013682644,"about_ca_system_score_gemma":0.0018536107,"threshold_uncertainty_score":0.049899817},"labels":[],"label_agreement":null},{"id":"W2489056302","doi":"10.1201/b16185-59","title":"Curly Coated Retriever","year":2012,"lang":"en","type":"book-chapter","venue":"Veterinary Medical Guide to Dog and Cat Breeds","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Labrador Retriever; Medicine; Surgery","score_opus":0.03852721606013033,"score_gpt":0.2960657649061716,"score_spread":0.25753854884604127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489056302","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054707355,0.013755416,0.044597723,0.0034822314,0.003191814,0.00038082668,0.0040197107,0.008194407,0.91690713],"genre_scores_gemma":[0.0022086683,0.0022956051,0.008317858,0.0010635734,0.00015667501,0.000036743182,0.0009970783,0.0006335349,0.9842904],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997055,0.000014332393,0.00001200693,0.00007819675,0.00016081234,0.000029102379],"domain_scores_gemma":[0.99978894,0.000031670286,0.000011540693,0.000035167483,0.00008833511,0.000044337183],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045922227,0.0011379161,0.00090269174,0.001531388,0.0009277376,0.0013800326,0.0013940007,0.0014086934,0.28892785],"category_scores_gemma":[0.0006386644,0.0005840208,0.0006678772,0.0005613431,0.00048536793,0.0016588058,0.0014112849,0.0016322574,0.2892275],"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":[0.000104343366,0.00011334837,0.00031800766,0.00022732794,0.000011504866,0.0004564336,0.00014749644,0.000110253444,0.016561968,0.003913645,0.5086707,0.46936503],"study_design_scores_gemma":[0.0000067116616,0.000061421364,0.000619041,0.00007469723,0.00000807871,0.0011245414,0.000044410288,0.00015533966,0.0022746094,0.00090329844,0.99471647,0.000011360432],"about_ca_topic_score_codex":0.002339281,"about_ca_topic_score_gemma":0.00853948,"teacher_disagreement_score":0.71107215,"about_ca_system_score_codex":0.00033543902,"about_ca_system_score_gemma":0.0007138777,"threshold_uncertainty_score":0.96655995},"labels":[],"label_agreement":null},{"id":"W2489771906","doi":"10.1201/b16185-73","title":"Flat-Coated Retriever","year":2012,"lang":"en","type":"book-chapter","venue":"Veterinary Medical Guide to Dog and Cat Breeds","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Labrador Retriever; Business; Medicine; Surgery","score_opus":0.03754537617964093,"score_gpt":0.29166667370621246,"score_spread":0.25412129752657153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489771906","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025537325,0.019228572,0.17175841,0.002237054,0.0025709933,0.0010742524,0.010821206,0.0145994,0.7521728],"genre_scores_gemma":[0.014544577,0.004945347,0.046871733,0.0014157426,0.00019630919,0.00015166446,0.004067274,0.0012065608,0.9266008],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99972194,0.000010156234,0.000014237428,0.00007706803,0.00014965254,0.000026983696],"domain_scores_gemma":[0.9998455,0.000024887026,0.000011054383,0.0000322055,0.000057059235,0.00002919305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038968967,0.00088483276,0.0007137504,0.0010124153,0.00052873435,0.0007497897,0.0013718206,0.0009403895,0.16357511],"category_scores_gemma":[0.00043544086,0.0005399514,0.00066612277,0.00044453796,0.00033584493,0.0009079147,0.00092559564,0.0009869316,0.15159072],"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":[0.00026574873,0.00022536679,0.00082279055,0.00043034222,0.000032276006,0.00091035047,0.00012490441,0.00026096337,0.08423306,0.0033276319,0.22863491,0.6807316],"study_design_scores_gemma":[0.000032010666,0.00037869974,0.003616169,0.00016814575,0.000041738396,0.0066271783,0.00007935518,0.0007801861,0.022524908,0.0015618468,0.9641482,0.000041675074],"about_ca_topic_score_codex":0.001279917,"about_ca_topic_score_gemma":0.003971942,"teacher_disagreement_score":0.16357511,"about_ca_system_score_codex":0.00019273386,"about_ca_system_score_gemma":0.0004631344,"threshold_uncertainty_score":0.54721326},"labels":[],"label_agreement":null},{"id":"W2495876702","doi":"10.1016/j.tcs.2016.07.018","title":"An efficient method to evaluate intersections on big data sets","year":2016,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Trie; Intersection (aeronautics); Identifier; Computer science; Context (archaeology); Set (abstract data type); Interval (graph theory); Theoretical computer science; Tree (set theory); Search tree; Sequence (biology); Data structure; Node (physics); Inverted index; Algorithm; Binary tree; Data mining; Mathematics; Information retrieval; Search algorithm; Search engine indexing; Combinatorics","score_opus":0.0577306352145133,"score_gpt":0.3662562790384329,"score_spread":0.30852564382391956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2495876702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018818097,0.00047747628,0.973612,0.00019317026,0.00016205576,0.0001830461,0.0005279702,0.004251319,0.0017747766],"genre_scores_gemma":[0.12548777,0.00024402008,0.8683389,0.00008932427,0.00017042331,0.00036014093,0.0019304166,0.0004952567,0.0028837223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954035,0.0006258845,0.000348058,0.0004569422,0.0029061914,0.00025950026],"domain_scores_gemma":[0.9906889,0.003800943,0.00053544325,0.0017039493,0.0028818068,0.00038880878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024022132,0.0014911154,0.0019562747,0.00627069,0.0015316942,0.0031232492,0.0024799742,0.0012288633,0.0072985482],"category_scores_gemma":[0.015447699,0.00083800097,0.001177552,0.005835533,0.001228525,0.0041599046,0.0040447125,0.0019883986,0.0025069413],"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":[0.0008876733,0.0003233031,0.0075156274,0.00038165302,0.00023572314,0.00020557805,0.0003489428,0.060256418,0.015029802,0.043009993,0.01822136,0.8535838],"study_design_scores_gemma":[0.000092812494,0.00023021337,0.002007308,0.00005357874,0.00009115059,0.0003766025,0.00024536278,0.9000005,0.01759457,0.067030154,0.012214665,0.00006307233],"about_ca_topic_score_codex":0.0024693508,"about_ca_topic_score_gemma":0.004130742,"teacher_disagreement_score":0.0072985482,"about_ca_system_score_codex":0.0010971763,"about_ca_system_score_gemma":0.0026833236,"threshold_uncertainty_score":0.024416089},"labels":[],"label_agreement":null},{"id":"W2503041365","doi":"10.2140/involve.2016.9.657","title":"Avoiding approximate repetitions with respect to the longest common subsequence distance","year":2016,"lang":"en","type":"article","venue":"Involve a Journal of Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Longest common subsequence problem; Hamming distance; Edit distance; Combinatorics; Mathematics; Lemma (botany); Similarity (geometry); Repetition (rhetorical device); Longest increasing subsequence; Entropy (arrow of time); Subsequence; Discrete mathematics; Algorithm; Computer science; Artificial intelligence; Physics; Mathematical analysis","score_opus":0.031743597699848185,"score_gpt":0.26185046917785315,"score_spread":0.23010687147800496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2503041365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14243065,0.0011973673,0.8469722,0.00044363097,0.00008605421,0.000119923636,0.00019059979,0.0006366057,0.007922909],"genre_scores_gemma":[0.68135923,0.00091214065,0.3116345,0.00029733762,0.00030799708,0.00029125778,0.0004868388,0.00029243986,0.0044182017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952319,0.0013446613,0.00042290392,0.0008431903,0.0018308247,0.00032633013],"domain_scores_gemma":[0.9765048,0.014322649,0.0025035841,0.004238833,0.0019618222,0.00046826113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023138851,0.00088451325,0.0015417285,0.0027270217,0.0013529107,0.0020911628,0.0015945891,0.0015093948,0.0018145104],"category_scores_gemma":[0.030607337,0.00056270993,0.00092948455,0.0030617819,0.0036646242,0.0053293863,0.0030317758,0.0019652243,0.00089039723],"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":[0.0006141009,0.00012970218,0.0051182644,0.00043194953,0.00014029662,0.001397873,0.0016549011,0.08496412,0.025852907,0.7479605,0.0030415712,0.12869379],"study_design_scores_gemma":[0.00007027137,0.00039763635,0.0013799856,0.00009729493,0.00008934467,0.0017172149,0.00029781245,0.2920916,0.020945083,0.6750339,0.007748488,0.00013137903],"about_ca_topic_score_codex":0.0007324583,"about_ca_topic_score_gemma":0.00055877573,"teacher_disagreement_score":0.0027270217,"about_ca_system_score_codex":0.0008645785,"about_ca_system_score_gemma":0.0011929531,"threshold_uncertainty_score":0.012237132},"labels":[],"label_agreement":null},{"id":"W2504721752","doi":"10.1016/j.dam.2016.07.006","title":"<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si5.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>V</mml:mi></mml:math>-Order: New combinatorial properties &amp; a simple comparison algorithm","year":2016,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Scroll; Order (exchange); Simple (philosophy); Combinatorics; Discrete mathematics; Algorithm; Archaeology; Geography","score_opus":0.022767750903617785,"score_gpt":0.2517314755832914,"score_spread":0.2289637246796736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2504721752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034539066,0.00047611326,0.5318243,0.0026699705,0.0011131355,0.0002823976,0.038834948,0.08281118,0.33853403],"genre_scores_gemma":[0.06956385,0.0010810626,0.47917116,0.0012892816,0.00083387445,0.0005857714,0.06338998,0.08126017,0.30282488],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993641,0.000094029216,0.000057210385,0.00011563298,0.0003118719,0.000057172645],"domain_scores_gemma":[0.99796283,0.00066276395,0.00010759013,0.0005282282,0.00061563426,0.00012299653],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007803244,0.0010259316,0.00078569993,0.0022364852,0.0007616716,0.0037975933,0.0022383162,0.0010025353,0.3616515],"category_scores_gemma":[0.005189363,0.00065324845,0.0006087863,0.0034555343,0.0006842183,0.0052482956,0.0015775416,0.0015985089,0.21247806],"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":[0.00023412942,0.00006170415,0.00027905803,0.00040974145,0.000019555577,0.00008070473,0.00011560507,0.0016844574,0.0055305366,0.124078214,0.67138225,0.19612406],"study_design_scores_gemma":[0.00009870833,0.00004062329,0.0005895058,0.00007792039,0.000013041777,0.00022455491,0.00006024639,0.015598407,0.021163328,0.098577656,0.8634921,0.00006387778],"about_ca_topic_score_codex":0.0023308885,"about_ca_topic_score_gemma":0.0040548174,"teacher_disagreement_score":0.3616515,"about_ca_system_score_codex":0.001405715,"about_ca_system_score_gemma":0.0010107538,"threshold_uncertainty_score":0.91052663},"labels":[],"label_agreement":null},{"id":"W2509063142","doi":"10.1007/s00453-016-0199-7","title":"Full-Fledged Real-Time Indexing for Constant Size Alphabets","year":2016,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Labex Bézout","keywords":"Search engine indexing; Constant (computer programming); Alphabet; Theory of computation; Combinatorics; Symbol (formal); String (physics); String searching algorithm; Matching (statistics); Mathematics; Pattern matching; Computer science; Algorithm; Discrete mathematics; Statistics; Information retrieval; Artificial intelligence","score_opus":0.010992617136929688,"score_gpt":0.24548944568049474,"score_spread":0.23449682854356504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509063142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06579012,0.0019757496,0.90530163,0.0013246567,0.00051273755,0.00016706873,0.001344242,0.0077358405,0.015847927],"genre_scores_gemma":[0.44788602,0.0007743083,0.5280111,0.00049848424,0.0004099301,0.00029944483,0.0023607672,0.001016516,0.018743498],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99680495,0.0004970709,0.00038363566,0.00065267057,0.0012054818,0.0004562693],"domain_scores_gemma":[0.9862336,0.0044931923,0.0005922182,0.0070834337,0.0011537899,0.0004437382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017295139,0.00087355374,0.001513171,0.00199646,0.0014371043,0.0035423976,0.0035980958,0.0017036127,0.013530742],"category_scores_gemma":[0.01610487,0.00062094827,0.00085403473,0.0046951245,0.0018462894,0.009369676,0.0041596675,0.002195672,0.0048297513],"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":[0.0023236866,0.00041670422,0.0013922567,0.000647738,0.000086299035,0.00034813487,0.00064460386,0.08039921,0.024181362,0.1325189,0.038439784,0.7186014],"study_design_scores_gemma":[0.0002836962,0.00049473107,0.0006369027,0.00014681839,0.00008994826,0.0010686278,0.0002934279,0.5517791,0.027310362,0.39225227,0.025536422,0.00010768786],"about_ca_topic_score_codex":0.0016560828,"about_ca_topic_score_gemma":0.002589064,"teacher_disagreement_score":0.013530742,"about_ca_system_score_codex":0.0013432296,"about_ca_system_score_gemma":0.0025060163,"threshold_uncertainty_score":0.04526478},"labels":[],"label_agreement":null},{"id":"W2509151057","doi":"10.48550/arxiv.1608.03522","title":"On (a,b) Pairs in Random Fibonacci Sequences","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Fibonacci number; Combinatorics; Coprime integers; Tree (set theory); Mathematics; Binary tree; Root (linguistics); Discrete mathematics; Node (physics); Physics","score_opus":0.054685149593993614,"score_gpt":0.18950572040620564,"score_spread":0.13482057081221202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509151057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5058651,0.005394828,0.46335346,0.0016434054,0.00026676874,0.00025508992,0.00043123055,0.0006758304,0.022114286],"genre_scores_gemma":[0.9191221,0.0018850662,0.0683634,0.00071044936,0.000320017,0.0005890916,0.00067970285,0.0002487356,0.008081404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957551,0.001782876,0.00020662432,0.0006723897,0.0009979418,0.00058502675],"domain_scores_gemma":[0.97408414,0.021013435,0.0020263016,0.0009741068,0.000893105,0.0010089752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036151095,0.0017128321,0.0021591946,0.004925251,0.0028361306,0.002699548,0.002325062,0.0031685114,0.003947973],"category_scores_gemma":[0.02644348,0.0013864203,0.001008763,0.0040230094,0.0042911163,0.0069007105,0.0032461253,0.002551915,0.001358973],"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":[0.0008320937,0.0001998448,0.0055762976,0.00037889357,0.00008135259,0.0017669164,0.0013041383,0.09872681,0.007087104,0.84804153,0.005037193,0.030967858],"study_design_scores_gemma":[0.00014031149,0.00020948003,0.001011576,0.00020161035,0.000046193807,0.0012033689,0.00020414617,0.39935443,0.0034259742,0.5905902,0.0035139362,0.00009882922],"about_ca_topic_score_codex":0.001091671,"about_ca_topic_score_gemma":0.0011534387,"teacher_disagreement_score":0.004925251,"about_ca_system_score_codex":0.0017575995,"about_ca_system_score_gemma":0.00081983634,"threshold_uncertainty_score":0.019118786},"labels":[],"label_agreement":null},{"id":"W2513395528","doi":"10.1145/2905368","title":"Data Structures for Path Queries","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Multiset; Path (computing); Combinatorics; Mathematics; Selection (genetic algorithm); Discrete mathematics; Computer science","score_opus":0.05610397486646216,"score_gpt":0.30398149261818486,"score_spread":0.2478775177517227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513395528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020875128,0.0023920878,0.9455814,0.0032400428,0.00041543957,0.0007925519,0.010146701,0.0110516185,0.005505103],"genre_scores_gemma":[0.2023782,0.0019392226,0.75570834,0.0025148639,0.0005874972,0.0026999086,0.02333941,0.0024393676,0.008393247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99145585,0.0017187578,0.0016466732,0.0015318324,0.0029998387,0.0006471413],"domain_scores_gemma":[0.9612814,0.015529556,0.002471507,0.016498344,0.0035737925,0.0006452829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056563565,0.0017321199,0.0023534982,0.00244209,0.0021967627,0.005052351,0.0049329037,0.0025864646,0.015133435],"category_scores_gemma":[0.038396668,0.0016839058,0.0021691548,0.007268584,0.0022837624,0.024254877,0.007946147,0.0054379934,0.0052636657],"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":[0.0024965727,0.00047225508,0.004821545,0.0016886801,0.00021869125,0.0004353153,0.0012542696,0.055376396,0.013395638,0.4424328,0.09149181,0.38591594],"study_design_scores_gemma":[0.0004256952,0.00051649194,0.000570866,0.00036454468,0.00012306779,0.0006517974,0.00047781208,0.21606651,0.017159618,0.66160804,0.10188721,0.00014834097],"about_ca_topic_score_codex":0.0022582286,"about_ca_topic_score_gemma":0.0034202605,"teacher_disagreement_score":0.015133435,"about_ca_system_score_codex":0.003220059,"about_ca_system_score_gemma":0.0034868985,"threshold_uncertainty_score":0.050626397},"labels":[],"label_agreement":null},{"id":"W2514119406","doi":"10.1137/1.9781611974782.26","title":"Space-Efficient Construction of Compressed Indexes in Deterministic Linear Time","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Compressed suffix array; Suffix tree; Generalized suffix tree; Alphabet; String (physics); Suffix; Time complexity; Binary logarithm; Parsing; Algorithm; Linear space; Spacetime; Suffix array; Computer science; Discrete mathematics; Combinatorics; Mathematics; Tree (set theory); Data structure; Physics","score_opus":0.02086790557803845,"score_gpt":0.27656729246714035,"score_spread":0.2556993868891019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514119406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059048638,0.0010020674,0.91458964,0.0008124212,0.00026858933,0.00030558562,0.0018006278,0.010021798,0.0121506285],"genre_scores_gemma":[0.30593795,0.00056156475,0.67958844,0.00045235234,0.0001923581,0.0005504999,0.0046372656,0.0011491373,0.0069303894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690056,0.00039010207,0.00027657842,0.0005055602,0.0015614771,0.0003658388],"domain_scores_gemma":[0.9945357,0.0019793767,0.0003904443,0.0019827245,0.0009676344,0.00014413359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009112704,0.0007786278,0.0012720083,0.0014326404,0.0011788999,0.0029281124,0.001865156,0.0011481565,0.004879049],"category_scores_gemma":[0.009928531,0.00064254616,0.00081593834,0.0041041407,0.0013460303,0.005589493,0.0033998068,0.0014579578,0.0031434053],"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":[0.001022791,0.00039756426,0.0029272228,0.00087844784,0.00013620836,0.0008009266,0.0011704218,0.07145294,0.08399906,0.26275048,0.03753301,0.536931],"study_design_scores_gemma":[0.0002491572,0.0002554324,0.00091329205,0.00012870555,0.000115837924,0.00089826155,0.000414956,0.5083775,0.15565482,0.29018876,0.042687207,0.000116125506],"about_ca_topic_score_codex":0.0012251028,"about_ca_topic_score_gemma":0.0020077378,"teacher_disagreement_score":0.004879049,"about_ca_system_score_codex":0.0013466579,"about_ca_system_score_gemma":0.003300475,"threshold_uncertainty_score":0.016322076},"labels":[],"label_agreement":null},{"id":"W2528068670","doi":"10.1016/j.comgeo.2020.101630","title":"Fast and compact planar embeddings","year":2020,"lang":"en","type":"article","venue":"Computational Geometry","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Horizon 2020 Framework Programme; H2020 Marie Skłodowska-Curie Actions; Universidade da Coruña; Fondo Nacional de Desarrollo Científico y Tecnológico; Helsingin Yliopisto; Núcleo Milenio Información y Coordinación en Redes, ICR; Corporación de Fomento de la Producción; Academy of Finland; Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Sublinear function; Embedding; Simplicity; Computer science; Planar; Speedup; Representation (politics); Book embedding; Planar graph; Simple (philosophy); Enhanced Data Rates for GSM Evolution; Theoretical computer science; Graph embedding; Graph; Encoding (memory); Algorithm; Parallel computing; Topology (electrical circuits); Mathematics; Discrete mathematics; Combinatorics; Line graph; Computer graphics (images); 1-planar graph; Artificial intelligence; Physics","score_opus":0.019587141123473296,"score_gpt":0.25156464930427624,"score_spread":0.23197750818080295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528068670","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04847092,0.0022220532,0.92319125,0.001154977,0.0004256073,0.00012214418,0.0013708251,0.0046440535,0.01839814],"genre_scores_gemma":[0.388777,0.0025785284,0.5783879,0.00042904465,0.0003945545,0.00033398642,0.0045128777,0.0016185553,0.02296763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983113,0.0002446797,0.00009708434,0.0003343134,0.000845182,0.00016736526],"domain_scores_gemma":[0.9969542,0.00096407277,0.00019526189,0.0012896495,0.00048086967,0.00011599729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060197164,0.0019238639,0.0015029316,0.002202693,0.00066153,0.0026346906,0.0018451946,0.001454547,0.011925255],"category_scores_gemma":[0.008534895,0.0008920638,0.0008248487,0.0034253416,0.0012869794,0.006921616,0.00597408,0.0031057363,0.0055986787],"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":[0.00076423655,0.0001569928,0.0007851115,0.0004443809,0.000079154124,0.0002750833,0.00037873443,0.07869635,0.013987863,0.2130841,0.042030867,0.64931715],"study_design_scores_gemma":[0.00013507917,0.00020594131,0.00062217127,0.00011501616,0.00005525018,0.000696628,0.0004425662,0.4205123,0.019541897,0.5116898,0.045917604,0.00006578803],"about_ca_topic_score_codex":0.00080423645,"about_ca_topic_score_gemma":0.00129379,"teacher_disagreement_score":0.011925255,"about_ca_system_score_codex":0.00075544015,"about_ca_system_score_gemma":0.0006762832,"threshold_uncertainty_score":0.039893925},"labels":[],"label_agreement":null},{"id":"W2528405545","doi":"10.48550/arxiv.cs/0601081","title":"An O(1) Solution to the Prefix Sum Problem on a Specialized Memory Architecture","year":2006,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Prefix; Computer science; Computation; Parallel computing; Theoretical computer science; Algorithm; Arithmetic; Mathematics","score_opus":0.020508234035743762,"score_gpt":0.2497156969849931,"score_spread":0.22920746294924935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528405545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12286142,0.001139407,0.8520929,0.0013919427,0.00020251324,0.0002037451,0.00028042056,0.0025275908,0.01929991],"genre_scores_gemma":[0.44829896,0.0006328891,0.5379589,0.00027752342,0.00021057531,0.0002688621,0.0006531732,0.00023537592,0.011463782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993406,0.00014806497,0.000039587205,0.00018688253,0.00014339757,0.00014151179],"domain_scores_gemma":[0.99877757,0.0005695621,0.00008013929,0.00043455305,0.00009356812,0.00004461649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060731947,0.0007368697,0.0009915025,0.00047756766,0.0007292698,0.0016365951,0.0019670676,0.0011702117,0.012201717],"category_scores_gemma":[0.0035031538,0.00035431253,0.00056447694,0.0015055126,0.0006098008,0.0047887294,0.0014669703,0.0014701022,0.0021216916],"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":[0.0008746897,0.0003885412,0.0009111913,0.0008173541,0.00014607472,0.00027611986,0.00025064917,0.18921204,0.029370755,0.16892807,0.02725874,0.58156574],"study_design_scores_gemma":[0.00017208538,0.0003147012,0.00041637258,0.00005050137,0.00009857653,0.00042825777,0.00016919624,0.822936,0.013988447,0.15008914,0.011306718,0.00002997019],"about_ca_topic_score_codex":0.00086542213,"about_ca_topic_score_gemma":0.0020551397,"teacher_disagreement_score":0.012201717,"about_ca_system_score_codex":0.00087021856,"about_ca_system_score_gemma":0.0012720556,"threshold_uncertainty_score":0.04081887},"labels":[],"label_agreement":null},{"id":"W2534091751","doi":"10.1109/fskd.2016.7603199","title":"On the massive string matching problem","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"Computer science; Matching (statistics); String searching algorithm; String (physics); Pattern matching; Artificial intelligence; Mathematics; Physics; Theoretical physics; Statistics","score_opus":0.014631032746071183,"score_gpt":0.22496975326399515,"score_spread":0.21033872051792396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2534091751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035043985,0.0018349674,0.9492997,0.0025706815,0.00030842808,0.000120939505,0.00044584458,0.00092736963,0.009448026],"genre_scores_gemma":[0.41775808,0.0026381568,0.5571509,0.001743953,0.0011524309,0.00040321535,0.0023625777,0.00046078133,0.016329896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99724436,0.0008668447,0.00018517427,0.0007510245,0.00067099684,0.0002816162],"domain_scores_gemma":[0.9938484,0.0042450516,0.00043611164,0.0009048396,0.00035560536,0.00021005483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023716355,0.00074040785,0.0017722085,0.0015801559,0.0016324267,0.0021042249,0.0020968823,0.0026256596,0.0073132417],"category_scores_gemma":[0.011936164,0.0004791072,0.00088858395,0.0042454014,0.0017311308,0.0078101926,0.003360083,0.0022844416,0.0018195119],"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":[0.0005759296,0.0003527493,0.0014643242,0.00062816904,0.00014334258,0.0005628952,0.00032424444,0.18359871,0.003252096,0.48053703,0.030208116,0.29835242],"study_design_scores_gemma":[0.00007359548,0.00008339978,0.0002535745,0.00003583492,0.00002558963,0.00036590893,0.000088536784,0.30007192,0.0014740239,0.6869826,0.010521873,0.0000232505],"about_ca_topic_score_codex":0.0010047365,"about_ca_topic_score_gemma":0.0006241754,"teacher_disagreement_score":0.0073132417,"about_ca_system_score_codex":0.00089855725,"about_ca_system_score_gemma":0.0010646821,"threshold_uncertainty_score":0.024465263},"labels":[],"label_agreement":null},{"id":"W2536374144","doi":"10.1109/iwsda.2013.6849074","title":"Randomness properties of stream ciphers for wireless communications","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Stream cipher; NIST; Computer science; Randomness; Wireless; Stream cipher attack; Suite; Randomness tests; Cryptography; Algorithm; Telecommunications; Mathematics; Statistics; Geography; Speech recognition","score_opus":0.03841414934220077,"score_gpt":0.25370329266915564,"score_spread":0.21528914332695487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536374144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7859685,0.0052908966,0.18657762,0.0006142891,0.00027469563,0.00049885415,0.0009896029,0.001017432,0.018768046],"genre_scores_gemma":[0.98072445,0.0008875438,0.016559402,0.00006857642,0.00006516598,0.00009218624,0.00050184334,0.00008897259,0.0010119065],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99509406,0.0013601768,0.0003914062,0.00031018624,0.0024619405,0.00038223976],"domain_scores_gemma":[0.9780382,0.015270059,0.0022508253,0.0018484421,0.0023548394,0.00023773816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044096108,0.0007004067,0.00058519596,0.0017142,0.0005676473,0.0010844573,0.0004454625,0.00049709785,0.0023340543],"category_scores_gemma":[0.02089673,0.00020061471,0.00051014486,0.0010440745,0.0009133818,0.0028291456,0.00065162464,0.0006650942,0.00052147446],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034468381,0.00046978876,0.026071442,0.0013781063,0.00042420268,0.0008083232,0.00028083526,0.48759994,0.18546818,0.11025056,0.0048973314,0.17890447],"study_design_scores_gemma":[0.00019183634,0.004206833,0.007468718,0.00020792003,0.00023970463,0.0015229385,0.0001582154,0.6384482,0.30451074,0.031931296,0.010960379,0.00015323944],"about_ca_topic_score_codex":0.00035887535,"about_ca_topic_score_gemma":0.0003675195,"teacher_disagreement_score":0.0044096108,"about_ca_system_score_codex":0.0007898904,"about_ca_system_score_gemma":0.0010187663,"threshold_uncertainty_score":0.023320556},"labels":[],"label_agreement":null},{"id":"W2537451284","doi":"","title":"StringMasters 2009 & 2010 Special Issue","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Atmosphere (unit); String (physics); Work (physics); Computer science; Library science; Data science; Mathematics; Geography; Engineering; Meteorology","score_opus":0.017087609706376905,"score_gpt":0.24354562943476424,"score_spread":0.22645801972838733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537451284","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035777898,0.022112228,0.009829074,0.075818606,0.4853175,0.00063528307,0.017239094,0.005864078,0.37960637],"genre_scores_gemma":[0.005681356,0.007910988,0.0019794216,0.007126727,0.0801968,0.00019901615,0.01380877,0.0019918534,0.881105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825126,0.00016963763,0.0001559162,0.00041394038,0.0007796446,0.00022958383],"domain_scores_gemma":[0.9915154,0.0010410517,0.0004443163,0.0008233731,0.0034730409,0.0027028793],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031883097,0.001502234,0.0018430136,0.0038276094,0.002757953,0.01027053,0.0023657638,0.0032568444,0.35028294],"category_scores_gemma":[0.009255482,0.0006645081,0.0011306857,0.0031363696,0.0009208872,0.0073483167,0.0032978973,0.0029465298,0.29208195],"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":[0.000054980497,0.000023411321,0.00010657007,0.00015015867,0.000004513926,0.00005171554,0.000011621418,0.000057980444,0.00029770972,0.0017666434,0.9687645,0.02871022],"study_design_scores_gemma":[0.0000064374913,0.000017958844,0.00033712276,0.00007453479,0.0000033004558,0.000046051737,0.000012901218,0.00007853816,0.00021568182,0.000676235,0.9985262,0.00000501035],"about_ca_topic_score_codex":0.0024635517,"about_ca_topic_score_gemma":0.0058565503,"teacher_disagreement_score":0.35028294,"about_ca_system_score_codex":0.0041247616,"about_ca_system_score_gemma":0.0041032676,"threshold_uncertainty_score":0.92674255},"labels":[],"label_agreement":null},{"id":"W2538355508","doi":"10.1038/nmeth.4037","title":"Comparison of high-throughput sequencing data compression tools","year":2016,"lang":"en","type":"article","venue":"Nature Methods","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Throughput; Computer science; Benchmarking; Benchmark (surveying); Raw data; Data compression; Data set; DNA sequencing; Data mining; Set (abstract data type); Biology; Artificial intelligence; Operating system","score_opus":0.16141766759577478,"score_gpt":0.48017606909231786,"score_spread":0.3187584014965431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2538355508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4339515,0.0075360485,0.5144504,0.0013805776,0.0009373322,0.00072424306,0.005651392,0.026779944,0.008588707],"genre_scores_gemma":[0.41062358,0.0032721185,0.5680375,0.00042049924,0.00018964037,0.0007321677,0.011987346,0.0016872507,0.003049819],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99571747,0.0008810699,0.00051057426,0.00044675666,0.0022135738,0.0002305774],"domain_scores_gemma":[0.98171073,0.011561968,0.0007034947,0.0017549795,0.0039620763,0.0003068195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006209938,0.0012197666,0.00094834703,0.0039177327,0.000777176,0.0022802893,0.0019795708,0.0014107252,0.0036596274],"category_scores_gemma":[0.023572056,0.0005153536,0.0010022937,0.004154898,0.00055931095,0.0021403998,0.000996041,0.0010882434,0.0013899688],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066058086,0.0010796483,0.013716576,0.0019912575,0.0006963049,0.00054548075,0.00057163223,0.085485086,0.13758247,0.012840787,0.013984078,0.7249008],"study_design_scores_gemma":[0.00043375383,0.001758645,0.017442405,0.0003351515,0.00037344327,0.0012248002,0.0004368345,0.58905894,0.3583408,0.010533959,0.01976531,0.00029599873],"about_ca_topic_score_codex":0.0012965007,"about_ca_topic_score_gemma":0.0013800695,"teacher_disagreement_score":0.006209938,"about_ca_system_score_codex":0.0011418719,"about_ca_system_score_gemma":0.0014943214,"threshold_uncertainty_score":0.032841682},"labels":[],"label_agreement":null},{"id":"W2549141685","doi":"10.1016/j.is.2017.01.002","title":"Upscaledb: Efficient integer-key compression in a key-value store using SIMD instructions","year":2017,"lang":"en","type":"article","venue":"Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Computer science; SIMD; Byte; Data compression; Key (lock); Associative array; Parallel computing; Compression (physics); Compression ratio; Database; Operating system; Algorithm; Programming language","score_opus":0.02574336979932961,"score_gpt":0.28147636981620056,"score_spread":0.25573300001687094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549141685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094793685,0.00429001,0.7550429,0.0008074238,0.0009090541,0.0005690697,0.0030034943,0.115853414,0.02473103],"genre_scores_gemma":[0.4888342,0.0011260202,0.47359464,0.0007379436,0.00032386486,0.00043710644,0.0050017266,0.0032337212,0.026710752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993235,0.000050567036,0.000047889924,0.00009250342,0.00038462714,0.00010092821],"domain_scores_gemma":[0.9992924,0.00016049684,0.000042513802,0.00028876733,0.00016350245,0.000052309977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003952932,0.0012058216,0.00081866304,0.0015456672,0.00062032684,0.001557556,0.0017501394,0.0005132924,0.016234705],"category_scores_gemma":[0.0014189375,0.0004844578,0.00038357143,0.0020882078,0.00062765385,0.0021452194,0.0020938911,0.0009300984,0.004620404],"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":[0.0022170683,0.0003921297,0.0016066418,0.00045279186,0.00011241638,0.00039980788,0.0002077188,0.0077207196,0.07543362,0.027675537,0.090382576,0.793399],"study_design_scores_gemma":[0.00079898664,0.00067298976,0.0014482489,0.00013510729,0.00015873004,0.00089188333,0.0002125303,0.33888078,0.5373127,0.030826297,0.08850489,0.00015695575],"about_ca_topic_score_codex":0.0018879881,"about_ca_topic_score_gemma":0.0030840775,"teacher_disagreement_score":0.016234705,"about_ca_system_score_codex":0.0008709166,"about_ca_system_score_gemma":0.0012674273,"threshold_uncertainty_score":0.05431044},"labels":[],"label_agreement":null},{"id":"W2551643417","doi":"10.1007/978-3-319-71147-8_10","title":"Graph Editing to a Given Neighbourhood Degree List is Fixed-Parameter Tractable","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Neighbourhood (mathematics); Degree (music); Graph; Theoretical computer science; Algorithm; Mathematics; Physics","score_opus":0.030041218049764597,"score_gpt":0.2667288147417829,"score_spread":0.2366875966920183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551643417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07918093,0.00074001483,0.8570471,0.0034265877,0.00020081694,0.0003742326,0.0025680936,0.0036865484,0.05277571],"genre_scores_gemma":[0.6353684,0.0009399986,0.297442,0.0009670804,0.00052875903,0.00063401635,0.003566254,0.0032897373,0.05726385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730504,0.00059395365,0.00012902539,0.0010273346,0.0005298978,0.00041475068],"domain_scores_gemma":[0.9741969,0.018415073,0.0010559895,0.004539098,0.0011670165,0.0006259142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019905043,0.0016361815,0.0036991339,0.0012282348,0.002406549,0.0059625213,0.0061340444,0.0041121957,0.02039305],"category_scores_gemma":[0.028478244,0.0011483768,0.0023199718,0.0034425866,0.0025645043,0.010494715,0.0033478532,0.0054380833,0.00413815],"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":[0.00037801487,0.00030726002,0.0009089769,0.0007502647,0.00013201826,0.00050591066,0.00076816656,0.35889342,0.0037461254,0.50960237,0.034646526,0.08936092],"study_design_scores_gemma":[0.00006326785,0.000027131275,0.00012564746,0.000035731955,0.00005269435,0.00017289979,0.000102759186,0.3447727,0.0013065052,0.6489366,0.0043800436,0.000023937559],"about_ca_topic_score_codex":0.0049080085,"about_ca_topic_score_gemma":0.007864226,"teacher_disagreement_score":0.02039305,"about_ca_system_score_codex":0.003441756,"about_ca_system_score_gemma":0.0029576076,"threshold_uncertainty_score":0.06822151},"labels":[],"label_agreement":null},{"id":"W2552316968","doi":"10.1016/j.tcs.2016.10.015","title":"On prefix normal words and prefix normal forms","year":2016,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Prefix; Word (group theory); Mathematics; Combinatorics; Context (archaeology); Equivalence (formal languages); Binary number; Unary operation; Discrete mathematics; Prefix code; Arithmetic; Algorithm; Linguistics","score_opus":0.006545220852153862,"score_gpt":0.22883456753285955,"score_spread":0.22228934668070569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552316968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06657339,0.00943918,0.8254542,0.006264267,0.0015049095,0.00016710814,0.0007030787,0.00077926426,0.08911466],"genre_scores_gemma":[0.64355975,0.014594988,0.25962132,0.0030593113,0.0041322946,0.0006491904,0.002137716,0.0011106799,0.07113475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964222,0.0010690225,0.00031493235,0.0006157191,0.0012594098,0.00031881913],"domain_scores_gemma":[0.990789,0.00577927,0.0004878601,0.001661426,0.0010479041,0.00023456366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020341887,0.001380013,0.0014449725,0.00414802,0.0019307515,0.0044678603,0.0014757715,0.002218086,0.010337066],"category_scores_gemma":[0.018868698,0.00077088573,0.0009829698,0.007663724,0.0063397232,0.017757779,0.0054999734,0.0042537143,0.002440621],"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":[0.00004121688,0.000015523487,0.00015343269,0.000050611063,0.000005596151,0.00009197155,0.00024257242,0.002472934,0.0003764901,0.9610745,0.0025243252,0.03295087],"study_design_scores_gemma":[0.0000030298302,0.000006327766,0.000027153488,0.000018509621,0.0000035849698,0.000092961556,0.00003612303,0.005458115,0.0002339062,0.9903808,0.0037329374,0.0000065676422],"about_ca_topic_score_codex":0.0011344656,"about_ca_topic_score_gemma":0.00084611657,"teacher_disagreement_score":0.010337066,"about_ca_system_score_codex":0.001614827,"about_ca_system_score_gemma":0.0010151409,"threshold_uncertainty_score":0.034580886},"labels":[],"label_agreement":null},{"id":"W2552773400","doi":"10.1016/j.jda.2016.11.002","title":"A prefix array for parameterized strings","year":2016,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Parameterized complexity; Prefix; Mathematics; Combinatorics; Computer science; Algorithm","score_opus":0.019458479569679422,"score_gpt":0.27346738350236816,"score_spread":0.2540089039326887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552773400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014599949,0.0004321618,0.9752548,0.00038500404,0.00020744764,0.00009210236,0.00088323036,0.0021657923,0.0059796106],"genre_scores_gemma":[0.14176747,0.0008931569,0.842441,0.0003314258,0.00026561835,0.00045730587,0.0030176248,0.000906918,0.009919471],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976931,0.00050466054,0.00034825626,0.0004777137,0.0007870671,0.00018917632],"domain_scores_gemma":[0.99384356,0.0021167663,0.00034120178,0.0026151254,0.00086494425,0.00021834642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014206906,0.0006380578,0.0013133886,0.0020233209,0.0011975613,0.003516344,0.0017611444,0.0013213205,0.011445909],"category_scores_gemma":[0.011779214,0.0005808904,0.0008075059,0.00565326,0.001329503,0.0074394974,0.0031787842,0.0025085672,0.004999672],"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":[0.00067778205,0.00015244987,0.0010024294,0.00026381173,0.000042590615,0.00024858754,0.0003354804,0.039658334,0.013326986,0.45012504,0.015507644,0.47865883],"study_design_scores_gemma":[0.000085555796,0.00030543894,0.0002896292,0.00016729189,0.000050743914,0.000625373,0.00019282741,0.30178642,0.020458072,0.6113914,0.064566635,0.000080590435],"about_ca_topic_score_codex":0.00044881695,"about_ca_topic_score_gemma":0.00042280863,"teacher_disagreement_score":0.011445909,"about_ca_system_score_codex":0.0008632319,"about_ca_system_score_gemma":0.0015256868,"threshold_uncertainty_score":0.03829038},"labels":[],"label_agreement":null},{"id":"W2554727976","doi":"10.3384/diss.diva-132421","title":"Taut Strings and Real Interpolation","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Engineering Link (Canada)","funders":"","keywords":"Interpolation (computer graphics); Mathematics; Computer science; Computer graphics (images)","score_opus":0.0074593874072087455,"score_gpt":0.2555119779008368,"score_spread":0.24805259049362804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554727976","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08716208,0.0096758725,0.80465585,0.00305352,0.00080565194,0.00005701838,0.0005319766,0.000528032,0.09353007],"genre_scores_gemma":[0.75465703,0.0078611635,0.18215118,0.0010283403,0.0011346057,0.00016399898,0.00094591425,0.0005478961,0.051509902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993838,0.00017535665,0.000033633078,0.00014640087,0.00019264742,0.00006820574],"domain_scores_gemma":[0.9985732,0.00082179235,0.00015136943,0.0002112254,0.00015900125,0.00008328428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092931144,0.0005796305,0.0006455416,0.0018058881,0.0007630185,0.0014682449,0.0007377284,0.0011891356,0.008374896],"category_scores_gemma":[0.005218979,0.00026215584,0.0007094446,0.0017054237,0.0024514138,0.0029914817,0.0017868248,0.0023106898,0.0014015089],"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":[0.000054096807,0.000016664126,0.00016033232,0.000072972725,0.000009973433,0.00005577997,0.00010066482,0.020310735,0.0008748201,0.9437757,0.0020955587,0.032472707],"study_design_scores_gemma":[0.000008404286,0.00003134466,0.000118440956,0.000029232606,0.0000034302532,0.000054253636,0.00003408387,0.046626315,0.0004619689,0.9464278,0.006193922,0.000010729436],"about_ca_topic_score_codex":0.00051639805,"about_ca_topic_score_gemma":0.00038751733,"teacher_disagreement_score":0.008374896,"about_ca_system_score_codex":0.00077632035,"about_ca_system_score_gemma":0.00044700937,"threshold_uncertainty_score":0.028016806},"labels":[],"label_agreement":null},{"id":"W2555880401","doi":"10.1109/spcom.2016.7746651","title":"Text compression using lexicographic permutation of binary strings","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Lexicographical order; Lossless compression; String (physics); Computer science; Binary number; Data compression; Permutation (music); Reduction (mathematics); Rank (graph theory); Compression ratio; Compression (physics); String searching algorithm; Algorithm; Binary code; n-gram; Speech recognition; Mathematics; Combinatorics; Artificial intelligence; Arithmetic; Pattern matching; Language model; Physics","score_opus":0.02569379645617112,"score_gpt":0.266010369188574,"score_spread":0.2403165727324029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555880401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05784909,0.0016854063,0.92762107,0.0006345425,0.00040845186,0.0002716981,0.0010268758,0.004606628,0.0058963234],"genre_scores_gemma":[0.24457562,0.0017511774,0.7420291,0.00038552406,0.0002931019,0.0002591124,0.0027100479,0.00040539008,0.007591075],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936575,0.00012622013,0.00007781078,0.00011004811,0.00027153527,0.000048669062],"domain_scores_gemma":[0.99853635,0.0005949045,0.00016342409,0.00040002627,0.0002774333,0.000027804716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004365008,0.000693237,0.00058142847,0.0018840322,0.00040852907,0.0009766499,0.0006778509,0.00055238756,0.003145043],"category_scores_gemma":[0.0034416919,0.00021701904,0.00036722302,0.0022007644,0.0005714135,0.0015676125,0.0006140659,0.0006094548,0.0021590856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007142369,0.00013529736,0.0010328324,0.00046397254,0.000049012535,0.0005657781,0.0002246933,0.023602145,0.10374881,0.026611988,0.008803993,0.8340472],"study_design_scores_gemma":[0.00016694443,0.00080162607,0.0028054393,0.00022971371,0.00009558649,0.0026962205,0.00035064697,0.46970668,0.414782,0.054633718,0.053608302,0.00012321067],"about_ca_topic_score_codex":0.00075200194,"about_ca_topic_score_gemma":0.00079121214,"teacher_disagreement_score":0.003145043,"about_ca_system_score_codex":0.00034712104,"about_ca_system_score_gemma":0.0005551073,"threshold_uncertainty_score":0.010521233},"labels":[],"label_agreement":null},{"id":"W2559503456","doi":"10.1145/3015022.3015023","title":"In Vacuo and In Situ Evaluation of SIMD Codecs","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"SIMD; Codec; Computer science; In situ; Parallel computing; Chemistry; Computer hardware; Organic chemistry","score_opus":0.03267593823126133,"score_gpt":0.3029923764970704,"score_spread":0.2703164382658091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559503456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8958109,0.0026109526,0.05301716,0.000622924,0.00046504926,0.00039721176,0.0026779545,0.02326745,0.021130322],"genre_scores_gemma":[0.8389605,0.0007047827,0.1417153,0.00043625355,0.00013628545,0.00031219056,0.00775091,0.0028777986,0.007105977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494153,0.001238557,0.00038951577,0.00065816886,0.002403326,0.00036889254],"domain_scores_gemma":[0.98330724,0.0071543287,0.00056394516,0.004475037,0.0040870323,0.00041233777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004688126,0.00092545064,0.0008324419,0.0020312394,0.0010119631,0.0019156913,0.0024437055,0.0012149967,0.0044440757],"category_scores_gemma":[0.027091615,0.0004738268,0.00053559773,0.0033806313,0.0013642769,0.004213555,0.0016631681,0.0012339941,0.0017867244],"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":[0.008506185,0.0015399554,0.0223847,0.0016250975,0.0004796951,0.00082829985,0.001221248,0.15049492,0.08898541,0.019532282,0.044572495,0.65982974],"study_design_scores_gemma":[0.00086132664,0.00191487,0.0059386417,0.000095006166,0.00011946175,0.0006121276,0.00061129336,0.7974325,0.16268252,0.0051487847,0.024464091,0.00011935447],"about_ca_topic_score_codex":0.008009925,"about_ca_topic_score_gemma":0.009017794,"teacher_disagreement_score":0.008009925,"about_ca_system_score_codex":0.001961261,"about_ca_system_score_gemma":0.0019670555,"threshold_uncertainty_score":0.024793506},"labels":[],"label_agreement":null},{"id":"W2564774846","doi":"10.1109/dcc.2016.119","title":"Grammatical Ziv-Lempel Compression: Achieving PPM-Class Text Compression Ratios with LZ-Class Decompression Speed","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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; Compression ratio; Data compression; Markov chain; Algorithm; Parallel computing; Speech recognition; Engineering","score_opus":0.015441098737651702,"score_gpt":0.2482501215768755,"score_spread":0.2328090228392238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564774846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16989453,0.0018272746,0.6309701,0.0017416433,0.00040086472,0.00048358797,0.0049215197,0.13310449,0.05665587],"genre_scores_gemma":[0.5062042,0.0008333857,0.45283118,0.00066209765,0.00030725295,0.00040540937,0.01126017,0.005814681,0.021681668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931645,0.00005846653,0.000039955252,0.00008430308,0.0004056377,0.00009529043],"domain_scores_gemma":[0.9988918,0.00030996808,0.000057685123,0.00026101578,0.0004057245,0.000073937685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006967235,0.00096304674,0.00048147322,0.0014425465,0.0004434217,0.0010030575,0.0015095609,0.000740518,0.015892858],"category_scores_gemma":[0.0037214328,0.0001932458,0.0003561998,0.0016598683,0.000738789,0.0018875117,0.0012692466,0.0010289502,0.00680729],"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":[0.0013110714,0.00022063522,0.0016502579,0.0006046847,0.000047221823,0.00041169015,0.00026028266,0.032804634,0.1723612,0.019627612,0.07547238,0.69522834],"study_design_scores_gemma":[0.00038150977,0.0005151135,0.001886937,0.000089332614,0.00006217229,0.00060657255,0.0001849125,0.38890544,0.5263287,0.016614832,0.064344056,0.00008045899],"about_ca_topic_score_codex":0.002306178,"about_ca_topic_score_gemma":0.0039149667,"teacher_disagreement_score":0.015892858,"about_ca_system_score_codex":0.0008343037,"about_ca_system_score_gemma":0.0012383414,"threshold_uncertainty_score":0.053166926},"labels":[],"label_agreement":null},{"id":"W2565125296","doi":"10.1109/dcc.2016.114","title":"Engineering Wavelet Tree Implementations for Compressed Web Graph Representations","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Computer science; Wavelet; Implementation; ENCODE; Data structure; Theoretical computer science; Bit array; Tree (set theory); Block (permutation group theory); Algorithm; Artificial intelligence; Mathematics; Combinatorics; Programming language","score_opus":0.022554625028342483,"score_gpt":0.2818460882914857,"score_spread":0.25929146326314323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565125296","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03707596,0.00027315176,0.94931835,0.0003246434,0.00009307116,0.00013553092,0.000784822,0.007840593,0.0041538686],"genre_scores_gemma":[0.27869198,0.000402934,0.71271837,0.00022502482,0.00007655223,0.0003378464,0.002922058,0.0013106457,0.003314593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990465,0.00016939448,0.00008284976,0.000100180834,0.0005051806,0.000095799565],"domain_scores_gemma":[0.99664634,0.0014614863,0.00021848099,0.00077503675,0.0008223727,0.000076171185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078055676,0.00059225195,0.0003546192,0.0013290902,0.00028391747,0.0012451794,0.001422731,0.0006845901,0.005897263],"category_scores_gemma":[0.0074091344,0.00027121976,0.00035532075,0.002181844,0.0005499562,0.0029598637,0.0012105054,0.0009262282,0.0015977854],"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":[0.0010672804,0.00032248354,0.0020383112,0.00058969157,0.00007159254,0.000501807,0.0005570289,0.19427739,0.04811397,0.089841425,0.024194306,0.6384247],"study_design_scores_gemma":[0.000095331525,0.0001724112,0.00028238446,0.000053867447,0.000020465246,0.00020531821,0.00011238059,0.9095012,0.048458707,0.02963539,0.01142865,0.00003384442],"about_ca_topic_score_codex":0.0014745186,"about_ca_topic_score_gemma":0.001988939,"teacher_disagreement_score":0.005897263,"about_ca_system_score_codex":0.0008548358,"about_ca_system_score_gemma":0.0006763445,"threshold_uncertainty_score":0.019728303},"labels":[],"label_agreement":null},{"id":"W2566137452","doi":"","title":"Computing the Genomic Distance in Linear Time","year":2010,"lang":"en","type":"article","venue":"PUB – Publications at Bielefeld University (Bielefeld University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science","score_opus":0.0077805722286413,"score_gpt":0.18276728020584393,"score_spread":0.17498670797720262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566137452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11715199,0.0024131304,0.80796,0.0070787007,0.0011393141,0.0004123317,0.007775592,0.02260343,0.033465516],"genre_scores_gemma":[0.33746725,0.0007539457,0.61406785,0.0011809118,0.0005360805,0.0003817201,0.014347682,0.0016185374,0.029646033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968002,0.0005129156,0.00022938766,0.0010650693,0.00092342077,0.0004690307],"domain_scores_gemma":[0.9954809,0.0024884208,0.00020633037,0.0011581432,0.00043890718,0.00022718344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102837,0.0018683998,0.0022095712,0.0020766014,0.0012838636,0.004762045,0.0026571834,0.0019427293,0.038607337],"category_scores_gemma":[0.008847986,0.0006985026,0.0017480762,0.004092203,0.0012625969,0.0065140785,0.0030635726,0.0021479803,0.015185248],"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":[0.002063695,0.0005218826,0.004996853,0.00066954235,0.00032214652,0.00039737436,0.0003932586,0.056072254,0.02212763,0.039697796,0.08279983,0.7899377],"study_design_scores_gemma":[0.0012263888,0.00041470316,0.0044299173,0.00012808034,0.0002915883,0.001056138,0.0011591263,0.5107635,0.026661696,0.41529837,0.038470175,0.0001002441],"about_ca_topic_score_codex":0.005542532,"about_ca_topic_score_gemma":0.015388524,"teacher_disagreement_score":0.038607337,"about_ca_system_score_codex":0.0023392688,"about_ca_system_score_gemma":0.003723072,"threshold_uncertainty_score":0.12915438},"labels":[],"label_agreement":null},{"id":"W2574587615","doi":"","title":"Forced Repetitions over Alphabet Lists.","year":2016,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Alphabet; Computer science; Natural language processing; Arithmetic; Mathematics; Linguistics","score_opus":0.02033900445680297,"score_gpt":0.2581649648182438,"score_spread":0.23782596036144082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574587615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11902699,0.005320279,0.78861064,0.002754702,0.0019820316,0.00029936148,0.0034226924,0.0076504685,0.070932865],"genre_scores_gemma":[0.72697043,0.001618627,0.21118638,0.0017332623,0.001019995,0.0004165721,0.004014851,0.0015218215,0.05151811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99621457,0.0010677384,0.000433631,0.0007232255,0.0011024266,0.00045840588],"domain_scores_gemma":[0.98542386,0.006600045,0.00074304873,0.005504855,0.0014392142,0.00028892313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00146556,0.0005971555,0.0008117615,0.0019299263,0.0014528455,0.0021131358,0.0022268402,0.0013686469,0.015805108],"category_scores_gemma":[0.018078363,0.00047369784,0.0007408882,0.0024796226,0.0012910463,0.005252101,0.0032204308,0.0017124679,0.005799658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013047239,0.00021561704,0.0025505796,0.00075084285,0.00015023805,0.001944083,0.0009204087,0.02272027,0.017728033,0.5079235,0.0397037,0.40408802],"study_design_scores_gemma":[0.00008577144,0.00018658853,0.00072115124,0.00031352998,0.000095625204,0.001991432,0.00024446152,0.09553966,0.03383289,0.81462055,0.052289765,0.00007864114],"about_ca_topic_score_codex":0.000711901,"about_ca_topic_score_gemma":0.0012755813,"teacher_disagreement_score":0.015805108,"about_ca_system_score_codex":0.00089722354,"about_ca_system_score_gemma":0.0013672698,"threshold_uncertainty_score":0.052873313},"labels":[],"label_agreement":null},{"id":"W2577316929","doi":"10.1109/mmsp.2016.7813407","title":"Novel UEP product code scheme with protograph-based linear permutation and iterative decoding for scalable image transmission","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Decoding methods; Permutation (music); Computer science; Code (set theory); Transmission (telecommunications); Scheme (mathematics); Scalability; Product (mathematics); Algorithm; Theoretical computer science; Mathematics; Telecommunications","score_opus":0.019517924688147288,"score_gpt":0.2690251783134539,"score_spread":0.24950725362530662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577316929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03158345,0.00057815085,0.9603173,0.00014002933,0.00006752977,0.000089451496,0.0001190411,0.001207381,0.0058976393],"genre_scores_gemma":[0.4703698,0.00054493995,0.52180976,0.00021375259,0.00007059862,0.00018630439,0.0004046862,0.000112168294,0.0062880344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993549,0.00016019905,0.00003211111,0.000085453175,0.00028823013,0.00007913232],"domain_scores_gemma":[0.9992398,0.00023335339,0.00008706385,0.00019441,0.00020793652,0.000037341135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049112225,0.0007085807,0.00052262394,0.0007394796,0.0005223274,0.000652643,0.0012050896,0.0006606552,0.0018125958],"category_scores_gemma":[0.0014223888,0.00028921876,0.0002947165,0.0012308969,0.0005565016,0.0015415474,0.0012294217,0.0008641445,0.00081089017],"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":[0.0006157886,0.0001786094,0.0010344062,0.00037241285,0.00010475661,0.0009182033,0.00045698768,0.12878193,0.22356424,0.16223976,0.006574585,0.4751583],"study_design_scores_gemma":[0.000045998448,0.00041459527,0.00031934123,0.000042120435,0.000045510267,0.0012023445,0.000043851232,0.8479191,0.12271604,0.014302331,0.012873079,0.000075672375],"about_ca_topic_score_codex":0.00092694064,"about_ca_topic_score_gemma":0.001280798,"teacher_disagreement_score":0.0018125958,"about_ca_system_score_codex":0.000516737,"about_ca_system_score_gemma":0.00078712497,"threshold_uncertainty_score":0.0060637593},"labels":[],"label_agreement":null},{"id":"W2579810741","doi":"10.21700/ijcis.2016.128","title":"Virus Recognition Based on Combination of Hashing and Neural Networks","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Computer science; Artificial intelligence; Hash function; Pattern recognition (psychology); Computer security","score_opus":0.0195956536982333,"score_gpt":0.2763916870543374,"score_spread":0.2567960333561041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579810741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18104461,0.0020070593,0.80980444,0.00024933217,0.0005133614,0.0002632247,0.00037527803,0.0017028558,0.004039855],"genre_scores_gemma":[0.7699446,0.0005885625,0.22534572,0.00013250798,0.0001565593,0.000106643376,0.0005251243,0.00004041161,0.0031598234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992841,0.00012365873,0.00004854688,0.0001614265,0.00029172446,0.00009052632],"domain_scores_gemma":[0.99913305,0.0002577047,0.000100844816,0.00012664632,0.0003279916,0.0000536658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006481737,0.000484598,0.0011329952,0.0015485361,0.000434116,0.00067722297,0.00081204425,0.00058849825,0.0013480104],"category_scores_gemma":[0.001472763,0.00026660925,0.00059557246,0.0011732627,0.00031959274,0.0015911389,0.00077673624,0.0004986592,0.00071758346],"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":[0.00059323333,0.00034065745,0.008733023,0.0002670846,0.00027508306,0.00016967284,0.000088218236,0.044371106,0.08114924,0.0045426325,0.0041398783,0.85533017],"study_design_scores_gemma":[0.000025288338,0.00021726945,0.003665966,0.000014332812,0.000068505105,0.0004327053,0.000046795165,0.96696186,0.023656005,0.0034923344,0.001373721,0.000045221368],"about_ca_topic_score_codex":0.0016206346,"about_ca_topic_score_gemma":0.0020682733,"teacher_disagreement_score":0.0016206346,"about_ca_system_score_codex":0.00042192466,"about_ca_system_score_gemma":0.00054752675,"threshold_uncertainty_score":0.004509568},"labels":[],"label_agreement":null},{"id":"W2583611270","doi":"10.1007/s11786-016-0288-7","title":"Palindromic Subsequence Automata and Longest Common Palindromic Subsequence","year":2017,"lang":"en","type":"article","venue":"Mathematics in Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Subsequence; Palindrome; Longest increasing subsequence; Automaton; Combinatorics; Longest common subsequence problem; Mathematics; Palindromic sequence; Discrete mathematics; Computer science; Theoretical computer science; Genetics; Biology","score_opus":0.029761861630975165,"score_gpt":0.2988133188211195,"score_spread":0.26905145719014434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583611270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12821081,0.0016981364,0.84789425,0.00070621434,0.00047875554,0.0001390088,0.00084378617,0.0017564025,0.018272595],"genre_scores_gemma":[0.73312145,0.00084883446,0.25175366,0.00038899278,0.00036987627,0.0003071782,0.001501156,0.00045747252,0.01125135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982095,0.00035333002,0.00026469253,0.000608806,0.00043183818,0.00013191349],"domain_scores_gemma":[0.99155104,0.0039539295,0.00079386844,0.0022466686,0.0012061305,0.00024834572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011357627,0.00060646114,0.0010219592,0.0024019822,0.0017171215,0.002504067,0.0019833993,0.0014549294,0.0066290065],"category_scores_gemma":[0.010765742,0.00049349846,0.001227795,0.0034016052,0.0022571448,0.00579169,0.0018124484,0.0017427283,0.0017850396],"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":[0.0003257224,0.00011206686,0.00172062,0.00024566098,0.00005093528,0.00057467114,0.00069368526,0.020256875,0.0068005254,0.88476187,0.002263717,0.08219345],"study_design_scores_gemma":[0.000017672894,0.00009669555,0.00026357095,0.00004828762,0.00003436654,0.00049210386,0.00017595812,0.09371074,0.003987452,0.8947255,0.0064186854,0.000028856026],"about_ca_topic_score_codex":0.0008059031,"about_ca_topic_score_gemma":0.00087755476,"teacher_disagreement_score":0.0066290065,"about_ca_system_score_codex":0.0010016374,"about_ca_system_score_gemma":0.00106273,"threshold_uncertainty_score":0.022176266},"labels":[],"label_agreement":null},{"id":"W2584903853","doi":"","title":"Bipartite grammar-based representations of large sparse binary matrices: Framework and transforms","year":2016,"lang":"en","type":"article","venue":"International Symposium on Information Theory and its Applications","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Terminal and nonterminal symbols; Bipartite graph; Logical matrix; Binary number; Matrix (chemical analysis); Combinatorics; Mathematics; Algorithm; Context (archaeology); Discrete mathematics; Graph; Computer science; Rule-based machine translation; Arithmetic; Artificial intelligence","score_opus":0.00808969763943832,"score_gpt":0.26821327339757695,"score_spread":0.2601235757581386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584903853","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008164554,0.000115025774,0.9887194,0.000121133,0.000041955253,0.0000387478,0.00016381203,0.00052003976,0.0021152382],"genre_scores_gemma":[0.24893269,0.000508799,0.74219745,0.00030326474,0.00012266535,0.00035695542,0.0012433729,0.0005542581,0.0057805832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992768,0.00022303757,0.000045975903,0.00013230692,0.000247404,0.000074492375],"domain_scores_gemma":[0.99912673,0.00033967206,0.000092787166,0.00019993576,0.00018670343,0.000054085023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006046745,0.0005597595,0.0004981889,0.0011718783,0.00040083856,0.0010661193,0.00092528004,0.0008741632,0.0035190198],"category_scores_gemma":[0.0029444783,0.00030839248,0.0006913511,0.0015915388,0.0011973942,0.0020415597,0.0011801049,0.0011492464,0.0013951841],"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":[0.00013708,0.000083872714,0.0005498653,0.000148595,0.000023597111,0.00046355347,0.000439609,0.16100845,0.02156121,0.6274144,0.005388534,0.18278123],"study_design_scores_gemma":[0.000021995258,0.000058600737,0.00014830605,0.000025419471,0.000010528027,0.00022689882,0.00009543595,0.6818277,0.0059148567,0.30163437,0.010004025,0.000031860938],"about_ca_topic_score_codex":0.002244922,"about_ca_topic_score_gemma":0.0020458729,"teacher_disagreement_score":0.0035190198,"about_ca_system_score_codex":0.0005179173,"about_ca_system_score_gemma":0.0009276541,"threshold_uncertainty_score":0.011772335},"labels":[],"label_agreement":null},{"id":"W2585936885","doi":"10.1145/3007186","title":"Inverted Treaps","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Inverted index; Merge (version control); Identifier; ENCODE; Intersection (aeronautics); Thresholding; Representation (politics); Index (typography); Data mining; Information retrieval; Search engine indexing; Theoretical computer science; Artificial intelligence; Image (mathematics)","score_opus":0.02721772894203236,"score_gpt":0.2607516944946491,"score_spread":0.2335339655526167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585936885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033885617,0.0015767926,0.89444864,0.0005375368,0.0008868058,0.00069156656,0.01987669,0.018907933,0.029188365],"genre_scores_gemma":[0.20260128,0.0012562622,0.7214019,0.0005281541,0.0005711238,0.0010097022,0.045687392,0.0027168214,0.024227493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755883,0.00021654325,0.00031571495,0.000442718,0.0011895332,0.00027661194],"domain_scores_gemma":[0.9931722,0.0010407699,0.0005097171,0.0028395029,0.0021779698,0.00025977826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011378656,0.0012011182,0.0017347918,0.0058542746,0.0014308487,0.004240888,0.0028449276,0.0011226523,0.01620859],"category_scores_gemma":[0.010539912,0.0006629422,0.0013292421,0.010288121,0.00096756977,0.00751753,0.0032285077,0.0017601036,0.008602586],"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":[0.0009246802,0.00030428285,0.0026634587,0.00070593343,0.00017389012,0.00043071024,0.00048884825,0.041065928,0.02799455,0.12322185,0.080766186,0.7212597],"study_design_scores_gemma":[0.00021961065,0.000993196,0.00266837,0.0002778753,0.00020373073,0.0021646698,0.00068653765,0.4867764,0.08604645,0.17552565,0.24405876,0.00037885114],"about_ca_topic_score_codex":0.006262681,"about_ca_topic_score_gemma":0.006518181,"teacher_disagreement_score":0.01620859,"about_ca_system_score_codex":0.0014141997,"about_ca_system_score_gemma":0.0027329961,"threshold_uncertainty_score":0.05422312},"labels":[],"label_agreement":null},{"id":"W2586556622","doi":"10.1016/j.jda.2017.01.003","title":"Practical algorithms to rank necklaces, Lyndon words, and de Bruijn sequences","year":2017,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"De Bruijn sequence; Lexicographical order; Substring; Combinatorics; Ranking (information retrieval); Rank (graph theory); Sequence (biology); Mathematics; Order (exchange); Algorithm; Simple (philosophy); Computer science; Artificial intelligence; Data structure","score_opus":0.03259474542133807,"score_gpt":0.34319060051526473,"score_spread":0.3105958550939267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586556622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047242735,0.0009449106,0.9394754,0.0007299039,0.00025071838,0.00017627008,0.0003408304,0.0012465416,0.009592687],"genre_scores_gemma":[0.29843444,0.0008124114,0.6788597,0.00036181178,0.00038560384,0.0003934534,0.0010769726,0.00048197908,0.019193722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973303,0.00078514277,0.0002120849,0.00041987022,0.0009772788,0.00027531284],"domain_scores_gemma":[0.99273294,0.0039132955,0.00048612786,0.001623404,0.0009529375,0.00029132326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002784891,0.0013645536,0.0014054948,0.0029983276,0.0012912404,0.0027818985,0.0017869243,0.0015475397,0.010762207],"category_scores_gemma":[0.022089958,0.00078093953,0.0007249888,0.0027718893,0.0022585487,0.0056981295,0.0035882075,0.0027593905,0.0031758859],"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":[0.0007755924,0.0002290279,0.0008326599,0.00036205212,0.000050594317,0.00013542788,0.0004614001,0.067394614,0.0061931787,0.5543922,0.014114942,0.3550583],"study_design_scores_gemma":[0.00014039224,0.00024749493,0.00015834812,0.00008766407,0.000026182277,0.00020241215,0.00020986881,0.29191443,0.0064452146,0.6912337,0.009274818,0.00005946623],"about_ca_topic_score_codex":0.0013898185,"about_ca_topic_score_gemma":0.003184593,"teacher_disagreement_score":0.010762207,"about_ca_system_score_codex":0.0012743281,"about_ca_system_score_gemma":0.002050048,"threshold_uncertainty_score":0.036003172},"labels":[],"label_agreement":null},{"id":"W2587741488","doi":"10.1137/140998949","title":"Time-Optimal Top-$k$ Document Retrieval","year":2017,"lang":"en","type":"article","venue":"SIAM Journal on Computing","topic":"Algorithms and Data Compression","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 Waterloo","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico","keywords":"Computer science; Information retrieval; Top-down and bottom-up design; Document retrieval; Combinatorics; Mathematics; Programming language","score_opus":0.015024961139985544,"score_gpt":0.28698931078504725,"score_spread":0.2719643496450617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587741488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09880214,0.0066810865,0.83730996,0.0020453944,0.00058247504,0.00048070116,0.0065273903,0.024853516,0.022717297],"genre_scores_gemma":[0.30119798,0.0012402317,0.6716886,0.000605672,0.00042714237,0.0003329786,0.009778399,0.0010394885,0.01368939],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972344,0.00045031655,0.00035385482,0.0006487589,0.0007992956,0.0005132531],"domain_scores_gemma":[0.9974782,0.000675727,0.00021864958,0.0011466102,0.00035340906,0.00012740404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082795805,0.0011830054,0.0024168014,0.002515289,0.0014402418,0.0029556816,0.004031243,0.0019429659,0.011181025],"category_scores_gemma":[0.0066628596,0.0007977696,0.0013258689,0.0062378473,0.0011293886,0.0057044844,0.0035241116,0.0010746246,0.010521791],"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":[0.0014810511,0.00051923434,0.001564439,0.0009905099,0.00014512842,0.00026899687,0.00037380756,0.045668844,0.037954576,0.027110431,0.06880992,0.81511295],"study_design_scores_gemma":[0.0008470632,0.00061938347,0.0022146385,0.00011634908,0.00030327414,0.00181567,0.0006256372,0.75166494,0.048327245,0.1593085,0.03394513,0.00021218901],"about_ca_topic_score_codex":0.0051042624,"about_ca_topic_score_gemma":0.010841206,"teacher_disagreement_score":0.011181025,"about_ca_system_score_codex":0.0020542704,"about_ca_system_score_gemma":0.0036564642,"threshold_uncertainty_score":0.03740424},"labels":[],"label_agreement":null},{"id":"W2590479319","doi":"","title":"Efficient dynamic range minimum query","year":2010,"lang":"en","type":"preprint","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Computer science; Range (aeronautics); Query optimization; Information retrieval; Engineering","score_opus":0.03184430581383486,"score_gpt":0.2937588846034415,"score_spread":0.26191457878960667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590479319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10697189,0.0044268155,0.826651,0.003015468,0.0003476631,0.00040481176,0.0031640404,0.010665482,0.04435285],"genre_scores_gemma":[0.5994979,0.0010148685,0.36810538,0.00070473284,0.0003558235,0.00032552396,0.005498723,0.0012078603,0.023289146],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99802834,0.0002754727,0.000118489166,0.00037569026,0.00093436654,0.0002675874],"domain_scores_gemma":[0.99771297,0.0009186593,0.000108227796,0.0008692381,0.00032114552,0.00006982316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081500714,0.0007121626,0.0019405289,0.0017329232,0.00086580194,0.0019338294,0.0018017164,0.0011598041,0.016263701],"category_scores_gemma":[0.0049055405,0.0004981416,0.00057211996,0.0028952663,0.0006492674,0.0039044023,0.003424051,0.00122151,0.0038758123],"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":[0.003011295,0.00052974734,0.0021715786,0.0009270838,0.00014222525,0.00045476976,0.0003975995,0.05155687,0.07320857,0.053502206,0.092262365,0.72183573],"study_design_scores_gemma":[0.0005603569,0.00056118635,0.0019615593,0.000114655784,0.00015499262,0.001948873,0.00043154653,0.77018416,0.06680634,0.10298503,0.05420618,0.00008517407],"about_ca_topic_score_codex":0.0011589382,"about_ca_topic_score_gemma":0.0016702779,"teacher_disagreement_score":0.016263701,"about_ca_system_score_codex":0.0010259285,"about_ca_system_score_gemma":0.00084786664,"threshold_uncertainty_score":0.054407477},"labels":[],"label_agreement":null},{"id":"W2590761221","doi":"10.29173/cais151","title":"Fast Adaptive Data Compression for Information Retrieval","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Information retrieval; Compression (physics); Data compression; Data mining; Artificial intelligence","score_opus":0.036438392775160436,"score_gpt":0.2557913245717911,"score_spread":0.21935293179663068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590761221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011939966,0.023828538,0.93833166,0.0012436986,0.0021901717,0.00032902727,0.0009189377,0.005760772,0.01545728],"genre_scores_gemma":[0.19565576,0.016627321,0.7008394,0.0007615258,0.0028409366,0.0006782782,0.004028502,0.000836036,0.07773229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999491,0.00011695343,0.00002766667,0.00006771392,0.00024858103,0.000048201488],"domain_scores_gemma":[0.99879265,0.00053461024,0.000055734286,0.00027607067,0.0003113507,0.000029532217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044681685,0.0009286255,0.0010663103,0.0021926945,0.00040230033,0.0010129161,0.0010359066,0.0009936037,0.02445757],"category_scores_gemma":[0.0028394174,0.00030484571,0.000454661,0.0032890972,0.00051651173,0.0015919504,0.0007704029,0.00094606244,0.010769358],"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":[0.00043025817,0.00006446546,0.00020702754,0.0006094222,0.00005119734,0.000114801944,0.000041938074,0.009424336,0.031785287,0.014565153,0.03828941,0.90441674],"study_design_scores_gemma":[0.00020469364,0.0005462142,0.0028055136,0.00042813967,0.00020478248,0.001249301,0.00008414289,0.68430275,0.11771403,0.0473954,0.14494637,0.00011862281],"about_ca_topic_score_codex":0.0016968498,"about_ca_topic_score_gemma":0.0016464839,"teacher_disagreement_score":0.02445757,"about_ca_system_score_codex":0.0004598388,"about_ca_system_score_gemma":0.00046684672,"threshold_uncertainty_score":0.08181876},"labels":[],"label_agreement":null},{"id":"W2591863098","doi":"","title":"P m U P k -equipackable paths and cycles.","year":2017,"lang":"ca","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Combinatorics","score_opus":0.01918080020038879,"score_gpt":0.2706396959340914,"score_spread":0.25145889573370256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591863098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16787438,0.0039101955,0.6506415,0.0039014274,0.00092123746,0.00032997466,0.005569181,0.0035928062,0.16325933],"genre_scores_gemma":[0.71148556,0.0019966238,0.22184148,0.0010369126,0.00037089307,0.0004993212,0.0058701215,0.000833284,0.056065805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988543,0.00024563572,0.000103379476,0.00028041968,0.00028378956,0.0002325284],"domain_scores_gemma":[0.99603695,0.0015520648,0.00035988755,0.0014117876,0.0004114308,0.00022785617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055692194,0.0007125312,0.000637745,0.0018991785,0.0015126128,0.0026684136,0.0011862308,0.0011261597,0.01818504],"category_scores_gemma":[0.0085761435,0.000439024,0.00058051234,0.0028935033,0.0013520084,0.0046304544,0.0030699188,0.0019826433,0.003923686],"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":[0.00065520784,0.00015935175,0.0016337456,0.00032388,0.000055027656,0.00057627144,0.00033682433,0.0112902,0.004560524,0.71497303,0.038047817,0.22738811],"study_design_scores_gemma":[0.000028068736,0.000060810235,0.00065660034,0.00010254876,0.000027914999,0.0005805994,0.00020825212,0.024513494,0.005568011,0.9314413,0.036786098,0.000026263959],"about_ca_topic_score_codex":0.0011389658,"about_ca_topic_score_gemma":0.0015710151,"teacher_disagreement_score":0.01818504,"about_ca_system_score_codex":0.00081746606,"about_ca_system_score_gemma":0.0010219329,"threshold_uncertainty_score":0.060835063},"labels":[],"label_agreement":null},{"id":"W2592132648","doi":"10.22146/jnteti.v6i1.290","title":"Modifikasi Algoritme J-Bit Encoding untuk Meningkatkan Rasio Kompresi","year":2017,"lang":"id","type":"article","venue":"Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI)","topic":"Algorithms and Data Compression","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":"","keywords":"Encoding (memory); Mathematics; Computer science; Artificial intelligence","score_opus":0.036117666806039166,"score_gpt":0.2874742374754726,"score_spread":0.25135657066943345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592132648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17781587,0.0029888963,0.75026935,0.0012848245,0.0015066284,0.0005207548,0.0011238154,0.017554319,0.046935566],"genre_scores_gemma":[0.41397887,0.0017210058,0.46462467,0.0011759207,0.00029966378,0.00037838123,0.0018922309,0.0015142353,0.11441503],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946386,0.00005381356,0.000059224847,0.00012035958,0.00021529674,0.00008745388],"domain_scores_gemma":[0.9990447,0.00015467395,0.00006199317,0.00037553438,0.00032564852,0.000037384187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043503963,0.0009029619,0.00059334526,0.0006110193,0.0007176993,0.0018212699,0.0009437253,0.000763532,0.012145087],"category_scores_gemma":[0.0016683986,0.00029919815,0.00053984637,0.0008270181,0.0005129001,0.002395013,0.00092424505,0.0010452409,0.004879005],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010149913,0.00016635643,0.0016031025,0.00045136333,0.00007336327,0.00037931724,0.0007181655,0.006045409,0.3462889,0.017109234,0.014164416,0.61198545],"study_design_scores_gemma":[0.00010508,0.0007162093,0.0032033734,0.00014229247,0.00020229988,0.0015982909,0.00060902146,0.09526954,0.70719093,0.008872829,0.18192606,0.00016411205],"about_ca_topic_score_codex":0.0023053084,"about_ca_topic_score_gemma":0.002908629,"teacher_disagreement_score":0.012145087,"about_ca_system_score_codex":0.000827348,"about_ca_system_score_gemma":0.0008411774,"threshold_uncertainty_score":0.040629327},"labels":[],"label_agreement":null},{"id":"W2592164980","doi":"","title":"A prefix array for parameterized strings","year":2016,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Parameterized complexity; String (physics); Prefix; Mathematics; Combinatorics; Computer science; Generalization; Trie; Data structure; Algorithm","score_opus":0.06454295354089348,"score_gpt":0.29931129036075055,"score_spread":0.23476833681985707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592164980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009039902,0.00054235937,0.9558681,0.00036732692,0.0003079735,0.00023186392,0.006392061,0.015316716,0.011933706],"genre_scores_gemma":[0.073971644,0.00085199124,0.88223845,0.0003427082,0.00021075034,0.00082041504,0.017736143,0.005035618,0.018792203],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972365,0.00049707555,0.00052772666,0.00059274514,0.00092669675,0.00021925196],"domain_scores_gemma":[0.99335265,0.001963709,0.0003561981,0.0028719192,0.0012502274,0.00020530692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014393609,0.0011931646,0.0014430487,0.0028551887,0.0013243991,0.003808098,0.002147935,0.0015449867,0.034979846],"category_scores_gemma":[0.012090011,0.00090708886,0.0011503082,0.007142556,0.001120398,0.0075362907,0.002917657,0.0021139968,0.022177309],"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":[0.00087651314,0.00016354187,0.0010695783,0.0006094878,0.000048298785,0.00045748721,0.00045702365,0.011683132,0.01789688,0.23159629,0.061910003,0.67323184],"study_design_scores_gemma":[0.00017079571,0.0003651679,0.0005735154,0.00043643653,0.00009317413,0.0012334283,0.00033936702,0.107637264,0.054712858,0.42723906,0.40703315,0.00016575858],"about_ca_topic_score_codex":0.0006580672,"about_ca_topic_score_gemma":0.0006609808,"teacher_disagreement_score":0.034979846,"about_ca_system_score_codex":0.0010590808,"about_ca_system_score_gemma":0.0019742853,"threshold_uncertainty_score":0.117019236},"labels":[],"label_agreement":null},{"id":"W2592557380","doi":"10.1016/j.tcs.2017.02.016","title":"Constructing an indeterminate string from its associated graph","year":2017,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Mathematics; Cardinality (data modeling); Discrete mathematics; Heuristics; Clique; Alphabet; String (physics); Vertex cover; Heuristic; Graph; Computer science; Mathematical optimization","score_opus":0.020535399402898905,"score_gpt":0.2824883555088229,"score_spread":0.261952956105924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592557380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12367845,0.00023089742,0.85234076,0.0012390743,0.0004003194,0.00015199093,0.0008807266,0.0018183204,0.019259423],"genre_scores_gemma":[0.5569551,0.00040656808,0.42619023,0.00034661283,0.000115479495,0.00020008461,0.0014304272,0.00089730474,0.013458288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99925846,0.00017604505,0.00005312165,0.0001718727,0.00023378588,0.0001066126],"domain_scores_gemma":[0.99816006,0.000872809,0.000086616164,0.000540965,0.0002564681,0.00008313605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005724675,0.00053069816,0.0006121192,0.0013313815,0.00088048587,0.0016100378,0.0011342247,0.0013620037,0.006532608],"category_scores_gemma":[0.0049285335,0.00027125987,0.00057121547,0.0020485735,0.0009769291,0.0025437109,0.0017895995,0.0016299682,0.0021797472],"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":[0.00065983494,0.00018182791,0.0015169035,0.00045464482,0.00003274634,0.00093428756,0.000571947,0.022739885,0.026367957,0.68752587,0.00954277,0.24947134],"study_design_scores_gemma":[0.00005033114,0.00015180276,0.00046431756,0.00008690455,0.000048924572,0.00061805156,0.00027023163,0.1183071,0.021740492,0.83840823,0.019798478,0.00005502679],"about_ca_topic_score_codex":0.0004955449,"about_ca_topic_score_gemma":0.00049114734,"teacher_disagreement_score":0.006532608,"about_ca_system_score_codex":0.0005061815,"about_ca_system_score_gemma":0.0006463114,"threshold_uncertainty_score":0.021853745},"labels":[],"label_agreement":null},{"id":"W2594669407","doi":"10.1109/acssc.2016.7869036","title":"Construction of minimal sets for capacity-approaching variable-length constrained sequence codes","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates - Technology Futures","keywords":"Sequence (biology); Construct (python library); Computer science; Set (abstract data type); State (computer science); Encoder; Variable (mathematics); Code (set theory); Process (computing); Algorithm; Theoretical computer science; Mathematics; Programming language","score_opus":0.046937086305031954,"score_gpt":0.26820791060297017,"score_spread":0.2212708242979382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594669407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026007926,0.000087906126,0.9705486,0.00006205447,0.000012286391,0.0000859923,0.00009282348,0.00013694786,0.0029655027],"genre_scores_gemma":[0.43309036,0.00022646843,0.5635639,0.00009853456,0.000024040044,0.00053180766,0.00049138174,0.00012388694,0.0018495804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989254,0.0003366258,0.0000944978,0.00012282937,0.0004248026,0.00009576092],"domain_scores_gemma":[0.9976865,0.0013136124,0.00023261966,0.00024594943,0.00042792442,0.00009343311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001363356,0.00063721434,0.0007586534,0.001167618,0.0005720911,0.00083632057,0.0009017723,0.00059188576,0.0017000709],"category_scores_gemma":[0.005879123,0.00043665167,0.0005538495,0.0005804985,0.0011973566,0.0012823029,0.0016992795,0.0010811049,0.00036062012],"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":[0.00018596096,0.0000831906,0.0007557948,0.00028688373,0.000041889463,0.00016816908,0.00028726758,0.31253663,0.031158019,0.5638028,0.0015655936,0.08912781],"study_design_scores_gemma":[0.000034845827,0.00020491303,0.00024635592,0.00009469449,0.000018030496,0.00013546947,0.00007583901,0.7084943,0.050359786,0.23456563,0.0057115825,0.000058477784],"about_ca_topic_score_codex":0.0003562844,"about_ca_topic_score_gemma":0.0005455093,"teacher_disagreement_score":0.0017000709,"about_ca_system_score_codex":0.00070923165,"about_ca_system_score_gemma":0.0012067045,"threshold_uncertainty_score":0.007210195},"labels":[],"label_agreement":null},{"id":"W2594960983","doi":"","title":"The Maximum Number of Runs in a String","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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":"Substring; Combinatorics; Mathematics; String (physics); Integer (computer science); Exponent; Period (music); Prefix; Discrete mathematics; Physics; Data structure; Computer science","score_opus":0.01080755792253085,"score_gpt":0.2761886386070594,"score_spread":0.26538108068452854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594960983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7215138,0.0068825656,0.17123398,0.0034445892,0.0009841112,0.00039614472,0.013697984,0.004747582,0.07709918],"genre_scores_gemma":[0.8386822,0.0020005545,0.12908997,0.0005824406,0.0007463907,0.0006802884,0.0070490306,0.00080656534,0.020362653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981906,0.00023740901,0.0003633721,0.000573592,0.00039322017,0.00024173273],"domain_scores_gemma":[0.9948088,0.0024118214,0.0008093824,0.0011499278,0.00049247325,0.00032758177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009808387,0.0005634049,0.00070671603,0.0012064254,0.0010910934,0.001862548,0.0007058857,0.0008645872,0.0065845177],"category_scores_gemma":[0.007069865,0.00043372225,0.00034110036,0.0011329758,0.00087824825,0.0034332892,0.0015148543,0.00074177835,0.0021493286],"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":[0.0039101834,0.0003017078,0.03308985,0.0016973581,0.00029114936,0.0024505898,0.0015152828,0.007451391,0.14877401,0.13330157,0.023178924,0.6440379],"study_design_scores_gemma":[0.0003449741,0.0024633624,0.051915072,0.0014436216,0.0005493813,0.017434848,0.0019279076,0.05533174,0.24341004,0.30091095,0.32388198,0.00038614805],"about_ca_topic_score_codex":0.00020609659,"about_ca_topic_score_gemma":0.0003119647,"teacher_disagreement_score":0.0065845177,"about_ca_system_score_codex":0.00049895496,"about_ca_system_score_gemma":0.0006967597,"threshold_uncertainty_score":0.022027433},"labels":[],"label_agreement":null},{"id":"W2596520444","doi":"10.1088/1757-899x/180/1/012062","title":"On Using Goldbach G0 Codes and Even-Rodeh Codes for Text Compression on Using Goldbach G0 Codes and Even-Rodeh Codes for Text Compression","year":2017,"lang":"en","type":"article","venue":"IOP Conference Series Materials Science and Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"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":"ASCII; Uncompressed video; Computer science; Goldbach's conjecture; Arithmetic; Mathematics; Artificial intelligence; Discrete mathematics; Number theory","score_opus":0.04564023271615302,"score_gpt":0.29192111994358283,"score_spread":0.2462808872274298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596520444","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66056216,0.004180867,0.3183912,0.00081261405,0.00016849698,0.00020681883,0.00036786313,0.001590657,0.013719246],"genre_scores_gemma":[0.7021435,0.0014952112,0.2902942,0.00028622008,0.00006403449,0.00014579597,0.00069325964,0.00023928317,0.0046384614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787796,0.00071445195,0.00016136024,0.000232238,0.0008464926,0.00016756647],"domain_scores_gemma":[0.9907802,0.005820098,0.00064634887,0.0012725416,0.0013382178,0.00014273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025576365,0.0007789655,0.00043078986,0.0017066484,0.00051143725,0.0011194295,0.0005480836,0.00075635465,0.0017691415],"category_scores_gemma":[0.015858766,0.00017268151,0.00031887236,0.0018721805,0.0010812645,0.002740112,0.0007467353,0.0006255464,0.0006566272],"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":[0.0028936297,0.0002686033,0.00794113,0.0006520143,0.00012987072,0.00047125792,0.00059976353,0.19311301,0.09456621,0.048345644,0.0033790492,0.64763975],"study_design_scores_gemma":[0.00014796572,0.001228755,0.0030162176,0.00018293332,0.000094489405,0.00087508635,0.00044576696,0.7166684,0.24375665,0.024318064,0.009172519,0.00009308775],"about_ca_topic_score_codex":0.0024673762,"about_ca_topic_score_gemma":0.0028924937,"teacher_disagreement_score":0.0025576365,"about_ca_system_score_codex":0.00067821017,"about_ca_system_score_gemma":0.0010326201,"threshold_uncertainty_score":0.013526201},"labels":[],"label_agreement":null},{"id":"W2609313589","doi":"","title":"Conditional expectation algorithms for covering arrays","year":2014,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Algorithm","score_opus":0.017256465950654852,"score_gpt":0.2662495331624527,"score_spread":0.24899306721179784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609313589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012066381,0.00040330525,0.9821915,0.00077711185,0.00007324547,0.00005802848,0.00033544985,0.0011404115,0.0029546176],"genre_scores_gemma":[0.38550422,0.0010286667,0.5958844,0.0010586125,0.00050857227,0.00062987854,0.003828014,0.0011981239,0.010359499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653256,0.0015313585,0.00019561293,0.0006130389,0.00071040174,0.00041691455],"domain_scores_gemma":[0.9718685,0.02245838,0.0008049449,0.0028064086,0.0015004571,0.00056131376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032703392,0.0015063637,0.0023818926,0.0016476357,0.0010948151,0.0029478746,0.0041348143,0.0022349355,0.009590311],"category_scores_gemma":[0.029051213,0.0011532935,0.0015636313,0.003576285,0.0019613646,0.007899496,0.004196852,0.0044253897,0.0021999592],"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":[0.00059581717,0.000410457,0.0017121013,0.00031417573,0.00016212695,0.0001478064,0.00031193736,0.36857364,0.002358551,0.38302127,0.020054825,0.22233725],"study_design_scores_gemma":[0.000040295836,0.00004051007,0.00015977884,0.000023854189,0.00001820257,0.000056814424,0.000031331947,0.7037076,0.00096928567,0.2935917,0.0013430646,0.000017636681],"about_ca_topic_score_codex":0.0021976535,"about_ca_topic_score_gemma":0.0025666824,"teacher_disagreement_score":0.009590311,"about_ca_system_score_codex":0.0019903507,"about_ca_system_score_gemma":0.0023601109,"threshold_uncertainty_score":0.032082736},"labels":[],"label_agreement":null},{"id":"W2610512692","doi":"10.1016/j.ipl.2017.04.010","title":"Finding the largest fixed-density necklace and Lyndon word","year":2017,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Necklace; Lexicographical order; Word (group theory); String (physics); Mathematics; Combinatorics; Discrete mathematics; Geometry","score_opus":0.013703008732276704,"score_gpt":0.24386364245283912,"score_spread":0.23016063372056242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610512692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28315496,0.0022025125,0.69151676,0.0020278434,0.00042672205,0.00022400652,0.0013754582,0.0023201087,0.01675162],"genre_scores_gemma":[0.589299,0.0007169736,0.3873584,0.0004749987,0.00019385102,0.00034094608,0.002114925,0.00067140936,0.018829497],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991617,0.00015693194,0.00008365346,0.00022880656,0.00024279453,0.0001261437],"domain_scores_gemma":[0.99636203,0.0020320266,0.00022049669,0.00057401083,0.0005967155,0.00021479094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009146324,0.00096992386,0.0016494603,0.0026272773,0.0014228508,0.0015919335,0.0018106204,0.0022499796,0.010709468],"category_scores_gemma":[0.016846407,0.0007324894,0.0007668889,0.0017169971,0.0016445201,0.0045052953,0.0023623887,0.0016014735,0.0030459722],"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":[0.002402964,0.00039773996,0.006601711,0.0011953915,0.00014955757,0.0015987427,0.0011873529,0.08468735,0.036938563,0.309675,0.053277403,0.5018882],"study_design_scores_gemma":[0.00016840569,0.0003705413,0.0017942666,0.00021369144,0.00010678607,0.001208997,0.0007660982,0.5075792,0.023072042,0.44687697,0.017674822,0.00016819205],"about_ca_topic_score_codex":0.0018899307,"about_ca_topic_score_gemma":0.0028841882,"teacher_disagreement_score":0.010709468,"about_ca_system_score_codex":0.0009278025,"about_ca_system_score_gemma":0.0014077284,"threshold_uncertainty_score":0.035826743},"labels":[],"label_agreement":null},{"id":"W2610819251","doi":"10.1016/j.tcs.2017.04.008","title":"Reconstructing a string from its Lyndon arrays","year":2017,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"String (physics); Combinatorics; Computer science; Mathematics; Algorithm","score_opus":0.0204940698894321,"score_gpt":0.2687786662791555,"score_spread":0.2482845963897234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610819251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13667315,0.00052755483,0.85344255,0.0007291485,0.00030872854,0.000045925746,0.000454524,0.001760184,0.0060581826],"genre_scores_gemma":[0.5223949,0.00057647773,0.46185952,0.00031178675,0.00016523832,0.00013046083,0.0015800621,0.0004134286,0.012568077],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999286,0.00015164429,0.00007681199,0.00012413348,0.00027633616,0.00008503164],"domain_scores_gemma":[0.9980394,0.0009188864,0.00014011879,0.00055040483,0.00027832694,0.00007289871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006373531,0.0005815668,0.00073716615,0.00087748165,0.00048787642,0.0010121237,0.00068623846,0.0015148591,0.00283399],"category_scores_gemma":[0.0050105243,0.0003506456,0.0004943699,0.0014653285,0.00073033624,0.0021712005,0.0016050166,0.0015426406,0.0016822426],"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":[0.0018529715,0.0001979775,0.003596322,0.0005890444,0.00008918831,0.0012984034,0.0007503783,0.040179137,0.11428533,0.18644473,0.011970286,0.63874626],"study_design_scores_gemma":[0.00010885081,0.000477257,0.0015418561,0.00019692355,0.00009373509,0.0015623231,0.0006434229,0.50788665,0.13807109,0.32885495,0.020451527,0.00011140238],"about_ca_topic_score_codex":0.000500473,"about_ca_topic_score_gemma":0.00068366394,"teacher_disagreement_score":0.00283399,"about_ca_system_score_codex":0.00028826573,"about_ca_system_score_gemma":0.0006044435,"threshold_uncertainty_score":0.009480655},"labels":[],"label_agreement":null},{"id":"W2610876956","doi":"10.1007/978-3-319-59162-9_4","title":"Enhancing English-Japanese Translation Using Syntactic Pattern Recognition Methods","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Sentence; Natural language processing; Machine translation; Artificial intelligence; String (physics); Set (abstract data type); Matching (statistics); Translation (biology); Representation (politics); Point (geometry); Speech recognition; Programming language; Mathematics","score_opus":0.06543262994484582,"score_gpt":0.34790471658184746,"score_spread":0.28247208663700163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610876956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14849648,0.0033468772,0.7685836,0.0013972073,0.002498166,0.00025344457,0.0025491947,0.011644837,0.06123019],"genre_scores_gemma":[0.39574617,0.0031912734,0.5469103,0.00068822363,0.00067605823,0.00025201836,0.0070512425,0.0033279783,0.04215677],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961746,0.000092548806,0.000048695343,0.000077988334,0.00011160793,0.000051583484],"domain_scores_gemma":[0.9990433,0.00022842211,0.000045267254,0.00012801727,0.0005263585,0.000028571463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046906527,0.0012516308,0.00074593694,0.00086313556,0.0005900414,0.0013150796,0.00042856045,0.0005427134,0.012210945],"category_scores_gemma":[0.0019303197,0.0002747513,0.00073043065,0.0015479199,0.0002760926,0.0015707712,0.0009780616,0.0008972274,0.009014604],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043397423,0.00019244346,0.0010905082,0.0009861542,0.00008174495,0.0007678342,0.00066794746,0.005842004,0.15586653,0.009144918,0.0247254,0.8002005],"study_design_scores_gemma":[0.00022611479,0.00087648263,0.008102186,0.0002628386,0.0010263532,0.0026026098,0.0022734588,0.32713494,0.46803558,0.018142221,0.17111531,0.0002019567],"about_ca_topic_score_codex":0.0024985087,"about_ca_topic_score_gemma":0.0036313098,"teacher_disagreement_score":0.012210945,"about_ca_system_score_codex":0.00025370924,"about_ca_system_score_gemma":0.0007704433,"threshold_uncertainty_score":0.040849626},"labels":[],"label_agreement":null},{"id":"W2613337430","doi":"10.1016/j.tcs.2020.04.008","title":"Step-optimal implementations of large single-writer registers","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Register (sociolinguistics); Algorithm; Arithmetic; Shift register; Upper and lower bounds; Binary logarithm; Time complexity; Bit (key); Discrete mathematics; Mathematics","score_opus":0.02542056911127512,"score_gpt":0.28924634464861265,"score_spread":0.26382577553733755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613337430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16596563,0.0013065191,0.8068942,0.00062606577,0.00024120716,0.00015454345,0.00043742376,0.0077180583,0.016656354],"genre_scores_gemma":[0.6670701,0.00033232383,0.31995407,0.00017199884,0.00007411786,0.00014742443,0.00041430083,0.00044307398,0.011392562],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990208,0.00018457999,0.00010051943,0.00014894025,0.0003665987,0.00017859507],"domain_scores_gemma":[0.99773526,0.0007520548,0.00011154342,0.0010281355,0.00029435236,0.000078585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064647215,0.00059840723,0.0005891574,0.0006511531,0.000640548,0.0016495074,0.0019969712,0.0006431291,0.011251923],"category_scores_gemma":[0.0037598156,0.00054924644,0.00041423793,0.0011263106,0.0004954974,0.0032560285,0.0013428401,0.0009809289,0.002621365],"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":[0.0040855636,0.00045515876,0.0025438983,0.0006227388,0.00011909368,0.00030668272,0.00043266977,0.063681275,0.09059351,0.13173482,0.020755585,0.68466896],"study_design_scores_gemma":[0.0007196056,0.00073362916,0.0013350619,0.00014347325,0.00017460852,0.000492782,0.00032738023,0.60020095,0.21216021,0.16072372,0.022884857,0.00010367949],"about_ca_topic_score_codex":0.00060001144,"about_ca_topic_score_gemma":0.0024515255,"teacher_disagreement_score":0.011251923,"about_ca_system_score_codex":0.00076365785,"about_ca_system_score_gemma":0.0017195885,"threshold_uncertainty_score":0.037641466},"labels":[],"label_agreement":null},{"id":"W2613810684","doi":"10.1109/tit.2019.2941895","title":"Universal Weak Variable-Length Source Coding on Countably Infinite Alphabets","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","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":"Université de Montréal","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; Horizon 2020 Framework Programme; European Commission","keywords":"Lossless compression; Context-adaptive variable-length coding; Variable-length code; Entropy encoding; Entropy (arrow of time); Shannon–Fano coding; Entropy rate; Source code; Rate–distortion theory; Tunstall coding","score_opus":0.006594828244757613,"score_gpt":0.2022408314730425,"score_spread":0.1956460032282849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613810684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066445544,0.0005688984,0.9267231,0.00033706456,0.000043107877,0.000019157833,0.00009036269,0.00019611728,0.0055766334],"genre_scores_gemma":[0.9282547,0.00077075127,0.06787373,0.00019458191,0.000089868234,0.00007562434,0.00013646045,0.00005858617,0.0025456124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885345,0.00039995305,0.00008737498,0.00016864693,0.000357858,0.00013268163],"domain_scores_gemma":[0.9951858,0.0031284236,0.00061433524,0.0006223186,0.00033161405,0.00011760052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014469747,0.00043853465,0.0006982407,0.0007238728,0.00034843248,0.0011425497,0.0010757897,0.00050911744,0.00078006263],"category_scores_gemma":[0.008319067,0.00029178173,0.0004274179,0.0007515008,0.0014935831,0.0022639278,0.0019070313,0.0012627658,0.00024404006],"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":[0.00014993997,0.000025304542,0.00042078985,0.0001380357,0.000022569258,0.00031324962,0.00022744483,0.18062995,0.014115478,0.7679366,0.0008303986,0.03519031],"study_design_scores_gemma":[0.000011307853,0.000040589515,0.00018284585,0.000032292955,0.000009109168,0.00013196874,0.000035726167,0.6880243,0.0067241346,0.30339482,0.0013928039,0.000020084684],"about_ca_topic_score_codex":0.0003740252,"about_ca_topic_score_gemma":0.00020056096,"teacher_disagreement_score":0.0014469747,"about_ca_system_score_codex":0.0007050696,"about_ca_system_score_gemma":0.00050830934,"threshold_uncertainty_score":0.0076524615},"labels":[],"label_agreement":null},{"id":"W26149291","doi":"10.1016/j.compbiomed.2015.06.008","title":"Data compression using error correcting codes","year":2007,"lang":"en","type":"dissertation","venue":"Computers in Biology and Medicine","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service","keywords":"Turbo code; Algorithm; Lossless compression; Huffman coding; Computer science; Entropy encoding; Variable-length code; Data compression; Fountain code; Block code; Concatenated error correction code; Forward error correction; Tornado code; Theoretical computer science; Decoding methods","score_opus":0.08796919056982982,"score_gpt":0.43588547319833015,"score_spread":0.34791628262850033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W26149291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29601297,0.0029497948,0.6895354,0.0015536213,0.0008156728,0.00042085114,0.001703477,0.003835939,0.0031722933],"genre_scores_gemma":[0.73652303,0.0008981255,0.25760347,0.00021013184,0.00024512253,0.0003434999,0.0016846327,0.00016583559,0.0023260883],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987741,0.0003283535,0.00014283598,0.0002217217,0.00045281375,0.00008011158],"domain_scores_gemma":[0.98929393,0.005583809,0.00081344886,0.0017260904,0.0024844469,0.00009823863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001801383,0.00058307365,0.0005247874,0.0015752871,0.00045283657,0.0009798757,0.0006769871,0.00086956256,0.0014182748],"category_scores_gemma":[0.021322453,0.0002042863,0.00035309372,0.0018153785,0.000614914,0.00096182444,0.0008004626,0.0010850545,0.0006406323],"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":[0.002178543,0.00022818614,0.014962408,0.00027596598,0.00017216887,0.0005921174,0.0002741735,0.08101838,0.024655795,0.0061335927,0.008354049,0.86115456],"study_design_scores_gemma":[0.00012944415,0.0004306749,0.010358529,0.00016310066,0.00010298213,0.0014301335,0.00013378284,0.84803843,0.12087089,0.01303259,0.0052267625,0.00008261536],"about_ca_topic_score_codex":0.0020736272,"about_ca_topic_score_gemma":0.0017704312,"teacher_disagreement_score":0.0020736272,"about_ca_system_score_codex":0.0005791608,"about_ca_system_score_gemma":0.0011105784,"threshold_uncertainty_score":0.00952673},"labels":[],"label_agreement":null},{"id":"W2615426555","doi":"10.1007/11602613_39","title":"Space Efficient Algorithms for Ordered Tree Comparison","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Tree (set theory); Algorithm; Space (punctuation); Computational complexity theory; Theoretical computer science; Time complexity; Tree structure; Mathematics; Binary tree; Combinatorics","score_opus":0.025602120023943638,"score_gpt":0.2801166683802985,"score_spread":0.25451454835635484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615426555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011406416,0.0027090597,0.9675217,0.00044322287,0.00034266812,0.00028992436,0.00088317384,0.005374161,0.011029661],"genre_scores_gemma":[0.062920615,0.0010374573,0.92339706,0.00019736007,0.00022728356,0.00046032033,0.0023023263,0.0010166839,0.008440841],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967443,0.00070637587,0.0003644534,0.0004866047,0.0013308388,0.0003675147],"domain_scores_gemma":[0.99389476,0.0031667855,0.0002882442,0.0016165805,0.00086625555,0.00016733762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017829795,0.001994707,0.002411473,0.003656718,0.0014962758,0.004519305,0.0046816044,0.0017879801,0.021689644],"category_scores_gemma":[0.0105539635,0.0010793472,0.0016588231,0.009520058,0.001167301,0.009697485,0.0037605052,0.0031878506,0.0067463345],"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":[0.00062481523,0.00032379766,0.00040139057,0.00050915993,0.00007968613,0.00007007405,0.00025019853,0.026254166,0.006028578,0.11966479,0.033551592,0.81224185],"study_design_scores_gemma":[0.00044736976,0.00032807773,0.00052240666,0.00015867982,0.00011082179,0.00046558375,0.00027930312,0.29728678,0.012900141,0.6497146,0.037690625,0.00009568517],"about_ca_topic_score_codex":0.002457147,"about_ca_topic_score_gemma":0.00461379,"teacher_disagreement_score":0.021689644,"about_ca_system_score_codex":0.002388827,"about_ca_system_score_gemma":0.0027982153,"threshold_uncertainty_score":0.07255912},"labels":[],"label_agreement":null},{"id":"W2623433906","doi":"10.1145/2000807.2000820","title":"Succinct indexes for strings, binary relations and multilabeled trees","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","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 Waterloo","funders":"","keywords":"String (physics); Set (abstract data type); Constant (computer programming); Binary number; Encoding (memory); Computer science; Rank (graph theory); Type (biology); Mathematics; Theoretical computer science; Combinatorics; Discrete mathematics; Arithmetic","score_opus":0.042778223462201795,"score_gpt":0.2595635280352131,"score_spread":0.21678530457301132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623433906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075742374,0.00030064658,0.9864741,0.0002568209,0.00009120521,0.00013394427,0.000720057,0.0018771203,0.0025717837],"genre_scores_gemma":[0.10051043,0.00080009043,0.8871221,0.00049937953,0.0001503727,0.00054061547,0.002648414,0.0011140322,0.006614547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602747,0.00062033295,0.0006562052,0.0005321706,0.0018687698,0.0002949651],"domain_scores_gemma":[0.99108773,0.0029210844,0.0011915335,0.0033380997,0.0011829417,0.0002787668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00207549,0.0009250278,0.0010432369,0.0019312606,0.000999146,0.004020662,0.0021585145,0.0011102981,0.006111727],"category_scores_gemma":[0.012086086,0.0008041866,0.0013045085,0.004053947,0.0028041094,0.014501384,0.0035628052,0.0028280725,0.0025850935],"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":[0.00053087226,0.00014647024,0.0014314557,0.0006919084,0.000047367037,0.00029106482,0.0009556079,0.032732565,0.030327411,0.7006647,0.012878714,0.21930185],"study_design_scores_gemma":[0.000112588285,0.00039312543,0.00049540645,0.00033688018,0.0000957104,0.00062115013,0.0003257406,0.19561304,0.09882907,0.58335674,0.11962747,0.00019310316],"about_ca_topic_score_codex":0.0010042465,"about_ca_topic_score_gemma":0.0014940033,"teacher_disagreement_score":0.006111727,"about_ca_system_score_codex":0.0019452671,"about_ca_system_score_gemma":0.0019672897,"threshold_uncertainty_score":0.020445824},"labels":[],"label_agreement":null},{"id":"W2732566993","doi":"10.1007/s00453-019-00637-x","title":"Fast Compressed Self-indexes with Deterministic Linear-Time Construction","year":2019,"lang":"en","type":"preprint","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Compressed suffix array; Binary logarithm; Alphabet; Combinatorics; Suffix; Log-log plot; Time complexity; Sigma; Mathematics; Suffix array; Algorithm; Omega; Discrete mathematics; Suffix tree; Arithmetic; Physics","score_opus":0.007542539180165174,"score_gpt":0.22188954415257112,"score_spread":0.21434700497240594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732566993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04698035,0.0010156026,0.9284277,0.0010513461,0.00043989203,0.0002109997,0.001222519,0.00982369,0.010827904],"genre_scores_gemma":[0.37962124,0.00042572658,0.6026663,0.00046548742,0.0003950356,0.0005351987,0.002983242,0.0017858701,0.011121928],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959266,0.0007074785,0.00029626247,0.00059982255,0.0019905542,0.00047935674],"domain_scores_gemma":[0.98997784,0.0034698795,0.0003931688,0.004870722,0.0010216244,0.0002666409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015841745,0.000953782,0.0017122631,0.0018655794,0.00170161,0.0035191635,0.0023505543,0.0017480414,0.008998745],"category_scores_gemma":[0.01170055,0.0008095136,0.001027455,0.0040093926,0.0018198738,0.007209129,0.0061037233,0.0021724487,0.0032347746],"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":[0.0025118862,0.00059942383,0.0027113226,0.00068756466,0.00015728053,0.00042001434,0.0007048398,0.056468714,0.036808863,0.2742059,0.047614135,0.57711],"study_design_scores_gemma":[0.0004122015,0.0002829052,0.0007356364,0.00008057974,0.0001153546,0.0006297652,0.0001942958,0.51368564,0.06659883,0.39512718,0.022034818,0.000102814],"about_ca_topic_score_codex":0.0009932909,"about_ca_topic_score_gemma":0.0018200176,"teacher_disagreement_score":0.008998745,"about_ca_system_score_codex":0.0017079001,"about_ca_system_score_gemma":0.0027569158,"threshold_uncertainty_score":0.030103803},"labels":[],"label_agreement":null},{"id":"W2734809496","doi":"10.3934/medsci.2017.3.261","title":"The Role of The Prefix Array in Sequence Analysis: A Survey","year":2017,"lang":"en","type":"article","venue":"AIMS Medical Science","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Prefix; Sequence (biology); Computer science; Hamming distance; Algorithm; Array data structure; Extension (predicate logic); Theoretical computer science; Mathematics; Combinatorics; Biology; Genetics","score_opus":0.02777259007136487,"score_gpt":0.31615179910497054,"score_spread":0.2883792090336057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734809496","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0094620995,0.4722068,0.49195048,0.0036937175,0.0009986756,0.00010890752,0.00040740834,0.00088072487,0.020291083],"genre_scores_gemma":[0.063910924,0.6049606,0.31909126,0.0016312023,0.0032745271,0.00021641629,0.0013301076,0.00047978168,0.0051052165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977471,0.0005510789,0.00024479924,0.0005481447,0.0008111064,0.000097811004],"domain_scores_gemma":[0.9937355,0.0048354506,0.00020189276,0.00051932794,0.00057911495,0.00012876236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022385346,0.0010493412,0.0014197289,0.0049722213,0.00085668603,0.0036345015,0.001849468,0.0018557734,0.0029483512],"category_scores_gemma":[0.007904079,0.0009458273,0.00096922956,0.010853761,0.0027684711,0.00892059,0.0016394352,0.0028050747,0.0024853651],"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":[0.000073831674,0.0000777969,0.0017274085,0.0028124333,0.00006654499,0.00013570441,0.0003350111,0.0073714782,0.0021887047,0.17119545,0.011093817,0.80292183],"study_design_scores_gemma":[0.000027555656,0.0003200424,0.002178749,0.0016896515,0.00009514324,0.002037823,0.00046704835,0.05019935,0.00688028,0.47769004,0.45827287,0.00014137363],"about_ca_topic_score_codex":0.0015177751,"about_ca_topic_score_gemma":0.0007257385,"teacher_disagreement_score":0.0049722213,"about_ca_system_score_codex":0.0014642536,"about_ca_system_score_gemma":0.0014380703,"threshold_uncertainty_score":0.011838675},"labels":[],"label_agreement":null},{"id":"W2739962508","doi":"10.24963/ijcai.2017/611","title":"Lossy Compression of Pattern Databases Using Acyclic Random Hypergraphs","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Regina","funders":"","keywords":"Heuristics; Computer science; Heuristic; Bloom filter; Compression (physics); Data compression; Directed acyclic graph; Lossy compression; Algorithm; Database; Filter (signal processing); Theoretical computer science; Artificial intelligence","score_opus":0.06606738627133817,"score_gpt":0.3277021385232198,"score_spread":0.2616347522518816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739962508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27982497,0.0022566575,0.7009817,0.0006379519,0.00013220782,0.0002601939,0.0019778807,0.0087042935,0.0052241157],"genre_scores_gemma":[0.71015805,0.0009477386,0.28173825,0.00028455473,0.0000419353,0.00021025116,0.0032854988,0.00032679323,0.0030069763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992386,0.00015484539,0.00008539166,0.00012279711,0.0003222411,0.00007610713],"domain_scores_gemma":[0.99724895,0.0009973135,0.00020224942,0.0011046688,0.0003950693,0.000051758398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005450371,0.00043001134,0.0004889227,0.0018717286,0.0003524737,0.00070029055,0.0010447776,0.00042445265,0.0015816385],"category_scores_gemma":[0.003762535,0.00020826541,0.00027576167,0.0035793143,0.00041478523,0.002112417,0.0008076971,0.0003902248,0.00045471042],"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":[0.0010192881,0.00017202768,0.0037367481,0.00033911123,0.00009884542,0.0008294407,0.000369171,0.09704884,0.05994758,0.021503946,0.012385716,0.8025493],"study_design_scores_gemma":[0.00012733693,0.00034086948,0.0030180346,0.00007593317,0.000068763715,0.0013947765,0.00034423277,0.7554869,0.19006312,0.031004354,0.018017614,0.000058080506],"about_ca_topic_score_codex":0.0020382612,"about_ca_topic_score_gemma":0.002160957,"teacher_disagreement_score":0.0020382612,"about_ca_system_score_codex":0.0006942195,"about_ca_system_score_gemma":0.0006404314,"threshold_uncertainty_score":0.0052911043},"labels":[],"label_agreement":null},{"id":"W2740058122","doi":"10.1109/cwit.2017.7994820","title":"Almost minimum-redundancy construction of balanced codes using limited-precision integers","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Redundancy (engineering); Decoding methods; Encoding (memory); ENCODE; Computer science; Algorithm; Theoretical computer science; Computational complexity theory; Block code; Artificial intelligence","score_opus":0.034362107925305134,"score_gpt":0.30145759232129504,"score_spread":0.2670954843959899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740058122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13030927,0.0004935418,0.8576096,0.00033264564,0.00010428047,0.00008702288,0.00023907446,0.0004846332,0.010339972],"genre_scores_gemma":[0.58551794,0.00064361864,0.40589398,0.00022405008,0.00006762923,0.00019697988,0.00060263486,0.00015579538,0.006697354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99938416,0.0001304391,0.00004337788,0.00007418409,0.00027323345,0.00009460669],"domain_scores_gemma":[0.9991911,0.00032610464,0.00012463816,0.00018883515,0.000119227865,0.000050151804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044393705,0.0004882961,0.0005505282,0.00073762535,0.0005107723,0.0007392224,0.0006251152,0.0004507092,0.0016045773],"category_scores_gemma":[0.0023085647,0.00028979813,0.00038313412,0.0008797072,0.0006368097,0.0016009384,0.0012812885,0.00073558657,0.0006224194],"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":[0.00061693974,0.00010567114,0.0008063511,0.00024989608,0.0000464541,0.00045583784,0.00028390053,0.07925657,0.08634894,0.64368445,0.0036774362,0.18446757],"study_design_scores_gemma":[0.0002062081,0.0005069599,0.0005094259,0.00014624925,0.00005314628,0.00085404154,0.000108030225,0.43556726,0.11199838,0.4273346,0.022615055,0.00010065943],"about_ca_topic_score_codex":0.0005100505,"about_ca_topic_score_gemma":0.00070782006,"teacher_disagreement_score":0.0016045773,"about_ca_system_score_codex":0.0005435181,"about_ca_system_score_gemma":0.0009006719,"threshold_uncertainty_score":0.005367875},"labels":[],"label_agreement":null},{"id":"W2753236625","doi":"10.4230/lipics.cpm.2017.5","title":"Path Queries on Functions","year":2017,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Combinatorics; Path (computing); Element (criminal law); Range (aeronautics); Function (biology); Mathematics; Domain (mathematical analysis); Binary logarithm; Discrete mathematics; Computer science; Mathematical analysis","score_opus":0.020877183787311186,"score_gpt":0.273045631051949,"score_spread":0.25216844726463783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753236625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27656054,0.004131348,0.65850115,0.00472248,0.00033452574,0.0006515791,0.0171121,0.014676584,0.023309665],"genre_scores_gemma":[0.75086766,0.0013621367,0.21885228,0.0013078357,0.0003195717,0.0008070139,0.011723801,0.0012457184,0.013513909],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99722433,0.0006735691,0.00034439375,0.00062413054,0.0007000484,0.00043356436],"domain_scores_gemma":[0.98914856,0.0073465216,0.00046153666,0.0021397506,0.00069600425,0.00020753607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019567953,0.0010214789,0.001402465,0.0016174952,0.0010262027,0.0022753251,0.0013087603,0.0016891693,0.011858349],"category_scores_gemma":[0.014792647,0.00042009357,0.0007013999,0.0037862652,0.0012792648,0.010703736,0.0031715853,0.0013730824,0.0017909254],"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":[0.0038690816,0.00031743295,0.006436108,0.0011265766,0.00013385389,0.0006402184,0.001365996,0.044886857,0.02054268,0.2978283,0.07670498,0.5461479],"study_design_scores_gemma":[0.00048294986,0.0006966281,0.0021857761,0.0002510402,0.0000913921,0.0012522939,0.0011383268,0.19677277,0.036564138,0.66378117,0.096655,0.00012847818],"about_ca_topic_score_codex":0.0019238648,"about_ca_topic_score_gemma":0.0016590789,"teacher_disagreement_score":0.011858349,"about_ca_system_score_codex":0.0022583124,"about_ca_system_score_gemma":0.0010133388,"threshold_uncertainty_score":0.03967011},"labels":[],"label_agreement":null},{"id":"W2758508602","doi":"10.1016/j.ipl.2017.09.011","title":"Stream VByte : Faster byte-oriented integer compression","year":2017,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"National Research Council Canada","keywords":"Byte; Computer science; SIMD; Data compression; Parallel computing; Data stream; Decoding methods; Integer (computer science); Cache; Compression (physics); Algorithm; Computer hardware; Programming language","score_opus":0.01176430296315444,"score_gpt":0.24859861746291584,"score_spread":0.2368343144997614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758508602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05266717,0.0051403,0.80341756,0.0010531913,0.0023154712,0.0005026883,0.0042511467,0.09495306,0.035699412],"genre_scores_gemma":[0.23162585,0.0017184325,0.71503925,0.0011384106,0.0006166769,0.00044878063,0.007938086,0.006404495,0.03507003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934286,0.00008011998,0.000052330284,0.00008292058,0.00035548926,0.00008625296],"domain_scores_gemma":[0.99902546,0.00032606922,0.00004605965,0.00030426023,0.00023329756,0.00006477215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007262747,0.0011430559,0.0008561021,0.0020001458,0.0004244375,0.0020250913,0.0013171842,0.00065605046,0.026645346],"category_scores_gemma":[0.002858659,0.00040124878,0.000446249,0.0023292436,0.00043907235,0.002220825,0.0016769966,0.0010814185,0.00656005],"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":[0.0021536013,0.00020894929,0.0008846833,0.0003446069,0.00008739533,0.00020444504,0.00014303564,0.0058165626,0.03734106,0.018884158,0.068927445,0.865004],"study_design_scores_gemma":[0.0011663184,0.00067360123,0.0016209949,0.00028408066,0.00012827847,0.0011073835,0.00022250219,0.46695524,0.33689803,0.03538906,0.15540095,0.00015368332],"about_ca_topic_score_codex":0.0020511972,"about_ca_topic_score_gemma":0.0028350304,"teacher_disagreement_score":0.026645346,"about_ca_system_score_codex":0.00063623243,"about_ca_system_score_gemma":0.0009817166,"threshold_uncertainty_score":0.089137495},"labels":[],"label_agreement":null},{"id":"W2760465763","doi":"","title":"Pattern Discovery in DNA Sequences","year":2012,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computational biology; Evolutionary biology; Biology; Genetics; Data science; Computer science","score_opus":0.0037998672769348736,"score_gpt":0.1584252505442768,"score_spread":0.15462538326734193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760465763","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011957556,0.0062681194,0.9661115,0.0027908725,0.0006868015,0.0006005519,0.0038126123,0.0033714103,0.004400636],"genre_scores_gemma":[0.11328144,0.006155271,0.86246675,0.0018832156,0.0006987715,0.0013918789,0.009504547,0.00031710873,0.004300926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98912024,0.003226493,0.0011653637,0.003073575,0.003128149,0.00028633475],"domain_scores_gemma":[0.97580963,0.017144358,0.0019902403,0.0027927537,0.001964737,0.00029826752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060229483,0.0012787575,0.0022166502,0.008112908,0.0010786231,0.004052611,0.0025053036,0.002217858,0.0041611847],"category_scores_gemma":[0.031863563,0.0009521133,0.0028441132,0.006799577,0.0024965876,0.0050085825,0.0031037915,0.002933031,0.002943746],"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":[0.00038420636,0.0002661666,0.013481261,0.0047045383,0.00072950625,0.0012382903,0.0008622248,0.036330666,0.011749002,0.16149707,0.026120238,0.74263674],"study_design_scores_gemma":[0.00011952815,0.0002995831,0.0048372634,0.00095563906,0.00019518827,0.002441001,0.00046777664,0.4079416,0.014038939,0.48264742,0.08591774,0.00013830642],"about_ca_topic_score_codex":0.0012011359,"about_ca_topic_score_gemma":0.0009233007,"teacher_disagreement_score":0.008112908,"about_ca_system_score_codex":0.001274262,"about_ca_system_score_gemma":0.0020914744,"threshold_uncertainty_score":0.03185278},"labels":[],"label_agreement":null},{"id":"W2762796277","doi":"10.1016/j.jda.2017.10.002","title":"Necklaces and Lyndon words in colexicographic and binary reflected Gray code order","year":2017,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science, ICT and Future Planning","keywords":"De Bruijn sequence; Gray code; Binary number; Combinatorics; Order (exchange); Code (set theory); Sequence (biology); Gray (unit); Mathematics; Computer science; Algorithm; Arithmetic; Chemistry; Set (abstract data type)","score_opus":0.01710391269247407,"score_gpt":0.2983183978350761,"score_spread":0.281214485142602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762796277","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70594865,0.0010274552,0.22338867,0.0011211851,0.0003766524,0.00010109497,0.00037361187,0.00057188544,0.06709068],"genre_scores_gemma":[0.9229555,0.00044916075,0.03469777,0.00046051905,0.00014129224,0.00009073534,0.00029313756,0.00026103493,0.040650852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999446,0.000112543916,0.000046987327,0.000081070604,0.0001886986,0.00012470776],"domain_scores_gemma":[0.99832326,0.0006628737,0.0002478307,0.00026580368,0.00031469113,0.00018564177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049097365,0.00043540326,0.0005238129,0.0018523054,0.00093027484,0.0019610978,0.00063122774,0.0010830902,0.0078360895],"category_scores_gemma":[0.005267479,0.00030696712,0.00038929255,0.0013171486,0.0020241558,0.0022871515,0.001445676,0.001328934,0.0010724289],"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":[0.00019280883,0.000030383218,0.0005964128,0.000035435776,0.0000047090653,0.00021642653,0.00034007916,0.0043296167,0.0025528227,0.9704549,0.0017473141,0.019499047],"study_design_scores_gemma":[0.00003703951,0.00009098984,0.00059139857,0.00005835096,0.000013272197,0.00037612772,0.00029492495,0.04887199,0.004678952,0.9354814,0.009452533,0.000052964184],"about_ca_topic_score_codex":0.0025297466,"about_ca_topic_score_gemma":0.002817922,"teacher_disagreement_score":0.0078360895,"about_ca_system_score_codex":0.0012634902,"about_ca_system_score_gemma":0.0009373294,"threshold_uncertainty_score":0.026214361},"labels":[],"label_agreement":null},{"id":"W2764077472","doi":"10.3842/sigma.2018.060","title":"(2+)-Replication and the Baby Monster","year":2018,"lang":"en","type":"article","venue":"Symmetry Integrability and Geometry Methods and Applications","topic":"Algorithms and Data Compression","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":"Concordia University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Ministério da Ciência, Tecnologia e Ensino Superior","keywords":"Monster; Replication (statistics); Mathematics; Art; Combinatorics; Virology; Medicine; Art history","score_opus":0.020631313116809647,"score_gpt":0.3482385327130899,"score_spread":0.32760721959628025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2764077472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5174273,0.0012520957,0.3456851,0.0013704092,0.000454854,0.00008377946,0.00018505252,0.0005732318,0.1329682],"genre_scores_gemma":[0.9446487,0.0002826686,0.026751885,0.00025818814,0.00014988854,0.00004109069,0.000062595806,0.00015427766,0.02765065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995079,0.00011824436,0.000022597007,0.0000913983,0.00015214272,0.00010769291],"domain_scores_gemma":[0.9991948,0.00016605388,0.00010454347,0.00036158916,0.000100622885,0.00007238393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009766212,0.000348691,0.00035691092,0.0004735547,0.00070394756,0.001250771,0.0006182174,0.0005268084,0.005690853],"category_scores_gemma":[0.0023428893,0.00019174459,0.00045525274,0.00036741595,0.0023166742,0.0030058702,0.0016617744,0.000946213,0.00079269544],"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":[0.00002449279,0.000006107527,0.000112737456,0.000011695309,0.0000017898446,0.00007031246,0.00012792785,0.00083776726,0.001956568,0.99144286,0.00035783584,0.0050498564],"study_design_scores_gemma":[0.00001633495,0.00006398576,0.00027901676,0.000016510108,0.0000056932827,0.00042224882,0.00012376973,0.01288586,0.008745141,0.9644661,0.012951107,0.00002409234],"about_ca_topic_score_codex":0.00048162608,"about_ca_topic_score_gemma":0.00029304912,"teacher_disagreement_score":0.005690853,"about_ca_system_score_codex":0.0005870851,"about_ca_system_score_gemma":0.00050945557,"threshold_uncertainty_score":0.019037783},"labels":[],"label_agreement":null},{"id":"W2766136522","doi":"10.1016/j.jda.2018.08.001","title":"Lyndon array construction during Burrows–Wheeler inversion","year":2018,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Inversion (geology); Representation (politics); Stack (abstract data type); Time complexity; Inverse; Parenthesis; Space (punctuation); String (physics)","score_opus":0.009784970311766398,"score_gpt":0.24248935677992522,"score_spread":0.23270438646815883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766136522","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020380685,0.00021678313,0.96367645,0.00028758045,0.00029087742,0.00008796676,0.00016237004,0.002904972,0.011992419],"genre_scores_gemma":[0.22792365,0.00021567802,0.75185454,0.00036773892,0.00015976433,0.00024355296,0.0007302671,0.0015773507,0.016927399],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982882,0.00041807463,0.00012760653,0.00025822278,0.00062310917,0.00028474294],"domain_scores_gemma":[0.99797946,0.00050929206,0.000086590495,0.0007858853,0.00055284816,0.00008587725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012674073,0.00078604853,0.0010769202,0.0011674945,0.0012584744,0.0019010721,0.0015633501,0.0009952153,0.0131495325],"category_scores_gemma":[0.006420679,0.0005729309,0.00071811734,0.0016497971,0.0010440283,0.0027610431,0.0029683753,0.0021752538,0.006345012],"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":[0.0009528012,0.00016661039,0.0013454654,0.00026675427,0.00005853787,0.00036061692,0.000651414,0.015148065,0.05656088,0.2839632,0.023385268,0.6171404],"study_design_scores_gemma":[0.0002657143,0.0004865925,0.0011024355,0.00019163101,0.0000945135,0.0009131914,0.00061662437,0.21042243,0.22613905,0.4263635,0.13318768,0.00021662247],"about_ca_topic_score_codex":0.0011696696,"about_ca_topic_score_gemma":0.002453985,"teacher_disagreement_score":0.0131495325,"about_ca_system_score_codex":0.0006810319,"about_ca_system_score_gemma":0.0017860781,"threshold_uncertainty_score":0.04398954},"labels":[],"label_agreement":null},{"id":"W2771233158","doi":"10.4018/978-1-59904-845-1.ch080","title":"A New Algorithm for Subset Matching Problem Based on Set-String Transformation","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"String searching algorithm; Pattern matching; Approximate string matching; String (physics); Matching (statistics); Algorithm; Set (abstract data type); Mathematics; Context (archaeology); Computer science; Tree (set theory); Discrete mathematics; Combinatorics; Programming language","score_opus":0.019174227011840593,"score_gpt":0.2503008154356428,"score_spread":0.2311265884238022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771233158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005474553,0.0001882724,0.9879952,0.00023171533,0.00012389681,0.00022089311,0.00019560063,0.002566285,0.003003539],"genre_scores_gemma":[0.032769762,0.00015720418,0.96133584,0.0001931105,0.00007915646,0.00045015386,0.0011396736,0.00042850833,0.0034465878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983255,0.00025047443,0.00019811362,0.00055575406,0.00049113063,0.00017887681],"domain_scores_gemma":[0.9991817,0.0002530924,0.000054469656,0.00022990281,0.00022724387,0.000053616182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083495857,0.0013718505,0.0023024168,0.002515545,0.0014241217,0.0018271992,0.002885092,0.0018077528,0.012922321],"category_scores_gemma":[0.0028776925,0.00059146335,0.0020030388,0.0035551216,0.00078416476,0.0051521487,0.0033405183,0.0021639192,0.003974157],"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":[0.0004706586,0.00034980645,0.0010997532,0.00042220834,0.000101435005,0.00020821727,0.0002576808,0.03718538,0.017710121,0.07239195,0.024907405,0.84489536],"study_design_scores_gemma":[0.00033040208,0.000354297,0.00057718845,0.00005969805,0.00009876272,0.0009683331,0.00020720762,0.76651275,0.02056122,0.16225992,0.047996767,0.00007342727],"about_ca_topic_score_codex":0.0014938548,"about_ca_topic_score_gemma":0.0014406157,"teacher_disagreement_score":0.012922321,"about_ca_system_score_codex":0.0009331462,"about_ca_system_score_gemma":0.0016634688,"threshold_uncertainty_score":0.04322946},"labels":[],"label_agreement":null},{"id":"W2775637391","doi":"10.24870/cjb.2017-a221","title":"Pipeline to upgrade the genome annotations","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Biotechnology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Upgrade; Pipeline (software); Genome; Computer science; Computational biology; Biology; Programming language; Genetics; Operating system; Gene","score_opus":0.017264403361024364,"score_gpt":0.24983421094878971,"score_spread":0.23256980758776535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775637391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025499329,0.0009748131,0.6391546,0.0012380747,0.0007887594,0.0015048054,0.0595514,0.25719813,0.014090106],"genre_scores_gemma":[0.06770861,0.00085433084,0.6385906,0.0008576452,0.00022461155,0.0014421606,0.24921176,0.017902382,0.023207935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876606,0.0001316313,0.00011530729,0.0003878531,0.00043590405,0.00016327846],"domain_scores_gemma":[0.99740785,0.00044065918,0.00013785047,0.00076768483,0.0011035281,0.0001424386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018927834,0.0016706119,0.0009985056,0.0034805257,0.0012572088,0.0018012646,0.0016483268,0.0008349589,0.018344525],"category_scores_gemma":[0.00486388,0.0009010651,0.0014966562,0.0029284176,0.0004266784,0.0024081464,0.002808215,0.0021474946,0.020209363],"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":[0.0019579548,0.00026898875,0.004476135,0.0012566076,0.00017082822,0.0009770496,0.0010267985,0.008533021,0.09353532,0.0064362916,0.27975208,0.6016089],"study_design_scores_gemma":[0.000304222,0.00038801864,0.014192877,0.00025140107,0.00028601504,0.0010278828,0.00039433804,0.09787323,0.11443227,0.017465228,0.75301605,0.00036845705],"about_ca_topic_score_codex":0.007410358,"about_ca_topic_score_gemma":0.004215596,"teacher_disagreement_score":0.018344525,"about_ca_system_score_codex":0.0010634282,"about_ca_system_score_gemma":0.00199926,"threshold_uncertainty_score":0.061368525},"labels":[],"label_agreement":null},{"id":"W2775661960","doi":"10.1109/ecai.2017.8166387","title":"FPGA systolic array GZIP compressor","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"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; Data compression; Field-programmable gate array; Compression ratio; Throughput; Software; Computer hardware; Embedded system; Operating system; Algorithm; Wireless","score_opus":0.02813280717871854,"score_gpt":0.27917331465194645,"score_spread":0.2510405074732279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775661960","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15646079,0.0016749337,0.6844965,0.0004625273,0.0005488077,0.0005593763,0.0027133462,0.11272214,0.04036161],"genre_scores_gemma":[0.6304209,0.0009904957,0.32371986,0.0005690125,0.00018714642,0.000457217,0.0048972415,0.0025239126,0.036234215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997993,0.000018629169,0.000012654535,0.00002981891,0.00010220816,0.000037410675],"domain_scores_gemma":[0.999824,0.00004542723,0.00001666872,0.000030050975,0.00007289727,0.000010966562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014049553,0.0006960257,0.00028293414,0.0008960095,0.00028366016,0.0004993506,0.0008094064,0.0002530239,0.01793814],"category_scores_gemma":[0.0005060481,0.00017388751,0.00019349635,0.0007234721,0.00022290443,0.00057044264,0.00031207624,0.00033474038,0.0031959203],"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":[0.0019957519,0.00015426188,0.002086624,0.00059923023,0.00008047115,0.0007161752,0.0002408495,0.017593892,0.12726742,0.0077404147,0.06477964,0.77674514],"study_design_scores_gemma":[0.00045547163,0.0013017755,0.004279505,0.00012794067,0.00011688971,0.0013252865,0.00023777327,0.27595943,0.5293826,0.003480451,0.18319802,0.00013493422],"about_ca_topic_score_codex":0.0016557841,"about_ca_topic_score_gemma":0.0021290488,"teacher_disagreement_score":0.01793814,"about_ca_system_score_codex":0.0004445043,"about_ca_system_score_gemma":0.00039960278,"threshold_uncertainty_score":0.060009062},"labels":[],"label_agreement":null},{"id":"W2777684402","doi":"10.1111/1755-0998.12746","title":"Reducing cryptic relatedness in genomic data sets via a central node exclusion algorithm","year":2017,"lang":"en","type":"article","venue":"Molecular Ecology Resources","topic":"Algorithms and Data Compression","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":"BIO (Canada); University of Guelph","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Empresa Brasileira de Pesquisa Agropecuária; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Biology; Computational biology; Node (physics); Genetics; Algorithm; Evolutionary biology; Computer science","score_opus":0.01755604893483978,"score_gpt":0.2659630247171758,"score_spread":0.24840697578233603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777684402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0452912,0.0002358669,0.95241994,0.00016811247,0.000048842638,0.0002041663,0.00020591599,0.000975069,0.00045092625],"genre_scores_gemma":[0.14465277,0.000118519,0.8515253,0.00017399213,0.0000783409,0.0005943005,0.0014822246,0.00021060703,0.0011639674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960671,0.0018352449,0.0003182044,0.0008596118,0.0006404092,0.0002794727],"domain_scores_gemma":[0.9881787,0.007842504,0.00067938893,0.0012792889,0.0016804922,0.000339699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008143663,0.0009917477,0.0015749076,0.0025016207,0.0014761053,0.0012445889,0.002219909,0.0011982026,0.0017048417],"category_scores_gemma":[0.021387154,0.0005577517,0.0015813066,0.002116804,0.0010385158,0.0013885457,0.002192856,0.0017464693,0.0008861354],"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":[0.001457067,0.00069525297,0.03967938,0.00042417058,0.0011849593,0.0007666701,0.0017474034,0.23600143,0.029863767,0.020617288,0.0077413735,0.6598212],"study_design_scores_gemma":[0.00014554244,0.00023394868,0.004499292,0.000046848003,0.00015471708,0.00028066456,0.00019393122,0.9660303,0.0060947887,0.017854614,0.004428973,0.000036427547],"about_ca_topic_score_codex":0.00465862,"about_ca_topic_score_gemma":0.007547234,"teacher_disagreement_score":0.008143663,"about_ca_system_score_codex":0.00058763125,"about_ca_system_score_gemma":0.002071979,"threshold_uncertainty_score":0.04306835},"labels":[],"label_agreement":null},{"id":"W2778964950","doi":"10.48550/arxiv.1712.07431","title":"Text Indexing and Searching in Sublinear Time","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Combinatorics; Binary logarithm; Log-log plot; Sublinear function; Alphabet; Search engine indexing; Space (punctuation); Mathematics; Physics; Computer science","score_opus":0.07549430422908276,"score_gpt":0.20563749298977446,"score_spread":0.1301431887606917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778964950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035302915,0.0068562273,0.8212081,0.007432749,0.0014325494,0.0009761889,0.009630698,0.05967926,0.057481315],"genre_scores_gemma":[0.19399677,0.0020601978,0.7297742,0.0024009622,0.0011071807,0.0013360282,0.016786996,0.0048598163,0.04767793],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99182105,0.0007955711,0.0007355542,0.001952878,0.003528284,0.0011667646],"domain_scores_gemma":[0.9897138,0.0035904858,0.0005940978,0.004698007,0.0010593863,0.00034436575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016316242,0.0025984973,0.0023199783,0.0030768088,0.0014564479,0.005617679,0.005109304,0.002399424,0.03641501],"category_scores_gemma":[0.013787686,0.0010977001,0.0022365407,0.008400056,0.0018403946,0.015559336,0.0052274526,0.0026907723,0.027380293],"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":[0.0016387231,0.00045677266,0.0018465379,0.0012092132,0.0002139752,0.00027508338,0.00044003283,0.01484917,0.025769314,0.069689214,0.14554526,0.7380668],"study_design_scores_gemma":[0.0009103778,0.0003821641,0.0018896234,0.00023165808,0.00033906233,0.0014650008,0.00046566283,0.36109698,0.045700554,0.45928478,0.12805937,0.00017466037],"about_ca_topic_score_codex":0.0051637026,"about_ca_topic_score_gemma":0.011069033,"teacher_disagreement_score":0.03641501,"about_ca_system_score_codex":0.0039359736,"about_ca_system_score_gemma":0.0054050516,"threshold_uncertainty_score":0.12182033},"labels":[],"label_agreement":null},{"id":"W2780044948","doi":"10.1109/eisic.2017.19","title":"Text Mining in Unclean, Noisy or Scrambled Datasets for Digital Forensics Analytics","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Punctuation; Preprocessor; String (physics); Digital forensics; Suffix; Mobile device; Data mining; Analytics; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Computer security","score_opus":0.05723131250928121,"score_gpt":0.3220233973309604,"score_spread":0.2647920848216792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780044948","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32548812,0.005320063,0.5845717,0.004232138,0.0007398954,0.0013295092,0.053829197,0.018806102,0.00568325],"genre_scores_gemma":[0.40144128,0.0016384829,0.5328238,0.00049177575,0.00056465156,0.0009070843,0.05896231,0.0005475797,0.002623028],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976942,0.00045627018,0.0004284741,0.0006039175,0.00067134434,0.00014572065],"domain_scores_gemma":[0.9920406,0.0037992727,0.001271267,0.0014112913,0.0012685262,0.0002090139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023486677,0.0013583299,0.0011446265,0.011443141,0.0014433449,0.002233323,0.0016322084,0.0020349468,0.0013437433],"category_scores_gemma":[0.012691791,0.0003465044,0.0011462802,0.008131248,0.0007510043,0.00391572,0.0015972803,0.0014688441,0.0030197103],"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":[0.0014157292,0.0012131613,0.031942036,0.0023103585,0.0004305659,0.00387063,0.0015794428,0.028370216,0.084358305,0.008418539,0.047511887,0.7885791],"study_design_scores_gemma":[0.00018715565,0.0007305016,0.04022482,0.000728517,0.0004960293,0.0037391349,0.006506724,0.6684401,0.12907076,0.06790066,0.081755675,0.00021985234],"about_ca_topic_score_codex":0.0009872547,"about_ca_topic_score_gemma":0.0016761394,"teacher_disagreement_score":0.011443141,"about_ca_system_score_codex":0.0005460235,"about_ca_system_score_gemma":0.0010954154,"threshold_uncertainty_score":0.0124210715},"labels":[],"label_agreement":null},{"id":"W2781719159","doi":"","title":"Algorithms to Reconstruct the Target Dna from Its Spectrum Connected at Some Level","year":2017,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"Algorithms and Data Compression","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":"University of Saskatchewan","funders":"","keywords":"Substring; DNA; Algorithm; Fragment (logic); Set (abstract data type); Restriction enzyme; Combinatorics; String (physics); Spectrum (functional analysis); Class (philosophy); Mathematics; Computer science; Genetics; Biology; Physics; Artificial intelligence","score_opus":0.04539615546157806,"score_gpt":0.2652025819373759,"score_spread":0.21980642647579784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781719159","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02364038,0.0004374804,0.96996135,0.00038201432,0.000048311722,0.00016645773,0.00029936744,0.0016427942,0.0034218552],"genre_scores_gemma":[0.07790546,0.00040222675,0.9149473,0.00023846628,0.00004893157,0.0003061144,0.0019994061,0.00026139367,0.0038908191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999255,0.00013418516,0.000082764054,0.00025657687,0.00017690563,0.00009458048],"domain_scores_gemma":[0.9974504,0.0013886002,0.00023735697,0.0006649062,0.00018864538,0.00007008067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090916164,0.0011021837,0.000874319,0.0014746105,0.00075051637,0.0016108627,0.0020324218,0.0020651773,0.0051144375],"category_scores_gemma":[0.0040484276,0.0006132857,0.0013897741,0.0015262652,0.0009995712,0.0031802258,0.0020065573,0.0021116913,0.0023096753],"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":[0.00052713434,0.0003899846,0.0028704756,0.00086962874,0.00018186751,0.00026025667,0.00059607386,0.11629469,0.028084805,0.06937141,0.013594347,0.7669593],"study_design_scores_gemma":[0.00015772645,0.00024223697,0.0015215614,0.00012483104,0.00011298731,0.001203412,0.00050821697,0.7453321,0.030324675,0.20326684,0.017144205,0.00006124014],"about_ca_topic_score_codex":0.0008870355,"about_ca_topic_score_gemma":0.0017030111,"teacher_disagreement_score":0.0051144375,"about_ca_system_score_codex":0.00085408223,"about_ca_system_score_gemma":0.0012946202,"threshold_uncertainty_score":0.017109513},"labels":[],"label_agreement":null},{"id":"W2783084218","doi":"10.4230/lipics.isaac.2017.30","title":"Succinct Color Searching in One Dimension","year":2017,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Combinatorics; Dimension (graph theory); Set (abstract data type); Omega; Interval (graph theory); Rank (graph theory); Space (punctuation); Integer (computer science); Mathematics; Binary logarithm; Discrete mathematics; Point (geometry); Computer science; Physics; Geometry","score_opus":0.03602457941706265,"score_gpt":0.2935508951595492,"score_spread":0.2575263157424865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783084218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16852392,0.0022200674,0.80576134,0.0024034842,0.00025748208,0.00031149542,0.0049273893,0.008072068,0.007522829],"genre_scores_gemma":[0.5184683,0.0008937485,0.46569967,0.0010834486,0.00016070047,0.00053067884,0.0056693126,0.0007015072,0.0067926142],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940293,0.0012705905,0.0007863526,0.0010984212,0.0022095446,0.00060581317],"domain_scores_gemma":[0.98076254,0.0066531375,0.001811607,0.008824426,0.0015360926,0.0004122439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026338527,0.00088491704,0.0019805704,0.0013630171,0.0012067737,0.0039610527,0.003551537,0.0015457651,0.006440796],"category_scores_gemma":[0.016288666,0.0008635461,0.0009607135,0.0046322853,0.0019584564,0.014241291,0.0041159997,0.0024436612,0.0017825967],"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":[0.0034182863,0.00072594505,0.008839749,0.0014120457,0.00018953941,0.00047000163,0.0014819211,0.20833807,0.024048185,0.30465677,0.027257336,0.41916212],"study_design_scores_gemma":[0.00038320056,0.00045969072,0.0011567936,0.00021181162,0.00008154268,0.0005720059,0.000530931,0.5896574,0.030585537,0.35056612,0.025629943,0.00016501144],"about_ca_topic_score_codex":0.0027413915,"about_ca_topic_score_gemma":0.0030704893,"teacher_disagreement_score":0.006440796,"about_ca_system_score_codex":0.0025947776,"about_ca_system_score_gemma":0.0026168784,"threshold_uncertainty_score":0.021546602},"labels":[],"label_agreement":null},{"id":"W2783349915","doi":"10.1109/cyberc.2017.26","title":"Searching BWT against Pattern Matching Machine to Find Multiple String Matches","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Winnipeg","funders":"","keywords":"String searching algorithm; Computer science; Matching (statistics); Pattern matching; String (physics); Approximate string matching; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.03053548125933459,"score_gpt":0.2855129213988308,"score_spread":0.2549774401394962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783349915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048235744,0.0006738878,0.9433673,0.00023122317,0.00011661045,0.00014455398,0.00032960597,0.0047228537,0.0021782187],"genre_scores_gemma":[0.19573377,0.00026574385,0.79922616,0.00020309152,0.00008047473,0.0002508386,0.001226848,0.0004306724,0.0025823887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739265,0.0003614146,0.00036435341,0.00078815746,0.00087814033,0.00021529527],"domain_scores_gemma":[0.99650985,0.0015370025,0.0004280263,0.00089885975,0.0005364794,0.000089801535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012566802,0.00088220276,0.0015768261,0.0027048127,0.0009732553,0.0010525736,0.002229516,0.0013739531,0.0040252223],"category_scores_gemma":[0.008000208,0.0004189644,0.0008481588,0.004402077,0.00077150424,0.0043184673,0.0013120008,0.0010805838,0.0019453124],"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":[0.00076069415,0.00034058798,0.0049116868,0.00071309024,0.00014760511,0.0006138698,0.00034775224,0.030932968,0.060245402,0.02041065,0.008758867,0.87181675],"study_design_scores_gemma":[0.00015127078,0.00047980912,0.0018831692,0.00006942345,0.00011969631,0.0018394385,0.00024904445,0.82345754,0.10356224,0.051122714,0.016999627,0.00006607183],"about_ca_topic_score_codex":0.00090945454,"about_ca_topic_score_gemma":0.0007922367,"teacher_disagreement_score":0.0040252223,"about_ca_system_score_codex":0.0005088933,"about_ca_system_score_gemma":0.0012843412,"threshold_uncertainty_score":0.0134657025},"labels":[],"label_agreement":null},{"id":"W2783369107","doi":"10.1007/s00373-011-1019-0","title":"Algorithmic Folding Complexity","year":2011,"lang":"en","type":"article","venue":"Graphs and Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Equidistant; Fold (higher-order function); Mathematics; Upper and lower bounds; Combinatorics; String (physics); Folding (DSP implementation); Sequence (biology); Binary number; Simple (philosophy); Geometry; Computer science; Mathematical analysis; Biology; Arithmetic","score_opus":0.05806883863181366,"score_gpt":0.2246883979558044,"score_spread":0.16661955932399072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783369107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11927013,0.0040754625,0.5843719,0.010301063,0.0006586992,0.00015673523,0.001568963,0.0021741749,0.27742282],"genre_scores_gemma":[0.7737121,0.002688849,0.13952522,0.0021575652,0.0009840636,0.00034211867,0.0033260405,0.0011259192,0.07613824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862266,0.00030846457,0.00007110826,0.00039301108,0.0004476036,0.00015720174],"domain_scores_gemma":[0.9955337,0.0024546557,0.00014358366,0.0012358944,0.00043998743,0.0001922227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091792986,0.0008512756,0.0011157007,0.0016683986,0.001845353,0.004565108,0.0018723159,0.0016251295,0.02257713],"category_scores_gemma":[0.0074132206,0.00061858044,0.0012741564,0.0029399754,0.0025204974,0.009003705,0.0034214032,0.004158074,0.0029504353],"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":[0.00003129682,0.000032204174,0.00042241075,0.00007663068,0.000016540826,0.000037303595,0.0001444354,0.0058310563,0.00037992522,0.9526409,0.0088102715,0.031577054],"study_design_scores_gemma":[0.0000040432365,0.0000034583963,0.00008448406,0.000009710391,0.000006286839,0.00003268075,0.00002747076,0.008928956,0.00026549722,0.9850277,0.005605922,0.0000038879866],"about_ca_topic_score_codex":0.0011527066,"about_ca_topic_score_gemma":0.0012624309,"teacher_disagreement_score":0.02257713,"about_ca_system_score_codex":0.0025295012,"about_ca_system_score_gemma":0.0011195457,"threshold_uncertainty_score":0.075528026},"labels":[],"label_agreement":null},{"id":"W2784266189","doi":"","title":"The Linear Equivalence of the Suffix Array and the Partially Sorted Lyndon Array.","year":2017,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Equivalence (formal languages); Suffix array; Suffix; Computer science; Mathematics; Combinatorics; Algorithm; Discrete mathematics; Data structure; Programming language","score_opus":0.028967915614915542,"score_gpt":0.2742273210300127,"score_spread":0.24525940541509714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784266189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104842156,0.0031640278,0.7028167,0.002806957,0.0013513925,0.00015836071,0.0019519343,0.0023405992,0.18056783],"genre_scores_gemma":[0.7783569,0.0018993695,0.15648486,0.002138501,0.0013408164,0.00030904682,0.0032874013,0.0010683902,0.05511472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970943,0.00071648305,0.0003128659,0.00062780624,0.00089649344,0.00035210123],"domain_scores_gemma":[0.9937496,0.0026625746,0.00046435834,0.0016195107,0.0012972158,0.00020677492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015138901,0.00028900075,0.00063407107,0.0015044034,0.0013085832,0.0043763863,0.0012051115,0.0010038839,0.01347017],"category_scores_gemma":[0.016361717,0.00041337917,0.000623881,0.0022873941,0.0029949555,0.009697365,0.003194848,0.0021918423,0.0037688354],"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":[0.00020525612,0.000040773342,0.00041485974,0.00006958219,0.000012114506,0.00015981414,0.0004712645,0.0018111914,0.0030845376,0.9207232,0.0054218965,0.06758555],"study_design_scores_gemma":[0.00002571059,0.00009193961,0.00044166044,0.000057468646,0.000019594741,0.0002878781,0.00021639826,0.00872719,0.005007834,0.95554876,0.029543448,0.00003209655],"about_ca_topic_score_codex":0.0018594124,"about_ca_topic_score_gemma":0.001251085,"teacher_disagreement_score":0.01347017,"about_ca_system_score_codex":0.0011127361,"about_ca_system_score_gemma":0.0015586428,"threshold_uncertainty_score":0.045062244},"labels":[],"label_agreement":null},{"id":"W2784607611","doi":"10.11606/d.55.2018.tde-23012018-095925","title":"Estudos em transmissões multicasting de vídeo comprimido","year":2018,"lang":"pt","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Adidas (Canada)","funders":"","keywords":"Humanities; Physics; Computer science; Art","score_opus":0.0270717853668659,"score_gpt":0.3008972100947536,"score_spread":0.27382542472788773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784607611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92468804,0.002166577,0.030842347,0.00042031807,0.00011736971,0.00042820198,0.00038306892,0.0005629227,0.040391076],"genre_scores_gemma":[0.97454923,0.0013641967,0.014626032,0.00008841651,0.000044871274,0.00012104585,0.00033004684,0.000099437326,0.008776853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784327,0.00063494337,0.00015718497,0.00028875255,0.0008381157,0.00023777339],"domain_scores_gemma":[0.9915182,0.005193744,0.0004553644,0.0007928117,0.0017976678,0.00024216496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025093441,0.0004647678,0.000426678,0.0015365236,0.0012226729,0.0018134406,0.0011737641,0.0008853063,0.005305674],"category_scores_gemma":[0.010669711,0.000324749,0.00038770112,0.0018838743,0.0007358449,0.0024672234,0.0010370738,0.00086849433,0.0008890688],"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":[0.0019052287,0.0021997583,0.06877442,0.004086461,0.00025925852,0.0035157902,0.025643144,0.034912903,0.13900581,0.025675537,0.008434546,0.68558717],"study_design_scores_gemma":[0.00036447775,0.005914653,0.08325039,0.0012527305,0.00058473233,0.006330546,0.0429876,0.25700736,0.46230277,0.011947962,0.12780347,0.00025332157],"about_ca_topic_score_codex":0.0056504006,"about_ca_topic_score_gemma":0.0042620883,"teacher_disagreement_score":0.0056504006,"about_ca_system_score_codex":0.0012333338,"about_ca_system_score_gemma":0.0005949892,"threshold_uncertainty_score":0.01774925},"labels":[],"label_agreement":null},{"id":"W2785442021","doi":"10.1109/itw.2017.8277952","title":"Design of optimal entropy-constrained scalar quantizer for sequential coding of correlated sources","year":2017,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Alphabet; Entropy (arrow of time); Encoder; Algorithm; Tuple; Computer science; Coding (social sciences); Combinatorics; Mathematics; Discrete mathematics; Statistics; Physics; Philosophy","score_opus":0.047999149356940427,"score_gpt":0.2898024989542073,"score_spread":0.24180334959726685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785442021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005609958,0.00007308751,0.9935742,0.00006178055,0.000012896235,0.000026336205,0.000033214925,0.00012062085,0.0004880134],"genre_scores_gemma":[0.31387907,0.00031782582,0.6824873,0.00014512383,0.000044420158,0.00018672926,0.00021950653,0.00007104003,0.0026489375],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994374,0.00013125669,0.00003832186,0.00014276111,0.00020626037,0.000043926717],"domain_scores_gemma":[0.9991998,0.0003064814,0.00012743202,0.00008329856,0.00024716044,0.000035870093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008685315,0.0007326332,0.0006276781,0.00048593662,0.00031671821,0.00058235606,0.0008503157,0.00055707217,0.0020076297],"category_scores_gemma":[0.002185874,0.00034932385,0.00032815724,0.0006431046,0.00057215296,0.0012674545,0.00085348147,0.0007344136,0.00046065374],"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":[0.0005004778,0.00010519522,0.0010328258,0.00030246668,0.00007979267,0.00015550316,0.00021676041,0.4461772,0.074662596,0.08748201,0.0032027187,0.38608244],"study_design_scores_gemma":[0.00003821571,0.000113143054,0.00013831214,0.000016454094,0.0000151657105,0.000058261776,0.000019711593,0.97043407,0.015596375,0.011693707,0.0018574334,0.000019122375],"about_ca_topic_score_codex":0.0017319741,"about_ca_topic_score_gemma":0.0025811056,"teacher_disagreement_score":0.0020076297,"about_ca_system_score_codex":0.00067073584,"about_ca_system_score_gemma":0.0019133977,"threshold_uncertainty_score":0.006716192},"labels":[],"label_agreement":null},{"id":"W2790857551","doi":"10.1016/j.tcs.2018.02.001","title":"On the string matching with k mismatches","year":2018,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"String (physics); Computer science; String searching algorithm; Mathematics; Matching (statistics); Combinatorics; Algorithm; Pattern matching; Programming language; Statistics","score_opus":0.010314673885081276,"score_gpt":0.2341122272412989,"score_spread":0.22379755335621762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790857551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07434918,0.0051105046,0.89152724,0.0032527589,0.0007405296,0.00016450728,0.00050601206,0.0012026901,0.023146639],"genre_scores_gemma":[0.61298615,0.0056066364,0.35294247,0.0018310247,0.0014221105,0.00031022594,0.0015015753,0.0009419785,0.02245789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940692,0.001918658,0.00059353194,0.0012252097,0.001555768,0.00063752366],"domain_scores_gemma":[0.9805367,0.013492695,0.0008125682,0.0037494828,0.0010480273,0.00036046613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003805275,0.0010488294,0.0024045317,0.0032296726,0.0018037724,0.003501518,0.0037052545,0.0043187644,0.009737788],"category_scores_gemma":[0.031213133,0.0010090984,0.0011810546,0.00844227,0.0042886822,0.014884757,0.007139337,0.0035013168,0.0031542252],"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":[0.0015108971,0.00022481095,0.0022744166,0.00057826575,0.00012977043,0.00060718064,0.00057498337,0.10229606,0.005880007,0.53419757,0.015867524,0.3358585],"study_design_scores_gemma":[0.00006281592,0.00009959745,0.00031210712,0.00008346515,0.000050910545,0.00034395527,0.00010340498,0.25629812,0.0028468417,0.73341906,0.00633512,0.000044589182],"about_ca_topic_score_codex":0.0018983056,"about_ca_topic_score_gemma":0.0011216861,"teacher_disagreement_score":0.009737788,"about_ca_system_score_codex":0.0015552687,"about_ca_system_score_gemma":0.0017203056,"threshold_uncertainty_score":0.032576144},"labels":[],"label_agreement":null},{"id":"W2791622101","doi":"10.1093/comjnl/bxac182","title":"Two-Dimensional Block Trees","year":2022,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Block (permutation group theory); Adjacency list; Raster graphics; Exploit; Computer science; Tree (set theory); Adjacency matrix; Representation (politics); Data structure; Sequence (biology); Theoretical computer science; Space (punctuation); Tree structure; Algorithm; Pattern recognition (psychology); Combinatorics; Mathematics; Artificial intelligence; Graph","score_opus":0.015094519679204782,"score_gpt":0.23862485031150107,"score_spread":0.2235303306322963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791622101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09007676,0.001243527,0.88947403,0.00061856234,0.00021389098,0.0002362624,0.003390163,0.0029054512,0.0118412925],"genre_scores_gemma":[0.4244241,0.0010781114,0.55243206,0.00028433127,0.00013161845,0.00046145028,0.007858211,0.00035793748,0.012972203],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994141,0.00010851929,0.000060274753,0.00007168269,0.00027260525,0.00007283195],"domain_scores_gemma":[0.99838805,0.0005248894,0.00014029503,0.00040461673,0.00046916536,0.00007294177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033932217,0.00029568438,0.00046155305,0.0013993791,0.00046871553,0.0010693937,0.0007215975,0.00044531454,0.0058306246],"category_scores_gemma":[0.0032282039,0.00022998644,0.00037400948,0.0029988592,0.00037924876,0.002020819,0.0010713296,0.00047394604,0.002058584],"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":[0.0006851521,0.0001791395,0.0035619605,0.0005712729,0.000091238195,0.0005282202,0.00062458124,0.14785905,0.05133515,0.19095156,0.044968054,0.5586447],"study_design_scores_gemma":[0.00009796102,0.00019544644,0.001601893,0.000064143336,0.00002735759,0.0006981953,0.00016186322,0.8257018,0.022440827,0.07844488,0.07051763,0.000048055022],"about_ca_topic_score_codex":0.0031822748,"about_ca_topic_score_gemma":0.0038445098,"teacher_disagreement_score":0.0058306246,"about_ca_system_score_codex":0.0005460063,"about_ca_system_score_gemma":0.0006942409,"threshold_uncertainty_score":0.019505382},"labels":[],"label_agreement":null},{"id":"W2791946429","doi":"10.1561/1900000055","title":"Algorithmic Aspects of Parallel Data Processing","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data processing; Massively parallel; SPARK (programming language); Parallel processing; Sorting; Joins; Data processing system; Scope (computer science); Computation; Parallel computing; Distributed computing; Theoretical computer science; Algorithm; Database","score_opus":0.08973294613584182,"score_gpt":0.36032610517810243,"score_spread":0.2705931590422606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791946429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051820506,0.009456567,0.953331,0.0034359077,0.0004245716,0.00016002204,0.00021263785,0.0003256033,0.027471775],"genre_scores_gemma":[0.18722944,0.024242045,0.7656401,0.0013180721,0.0032449532,0.0009916673,0.0013878592,0.00044269665,0.015503094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99552995,0.0009777508,0.0003687476,0.00068041385,0.0022071977,0.00023606577],"domain_scores_gemma":[0.9958896,0.002379265,0.0001626448,0.00085244246,0.0006375653,0.00007859058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029281739,0.0013078781,0.0010732599,0.0016988858,0.0013050522,0.004685568,0.002427862,0.001362633,0.0043108137],"category_scores_gemma":[0.012358523,0.00085516216,0.0013338526,0.0042700283,0.0032820515,0.0067312866,0.0028948851,0.003504942,0.0018056682],"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":[0.000036731093,0.00004401791,0.0004923624,0.0004819036,0.000045616904,0.00009280739,0.00018978806,0.045272294,0.00064856245,0.87828416,0.0057624136,0.06864947],"study_design_scores_gemma":[0.00001452646,0.00001495915,0.00012293046,0.0000474176,0.000013541365,0.00010753869,0.000039662664,0.09399339,0.00047251864,0.88428736,0.02087571,0.000010532237],"about_ca_topic_score_codex":0.001283319,"about_ca_topic_score_gemma":0.0011589818,"teacher_disagreement_score":0.004685568,"about_ca_system_score_codex":0.0017217671,"about_ca_system_score_gemma":0.0020179823,"threshold_uncertainty_score":0.015485823},"labels":[],"label_agreement":null},{"id":"W2792086409","doi":"","title":"The Lights Out Game on Subdivided Caterpillars.","year":2018,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Mathematical economics","score_opus":0.014639330624352824,"score_gpt":0.2523799178152956,"score_spread":0.2377405871909428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792086409","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22942361,0.0019152161,0.47696784,0.00403387,0.0010333917,0.00019568604,0.0010509966,0.002625519,0.28275394],"genre_scores_gemma":[0.79142946,0.0006808777,0.11805597,0.0006895222,0.00019948663,0.00012249553,0.0008340009,0.0005089401,0.08747927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996196,0.00010299658,0.000014427867,0.00006657287,0.00010136776,0.00009499772],"domain_scores_gemma":[0.9990909,0.00051604793,0.00004045725,0.00016564298,0.000057778725,0.00012909924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003810448,0.00057253515,0.00068734825,0.000530395,0.0012731174,0.0017416651,0.0013348496,0.0012514527,0.020424822],"category_scores_gemma":[0.0030100986,0.000305346,0.00048044673,0.0006761157,0.0014512886,0.0033438492,0.002799308,0.0013331097,0.0026319658],"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":[0.0013738134,0.0001430531,0.00092775485,0.0001839908,0.00006308233,0.00063672813,0.00045216948,0.04980679,0.0088392645,0.7671123,0.055334847,0.11512624],"study_design_scores_gemma":[0.00013565988,0.00018236692,0.0007805161,0.000100375815,0.00002849232,0.0003098851,0.00045927754,0.1885235,0.0057732975,0.75566334,0.04799518,0.000048222482],"about_ca_topic_score_codex":0.0025587257,"about_ca_topic_score_gemma":0.004293882,"teacher_disagreement_score":0.020424822,"about_ca_system_score_codex":0.0008339408,"about_ca_system_score_gemma":0.0004741001,"threshold_uncertainty_score":0.068327785},"labels":[],"label_agreement":null},{"id":"W2796436043","doi":"10.1109/tkde.2020.2981311","title":"HyperMinHash: MinHash in LogLog space","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Jaccard index; Cardinality (data modeling); Combinatorics; Mathematics; Discrete mathematics; Computer science; Data mining; Statistics","score_opus":0.04477670225587619,"score_gpt":0.28229477497768213,"score_spread":0.23751807272180595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796436043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019285489,0.0014724972,0.93421113,0.0011292387,0.0005660467,0.00029600784,0.0024075634,0.028196756,0.012435346],"genre_scores_gemma":[0.28337914,0.0011753531,0.6874025,0.0015025787,0.0005160156,0.00074766576,0.004372739,0.0049658995,0.015938066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978259,0.00035163818,0.00016326841,0.00034985715,0.001120261,0.00018891538],"domain_scores_gemma":[0.99468935,0.0017450373,0.00020127295,0.0025754413,0.00059313496,0.00019587048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014167804,0.0010273125,0.00087629893,0.0010996897,0.0006775057,0.003138729,0.00236129,0.0012223388,0.024936015],"category_scores_gemma":[0.013539694,0.0005730311,0.0006214766,0.0021235128,0.001346093,0.0061688395,0.0033567748,0.002199578,0.008965727],"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":[0.0015036041,0.00023244231,0.0015609636,0.000853671,0.000079644415,0.0002959715,0.0005946997,0.048700795,0.021992682,0.16589835,0.07646733,0.68181986],"study_design_scores_gemma":[0.0002831931,0.00034303576,0.0006169669,0.00021155397,0.00004354723,0.0006967098,0.00029313055,0.5961723,0.0496827,0.23958573,0.11195824,0.00011288464],"about_ca_topic_score_codex":0.0013040669,"about_ca_topic_score_gemma":0.0019479017,"teacher_disagreement_score":0.024936015,"about_ca_system_score_codex":0.0012019565,"about_ca_system_score_gemma":0.0019458095,"threshold_uncertainty_score":0.08341932},"labels":[],"label_agreement":null},{"id":"W2796779090","doi":"10.22215/etd/2016-11773","title":"String Searching Using External Memory","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"String (physics); Prefix; Computer science; Strengths and weaknesses; Theoretical computer science; Data mining; String searching algorithm; Trie; Data structure; Information retrieval; Mathematics; Programming language; Psychology","score_opus":0.026373589786600912,"score_gpt":0.30928001936395083,"score_spread":0.2829064295773499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796779090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13443463,0.0049151173,0.7768644,0.00093330856,0.00060571614,0.00030844242,0.0009898391,0.009273549,0.071675055],"genre_scores_gemma":[0.44501603,0.0029032077,0.5100851,0.0005468923,0.00019289339,0.0003914366,0.0021928935,0.001013883,0.03765768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986249,0.00020608483,0.0001428122,0.00031936003,0.0005680756,0.00013873671],"domain_scores_gemma":[0.9967871,0.0010171487,0.00020303176,0.0012595719,0.00065914297,0.00007405867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071797916,0.0008806608,0.00083648675,0.0018660263,0.00085795746,0.0028480766,0.0020904636,0.00088574964,0.0143292975],"category_scores_gemma":[0.0068443674,0.000368263,0.0005613254,0.0037593425,0.0008359975,0.007025055,0.0023608631,0.0008155925,0.0047420952],"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":[0.00086565624,0.00015522257,0.0023373368,0.00056078215,0.000087488734,0.0003427048,0.0004461017,0.018801924,0.0349679,0.052808728,0.013977223,0.874649],"study_design_scores_gemma":[0.00023809505,0.001092849,0.0027466672,0.00062528107,0.00028550962,0.0030216395,0.0009648517,0.41880843,0.2586964,0.12544101,0.18793023,0.0001490085],"about_ca_topic_score_codex":0.00086424086,"about_ca_topic_score_gemma":0.000980175,"teacher_disagreement_score":0.0143292975,"about_ca_system_score_codex":0.00066277955,"about_ca_system_score_gemma":0.00087679015,"threshold_uncertainty_score":0.04793626},"labels":[],"label_agreement":null},{"id":"W2798963609","doi":"10.1145/3209978.3210147","title":"A New Term Frequency Normalization Model for Probabilistic Information Retrieval","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"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; National Natural Science Foundation of China; Ontario Research Foundation","keywords":"Normalization (sociology); Computer science; Probabilistic logic; Divergence-from-randomness model; Term (time); Intuition; Term Discrimination; Information retrieval; Artificial intelligence; Algorithm; Data mining; Search engine","score_opus":0.019296375602784577,"score_gpt":0.25680317161777466,"score_spread":0.23750679601499008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798963609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00495359,0.002164628,0.9875694,0.00057050335,0.00020503951,0.0002063121,0.00063135085,0.0019630252,0.0017361231],"genre_scores_gemma":[0.22243997,0.0037895662,0.75008315,0.0015470516,0.0012636122,0.0018380812,0.004757959,0.0006892979,0.013591274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648345,0.0008310128,0.0003006735,0.00088046584,0.0012870284,0.00021748223],"domain_scores_gemma":[0.99794644,0.00074797665,0.00017691475,0.00043550314,0.00062072213,0.00007246164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004191403,0.0017883835,0.0019535024,0.0035559542,0.0011504457,0.0023953095,0.003704691,0.0023667081,0.0044490383],"category_scores_gemma":[0.010980105,0.00068198267,0.002108066,0.006035229,0.0015409067,0.0061036455,0.0017837469,0.0031614495,0.0052114045],"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":[0.0006322138,0.00032039965,0.001770324,0.00065229135,0.00032655324,0.00018783232,0.00023147017,0.13102251,0.026171042,0.052180264,0.032369923,0.7541352],"study_design_scores_gemma":[0.000061195926,0.00018457604,0.0014259975,0.00005462253,0.00012495938,0.0003378437,0.00004491833,0.9337355,0.0076384614,0.041614577,0.014662007,0.00011519388],"about_ca_topic_score_codex":0.00843573,"about_ca_topic_score_gemma":0.008012066,"teacher_disagreement_score":0.00843573,"about_ca_system_score_codex":0.0022958575,"about_ca_system_score_gemma":0.0023068178,"threshold_uncertainty_score":0.02216649},"labels":[],"label_agreement":null},{"id":"W2799512315","doi":"10.1007/978-981-10-8476-8_12","title":"BWT: An Index Structure to Speed-Up Both Exact and Inexact String Matching","year":2018,"lang":"en","type":"book-chapter","venue":"Studies in big data","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Substring; String searching algorithm; Trie; String (physics); Search tree; Approximate string matching; Pattern matching; Combinatorics; Mathematics; Redundancy (engineering); String metric; Tree (set theory); Algorithm; Set (abstract data type); Suffix tree; Computer science; Discrete mathematics; Data structure; Search algorithm; Artificial intelligence","score_opus":0.16180645473176478,"score_gpt":0.35172747741426014,"score_spread":0.18992102268249536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799512315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005655567,0.0019571362,0.96553826,0.00039491354,0.0012220623,0.00016196712,0.0011831588,0.016836448,0.0070505165],"genre_scores_gemma":[0.03710635,0.0011113252,0.9410937,0.00037973063,0.0004885617,0.00024352208,0.003175723,0.0029661166,0.013435064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678,0.00025925803,0.00033763456,0.0004354461,0.0019807054,0.00020704934],"domain_scores_gemma":[0.9954613,0.001209479,0.00022865394,0.001868031,0.0010629412,0.00016955567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019027856,0.0015049888,0.002242186,0.004291917,0.0014941173,0.0034328601,0.0044203484,0.0020238939,0.021598902],"category_scores_gemma":[0.011384795,0.001159714,0.0013559143,0.009655287,0.0015045245,0.009480079,0.0050472002,0.0028934884,0.012522971],"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":[0.00034410876,0.00013575808,0.0004172457,0.00043986205,0.00007196998,0.00014143166,0.00017661281,0.010931812,0.011329629,0.057763636,0.072002575,0.8462453],"study_design_scores_gemma":[0.00023821516,0.0002666784,0.0005610614,0.00023765015,0.0001467149,0.0011230488,0.00017923435,0.4671343,0.06339839,0.31638098,0.15019694,0.00013685717],"about_ca_topic_score_codex":0.0027484847,"about_ca_topic_score_gemma":0.0028338323,"teacher_disagreement_score":0.021598902,"about_ca_system_score_codex":0.0011644579,"about_ca_system_score_gemma":0.0022037579,"threshold_uncertainty_score":0.07225555},"labels":[],"label_agreement":null},{"id":"W2799530285","doi":"10.1145/3168005","title":"Selection and Sorting in the “Restore” Model","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Subroutine; Sorting; Sequence (biology); Permutation (music); Selection (genetic algorithm); Computer science; Algorithm; Space (punctuation); Computation; Order (exchange); Mathematics; Theoretical computer science; Artificial intelligence","score_opus":0.03102233657756117,"score_gpt":0.283626278682251,"score_spread":0.25260394210468984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799530285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09886861,0.0004548433,0.8639436,0.0023735776,0.00019867068,0.00014947746,0.00032690098,0.002264241,0.03142019],"genre_scores_gemma":[0.6720391,0.00085341634,0.27011323,0.0012161396,0.00044157304,0.00050051505,0.00094153336,0.00047404284,0.05342046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847096,0.00034548918,0.00006062862,0.00032802977,0.00045885437,0.00033608897],"domain_scores_gemma":[0.9987041,0.0004277502,0.00014749783,0.0004479166,0.00015143432,0.00012127589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008621735,0.0006845875,0.0008032194,0.00067962817,0.0011222145,0.0023806873,0.002542517,0.0016640812,0.009889338],"category_scores_gemma":[0.0022084475,0.00039173188,0.0012453384,0.0011218346,0.0026293409,0.0058515,0.0018240719,0.0020267505,0.0022354545],"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":[0.00052849844,0.00016455143,0.0006234668,0.00018087958,0.00003296708,0.00053146173,0.0003071865,0.11169034,0.010869653,0.8326046,0.0095476555,0.032918647],"study_design_scores_gemma":[0.00014082609,0.00025708452,0.00033647093,0.000018839142,0.00003551722,0.00028653987,0.00018409283,0.45325032,0.009403518,0.50908595,0.026955407,0.00004545265],"about_ca_topic_score_codex":0.0018656303,"about_ca_topic_score_gemma":0.001723412,"teacher_disagreement_score":0.009889338,"about_ca_system_score_codex":0.0014928104,"about_ca_system_score_gemma":0.0012579334,"threshold_uncertainty_score":0.03308314},"labels":[],"label_agreement":null},{"id":"W2800253090","doi":"10.1038/s41467-017-02480-6","title":"Optimal compressed representation of high throughput sequence data via light assembly","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"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":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Simons Institute for the Theory of Computing, University of California Berkeley; National Institutes of Health; National Science Foundation","keywords":"Sequence assembly; Computer science; Trie; Contig; Representation (politics); Data compression; Node (physics); Compression (physics); Algorithm; Compression ratio; Throughput; Reference genome; External Data Representation; Data structure; Theoretical computer science; Parallel computing; Genome; Artificial intelligence; Biology","score_opus":0.07744304994520126,"score_gpt":0.37532753633135524,"score_spread":0.29788448638615395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800253090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035415903,0.00020893558,0.9612088,0.00019664835,0.00004558912,0.000039341074,0.00031362372,0.0011950638,0.0013761275],"genre_scores_gemma":[0.25179377,0.0003402944,0.74205714,0.00020014189,0.00007294608,0.00021663666,0.0019773473,0.00036663335,0.002975075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921644,0.00015502739,0.000048163896,0.00013183556,0.00037407826,0.00007451586],"domain_scores_gemma":[0.9986161,0.00057828095,0.00013995793,0.0004085907,0.00020159633,0.000055495966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537251,0.000590265,0.0005565879,0.0008768256,0.00040777054,0.0010845647,0.001127262,0.00072025956,0.0017993374],"category_scores_gemma":[0.0035122975,0.00031224973,0.00047893325,0.0014904907,0.00075613125,0.0016399076,0.0018922195,0.001206954,0.0010775093],"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":[0.00081236,0.00020444886,0.0013244187,0.000381306,0.000047665093,0.00065162417,0.0008159095,0.29665396,0.15873377,0.073146984,0.008659709,0.4585679],"study_design_scores_gemma":[0.000045621542,0.00010408593,0.00034984172,0.0000279507,0.000012335644,0.00024438943,0.000111585185,0.9056755,0.058238003,0.028089713,0.007062335,0.00003865633],"about_ca_topic_score_codex":0.0009751948,"about_ca_topic_score_gemma":0.0013172295,"teacher_disagreement_score":0.0017993374,"about_ca_system_score_codex":0.0004957126,"about_ca_system_score_gemma":0.0006136619,"threshold_uncertainty_score":0.0060194135},"labels":[],"label_agreement":null},{"id":"W2804358784","doi":"10.4230/lipics.aofa.2018.36","title":"Average Cost of QuickXsort with Pivot Sampling","year":2018,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Quicksort; Sorting; Selection (genetic algorithm); Term (time); Mathematical optimization; Sampling (signal processing); Computer science; Isolation (microbiology); Matching (statistics); Linear programming; sort; Algorithm; Mathematics; Sorting algorithm; Statistics; Arithmetic; Artificial intelligence","score_opus":0.03303782809232589,"score_gpt":0.2881667979971099,"score_spread":0.25512896990478406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804358784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1882364,0.008569496,0.72048455,0.005178857,0.0011164307,0.00059420476,0.0037005392,0.017474234,0.054645304],"genre_scores_gemma":[0.57780457,0.0015447285,0.38760832,0.0014693873,0.0005091106,0.00073676254,0.0039671343,0.005121745,0.021238303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889135,0.0017308258,0.00065034593,0.0014422393,0.0051672347,0.0020958616],"domain_scores_gemma":[0.9804248,0.009747706,0.00080199656,0.0058451085,0.0024108305,0.0007695823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005578994,0.0018694754,0.001840038,0.002265585,0.0017210321,0.004969547,0.0044854027,0.0016317812,0.016155867],"category_scores_gemma":[0.02795314,0.0010597374,0.0015884911,0.0040356065,0.0026342422,0.011724041,0.004503642,0.002761932,0.0040287813],"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":[0.004674547,0.00054758746,0.008247903,0.0015394482,0.0003569149,0.00035155474,0.0005090339,0.26234692,0.02632352,0.1998619,0.0708209,0.4244198],"study_design_scores_gemma":[0.00020484634,0.00030375316,0.0017595348,0.00013411748,0.00020311736,0.00039925694,0.00018874012,0.8270506,0.03100561,0.12163086,0.017028673,0.00009086846],"about_ca_topic_score_codex":0.0046189106,"about_ca_topic_score_gemma":0.009602143,"teacher_disagreement_score":0.016155867,"about_ca_system_score_codex":0.004945519,"about_ca_system_score_gemma":0.0072669555,"threshold_uncertainty_score":0.05404675},"labels":[],"label_agreement":null},{"id":"W2804617844","doi":"10.1016/j.tcs.2018.05.017","title":"Designing and implementing algorithms for the closest string problem","year":2018,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parameterized complexity; Algorithm; String (physics); Hamming distance; Time complexity; Set (abstract data type); String searching algorithm; Computer science; Mathematics; Pattern matching","score_opus":0.02336628486097867,"score_gpt":0.29476499538044393,"score_spread":0.27139871051946524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804617844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008885239,0.0002585096,0.98668414,0.0004570487,0.00012420482,0.00011546103,0.00008408095,0.0016414319,0.0017499168],"genre_scores_gemma":[0.069690056,0.00029394918,0.92707896,0.00021620469,0.00013908291,0.00019543871,0.00044855234,0.0003579085,0.001579829],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928526,0.0020966134,0.00076936843,0.0014953772,0.0021632814,0.00062267284],"domain_scores_gemma":[0.9860486,0.0074076774,0.00072567345,0.003983489,0.0015169511,0.00031765955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004582409,0.0013031407,0.0022205652,0.0025105798,0.0021474387,0.0048212516,0.005749437,0.004044761,0.0074418434],"category_scores_gemma":[0.031874787,0.0012145853,0.0017426097,0.0047026374,0.0023652092,0.011278605,0.006190874,0.0045025884,0.003738232],"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":[0.000694147,0.0005040777,0.0020719343,0.0006232952,0.00015732386,0.00017126714,0.0005844516,0.096050695,0.010843045,0.20208566,0.016750485,0.66946363],"study_design_scores_gemma":[0.0001839202,0.00016263657,0.00019841336,0.000079323385,0.000052073316,0.00034231332,0.000333415,0.59942377,0.015935574,0.37441412,0.008824694,0.00004972407],"about_ca_topic_score_codex":0.001285161,"about_ca_topic_score_gemma":0.0016947389,"teacher_disagreement_score":0.0074418434,"about_ca_system_score_codex":0.0015869032,"about_ca_system_score_gemma":0.0030329868,"threshold_uncertainty_score":0.02489549},"labels":[],"label_agreement":null},{"id":"W2804942034","doi":"10.1007/s00453-020-00687-6","title":"Compressed Dynamic Range Majority and Minority Data Structures","year":2020,"lang":"en","type":"preprint","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Instituto Millenium; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Alphabet; Mathematics; Order (exchange); Binary logarithm; Sigma; Range (aeronautics); Sequence (biology); Space (punctuation); Algorithm; Discrete mathematics; Physics; Computer science","score_opus":0.0485731490374837,"score_gpt":0.2966517954176518,"score_spread":0.2480786463801681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804942034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17747019,0.004194499,0.77481484,0.005540106,0.00078707293,0.0002177191,0.001858619,0.0018939509,0.033223],"genre_scores_gemma":[0.7599674,0.001426367,0.20650348,0.0010959257,0.0010936533,0.00035656657,0.0022165,0.0004905817,0.026849575],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985953,0.00024605822,0.000071296374,0.0002238357,0.00071505184,0.00014838808],"domain_scores_gemma":[0.9964528,0.001257021,0.00019546805,0.0014365567,0.0005543215,0.000103733124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009283862,0.00042696728,0.00072744396,0.0013954598,0.0009792037,0.0020136368,0.0012374524,0.0007553855,0.006890499],"category_scores_gemma":[0.0081398515,0.00026353312,0.00036791735,0.0023187008,0.0013464045,0.004421935,0.002526263,0.0017378102,0.001350423],"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":[0.0011997214,0.00018945463,0.0017239212,0.00022892859,0.000041294064,0.0002227583,0.00059911434,0.036112048,0.01656349,0.44357646,0.029521914,0.47002074],"study_design_scores_gemma":[0.0001151919,0.00018137236,0.0009550086,0.00010337116,0.000053758107,0.00077415997,0.00036788604,0.3316895,0.04326761,0.589389,0.033054136,0.00004901037],"about_ca_topic_score_codex":0.0007068565,"about_ca_topic_score_gemma":0.00080517505,"teacher_disagreement_score":0.006890499,"about_ca_system_score_codex":0.00083713385,"about_ca_system_score_gemma":0.0008432126,"threshold_uncertainty_score":0.023051023},"labels":[],"label_agreement":null},{"id":"W2805327676","doi":"10.31031/oabb.2018.01.000523","title":"String Matching in DNA Databases","year":2018,"lang":"en","type":"article","venue":"Open Access Biostatistics & Bioinformatics","topic":"Algorithms and Data Compression","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 Winnipeg","funders":"","keywords":"Database; String (physics); Computer science; Matching (statistics); String searching algorithm; DNA; Information retrieval; Computational biology; Biology; Pattern matching; Artificial intelligence; Mathematics; Physics; Genetics; Theoretical physics; Statistics","score_opus":0.07483328991906217,"score_gpt":0.393748852722946,"score_spread":0.31891556280388383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805327676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007046241,0.005395903,0.7752108,0.002625095,0.0007899129,0.0015013104,0.14011486,0.040553465,0.026762431],"genre_scores_gemma":[0.058609813,0.0069766515,0.69174993,0.001809911,0.0004595362,0.0025260865,0.22037181,0.002847296,0.014648877],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942246,0.0015077639,0.0013001686,0.0011021566,0.0015928008,0.000272468],"domain_scores_gemma":[0.99307257,0.0036889887,0.0005334323,0.0017546332,0.00077916856,0.00017116225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003677228,0.001393006,0.0021344998,0.009758052,0.00093961344,0.0037989805,0.0032199689,0.0028082363,0.04167615],"category_scores_gemma":[0.020935765,0.00077223236,0.0018285859,0.0152359735,0.000912996,0.007048537,0.0034502805,0.0015471986,0.034081113],"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":[0.0009508664,0.00025885378,0.0017858278,0.0047761253,0.00034882678,0.00079697295,0.00032258374,0.014964871,0.0074376785,0.10584938,0.16892686,0.69358116],"study_design_scores_gemma":[0.00024957757,0.00019738298,0.0011226991,0.0012158719,0.0001466771,0.0013177482,0.0003287259,0.055231288,0.013271817,0.46859732,0.45821387,0.00010702877],"about_ca_topic_score_codex":0.0013034448,"about_ca_topic_score_gemma":0.0009522657,"teacher_disagreement_score":0.04167615,"about_ca_system_score_codex":0.001118964,"about_ca_system_score_gemma":0.002531268,"threshold_uncertainty_score":0.13942057},"labels":[],"label_agreement":null},{"id":"W2806423369","doi":"10.1016/j.tcs.2020.05.039","title":"Tree path majority data structures","year":2020,"lang":"en","type":"preprint","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Natural Sciences and Engineering Research Council of Canada; Instituto Millenium","keywords":"Combinatorics; Logarithm; Binary logarithm; Sigma; Mathematics; Path (computing); Tree (set theory); Log-log plot; Time complexity; Entropy (arrow of time); Data structure; Space (punctuation); Linear space; Discrete mathematics; Physics; Computer science; Mathematical analysis","score_opus":0.040455948883471746,"score_gpt":0.29748064855604134,"score_spread":0.2570246996725696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806423369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13867001,0.002762075,0.7974454,0.0044647898,0.00060732284,0.00032020194,0.004307291,0.004704824,0.046718065],"genre_scores_gemma":[0.67875046,0.0014132961,0.2675372,0.0014164712,0.0005505704,0.00053224456,0.0053245095,0.001127911,0.043347396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987884,0.00022731653,0.0000920909,0.00022949475,0.0005056088,0.00015723864],"domain_scores_gemma":[0.99506736,0.0016166583,0.00028083666,0.00199557,0.00086322235,0.00017624123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001071911,0.00042546217,0.00086282357,0.0012535242,0.0014680973,0.0021994933,0.0013022623,0.000978625,0.015580435],"category_scores_gemma":[0.0067046536,0.00035291974,0.00038970416,0.0028152259,0.0011316652,0.006386753,0.0032064999,0.0018297883,0.003962867],"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":[0.0010297988,0.0001726676,0.0013502837,0.00036527423,0.000052500778,0.00017835418,0.00043142308,0.014049644,0.012194775,0.54990613,0.047832992,0.3724361],"study_design_scores_gemma":[0.00010481,0.00024231512,0.0005102371,0.0000900003,0.000055302036,0.00043418637,0.00020391207,0.07979195,0.021138478,0.85025024,0.047135644,0.000042837415],"about_ca_topic_score_codex":0.00045122055,"about_ca_topic_score_gemma":0.0009492632,"teacher_disagreement_score":0.015580435,"about_ca_system_score_codex":0.0008885124,"about_ca_system_score_gemma":0.0013283469,"threshold_uncertainty_score":0.05212176},"labels":[],"label_agreement":null},{"id":"W2806692674","doi":"10.1007/978-3-319-96418-8_21","title":"A New Style of Mathematical Proof","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematical proof; Computer science; Proof assistant; Style (visual arts); Proof theory; Computer-assisted proof; Calculus (dental); Automated theorem proving; Theoretical computer science; Mathematics","score_opus":0.01740536563602675,"score_gpt":0.25391264512180994,"score_spread":0.2365072794857832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806692674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014848341,0.010318091,0.6900095,0.01498143,0.0068134833,0.000069779344,0.0004773918,0.0009434773,0.27490196],"genre_scores_gemma":[0.13814057,0.02675269,0.54598814,0.018097328,0.023617735,0.0006287206,0.0009831924,0.0027548054,0.24303679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985049,0.0004460054,0.000098523175,0.00029278634,0.0005915474,0.000066254484],"domain_scores_gemma":[0.997681,0.0012979868,0.000086996864,0.00046498436,0.00038904083,0.000080064136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002134049,0.0014061313,0.0008555264,0.0027242983,0.0015089989,0.004719955,0.002183934,0.0016184534,0.022959169],"category_scores_gemma":[0.006319423,0.0006992636,0.0015408715,0.001679076,0.007450414,0.011450339,0.0032905906,0.0079991985,0.010138759],"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":[0.0000073458427,0.00000953943,0.00002567166,0.00013560533,0.000009777244,0.00003245053,0.00013447512,0.00027184185,0.00033360545,0.95189524,0.02363596,0.02350844],"study_design_scores_gemma":[0.000009697489,0.000009539681,0.000038851227,0.000067782305,0.000008780892,0.00014972607,0.000023723247,0.00095775386,0.0003614413,0.860955,0.1374041,0.000013606858],"about_ca_topic_score_codex":0.00047280887,"about_ca_topic_score_gemma":0.00047321763,"teacher_disagreement_score":0.022959169,"about_ca_system_score_codex":0.001808888,"about_ca_system_score_gemma":0.0008178689,"threshold_uncertainty_score":0.07680607},"labels":[],"label_agreement":null},{"id":"W2806844872","doi":"","title":"Combining MIML and Distant Supervision for KBP Slot Filling.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.020450938072427545,"score_gpt":0.2664074188859343,"score_spread":0.24595648081350674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806844872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016801542,0.00084141816,0.9595439,0.0005938092,0.0002685044,0.0001529396,0.0012446423,0.01565531,0.004898059],"genre_scores_gemma":[0.3201912,0.0003435707,0.6652095,0.00064804376,0.00034893723,0.00035180847,0.0053826366,0.0012893016,0.006234961],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972384,0.00087664655,0.00017341379,0.0005460823,0.0009171901,0.0002482155],"domain_scores_gemma":[0.9941148,0.0024017298,0.000271868,0.0018717878,0.0011114985,0.00022830938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025776546,0.0008512666,0.0013760981,0.002388568,0.0010988519,0.0019211319,0.0031102856,0.0013953341,0.006760722],"category_scores_gemma":[0.014010199,0.00052204146,0.0006096256,0.0024624295,0.0011721049,0.00550884,0.0044158073,0.0019295159,0.0048365174],"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":[0.00079723855,0.0002988879,0.0016807356,0.00041187587,0.000059408507,0.00019156885,0.00038909388,0.021563334,0.011492799,0.018706877,0.037125334,0.9072828],"study_design_scores_gemma":[0.00009885644,0.00017865065,0.0007919516,0.00008912413,0.000049150534,0.00023300103,0.00040499785,0.864368,0.02808713,0.08030608,0.025325315,0.0000677415],"about_ca_topic_score_codex":0.0038455182,"about_ca_topic_score_gemma":0.008667415,"teacher_disagreement_score":0.006760722,"about_ca_system_score_codex":0.0007987699,"about_ca_system_score_gemma":0.0026097614,"threshold_uncertainty_score":0.022616863},"labels":[],"label_agreement":null},{"id":"W2807205034","doi":"","title":"Combining Open IE and Distant Supervision for KBP Slot Filling.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Open source; Operating system","score_opus":0.031086140515368094,"score_gpt":0.29410978345993205,"score_spread":0.26302364294456393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807205034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013076342,0.0005609834,0.9753686,0.00029165257,0.0002058842,0.00008980409,0.00052112574,0.006100057,0.003785443],"genre_scores_gemma":[0.3312268,0.0004413805,0.6562083,0.00039604583,0.0003252634,0.00024360382,0.003961622,0.001007904,0.006189028],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975695,0.0006120575,0.00017665255,0.0005819053,0.0007875353,0.0002724537],"domain_scores_gemma":[0.99284005,0.002698578,0.0002703102,0.0026311087,0.0012787604,0.0002811583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023474912,0.0008152502,0.0013852206,0.0018966609,0.0009805439,0.0019575506,0.0025869738,0.0014273055,0.0051982324],"category_scores_gemma":[0.016202591,0.0004891115,0.0006123985,0.0023395247,0.0013125739,0.006457693,0.005103645,0.0023783522,0.0032512129],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076828414,0.00031419375,0.0017053616,0.00033349756,0.000059372327,0.00023894486,0.00055195997,0.02637555,0.014523795,0.031080427,0.023861356,0.90018725],"study_design_scores_gemma":[0.0000720246,0.00017765707,0.00091935304,0.000105970634,0.000051406558,0.00035724184,0.0005558477,0.79060435,0.03509639,0.14941043,0.022570409,0.00007894921],"about_ca_topic_score_codex":0.0026039418,"about_ca_topic_score_gemma":0.004582254,"teacher_disagreement_score":0.0051982324,"about_ca_system_score_codex":0.0004521057,"about_ca_system_score_gemma":0.0020432733,"threshold_uncertainty_score":0.017389834},"labels":[],"label_agreement":null},{"id":"W2808240512","doi":"10.2139/ssrn.1713635","title":"The Interval Ordering Problem","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interval (graph theory); Mathematics; Bottleneck; Time complexity; Real line; Combinatorics; Cover (algebra); Discrete mathematics; Set (abstract data type); Function (biology); Polynomial; Approximation algorithm; Constant (computer programming); Computer science; Mathematical analysis","score_opus":0.005059904200827594,"score_gpt":0.22695704966802124,"score_spread":0.22189714546719366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808240512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050123204,0.005459207,0.83625305,0.007315279,0.0008853953,0.00013128105,0.0015314644,0.00049237674,0.09780884],"genre_scores_gemma":[0.5461543,0.008577222,0.37153774,0.001619672,0.002768818,0.00038010988,0.0056129578,0.00056826,0.06278088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985668,0.00039821028,0.000107323416,0.00036781785,0.00042110644,0.0001387211],"domain_scores_gemma":[0.9956809,0.002860197,0.00027155096,0.0006507919,0.00033435694,0.00020218326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013072224,0.000677701,0.0011856435,0.0012675348,0.0011492168,0.0035422558,0.0014338824,0.0016284247,0.017695839],"category_scores_gemma":[0.009538726,0.0006393751,0.0008609716,0.0034911847,0.0014373364,0.0072189574,0.001905,0.003924613,0.0021422917],"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":[0.00018463211,0.0000986086,0.00054935034,0.00023597339,0.000040347342,0.0001489012,0.0001909648,0.01975374,0.0008965491,0.8434265,0.022356544,0.11211779],"study_design_scores_gemma":[0.000029422885,0.000022143575,0.00015323062,0.000037746275,0.000014828331,0.00014224321,0.00007683449,0.03516214,0.00044597097,0.9506054,0.013298384,0.000011643309],"about_ca_topic_score_codex":0.0008208475,"about_ca_topic_score_gemma":0.00065605046,"teacher_disagreement_score":0.017695839,"about_ca_system_score_codex":0.0010037305,"about_ca_system_score_gemma":0.0010971716,"threshold_uncertainty_score":0.0591985},"labels":[],"label_agreement":null},{"id":"W2809572382","doi":"10.1007/978-3-319-76285-2_5","title":"The Use of the Burrows–Wheeler Transform for Analysis and Composition","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Genome; String (physics); String searching algorithm; Alphabet; Cytosine; Computer science; Nucleobase; DNA; Thymine; Human genome; Algorithm; Pattern matching; Computational biology; Genetics; Biology; Gene; Mathematics; Artificial intelligence","score_opus":0.04399293497821261,"score_gpt":0.2486928721964303,"score_spread":0.2046999372182177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809572382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011022128,0.004502388,0.97638094,0.00041033665,0.0007084605,0.000030495112,0.00007405067,0.0007256279,0.016065529],"genre_scores_gemma":[0.029148862,0.008874339,0.9260967,0.0004325436,0.0010182905,0.00013850823,0.00034295567,0.0012811219,0.032666583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985538,0.00024977166,0.00012434195,0.00026472047,0.0007362104,0.00007106675],"domain_scores_gemma":[0.99853694,0.0007144402,0.000064344465,0.00039453816,0.00025463317,0.00003511658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014741633,0.0015176132,0.001198388,0.0031400481,0.00084390905,0.0033466376,0.0017609935,0.001512306,0.01052856],"category_scores_gemma":[0.006035773,0.0008724549,0.0013340337,0.0042003845,0.0035206506,0.005479025,0.0022498607,0.0043553067,0.008144307],"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":[0.000053253025,0.000031589247,0.00008827208,0.00027667527,0.000031441556,0.00011066077,0.00016884375,0.0047283256,0.009299134,0.5382961,0.013246217,0.43366954],"study_design_scores_gemma":[0.000015012482,0.000044605105,0.00021229555,0.00013713552,0.000029569972,0.0006611937,0.00006863616,0.060779512,0.023414876,0.7211018,0.19346678,0.000068516216],"about_ca_topic_score_codex":0.00087152387,"about_ca_topic_score_gemma":0.0007620981,"teacher_disagreement_score":0.01052856,"about_ca_system_score_codex":0.0008135123,"about_ca_system_score_gemma":0.0007532943,"threshold_uncertainty_score":0.035221577},"labels":[],"label_agreement":null},{"id":"W2810486625","doi":"10.4230/lipics.sea.2018.6","title":"Speeding up Dualization in the Fredman-Khachiyan Algorithm B","year":2018,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.021613850467479278,"score_gpt":0.2850080168253123,"score_spread":0.263394166357833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810486625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12069451,0.00041535284,0.8514726,0.0010975223,0.00017143734,0.00026655997,0.0003280295,0.006398929,0.01915507],"genre_scores_gemma":[0.3935285,0.00012475716,0.5985887,0.00044281853,0.00006111531,0.00026735468,0.0005959826,0.0005408202,0.005849881],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798644,0.00052745687,0.00012711594,0.0004048553,0.00048689457,0.0004672481],"domain_scores_gemma":[0.9971169,0.0015052388,0.00017690395,0.00064780837,0.0004238496,0.00012933141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002193714,0.0009048488,0.0010999234,0.0012955002,0.0011157846,0.0022082385,0.0018301064,0.0017763501,0.006504504],"category_scores_gemma":[0.009007293,0.0005346921,0.0011038044,0.0010565716,0.0014498974,0.0031599742,0.0034767154,0.0026281194,0.0020907759],"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":[0.0026205725,0.00062816706,0.0051653828,0.00056790694,0.00011881043,0.0003700907,0.0007659183,0.10971848,0.038331367,0.25859407,0.018691279,0.5644279],"study_design_scores_gemma":[0.00038231793,0.00019629937,0.0007821796,0.000080473714,0.000055685872,0.00036062894,0.00018891433,0.7892912,0.027100075,0.17010456,0.011400084,0.00005754933],"about_ca_topic_score_codex":0.0043474566,"about_ca_topic_score_gemma":0.0044027898,"teacher_disagreement_score":0.006504504,"about_ca_system_score_codex":0.001812387,"about_ca_system_score_gemma":0.0032337217,"threshold_uncertainty_score":0.021759748},"labels":[],"label_agreement":null},{"id":"W2811278891","doi":"10.1007/978-3-319-74421-6_12","title":"Using the Random Decrement Technique on Short Records with Varying Signal-to-Noise Ratios","year":2018,"lang":"en","type":"book-chapter","venue":"Conference proceedings of the Society for Experimental Mechanics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Rowan Williams Davies & Irwin (Canada)","funders":"","keywords":"Random noise; Noise (video); SIGNAL (programming language); Statistics; Acoustics; Mathematics; Computer science; Physics; Artificial intelligence","score_opus":0.053876238505453006,"score_gpt":0.2852103077278347,"score_spread":0.23133406922238167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811278891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12733735,0.001051651,0.86483324,0.00036172508,0.0002334831,0.00013506679,0.00037108475,0.002402737,0.0032738077],"genre_scores_gemma":[0.33813292,0.0014431275,0.6519119,0.00014177032,0.00014564712,0.00012760161,0.00078994065,0.0006198743,0.0066871857],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945754,0.00011352976,0.000052961143,0.00012652193,0.00020379947,0.00004555902],"domain_scores_gemma":[0.9968094,0.0015567385,0.00019942621,0.00089013914,0.00044023374,0.000104028564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014857472,0.00082562293,0.00054399826,0.0012423972,0.0005271253,0.0013126327,0.0010477493,0.0010362081,0.0032532737],"category_scores_gemma":[0.006335844,0.000327648,0.00047935615,0.0018918565,0.0006340599,0.0016469597,0.00079616986,0.0011434339,0.0013473064],"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":[0.0013068377,0.00018525196,0.0023600883,0.0005138978,0.00013186854,0.0004233215,0.00031617362,0.01207601,0.5028442,0.006896356,0.0016732268,0.4712727],"study_design_scores_gemma":[0.000076334305,0.0006792646,0.013199736,0.00011467226,0.00025888463,0.00204453,0.00017382448,0.416887,0.5483681,0.0067094993,0.011374067,0.0001141051],"about_ca_topic_score_codex":0.0011183624,"about_ca_topic_score_gemma":0.0023231604,"teacher_disagreement_score":0.0032532737,"about_ca_system_score_codex":0.00035717982,"about_ca_system_score_gemma":0.00042717205,"threshold_uncertainty_score":0.010883331},"labels":[],"label_agreement":null},{"id":"W2820145021","doi":"10.1109/tkde.2018.2854797","title":"Introducing Cuts Into a Top-Down Process for Checking Tree Inclusion","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"Tree (set theory); Matching (statistics); Bounded function; Computer science; Set (abstract data type); Combinatorics; Order (exchange); Space (punctuation); Theoretical computer science; Algorithm; Discrete mathematics; Mathematics; Programming language; Statistics","score_opus":0.021276819399349816,"score_gpt":0.2953921537667026,"score_spread":0.27411533436735275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2820145021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0095673585,0.00018610424,0.98394763,0.00023045462,0.00008179942,0.00041700125,0.0004556422,0.004006475,0.0011074172],"genre_scores_gemma":[0.06183376,0.00011943536,0.9330922,0.00023715598,0.00006546035,0.00037277828,0.0017796998,0.0007977198,0.0017017795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871793,0.0024551095,0.0013450196,0.0031959892,0.004573306,0.0012514121],"domain_scores_gemma":[0.96380687,0.023796085,0.0021403602,0.005012632,0.004285565,0.000958397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065602115,0.0022606624,0.0025318444,0.004333053,0.0020827884,0.005155134,0.004565752,0.0026459566,0.007747043],"category_scores_gemma":[0.034004014,0.0020616367,0.0043079266,0.00348284,0.004044601,0.009410451,0.0075546918,0.0053543444,0.0022334568],"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":[0.0025176415,0.00085822225,0.0106067415,0.0019608226,0.0005257136,0.0022886952,0.0018671451,0.15390594,0.056102354,0.15684466,0.013463741,0.5990584],"study_design_scores_gemma":[0.00022747277,0.00051991164,0.0016631873,0.00033528247,0.00026805594,0.0005056067,0.0004169965,0.6764312,0.038050193,0.26166385,0.01974139,0.0001768519],"about_ca_topic_score_codex":0.009084604,"about_ca_topic_score_gemma":0.00903638,"teacher_disagreement_score":0.009084604,"about_ca_system_score_codex":0.0018145656,"about_ca_system_score_gemma":0.003687441,"threshold_uncertainty_score":0.034694076},"labels":[],"label_agreement":null},{"id":"W28501369","doi":"10.69645/rbcp2852","title":"Copy number variation","year":2009,"lang":"en","type":"article","venue":"˜The œbiomedical & life sciences collection.","topic":"Algorithms and Data Compression","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Variation (astronomy); Copy-number variation; Biology; Evolutionary biology; Genetics; Physics; Gene; Astrophysics; Genome","score_opus":0.015006928146770671,"score_gpt":0.2764960838783242,"score_spread":0.2614891557315535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W28501369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63060635,0.019834865,0.08733474,0.0044463365,0.0026278945,0.0017757084,0.15852472,0.0030035975,0.09184577],"genre_scores_gemma":[0.9313037,0.0018698177,0.020522041,0.0009487594,0.0003005221,0.0011247832,0.024626441,0.00054303673,0.018760877],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99402493,0.0011269045,0.0006475275,0.0020818235,0.0017933452,0.0003254213],"domain_scores_gemma":[0.99315864,0.0036400412,0.0010355534,0.001150084,0.00080585777,0.00020981178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023977014,0.00091648044,0.0012573537,0.0058183237,0.0009660669,0.001828325,0.0011871204,0.001219465,0.034796774],"category_scores_gemma":[0.018219776,0.00034525467,0.0014561518,0.0038281567,0.00091138587,0.0007087823,0.00075291004,0.0011478034,0.003867998],"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":[0.00444372,0.0003816294,0.4765887,0.0017250758,0.003805204,0.007049034,0.0013273793,0.0053553367,0.020965775,0.036239874,0.057270415,0.38484788],"study_design_scores_gemma":[0.00061740936,0.0009388322,0.69768333,0.0010618871,0.0021570409,0.03887112,0.0004213469,0.016241163,0.027386632,0.06685202,0.14734718,0.0004220883],"about_ca_topic_score_codex":0.005632476,"about_ca_topic_score_gemma":0.0038909286,"teacher_disagreement_score":0.034796774,"about_ca_system_score_codex":0.00092461717,"about_ca_system_score_gemma":0.00064292626,"threshold_uncertainty_score":0.1164068},"labels":[],"label_agreement":null},{"id":"W2884379947","doi":"10.1109/dcc.2018.00058","title":"Optimal Single- and Multiple-Tree Almost Instantaneous Variable-to-Fixed Codes","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Prefix; Property (philosophy); Variable (mathematics); Computer science; Prefix code; Trie; Tree (set theory); Constraint (computer-aided design); Algorithm; Theoretical computer science; Mathematics; Data structure; Block code; Combinatorics; Linear code; Decoding methods; Programming language","score_opus":0.0166649014752136,"score_gpt":0.23374944880273066,"score_spread":0.21708454732751706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884379947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015584363,0.00024440474,0.98076665,0.00018037559,0.000075217984,0.000027471839,0.000114162605,0.0003740582,0.0026332706],"genre_scores_gemma":[0.1997685,0.00034701376,0.79568535,0.00016515274,0.00007221232,0.0000757209,0.0003543137,0.0003272564,0.0032045755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910516,0.000202121,0.00007109568,0.00018153724,0.00032142343,0.0001186471],"domain_scores_gemma":[0.9971825,0.0012965455,0.00017259203,0.0008540117,0.00039745693,0.00009682624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082081824,0.00044682532,0.0006456025,0.0008079257,0.0005638852,0.0009880182,0.00093454757,0.0008126558,0.0028524066],"category_scores_gemma":[0.0070366203,0.00032164378,0.00044224842,0.0014500135,0.00097581383,0.002481717,0.0013796298,0.001404526,0.00092479744],"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":[0.0002309153,0.000081901264,0.0014143275,0.00017566902,0.000043311244,0.00021787558,0.0002423087,0.16034427,0.016752169,0.35006216,0.0076517677,0.46278328],"study_design_scores_gemma":[0.000039308536,0.00011492487,0.00042008676,0.00006777141,0.000026522965,0.0005443244,0.00010708316,0.7749171,0.030199999,0.1809218,0.012594121,0.000046975187],"about_ca_topic_score_codex":0.0009674628,"about_ca_topic_score_gemma":0.0021742852,"teacher_disagreement_score":0.0028524066,"about_ca_system_score_codex":0.0005290781,"about_ca_system_score_gemma":0.0013100317,"threshold_uncertainty_score":0.009542286},"labels":[],"label_agreement":null},{"id":"W2884798430","doi":"10.1089/cmb.2018.0068","title":"Dynamic Alignment-Free and Reference-Free Read Compression","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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; Simon Fraser University","funders":"Menzies Centre for Australian Studies, King's College London, University of London","keywords":"Computer science; Free water; Environmental science","score_opus":0.01813697689699842,"score_gpt":0.2940232905158488,"score_spread":0.2758863136188504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884798430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044046145,0.0025977797,0.9361342,0.00042766676,0.0004549104,0.00022771119,0.0014039272,0.009696485,0.005011281],"genre_scores_gemma":[0.20801544,0.0013701427,0.7747545,0.00040808666,0.00023673275,0.00033332483,0.0059056086,0.0010531831,0.007922926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990225,0.00013347605,0.00008399512,0.00022287981,0.00045962824,0.00007756463],"domain_scores_gemma":[0.9978435,0.0006714685,0.00014624062,0.0007188509,0.00056871853,0.00005126689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006554511,0.0010361257,0.00065076014,0.0018118825,0.00046382335,0.0007069532,0.0016927264,0.0009383175,0.0027040218],"category_scores_gemma":[0.0037105705,0.00025609677,0.0006878279,0.001885787,0.0005143846,0.0013963464,0.0009826187,0.0009809157,0.0016041273],"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":[0.000539332,0.00016110127,0.0009797638,0.0004912585,0.00007596558,0.000456298,0.00029868883,0.054580145,0.113124475,0.01287163,0.01657068,0.7998507],"study_design_scores_gemma":[0.00016042675,0.00038908655,0.0018714522,0.000095990516,0.000102940765,0.0020906487,0.00019238619,0.5446744,0.38743111,0.014114869,0.048723795,0.00015281334],"about_ca_topic_score_codex":0.0014992701,"about_ca_topic_score_gemma":0.0019835238,"teacher_disagreement_score":0.0027040218,"about_ca_system_score_codex":0.00043526155,"about_ca_system_score_gemma":0.00081297406,"threshold_uncertainty_score":0.009045839},"labels":[],"label_agreement":null},{"id":"W2886760888","doi":"10.1109/isit.2018.8437665","title":"Individually Optimal Single- and Multiple-Tree Almost Instantaneous Variable-to-Fixed Codes","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Prefix; Computer science; String (physics); Prefix code; Variable (mathematics); Tree (set theory); Dynamic programming; Algorithm; Parsing; Constraint (computer-aided design); Property (philosophy); Trie; Theoretical computer science; Block code; Mathematics; Data structure; Linear code; Combinatorics; Artificial intelligence; Decoding methods; Programming language","score_opus":0.0173720346367076,"score_gpt":0.2329649323319181,"score_spread":0.21559289769521048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886760888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027775493,0.00030578373,0.9666061,0.00016891299,0.000084897205,0.000032843385,0.00013537353,0.00039555924,0.0044950857],"genre_scores_gemma":[0.377149,0.0003921661,0.61726326,0.00016941882,0.000078513294,0.000077546574,0.00035911522,0.00027849028,0.004232503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929,0.00015062127,0.00005076683,0.00016083384,0.00022503434,0.00012274536],"domain_scores_gemma":[0.9981717,0.0008108474,0.00012313717,0.0005473721,0.0002590082,0.00008794077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671539,0.00047333472,0.00064939586,0.0007175985,0.0005564611,0.0008475944,0.0009461165,0.00080436555,0.0028409613],"category_scores_gemma":[0.0046942355,0.00027605917,0.000435434,0.0012705638,0.00089543004,0.0019724278,0.0013488599,0.0012585729,0.0007594654],"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":[0.00026253538,0.00007807867,0.0014160399,0.00015403368,0.000045202047,0.0002426007,0.00020236448,0.24367812,0.016936688,0.31497785,0.0066307564,0.41537574],"study_design_scores_gemma":[0.0000291715,0.0001323582,0.00040326858,0.000053934924,0.000030506466,0.00047786403,0.00008801994,0.83556294,0.021120867,0.1338267,0.008227412,0.000046960307],"about_ca_topic_score_codex":0.00088050676,"about_ca_topic_score_gemma":0.0021847768,"teacher_disagreement_score":0.0028409613,"about_ca_system_score_codex":0.0005310962,"about_ca_system_score_gemma":0.0012406347,"threshold_uncertainty_score":0.009503961},"labels":[],"label_agreement":null},{"id":"W2889833303","doi":"10.1145/3375890","title":"Fully Functional Suffix Trees and Optimal Text Searching in BWT-Runs Bounded Space","year":2020,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Log-log plot; Binary logarithm; Bounded function; Search engine indexing; Space (punctuation); Suffix; Generalized suffix tree; Suffix tree; Suffix array","score_opus":0.03092524817749018,"score_gpt":0.24822707174398864,"score_spread":0.21730182356649846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889833303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120047696,0.0026886517,0.84359443,0.0017793889,0.00022457904,0.00017141837,0.0021344738,0.014049872,0.015309391],"genre_scores_gemma":[0.32933298,0.0009796878,0.6566136,0.0004936987,0.00027945155,0.00036406599,0.0039685057,0.0013879869,0.006580095],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963297,0.00075645285,0.00042707848,0.0008924361,0.0011210503,0.0004732653],"domain_scores_gemma":[0.9916945,0.0041569686,0.0005669447,0.0025599292,0.0007775444,0.00024413144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017322147,0.0008935678,0.0015868292,0.0017172131,0.0011534387,0.0034066185,0.003032583,0.0017431107,0.004700832],"category_scores_gemma":[0.014327141,0.00072198827,0.001149789,0.0047832625,0.0021092542,0.010362448,0.0033331998,0.001988992,0.0031370958],"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":[0.0019939935,0.0003571077,0.0025722045,0.0008752211,0.000106661886,0.0005653216,0.0013755877,0.16308166,0.0398444,0.29760966,0.023489714,0.4681285],"study_design_scores_gemma":[0.00018679418,0.00026940048,0.00054949266,0.0001042275,0.00005400207,0.00048411623,0.00023112539,0.5128637,0.012288331,0.45803377,0.014859993,0.00007506116],"about_ca_topic_score_codex":0.0026889506,"about_ca_topic_score_gemma":0.0033658175,"teacher_disagreement_score":0.004700832,"about_ca_system_score_codex":0.001715449,"about_ca_system_score_gemma":0.0022104143,"threshold_uncertainty_score":0.015725851},"labels":[],"label_agreement":null},{"id":"W2890851695","doi":"10.5539/mas.v12n10p23","title":"Measuring Parallel Performance of Sorting Algorithms","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sorting; Computer science; Sorting algorithm; Parallel computing; sort; Algorithm; Field (mathematics); Mathematics; Database","score_opus":0.0387345257834099,"score_gpt":0.24780960970785385,"score_spread":0.20907508392444396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890851695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91233915,0.0011525437,0.06634417,0.00016692917,0.00016117745,0.00021166846,0.0008212202,0.0033843499,0.015418783],"genre_scores_gemma":[0.9370294,0.0005508251,0.057650413,0.00003471041,0.00005362024,0.0001766466,0.0018916826,0.00032558801,0.0022870605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972299,0.00044678795,0.00031237892,0.00040073006,0.0013343242,0.00027586648],"domain_scores_gemma":[0.9950787,0.0018525146,0.00035528882,0.000802998,0.0017520039,0.00015850693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014056969,0.000708605,0.00048943213,0.0023609172,0.000690948,0.0010260039,0.0007321087,0.0005269425,0.0022871024],"category_scores_gemma":[0.0076456387,0.000254541,0.00038393796,0.00342458,0.00038255876,0.0015800302,0.0005549015,0.0004446664,0.000829347],"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":[0.002887599,0.0011150852,0.058774717,0.0013475395,0.0005778627,0.0003756239,0.00082568295,0.24246001,0.20318611,0.008291669,0.008480835,0.4716773],"study_design_scores_gemma":[0.00017298,0.0026051959,0.049728222,0.00006796345,0.0002461364,0.0006208684,0.000536937,0.6680949,0.25593483,0.006957068,0.014905671,0.0001292219],"about_ca_topic_score_codex":0.0016875917,"about_ca_topic_score_gemma":0.0009077737,"teacher_disagreement_score":0.0023609172,"about_ca_system_score_codex":0.00072732195,"about_ca_system_score_gemma":0.000851721,"threshold_uncertainty_score":0.0076510906},"labels":[],"label_agreement":null},{"id":"W2891585194","doi":"10.48550/arxiv.1906.06172","title":"Deep Learning-Based Decoding of Constrained Sequence Codes","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Decoding methods; Computer science; Convolutional code; Sequential decoding; Algorithm; List decoding; Convolutional neural network; Throughput; Sequence (biology); Concatenated error correction code; Block code; Artificial intelligence; Wireless; Telecommunications","score_opus":0.07426583864467266,"score_gpt":0.20734622515707277,"score_spread":0.13308038651240012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891585194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08352133,0.00054190244,0.90828574,0.0003074087,0.00011392604,0.00004818259,0.00019195133,0.0012362058,0.0057533886],"genre_scores_gemma":[0.83718467,0.00033581306,0.15674148,0.00025070316,0.00003922469,0.00006651981,0.00037386848,0.000103582664,0.004904228],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994974,0.00009265037,0.000034815734,0.00008440548,0.00019916026,0.00009145158],"domain_scores_gemma":[0.9986443,0.0006474075,0.00013632128,0.0001636233,0.00036859963,0.00003980728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056497,0.00055422547,0.00047136866,0.0003728491,0.00027237137,0.00057272805,0.0007200313,0.0006599158,0.0014502283],"category_scores_gemma":[0.003203532,0.00021077933,0.0003267646,0.0004778304,0.0006845813,0.0011704982,0.00067170087,0.0009809728,0.00036215739],"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":[0.00026198933,0.00006325985,0.0012020678,0.00012771288,0.000041465857,0.00021307792,0.00009202815,0.8126152,0.025633404,0.030179488,0.0024353913,0.1271349],"study_design_scores_gemma":[0.0000050693775,0.000023271792,0.00005865008,0.000006109561,0.0000037640598,0.000025753803,0.0000050273284,0.98842955,0.007940731,0.0030526768,0.00044460365,0.0000047607955],"about_ca_topic_score_codex":0.0075209886,"about_ca_topic_score_gemma":0.009514487,"teacher_disagreement_score":0.0075209886,"about_ca_system_score_codex":0.0009540288,"about_ca_system_score_gemma":0.0017605905,"threshold_uncertainty_score":0.014954388},"labels":[],"label_agreement":null},{"id":"W2897193193","doi":"10.1016/j.tcs.2018.10.021","title":"Path queries on functions","year":2018,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico","keywords":"Ackermann function; Combinatorics; Successor cardinal; Element (criminal law); Inverse; Mathematics; Range (aeronautics); Path (computing); Function (biology); Discrete mathematics; Graph; Computer science","score_opus":0.00960591139529451,"score_gpt":0.24773992844400522,"score_spread":0.2381340170487107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897193193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20216979,0.005462445,0.6803957,0.008284636,0.0008894463,0.00047300052,0.0071148546,0.008519204,0.08669083],"genre_scores_gemma":[0.77522427,0.00269478,0.1631532,0.0017621462,0.00070763804,0.0004312018,0.007957407,0.0018513482,0.04621802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99660873,0.0006992087,0.0002214033,0.00064573827,0.001342018,0.00048283214],"domain_scores_gemma":[0.9920379,0.0044036563,0.00026967123,0.0023160714,0.00072537264,0.0002473437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018577246,0.0009833978,0.0013764454,0.0021910071,0.0012891114,0.003946181,0.0016424998,0.0021324423,0.019318426],"category_scores_gemma":[0.011607271,0.0005553973,0.0008329338,0.004412052,0.0023392485,0.012874832,0.004828991,0.003249291,0.003770488],"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":[0.0008720001,0.00011217988,0.0011755617,0.00033036873,0.000044645865,0.00018443656,0.0004123635,0.009077893,0.0039204806,0.79338205,0.03741874,0.15306929],"study_design_scores_gemma":[0.00006308462,0.000087101376,0.0002655055,0.00005378118,0.00003189765,0.00028259764,0.00013266639,0.02997785,0.004069501,0.93763596,0.027376946,0.000023150042],"about_ca_topic_score_codex":0.0011394834,"about_ca_topic_score_gemma":0.000842839,"teacher_disagreement_score":0.019318426,"about_ca_system_score_codex":0.0023640224,"about_ca_system_score_gemma":0.0014889175,"threshold_uncertainty_score":0.064626575},"labels":[],"label_agreement":null},{"id":"W2897972648","doi":"10.4171/msl/12","title":"The algorithmic hardness threshold for continuous random energy models","year":2020,"lang":"en","type":"preprint","venue":"Mathematical Statistics and Learning","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Agence Nationale de la Recherche","keywords":"Parameterized complexity; Energy (signal processing); Combinatorics; Function (biology); Mathematics; Random graph; Discrete mathematics; Hypercube; Graph","score_opus":0.029585909753493303,"score_gpt":0.26395217251459757,"score_spread":0.23436626276110428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897972648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29005164,0.0014212516,0.6555339,0.010747633,0.00022101363,0.00033272343,0.0014649448,0.0021193295,0.038107578],"genre_scores_gemma":[0.9037132,0.0005527505,0.08374644,0.0016079014,0.00036105866,0.000511939,0.0012513588,0.0005005194,0.007754795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960089,0.0013336175,0.00019323679,0.0008649971,0.00089263887,0.0007066532],"domain_scores_gemma":[0.97233325,0.021789009,0.0011407472,0.0032319434,0.00064539624,0.0008595901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002755212,0.0013587311,0.002025053,0.001176413,0.001601164,0.0042642197,0.0039185905,0.003484724,0.008096843],"category_scores_gemma":[0.021054765,0.00090373564,0.0025588826,0.0011481461,0.004590919,0.0098930085,0.004943607,0.0067190705,0.0009790251],"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":[0.00051672844,0.00042417034,0.0026127791,0.0007160893,0.00017741144,0.00034267988,0.00063739816,0.20626976,0.0047880625,0.74906844,0.012471507,0.021974934],"study_design_scores_gemma":[0.0000777726,0.000043705473,0.0002589513,0.000026254223,0.000023500672,0.00009194465,0.0000696549,0.3315813,0.0009268222,0.66532725,0.0015461141,0.00002671509],"about_ca_topic_score_codex":0.001142382,"about_ca_topic_score_gemma":0.0012782607,"teacher_disagreement_score":0.008096843,"about_ca_system_score_codex":0.0026311409,"about_ca_system_score_gemma":0.0020730894,"threshold_uncertainty_score":0.027086616},"labels":[],"label_agreement":null},{"id":"W2898462080","doi":"10.1016/j.jda.2018.09.003","title":"String covering with optimal covers","year":2018,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Combinatorics; Mathematics; Computer science","score_opus":0.009639088027083973,"score_gpt":0.2480819542534558,"score_spread":0.23844286622637184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898462080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2873821,0.0026870845,0.65164745,0.0026246554,0.00052395125,0.00015792192,0.0014967662,0.0019376486,0.051542472],"genre_scores_gemma":[0.8550064,0.0016231551,0.12515737,0.00058484485,0.00050816656,0.0002295564,0.0019522363,0.0005828709,0.014355351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99769235,0.0006377248,0.0001521891,0.00043206004,0.00068971334,0.00039600994],"domain_scores_gemma":[0.9934237,0.00378119,0.00031870144,0.001732297,0.0004174758,0.00032662533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012251181,0.0008924004,0.0015702179,0.0018735388,0.0012310288,0.0026113358,0.0011343467,0.0018631552,0.008117757],"category_scores_gemma":[0.0126175815,0.00076860486,0.0010383828,0.0032596285,0.0014863231,0.0052201105,0.0039272252,0.0020035468,0.0013609438],"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":[0.001129388,0.00022498795,0.002535792,0.00046251915,0.00015505916,0.00067958,0.00042637676,0.16597308,0.008324297,0.5762651,0.024199951,0.21962391],"study_design_scores_gemma":[0.000058994272,0.00012754653,0.0006258399,0.00006140357,0.0000625385,0.0004924653,0.00010147458,0.30943736,0.0046843486,0.6755155,0.008806509,0.000026024863],"about_ca_topic_score_codex":0.000615612,"about_ca_topic_score_gemma":0.00050857617,"teacher_disagreement_score":0.008117757,"about_ca_system_score_codex":0.0010618839,"about_ca_system_score_gemma":0.00087220466,"threshold_uncertainty_score":0.027156651},"labels":[],"label_agreement":null},{"id":"W2898623953","doi":"10.1016/j.tcs.2018.10.033","title":"Off-line and on-line algorithms for closed string factorization","year":2018,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Combinatorics; Mathematics; Factorization; Prefix; Suffix; String (physics); Line (geometry); Algorithm; Integer (computer science); Discrete mathematics; Data structure; Computer science","score_opus":0.033646803485844784,"score_gpt":0.3082231752536396,"score_spread":0.2745763717677948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898623953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01364161,0.00081329106,0.97122306,0.00061095686,0.00027112328,0.00017149128,0.00034002084,0.003690087,0.009238261],"genre_scores_gemma":[0.13076238,0.00065614044,0.8464438,0.00048189846,0.0004377604,0.00037353058,0.00195722,0.0012918897,0.017595472],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99480057,0.0014264977,0.00043893946,0.00089075713,0.0018176817,0.00062557886],"domain_scores_gemma":[0.9862316,0.006482122,0.00055001123,0.0049461746,0.0014050279,0.00038510395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00228466,0.0019773073,0.0019446505,0.002449389,0.001657717,0.0049987943,0.0034872834,0.002976361,0.027670803],"category_scores_gemma":[0.015584121,0.0007729977,0.0016101634,0.0038549954,0.0016704862,0.0088145705,0.0047802464,0.0038630075,0.011121017],"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":[0.0012025437,0.00060499477,0.00087959843,0.00028107088,0.00007044069,0.00018501465,0.00031054704,0.037038114,0.0068668323,0.0871265,0.022631489,0.84280276],"study_design_scores_gemma":[0.0002641849,0.0003411015,0.0004834834,0.00010237135,0.000065906264,0.00064782216,0.00035003154,0.65589005,0.01783529,0.30395308,0.019993063,0.00007361931],"about_ca_topic_score_codex":0.0019311816,"about_ca_topic_score_gemma":0.0034910864,"teacher_disagreement_score":0.027670803,"about_ca_system_score_codex":0.0015090649,"about_ca_system_score_gemma":0.0025153283,"threshold_uncertainty_score":0.09256804},"labels":[],"label_agreement":null},{"id":"W2898677730","doi":"10.5539/mas.v12n11p406","title":"CRUSH: A New Lossless Compression Algorithm","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Algorithm; Huffman coding; Golomb coding; Lossless compression; Entropy encoding; Data compression; Lossy compression; Arithmetic coding; Context-adaptive binary arithmetic coding; Image compression; Artificial intelligence","score_opus":0.017197513408559906,"score_gpt":0.2607266086218073,"score_spread":0.2435290952132474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898677730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011689239,0.0016956315,0.9785985,0.0003284153,0.00019061861,0.000118201104,0.00022210443,0.0028258706,0.00433146],"genre_scores_gemma":[0.13508579,0.0017952413,0.84011394,0.0005059224,0.000288517,0.0002458552,0.0014659608,0.0005090542,0.019989785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99952364,0.00003708829,0.00003154067,0.0000632434,0.00030339122,0.000041050254],"domain_scores_gemma":[0.999587,0.000102028214,0.00004016173,0.0000762673,0.00017309813,0.000021397049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046103288,0.0006491795,0.0005429061,0.001805089,0.00046912674,0.0010351031,0.0011165955,0.0008361074,0.003251363],"category_scores_gemma":[0.0012915651,0.00023909684,0.00043980015,0.0014019668,0.00067624333,0.0018743656,0.0009581192,0.0011872483,0.0016825179],"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":[0.00046545547,0.00007531539,0.0006406309,0.00019512163,0.00005607366,0.00025968908,0.0001485812,0.031053811,0.051588535,0.02812046,0.016509239,0.87088716],"study_design_scores_gemma":[0.00014992076,0.00039867044,0.0009808003,0.00009273614,0.000058807313,0.0016994025,0.0000918041,0.7998383,0.10256174,0.019707145,0.07432774,0.00009297736],"about_ca_topic_score_codex":0.0018521759,"about_ca_topic_score_gemma":0.0013811266,"teacher_disagreement_score":0.003251363,"about_ca_system_score_codex":0.00051059655,"about_ca_system_score_gemma":0.0007113642,"threshold_uncertainty_score":0.010876954},"labels":[],"label_agreement":null},{"id":"W2904368314","doi":"10.1016/j.tcs.2018.10.019","title":"A simple linear-space data structure for constant-time range minimum query","year":2018,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data structure; Range (aeronautics); Simple (philosophy); Range query (database); Set (abstract data type); Mathematics; Linear space; Query optimization; Space (punctuation); Constant (computer programming); Computer science; Discrete mathematics; Algorithm; Sargable; Data mining; Web search query; Search engine; Information retrieval","score_opus":0.01974509309859996,"score_gpt":0.2915802183371953,"score_spread":0.2718351252385953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904368314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06425414,0.0021128615,0.9069362,0.0016380156,0.0005059042,0.0005526023,0.0032273165,0.011465008,0.009307893],"genre_scores_gemma":[0.34957877,0.0005752276,0.6336101,0.00084828085,0.00030982826,0.00065926055,0.003805342,0.00076964457,0.009843548],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99851865,0.0001597321,0.0001764189,0.0002836807,0.00067348307,0.00018808355],"domain_scores_gemma":[0.99707925,0.000519292,0.00021797908,0.001552718,0.0004523209,0.00017850807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008679301,0.0006453223,0.0015877049,0.0015842431,0.0011047439,0.0020153336,0.002790368,0.001091082,0.010341222],"category_scores_gemma":[0.0043746703,0.00054267095,0.00067708973,0.004816783,0.0010380677,0.004596612,0.003922134,0.0015274348,0.0031435008],"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":[0.0028969948,0.0008506981,0.0021728093,0.0010564316,0.00013065636,0.00024061796,0.0006069866,0.03013575,0.06351103,0.14034706,0.06848599,0.6895649],"study_design_scores_gemma":[0.0018439528,0.0024657384,0.0023871877,0.00021162737,0.0003072601,0.0015146281,0.00051644037,0.45310634,0.07029644,0.3465109,0.12046847,0.0003709599],"about_ca_topic_score_codex":0.0017509685,"about_ca_topic_score_gemma":0.0028411124,"teacher_disagreement_score":0.010341222,"about_ca_system_score_codex":0.0014960762,"about_ca_system_score_gemma":0.0021652058,"threshold_uncertainty_score":0.034594834},"labels":[],"label_agreement":null},{"id":"W2905251131","doi":"10.1109/isgteurope.2018.8571649","title":"Modified Differential Golomb Arithmetic Lossless Compression Algorithm for Smart Grid Applications","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Regina","funders":"","keywords":"Lossless compression; Computer science; Golomb coding; Data compression; Algorithm; Lossy compression; Smart grid; Computer data storage; Smart meter; Grid; Transmission (telecommunications); Compression ratio; Real-time computing; Computer engineering; Computer hardware; Image compression; Artificial intelligence; Engineering; Mathematics; Telecommunications","score_opus":0.020492447829941963,"score_gpt":0.2742844412957932,"score_spread":0.25379199346585124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905251131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04713994,0.0020509409,0.94374937,0.0005891543,0.00020850833,0.00010746271,0.00020292809,0.0016531697,0.004298494],"genre_scores_gemma":[0.32811642,0.0013748724,0.66076005,0.0003602949,0.0001870232,0.0001898568,0.0010033703,0.00012629533,0.007881879],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99970776,0.000041063104,0.00001891716,0.000025893336,0.00018646651,0.000019821138],"domain_scores_gemma":[0.99962986,0.00010932259,0.000034724344,0.00006454457,0.00014826482,0.000013292421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003154859,0.00040812834,0.0003392502,0.00072543556,0.00027375482,0.0005547987,0.0006525947,0.00045322563,0.0020410954],"category_scores_gemma":[0.0015652322,0.00010786488,0.00019274322,0.0011417918,0.00025593126,0.0008332156,0.00033355277,0.0005672857,0.00092686247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038985786,0.00011110498,0.00061308075,0.00014928113,0.000028776489,0.00025110564,0.00008451365,0.06322572,0.06491686,0.014447473,0.011707141,0.8440751],"study_design_scores_gemma":[0.000058883357,0.00018125784,0.0012854852,0.000030815107,0.000018603596,0.00057125645,0.00003427349,0.92709285,0.05228008,0.0059972852,0.012420035,0.000029202381],"about_ca_topic_score_codex":0.0014844291,"about_ca_topic_score_gemma":0.0013802522,"teacher_disagreement_score":0.0020410954,"about_ca_system_score_codex":0.00036584854,"about_ca_system_score_gemma":0.0006301482,"threshold_uncertainty_score":0.006828189},"labels":[],"label_agreement":null},{"id":"W2905575949","doi":"10.1093/bioinformatics/bty1015","title":"SPRING: a next-generation compressor for FASTQ data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":91,"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":"National Cancer Institute; University of Illinois at Urbana-Champaign; National Institutes of Health; Sunnybrook Research Institute; Silicon Valley Community Foundation","keywords":"Computer science; Lossless compression; Scalability; Lossy compression; Data compression; Data mining; Redundancy (engineering); Identifier; Compression (physics); Database; Artificial intelligence; Computer network; Operating system","score_opus":0.1701892097079504,"score_gpt":0.3126197987859841,"score_spread":0.14243058907803371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905575949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03717218,0.001932525,0.7046961,0.0020845023,0.0012806546,0.00093226664,0.019589502,0.2201468,0.012165411],"genre_scores_gemma":[0.16683571,0.0014459696,0.7144243,0.0018313781,0.00070378656,0.0019957437,0.06849612,0.014386315,0.029880723],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99819845,0.00016157361,0.00016794253,0.00031195616,0.0010142236,0.00014596805],"domain_scores_gemma":[0.99660695,0.0009193017,0.00018962083,0.000920224,0.001223359,0.00014063029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002101411,0.0016274801,0.0006736658,0.0017276222,0.0012820471,0.0015120462,0.0030153408,0.0011907711,0.02184419],"category_scores_gemma":[0.008034871,0.00059503916,0.0008668639,0.0025093667,0.0011980913,0.0034657235,0.0023743731,0.0018180202,0.009098105],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029308214,0.00030501318,0.004287962,0.0012346874,0.00026627202,0.0007021545,0.0007338182,0.014102874,0.06632976,0.021567788,0.37592146,0.5116174],"study_design_scores_gemma":[0.00095584383,0.000643967,0.0031417296,0.00032352266,0.00013791923,0.0013045961,0.00032122486,0.26977253,0.35615087,0.02458731,0.3423069,0.0003536525],"about_ca_topic_score_codex":0.0030788467,"about_ca_topic_score_gemma":0.0032420333,"teacher_disagreement_score":0.02184419,"about_ca_system_score_codex":0.0010699354,"about_ca_system_score_gemma":0.0016290754,"threshold_uncertainty_score":0.07307607},"labels":[],"label_agreement":null},{"id":"W2908455634","doi":"","title":"Emanation Graph: A New t-Spanner.","year":2018,"lang":"en","type":"article","venue":"Canadian Conference on Computational Geometry","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Spanner; Computer science; Graph; Theoretical computer science; Distributed computing","score_opus":0.033883652390772644,"score_gpt":0.26529704014268607,"score_spread":0.23141338775191342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908455634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040323965,0.0011714279,0.88888675,0.00080045353,0.0007094595,0.00025736465,0.0034271528,0.0029110163,0.061512396],"genre_scores_gemma":[0.27066207,0.002559151,0.64477044,0.0008899511,0.00041763927,0.0004084474,0.010347891,0.002294713,0.067649774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993698,0.00008245904,0.000056922818,0.00022087144,0.00019234054,0.00007770831],"domain_scores_gemma":[0.99905044,0.00016535312,0.00008282915,0.00030986272,0.00023728969,0.00015431504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004303601,0.00076439395,0.0006972944,0.0022011506,0.0009858232,0.0018058281,0.0016881035,0.0011004641,0.021934355],"category_scores_gemma":[0.002001275,0.0003868673,0.00097441644,0.0026807955,0.0009429941,0.0038476398,0.0028792568,0.0018971422,0.006844257],"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":[0.00037652222,0.00019521033,0.00091491017,0.00040515055,0.00006616838,0.0005253411,0.0004259851,0.025171245,0.014472913,0.5398483,0.04365803,0.3739402],"study_design_scores_gemma":[0.00004770476,0.00022054884,0.00087707763,0.00015273882,0.00007440042,0.0014583624,0.0003686964,0.10452121,0.011897338,0.70632565,0.17398739,0.000068967856],"about_ca_topic_score_codex":0.0012611407,"about_ca_topic_score_gemma":0.0016969936,"teacher_disagreement_score":0.021934355,"about_ca_system_score_codex":0.00055380387,"about_ca_system_score_gemma":0.00066973874,"threshold_uncertainty_score":0.07337773},"labels":[],"label_agreement":null},{"id":"W2912383825","doi":"10.1016/j.jda.2012.10.001","title":"Indexing hypertext","year":2012,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Search engine indexing; Hypertext; Graph; Generalization; Theoretical computer science; Information retrieval; World Wide Web; Mathematics","score_opus":0.018523307870755,"score_gpt":0.26859644792830023,"score_spread":0.2500731400575452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912383825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11951122,0.010454915,0.60105395,0.00719096,0.0048368447,0.0017690291,0.041781392,0.023963055,0.18943864],"genre_scores_gemma":[0.466241,0.00777189,0.27400747,0.001296748,0.0020408323,0.0012699452,0.07272007,0.0030524556,0.17159948],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975539,0.0004061572,0.00030318342,0.00028035953,0.0012458467,0.00021044347],"domain_scores_gemma":[0.99340785,0.0011639176,0.0002710176,0.0032533854,0.0015493719,0.000354509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011252745,0.0006549303,0.0013293233,0.008281692,0.0015348421,0.0067919134,0.0013289022,0.0011528379,0.04018693],"category_scores_gemma":[0.009472242,0.0005506195,0.0007045184,0.010563743,0.0011100385,0.008713184,0.0035155052,0.0015923475,0.020874102],"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":[0.0007287676,0.00046943853,0.0025260088,0.000587012,0.000096397736,0.00028713694,0.00035363072,0.005600013,0.016164688,0.11445844,0.13277946,0.725949],"study_design_scores_gemma":[0.0002377136,0.00034672627,0.0033709717,0.00038144874,0.00022847574,0.0014749286,0.00069109135,0.12328401,0.06421448,0.42718795,0.37845993,0.0001221878],"about_ca_topic_score_codex":0.0014055187,"about_ca_topic_score_gemma":0.0017024485,"teacher_disagreement_score":0.04018693,"about_ca_system_score_codex":0.0013212324,"about_ca_system_score_gemma":0.0019883343,"threshold_uncertainty_score":0.1344387},"labels":[],"label_agreement":null},{"id":"W2912772774","doi":"","title":"Proceedings of the 7th ACM SIGPLAN workshop on ERLANG","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Canadian Bank Note Company (Canada)","funders":"","keywords":"Erlang (programming language); Computer science; Session (web analytics); Presentation (obstetrics); Programming language; Functional programming; Code refactoring; Software engineering; Library science; World Wide Web; Software","score_opus":0.03290750175664625,"score_gpt":0.24075587689556707,"score_spread":0.20784837513892082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912772774","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009666967,0.048544087,0.59010124,0.016887324,0.03257456,0.0007364248,0.0035727364,0.016156375,0.28176033],"genre_scores_gemma":[0.06600809,0.052622713,0.3560362,0.004668334,0.008409587,0.001187482,0.016892692,0.010279708,0.4838952],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966852,0.0010079338,0.00042147018,0.00051622343,0.0010040391,0.00036516515],"domain_scores_gemma":[0.99620986,0.0012556915,0.0000932002,0.00093537907,0.0010161203,0.00048973045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047542704,0.0020044146,0.0014023434,0.001982133,0.0013786842,0.006034483,0.0022611378,0.0016016725,0.09421154],"category_scores_gemma":[0.009621458,0.0013860771,0.0015621508,0.0022281087,0.0011380239,0.0055803116,0.003266502,0.005173763,0.036332745],"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":[0.0005690342,0.0003073683,0.0007583121,0.0004972367,0.000069059955,0.00027197087,0.0006709281,0.00553931,0.0025018447,0.06491112,0.5165841,0.4073197],"study_design_scores_gemma":[0.00003793941,0.000050386192,0.0002848209,0.0002806462,0.000034864333,0.00022939821,0.00013386297,0.0054110447,0.0009794246,0.018307636,0.974226,0.000023992867],"about_ca_topic_score_codex":0.0055602323,"about_ca_topic_score_gemma":0.0070285983,"teacher_disagreement_score":0.09421154,"about_ca_system_score_codex":0.001636733,"about_ca_system_score_gemma":0.0036482085,"threshold_uncertainty_score":0.31516904},"labels":[],"label_agreement":null},{"id":"W2913027376","doi":"","title":"Proceedings of the 18th annual conference on Combinatorial Pattern Matching","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Matching (statistics); Computer science; Mathematics; Statistics","score_opus":0.013326536666957609,"score_gpt":0.24508293462422773,"score_spread":0.23175639795727013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913027376","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030786684,0.023084164,0.7311737,0.012017055,0.033919003,0.00043217832,0.0026531783,0.0033718545,0.16256227],"genre_scores_gemma":[0.19537431,0.024464903,0.5075075,0.0030800865,0.009850491,0.0005332566,0.013266995,0.002190012,0.24373251],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859446,0.000372001,0.00012800553,0.0002668742,0.000493139,0.00014553175],"domain_scores_gemma":[0.9970796,0.00087117724,0.00011064274,0.00097587,0.00067949947,0.00028314735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018690857,0.0009308685,0.002197508,0.0019418484,0.0010958762,0.004614487,0.0017920688,0.0010236684,0.044457994],"category_scores_gemma":[0.005721625,0.00048004644,0.00121438,0.002669614,0.0009652776,0.0030224763,0.0017281718,0.0024671708,0.013481677],"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":[0.0007387829,0.0005130951,0.0015675126,0.00045245668,0.00029076982,0.00018281715,0.00012439398,0.0073903347,0.005764924,0.067486264,0.27205104,0.6434376],"study_design_scores_gemma":[0.00016920672,0.00029709123,0.0023080541,0.00030773616,0.00028456125,0.0011396119,0.00020820684,0.12841041,0.013136482,0.22471508,0.62894887,0.0000746987],"about_ca_topic_score_codex":0.001382359,"about_ca_topic_score_gemma":0.0028008486,"teacher_disagreement_score":0.044457994,"about_ca_system_score_codex":0.0010161725,"about_ca_system_score_gemma":0.0016706572,"threshold_uncertainty_score":0.14872682},"labels":[],"label_agreement":null},{"id":"W2913061818","doi":"10.1016/j.tcs.2019.08.005","title":"Refining the r-index","year":2019,"lang":"en","type":"preprint","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; Japan Society for the Promotion of Science","keywords":"Index (typography); Computer science; Parsing; Matching (statistics); Lemma (botany); Product (mathematics); Data mining; Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Statistics; Programming language; Biology","score_opus":0.014765413942284405,"score_gpt":0.2647630129646452,"score_spread":0.24999759902236082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913061818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057168253,0.005346621,0.84691536,0.003556373,0.001421861,0.00017137991,0.0008059629,0.0018512439,0.08276293],"genre_scores_gemma":[0.52271044,0.0032912537,0.4357877,0.0021577973,0.0024958076,0.0002970928,0.0015241725,0.0020556392,0.029680137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934034,0.0023493252,0.00052088045,0.0012511482,0.0019540666,0.00052117807],"domain_scores_gemma":[0.98066163,0.007280044,0.0009510822,0.0073943287,0.0031896373,0.0005232412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054894253,0.0011524458,0.0019403212,0.0043954463,0.0017425184,0.0051518455,0.002503444,0.002193115,0.011222406],"category_scores_gemma":[0.03274025,0.0005885617,0.0009436601,0.0032674833,0.0033118718,0.009722671,0.0057970523,0.0036110173,0.0070532043],"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":[0.00045391207,0.00008759081,0.0010529237,0.00022155035,0.00003788263,0.00015135201,0.0002508374,0.0094946185,0.0066700303,0.81950045,0.012647334,0.14943156],"study_design_scores_gemma":[0.000055475462,0.00015062345,0.00035257725,0.00011691086,0.000036968933,0.00040526438,0.00010347914,0.08246705,0.0077947676,0.87932587,0.02913786,0.00005310166],"about_ca_topic_score_codex":0.00097243965,"about_ca_topic_score_gemma":0.0010016522,"teacher_disagreement_score":0.011222406,"about_ca_system_score_codex":0.0017022946,"about_ca_system_score_gemma":0.0017333373,"threshold_uncertainty_score":0.03754264},"labels":[],"label_agreement":null},{"id":"W2914113942","doi":"10.3166/isi.23.6.73-85","title":"Opti-SW: An improved gene sequence alignment algorithm","year":2018,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequence (biology); Computational biology; Gene; Alignment-free sequence analysis; Algorithm; Multiple sequence alignment; Sequence alignment; Computer science; Biology; Genetics; Peptide sequence","score_opus":0.03294622218731524,"score_gpt":0.27078059334643506,"score_spread":0.23783437115911982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914113942","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016445268,0.0005541677,0.9577851,0.00016549829,0.00025631874,0.0001273474,0.0014297661,0.021504965,0.001731643],"genre_scores_gemma":[0.021585053,0.00021338894,0.9692947,0.0001660688,0.00006039772,0.0002446257,0.0034621023,0.00168306,0.0032905939],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992817,0.0001297193,0.00007286218,0.00019001009,0.00026529343,0.00006043656],"domain_scores_gemma":[0.99934644,0.00017065936,0.00004741752,0.00020019172,0.0002004244,0.00003486536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076989725,0.0015106918,0.0014071998,0.001737667,0.0008332042,0.001093717,0.0019080807,0.0010096374,0.0060486486],"category_scores_gemma":[0.0023565197,0.00060666783,0.0011202584,0.002593824,0.00045842148,0.0014751407,0.0014309045,0.0018412874,0.004666405],"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":[0.0009694427,0.00024450835,0.0013758279,0.00043007685,0.00016557427,0.00016501213,0.00013098777,0.017716233,0.061411627,0.0051317276,0.028211875,0.8840471],"study_design_scores_gemma":[0.00044132367,0.0005544979,0.0027977875,0.000080690734,0.00020713858,0.00074185827,0.00010038188,0.8043429,0.10098241,0.019468838,0.070177704,0.00010442018],"about_ca_topic_score_codex":0.0016121246,"about_ca_topic_score_gemma":0.0032650586,"teacher_disagreement_score":0.0060486486,"about_ca_system_score_codex":0.00048602812,"about_ca_system_score_gemma":0.0015501825,"threshold_uncertainty_score":0.020234764},"labels":[],"label_agreement":null},{"id":"W2914993520","doi":"10.1016/s0304-3975(02)00589-3","title":"Euclidean strings","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Victoria","funders":"","keywords":"Combinatorics; Mathematics; Euclidean geometry; String (physics); Euclidean algorithm; Euclidean domain; Discrete mathematics; Graph; Prime (order theory); Euclidean distance matrix; Euclidean space","score_opus":0.008417326049985073,"score_gpt":0.23900861291711745,"score_spread":0.23059128686713237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914993520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052435502,0.0056243315,0.5292533,0.004026788,0.0039807684,0.00024151028,0.0060388283,0.0030287628,0.39537024],"genre_scores_gemma":[0.43000054,0.0046944157,0.24157767,0.0028331126,0.0016725658,0.0004416854,0.0097420355,0.001865382,0.3071727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983631,0.000320926,0.00013648605,0.00040264847,0.00060531107,0.00017153964],"domain_scores_gemma":[0.99867755,0.00034178174,0.000121383746,0.00045284056,0.00029640444,0.000109984496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056577806,0.00089109194,0.00091214513,0.0024541775,0.0011361062,0.0028874427,0.0011699297,0.001642927,0.0523133],"category_scores_gemma":[0.00456998,0.0003485599,0.00065999164,0.003488566,0.0013322363,0.0039600483,0.0024512317,0.002302281,0.02179417],"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":[0.00018328938,0.000034354423,0.0001647893,0.00017275453,0.000016835522,0.000104182865,0.0000844208,0.0017122317,0.0023486875,0.8487523,0.021865498,0.12456055],"study_design_scores_gemma":[0.00004331446,0.00009727962,0.00033219485,0.00013336857,0.000029172395,0.000640055,0.00011482406,0.008798864,0.008137259,0.7829262,0.19869979,0.000047735866],"about_ca_topic_score_codex":0.0002521843,"about_ca_topic_score_gemma":0.00024266858,"teacher_disagreement_score":0.0523133,"about_ca_system_score_codex":0.000834306,"about_ca_system_score_gemma":0.0005597365,"threshold_uncertainty_score":0.17500544},"labels":[],"label_agreement":null},{"id":"W2921281695","doi":"10.4230/lipics.approx-random.2019.56","title":"String Matching: Communication, Circuits, and Learning","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"String (physics); Matching (statistics); Computer science; Electronic circuit; Physics; Mathematics; Electrical engineering; Theoretical physics; Engineering","score_opus":0.07923437772593701,"score_gpt":0.20414089289749307,"score_spread":0.12490651517155606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921281695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112075634,0.012540794,0.809431,0.021520458,0.0006481301,0.0003441323,0.0018404596,0.0018660869,0.03973318],"genre_scores_gemma":[0.7626075,0.0075151995,0.20580551,0.0022505182,0.0015877651,0.0007475588,0.0023430951,0.0004667297,0.016676148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949999,0.0015752794,0.00024027507,0.0013054487,0.0013023431,0.0005766786],"domain_scores_gemma":[0.9724648,0.021918764,0.001390817,0.0029782953,0.0007707581,0.0004765141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029268737,0.0015799083,0.0019778598,0.0016839331,0.001825877,0.005870529,0.0032625534,0.0043946872,0.009388873],"category_scores_gemma":[0.026025068,0.0008697929,0.0013133585,0.005111813,0.005109895,0.014894017,0.003314347,0.005650931,0.0014263578],"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":[0.00055914035,0.00026287406,0.0019539658,0.000610753,0.000102527534,0.00015941731,0.00023822459,0.191621,0.0031680267,0.61518914,0.01755506,0.16857979],"study_design_scores_gemma":[0.00004809207,0.00003997576,0.00032969928,0.000057745663,0.000020099773,0.00009444299,0.000057057237,0.2242433,0.002372934,0.76842207,0.0042894077,0.000025173862],"about_ca_topic_score_codex":0.0028910516,"about_ca_topic_score_gemma":0.0019722418,"teacher_disagreement_score":0.009388873,"about_ca_system_score_codex":0.0062134024,"about_ca_system_score_gemma":0.0029021946,"threshold_uncertainty_score":0.045081556},"labels":[],"label_agreement":null},{"id":"W2921895451","doi":"10.23919/isita.2018.8664360","title":"Compression by Substring Enumeration with a Finite Alphabet Using Sorting","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"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":"Substring; Lexicographical order; Upper and lower bounds; Enumeration; Sorting; Algorithm; Code word; Encoding (memory); Computer science; Compression (physics); Alphabet; Data compression; Combinatorics; Encoder; Pooling; Mathematics; Order (exchange); Data structure; Decoding methods; Artificial intelligence; Statistics","score_opus":0.018831673094846364,"score_gpt":0.2555191560520908,"score_spread":0.23668748295724443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921895451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05459625,0.0005990191,0.93994504,0.00017837342,0.00006615823,0.000106519656,0.00020391779,0.0014885894,0.0028161288],"genre_scores_gemma":[0.18028359,0.0003897078,0.8155799,0.00016340468,0.000048786533,0.00012077259,0.0007130518,0.00015381486,0.002547026],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989504,0.00016272561,0.00014634812,0.00017790559,0.00047615907,0.00008643265],"domain_scores_gemma":[0.99750656,0.0011438219,0.00018357627,0.00067594985,0.00044061264,0.000049468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069824664,0.00050256663,0.00087676203,0.0022360128,0.0005348498,0.0009328577,0.0011186934,0.00056673633,0.0013363429],"category_scores_gemma":[0.0039221267,0.00023343903,0.00047638846,0.0030480246,0.0006784122,0.0020290927,0.0007651125,0.0007906269,0.00046019704],"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":[0.00057418144,0.00015907749,0.002006518,0.00025914688,0.000047616588,0.00026104716,0.00019067463,0.061153002,0.05964331,0.038354937,0.0025500965,0.8348004],"study_design_scores_gemma":[0.00012279468,0.00032025378,0.00199883,0.000100728226,0.000069415735,0.0009996574,0.0001670522,0.7529362,0.17359366,0.05083613,0.018776651,0.000078646175],"about_ca_topic_score_codex":0.0019138705,"about_ca_topic_score_gemma":0.0024703976,"teacher_disagreement_score":0.0022360128,"about_ca_system_score_codex":0.0007601934,"about_ca_system_score_gemma":0.0013852293,"threshold_uncertainty_score":0.005515635},"labels":[],"label_agreement":null},{"id":"W2937143200","doi":"10.1109/ecai.2018.8678935","title":"The Performances of the Fixed Constraints Transform Applied in Text Compression Experimental Results and Comparisons","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Fundação para a Ciência e a Tecnologia","keywords":"Lossless compression; Computer science; Compression (physics); Data compression; Word (group theory); Phrase; Compression ratio; Data compression ratio; Search engine indexing; Algorithm; Binary number; Image compression; Encoding (memory); Speech recognition; Arithmetic; Artificial intelligence; Mathematics; Image (mathematics); Image processing","score_opus":0.015345264171151942,"score_gpt":0.2561478140732352,"score_spread":0.24080254990208327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937143200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9071118,0.0040650805,0.06838841,0.00024369695,0.00023217806,0.00026984545,0.0015659297,0.0054838588,0.01263918],"genre_scores_gemma":[0.90970063,0.0016463728,0.07816956,0.00007394783,0.00006756633,0.00017581016,0.00407306,0.0005074528,0.005585544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842083,0.00022594086,0.0001831303,0.00022645795,0.0007600159,0.00018356166],"domain_scores_gemma":[0.9973801,0.0012744942,0.00013560834,0.0002626433,0.00087096496,0.000076218756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011428811,0.000979027,0.00068862806,0.0019091517,0.00048157765,0.0009206284,0.0008597333,0.0007962791,0.003508858],"category_scores_gemma":[0.005959529,0.00016617974,0.0004016332,0.0026438334,0.00052173476,0.0010504229,0.000548503,0.000400056,0.0010513354],"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":[0.005338265,0.00069148623,0.0047552944,0.0014529437,0.00019835401,0.0006659036,0.00054690085,0.10550039,0.22947815,0.0018161898,0.0041677426,0.64538836],"study_design_scores_gemma":[0.0001891137,0.0029053902,0.01060538,0.00008683535,0.00018141467,0.000641412,0.00047089747,0.33746862,0.639773,0.00082952296,0.006752584,0.00009576727],"about_ca_topic_score_codex":0.004439401,"about_ca_topic_score_gemma":0.0024073904,"teacher_disagreement_score":0.004439401,"about_ca_system_score_codex":0.00056221936,"about_ca_system_score_gemma":0.0004987419,"threshold_uncertainty_score":0.0117383},"labels":[],"label_agreement":null},{"id":"W2944281135","doi":"10.4230/lipics.ccc.2023.4","title":"Improved Algorithms for Alternating Matrix Space Isometry: From Theory to Practice","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"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; University of Toronto","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Hypergraph; Isomorphism (crystallography); Graph isomorphism; Generalization; Mathematics; Group (periodic table); Combinatorics; Quotient; Subgraph isomorphism problem; Algorithm; Graph; Algebra over a field; Discrete mathematics; Pure mathematics","score_opus":0.051372254190628776,"score_gpt":0.24163309270872463,"score_spread":0.19026083851809586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944281135","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012764668,0.0003426737,0.976324,0.0005027254,0.000086919965,0.000115991636,0.00009463243,0.003716307,0.0060521187],"genre_scores_gemma":[0.1732877,0.00036228026,0.819005,0.0003910687,0.00021260596,0.00028250035,0.0005840609,0.0010884869,0.004786357],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951199,0.0012781667,0.00040714335,0.0010954301,0.0017377082,0.00036167577],"domain_scores_gemma":[0.9888737,0.0050511775,0.00044001077,0.004296964,0.0010853508,0.00025268318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031864978,0.0011920609,0.0010931054,0.0025243498,0.0010355248,0.0031400376,0.0026164663,0.0017934351,0.01200472],"category_scores_gemma":[0.020830724,0.00062807096,0.001287807,0.00279574,0.0022049178,0.010945012,0.0043724612,0.0035629661,0.0048272107],"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":[0.00032001408,0.000215377,0.0020363345,0.00029164637,0.00006264452,0.000094968396,0.0004655512,0.021327596,0.008633438,0.32781416,0.0094020115,0.6293363],"study_design_scores_gemma":[0.000117547715,0.0001625508,0.00041041523,0.00007025168,0.00003938951,0.0003615452,0.00023328923,0.2881534,0.016822372,0.67632985,0.017243234,0.000056102326],"about_ca_topic_score_codex":0.0011089282,"about_ca_topic_score_gemma":0.0015277083,"teacher_disagreement_score":0.01200472,"about_ca_system_score_codex":0.0016351824,"about_ca_system_score_gemma":0.001723548,"threshold_uncertainty_score":0.04015982},"labels":[],"label_agreement":null},{"id":"W2944913135","doi":"10.1155/2019/3185137","title":"Low-Complexity Scalable Architectures for Parallel Computation of Similarity Measures","year":2019,"lang":"en","type":"article","venue":"Scientific Programming","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Scalability; Computation; Flexibility (engineering); Scheduling (production processes); Curse of dimensionality; Parallel computing; Similarity (geometry); Theoretical computer science; Algorithm; Artificial intelligence; Mathematics; Mathematical optimization","score_opus":0.039559908593060425,"score_gpt":0.2835737805798486,"score_spread":0.2440138719867882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944913135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09758263,0.0013430523,0.88977706,0.00024835987,0.00009374902,0.00012549157,0.00016934007,0.0022748492,0.008385567],"genre_scores_gemma":[0.51027614,0.0009055729,0.48301584,0.00012768774,0.00007583177,0.00037032444,0.0006432921,0.00011308452,0.0044721873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997639,0.00004846627,0.000020139494,0.000044569493,0.00008724286,0.000035684],"domain_scores_gemma":[0.99954873,0.00017787688,0.00005374673,0.000087300315,0.000114110015,0.000018211325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026965418,0.00049225247,0.00027837735,0.0006651401,0.00029849357,0.00064893335,0.0011475191,0.00030345935,0.0038568361],"category_scores_gemma":[0.0010302102,0.00021702421,0.0003122137,0.0012422145,0.0002288012,0.0009921493,0.00045726166,0.0005005653,0.0009604138],"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":[0.0005164771,0.00026166768,0.0024320153,0.0007899635,0.00013963539,0.0003736471,0.00023136567,0.22105442,0.14137954,0.04925045,0.013501973,0.57006896],"study_design_scores_gemma":[0.00008225916,0.0004700399,0.001166406,0.000037342616,0.000059348982,0.00025178192,0.00010159394,0.92102545,0.045267437,0.01908513,0.0124297645,0.00002337298],"about_ca_topic_score_codex":0.00067875854,"about_ca_topic_score_gemma":0.0015941656,"teacher_disagreement_score":0.0038568361,"about_ca_system_score_codex":0.00046727038,"about_ca_system_score_gemma":0.0006969081,"threshold_uncertainty_score":0.012902379},"labels":[],"label_agreement":null},{"id":"W2945709631","doi":"10.1109/jcn.2019.000021","title":"Error detection algorithm for Lempel-Ziv-77 compressed data","year":2019,"lang":"en","type":"article","venue":"Journal of Communications and Networks","topic":"Algorithms and Data Compression","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":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Computer science; Parity bit; Algorithm; Checksum; Hamming code; Error detection and correction; Cyclic redundancy check; Bit error rate; Data compression; Redundancy (engineering); Decoding methods; Block code","score_opus":0.0480410243959005,"score_gpt":0.31154297135214476,"score_spread":0.26350194695624424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945709631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036064506,0.0005753165,0.96028084,0.00025899353,0.000081235135,0.00013282201,0.00013676,0.0011709462,0.0012986087],"genre_scores_gemma":[0.31677774,0.0005097551,0.67780167,0.00031344587,0.00013946727,0.00026630628,0.0007617712,0.00008458471,0.0033451817],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986072,0.00019455726,0.00010906576,0.00015660601,0.00082056265,0.00011197571],"domain_scores_gemma":[0.9981421,0.00065665017,0.00027541033,0.00027387234,0.0005996315,0.00005232162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010887956,0.0005844184,0.0007070046,0.0018328723,0.00050488475,0.00079395156,0.0011912232,0.0008629962,0.0014463133],"category_scores_gemma":[0.0053202487,0.00014608153,0.00030441064,0.0012029267,0.0006110534,0.0014946545,0.0010290777,0.000829601,0.00078584714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010909725,0.00016080048,0.0029436038,0.0002701369,0.00007806066,0.0004692154,0.00031840408,0.074920155,0.07956589,0.03685603,0.0054954235,0.79783136],"study_design_scores_gemma":[0.000090667374,0.00022157705,0.0010048754,0.00004790633,0.000029561754,0.00089324435,0.00009458842,0.8748,0.108338475,0.00752228,0.0069055906,0.00005117155],"about_ca_topic_score_codex":0.0015357111,"about_ca_topic_score_gemma":0.0011668047,"teacher_disagreement_score":0.0018328723,"about_ca_system_score_codex":0.00081107527,"about_ca_system_score_gemma":0.0012874521,"threshold_uncertainty_score":0.0058847666},"labels":[],"label_agreement":null},{"id":"W2946681874","doi":"10.1080/17459737.2018.1542055","title":"Music and combinatorics on words: a historical survey","year":2018,"lang":"en","type":"article","venue":"Journal of Mathematics and Music","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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":"","keywords":"Combinatorics on words; Combinatorics; Computer science; Mathematics; Word (group theory)","score_opus":0.0516733048610107,"score_gpt":0.25621268360068206,"score_spread":0.20453937873967137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946681874","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055586947,0.866356,0.021005921,0.005794845,0.002294146,0.00002492082,0.00024315374,0.000101833815,0.09862061],"genre_scores_gemma":[0.10315572,0.8433276,0.013375338,0.0039046549,0.010796346,0.00008902226,0.00055578776,0.00022253983,0.024573062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989599,0.0002753509,0.00011542197,0.00021943991,0.0003298383,0.0001000426],"domain_scores_gemma":[0.9969214,0.002332737,0.00010697811,0.00015008866,0.00038802496,0.00010075698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011563975,0.00080584054,0.0012386739,0.005760621,0.001873982,0.004402938,0.0009140866,0.0014918247,0.009229257],"category_scores_gemma":[0.0041740425,0.00064799737,0.0005634661,0.010524184,0.0061021764,0.010028529,0.0017945383,0.0030973444,0.0031824382],"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":[0.0001275232,0.00007084508,0.00086620485,0.002445461,0.00004890411,0.00015809402,0.0009770232,0.0015447515,0.00057999213,0.71452373,0.030056464,0.24860102],"study_design_scores_gemma":[0.00001641746,0.000077051685,0.0014285517,0.0009161737,0.00001915219,0.0006254373,0.00039328737,0.0010288025,0.0003791138,0.30465007,0.6904091,0.00005683993],"about_ca_topic_score_codex":0.003006369,"about_ca_topic_score_gemma":0.0021539028,"teacher_disagreement_score":0.009229257,"about_ca_system_score_codex":0.0026561199,"about_ca_system_score_gemma":0.0013582684,"threshold_uncertainty_score":0.030874908},"labels":[],"label_agreement":null},{"id":"W2948863035","doi":"10.1109/access.2019.2920917","title":"Parallel Multidimensional Lookahead Sorting Algorithm","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Algorithms and Data Compression","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 Victoria","funders":"","keywords":"Computer science; Speedup; Parallel computing; Overhead (engineering); Sorting; Sorting algorithm; Algorithm; Locality; Locality of reference; Parallel algorithm; CPU cache; Cache-oblivious algorithm; Cache; Cache algorithms","score_opus":0.024101098030254866,"score_gpt":0.2965552075192603,"score_spread":0.27245410948900545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948863035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01335485,0.00047336577,0.9781415,0.00020978412,0.00018627579,0.00011555444,0.0001798686,0.0020112502,0.0053275954],"genre_scores_gemma":[0.117692456,0.00036234313,0.8712598,0.00025886405,0.00008456175,0.00019426948,0.00083149655,0.00018008005,0.009136162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995683,0.000048234237,0.000041194333,0.00007651978,0.00022107695,0.000044642482],"domain_scores_gemma":[0.9997248,0.000043978504,0.000021969685,0.000070179136,0.00011515037,0.00002398241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028044643,0.00040305653,0.0006625323,0.0010025483,0.0007797668,0.0009755433,0.0012088502,0.0005648289,0.0049644965],"category_scores_gemma":[0.0006393919,0.00024443035,0.00049010955,0.0012172092,0.00039657086,0.0011309911,0.0009873201,0.000728571,0.0017604355],"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":[0.0006846079,0.0001821342,0.0010791826,0.00024262465,0.00007777324,0.00025493593,0.00015902489,0.10585198,0.052493487,0.048377838,0.018067181,0.7725292],"study_design_scores_gemma":[0.00014512941,0.00021043392,0.0004969107,0.000032853517,0.00003955554,0.0004990516,0.00005666534,0.8843667,0.03908919,0.026059952,0.048943978,0.000059564347],"about_ca_topic_score_codex":0.0013439672,"about_ca_topic_score_gemma":0.0018127216,"teacher_disagreement_score":0.0049644965,"about_ca_system_score_codex":0.00056371134,"about_ca_system_score_gemma":0.0013321401,"threshold_uncertainty_score":0.01660788},"labels":[],"label_agreement":null},{"id":"W2949137682","doi":"10.48550/arxiv.1203.6233","title":"Information Theory of DNA Shotgun Sequencing","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; DNA sequencing; Sequence (biology); Sequencing by ligation; k-mer; Algorithm; Hybrid genome assembly; DNA; Sequence assembly; Computational biology; Computer science; Biology; Genetics; Base sequence; Genomic library; Gene","score_opus":0.07011755826983199,"score_gpt":0.18107353538634283,"score_spread":0.11095597711651084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949137682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00828453,0.008953434,0.963685,0.0018525303,0.00036416113,0.00008249155,0.0006421634,0.00027590382,0.015859729],"genre_scores_gemma":[0.5824299,0.030880738,0.35809714,0.002799621,0.0030280591,0.0012258745,0.0023748872,0.0004031827,0.018760687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950846,0.0019502632,0.00029465975,0.0005711878,0.0017818435,0.00031748033],"domain_scores_gemma":[0.9817926,0.014378587,0.0007206444,0.0013420056,0.0015213544,0.00024482262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055863243,0.0010962678,0.001960788,0.0032075301,0.0008549323,0.003513034,0.0023418998,0.0024394,0.002878118],"category_scores_gemma":[0.020559201,0.000673401,0.0011517708,0.0028858588,0.0038318464,0.0044818185,0.0021370486,0.0032838883,0.0011521874],"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":[0.000040201154,0.000021969126,0.0003466844,0.00036163136,0.000041994826,0.00012885698,0.00011145868,0.07199891,0.0008241814,0.90499043,0.0029241804,0.018209536],"study_design_scores_gemma":[0.000009493695,0.000022223134,0.00014435191,0.00006428747,0.000009937377,0.00007443941,0.000019478368,0.15309618,0.00034789406,0.8427301,0.0034568997,0.000024798625],"about_ca_topic_score_codex":0.0018969995,"about_ca_topic_score_gemma":0.00056496,"teacher_disagreement_score":0.0055863243,"about_ca_system_score_codex":0.003015447,"about_ca_system_score_gemma":0.0017053621,"threshold_uncertainty_score":0.029543698},"labels":[],"label_agreement":null},{"id":"W2949366051","doi":"10.1002/spe.2402","title":"Consistently faster and smaller compressed bitmaps with Roaring","year":2016,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital; Université TÉLUQ","funders":"","keywords":"Bitmap; Uncompressed video; Computer science; SPARK (programming language); Computer graphics (images); Data compression; Compression (physics); Algorithm; Artificial intelligence; Materials science","score_opus":0.014158067012897405,"score_gpt":0.2441551405037744,"score_spread":0.229997073490877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949366051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11063614,0.0040844535,0.8159954,0.0013877555,0.0008378996,0.00029639294,0.0017404039,0.04341338,0.02160822],"genre_scores_gemma":[0.3288226,0.0011797633,0.64630085,0.0009753216,0.00026260127,0.00036816925,0.004595901,0.0038021028,0.013692774],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838877,0.0001583648,0.00019678372,0.00022628164,0.0008997459,0.00013010952],"domain_scores_gemma":[0.9950659,0.0013401654,0.0003260611,0.001848737,0.0012891121,0.0001299413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091919623,0.0007923039,0.00074316695,0.0014838765,0.0005417644,0.0022366885,0.0018098422,0.0007863112,0.007435939],"category_scores_gemma":[0.007661787,0.00040653316,0.00054696685,0.0037925886,0.00079435855,0.0051552244,0.0019312449,0.0012539959,0.003797281],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00104944,0.00022246515,0.0022913755,0.00063790975,0.00011752039,0.00037101773,0.0008289182,0.024196604,0.0931358,0.032871455,0.038442623,0.8058347],"study_design_scores_gemma":[0.0002336895,0.0006896112,0.0034779776,0.0002738435,0.0001522546,0.0016775462,0.00072650873,0.33032694,0.44171757,0.045993574,0.17438942,0.00034107885],"about_ca_topic_score_codex":0.0012553995,"about_ca_topic_score_gemma":0.0013744372,"teacher_disagreement_score":0.007435939,"about_ca_system_score_codex":0.0005910945,"about_ca_system_score_gemma":0.00065381645,"threshold_uncertainty_score":0.0248757},"labels":[],"label_agreement":null},{"id":"W2949514071","doi":"10.48550/arxiv.1112.3323","title":"Independence of Tabulation-Based Hash Classes","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Calgary","funders":"","keywords":"Hash function; Mathematics; Double hashing; Pairwise independence; Discrete mathematics; Independence (probability theory); Characterization (materials science); Perfect hash function; Combinatorics; Random variable; Computer science; Hash table; Multivariate random variable; Statistics","score_opus":0.09245499738779081,"score_gpt":0.19218178935904834,"score_spread":0.09972679197125753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949514071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40925762,0.00039196652,0.5619743,0.0009581011,0.00007730588,0.00042494154,0.0015422518,0.001471944,0.023901556],"genre_scores_gemma":[0.94959056,0.0001725959,0.04333753,0.00022421278,0.00011214601,0.00031528465,0.0012875217,0.00022623049,0.004733956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895382,0.0019468351,0.0009038647,0.0019252807,0.0037884624,0.0018974051],"domain_scores_gemma":[0.95112264,0.025263565,0.0039787353,0.013909499,0.0038904396,0.0018351182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044321697,0.0007115866,0.0014953293,0.0015493747,0.0022740327,0.0040660594,0.0029993996,0.001402075,0.008283145],"category_scores_gemma":[0.03227071,0.0013077086,0.0014780245,0.0019123472,0.003733183,0.009664382,0.005798537,0.004334353,0.0021787372],"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":[0.0036382198,0.0005128413,0.019315954,0.0005120552,0.00017896727,0.0004695832,0.0012673573,0.05484411,0.031864118,0.75871944,0.006533094,0.12214427],"study_design_scores_gemma":[0.00035800494,0.0005834645,0.0062653967,0.00009295844,0.00021196694,0.0018088534,0.00033746343,0.32098845,0.08266836,0.5694985,0.016972277,0.00021437352],"about_ca_topic_score_codex":0.00047463682,"about_ca_topic_score_gemma":0.00038977305,"teacher_disagreement_score":0.008283145,"about_ca_system_score_codex":0.0022914284,"about_ca_system_score_gemma":0.0021657993,"threshold_uncertainty_score":0.027709842},"labels":[],"label_agreement":null},{"id":"W2949736060","doi":"10.1109/icde.2019.00107","title":"Multi-Dimensional Genomic Data Management for Region-Preserving Operations","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Banting and Best Diabetes Centre, University of Toronto","keywords":"Computer science; Context (archaeology); SPARK (programming language); Big data; Process (computing); Data mining; Data management; Query optimization; Relational database; Theoretical computer science; Programming language","score_opus":0.06795615948338135,"score_gpt":0.29914481272950405,"score_spread":0.2311886532461227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949736060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009094449,0.0004489677,0.97369826,0.000423434,0.00009427402,0.00014824442,0.0013605152,0.013007949,0.0017239668],"genre_scores_gemma":[0.12779228,0.00050087855,0.8610803,0.00062055496,0.00013184386,0.00029258733,0.005034013,0.0021912358,0.0023563835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99346983,0.0011773786,0.001293626,0.001454272,0.0022190167,0.00038587017],"domain_scores_gemma":[0.99082667,0.0027004543,0.0006495759,0.004433085,0.0011291845,0.00026111325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065179463,0.0008556507,0.0009780653,0.0020252774,0.00092404743,0.0045204894,0.0036615506,0.0009806985,0.0030430183],"category_scores_gemma":[0.011784877,0.0006735772,0.001981207,0.00429111,0.0016038716,0.008024047,0.0060092867,0.002000026,0.0014062003],"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":[0.001617501,0.00034005792,0.010675281,0.0015374548,0.0003843503,0.0016312028,0.0038814733,0.052090403,0.061285853,0.38702866,0.040398438,0.4391293],"study_design_scores_gemma":[0.00025388921,0.00030531568,0.0023764193,0.00025673822,0.00023109227,0.0017397732,0.0007987543,0.34268874,0.12871271,0.2508873,0.27149153,0.00025770473],"about_ca_topic_score_codex":0.0027357135,"about_ca_topic_score_gemma":0.0023674075,"teacher_disagreement_score":0.0065179463,"about_ca_system_score_codex":0.0015222229,"about_ca_system_score_gemma":0.0018486679,"threshold_uncertainty_score":0.034470618},"labels":[],"label_agreement":null},{"id":"W2949802744","doi":"10.48550/arxiv.1503.05977","title":"Dynamic Data Structures for Document Collections and Graphs","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Computer science; Search engine indexing; Dynamism; Bottleneck; Rank (graph theory); Matching (statistics); Data structure; Sequence (biology); Theoretical computer science; Information retrieval; Combinatorics; Mathematics","score_opus":0.08947125315930614,"score_gpt":0.22940919497017198,"score_spread":0.13993794181086583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949802744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009576916,0.0018812924,0.9759464,0.002519984,0.00015241222,0.00028666385,0.0030593302,0.0016718013,0.0049052536],"genre_scores_gemma":[0.13276482,0.0031520054,0.8469334,0.0007401359,0.00038838977,0.0011014371,0.00791041,0.0006232944,0.0063861446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667156,0.00077840674,0.00034683596,0.0006326513,0.0014228915,0.0001476633],"domain_scores_gemma":[0.9911629,0.0035426472,0.00091121113,0.0031587724,0.0010113929,0.00021310055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020872143,0.0007743199,0.0011438156,0.0047920095,0.0015612898,0.0039863954,0.0025021846,0.001545581,0.003922486],"category_scores_gemma":[0.017645191,0.00092475076,0.0011498382,0.01135394,0.0027536403,0.009909482,0.0039786818,0.0032626216,0.0014595503],"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":[0.00008794003,0.000070091715,0.0006071949,0.0003662425,0.000036411613,0.00016016865,0.00041873218,0.03655413,0.001995235,0.7920528,0.017254114,0.15039703],"study_design_scores_gemma":[0.000023932835,0.000024665338,0.0002684432,0.000059575275,0.00001872425,0.00032762715,0.00015922035,0.12363551,0.0018157654,0.8388124,0.034827553,0.000026544745],"about_ca_topic_score_codex":0.003385218,"about_ca_topic_score_gemma":0.0040981346,"teacher_disagreement_score":0.0047920095,"about_ca_system_score_codex":0.0031182219,"about_ca_system_score_gemma":0.00183539,"threshold_uncertainty_score":0.022624373},"labels":[],"label_agreement":null},{"id":"W2949865904","doi":"10.48550/arxiv.0911.0086","title":"Sorting under Partial Information (without the Ellipsoid Algorithm)","year":2009,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fédération Wallonie-Bruxelles; Fonds De La Recherche Scientifique - FNRS; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mathematics; Logarithm; Combinatorics; Time complexity; Binary logarithm; Log-log plot; Sorting algorithm; Algorithm; Linear extension; Pairwise comparison; Upper and lower bounds; Sorting; Approximation algorithm; Ellipsoid method; Entropy (arrow of time); Discrete mathematics; Regular polygon; Convex optimization; Convex combination; Partially ordered set","score_opus":0.054921576282950524,"score_gpt":0.19649195010611303,"score_spread":0.1415703738231625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949865904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032323588,0.00035185882,0.96037227,0.0004913336,0.000079503065,0.000117141004,0.00039766516,0.0011650791,0.0047014747],"genre_scores_gemma":[0.2186178,0.00037119613,0.775513,0.0002940604,0.00006346185,0.0001635644,0.0008508749,0.0001621922,0.0039637475],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971355,0.00064417324,0.00022950444,0.00058350037,0.001011459,0.00039584894],"domain_scores_gemma":[0.99582916,0.0016838496,0.00037286986,0.001401138,0.00051323965,0.00019981863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021210406,0.00073642365,0.0015559796,0.0018009433,0.0008846405,0.0020150947,0.0022271972,0.0011077209,0.0044179694],"category_scores_gemma":[0.007909125,0.00061183865,0.001152492,0.003838372,0.0014408606,0.006645915,0.0031581346,0.0017586381,0.0011802927],"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":[0.00094847707,0.00017753115,0.0016093922,0.0002876741,0.00007770672,0.0001383491,0.00041011194,0.2783384,0.00758921,0.27878058,0.009519161,0.42212334],"study_design_scores_gemma":[0.00007335552,0.00011716221,0.00039946902,0.000034867786,0.000021847396,0.00013148064,0.000063003754,0.759777,0.0054932684,0.2268171,0.007022537,0.000048934613],"about_ca_topic_score_codex":0.0039313403,"about_ca_topic_score_gemma":0.0050306446,"teacher_disagreement_score":0.0044179694,"about_ca_system_score_codex":0.0016917225,"about_ca_system_score_gemma":0.0026384576,"threshold_uncertainty_score":0.014779508},"labels":[],"label_agreement":null},{"id":"W2950240972","doi":"10.48550/arxiv.1211.0587","title":"Partition Tree Weighting","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Weighting; Computer science; Partition (number theory); Piecewise; Algorithm; Tree (set theory); Redundancy (engineering); Bayesian probability; Data mining; Mathematics; Artificial intelligence","score_opus":0.0865792871209727,"score_gpt":0.18552729023312947,"score_spread":0.09894800311215678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950240972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019214544,0.00016439192,0.99664176,0.00005306568,0.000033754055,0.00004403379,0.00006395829,0.00028902877,0.00078854366],"genre_scores_gemma":[0.06579213,0.00038572622,0.92883027,0.00014202882,0.00010042368,0.00025763435,0.0006603622,0.0004299395,0.0034014634],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984396,0.00040693322,0.000077869256,0.00027904275,0.0006722638,0.00012436922],"domain_scores_gemma":[0.9977169,0.0010160767,0.00015036008,0.000512466,0.00051561644,0.00008859881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001591063,0.0010271079,0.0013563631,0.0030254608,0.00089814,0.0018243922,0.0023687864,0.0015519068,0.00767672],"category_scores_gemma":[0.009346857,0.00060555316,0.0011745783,0.003248425,0.00070351,0.0032737372,0.0027805034,0.0018935464,0.0025465714],"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":[0.00023950078,0.00008896985,0.0010784101,0.00021667882,0.00012293422,0.000122015466,0.00024907585,0.11089915,0.012705019,0.113708936,0.007918287,0.75265104],"study_design_scores_gemma":[0.000040815652,0.00010100112,0.0003529201,0.0000636802,0.000058945352,0.0003255829,0.000078281686,0.8305117,0.009677742,0.13831921,0.020436058,0.000034161578],"about_ca_topic_score_codex":0.0013455162,"about_ca_topic_score_gemma":0.0017923042,"teacher_disagreement_score":0.00767672,"about_ca_system_score_codex":0.0008795296,"about_ca_system_score_gemma":0.0012777311,"threshold_uncertainty_score":0.025681198},"labels":[],"label_agreement":null},{"id":"W2950472498","doi":"10.48550/arxiv.1208.0092","title":"Efficient Indexing and Querying over Syntactically Annotated Trees","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Alberta","funders":"","keywords":"Computer science; Search engine indexing; Parsing; Coding (social sciences); Set (abstract data type); Index (typography); Tree (set theory); Natural language; Information retrieval; Artificial intelligence; Natural language processing; Mathematics; Combinatorics","score_opus":0.05404926755246188,"score_gpt":0.1964002652671958,"score_spread":0.14235099771473392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950472498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11323848,0.0011701912,0.86154747,0.00086941617,0.000115561976,0.0003256156,0.0060174675,0.0117277475,0.004987987],"genre_scores_gemma":[0.3193534,0.0008985198,0.6600578,0.00026916215,0.00015241129,0.0003784191,0.014965277,0.0008667222,0.0030582892],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971916,0.0005106182,0.00039427538,0.0004065467,0.00127562,0.00022128638],"domain_scores_gemma":[0.9898393,0.00514189,0.00076543126,0.0025226036,0.001519905,0.00021079344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016697381,0.00072111876,0.0014908655,0.003762971,0.0010368594,0.002457909,0.0023777052,0.0011589957,0.0022142448],"category_scores_gemma":[0.014997452,0.0005279253,0.00084675447,0.008297125,0.0010410814,0.0068355734,0.002273599,0.0012913278,0.0014503173],"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":[0.000919903,0.0004408057,0.0070398618,0.0010741142,0.00012822289,0.0007482731,0.0016642944,0.064421944,0.09946297,0.08244397,0.04541808,0.6962376],"study_design_scores_gemma":[0.00012590805,0.0001967884,0.002697485,0.0000977159,0.000085090855,0.00081828935,0.00078222464,0.7539971,0.06911944,0.15400666,0.017969545,0.00010384053],"about_ca_topic_score_codex":0.0028316493,"about_ca_topic_score_gemma":0.0043226783,"teacher_disagreement_score":0.003762971,"about_ca_system_score_codex":0.0010474409,"about_ca_system_score_gemma":0.0024430137,"threshold_uncertainty_score":0.008830488},"labels":[],"label_agreement":null},{"id":"W2950603471","doi":"10.48550/arxiv.1101.5376","title":"Succincter Text Indexing with Wildcards","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compressed suffix array; Search engine indexing; Suffix; Suffix array; Space (punctuation); Computer science; Combinatorics; Binary logarithm; Matching (statistics); Alphabet; Word (group theory); Algorithm; Data structure; Mathematics; Theoretical computer science; Suffix tree; Information retrieval; Statistics","score_opus":0.062409617773669386,"score_gpt":0.1682849665940609,"score_spread":0.10587534882039151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950603471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0946469,0.0015379154,0.88626534,0.0017559862,0.00045174247,0.00028670634,0.0026854842,0.007073686,0.005296279],"genre_scores_gemma":[0.2884346,0.001037593,0.69109154,0.0009791689,0.00056593335,0.00043149738,0.00777743,0.000939189,0.008743045],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974136,0.000442448,0.00040687906,0.0005105605,0.0009824027,0.0002441754],"domain_scores_gemma":[0.98995155,0.0039482513,0.00086501485,0.0040147705,0.0009983433,0.00022207179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014036741,0.00080132304,0.0017881748,0.0022404438,0.0009190872,0.002957491,0.002355206,0.0014388936,0.006243992],"category_scores_gemma":[0.0136688845,0.00058399636,0.00076579454,0.0066417325,0.0017025564,0.011873311,0.0034883057,0.0018175418,0.0042060227],"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":[0.0015272715,0.0005008762,0.0030757636,0.0007733202,0.00008111854,0.00058038114,0.0008853943,0.04801209,0.05253988,0.1400978,0.038719013,0.71320707],"study_design_scores_gemma":[0.00033538407,0.0006828635,0.0010514156,0.00013092524,0.00007118641,0.0013763066,0.000512975,0.54189414,0.08259199,0.3308768,0.04035363,0.00012236765],"about_ca_topic_score_codex":0.0010891,"about_ca_topic_score_gemma":0.0014109222,"teacher_disagreement_score":0.006243992,"about_ca_system_score_codex":0.0010062079,"about_ca_system_score_gemma":0.0015976591,"threshold_uncertainty_score":0.020888269},"labels":[],"label_agreement":null},{"id":"W2950714888","doi":"10.48550/arxiv.1511.01175","title":"Uniform generation of random regular graphs","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Combinatorics; Random regular graph; Graph; Mathematics; Random graph; Discrete mathematics; Running time; Uniform distribution (continuous); Computer science; Pathwidth; Algorithm; Line graph; Statistics","score_opus":0.10409732344079113,"score_gpt":0.1942930800345545,"score_spread":0.09019575659376337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950714888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022396015,0.00010896575,0.973938,0.00015223556,0.000036503585,0.00012534134,0.0001836462,0.0010337994,0.0020253367],"genre_scores_gemma":[0.41115573,0.00019417044,0.58162,0.0004077114,0.0000998512,0.0007751892,0.0014807945,0.00058989885,0.0036767782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975394,0.00084594195,0.00013688083,0.0006433522,0.00061543327,0.0002189996],"domain_scores_gemma":[0.99090225,0.0044564577,0.00040225065,0.0031460486,0.00081948156,0.0002735248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002416873,0.0007310508,0.0009923455,0.0017806803,0.00075167156,0.0013008522,0.0026041882,0.0011105383,0.0031833127],"category_scores_gemma":[0.015684469,0.0007645913,0.0010479295,0.0014383005,0.0017959458,0.002578075,0.0028622537,0.001688318,0.0010643586],"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":[0.0007326656,0.0002238725,0.004771801,0.000316167,0.00010811085,0.00035914397,0.00041960322,0.39704955,0.020111052,0.38386178,0.010132416,0.18191387],"study_design_scores_gemma":[0.00005730386,0.000049577746,0.00020605884,0.000014860775,0.000013778013,0.00012168293,0.000021747706,0.90477306,0.0072075855,0.085157216,0.0023596333,0.000017447097],"about_ca_topic_score_codex":0.0010543098,"about_ca_topic_score_gemma":0.0015561879,"teacher_disagreement_score":0.0031833127,"about_ca_system_score_codex":0.001235495,"about_ca_system_score_gemma":0.0010909437,"threshold_uncertainty_score":0.012781858},"labels":[],"label_agreement":null},{"id":"W2950735567","doi":"10.22215/etd/2010-09345","title":"Improved methods for generating quasi-gray codes","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Gray (unit); Computer science; Medicine","score_opus":0.03938209058954817,"score_gpt":0.3694343456734885,"score_spread":0.3300522550839403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950735567","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057924152,0.00015983872,0.98954016,0.00007750776,0.00009696752,0.00005789897,0.00008174677,0.0005168182,0.003676601],"genre_scores_gemma":[0.100632414,0.00031151783,0.88362527,0.00012854069,0.000084653046,0.00020804389,0.0003732806,0.00052409776,0.014112219],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907327,0.0002313139,0.000059451377,0.00012006542,0.00045288977,0.00006295789],"domain_scores_gemma":[0.99851197,0.0006235788,0.0000716989,0.00044672078,0.00030288968,0.000043137476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083027006,0.00060781976,0.00047066243,0.0017351635,0.00040834022,0.0009212857,0.001018845,0.00069666904,0.010913887],"category_scores_gemma":[0.003943417,0.0003590894,0.00072357355,0.00087736925,0.00081705925,0.0010695974,0.001516228,0.0008940729,0.0033720087],"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":[0.00022553968,0.000107100335,0.0006962572,0.00034181168,0.000056599612,0.00015224148,0.0002978003,0.10905585,0.030597458,0.2565655,0.00785718,0.59404665],"study_design_scores_gemma":[0.00010065019,0.00016783971,0.00049638835,0.0000718559,0.00004034835,0.000387777,0.00006310445,0.80685985,0.029965684,0.13830523,0.02349191,0.000049294787],"about_ca_topic_score_codex":0.0010674665,"about_ca_topic_score_gemma":0.0025497868,"teacher_disagreement_score":0.010913887,"about_ca_system_score_codex":0.0005861279,"about_ca_system_score_gemma":0.0007486003,"threshold_uncertainty_score":0.036510587},"labels":[],"label_agreement":null},{"id":"W2950820003","doi":"10.48550/arxiv.cs/0309005","title":"Indexing Schemes for Similarity Search In Datasets of Short Protein Fragments","year":2003,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fonterra Co-Operative Group; Victoria University; Victoria University of Wellington; University of Ottawa","keywords":"Search engine indexing; Nearest neighbor search; Similarity (geometry); Block (permutation group theory); Computer science; Alphabet; Pattern recognition (psychology); Fragment (logic); Data mining; Artificial intelligence; Algorithm; Mathematics; Combinatorics; Image (mathematics)","score_opus":0.09477066533544168,"score_gpt":0.3400283011467722,"score_spread":0.2452576358113305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950820003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05562282,0.0008871289,0.9350026,0.00036717835,0.00008918895,0.00036122437,0.0018748746,0.004510104,0.001284787],"genre_scores_gemma":[0.17567535,0.000310853,0.816346,0.00014560489,0.00010263536,0.00057875,0.005595162,0.00023551208,0.0010101403],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99568534,0.0008605358,0.00070374843,0.00057452574,0.0019367937,0.00023912208],"domain_scores_gemma":[0.98958147,0.0026097381,0.0009352259,0.004735469,0.0017968885,0.00034123578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036174445,0.00056983647,0.0014522494,0.0049358513,0.0011984856,0.0017012446,0.002987021,0.0011244183,0.002530305],"category_scores_gemma":[0.018216562,0.0004107007,0.0008450513,0.0083098225,0.0010706078,0.0046326634,0.0031449492,0.0013383249,0.0021981334],"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":[0.00093454117,0.00039933386,0.004624169,0.0005184657,0.00011063105,0.0001510899,0.0004972772,0.035578944,0.044373386,0.054307748,0.01609499,0.8424094],"study_design_scores_gemma":[0.00042026665,0.0008408528,0.004085109,0.00009492941,0.00009585149,0.0010097617,0.00033865418,0.73765403,0.06558101,0.16789062,0.021818556,0.0001703929],"about_ca_topic_score_codex":0.0013060637,"about_ca_topic_score_gemma":0.0017478233,"teacher_disagreement_score":0.0049358513,"about_ca_system_score_codex":0.001111539,"about_ca_system_score_gemma":0.001733433,"threshold_uncertainty_score":0.019131124},"labels":[],"label_agreement":null},{"id":"W2950907886","doi":"10.48550/arxiv.0907.2071","title":"Layered Working-Set Trees","year":2009,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Binary search tree; Binary tree; Element (criminal law); Upper and lower bounds; Multiplicative function; Set (abstract data type); Combinatorics; Amortized analysis; Mathematics; Ternary search tree; Logarithm; Tree (set theory); Binary number; Property (philosophy); Search tree; Computer science; Discrete mathematics; Data structure; Search algorithm; Algorithm; Tree structure; Interval tree; Arithmetic","score_opus":0.07937149507237835,"score_gpt":0.28899213517705724,"score_spread":0.2096206401046789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950907886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053005718,0.0016044142,0.92984927,0.00075301726,0.00014837336,0.00016412693,0.0011840435,0.0026701412,0.010620927],"genre_scores_gemma":[0.41705295,0.0015334212,0.5673888,0.0006744153,0.00023669009,0.000609608,0.0024525314,0.000822945,0.009228566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695337,0.0003968237,0.0003356538,0.00042763792,0.0013584053,0.00052809686],"domain_scores_gemma":[0.9903019,0.0031069566,0.00063016516,0.004093358,0.0013728244,0.00049477373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020305908,0.00072574953,0.0015204678,0.0021542872,0.0016530243,0.0037404916,0.0032816664,0.0016038043,0.0067192586],"category_scores_gemma":[0.016292807,0.0008411779,0.0012729525,0.004169361,0.0016327502,0.011237745,0.0053057214,0.0025254413,0.0027733054],"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":[0.0006785144,0.00023409392,0.0029538434,0.0005023648,0.00012868372,0.00030650868,0.00075067714,0.09427951,0.019646483,0.54305315,0.019994747,0.31747144],"study_design_scores_gemma":[0.00005879834,0.00020954492,0.00060998346,0.00010768255,0.000097819684,0.00064900704,0.00016840425,0.358991,0.013860654,0.5963664,0.028809575,0.0000710449],"about_ca_topic_score_codex":0.0012085537,"about_ca_topic_score_gemma":0.0016780461,"teacher_disagreement_score":0.0067192586,"about_ca_system_score_codex":0.001385724,"about_ca_system_score_gemma":0.001568533,"threshold_uncertainty_score":0.022478163},"labels":[],"label_agreement":null},{"id":"W2951035508","doi":"10.48550/arxiv.1509.05053","title":"Array Layouts for Comparison-Based Searching","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cache; Binary search algorithm; Value (mathematics); Latency (audio); Binary tree; Parallel computing; Binary number; Algorithm; Search algorithm; Arithmetic; Mathematics","score_opus":0.17016073171193988,"score_gpt":0.24265525163900303,"score_spread":0.07249451992706316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951035508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007921093,0.003744197,0.94716644,0.000864312,0.00058257167,0.00021135113,0.0012998249,0.016301615,0.021908564],"genre_scores_gemma":[0.07977864,0.0015502698,0.90498096,0.00061760336,0.00022803868,0.00034928005,0.0013538739,0.0029348782,0.008206355],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998242,0.00040691864,0.00019952284,0.00043669844,0.00056201976,0.00015271986],"domain_scores_gemma":[0.9949378,0.0018241107,0.00046167805,0.0018101414,0.0008337834,0.00013241383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001577329,0.0012217648,0.0010231506,0.0020656716,0.0010856579,0.0035682097,0.0032352158,0.0013325835,0.032553513],"category_scores_gemma":[0.01046956,0.00088186376,0.0010299654,0.0044157277,0.0012874765,0.007100579,0.0022321907,0.001597958,0.0138585055],"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":[0.0007077851,0.00016364292,0.0014981581,0.0012426138,0.00009471314,0.00025257512,0.00050536974,0.03167945,0.027106512,0.3044564,0.049577676,0.5827151],"study_design_scores_gemma":[0.00024771556,0.0007208614,0.0009562553,0.0003982505,0.00012728151,0.0011667524,0.0003666409,0.120807804,0.05260177,0.45588863,0.36649632,0.00022165482],"about_ca_topic_score_codex":0.0015614674,"about_ca_topic_score_gemma":0.002481225,"teacher_disagreement_score":0.032553513,"about_ca_system_score_codex":0.0015253796,"about_ca_system_score_gemma":0.0017291551,"threshold_uncertainty_score":0.108902395},"labels":[],"label_agreement":null},{"id":"W2951052484","doi":"10.48550/arxiv.1405.0189","title":"On Hardness of Jumbled Indexing","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Omega; Search engine indexing; Combinatorics; Substring; Preprocessor; Matching (statistics); Mathematics; Sigma; Constant (computer programming); Pattern matching; Computer science; Algorithm; Data structure; Statistics; Information retrieval; Physics; Artificial intelligence","score_opus":0.0630169761731807,"score_gpt":0.1861705511471469,"score_spread":0.1231535749739662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951052484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46539778,0.0087063275,0.32006025,0.036965933,0.0010653877,0.0007145911,0.023807246,0.016381992,0.1269005],"genre_scores_gemma":[0.8247285,0.0031346085,0.10453821,0.005891817,0.0017304912,0.0007715646,0.020332275,0.0033885895,0.03548405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99146956,0.0016613071,0.0006177101,0.0023050737,0.0021428845,0.0018035417],"domain_scores_gemma":[0.9604109,0.02747246,0.0016067848,0.007749612,0.0013229396,0.0014373589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031078781,0.0017309472,0.003999794,0.0017171713,0.0044858605,0.008787391,0.00604069,0.0037813901,0.022049177],"category_scores_gemma":[0.02523582,0.0015302998,0.003464487,0.0052604005,0.0047073583,0.023665706,0.0074262707,0.008362284,0.006969245],"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":[0.0069795786,0.0017045044,0.009689415,0.0039132535,0.00042381862,0.0012663346,0.0038794894,0.10664241,0.022303693,0.38638568,0.25165462,0.20515724],"study_design_scores_gemma":[0.00059152703,0.00023767806,0.0024729602,0.00020087525,0.00017745142,0.0009502394,0.00081281544,0.17274739,0.0077458825,0.7899769,0.023936858,0.00014948638],"about_ca_topic_score_codex":0.005816766,"about_ca_topic_score_gemma":0.0040140604,"teacher_disagreement_score":0.022049177,"about_ca_system_score_codex":0.0041289064,"about_ca_system_score_gemma":0.003850113,"threshold_uncertainty_score":0.07376188},"labels":[],"label_agreement":null},{"id":"W2951256320","doi":"10.48550/arxiv.1507.06866","title":"Compressed Data Structures for Dynamic Sequences","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Substring; String (physics); Combinatorics; Symbol (formal); Sigma; Alphabet; Order (exchange); Rank (graph theory); Data structure; Mathematics; Binary logarithm; Algorithm; Computer science; Discrete mathematics; Physics","score_opus":0.1754561594837511,"score_gpt":0.24601067322234296,"score_spread":0.07055451373859187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951256320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07582835,0.0021350717,0.8917012,0.0031946003,0.00044251487,0.0004911503,0.009232782,0.008092709,0.008881594],"genre_scores_gemma":[0.41890624,0.0012782906,0.55144304,0.0011263778,0.00039914213,0.0011825453,0.014811126,0.00079541065,0.010057844],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99787855,0.00027742697,0.00021909266,0.00042295177,0.0009922582,0.00020971305],"domain_scores_gemma":[0.99428153,0.0016284115,0.0004728325,0.0026327837,0.0008253521,0.000159227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008921296,0.00075990846,0.0010456309,0.0018764589,0.000933043,0.0020640572,0.0027572345,0.001178397,0.007554084],"category_scores_gemma":[0.010274366,0.0005876018,0.0006245119,0.0053855916,0.001263732,0.007017173,0.0029914945,0.0019060132,0.002053811],"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":[0.0014790013,0.0003616128,0.0021654887,0.0006847946,0.00008990642,0.00048348913,0.0008996805,0.10046887,0.023741404,0.2534313,0.05085879,0.5653357],"study_design_scores_gemma":[0.00020878344,0.00040893257,0.0007364023,0.00019238013,0.00006549957,0.00086454774,0.0005767077,0.51615775,0.0369027,0.3726518,0.07113705,0.000097405864],"about_ca_topic_score_codex":0.0021825721,"about_ca_topic_score_gemma":0.0028243433,"teacher_disagreement_score":0.007554084,"about_ca_system_score_codex":0.0015782304,"about_ca_system_score_gemma":0.0016888703,"threshold_uncertainty_score":0.025270939},"labels":[],"label_agreement":null},{"id":"W2951287769","doi":"10.48550/arxiv.1502.05204","title":"Clustered Integer 3SUM via Additive Combinatorics","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Combinatorics; Mathematics; Integer (computer science); Monotone polygon; Bounded function; Sublinear function; Exponential time hypothesis; Constant (computer programming); Discrete mathematics; Upper and lower bounds; Time complexity; Computer science","score_opus":0.07588828621721617,"score_gpt":0.19262196060295672,"score_spread":0.11673367438574055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951287769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03924262,0.0013396938,0.8845198,0.0014555489,0.00044593046,0.00020329493,0.001240443,0.00506443,0.06648823],"genre_scores_gemma":[0.3739826,0.00115259,0.5687864,0.0019880794,0.0006009439,0.00060983375,0.003677972,0.0019174865,0.047284048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976927,0.00038819815,0.00015872809,0.00059771934,0.0007900195,0.00037264818],"domain_scores_gemma":[0.9977302,0.00082361297,0.00018474806,0.0008896123,0.00024482823,0.00012709422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009951812,0.0013347772,0.0014860153,0.0020840804,0.0017092655,0.0047160275,0.0023471217,0.0010368021,0.028786698],"category_scores_gemma":[0.006213679,0.00060045713,0.001686184,0.004256015,0.0017761269,0.0064604646,0.0056271777,0.0027959119,0.008948677],"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":[0.0002961262,0.00013899118,0.00051961356,0.0003906265,0.00004850757,0.00014040309,0.00024508484,0.033227727,0.004472012,0.7388669,0.020706011,0.20094803],"study_design_scores_gemma":[0.00005951183,0.00008739943,0.00020891483,0.00007065331,0.000042104373,0.0002732341,0.00011787468,0.13575776,0.007062466,0.8145483,0.041725066,0.00004672866],"about_ca_topic_score_codex":0.001027777,"about_ca_topic_score_gemma":0.002092236,"teacher_disagreement_score":0.028786698,"about_ca_system_score_codex":0.0024599184,"about_ca_system_score_gemma":0.0016637912,"threshold_uncertainty_score":0.09630108},"labels":[],"label_agreement":null},{"id":"W2951332226","doi":"10.1089/cmb.2019.0309","title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","year":2020,"lang":"en","type":"preprint","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"String (physics); Search engine indexing; Computer science; Rank (graph theory); Sample (material); Suffix array; Compressed suffix array; Index (typography); Data structure; Suffix; Database index; Space (punctuation); Data mining; String searching algorithm; Information retrieval; Mathematics; Combinatorics; World Wide Web; Programming language","score_opus":0.03835700790850998,"score_gpt":0.29696711672646436,"score_spread":0.2586101088179544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951332226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022150341,0.0011206146,0.9487873,0.00022594321,0.00027426114,0.00025271927,0.0046605547,0.0177839,0.004744384],"genre_scores_gemma":[0.05398333,0.000415687,0.92294955,0.00016043863,0.00017422042,0.00032959043,0.01671887,0.001591901,0.0036763807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765885,0.00025620172,0.00032210373,0.0005161748,0.0010406356,0.000206077],"domain_scores_gemma":[0.996145,0.0006930748,0.00022252712,0.0014495709,0.0012880068,0.00020181833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013890835,0.001031622,0.0019901036,0.0038846687,0.0011408775,0.0025694256,0.0021325,0.0012066931,0.005631907],"category_scores_gemma":[0.008801332,0.00078612723,0.0012059652,0.0060498905,0.00064676796,0.0048255157,0.0034360362,0.0021814487,0.009092192],"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":[0.0005948395,0.0003178537,0.0041053537,0.00075759843,0.000121206096,0.0004243046,0.0005751784,0.01691737,0.09436843,0.032454807,0.04845808,0.80090505],"study_design_scores_gemma":[0.00025033476,0.0006071486,0.0051150233,0.00018369567,0.00017668465,0.0017777561,0.00048768247,0.5898419,0.148283,0.08765018,0.16538803,0.00023853603],"about_ca_topic_score_codex":0.0016595252,"about_ca_topic_score_gemma":0.0029764657,"teacher_disagreement_score":0.005631907,"about_ca_system_score_codex":0.00087270886,"about_ca_system_score_gemma":0.0029294437,"threshold_uncertainty_score":0.018840551},"labels":[],"label_agreement":null},{"id":"W2951477656","doi":"10.5539/jmr.v11n2p171","title":"Recursive Formula for the Random String Word Detection Probability, Overlaps and Probability Extremes","year":2019,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Word (group theory); String (physics); Feature (linguistics); Probability theory; Probability distribution; Probability and statistics; Algorithm; Discrete mathematics; Combinatorics; Statistics; Geometry","score_opus":0.09678047181280783,"score_gpt":0.3553861443698025,"score_spread":0.2586056725569946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951477656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023277868,0.00041469195,0.96860516,0.00020710684,0.00005568238,0.000057167592,0.00009263247,0.000248527,0.0070411554],"genre_scores_gemma":[0.59532654,0.0009104703,0.39270684,0.00029516686,0.00033875272,0.0005934925,0.00032227513,0.0004119722,0.009094559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981292,0.00048557945,0.00012683404,0.00038921725,0.0006997027,0.00016938797],"domain_scores_gemma":[0.9922448,0.0057910737,0.00045308398,0.0005117691,0.0008245487,0.0001747529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002561038,0.00052717485,0.0006191322,0.0025998545,0.0006197246,0.0020797392,0.001604905,0.0011635466,0.0058662365],"category_scores_gemma":[0.019963553,0.00035512296,0.0009112973,0.0010611204,0.0023578776,0.0048226174,0.0016463709,0.0015824393,0.0011944018],"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":[0.000058052676,0.00002715985,0.0015872143,0.0001250154,0.000021292572,0.0003033886,0.0003285087,0.023879293,0.0048714974,0.933544,0.0011590876,0.034095436],"study_design_scores_gemma":[0.000015493888,0.00006771378,0.0014651925,0.000074036434,0.00003093187,0.0010146325,0.00008110641,0.37344033,0.004910224,0.61399215,0.004843175,0.000065104985],"about_ca_topic_score_codex":0.0005579378,"about_ca_topic_score_gemma":0.000520683,"teacher_disagreement_score":0.0058662365,"about_ca_system_score_codex":0.0010601418,"about_ca_system_score_gemma":0.0007074882,"threshold_uncertainty_score":0.019624472},"labels":[],"label_agreement":null},{"id":"W2951745001","doi":"10.48550/arxiv.1211.7161","title":"Unshuffling a Square is NP-Hard","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"String (physics); Square (algebra); Interleaving; Combinatorics; Time complexity; Mathematics; Square tiling; Partition (number theory); Reduction (mathematics); Dynamic programming; Discrete mathematics; Computer science; Algorithm","score_opus":0.10373346287930134,"score_gpt":0.19646659060886645,"score_spread":0.09273312772956512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951745001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38634932,0.0026632906,0.52089363,0.014026454,0.00065918016,0.0006607008,0.0076818503,0.0056771664,0.061388366],"genre_scores_gemma":[0.7392861,0.0011615896,0.22409938,0.0018940245,0.00034729118,0.0004270911,0.0071106,0.0009984046,0.024675464],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846905,0.0002114805,0.000101733196,0.0005638472,0.00037832547,0.00027550056],"domain_scores_gemma":[0.99233,0.0061015477,0.000424135,0.0006697278,0.00029643442,0.00017818024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006574697,0.00090382603,0.0013727433,0.00057779485,0.0017937919,0.0032083718,0.00174021,0.0017504892,0.008190249],"category_scores_gemma":[0.005305643,0.0006808765,0.0013814205,0.0020968504,0.0022424741,0.0056198337,0.0021187298,0.003062609,0.0020057247],"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":[0.001361371,0.000787974,0.0048614494,0.0021178755,0.0003174298,0.0011353113,0.0012434245,0.24773942,0.023039524,0.2310761,0.08062215,0.40569806],"study_design_scores_gemma":[0.00018384458,0.00014306568,0.0010731304,0.00010649011,0.0000945143,0.00072804844,0.0007165182,0.3125451,0.016779117,0.6436288,0.023938034,0.000063319945],"about_ca_topic_score_codex":0.0030547932,"about_ca_topic_score_gemma":0.004994819,"teacher_disagreement_score":0.008190249,"about_ca_system_score_codex":0.0014493108,"about_ca_system_score_gemma":0.0016859464,"threshold_uncertainty_score":0.027399123},"labels":[],"label_agreement":null},{"id":"W2951833220","doi":"10.1007/978-1-4939-2864-4_73","title":"Closest String and Substring Problems","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Substring; Combinatorics; Hamming distance; String (physics); Approximate string matching; String searching algorithm; Mathematics; Edit distance; Discrete mathematics; Logarithm; Set (abstract data type); Algorithm; Pattern matching; Computer science; Artificial intelligence","score_opus":0.013939235147516165,"score_gpt":0.21822607671074917,"score_spread":0.204286841563233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951833220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00910053,0.06667147,0.6234804,0.006317574,0.0051917066,0.00016113193,0.0013828338,0.0015619156,0.28613248],"genre_scores_gemma":[0.121905334,0.08396705,0.52927625,0.0020554278,0.009490544,0.00053464633,0.0070130536,0.0016686831,0.24408902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983334,0.0002706308,0.00011855839,0.00034106412,0.0008717301,0.000064591135],"domain_scores_gemma":[0.9988494,0.000597022,0.00007540744,0.00027476883,0.00015042067,0.000053060827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007594871,0.0012976953,0.0018895234,0.0025130194,0.0010726189,0.0035375198,0.0023095247,0.0024038397,0.025871897],"category_scores_gemma":[0.005774557,0.00054410717,0.0009209807,0.00808962,0.0020147688,0.0071596727,0.0029139165,0.0038907826,0.011305314],"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":[0.000055856584,0.00006493154,0.00016748405,0.00077562983,0.00003165274,0.000117666816,0.00013205256,0.010946914,0.00085972593,0.46413386,0.081176475,0.44153765],"study_design_scores_gemma":[0.000013290551,0.000020028134,0.00010085334,0.0001268881,0.000012602214,0.00037446988,0.00004275758,0.013117116,0.0005445424,0.90072966,0.08490294,0.000014808847],"about_ca_topic_score_codex":0.0005951546,"about_ca_topic_score_gemma":0.00053272565,"teacher_disagreement_score":0.025871897,"about_ca_system_score_codex":0.001214796,"about_ca_system_score_gemma":0.0012519086,"threshold_uncertainty_score":0.08655012},"labels":[],"label_agreement":null},{"id":"W2951849834","doi":"10.48550/arxiv.1308.5586","title":"SLP compression for solutions of equations with constraints in free and hyperbolic groups","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Mathematics; Upper and lower bounds; Abelian group; Bounded function; Free product; Hyperbolic function; Group (periodic table); Pure mathematics; Mathematical analysis","score_opus":0.08688305343487528,"score_gpt":0.19037558381014164,"score_spread":0.10349253037526636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951849834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62966955,0.0012951293,0.33182684,0.0057917265,0.00021034529,0.00037503286,0.001886783,0.0014783903,0.027466241],"genre_scores_gemma":[0.87462133,0.000650794,0.11105625,0.00063059473,0.00018861087,0.0003018868,0.0023241553,0.00045116973,0.0097752195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981534,0.00037278063,0.00017908576,0.00034619926,0.0006320645,0.00031646667],"domain_scores_gemma":[0.9910529,0.006623301,0.00057240494,0.0010753114,0.00045991573,0.00021607023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012509034,0.00055997,0.00089437567,0.0010348561,0.0009413043,0.0023473776,0.0012151732,0.0009899306,0.009083832],"category_scores_gemma":[0.014972874,0.00035731553,0.0012031862,0.0019927563,0.00174455,0.007089373,0.0032893773,0.0028346935,0.0006436755],"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":[0.00080911425,0.00021681236,0.0048550745,0.0010325577,0.0001241315,0.0011863455,0.002834412,0.0687854,0.010116432,0.7342069,0.009248428,0.16658445],"study_design_scores_gemma":[0.00008495244,0.00010858942,0.00092097453,0.0000988336,0.00006699679,0.00045138408,0.0005838612,0.21368395,0.0127658425,0.76169336,0.009493987,0.000047358153],"about_ca_topic_score_codex":0.0013176427,"about_ca_topic_score_gemma":0.0013937054,"teacher_disagreement_score":0.009083832,"about_ca_system_score_codex":0.0021393185,"about_ca_system_score_gemma":0.001400267,"threshold_uncertainty_score":0.030388474},"labels":[],"label_agreement":null},{"id":"W2951870329","doi":"10.1002/spe.2326","title":"SIMD compression and the intersection of sorted integers","year":2015,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"SIMD; Intersection (aeronautics); Integer (computer science); Data compression; Compression (physics); Scheme (mathematics); Speedup; Compression ratio","score_opus":0.021093375553375936,"score_gpt":0.28754013740270334,"score_spread":0.2664467618493274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951870329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35906196,0.0027890783,0.5968573,0.000699364,0.00020801512,0.00022445428,0.0011439077,0.017456366,0.021559559],"genre_scores_gemma":[0.66970766,0.00067504833,0.32181045,0.00026960325,0.00009869085,0.00021272506,0.0015527813,0.0006662424,0.005006771],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982401,0.00025909368,0.00018570438,0.00020988329,0.0009653766,0.00013978414],"domain_scores_gemma":[0.99782073,0.000886974,0.00019700968,0.0006214216,0.0004294461,0.000044517627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088068173,0.0006062363,0.0005884049,0.0016576295,0.0004963211,0.0011702742,0.0012086246,0.00037509642,0.0031988886],"category_scores_gemma":[0.004723119,0.00029297062,0.0003726306,0.0032630416,0.00094015576,0.0022227247,0.0014458162,0.00048811856,0.0010131935],"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":[0.0020961028,0.0002176537,0.005346581,0.0003721555,0.00008334036,0.000508,0.000786301,0.060751736,0.087666154,0.06089571,0.016041523,0.76523465],"study_design_scores_gemma":[0.00025222023,0.0008431763,0.003207616,0.00010912323,0.00008881358,0.00089895586,0.0005434606,0.54494625,0.3570169,0.05054672,0.041447893,0.00009889688],"about_ca_topic_score_codex":0.00208135,"about_ca_topic_score_gemma":0.002044203,"teacher_disagreement_score":0.0031988886,"about_ca_system_score_codex":0.00087513577,"about_ca_system_score_gemma":0.0009165149,"threshold_uncertainty_score":0.010701358},"labels":[],"label_agreement":null},{"id":"W2951920636","doi":"10.48550/arxiv.1204.4835","title":"Succinct Indices for Range Queries with applications to Orthogonal Range Maxima","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Rectangle; Maxima; Combinatorics; Range (aeronautics); Binary logarithm; Mathematics; Maxima and minima; Point (geometry); Constant (computer programming); Entropy (arrow of time); Range query (database); Discrete mathematics; Computer science; Physics; Information retrieval; Geometry; Mathematical analysis; Search engine","score_opus":0.06879063847282897,"score_gpt":0.20705676598979264,"score_spread":0.13826612751696365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951920636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037873663,0.0007345236,0.9505811,0.0012061457,0.000088407214,0.00023603893,0.0007439928,0.0028385993,0.005697413],"genre_scores_gemma":[0.32040888,0.000608882,0.6698486,0.0007210277,0.0002856091,0.00075955555,0.001954989,0.0007000154,0.004712355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961349,0.000963665,0.00042062646,0.00075995177,0.0013700648,0.00035084476],"domain_scores_gemma":[0.9911209,0.004969769,0.00067832874,0.0024176906,0.00057268824,0.00024066749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027376488,0.0011247874,0.0016739969,0.0019438574,0.001248556,0.0026311371,0.002431558,0.0014297869,0.006604738],"category_scores_gemma":[0.017778043,0.00080793345,0.0011558203,0.0036616586,0.002285519,0.011997138,0.0056332075,0.003247624,0.0019708637],"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":[0.0015726516,0.0004913678,0.0030749205,0.000643358,0.00008812648,0.00036825292,0.001730363,0.09889057,0.02472684,0.44439745,0.01864008,0.40537602],"study_design_scores_gemma":[0.00017922722,0.00027602937,0.0005287138,0.00007325474,0.000049997478,0.00036648824,0.0003644304,0.39482808,0.015184868,0.5739412,0.014139755,0.000067910376],"about_ca_topic_score_codex":0.0011708334,"about_ca_topic_score_gemma":0.0019724811,"teacher_disagreement_score":0.006604738,"about_ca_system_score_codex":0.0013505098,"about_ca_system_score_gemma":0.001515491,"threshold_uncertainty_score":0.022095025},"labels":[],"label_agreement":null},{"id":"W2952002168","doi":"10.48550/arxiv.1304.7392","title":"A Universal Grammar-Based Code For Lossless Compression of Binary Trees","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science Foundation","keywords":"Lossless compression; Code word; Computer science; Binary tree; Binary number; Theoretical computer science; Tree (set theory); Mathematics; Algorithm; Decoding methods; Data compression; Combinatorics; Arithmetic","score_opus":0.0761930113248232,"score_gpt":0.20492372662699682,"score_spread":0.12873071530217362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952002168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03620048,0.0006276752,0.95943236,0.00040083422,0.0000676753,0.000060943476,0.00019439371,0.0005281645,0.0024874436],"genre_scores_gemma":[0.5834492,0.0011123089,0.40837294,0.0005160121,0.0001917657,0.0003099743,0.00071364595,0.00039219533,0.004941914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990953,0.0001702826,0.0000521678,0.00016338994,0.00042914215,0.00008974889],"domain_scores_gemma":[0.9976941,0.0011582732,0.00019763668,0.00051374885,0.00034984457,0.00008646928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076061406,0.0004042265,0.0005866407,0.0010017381,0.00048734003,0.00093051954,0.0010721688,0.0011906384,0.0011895897],"category_scores_gemma":[0.0059496225,0.00025042685,0.00040697597,0.0012619488,0.0016486525,0.0015881306,0.0016746362,0.0013579153,0.00038611566],"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":[0.00022961173,0.00007802373,0.0009199805,0.00030380444,0.000042570875,0.0005262091,0.00043145975,0.19026162,0.031665068,0.57600605,0.004165115,0.19537058],"study_design_scores_gemma":[0.00003317534,0.00008008127,0.00022029356,0.000060763858,0.000023782404,0.0004912665,0.000036296355,0.75363255,0.018048838,0.221516,0.005825756,0.000031155483],"about_ca_topic_score_codex":0.0011104287,"about_ca_topic_score_gemma":0.0009603099,"teacher_disagreement_score":0.0011906384,"about_ca_system_score_codex":0.00087006105,"about_ca_system_score_gemma":0.0011832431,"threshold_uncertainty_score":0.0063127875},"labels":[],"label_agreement":null},{"id":"W2952024306","doi":"","title":"Indeterminate Strings, Prefix Arrays & Undirected Graphs","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); McMaster University","funders":"","keywords":"Combinatorics; String (physics); Cardinality (data modeling); Indeterminate; Prefix; Mathematics; Alphabet; Discrete mathematics; Graph; Computer science; Pure mathematics","score_opus":0.04911968400956972,"score_gpt":0.18232086531265423,"score_spread":0.1332011813030845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952024306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17694193,0.006617217,0.7597176,0.0048898486,0.00044561122,0.00014057495,0.0024755376,0.0010281844,0.047743585],"genre_scores_gemma":[0.731477,0.007003138,0.23738696,0.0012037258,0.00058430963,0.0003081701,0.0031810927,0.00034400832,0.018511547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905914,0.00028728164,0.000051778123,0.00028750143,0.00021350547,0.00010073672],"domain_scores_gemma":[0.9966118,0.0021442915,0.00040443917,0.00057494733,0.00013582915,0.00012877792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061241246,0.00060293253,0.0005705525,0.0015640424,0.0007291572,0.0027307319,0.00095952104,0.0012643816,0.0044137724],"category_scores_gemma":[0.0038993796,0.0004847414,0.0005153767,0.0036885818,0.0022224595,0.0044794576,0.0010373218,0.0015930283,0.00093805837],"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":[0.00011320658,0.00005557775,0.0014553845,0.00021094098,0.000024143494,0.00023993255,0.00028556486,0.033759348,0.0030616936,0.8982563,0.00793871,0.05459915],"study_design_scores_gemma":[0.000008246788,0.000030365058,0.00032799641,0.000039587336,0.000010950817,0.00028764652,0.00009662372,0.040375594,0.0010070285,0.94482535,0.012973747,0.00001687591],"about_ca_topic_score_codex":0.0014896565,"about_ca_topic_score_gemma":0.0018728827,"teacher_disagreement_score":0.0044137724,"about_ca_system_score_codex":0.0014044826,"about_ca_system_score_gemma":0.00061644346,"threshold_uncertainty_score":0.014765561},"labels":[],"label_agreement":null},{"id":"W2952347883","doi":"10.48550/arxiv.math/0602300","title":"Deterministic Random Walks on the Integers","year":2006,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"Combinatorics; Random walk; Vertex (graph theory); Mathematics; Router; Graph; Path (computing); Discrete mathematics; Constant (computer programming); Binary logarithm; Computer science; Statistics","score_opus":0.04338474515174864,"score_gpt":0.26346902733319,"score_spread":0.22008428218144135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952347883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22034924,0.0021443167,0.7369853,0.0023157054,0.00024887177,0.00019943852,0.0009253087,0.0015439625,0.035287946],"genre_scores_gemma":[0.8822387,0.00095443556,0.10522334,0.00046236638,0.00014196297,0.00033853154,0.0006181072,0.00017364332,0.009848961],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998616,0.00047724874,0.0000671601,0.00028500461,0.00030699748,0.00024759385],"domain_scores_gemma":[0.9963431,0.002219261,0.00032893507,0.00074828265,0.00020908804,0.00015147537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009782858,0.0005754645,0.00081453734,0.0010365207,0.00091526227,0.0019062145,0.0010367419,0.00090230646,0.0042733443],"category_scores_gemma":[0.009914957,0.0004441771,0.0005355015,0.0012605577,0.0017725881,0.0036021292,0.0016246568,0.0013646322,0.0008881476],"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":[0.00027051748,0.000057408288,0.0009351117,0.00009561303,0.000026615982,0.00018476689,0.00015849683,0.13257217,0.0021390074,0.8315725,0.004628282,0.027359556],"study_design_scores_gemma":[0.000072222065,0.000041057046,0.00027791678,0.000035576842,0.000011210755,0.00011509311,0.000046451332,0.42633122,0.0013686812,0.56611425,0.0055594468,0.000026931288],"about_ca_topic_score_codex":0.0011734471,"about_ca_topic_score_gemma":0.001216943,"teacher_disagreement_score":0.0042733443,"about_ca_system_score_codex":0.0010712908,"about_ca_system_score_gemma":0.0006165037,"threshold_uncertainty_score":0.014295816},"labels":[],"label_agreement":null},{"id":"W2952519733","doi":"10.48550/arxiv.0809.1605","title":"MIC: Mutual Information based hierarchical Clustering","year":2008,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Mutual information; Hierarchical clustering; Computer science; Data mining; Artificial intelligence","score_opus":0.03872788420411607,"score_gpt":0.25887183760905447,"score_spread":0.2201439534049384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952519733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022761815,0.0013686497,0.99022114,0.00046147147,0.00013211957,0.00016033267,0.0005425741,0.0024553777,0.002382161],"genre_scores_gemma":[0.06725696,0.0013117002,0.9219804,0.00067169295,0.0004404709,0.00074327696,0.0028048316,0.0007476702,0.0040430585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945686,0.0017340024,0.00028505694,0.00089465326,0.002242929,0.00027480355],"domain_scores_gemma":[0.9966786,0.0013148133,0.00036957467,0.00070565473,0.000785239,0.00014606013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002921235,0.0018303397,0.002943802,0.0045712297,0.0018448506,0.0028252904,0.0054152044,0.0029818253,0.0050586183],"category_scores_gemma":[0.012633951,0.00087703654,0.00170537,0.006372574,0.0019632287,0.0035071797,0.004842755,0.002682419,0.004399248],"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":[0.00033292983,0.00013867214,0.0015006409,0.0006678333,0.0004270796,0.00024947184,0.0005705726,0.19749615,0.005780845,0.10727098,0.05513368,0.6304312],"study_design_scores_gemma":[0.00005252262,0.00011219657,0.0011300576,0.00011123409,0.000072697265,0.0003961645,0.00012778727,0.78691363,0.0053055226,0.16013736,0.045518473,0.00012234384],"about_ca_topic_score_codex":0.003151553,"about_ca_topic_score_gemma":0.0029847496,"teacher_disagreement_score":0.0054152044,"about_ca_system_score_codex":0.0016771101,"about_ca_system_score_gemma":0.0021795626,"threshold_uncertainty_score":0.016922772},"labels":[],"label_agreement":null},{"id":"W2952553535","doi":"10.48550/arxiv.1304.2798","title":"Optimal DNA shotgun sequencing: Noisy reads are as good as noiseless reads","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; Shotgun; DNA sequencing; Sequence (biology); DNA; Computational biology; Noise (video); Computer science; Channel (broadcasting); Algorithm; Biology; Genetics; Artificial intelligence; Gene; Computer network","score_opus":0.06393007705734222,"score_gpt":0.19893659689997611,"score_spread":0.1350065198426339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952553535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16648443,0.004728788,0.8081664,0.003166228,0.0004295662,0.000084851774,0.0005702388,0.0007442042,0.015625298],"genre_scores_gemma":[0.867853,0.0028879514,0.12219089,0.0022573518,0.0005479733,0.00028282215,0.00055610185,0.00039774427,0.003026192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894246,0.0031986826,0.00057364994,0.002144066,0.0038695901,0.00078937184],"domain_scores_gemma":[0.941139,0.04759594,0.0030993242,0.004994596,0.0021134184,0.0010577558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010837831,0.0010266664,0.0022971784,0.0018526511,0.0010530549,0.0041958275,0.00211518,0.00391879,0.0022808968],"category_scores_gemma":[0.06928849,0.0011366544,0.0008965787,0.0017306462,0.008185172,0.009514344,0.0046170717,0.0041965568,0.00080320716],"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":[0.00090379023,0.00013232148,0.002874045,0.0007765796,0.00012149497,0.00035223493,0.0005796182,0.12984851,0.032848045,0.7861652,0.0028067504,0.04259148],"study_design_scores_gemma":[0.000038469898,0.00015325469,0.00071166916,0.000097106466,0.000034213226,0.00030545844,0.00009775522,0.1891986,0.018216876,0.7885718,0.0025143523,0.00006055727],"about_ca_topic_score_codex":0.0005066024,"about_ca_topic_score_gemma":0.00030073934,"teacher_disagreement_score":0.010837831,"about_ca_system_score_codex":0.0016843564,"about_ca_system_score_gemma":0.0011362084,"threshold_uncertainty_score":0.05731666},"labels":[],"label_agreement":null},{"id":"W2952656830","doi":"10.48550/arxiv.0802.2829","title":"Understanding maximal repetitions in strings","year":2008,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Computer science","score_opus":0.22046088214419945,"score_gpt":0.19861443468950413,"score_spread":0.021846447454695328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952656830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15690854,0.004735414,0.7994511,0.0039253635,0.00021732676,0.00008531116,0.00037572405,0.0012636323,0.033037547],"genre_scores_gemma":[0.7861963,0.0028733723,0.19538227,0.0010375973,0.00095629616,0.00023445707,0.00056445267,0.00058343814,0.012171888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819523,0.00057778537,0.0001131211,0.00039613247,0.0005554285,0.00016228965],"domain_scores_gemma":[0.99210536,0.0059709703,0.00044332276,0.0009035163,0.00042530868,0.00015161477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016855034,0.00060606876,0.0007262899,0.001884171,0.0010439984,0.002614629,0.0013884731,0.0014813726,0.005687449],"category_scores_gemma":[0.012602832,0.0006976806,0.0006628323,0.0016654974,0.0040745335,0.011632462,0.0033574817,0.00290817,0.0016099672],"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":[0.00021483244,0.0000598088,0.002215427,0.00033226842,0.0000305449,0.00038140602,0.0019899255,0.018240063,0.01051072,0.8979565,0.0035017545,0.06456677],"study_design_scores_gemma":[0.00001852222,0.00004795363,0.00061811577,0.00006156228,0.000015002553,0.0003043034,0.00022309048,0.037954323,0.004289606,0.94602126,0.01041638,0.000029955401],"about_ca_topic_score_codex":0.0006500085,"about_ca_topic_score_gemma":0.00051402755,"teacher_disagreement_score":0.005687449,"about_ca_system_score_codex":0.00081334414,"about_ca_system_score_gemma":0.0004112249,"threshold_uncertainty_score":0.019026399},"labels":[],"label_agreement":null},{"id":"W2952658091","doi":"10.1002/spe.2289","title":"Compressed bitmap indexes: beyond unions and intersections","year":2014,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bitmap; Computer science; Computer graphics (images)","score_opus":0.009517417444694493,"score_gpt":0.2661045583367833,"score_spread":0.25658714089208884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952658091","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048479978,0.010499384,0.90386194,0.004247711,0.0010986712,0.00020126294,0.0017664793,0.009430941,0.020413684],"genre_scores_gemma":[0.31945848,0.008364722,0.64741707,0.0015908239,0.00148925,0.00042100291,0.004874927,0.0027236263,0.013660094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748504,0.00034724388,0.00025087455,0.0002766891,0.0014984799,0.00014154961],"domain_scores_gemma":[0.9916333,0.0027623787,0.0005347029,0.0028670046,0.0019728965,0.00022974423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016469761,0.0007524567,0.0010381577,0.003000726,0.00091801514,0.0046237693,0.0018215968,0.0007962973,0.010257162],"category_scores_gemma":[0.0123446025,0.00042216547,0.0005174791,0.008080705,0.0018087839,0.011189811,0.0029795251,0.0015921829,0.0038949857],"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":[0.0007089782,0.000101228776,0.0018100059,0.0005045352,0.000054476033,0.00027730456,0.0005867012,0.021805264,0.011965392,0.2664252,0.0636277,0.6321333],"study_design_scores_gemma":[0.00008657598,0.00020990636,0.0009870108,0.00038388063,0.00008371248,0.0011111202,0.00043371212,0.22631967,0.04349887,0.5311812,0.19558305,0.00012118825],"about_ca_topic_score_codex":0.0017752368,"about_ca_topic_score_gemma":0.001207597,"teacher_disagreement_score":0.010257162,"about_ca_system_score_codex":0.00088898325,"about_ca_system_score_gemma":0.0012784055,"threshold_uncertainty_score":0.03431362},"labels":[],"label_agreement":null},{"id":"W2952664795","doi":"10.1002/rsa.20305","title":"Network delay inference from additive metrics","year":2010,"lang":"en","type":"preprint","venue":"Random Structures and Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Natural Sciences and Engineering Research Council of Canada; Center for Integrated Protection Research of Engineering Structures; Division of Emerging Frontiers; Fonds Québécois de la Recherche sur la Nature et les Technologies; Harvard University; National Science Foundation","keywords":"Inference; Metric (unit); Multicast; Computer science; Network delay; Network topology; Algorithm; Time complexity; Mathematics; Topology (electrical circuits); Theoretical computer science; Artificial intelligence; Computer network; Combinatorics","score_opus":0.015375381536003947,"score_gpt":0.260441818624611,"score_spread":0.24506643708860706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952664795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029659506,0.0001661985,0.9687224,0.00028166958,0.000025881947,0.000021991169,0.0001887494,0.00026635427,0.00066736195],"genre_scores_gemma":[0.71413594,0.00033228885,0.28296703,0.00014488355,0.00013885918,0.000115582974,0.0008712024,0.00010551253,0.0011887143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714917,0.0011024172,0.0001647007,0.0006778153,0.00076204166,0.00014378334],"domain_scores_gemma":[0.9737464,0.019260475,0.002103901,0.0029637998,0.0015218928,0.00040349056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003992481,0.0007938131,0.0010445407,0.002953319,0.0006376329,0.0019007953,0.002037693,0.0009879373,0.0015602888],"category_scores_gemma":[0.042067375,0.0006415243,0.00072096277,0.0020537972,0.001738324,0.0045147385,0.0023067358,0.0020623852,0.00031131224],"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":[0.00026970237,0.00006401238,0.006172121,0.00012999095,0.000101091944,0.00010898981,0.00019203889,0.7357242,0.0029148487,0.16807936,0.0016955092,0.08454818],"study_design_scores_gemma":[0.00000984372,0.000019443078,0.000417451,0.000012299289,0.000009783009,0.000042243966,0.000019002464,0.87181234,0.0016840211,0.12522049,0.00074226037,0.00001081182],"about_ca_topic_score_codex":0.0018535535,"about_ca_topic_score_gemma":0.0013131609,"teacher_disagreement_score":0.003992481,"about_ca_system_score_codex":0.0018542734,"about_ca_system_score_gemma":0.0010548508,"threshold_uncertainty_score":0.021114528},"labels":[],"label_agreement":null},{"id":"W2952843666","doi":"10.48550/arxiv.0904.3062","title":"Approximate counting with a floating-point counter","year":2009,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"Université de Montréal","funders":"","keywords":"Point (geometry); Mathematics; Arithmetic; Computer science; Geometry","score_opus":0.026950663857941395,"score_gpt":0.2494700232265664,"score_spread":0.222519359368625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952843666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017265474,0.0013506301,0.97492844,0.00043618938,0.00016230212,0.000053288953,0.000085955675,0.0010956798,0.0046220957],"genre_scores_gemma":[0.40759528,0.001596819,0.5842393,0.00044361394,0.00024844235,0.00028768068,0.00023840787,0.00026053214,0.0050900043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960592,0.00068636297,0.00025680457,0.000531663,0.002185163,0.00028085528],"domain_scores_gemma":[0.990624,0.0054476727,0.0006868748,0.0020511048,0.0010967575,0.00009364256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027458235,0.0010086842,0.0011346499,0.0019626112,0.0010988932,0.003014104,0.0025106957,0.001422147,0.00271218],"category_scores_gemma":[0.023660924,0.0005718354,0.0005775988,0.00285483,0.0023835984,0.007060736,0.0019790875,0.0021482203,0.001235881],"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":[0.00078278314,0.000088886525,0.0030996618,0.0003117908,0.000093772906,0.00033301977,0.00029731888,0.20121765,0.019744089,0.5088276,0.0065435646,0.25865984],"study_design_scores_gemma":[0.000046180226,0.00010648933,0.00033989697,0.00010694609,0.000040735296,0.00036675791,0.0000467171,0.8185155,0.026259948,0.14372925,0.010369333,0.000072257695],"about_ca_topic_score_codex":0.0016375498,"about_ca_topic_score_gemma":0.0014447896,"teacher_disagreement_score":0.003014104,"about_ca_system_score_codex":0.001932868,"about_ca_system_score_gemma":0.0018021538,"threshold_uncertainty_score":0.01452148},"labels":[],"label_agreement":null},{"id":"W2952991946","doi":"10.3390/a12060124","title":"Lyndon Factorization Algorithms for Small Alphabets and Run-Length Encoded Strings","year":2019,"lang":"en","type":"article","venue":"Algorithms","topic":"Algorithms and Data Compression","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":"Sheridan College","funders":"","keywords":"Factorization; String (physics); Algorithm; Time complexity; Character (mathematics); Space (punctuation); Computer science; Combinatorics; Running time; Constant (computer programming); Mathematics; Edit distance; Discrete mathematics","score_opus":0.022270548047491047,"score_gpt":0.24867346058979645,"score_spread":0.2264029125423054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952991946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008761619,0.0004709338,0.98637635,0.000108740875,0.00007858566,0.000058743204,0.00011299555,0.0014884074,0.0025436028],"genre_scores_gemma":[0.09909737,0.00041366077,0.8936515,0.00018058416,0.00007920001,0.00021284916,0.00066053844,0.00033496955,0.0053694095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981881,0.0003463865,0.00020796999,0.00039299746,0.00064159685,0.00022288636],"domain_scores_gemma":[0.99723405,0.0010943018,0.00019058869,0.0007919732,0.00058608,0.00010310917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014585555,0.00087621587,0.0010862035,0.0017737808,0.0010032128,0.0020057238,0.0014940881,0.0011128751,0.004849016],"category_scores_gemma":[0.0075735627,0.000419312,0.0009304317,0.0020027424,0.0012735709,0.0037836598,0.0019693165,0.0014826265,0.0023005665],"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":[0.00094860885,0.00016602836,0.0010026504,0.0003488223,0.00006455162,0.00035909013,0.00049307704,0.059911545,0.032268055,0.20143677,0.010701345,0.6922995],"study_design_scores_gemma":[0.00017845457,0.00031142213,0.0005260983,0.00019465377,0.000048863047,0.0008078755,0.00028481954,0.6592748,0.07160707,0.21776742,0.048831787,0.00016669829],"about_ca_topic_score_codex":0.0032339368,"about_ca_topic_score_gemma":0.004554522,"teacher_disagreement_score":0.004849016,"about_ca_system_score_codex":0.0013768971,"about_ca_system_score_gemma":0.0016693121,"threshold_uncertainty_score":0.016221583},"labels":[],"label_agreement":null},{"id":"W2953124043","doi":"10.3233/fi-2011-617","title":"Pseudopower Avoidance","year":2012,"lang":"en","type":"preprint","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","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":"Western University","funders":"","keywords":"Alphabet; Mathematics; Sigma; Involution (esoterism); Combinatorics; Complementarity (molecular biology); Existential quantification; Discrete mathematics; Combinatorics on words; Word (group theory); Pure mathematics; Algorithm; Genetics; Physics; Biology; Linguistics; Philosophy","score_opus":0.023289971238546123,"score_gpt":0.2659659113730139,"score_spread":0.24267594013446778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953124043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1996761,0.0028928502,0.6825038,0.0012602116,0.0007850728,0.00012391897,0.00023268246,0.00065688684,0.111868456],"genre_scores_gemma":[0.9125825,0.0014763046,0.052355397,0.00062286656,0.00053399033,0.00014237536,0.0002637539,0.0002583992,0.031764377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913114,0.00017431502,0.000040793824,0.00018761739,0.00031598195,0.00015013057],"domain_scores_gemma":[0.9979583,0.00088374777,0.00023901377,0.00043362824,0.00030153204,0.00018375891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065999257,0.000508855,0.0005925283,0.0008476648,0.0009954083,0.0011233403,0.0010401966,0.0009932923,0.0064954534],"category_scores_gemma":[0.0034469508,0.00025005537,0.00083362893,0.00061078614,0.0022367863,0.0026350804,0.001899389,0.0010302543,0.0012127016],"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":[0.0000951604,0.000032500255,0.0005390628,0.00013887399,0.000020607495,0.0005242,0.00023118567,0.008997684,0.009533012,0.94644177,0.0020762922,0.031369604],"study_design_scores_gemma":[0.000030196314,0.00017938725,0.00043980003,0.000049587714,0.000022297048,0.0013150807,0.000116214775,0.065078415,0.007610911,0.9023033,0.022799985,0.00005479367],"about_ca_topic_score_codex":0.00024777727,"about_ca_topic_score_gemma":0.00020692952,"teacher_disagreement_score":0.0064954534,"about_ca_system_score_codex":0.00040552948,"about_ca_system_score_gemma":0.0004810136,"threshold_uncertainty_score":0.02172941},"labels":[],"label_agreement":null},{"id":"W2953361111","doi":"10.48550/arxiv.1006.3715","title":"Should Static Search Trees Ever Be Unbalanced?","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Tree (set theory); Search tree; Binary logarithm; Combinatorics; Mathematics; R-tree; Computer science; Algorithm; Statistics; Search algorithm","score_opus":0.13356184478082922,"score_gpt":0.23092658612007128,"score_spread":0.09736474133924206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953361111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47318545,0.0029786753,0.49527937,0.0056532845,0.00039719063,0.0002557819,0.0011931342,0.0029331008,0.018124005],"genre_scores_gemma":[0.8658252,0.0011904339,0.12417215,0.001444329,0.00036758455,0.00021539176,0.0011837151,0.00082214864,0.004779174],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664485,0.0006469369,0.00026390265,0.00061704486,0.0010289924,0.0007983098],"domain_scores_gemma":[0.97653574,0.012835511,0.0022282267,0.00548328,0.0021534716,0.0007637264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032061583,0.0005612762,0.0011273576,0.0008496495,0.0018628237,0.0021196464,0.0017207962,0.00198223,0.003810703],"category_scores_gemma":[0.03723001,0.0008908101,0.0005549915,0.0017701448,0.0021604225,0.010668282,0.0021886597,0.0015401343,0.0014741655],"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":[0.0034341936,0.0004310826,0.038615193,0.0011603582,0.00023294115,0.0015153362,0.0016460511,0.15468645,0.078027435,0.23011076,0.028129064,0.46201116],"study_design_scores_gemma":[0.00031593605,0.0010440382,0.009959483,0.00028365868,0.00032238525,0.0036479058,0.0017689825,0.3653699,0.045511663,0.49157676,0.08005528,0.0001440191],"about_ca_topic_score_codex":0.0017775993,"about_ca_topic_score_gemma":0.0028723723,"teacher_disagreement_score":0.003810703,"about_ca_system_score_codex":0.0010808515,"about_ca_system_score_gemma":0.0015301045,"threshold_uncertainty_score":0.016956031},"labels":[],"label_agreement":null},{"id":"W2953983509","doi":"10.21460/jutei.2019.31.148","title":"ANALISIS ALGORITMA MTF, MTF-1 DAN MTF-2 PADA BURROWS WHEELER COMPRESSION ALGORITHM","year":2019,"lang":"id","type":"article","venue":"Jurnal Terapan Teknologi Informasi","topic":"Algorithms and Data Compression","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":"Universitas Kristen Duta Wacana","keywords":"Algorithm; Physics; Lossless compression; Computer science; Mathematics; Data compression","score_opus":0.014144618407448578,"score_gpt":0.2473340132164599,"score_spread":0.23318939480901132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953983509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3526367,0.009408047,0.5690429,0.002097041,0.0015431066,0.0009445275,0.0064212154,0.021088762,0.036817625],"genre_scores_gemma":[0.45355284,0.0030790684,0.4984005,0.00045929558,0.00017942039,0.0006528329,0.010519899,0.0015556295,0.031600524],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876237,0.00008559094,0.00012771416,0.00018342248,0.0006839205,0.00015700691],"domain_scores_gemma":[0.9980884,0.00058996765,0.00010827307,0.00021156465,0.00095212314,0.00004970556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008896514,0.0012347472,0.0007085807,0.002561575,0.0010631057,0.0020510138,0.00089847646,0.00089286396,0.01009864],"category_scores_gemma":[0.0050482415,0.0002632564,0.00061951415,0.0033398136,0.00048719975,0.0021350638,0.000499606,0.00101655,0.0040796353],"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":[0.0008651199,0.00016645774,0.005142218,0.00053039164,0.00007578,0.0005296064,0.0004102048,0.013866733,0.052001033,0.0038287386,0.023620876,0.898963],"study_design_scores_gemma":[0.00023982818,0.00093042,0.02319721,0.00028235067,0.00027260662,0.0035098232,0.002100853,0.3811163,0.40512604,0.008310501,0.17469601,0.00021802488],"about_ca_topic_score_codex":0.012217658,"about_ca_topic_score_gemma":0.011760611,"teacher_disagreement_score":0.012217658,"about_ca_system_score_codex":0.0009871832,"about_ca_system_score_gemma":0.002017941,"threshold_uncertainty_score":0.033783317},"labels":[],"label_agreement":null},{"id":"W2963033861","doi":"10.1007/978-3-030-24886-4_9","title":"The Relative Edit-Distance Between Two Input-Driven Languages","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Edit distance; Programming language; Theoretical computer science","score_opus":0.014011162799821246,"score_gpt":0.2689131162496886,"score_spread":0.2549019534498674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963033861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045540188,0.00091638207,0.94072556,0.00043252902,0.00029011664,0.0000574274,0.0007389104,0.0018381475,0.00946065],"genre_scores_gemma":[0.4489684,0.0009192861,0.53251743,0.00034883813,0.00023383427,0.0001485833,0.0018961533,0.0012177097,0.013749777],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975533,0.00064030744,0.00020268076,0.00062932767,0.0008366592,0.00013771025],"domain_scores_gemma":[0.9940019,0.0032323182,0.00036952042,0.0012407041,0.0009383135,0.00021721411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015001511,0.00042966407,0.0004845303,0.0014238456,0.0004957424,0.0024222545,0.0016683049,0.001074646,0.0045418516],"category_scores_gemma":[0.010516962,0.00035314306,0.000788693,0.0015040546,0.000920328,0.0043537235,0.0016450564,0.0016240414,0.0015354011],"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":[0.0006164585,0.00015287293,0.0017367973,0.00084367144,0.00015277193,0.00063668273,0.0011764609,0.029973201,0.052348025,0.40875483,0.008678357,0.49492994],"study_design_scores_gemma":[0.00006584411,0.0005913562,0.0015276403,0.00023672808,0.00015466266,0.0021771912,0.00048786632,0.28850362,0.09531917,0.53917366,0.07161522,0.00014714448],"about_ca_topic_score_codex":0.0005697756,"about_ca_topic_score_gemma":0.00080510986,"teacher_disagreement_score":0.0045418516,"about_ca_system_score_codex":0.0007480394,"about_ca_system_score_gemma":0.00096020923,"threshold_uncertainty_score":0.015193999},"labels":[],"label_agreement":null},{"id":"W2963227782","doi":"10.4230/lipics.esa.2018.25","title":"Improved Time and Space Bounds for Dynamic Range Mode","year":2018,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Dalhousie University; University of Waterloo","funders":"","keywords":"Data structure; Linear space; Element (criminal law); Range query (database); Range (aeronautics); Computer science; Space (punctuation); Monte Carlo method; Algorithm; Binary logarithm; Theoretical computer science; Combinatorics; Mathematics; Information retrieval; Search engine; Web query classification; Statistics; Web search query","score_opus":0.007625279048213117,"score_gpt":0.25666534523955187,"score_spread":0.24904006619133875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963227782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063577406,0.0053742225,0.865008,0.005347298,0.0007495602,0.0007196478,0.003183713,0.02366634,0.032373745],"genre_scores_gemma":[0.31113017,0.0016263868,0.65794975,0.0024715173,0.0008920342,0.0012535705,0.00497804,0.003664141,0.01603441],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9752529,0.0038822405,0.0020810093,0.0048899716,0.00995695,0.0039368994],"domain_scores_gemma":[0.9449805,0.026576718,0.0023741208,0.02044718,0.004056244,0.0015652836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008664699,0.003622238,0.004054515,0.0038231304,0.0023313663,0.0067554438,0.0097697545,0.0028294756,0.024677172],"category_scores_gemma":[0.038579695,0.0022495333,0.005372074,0.0057338746,0.0034871357,0.026446862,0.014387568,0.007153964,0.00888705],"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":[0.006564333,0.001734348,0.008796167,0.0014144344,0.00035301995,0.00055371114,0.0015861527,0.12182403,0.043458927,0.18770081,0.06604396,0.5599701],"study_design_scores_gemma":[0.00076681067,0.0011857407,0.0011765722,0.00024864884,0.0003302144,0.0007914439,0.0004558836,0.7211312,0.020874621,0.22614022,0.026665254,0.00023337077],"about_ca_topic_score_codex":0.007659369,"about_ca_topic_score_gemma":0.0079000415,"teacher_disagreement_score":0.024677172,"about_ca_system_score_codex":0.0040334584,"about_ca_system_score_gemma":0.0068284455,"threshold_uncertainty_score":0.08255339},"labels":[],"label_agreement":null},{"id":"W2963278503","doi":"10.1109/glocomw.2018.8644185","title":"Deep Learning-Based Decoding for Constrained Sequence Codes","year":2018,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Decoding methods; Computer science; Sequential decoding; Convolutional code; List decoding; Encoding (memory); Sequence (biology); Deep learning; Algorithm; Serial concatenated convolutional codes; Convolutional neural network; Concatenated error correction code; Theoretical computer science; Artificial intelligence; Block code","score_opus":0.036197993825771234,"score_gpt":0.29975893353777144,"score_spread":0.26356093971200023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963278503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014327699,0.00041958055,0.9814579,0.00022142753,0.000053887463,0.00002838151,0.0001307467,0.00051936344,0.0028409837],"genre_scores_gemma":[0.5943116,0.000983894,0.39511466,0.0004654,0.000100155725,0.00016548073,0.0007198058,0.00022679858,0.007912272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993088,0.00014762797,0.000051665764,0.00010214935,0.00030799373,0.00008170818],"domain_scores_gemma":[0.99870276,0.00066782173,0.00009794232,0.0001778335,0.00031282744,0.00004074687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065119594,0.00060253585,0.0006226567,0.0005427711,0.00032180114,0.0007494607,0.0007678966,0.0008449447,0.0022127978],"category_scores_gemma":[0.004311268,0.00022980581,0.00030643263,0.00076812675,0.0008991722,0.0015309505,0.0010840115,0.00137404,0.0006848231],"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":[0.00017906727,0.000060590817,0.00058803725,0.00019189433,0.000043479453,0.00015888042,0.00011959081,0.61648154,0.018264031,0.13443384,0.0044481307,0.22503091],"study_design_scores_gemma":[0.000005800741,0.000020427333,0.0000459829,0.000015137643,0.0000032900043,0.000032061336,0.0000063919365,0.9694429,0.0063288026,0.02276744,0.0013245593,0.0000071646596],"about_ca_topic_score_codex":0.0042791534,"about_ca_topic_score_gemma":0.005815663,"teacher_disagreement_score":0.0042791534,"about_ca_system_score_codex":0.0010078124,"about_ca_system_score_gemma":0.0017481127,"threshold_uncertainty_score":0.008508503},"labels":[],"label_agreement":null},{"id":"W2963357518","doi":"10.1016/j.jnt.2018.03.002","title":"On (a,b) pairs in random Fibonacci sequences","year":2018,"lang":"en","type":"article","venue":"Journal of Number Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fibonacci number; Mathematics; Combinatorics; Fibonacci polynomials; Pisano period; Discrete mathematics","score_opus":0.01169797160708174,"score_gpt":0.27146823145588517,"score_spread":0.2597702598488034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963357518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5157761,0.0033370466,0.4094056,0.0026837906,0.0012728933,0.00028343181,0.0005416675,0.0005721528,0.06612734],"genre_scores_gemma":[0.9319816,0.001072524,0.048838716,0.0007542275,0.0004462015,0.00030497412,0.00049378985,0.0002026463,0.015905451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980508,0.0008194828,0.00009332552,0.0001998363,0.0005936067,0.00024304599],"domain_scores_gemma":[0.9911692,0.006721524,0.00053762464,0.00052906375,0.000592651,0.00044990747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018585366,0.001191587,0.0012367306,0.0040091127,0.002379435,0.0024059685,0.0013786047,0.0031350683,0.0068666325],"category_scores_gemma":[0.015039293,0.0008233191,0.0006671978,0.0029968198,0.0023689724,0.0034761275,0.0025422692,0.0017762935,0.0011613938],"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":[0.0005920624,0.00006272062,0.0013864902,0.00017929592,0.000028259428,0.0009031942,0.00045247332,0.028784946,0.005068188,0.93303955,0.005200735,0.024302045],"study_design_scores_gemma":[0.00010514194,0.00013478776,0.0007386792,0.00014188132,0.000026101981,0.0008732548,0.00021039207,0.16421157,0.0034259625,0.8258182,0.004247794,0.000066364315],"about_ca_topic_score_codex":0.0007972236,"about_ca_topic_score_gemma":0.0010213981,"teacher_disagreement_score":0.0068666325,"about_ca_system_score_codex":0.0011683033,"about_ca_system_score_gemma":0.00074356433,"threshold_uncertainty_score":0.022971153},"labels":[],"label_agreement":null},{"id":"W2963464696","doi":"","title":"A Note on Probabilistic Models over Strings: the Linear Algebra Approach","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"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":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid","keywords":"Graphical model; Linear algebra; Probabilistic logic; Inference; Normalization (sociology); Theoretical computer science; Bayesian inference; Computer science; Algebra over a field; String (physics); Numerical linear algebra; Algorithm; Mathematics; Bayesian probability; Linear system; Artificial intelligence; Pure mathematics","score_opus":0.023510150753670113,"score_gpt":0.2400926818704164,"score_spread":0.2165825311167463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963464696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037992485,0.0027846026,0.95984095,0.015026262,0.0007944541,0.000043305266,0.00036997377,0.00047097844,0.016870249],"genre_scores_gemma":[0.27075914,0.010583553,0.66404945,0.013267621,0.0121765835,0.0007072339,0.0014218412,0.0013744674,0.025660152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9876073,0.0049072113,0.0006786342,0.0022022563,0.0036656437,0.0009389176],"domain_scores_gemma":[0.9563352,0.036020838,0.0010848085,0.0040883124,0.0018554736,0.00061525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01036505,0.0018100801,0.0023013547,0.0029379828,0.0033317066,0.007826046,0.0053176098,0.0041271853,0.016610757],"category_scores_gemma":[0.03062868,0.0017222572,0.007142441,0.0047720843,0.011469662,0.037114557,0.007911732,0.020687204,0.0048826453],"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":[0.000020460411,0.000033186465,0.00013951559,0.0001171133,0.000024290299,0.000075337055,0.00018246048,0.004806955,0.00036002533,0.9795417,0.004424495,0.010274537],"study_design_scores_gemma":[0.0000039034853,0.00001029237,0.00003286627,0.000014412455,0.0000064282694,0.00003233313,0.000015429401,0.009424866,0.0001840582,0.98653156,0.0037263043,0.00001742127],"about_ca_topic_score_codex":0.004402365,"about_ca_topic_score_gemma":0.0031471953,"teacher_disagreement_score":0.016610757,"about_ca_system_score_codex":0.004429324,"about_ca_system_score_gemma":0.0026970485,"threshold_uncertainty_score":0.055568576},"labels":[],"label_agreement":null},{"id":"W2963530074","doi":"10.4230/lipics.isaac.2019.57","title":"On Approximate Range Mode and Range Selection","year":2019,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Dalhousie University; University of Waterloo","funders":"","keywords":"Range (aeronautics); Rank (graph theory); Combinatorics; Space (punctuation); Constant (computer programming); Mathematics; Position (finance); Selection (genetic algorithm); Range query (database); Sequence (biology); Element (criminal law); Discrete mathematics; Computer science; Search engine; Web search query; Chemistry; Sargable","score_opus":0.01617894227685548,"score_gpt":0.26434331517425186,"score_spread":0.24816437289739637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963530074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051541336,0.002829756,0.9187237,0.002715937,0.00013865129,0.00025125378,0.0013773188,0.0031864475,0.019235516],"genre_scores_gemma":[0.50372475,0.002435506,0.46839383,0.0024093399,0.00055159465,0.0012088331,0.004681071,0.0011057958,0.015489252],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930577,0.001446326,0.00045660415,0.0013418377,0.00283499,0.000862453],"domain_scores_gemma":[0.9843404,0.009729652,0.00089787063,0.003607491,0.0010964548,0.00032812468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00261229,0.0017274588,0.0023618808,0.0020071617,0.0013540231,0.0030025512,0.0037605478,0.002106585,0.010118131],"category_scores_gemma":[0.020096645,0.0008610274,0.0015708025,0.0054122466,0.0025552693,0.013829999,0.0056711123,0.0037506926,0.003289765],"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":[0.003050528,0.00051236735,0.007425438,0.00086022925,0.00014782745,0.00050952943,0.0015224803,0.14201465,0.03103298,0.32960525,0.035731472,0.4475873],"study_design_scores_gemma":[0.00019521487,0.00055096555,0.0016696937,0.00015105025,0.00012027935,0.001234445,0.0006172867,0.57551014,0.015351582,0.3734857,0.030990958,0.00012267259],"about_ca_topic_score_codex":0.0033393314,"about_ca_topic_score_gemma":0.0019938082,"teacher_disagreement_score":0.010118131,"about_ca_system_score_codex":0.0019635903,"about_ca_system_score_gemma":0.0017018262,"threshold_uncertainty_score":0.033848524},"labels":[],"label_agreement":null},{"id":"W2963537577","doi":"10.48550/arxiv.1606.04754","title":"A Correlational Encoder Decoder Architecture for Pivot Based Sequence\\n Generation","year":2016,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Sequence (biology); Architecture; Computer science; Soft-decision decoder; Arithmetic; Decoding methods; Computer architecture; Parallel computing; Algorithm; Mathematics; Operating system; Art; Genetics","score_opus":0.1357752411613671,"score_gpt":0.21803697333580846,"score_spread":0.08226173217444135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963537577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022589741,0.0005962287,0.9605793,0.00047760835,0.00019644348,0.000103549646,0.00037607402,0.0075966255,0.0074845017],"genre_scores_gemma":[0.5691147,0.00048161103,0.39818862,0.0006759274,0.000115248185,0.00023344113,0.001707015,0.00042791234,0.02905548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969506,0.000064026484,0.00001696098,0.00010700742,0.00006594604,0.0000511096],"domain_scores_gemma":[0.99949753,0.00017237547,0.000036560177,0.00010774664,0.00014808172,0.00003761737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007235452,0.0007006607,0.00056509604,0.0003873461,0.00039139518,0.0007938808,0.002006308,0.0012656727,0.006601035],"category_scores_gemma":[0.0014894707,0.00050781225,0.000551045,0.00041335533,0.0006360848,0.0012086504,0.0010382972,0.0017733934,0.0032368584],"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":[0.0006117323,0.00033641042,0.0017568278,0.0002639093,0.00016727476,0.00060176174,0.00025576944,0.36176962,0.038169447,0.043392416,0.013987279,0.53868765],"study_design_scores_gemma":[0.000023267366,0.000077638695,0.00014031294,0.000013561422,0.000023985858,0.000086575645,0.000011984314,0.9784389,0.011652149,0.0059565282,0.0035601396,0.000014870507],"about_ca_topic_score_codex":0.008219806,"about_ca_topic_score_gemma":0.01965897,"teacher_disagreement_score":0.008219806,"about_ca_system_score_codex":0.000959171,"about_ca_system_score_gemma":0.0019128524,"threshold_uncertainty_score":0.022082686},"labels":[],"label_agreement":null},{"id":"W2963542394","doi":"10.1016/j.disc.2019.111773","title":"Block-avoiding point sequencings of directed triple systems","year":2019,"lang":"en","type":"preprint","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Permutation (music); Combinatorics; Mathematics; Block (permutation group theory); Order (exchange); Directed graph; Graph; Transitive relation; Discrete mathematics; Physics","score_opus":0.026001093610206177,"score_gpt":0.2602901764056131,"score_spread":0.23428908279540692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963542394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36386845,0.0002579073,0.6046615,0.00022785737,0.00013621681,0.000121796584,0.00049170747,0.0006327672,0.029601807],"genre_scores_gemma":[0.86993676,0.00031860828,0.107988805,0.00014177745,0.000047507663,0.0001868559,0.0008014633,0.00036624895,0.0202119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99931574,0.00014461103,0.000054236792,0.00012560071,0.00022047649,0.00013931094],"domain_scores_gemma":[0.997621,0.0010148064,0.0002579658,0.00034123965,0.00048939674,0.00027566453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005904337,0.00043023727,0.0005546916,0.0016003662,0.0011553939,0.0016031777,0.0007957463,0.00093904376,0.007864226],"category_scores_gemma":[0.0038438728,0.00052686816,0.0006155461,0.0011283057,0.001043988,0.0018951884,0.0015627422,0.0013495224,0.0013716135],"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":[0.00013324353,0.000048575832,0.00080929004,0.00008240419,0.000016503958,0.0003271568,0.00033559947,0.020099478,0.007864424,0.94553685,0.0015133695,0.023233118],"study_design_scores_gemma":[0.000021399499,0.000047993006,0.0002464671,0.000030510168,0.000015067345,0.0001782116,0.00015141856,0.10064624,0.004752851,0.8898774,0.0040096524,0.00002281898],"about_ca_topic_score_codex":0.001276857,"about_ca_topic_score_gemma":0.0014168682,"teacher_disagreement_score":0.007864226,"about_ca_system_score_codex":0.00079648016,"about_ca_system_score_gemma":0.00072067487,"threshold_uncertainty_score":0.026308477},"labels":[],"label_agreement":null},{"id":"W2964005169","doi":"","title":"Bounding the Test Log-Likelihood of Generative Models","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Estimator; Normalization (sociology); Mathematics; Random variable; Bounding overwatch; Probability density function; Applied mathematics; Upper and lower bounds; Generative model; Algorithm; Latent variable; Computer science; Statistics; Artificial intelligence; Generative grammar","score_opus":0.05407829582841282,"score_gpt":0.17402319819289266,"score_spread":0.11994490236447984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964005169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04941503,0.00029774316,0.947253,0.00060679385,0.000029653358,0.00008519102,0.00015984869,0.0006365328,0.001516187],"genre_scores_gemma":[0.6895357,0.00027721183,0.30420145,0.000584794,0.00011574571,0.0005808485,0.0013831495,0.00043788875,0.0028832112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99290246,0.003921814,0.0003358567,0.0008846705,0.0015605945,0.00039446686],"domain_scores_gemma":[0.89701444,0.09357097,0.0020830953,0.004294518,0.002192527,0.0008444863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014072709,0.0012705559,0.0021355646,0.0017693216,0.00081388454,0.0033850232,0.0038518377,0.0033092992,0.003386346],"category_scores_gemma":[0.103492,0.0010341903,0.0010601585,0.001270746,0.0038520116,0.004354389,0.0053705378,0.0040268726,0.0011594887],"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":[0.0006450551,0.00024333874,0.016188672,0.00037019685,0.00020018675,0.0005488074,0.00043399518,0.7572481,0.007132748,0.102074996,0.0037730313,0.11114084],"study_design_scores_gemma":[0.000018174105,0.00003273327,0.00059613393,0.000029924911,0.000010540396,0.00011968641,0.000019448476,0.9584251,0.0029734499,0.037427396,0.00033232846,0.000015117555],"about_ca_topic_score_codex":0.0020505523,"about_ca_topic_score_gemma":0.0019258371,"teacher_disagreement_score":0.014072709,"about_ca_system_score_codex":0.0024248958,"about_ca_system_score_gemma":0.0018852619,"threshold_uncertainty_score":0.074424446},"labels":[],"label_agreement":null},{"id":"W2964110985","doi":"10.4230/lipics.stacs.2014.506","title":"Space-Efficient String Indexing for Wildcard Pattern Matching","year":2014,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Search engine indexing; Log-log plot; Binary logarithm; String (physics); Combinatorics; Alphabet; Mathematics; Pattern matching; Data structure; Matching (statistics); String searching algorithm; Computer science; Statistics; Information retrieval","score_opus":0.012138384331876216,"score_gpt":0.24470617512360687,"score_spread":0.23256779079173065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964110985","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07356841,0.0036508928,0.8954761,0.00096575444,0.0003962576,0.00040234957,0.002847724,0.013101835,0.009590651],"genre_scores_gemma":[0.2753137,0.0014875309,0.70695966,0.0006074267,0.0003463422,0.00044023167,0.0074522444,0.0011341197,0.006258756],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967272,0.0004681241,0.0004578189,0.0004919462,0.001561548,0.00029340002],"domain_scores_gemma":[0.9931131,0.002159142,0.00050860667,0.0032458433,0.0008124152,0.0001609757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012570771,0.0007693597,0.0018064582,0.0032318071,0.00096668286,0.0026528968,0.002687653,0.0012040776,0.0073940773],"category_scores_gemma":[0.010465317,0.0005469082,0.0007434148,0.008714428,0.0011135399,0.008844637,0.0031386497,0.0012512554,0.0035707585],"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":[0.001301447,0.0002880118,0.0023825075,0.00064686476,0.00009383488,0.00029613977,0.00042411807,0.013100956,0.038331214,0.06848066,0.024214637,0.85043955],"study_design_scores_gemma":[0.0004489743,0.0008959286,0.0020599589,0.00022964607,0.00017388522,0.0017676045,0.0005064648,0.43100902,0.1587183,0.3147836,0.0892387,0.00016788891],"about_ca_topic_score_codex":0.0012328617,"about_ca_topic_score_gemma":0.0013986157,"teacher_disagreement_score":0.0073940773,"about_ca_system_score_codex":0.001265616,"about_ca_system_score_gemma":0.0017218556,"threshold_uncertainty_score":0.02473563},"labels":[],"label_agreement":null},{"id":"W2964152270","doi":"","title":"Algorithms to Compute the Lyndon Array.","year":2016,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Suffix array; Compressed suffix array; Computation; Computer science; Suffix; Algorithm; Time complexity; Conjecture; Quadratic equation; Inverse; Data structure; Theoretical computer science; Mathematics; Discrete mathematics; Suffix tree","score_opus":0.047825790810012044,"score_gpt":0.28939569584184366,"score_spread":0.24156990503183162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964152270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036070272,0.00031182016,0.98769855,0.00012800956,0.0001019938,0.0001445848,0.00013960722,0.0032535228,0.0046147914],"genre_scores_gemma":[0.046200637,0.00031223422,0.9449395,0.00016316207,0.00007112859,0.00041445342,0.0009172105,0.0005471375,0.006434537],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794954,0.00032093385,0.00026942318,0.00040120134,0.0007993053,0.00025959],"domain_scores_gemma":[0.9958402,0.001230147,0.00030324416,0.0014521868,0.0010236443,0.00015059166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017637023,0.00122538,0.0010945116,0.002522884,0.0014506667,0.0030378886,0.002442578,0.0013686925,0.015921753],"category_scores_gemma":[0.010705761,0.00056479475,0.0011253147,0.002982442,0.001303644,0.005149497,0.004096819,0.0019193398,0.0082346145],"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":[0.000505137,0.00014567465,0.0019353033,0.0004846148,0.00007659264,0.00018198046,0.00048620772,0.015037527,0.019023217,0.14861678,0.01954235,0.79396456],"study_design_scores_gemma":[0.0002572949,0.00044980593,0.0014083756,0.00028136635,0.000121417484,0.0015512637,0.0007623527,0.40645424,0.08459791,0.35495445,0.14895232,0.00020922578],"about_ca_topic_score_codex":0.0016204772,"about_ca_topic_score_gemma":0.0035879845,"teacher_disagreement_score":0.015921753,"about_ca_system_score_codex":0.001344512,"about_ca_system_score_gemma":0.0026831923,"threshold_uncertainty_score":0.053263545},"labels":[],"label_agreement":null},{"id":"W2965108857","doi":"","title":"Probability Distillation: A Caveat and Alternatives.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Distillation; Reliability engineering; Environmental science; Engineering; Chemistry; Chromatography","score_opus":0.04868565856059613,"score_gpt":0.2873961231225094,"score_spread":0.23871046456191325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965108857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006894329,0.041712258,0.7151399,0.16466823,0.008953167,0.00015861818,0.0016623843,0.0006738988,0.060137134],"genre_scores_gemma":[0.35002378,0.029614206,0.53215647,0.044092245,0.014776051,0.0010156876,0.0010049776,0.00096687535,0.02634967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9874358,0.006229853,0.00065056275,0.0016374764,0.003711167,0.00033510223],"domain_scores_gemma":[0.9313373,0.050730012,0.0012192008,0.012122993,0.0040721577,0.0005184327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02135887,0.0012005183,0.0018150338,0.001830407,0.0022727686,0.005487385,0.0067654145,0.004771383,0.011725666],"category_scores_gemma":[0.11542667,0.00076593907,0.0011680907,0.0035678686,0.013850858,0.021072192,0.007137232,0.016282836,0.0029842474],"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":[0.00009204546,0.00002655831,0.00023088534,0.0002696853,0.000059722577,0.00005158828,0.00012450044,0.0020388155,0.00014072504,0.9412077,0.023471761,0.03228589],"study_design_scores_gemma":[0.000023266108,0.00001439773,0.00007429691,0.00010454188,0.000012358528,0.00008354574,0.000038870276,0.0054230886,0.0003268017,0.97704417,0.016833946,0.000020676556],"about_ca_topic_score_codex":0.002518913,"about_ca_topic_score_gemma":0.0038156086,"teacher_disagreement_score":0.02135887,"about_ca_system_score_codex":0.0012433882,"about_ca_system_score_gemma":0.0026325777,"threshold_uncertainty_score":0.112957835},"labels":[],"label_agreement":null},{"id":"W2966205006","doi":"10.1145/3595180","title":"Competitive Online Search Trees on Trees","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; Fonds De La Recherche Scientifique - FNRS; York University; National Science Foundation","keywords":"Ternary search tree; Weight-balanced tree; Binary search tree; Optimal binary search tree; Range tree; Self-balancing binary search tree; K-ary tree; Mathematics; Binary tree; Tree (set theory); Combinatorics; Generalization; Vertex (graph theory); Search tree; Path (computing); Interval tree; Set (abstract data type); Search algorithm; Computer science; Tree structure; Algorithm; Graph","score_opus":0.04541435443245161,"score_gpt":0.30852846220716484,"score_spread":0.2631141077747132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966205006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049793243,0.00089427864,0.9412731,0.00053193764,0.00006929532,0.00014033113,0.0004573897,0.00068899913,0.006151457],"genre_scores_gemma":[0.51718664,0.0010312046,0.47214523,0.00039588055,0.00017096277,0.00042792427,0.00095797534,0.00026100676,0.0074232216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976526,0.00079395453,0.00014698438,0.0003892016,0.0007002763,0.00031707567],"domain_scores_gemma":[0.994968,0.0028438843,0.0004105822,0.0009299343,0.0005196282,0.00032791676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018173825,0.0006193981,0.0016347163,0.00095997966,0.00070297555,0.0021058654,0.0023647086,0.0012612189,0.0043313084],"category_scores_gemma":[0.012753038,0.0005474,0.00069339556,0.0029438536,0.0010999517,0.0058052535,0.0020604206,0.0013673214,0.0012590715],"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":[0.00051541725,0.00030903495,0.0019313868,0.00039575965,0.00007961198,0.00018023151,0.00032551755,0.39083818,0.0050385566,0.4140162,0.01309879,0.17327128],"study_design_scores_gemma":[0.00006162872,0.00016423278,0.00015825595,0.000016283284,0.000015839765,0.00012206677,0.00004031501,0.84242594,0.001169907,0.15070368,0.0051074536,0.000014340774],"about_ca_topic_score_codex":0.0017765125,"about_ca_topic_score_gemma":0.0020024334,"teacher_disagreement_score":0.0043313084,"about_ca_system_score_codex":0.0013130377,"about_ca_system_score_gemma":0.001391521,"threshold_uncertainty_score":0.01448971},"labels":[],"label_agreement":null},{"id":"W2970626848","doi":"10.1080/24701475.2019.1639352","title":"Internet histories and computational methods: a “round-doc” discussion","year":2019,"lang":"en","type":"article","venue":"Internet Histories","topic":"Algorithms and Data Compression","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":"Western University; University of Waterloo","funders":"Università di Bologna","keywords":"The Internet; Computer science; World Wide Web; Data science","score_opus":0.018545533403510773,"score_gpt":0.27986366228821186,"score_spread":0.2613181288847011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970626848","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052565266,0.0066964165,0.007952961,0.9350576,0.023727776,0.000169864,0.00005584079,0.00006396844,0.02101904],"genre_scores_gemma":[0.2524408,0.01614208,0.015994716,0.63127756,0.037344158,0.0018224779,0.00016363991,0.00083489827,0.04397977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9583661,0.03140798,0.0008203137,0.0015915282,0.0034754681,0.004338615],"domain_scores_gemma":[0.8944386,0.09041148,0.0016446024,0.0017407603,0.0046068626,0.0071576843],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.062216606,0.0017063869,0.0015112018,0.0028466445,0.04056923,0.023866817,0.004436005,0.034648206,0.015344572],"category_scores_gemma":[0.07436905,0.0014222926,0.0019896177,0.0032674805,0.02120729,0.036310747,0.027956588,0.04650951,0.0026128103],"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":[0.00015426095,0.00012180431,0.00038005214,0.00038093756,0.000035993373,0.0016554757,0.15818913,0.0005653318,0.00075835024,0.51500934,0.2952398,0.02750957],"study_design_scores_gemma":[0.000021534317,0.000044262222,0.00022267835,0.00072493945,0.000010924618,0.0002388188,0.094581366,0.00042238532,0.00020103043,0.041741893,0.86172205,0.000068083216],"about_ca_topic_score_codex":0.0045001335,"about_ca_topic_score_gemma":0.0053086258,"teacher_disagreement_score":0.9377834,"about_ca_system_score_codex":0.013234892,"about_ca_system_score_gemma":0.011326713,"threshold_uncertainty_score":0.32903683},"labels":[],"label_agreement":null},{"id":"W2974083459","doi":"10.1002/spe.960","title":"A survey of practical algorithms for suffix tree construction in external memory","year":2010,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Suffix; Suffix tree; Computer science; Auxiliary memory; Scalability; Generalized suffix tree; Trie; Algorithm; Tree (set theory); Theoretical computer science; Data structure; Mathematics; Programming language; Database; Operating system","score_opus":0.03567803922419386,"score_gpt":0.34467880862528155,"score_spread":0.30900076940108767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974083459","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010595705,0.0076607284,0.96889603,0.00030661866,0.00009741176,0.00015521882,0.0002239557,0.006380686,0.0056835767],"genre_scores_gemma":[0.06437167,0.007670895,0.92203325,0.00021563974,0.00019284416,0.00034060594,0.0014471315,0.0009883292,0.0027396102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689215,0.0007501087,0.00039237848,0.0005491477,0.001166286,0.0002498821],"domain_scores_gemma":[0.99213713,0.0040151477,0.00051099603,0.0021239847,0.0010939584,0.00011869297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025255338,0.001622149,0.0016111004,0.0031048807,0.0011336694,0.0031309817,0.00394144,0.0017283659,0.006407551],"category_scores_gemma":[0.012408273,0.0011434898,0.0013648226,0.0068911747,0.0012407611,0.0058132973,0.0025395174,0.0019029151,0.0047347643],"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":[0.00024355178,0.00016059593,0.0010441873,0.0011768587,0.000065019674,0.00008456138,0.00023112936,0.025268152,0.008642182,0.04593757,0.0104337605,0.90671235],"study_design_scores_gemma":[0.00030790738,0.00066495355,0.0016813788,0.0007955412,0.0001660491,0.00222967,0.00040107523,0.61721957,0.06854552,0.19274971,0.11506093,0.00017768928],"about_ca_topic_score_codex":0.00094329077,"about_ca_topic_score_gemma":0.0010273198,"teacher_disagreement_score":0.006407551,"about_ca_system_score_codex":0.0011794234,"about_ca_system_score_gemma":0.0019192905,"threshold_uncertainty_score":0.02143544},"labels":[],"label_agreement":null},{"id":"W2974997458","doi":"10.1109/isit.2019.8849410","title":"Universal D-Semifaithfull Coding for Countably Infinite Alphabets","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Variable-length code; Universality (dynamical systems); Shannon–Fano coding; Coding (social sciences); Impossibility; Mathematics; Minimax; Converse; Discrete mathematics; Source code; Theoretical computer science; Computer science; Physics; Mathematical optimization; Quantum mechanics","score_opus":0.01168022105320477,"score_gpt":0.23441193800888263,"score_spread":0.22273171695567787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974997458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19972117,0.0007589168,0.79250526,0.00049950747,0.000031985368,0.00002697083,0.00021768786,0.00022432339,0.006014199],"genre_scores_gemma":[0.9573845,0.000498563,0.0400311,0.00012681008,0.00004132884,0.000054195385,0.00018197857,0.000040737286,0.0016408277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992238,0.00021001161,0.00008673286,0.00015170689,0.00021913607,0.0001085127],"domain_scores_gemma":[0.9937173,0.0045280512,0.00047895062,0.00073055906,0.00035368523,0.00019135737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001552212,0.00042937728,0.0006615991,0.0009766439,0.00043259087,0.001052549,0.00096572,0.00065887073,0.0011630206],"category_scores_gemma":[0.009660499,0.00032198065,0.00053357816,0.0006754394,0.0018083069,0.0028034868,0.0024574029,0.001186206,0.00015733481],"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":[0.00018961204,0.000034687037,0.00092310394,0.00016806932,0.000033566004,0.00031172758,0.00027073934,0.10628425,0.013395721,0.8459719,0.00067901483,0.03173772],"study_design_scores_gemma":[0.000023902256,0.00006764743,0.000444516,0.000055052595,0.000012097396,0.00029340768,0.00007862476,0.49507603,0.01116957,0.4915143,0.0012312736,0.000033620705],"about_ca_topic_score_codex":0.0005115543,"about_ca_topic_score_gemma":0.00033624572,"teacher_disagreement_score":0.001552212,"about_ca_system_score_codex":0.0009091703,"about_ca_system_score_gemma":0.0005859394,"threshold_uncertainty_score":0.00820899},"labels":[],"label_agreement":null},{"id":"W2975339399","doi":"10.1109/isit.2019.8849546","title":"Adaptive Sequence Phase Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Subsequence; Detector; Sequence (biology); Phase detector; Noise (video); Computer science; Algorithm; Phase (matter); Artificial intelligence; Mathematics; Physics; Telecommunications","score_opus":0.028357628550529937,"score_gpt":0.28251084558610734,"score_spread":0.2541532170355774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975339399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008577215,0.00017187826,0.98997974,0.000079579106,0.000028857508,0.000047961847,0.000041769126,0.0001976138,0.000875359],"genre_scores_gemma":[0.3027194,0.0005018611,0.69274575,0.000262771,0.00013044097,0.00022293195,0.00026498403,0.00011394529,0.0030378515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878365,0.00031203634,0.000061145074,0.00029454898,0.0004690765,0.00007946397],"domain_scores_gemma":[0.99688137,0.0016480745,0.00039252845,0.00044984708,0.0005483893,0.00007972107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263611,0.00070328417,0.00068869203,0.0007527059,0.00039524236,0.0006876561,0.0011322782,0.0010247544,0.0018251574],"category_scores_gemma":[0.009441818,0.000424102,0.00032657367,0.00082930113,0.0010537324,0.0017478241,0.001149888,0.0008131551,0.0008636371],"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":[0.00122523,0.00020606664,0.0025434298,0.00039505766,0.00007920119,0.00033112316,0.00023304782,0.17816861,0.17165935,0.10092617,0.004438482,0.5397943],"study_design_scores_gemma":[0.000108848966,0.00040890792,0.00073151995,0.000060451635,0.000032612334,0.0008945635,0.000053894728,0.84771836,0.0990966,0.039226227,0.011613147,0.000054895685],"about_ca_topic_score_codex":0.00044813292,"about_ca_topic_score_gemma":0.00051780546,"teacher_disagreement_score":0.0018251574,"about_ca_system_score_codex":0.00042393163,"about_ca_system_score_gemma":0.0009665456,"threshold_uncertainty_score":0.0066826344},"labels":[],"label_agreement":null},{"id":"W2976444311","doi":"10.1109/isit.2019.8849430","title":"Fast Construction of Almost Optimal Symbol Distributions for Asymmetric Numeral Systems","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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 Laval","funders":"","keywords":"Symbol (formal); Numeral system; Focus (optics); Task (project management); Computer science; Arithmetic; Algorithm; Encoder; Theoretical computer science; Mathematics; Engineering; Programming language","score_opus":0.008390866380249815,"score_gpt":0.23258978095768634,"score_spread":0.22419891457743651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976444311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023636222,0.00013655637,0.97320145,0.00012688387,0.000032571992,0.000036530982,0.00008566418,0.0005179357,0.0022262505],"genre_scores_gemma":[0.46619192,0.00044102248,0.52889735,0.00020099252,0.00010645766,0.0001757431,0.0003829414,0.00035892695,0.0032445868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987519,0.0004888594,0.000074622345,0.00013020638,0.00042623968,0.00012809985],"domain_scores_gemma":[0.99751604,0.0015297388,0.00015455575,0.0004159889,0.00028604813,0.00009759605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143941,0.00055091584,0.0007410386,0.000738457,0.00037329175,0.0009472183,0.0007352795,0.00058059476,0.0028189765],"category_scores_gemma":[0.0074097514,0.00035953522,0.0003382286,0.0007075938,0.0011305145,0.0015137353,0.0022804607,0.0012698228,0.00116003],"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":[0.000476752,0.000116349634,0.0011604867,0.00025662035,0.000050591843,0.00038739244,0.0003832317,0.14648041,0.040173527,0.43574074,0.005111157,0.3696627],"study_design_scores_gemma":[0.000045206132,0.000095655225,0.0002783878,0.000039292852,0.000011560839,0.0002813314,0.00005231425,0.74184287,0.0317272,0.22013429,0.00546395,0.000027960654],"about_ca_topic_score_codex":0.00024115597,"about_ca_topic_score_gemma":0.00046642704,"teacher_disagreement_score":0.0028189765,"about_ca_system_score_codex":0.0005351446,"about_ca_system_score_gemma":0.00083320966,"threshold_uncertainty_score":0.0094304085},"labels":[],"label_agreement":null},{"id":"W2976570834","doi":"10.1109/isit.2019.8849758","title":"Decision Procedure for the Existence of Two-Channel Prefix-Free Codes","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Prefix; Prefix code; Rectangle; Code (set theory); Computer science; Decision problem; Algorithm; Channel (broadcasting); Linear inequality; Mathematics; Mathematical optimization; Theoretical computer science; Inequality; Linear code; Block code; Telecommunications; Programming language; Decoding methods","score_opus":0.020712089648582975,"score_gpt":0.27491258908973043,"score_spread":0.2542004994411475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976570834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020446917,0.00012317048,0.975869,0.00025543696,0.00003200124,0.00016612266,0.00015320657,0.00021319203,0.0027409208],"genre_scores_gemma":[0.29090786,0.0002442907,0.70496947,0.00017944566,0.00006347862,0.00038697402,0.0005159727,0.00009231057,0.0026402324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99631834,0.0012195574,0.00032959165,0.00076967216,0.0008551228,0.0005076824],"domain_scores_gemma":[0.98609936,0.010895634,0.0007111366,0.000953791,0.0010620954,0.00027797272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003285485,0.0007585699,0.0010854867,0.00107582,0.0010166934,0.0018442282,0.0014610752,0.0014277828,0.006317653],"category_scores_gemma":[0.014905881,0.00057797274,0.00075786334,0.0013383089,0.0019490618,0.0034136323,0.0031898166,0.0029626403,0.0010511772],"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":[0.0016303301,0.00032613493,0.0010037206,0.0005438934,0.00013499241,0.0005236201,0.00051378855,0.17318033,0.032520756,0.50914943,0.00718635,0.27328664],"study_design_scores_gemma":[0.00027701532,0.00030640146,0.00033476687,0.00007886628,0.000040556675,0.00032097157,0.00012721485,0.72643954,0.036660995,0.23116992,0.0041525303,0.00009110992],"about_ca_topic_score_codex":0.0005911886,"about_ca_topic_score_gemma":0.00065549515,"teacher_disagreement_score":0.006317653,"about_ca_system_score_codex":0.00088073086,"about_ca_system_score_gemma":0.0019451549,"threshold_uncertainty_score":0.021134615},"labels":[],"label_agreement":null},{"id":"W2977258328","doi":"10.48550/arxiv.1910.01147","title":"Path and Ancestor Queries on Trees with Multidimensional Weight Vectors","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Combinatorics; Mathematics; Linear space; Path (computing); Order (exchange); Tree (set theory); Discrete mathematics; Computer science","score_opus":0.0391618951987208,"score_gpt":0.17085556053428316,"score_spread":0.13169366533556237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977258328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27302235,0.0016409286,0.7056137,0.0040883687,0.00018290356,0.00047911736,0.0032396852,0.0037069672,0.008025902],"genre_scores_gemma":[0.60806835,0.00076018064,0.37716857,0.00080183684,0.00026948136,0.00042327578,0.0042206286,0.00044378382,0.00784396],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993415,0.0016205797,0.0005881524,0.0013428954,0.0020107501,0.0010226815],"domain_scores_gemma":[0.9883966,0.0073608956,0.00091286405,0.0019869641,0.000893576,0.00044901943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037022948,0.0010856998,0.0019915067,0.0013714515,0.0017896873,0.003562836,0.0029848304,0.0020666046,0.00436313],"category_scores_gemma":[0.02088014,0.00072473875,0.0013072304,0.0047400906,0.0010810472,0.014395684,0.0041256235,0.002194646,0.00095656456],"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":[0.0019101735,0.00097035343,0.012200424,0.0012101047,0.00027700287,0.0015275413,0.0031287028,0.23205748,0.025355855,0.27426425,0.043920282,0.40317774],"study_design_scores_gemma":[0.00014098104,0.00024925973,0.00083800463,0.000042384032,0.000065287924,0.00066326594,0.0007981797,0.8210697,0.006278397,0.15997806,0.00982344,0.000053061347],"about_ca_topic_score_codex":0.005790068,"about_ca_topic_score_gemma":0.0066180006,"teacher_disagreement_score":0.005790068,"about_ca_system_score_codex":0.001956652,"about_ca_system_score_gemma":0.0017899461,"threshold_uncertainty_score":0.019579828},"labels":[],"label_agreement":null},{"id":"W2977350080","doi":"10.4230/lipics.approx-random.2019.56","title":"String Matching: Communication, Circuits, and Learning","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"String searching algorithm; Upper and lower bounds; VC dimension; Communication complexity; Matching (statistics); String (physics); Sample complexity; Mathematics; Computational complexity theory; Circuit complexity; Pattern matching; Dimension (graph theory); Classifier (UML); Discrete mathematics; Theoretical computer science; Computer science; Electronic circuit; Algorithm; Combinatorics; Artificial intelligence","score_opus":0.009260590006367071,"score_gpt":0.23186566141304576,"score_spread":0.2226050714066787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977350080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104195565,0.010482106,0.82668424,0.01688923,0.000612965,0.0002840525,0.0012578156,0.0015770788,0.038017087],"genre_scores_gemma":[0.7592721,0.007292592,0.20801617,0.0021188646,0.0017604484,0.00068319973,0.0018741492,0.00049108686,0.018491354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950873,0.0015320585,0.00025482124,0.0012013996,0.0013002261,0.0006241398],"domain_scores_gemma":[0.9697667,0.02456714,0.0014844221,0.002887587,0.000778472,0.00051569106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00302425,0.0014499968,0.0016280334,0.0016176692,0.0015462281,0.0059411423,0.0028595903,0.003951639,0.008731903],"category_scores_gemma":[0.026355868,0.0007657026,0.0011332683,0.0043581966,0.005366049,0.014897698,0.003260267,0.0050013117,0.0013296385],"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":[0.00060285925,0.00024147013,0.00176703,0.0005229793,0.000089921195,0.0001437197,0.00022314879,0.18670012,0.0038958073,0.61344105,0.01540749,0.17696449],"study_design_scores_gemma":[0.00005117033,0.00006493363,0.0003907915,0.00006317107,0.00002289699,0.00010447063,0.000059446484,0.27681634,0.0037227636,0.71352124,0.0051542995,0.00002858215],"about_ca_topic_score_codex":0.0025336635,"about_ca_topic_score_gemma":0.0017779581,"teacher_disagreement_score":0.008731903,"about_ca_system_score_codex":0.0058950353,"about_ca_system_score_gemma":0.0025396468,"threshold_uncertainty_score":0.042771637},"labels":[],"label_agreement":null},{"id":"W2979888527","doi":"10.1007/978-3-030-32686-9_3","title":"Rpair: Rescaling RePair with Rsync","year":2019,"lang":"en","type":"book-chapter","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Parsing; Hash function; Leverage (statistics); Computation; Data compression; Algorithm; Scheme (mathematics); Piecewise; Compression (physics); Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.04805417272412938,"score_gpt":0.25484428432126,"score_spread":0.20679011159713062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979888527","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011766333,0.00092351524,0.8853281,0.00034648142,0.0012916093,0.00018358913,0.0010078372,0.06863622,0.030516263],"genre_scores_gemma":[0.24292494,0.00056806556,0.6520841,0.00061702606,0.0004062758,0.00032707452,0.0038436193,0.0133955795,0.085833356],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992442,0.00008055289,0.000056618774,0.00015237072,0.00035684142,0.00010939564],"domain_scores_gemma":[0.9991136,0.00016412366,0.00004836786,0.00046919167,0.00017062646,0.000034032826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069481216,0.001224834,0.00076151197,0.0009921177,0.0005878191,0.0011717147,0.002050447,0.0009891344,0.037828792],"category_scores_gemma":[0.0024252879,0.000359243,0.0005074227,0.0010148871,0.0007543456,0.0018069245,0.0019531175,0.0012401685,0.012497429],"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":[0.00067785615,0.000114983435,0.00035207253,0.00030170413,0.000045000645,0.00040722077,0.0001777381,0.023100924,0.029781383,0.040798742,0.09092303,0.8133193],"study_design_scores_gemma":[0.00020739133,0.0004078422,0.0008597706,0.00020277375,0.0001057121,0.0018218537,0.00026854512,0.36543235,0.21006016,0.079428144,0.3410274,0.00017804338],"about_ca_topic_score_codex":0.0014004516,"about_ca_topic_score_gemma":0.0015848684,"teacher_disagreement_score":0.037828792,"about_ca_system_score_codex":0.0004565859,"about_ca_system_score_gemma":0.00072363176,"threshold_uncertainty_score":0.12654996},"labels":[],"label_agreement":null},{"id":"W2979933668","doi":"10.1109/ccece.2019.8861851","title":"Design and Evaluation of an FPGA-based Hardware Accelerator for Deflate Data Decompression","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Field-programmable gate array; Virtex; Computer hardware; Data compression; Benchmark (surveying); Embedded system; Uncompressed video; Video processing; Artificial intelligence","score_opus":0.13750307149090393,"score_gpt":0.3615872089889931,"score_spread":0.22408413749808917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979933668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695924,0.0017696994,0.19158645,0.00063289783,0.00042593945,0.00092159974,0.000807144,0.0077845794,0.026479246],"genre_scores_gemma":[0.8938162,0.00045729935,0.094019644,0.00019565866,0.00003291083,0.00016128492,0.00071245356,0.00014388547,0.010460611],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99980384,0.000023267321,0.0000125194765,0.000029884612,0.00008717939,0.000043358454],"domain_scores_gemma":[0.9997094,0.00006594259,0.000048726397,0.00003079637,0.000118157266,0.000026984364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021937846,0.0004359515,0.00025132095,0.00042803443,0.0001982441,0.00042492757,0.0007799181,0.0002390697,0.004349554],"category_scores_gemma":[0.00058515446,0.00014028682,0.00013725461,0.00028523797,0.00014957374,0.0004277768,0.00016325893,0.00024196692,0.0006260008],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019347669,0.00055779214,0.007499099,0.0014983793,0.00016963259,0.0013082902,0.00024912533,0.12023229,0.5309616,0.007885997,0.014401331,0.31330165],"study_design_scores_gemma":[0.00056032155,0.0050134803,0.007214584,0.00011538139,0.00013338907,0.0008523928,0.00014728062,0.4291186,0.5133836,0.0006167689,0.042781413,0.00006266821],"about_ca_topic_score_codex":0.0016338372,"about_ca_topic_score_gemma":0.002028335,"teacher_disagreement_score":0.004349554,"about_ca_system_score_codex":0.00046236353,"about_ca_system_score_gemma":0.0008109103,"threshold_uncertainty_score":0.0145507455},"labels":[],"label_agreement":null},{"id":"W2980570835","doi":"10.1109/ispa.2019.8868744","title":"Lossless Compression of Grayscale and Colour Images Using Multidimensional CSE","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Université Laval","funders":"","keywords":"Grayscale; Lossless compression; Computer science; Substring; Artificial intelligence; Pixel; Dimension (graph theory); Data compression; Pattern recognition (psychology); Computer vision; Algorithm; Mathematics; Data structure","score_opus":0.011339051833961217,"score_gpt":0.24604408713578385,"score_spread":0.23470503530182263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980570835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058490444,0.0021929513,0.9155364,0.0009312127,0.0009810629,0.00017028525,0.001205088,0.005176824,0.015315643],"genre_scores_gemma":[0.35803053,0.0028727055,0.6138547,0.0010443995,0.0004549669,0.00022829267,0.0033316042,0.0006184482,0.01956439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993917,0.00005486836,0.000050476476,0.000060551447,0.00038220434,0.000060148566],"domain_scores_gemma":[0.9987055,0.00036581027,0.00006704287,0.00044887105,0.0003735181,0.000039271923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005184598,0.00070005364,0.0006303324,0.0019461449,0.00030337257,0.0013589866,0.0008484388,0.00082966156,0.004614686],"category_scores_gemma":[0.002757427,0.00020519464,0.00061618764,0.002855794,0.00051551795,0.0019634706,0.0012826938,0.0008953166,0.0021587557],"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":[0.0007388599,0.00020487209,0.00084466115,0.00045077855,0.00006552972,0.0010902712,0.00033414082,0.039286762,0.22339992,0.040454593,0.021947393,0.67118216],"study_design_scores_gemma":[0.00008813406,0.0002822258,0.0023357333,0.00013504774,0.000046624533,0.0019378995,0.00021443483,0.482753,0.43316567,0.022031456,0.05688118,0.00012851576],"about_ca_topic_score_codex":0.00094638695,"about_ca_topic_score_gemma":0.0010625366,"teacher_disagreement_score":0.004614686,"about_ca_system_score_codex":0.00043366995,"about_ca_system_score_gemma":0.0003477908,"threshold_uncertainty_score":0.015437663},"labels":[],"label_agreement":null},{"id":"W2985159807","doi":"10.1002/cpe.6304","title":"Efficient computation of positional population counts using SIMD instructions","year":2021,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"National Research Council Canada","keywords":"SIMD; Byte; Computation; Population; Categorical variable; Generalization; Code (set theory)","score_opus":0.028173393668598026,"score_gpt":0.3417117682646383,"score_spread":0.3135383745960403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985159807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11298183,0.00063770515,0.845544,0.00058047654,0.00022528532,0.00012807379,0.001305647,0.02758667,0.011010406],"genre_scores_gemma":[0.44820148,0.00018907031,0.54342127,0.0002328009,0.00006980953,0.00034903525,0.0023625444,0.0008831918,0.004290773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848133,0.00021442478,0.00012901826,0.00023847447,0.000788124,0.00014871637],"domain_scores_gemma":[0.99661726,0.0012375505,0.00022609286,0.0007677892,0.0010050962,0.0001462513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079455087,0.00091750314,0.00066194026,0.0017185998,0.0007299901,0.0016096989,0.0016759479,0.00047741766,0.008015436],"category_scores_gemma":[0.005603847,0.00044988308,0.0005836077,0.0026628142,0.000846723,0.0022855613,0.0013928249,0.001009148,0.0032892723],"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":[0.0012663833,0.00022647379,0.010750537,0.00038343275,0.00012370263,0.0003194301,0.00038558233,0.13714379,0.035068303,0.059151158,0.041124467,0.7140568],"study_design_scores_gemma":[0.000090170135,0.000097393444,0.00077771,0.000033041124,0.000017329512,0.000089420646,0.000092056056,0.91529787,0.039930563,0.034935437,0.008606306,0.00003263028],"about_ca_topic_score_codex":0.0027240692,"about_ca_topic_score_gemma":0.0043351417,"teacher_disagreement_score":0.008015436,"about_ca_system_score_codex":0.0014492881,"about_ca_system_score_gemma":0.0025958242,"threshold_uncertainty_score":0.026814282},"labels":[],"label_agreement":null},{"id":"W2987134948","doi":"10.4230/lipics.icalp.2020.14","title":"Space Efficient Construction of Lyndon Arrays in Linear Time","year":2019,"lang":"en","type":"preprint","venue":"Repository KITopen (Karlsruhe Institute of Technology)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Deutsche Forschungsgemeinschaft","keywords":"Space (punctuation); String (physics); Linear space; Order (exchange); Construct (python library); Mathematics; Combinatorics; Algorithm; Time complexity; Discrete mathematics; Computer science","score_opus":0.008274238450181059,"score_gpt":0.23342003779184034,"score_spread":0.2251457993416593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987134948","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07221072,0.00077897427,0.899787,0.0006690919,0.00017046448,0.00023660646,0.0013193099,0.012808104,0.01201973],"genre_scores_gemma":[0.32688534,0.00039465338,0.6575688,0.00034254874,0.00007748688,0.00064805907,0.004443419,0.0008751201,0.008764515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796814,0.0004341305,0.00026193293,0.00036895336,0.00070683326,0.0002600319],"domain_scores_gemma":[0.99679023,0.0013179021,0.00031787503,0.0009986593,0.00047126,0.00010406546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071530236,0.00067416707,0.0010405732,0.000772196,0.0007670467,0.0022752902,0.0013448072,0.00074515474,0.006163448],"category_scores_gemma":[0.005587813,0.00055111304,0.00071086886,0.0021135863,0.0008142755,0.0046378863,0.0028171262,0.0010402987,0.0032996563],"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":[0.0017609404,0.000328565,0.003474245,0.001170719,0.00010593722,0.0006268581,0.0012770434,0.040449645,0.09911543,0.16281603,0.033178426,0.65569615],"study_design_scores_gemma":[0.00038284212,0.00066332065,0.0013796486,0.00028015443,0.000105559666,0.0008659327,0.0008905762,0.4493823,0.18825173,0.28503844,0.07256387,0.00019555898],"about_ca_topic_score_codex":0.0008018348,"about_ca_topic_score_gemma":0.0016913892,"teacher_disagreement_score":0.006163448,"about_ca_system_score_codex":0.0009792276,"about_ca_system_score_gemma":0.0017438974,"threshold_uncertainty_score":0.020618796},"labels":[],"label_agreement":null},{"id":"W2990235080","doi":"10.33011/computel.v1i.345","title":"OCR Evaluation Tools for the 21st Century","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Unicode; Computer science; Natural language processing; Word (group theory); Character (mathematics); Confusion; Artificial intelligence; Speech recognition; Linguistics; Psychology","score_opus":0.041108699107766676,"score_gpt":0.29369061927326084,"score_spread":0.2525819201654942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990235080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005329519,0.0019084521,0.70357275,0.00078890426,0.000634241,0.0008096608,0.008673661,0.25026816,0.028014613],"genre_scores_gemma":[0.04137687,0.0011780746,0.8580855,0.0007194561,0.0003985565,0.0014537635,0.025009127,0.049746774,0.02203186],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9824258,0.0028831963,0.0029225762,0.0015417001,0.009738061,0.0004886435],"domain_scores_gemma":[0.9356369,0.013860294,0.004175465,0.010388823,0.034828812,0.0011096246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012566859,0.0030882014,0.0014591792,0.011323209,0.0014506798,0.0049083135,0.0034617798,0.0017806015,0.047458023],"category_scores_gemma":[0.062359426,0.0010565153,0.0013182937,0.0044754934,0.0011417337,0.006115099,0.0037443691,0.0020463744,0.03188205],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034526174,0.0001417438,0.0028363445,0.0013630029,0.00012849183,0.00038066943,0.0006810207,0.0032789577,0.024352891,0.019501125,0.2058876,0.7411029],"study_design_scores_gemma":[0.00014978241,0.00035082598,0.008778914,0.0010757146,0.00014785383,0.0032954395,0.0004907735,0.0462386,0.12145197,0.026422743,0.79100484,0.0005925298],"about_ca_topic_score_codex":0.0037678867,"about_ca_topic_score_gemma":0.0035182792,"teacher_disagreement_score":0.047458023,"about_ca_system_score_codex":0.0019332947,"about_ca_system_score_gemma":0.0023725892,"threshold_uncertainty_score":0.15876293},"labels":[],"label_agreement":null},{"id":"W2990480882","doi":"","title":"Algorithms to Compute the Lyndon Array Revisited.","year":2019,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.018973375194458054,"score_gpt":0.25768951666373485,"score_spread":0.2387161414692768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990480882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009099554,0.0028767453,0.9657529,0.0017725436,0.00075407105,0.000069579066,0.00020553936,0.0019019538,0.017567106],"genre_scores_gemma":[0.17813508,0.002464641,0.78750145,0.0014952153,0.00084958057,0.0004126007,0.0009723239,0.0008796367,0.027289532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978751,0.0006293071,0.00019632211,0.0003725603,0.0006814173,0.00024535277],"domain_scores_gemma":[0.9942849,0.002937849,0.00022875823,0.0014252709,0.00093163893,0.00019154814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029399614,0.0009892541,0.0011555854,0.0022925963,0.0014183741,0.0040488485,0.00299333,0.0018949411,0.010175016],"category_scores_gemma":[0.019908508,0.00066392863,0.00083537045,0.004302778,0.0021273862,0.008710042,0.004347364,0.005502804,0.005012662],"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":[0.00043992535,0.000100185855,0.00090276974,0.00023876734,0.00005569231,0.00012369345,0.00034004537,0.016732208,0.0029225484,0.654159,0.026083317,0.29790193],"study_design_scores_gemma":[0.000060440245,0.0000578289,0.00019459231,0.00010528278,0.000026354424,0.00018559826,0.0001245197,0.12150991,0.0042016553,0.85214436,0.021348044,0.00004139085],"about_ca_topic_score_codex":0.0022880887,"about_ca_topic_score_gemma":0.003878886,"teacher_disagreement_score":0.010175016,"about_ca_system_score_codex":0.001547819,"about_ca_system_score_gemma":0.0022181345,"threshold_uncertainty_score":0.03403884},"labels":[],"label_agreement":null},{"id":"W2991315247","doi":"","title":"A Faster V-order String Comparison Algorithm.","year":2018,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Algorithm; Computer science; Order (exchange); String (physics); Physics; Theoretical physics","score_opus":0.03421952724317334,"score_gpt":0.2951806101801776,"score_spread":0.26096108293700426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991315247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02945048,0.0029593213,0.9202488,0.0006385921,0.00133141,0.0003791724,0.0022194337,0.024962397,0.017810497],"genre_scores_gemma":[0.15983742,0.00069597864,0.8029857,0.0005137728,0.00032858446,0.0003183836,0.006036261,0.0020847425,0.027199134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826497,0.00022374713,0.00016534621,0.00040251104,0.000757916,0.000185635],"domain_scores_gemma":[0.9976548,0.0006314976,0.000118905904,0.00080678,0.0006725767,0.00011547066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008836338,0.0010743237,0.001159063,0.0028336614,0.001180977,0.002354327,0.0025059008,0.0013307268,0.036584936],"category_scores_gemma":[0.006770191,0.0005832432,0.00093397655,0.005084177,0.0005048999,0.0037149556,0.0021744499,0.0014846914,0.016432777],"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":[0.000853035,0.00018833792,0.0010691603,0.0003077809,0.00009813687,0.00014880394,0.00015463043,0.0058674193,0.022268703,0.019301837,0.04188783,0.90785426],"study_design_scores_gemma":[0.00090478937,0.0011036976,0.00539445,0.00026816677,0.00025345077,0.0024834708,0.00063962943,0.49885875,0.14357941,0.13798855,0.20829217,0.00023350808],"about_ca_topic_score_codex":0.003904888,"about_ca_topic_score_gemma":0.0073784743,"teacher_disagreement_score":0.036584936,"about_ca_system_score_codex":0.00090414827,"about_ca_system_score_gemma":0.0022616056,"threshold_uncertainty_score":0.12238884},"labels":[],"label_agreement":null},{"id":"W2991376628","doi":"10.1016/j.physrep.2019.09.005","title":"Data science applications to string theory","year":2019,"lang":"en","type":"article","venue":"Physics Reports","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":135,"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":"Engineering and Physical Sciences Research Council; Banff International Research Station for Mathematical Innovation and Discovery; Universidad Nacional Autónoma de México; Aspen Center for Physics; Abdus Salam International Centre for Theoretical Physics; CERN; University of Pennsylvania; Microsoft Research","keywords":"String (physics); Physics; Cluster analysis; Variety (cybernetics); Machine learning; String theory; Unsupervised learning; Artificial intelligence; Theoretical computer science; Computer science; Theoretical physics","score_opus":0.039867548761288535,"score_gpt":0.32076990157527674,"score_spread":0.28090235281398823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991376628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017670799,0.063640416,0.89909524,0.009513474,0.0019450063,0.00017338147,0.0011413826,0.00048140585,0.022242617],"genre_scores_gemma":[0.043262515,0.11574469,0.81615376,0.0054758857,0.006375118,0.0009904486,0.0019084433,0.00038048168,0.009708684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956721,0.0016319063,0.00059439003,0.0005189915,0.0014442198,0.00013828467],"domain_scores_gemma":[0.9877808,0.009297025,0.00045463568,0.0013306082,0.0009935271,0.00014341151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041348375,0.0013948678,0.0016013065,0.006568644,0.0013646985,0.0045440407,0.00187827,0.003157096,0.0074876226],"category_scores_gemma":[0.017949652,0.00076297484,0.0020570308,0.008700429,0.0040266584,0.0068784566,0.003246201,0.007002025,0.003565715],"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":[0.00001578985,0.000034941226,0.0003441692,0.0010217446,0.000044386557,0.00017179888,0.00022629427,0.004597068,0.0006825959,0.88321394,0.013615909,0.09603138],"study_design_scores_gemma":[0.0000061491746,0.000028788398,0.00022594427,0.0005006394,0.0000131877305,0.00045636206,0.0000612194,0.012307819,0.00089310686,0.8303249,0.15514506,0.00003679171],"about_ca_topic_score_codex":0.00095082377,"about_ca_topic_score_gemma":0.0005208731,"teacher_disagreement_score":0.0074876226,"about_ca_system_score_codex":0.0018729568,"about_ca_system_score_gemma":0.0013087534,"threshold_uncertainty_score":0.025048614},"labels":[],"label_agreement":null},{"id":"W2992362114","doi":"10.1007/978-3-030-36412-0_1","title":"Exact Algorithms for the Bounded Repetition Longest Common Subsequence Problem","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Longest common subsequence problem; Longest increasing subsequence; Subsequence; Bounded function; Algorithm; Computer science; Simple (philosophy); Exponential function; Sequence (biology); Time complexity; Combinatorics; Discrete mathematics; Mathematics","score_opus":0.02583166160923958,"score_gpt":0.26755837882144345,"score_spread":0.24172671721220387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992362114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014088853,0.0013925132,0.9673719,0.0007705421,0.00032690936,0.00023024483,0.00073561096,0.0032178066,0.011865646],"genre_scores_gemma":[0.11737888,0.0008317203,0.8681422,0.0003658542,0.00040757234,0.0005178208,0.0025501917,0.00090731645,0.008898323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99658257,0.00066134124,0.00027653054,0.000945046,0.0010867225,0.0004478554],"domain_scores_gemma":[0.9922321,0.0045069223,0.00039429075,0.0019086367,0.00075841486,0.0001996812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019120796,0.0017114271,0.0027323307,0.001995987,0.0017065746,0.003490733,0.0050919615,0.002417404,0.015624709],"category_scores_gemma":[0.012902556,0.0011388286,0.0015643798,0.005079249,0.0015446395,0.007381506,0.0040043895,0.0035692574,0.0055196323],"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":[0.0009922107,0.00052047474,0.00069087825,0.0007818559,0.00016683529,0.00021616173,0.00038150683,0.14575242,0.0066962857,0.16258043,0.043853503,0.6373675],"study_design_scores_gemma":[0.00032485783,0.00014387623,0.00025161044,0.00007443295,0.000067817426,0.00025039347,0.00017028273,0.56267905,0.003622387,0.42213422,0.010236368,0.000044700573],"about_ca_topic_score_codex":0.0030982106,"about_ca_topic_score_gemma":0.00424307,"teacher_disagreement_score":0.015624709,"about_ca_system_score_codex":0.0019199006,"about_ca_system_score_gemma":0.0034065798,"threshold_uncertainty_score":0.052269816},"labels":[],"label_agreement":null},{"id":"W2998362270","doi":"10.1145/2528521.1508283","title":"Architectural support for SWAR text processing with parallel bit streams","year":2009,"lang":"en","type":"article","venue":"ACM SIGARCH Computer Architecture News","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; SIMD; Operand; Parallel computing; Instruction set; Set (abstract data type); Parsing; Stream processing; Simple (philosophy); Parallelism (grammar); Computer architecture; Programming language; Computer hardware","score_opus":0.01253498454135215,"score_gpt":0.25503459742731555,"score_spread":0.2424996128859634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998362270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12867156,0.0005215014,0.8239266,0.0005653356,0.00017992072,0.00016466629,0.0002854152,0.013647826,0.032037128],"genre_scores_gemma":[0.5814273,0.00077276415,0.39831764,0.0005831009,0.00017581793,0.0002662045,0.0013456107,0.0009374814,0.016174022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996941,0.000047648602,0.00004940841,0.000041181018,0.00013068381,0.000036853853],"domain_scores_gemma":[0.9990767,0.00022666401,0.00008844375,0.00031809928,0.00025246028,0.000037500547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031693265,0.00040731463,0.00031799803,0.0006630588,0.0004217737,0.0010579283,0.001467233,0.00034025364,0.005271821],"category_scores_gemma":[0.0014908938,0.000349061,0.00040960085,0.0008032377,0.00038883358,0.0017853335,0.0007714355,0.0009805486,0.0020749203],"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":[0.00079598284,0.00031732276,0.0038108646,0.00060808135,0.00008313476,0.00073242676,0.0004503451,0.047721785,0.34388715,0.15602012,0.015225949,0.4303468],"study_design_scores_gemma":[0.0001706294,0.0007213168,0.0015208445,0.000092368085,0.00012040489,0.0010192071,0.00014281126,0.50905496,0.33843124,0.06423653,0.08440634,0.000083299805],"about_ca_topic_score_codex":0.00044018246,"about_ca_topic_score_gemma":0.0013761701,"teacher_disagreement_score":0.005271821,"about_ca_system_score_codex":0.0003763457,"about_ca_system_score_gemma":0.00073026394,"threshold_uncertainty_score":0.017636001},"labels":[],"label_agreement":null},{"id":"W3000285870","doi":"10.1109/bibe.2019.00036","title":"MemAlign: A Memory Structure to Accelerate Gene Sequencing","year":2019,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"","keywords":"Computer science; sort; Pipeline (software); Reference genome; DNA sequencing; Parallel computing; Gene; Biology; Genetics; Database; Operating system","score_opus":0.015354809384645732,"score_gpt":0.23572098007258735,"score_spread":0.22036617068794162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000285870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036926236,0.002654158,0.8901499,0.00062643085,0.0006328151,0.00028306656,0.003168332,0.057870712,0.007688341],"genre_scores_gemma":[0.15895566,0.0010973254,0.8112844,0.00070151937,0.0004049242,0.00084520585,0.0092603965,0.003918676,0.013531789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994318,0.000091579095,0.00006526663,0.00014320483,0.00018683026,0.00008124221],"domain_scores_gemma":[0.99833953,0.00045443894,0.0001454183,0.0005991393,0.0003724022,0.000089048546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007810177,0.0010605964,0.0006311595,0.0022628682,0.0009951001,0.0015564122,0.002605437,0.0005843268,0.009061308],"category_scores_gemma":[0.0031856087,0.00064647716,0.0006039186,0.0025888595,0.0006187051,0.0030709375,0.0024177271,0.0010594255,0.0043515847],"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":[0.0020818599,0.00021225584,0.002872246,0.00054278056,0.00011822314,0.0003815553,0.00064788846,0.008162483,0.054015305,0.0259631,0.073941305,0.83106095],"study_design_scores_gemma":[0.0006557954,0.0017060961,0.0031524773,0.0002516942,0.00021651549,0.0014631072,0.0005448434,0.1847362,0.37975225,0.05881137,0.36845446,0.00025520325],"about_ca_topic_score_codex":0.0018509615,"about_ca_topic_score_gemma":0.0029792208,"teacher_disagreement_score":0.009061308,"about_ca_system_score_codex":0.0007616335,"about_ca_system_score_gemma":0.0013680422,"threshold_uncertainty_score":0.030313075},"labels":[],"label_agreement":null},{"id":"W3003247616","doi":"10.48550/arxiv.2001.10567","title":"Path Query Data Structures in Practice","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Computer science; Data structure; Path (computing); Tree traversal; Pointer (user interface); Theoretical computer science; Algorithm; Data mining; Artificial intelligence","score_opus":0.13781202928445627,"score_gpt":0.229072452462652,"score_spread":0.09126042317819574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003247616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2503716,0.0025391798,0.66165996,0.00486548,0.0006746452,0.0018093552,0.0125554,0.044950623,0.020573743],"genre_scores_gemma":[0.40707752,0.00084680517,0.56687695,0.0010174472,0.00011934221,0.0016879193,0.015244819,0.0021867976,0.004942424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98240906,0.0032136175,0.0023535981,0.0023621079,0.008579205,0.0010824497],"domain_scores_gemma":[0.95068914,0.02057339,0.0018898173,0.019883895,0.0063098767,0.00065391976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008148568,0.0013014266,0.0012217577,0.0019839506,0.0014871648,0.0043178955,0.003952301,0.0026654329,0.010895475],"category_scores_gemma":[0.061110288,0.00083492754,0.0010592197,0.0071930964,0.0019016359,0.015797885,0.0042228745,0.0032084878,0.004040992],"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":[0.003831321,0.002070213,0.013898316,0.0021304723,0.0002898675,0.00047418565,0.0021843247,0.09699771,0.034981813,0.18648246,0.11804482,0.53861445],"study_design_scores_gemma":[0.0009320337,0.0017958294,0.002561506,0.00027740397,0.00014582658,0.000934622,0.0015350394,0.6096316,0.06790097,0.21544944,0.09865892,0.00017679158],"about_ca_topic_score_codex":0.00309456,"about_ca_topic_score_gemma":0.0026238794,"teacher_disagreement_score":0.010895475,"about_ca_system_score_codex":0.0023511886,"about_ca_system_score_gemma":0.0041202297,"threshold_uncertainty_score":0.043094277},"labels":[],"label_agreement":null},{"id":"W3004226583","doi":"10.1007/s00500-022-07683-8","title":"Stochastic L-system inference from multiple string sequence inputs","year":2022,"lang":"en","type":"article","venue":"Soft Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; McMaster University","funders":"Canada First Research Excellence Fund","keywords":"Rewriting; String (physics); Computer science; Algorithm; Context (archaeology); Inference; Symbol (formal); Test suite; Sequence (biology); Theoretical computer science; Programming language; Mathematics; Artificial intelligence; Test case; Machine learning","score_opus":0.03100496176620802,"score_gpt":0.2609022408811905,"score_spread":0.2298972791149825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004226583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039736263,0.0003716143,0.9551641,0.0009670882,0.0001138818,0.00005228458,0.0005054651,0.0016579687,0.0014314177],"genre_scores_gemma":[0.80227864,0.00031071543,0.18971758,0.0006660882,0.00029811985,0.00022821876,0.0016473818,0.00027845657,0.004574828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786025,0.0007250886,0.00017312524,0.0006066448,0.00043615213,0.00019877964],"domain_scores_gemma":[0.9816704,0.015661461,0.0005172617,0.0009808369,0.0009587867,0.00021130555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002462385,0.0007782369,0.0016179804,0.0014733628,0.00083674066,0.0018980135,0.0016215506,0.002486816,0.0057577947],"category_scores_gemma":[0.020408725,0.00086724403,0.0013269534,0.0014784012,0.0010514761,0.002880347,0.0026542295,0.0026883371,0.0015174522],"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":[0.0008104784,0.000217644,0.0042545344,0.00038987736,0.00025790525,0.0005971968,0.00021747305,0.7324421,0.006721666,0.03830005,0.0038450614,0.21194598],"study_design_scores_gemma":[0.000012204219,0.00001929045,0.00023563823,0.000014114729,0.000013061214,0.00003006293,0.0000098702985,0.9798763,0.0011446013,0.018416384,0.00022045444,0.000008087618],"about_ca_topic_score_codex":0.0038752952,"about_ca_topic_score_gemma":0.0064503513,"teacher_disagreement_score":0.0057577947,"about_ca_system_score_codex":0.0013841795,"about_ca_system_score_gemma":0.0018831383,"threshold_uncertainty_score":0.019261777},"labels":[],"label_agreement":null},{"id":"W3010430734","doi":"","title":"Dynamic 3d sequence capture and enhancement","year":2017,"lang":"en","type":"article","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Iran Telecommunication Research Center; Simon Fraser University; Mitacs; IC Design Education Center; National Research Foundation of Korea; Fonds Wetenschappelijk Onderzoek; Sungkyunkwan University; National Research Foundation","keywords":"Sequence (biology); Computer science; Artificial intelligence; Biology; Genetics","score_opus":0.020188782445347758,"score_gpt":0.23859394746645446,"score_spread":0.2184051650211067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010430734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018290594,0.01373896,0.7740639,0.0014454265,0.0020574809,0.00076957047,0.01491127,0.019843286,0.15487954],"genre_scores_gemma":[0.11955901,0.016026786,0.58004755,0.001196247,0.00070879684,0.0005441981,0.031277936,0.005639968,0.24499957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994417,0.000049260827,0.000024686276,0.00012128921,0.00031719747,0.000045878274],"domain_scores_gemma":[0.99945766,0.00007863977,0.000033618275,0.00015253384,0.00023434951,0.00004318031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007697197,0.0011710301,0.00043307652,0.0033252682,0.0005900875,0.0016491171,0.0007404344,0.00093651254,0.049513355],"category_scores_gemma":[0.0013507612,0.0005278473,0.00071800104,0.0021554632,0.00034719615,0.0013704129,0.001547058,0.0009480819,0.026706755],"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":[0.000222109,0.000036751917,0.0007846554,0.0005778484,0.00004094471,0.000320846,0.00024699228,0.0026913523,0.0548217,0.004975378,0.09659371,0.8386877],"study_design_scores_gemma":[0.000030017114,0.00017712505,0.0075228806,0.00044828112,0.00006889187,0.0033200737,0.0003763891,0.029338617,0.09560817,0.0046102176,0.85832155,0.00017779491],"about_ca_topic_score_codex":0.0028854897,"about_ca_topic_score_gemma":0.0074337753,"teacher_disagreement_score":0.049513355,"about_ca_system_score_codex":0.00041079492,"about_ca_system_score_gemma":0.00074273854,"threshold_uncertainty_score":0.16563869},"labels":[],"label_agreement":null},{"id":"W3012034924","doi":"10.1089/cmb.2019.0309","title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","year":2020,"lang":"en","type":"article","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"Index (typography); Genomics; Computer science; Computational biology; Biology; Genome; Genetics; World Wide Web; Gene","score_opus":0.08315413654598122,"score_gpt":0.28051697112993457,"score_spread":0.19736283458395334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012034924","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021584405,0.0011063414,0.9497746,0.000220442,0.00026422233,0.00025069897,0.0046102293,0.01757266,0.0046162936],"genre_scores_gemma":[0.052721202,0.00040595082,0.92465574,0.00015454262,0.00016734409,0.00031919134,0.016451424,0.0015288299,0.0035958223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976676,0.00025662853,0.00032173665,0.00051499245,0.0010371457,0.00020182306],"domain_scores_gemma":[0.9961629,0.000682975,0.00022247022,0.0014372376,0.0012938161,0.00020067157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001391289,0.0010145738,0.0019718213,0.0038970024,0.0011413314,0.0025613324,0.0021615452,0.0011926799,0.005501387],"category_scores_gemma":[0.008683022,0.00079974823,0.00120252,0.006062482,0.00064716965,0.0048193643,0.003411456,0.0021768215,0.008867604],"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":[0.00059048063,0.00030735318,0.004059189,0.0007348023,0.00011971319,0.00041064908,0.0005488195,0.016668383,0.091163106,0.031156119,0.04602066,0.8082207],"study_design_scores_gemma":[0.0002436379,0.0006089519,0.005249063,0.00018216512,0.00017645073,0.0017735754,0.00047717866,0.58890086,0.15055116,0.086519204,0.16508144,0.0002363605],"about_ca_topic_score_codex":0.0017067996,"about_ca_topic_score_gemma":0.0030782146,"teacher_disagreement_score":0.005501387,"about_ca_system_score_codex":0.00088568125,"about_ca_system_score_gemma":0.0029335746,"threshold_uncertainty_score":0.018404007},"labels":[],"label_agreement":null},{"id":"W3013590109","doi":"10.18280/isi.250115","title":"Performance Comparison of Sorting Algorithms with Random Numbers as Inputs","year":2020,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sorting; Algorithm; Computer science; Sorting algorithm","score_opus":0.019075001123280876,"score_gpt":0.24941582254496125,"score_spread":0.2303408214216804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013590109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8634508,0.007335636,0.089005895,0.0008875163,0.0005897053,0.00032462899,0.001582531,0.009523744,0.027299466],"genre_scores_gemma":[0.89364624,0.0017470855,0.09688543,0.00014962886,0.00007916518,0.00017132684,0.0022859594,0.00032585004,0.0047093905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99591225,0.0010636981,0.0004232882,0.00045596765,0.0014804155,0.00066432677],"domain_scores_gemma":[0.99071294,0.005610549,0.00047574466,0.00072584266,0.002204234,0.00027075838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020978434,0.001031737,0.0010887126,0.003238282,0.0011313165,0.0023989095,0.001376256,0.0014629903,0.0040403986],"category_scores_gemma":[0.010694701,0.00026276315,0.00062305626,0.004643686,0.00057565107,0.0022248705,0.0006944663,0.00052828394,0.0011346985],"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":[0.011015854,0.001190547,0.01645886,0.0018853723,0.0004901957,0.00038383217,0.0005961538,0.37689817,0.032975476,0.014420527,0.0137665225,0.5299186],"study_design_scores_gemma":[0.00030941376,0.0018423481,0.005985231,0.000108658794,0.00017953494,0.0005215244,0.00053996465,0.8882101,0.089590184,0.004494861,0.008104465,0.000113651564],"about_ca_topic_score_codex":0.0045442646,"about_ca_topic_score_gemma":0.0026338475,"teacher_disagreement_score":0.0045442646,"about_ca_system_score_codex":0.0019129362,"about_ca_system_score_gemma":0.0019393889,"threshold_uncertainty_score":0.013879418},"labels":[],"label_agreement":null},{"id":"W3013680898","doi":"10.5539/mas.v14n4p52","title":"An Efficient Two-Level Dictionary-Based Technique for Segmentation and Compression Compound Images","year":2020,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Gamut; Computer science; Lossless compression; Artificial intelligence; Block (permutation group theory); Pattern recognition (psychology); Set (abstract data type); Pixel; Image compression; Segmentation; Image (mathematics); Representation (politics); Encoder; Color space; Computer vision; Data compression; Algorithm; Image processing; Mathematics","score_opus":0.03311945467718457,"score_gpt":0.29033460164488417,"score_spread":0.2572151469676996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013680898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010436867,0.0003145006,0.98702735,0.00006390789,0.000063626394,0.000075685355,0.00007898424,0.0007711319,0.0011680664],"genre_scores_gemma":[0.08479967,0.00041327768,0.90939057,0.000103650615,0.000052460196,0.00011686965,0.0004530804,0.000105665924,0.004564834],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99978286,0.00001997526,0.000019198775,0.000041888172,0.0001156103,0.0000204965],"domain_scores_gemma":[0.9998265,0.000040267973,0.000018819263,0.0000432481,0.00005986136,0.000011311352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015431289,0.00034072498,0.00051062455,0.00076335046,0.0003531353,0.0004580386,0.00065178826,0.0003792638,0.0024658367],"category_scores_gemma":[0.0004995229,0.00022101964,0.00039500915,0.0010124829,0.00028022594,0.0008923486,0.0005260938,0.0006580305,0.0013721903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019593743,0.0000617001,0.00039549547,0.00018111231,0.000027675318,0.00012622039,0.0001079015,0.011643381,0.28079537,0.009931029,0.004115435,0.6924188],"study_design_scores_gemma":[0.000061728475,0.0004653841,0.0014243089,0.000031579966,0.000047030553,0.0013215384,0.00007691477,0.696872,0.25744122,0.0035953268,0.038603287,0.000059716305],"about_ca_topic_score_codex":0.0013776919,"about_ca_topic_score_gemma":0.0027363342,"teacher_disagreement_score":0.0024658367,"about_ca_system_score_codex":0.00030002967,"about_ca_system_score_gemma":0.00057547935,"threshold_uncertainty_score":0.008249044},"labels":[],"label_agreement":null},{"id":"W3013736025","doi":"10.4230/lipics.stacs.2020.15","title":"The Tandem Duplication Distance Is NP-Hard","year":2020,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Université de Sherbrooke","funders":"","keywords":"Gene duplication; Tandem exon duplication; Tandem; Edit distance; Computer science; Genome; Tandem repeat; String (physics); Sequence (biology); Mathematics; Biology; Algorithm; Combinatorics; Computational biology; Genetics; Gene","score_opus":0.021399867699930453,"score_gpt":0.2490937005606947,"score_spread":0.22769383286076422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013736025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36191428,0.011506407,0.40456694,0.066197515,0.0018332065,0.0007822662,0.021540781,0.00418299,0.1274756],"genre_scores_gemma":[0.787515,0.005827371,0.14704786,0.00628463,0.0022474565,0.0006657298,0.015865248,0.0012147428,0.033331953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980446,0.0003174505,0.00010464404,0.0008193276,0.00036455717,0.00034936375],"domain_scores_gemma":[0.9905256,0.007959656,0.00042266666,0.00044508715,0.0003420175,0.00030502302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007571331,0.0015240315,0.002373561,0.0007085898,0.0018453476,0.0041525685,0.003522811,0.0034117394,0.012122665],"category_scores_gemma":[0.007389242,0.0008778162,0.0017738475,0.0028301536,0.0021852697,0.00813706,0.002338955,0.005950951,0.0020147113],"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":[0.0012138746,0.0010141266,0.0044158907,0.003701785,0.0005151446,0.001259446,0.0008267159,0.34215063,0.009676353,0.26676348,0.18194768,0.18651493],"study_design_scores_gemma":[0.0002591584,0.00015876249,0.0014738116,0.00014433048,0.00014290742,0.0011190322,0.0006343493,0.28084144,0.0044998643,0.67969555,0.030945208,0.000085650754],"about_ca_topic_score_codex":0.0037141703,"about_ca_topic_score_gemma":0.003823559,"teacher_disagreement_score":0.012122665,"about_ca_system_score_codex":0.0031325193,"about_ca_system_score_gemma":0.0022517594,"threshold_uncertainty_score":0.040554345},"labels":[],"label_agreement":null},{"id":"W3014463062","doi":"10.1101/2020.04.01.019984","title":"Fast protein database as a service with kAAmer","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centrale des Syndicats du Québec; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada","keywords":"Identification (biology); Computer science; Service (business); Computational biology; Database; Genomics; Biology; Genome; Gene; Genetics","score_opus":0.016473492985438983,"score_gpt":0.21824774378137343,"score_spread":0.20177425079593445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014463062","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022601467,0.0012180931,0.27910957,0.0006873378,0.00055406505,0.0002679935,0.032806177,0.6721144,0.010982176],"genre_scores_gemma":[0.07342741,0.0029935818,0.4741798,0.0022235443,0.0007708766,0.0016566259,0.30741683,0.09351286,0.04381841],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767715,0.00032217568,0.00026139873,0.0005624015,0.0009251477,0.00025175608],"domain_scores_gemma":[0.99581224,0.0008396285,0.00028327628,0.0018512849,0.00080709445,0.00040651803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003759612,0.0026472758,0.0025984442,0.00507894,0.0009532143,0.005018106,0.0041616946,0.002298895,0.06599821],"category_scores_gemma":[0.009852456,0.0017911224,0.0010330845,0.005347584,0.0006161104,0.0058586355,0.0050260215,0.003097112,0.11500785],"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":[0.0019637616,0.00018795859,0.001070577,0.0008678792,0.00024218702,0.00036275396,0.0001503488,0.0019828514,0.013785669,0.021692995,0.7754884,0.18220466],"study_design_scores_gemma":[0.0011903046,0.00022675282,0.0014792121,0.00025729748,0.00011320468,0.0015261639,0.00013970461,0.0998315,0.05390817,0.08204049,0.75895786,0.0003294171],"about_ca_topic_score_codex":0.00092000235,"about_ca_topic_score_gemma":0.0007019245,"teacher_disagreement_score":0.06599821,"about_ca_system_score_codex":0.0010713857,"about_ca_system_score_gemma":0.0020392044,"threshold_uncertainty_score":0.22078604},"labels":[],"label_agreement":null},{"id":"W3014663963","doi":"10.1109/access.2020.2984191","title":"High-Throughput FPGA-Based Hardware Accelerators for Deflate Compression and Decompression Using High-Level Synthesis","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; CMC Microsystems","keywords":"Field-programmable gate array; Computer science; Throughput; Compression ratio; Huffman coding; Lossless compression; Computer hardware; High-level synthesis; Benchmark (surveying); Data compression; Embedded system; Parallel computing; Algorithm; Operating system","score_opus":0.12893241942071304,"score_gpt":0.32891870892482633,"score_spread":0.1999862895041133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014663963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31879956,0.0023312957,0.6194785,0.00043711276,0.00032169747,0.0005114461,0.0012362682,0.015264101,0.041620072],"genre_scores_gemma":[0.75881886,0.00073083217,0.22529742,0.00021983673,0.000048574213,0.00025980573,0.0014627876,0.00039495775,0.012766943],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998091,0.000018799223,0.000012890105,0.000025200994,0.00010046557,0.000033608903],"domain_scores_gemma":[0.9997954,0.00006026251,0.000039335777,0.000027545782,0.00006723769,0.000010264013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016578584,0.00048004434,0.00022596399,0.0004598189,0.00018408782,0.00042931712,0.0005657252,0.00022148502,0.004582628],"category_scores_gemma":[0.00043578405,0.00015351964,0.00019884402,0.00029611064,0.00015220506,0.00042732604,0.00015493124,0.00034424238,0.0007019028],"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":[0.00064771867,0.00020411066,0.0018213668,0.0010477244,0.00011017972,0.00086354587,0.00020783805,0.08520534,0.573188,0.016749145,0.01678461,0.30317047],"study_design_scores_gemma":[0.00023490026,0.0013174594,0.002304216,0.00012525756,0.00009372022,0.0007942641,0.00007712531,0.31041545,0.62650627,0.002215685,0.055856742,0.000058898655],"about_ca_topic_score_codex":0.0014665875,"about_ca_topic_score_gemma":0.0027895442,"teacher_disagreement_score":0.004582628,"about_ca_system_score_codex":0.00053502887,"about_ca_system_score_gemma":0.0006805721,"threshold_uncertainty_score":0.015330374},"labels":[],"label_agreement":null},{"id":"W3017007515","doi":"10.4230/lipics.cpm.2020.11","title":"Summarizing Diverging String Sequences, with Applications to Chain-Letter Petitions","year":2020,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Automatic summarization; Heuristic; String (physics); Sequence (biology); Computer science; Tree (set theory); Variety (cybernetics); Set (abstract data type); Chain (unit); Algorithm; Theoretical computer science; Mathematics; Combinatorics; Artificial intelligence","score_opus":0.027909060437225013,"score_gpt":0.2671914755954198,"score_spread":0.23928241515819476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017007515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057616554,0.0020706195,0.93342924,0.0007027361,0.00012630764,0.00017461649,0.0012970483,0.003050419,0.0015324609],"genre_scores_gemma":[0.16556878,0.00074644224,0.8268556,0.0001543179,0.00012337911,0.00015700045,0.0038325347,0.0003177624,0.0022441885],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872845,0.0003076593,0.00017019978,0.00037965082,0.00034485693,0.00006906426],"domain_scores_gemma":[0.99509096,0.0026245406,0.0005577358,0.0010487475,0.0005413845,0.00013652675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013505064,0.0009557215,0.0014387257,0.0031139276,0.0010076531,0.0019301288,0.0016902013,0.0016701347,0.002306244],"category_scores_gemma":[0.010798249,0.00056865177,0.0007623534,0.005575363,0.0010690439,0.003257013,0.0012374057,0.0017212442,0.0013414564],"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":[0.0004629979,0.00016137105,0.00503339,0.00060603756,0.00011485395,0.00053051545,0.0008112881,0.26105198,0.013137642,0.05596959,0.0106170755,0.6515034],"study_design_scores_gemma":[0.00004282601,0.00015044898,0.0010312495,0.00008170413,0.00004908252,0.00049925136,0.00028926105,0.83353925,0.01328213,0.13829586,0.012701598,0.00003735312],"about_ca_topic_score_codex":0.0015476067,"about_ca_topic_score_gemma":0.0024967433,"teacher_disagreement_score":0.0031139276,"about_ca_system_score_codex":0.0009847779,"about_ca_system_score_gemma":0.0010228251,"threshold_uncertainty_score":0.0077151656},"labels":[],"label_agreement":null},{"id":"W3017834538","doi":"10.1016/j.tcs.2020.04.009","title":"A linear-space data structure for range-LCP queries in poly-logarithmic time","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ministry of Science and Technology, Taiwan; National Science Foundation","keywords":"Linear space; Data structure; Combinatorics; Mathematics; Binary logarithm; Space (punctuation); Logarithm; Log-log plot; Range query (database); Range (aeronautics); Suffix; Time complexity; Inverse; Discrete mathematics; Computer science; Search engine","score_opus":0.020610470389528217,"score_gpt":0.2714613027795172,"score_spread":0.25085083238998895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017834538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047779057,0.0019192778,0.8850842,0.0033162304,0.0005904362,0.0010744858,0.0073283142,0.035536155,0.017371818],"genre_scores_gemma":[0.28128988,0.00056892796,0.6838547,0.001689672,0.0004832734,0.0015332648,0.011912256,0.0030819478,0.015586011],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949114,0.0006741263,0.0005924583,0.00092057645,0.0022234854,0.0006780839],"domain_scores_gemma":[0.9875886,0.003313798,0.00057769276,0.0068433303,0.0011994926,0.00047704694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020197125,0.0015664286,0.0025091842,0.0035291002,0.0018613666,0.0044672815,0.003395681,0.0022217194,0.02835851],"category_scores_gemma":[0.010530001,0.0011148885,0.0016594051,0.010438956,0.002053944,0.011160557,0.007491876,0.0036154499,0.009491463],"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":[0.003079851,0.0010591956,0.0025057665,0.0010419989,0.00018317577,0.00024274518,0.0006569671,0.02518052,0.04321457,0.106790505,0.13210768,0.683937],"study_design_scores_gemma":[0.0021968524,0.0012678577,0.0020383287,0.00030129385,0.00037136232,0.0011654984,0.00094005524,0.39969027,0.07098174,0.4280676,0.09264484,0.00033416634],"about_ca_topic_score_codex":0.0037473978,"about_ca_topic_score_gemma":0.004466397,"teacher_disagreement_score":0.02835851,"about_ca_system_score_codex":0.0037836956,"about_ca_system_score_gemma":0.004702066,"threshold_uncertainty_score":0.09486872},"labels":[],"label_agreement":null},{"id":"W3022247802","doi":"10.1142/s0218195919500092","title":"The Most Likely Object to be Seen Through a Window","year":2019,"lang":"en","type":"article","venue":"International Journal of Computational Geometry & Applications","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Mathematics; Combinatorics; Interval (graph theory)","score_opus":0.01278905434978944,"score_gpt":0.2947066355962634,"score_spread":0.281917581246474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022247802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38977662,0.0009492105,0.6024767,0.0017419152,0.00008303725,0.00021640799,0.0013279285,0.0021881366,0.0012400658],"genre_scores_gemma":[0.6949103,0.00040057296,0.29842302,0.00029121162,0.00020676204,0.0002894167,0.0021774487,0.0005128451,0.0027884622],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99643075,0.0007149752,0.0002736835,0.0014267215,0.0007880915,0.0003657145],"domain_scores_gemma":[0.9800601,0.014566186,0.0016783183,0.0019754518,0.0009992627,0.0007207007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042214426,0.0009796148,0.0026168956,0.0016749701,0.001105248,0.003476547,0.0041110497,0.0035376577,0.0033401977],"category_scores_gemma":[0.030779079,0.0012252051,0.0012384031,0.002177785,0.0015196992,0.0125193335,0.0027408362,0.0019227774,0.00086539413],"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":[0.0053111757,0.0014756925,0.041961513,0.001798523,0.00053222425,0.0012537622,0.004838116,0.4399523,0.0687868,0.15582854,0.013082817,0.2651784],"study_design_scores_gemma":[0.00008198473,0.00033841564,0.0010802399,0.00003094607,0.00006318208,0.00017824919,0.000272135,0.9363149,0.008711813,0.051201213,0.0016900148,0.00003676977],"about_ca_topic_score_codex":0.003264545,"about_ca_topic_score_gemma":0.002020471,"teacher_disagreement_score":0.0042214426,"about_ca_system_score_codex":0.001624049,"about_ca_system_score_gemma":0.0015206026,"threshold_uncertainty_score":0.022325397},"labels":[],"label_agreement":null},{"id":"W3023624987","doi":"10.1016/j.tcs.2019.10.008","title":"Ranked document selection","year":2019,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science Foundation","keywords":"Selection (genetic algorithm); Computer science; Information retrieval; Mathematics; Natural language processing; Artificial intelligence","score_opus":0.004385236818466683,"score_gpt":0.23341579447857627,"score_spread":0.2290305576601096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023624987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11804845,0.012164762,0.7259176,0.0037569166,0.0031397757,0.0028729285,0.037135698,0.02572496,0.071238905],"genre_scores_gemma":[0.3565705,0.0032464305,0.46783057,0.0010149454,0.001963038,0.0010563681,0.054505467,0.0013751542,0.112437576],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964173,0.0007505154,0.0003471356,0.0005536171,0.0015995053,0.00033202977],"domain_scores_gemma":[0.99567974,0.0012826711,0.0001332341,0.0007698775,0.0019193031,0.00021527629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019260756,0.0014133117,0.0018352423,0.007889655,0.001654636,0.0032682444,0.0015743647,0.0014702708,0.024577932],"category_scores_gemma":[0.0083856415,0.00043719375,0.0016711402,0.0061115907,0.00041706662,0.0017735427,0.0010375308,0.0011126397,0.020870099],"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":[0.0010323228,0.00042959524,0.003760876,0.0005218659,0.00023929794,0.00032040972,0.00005429313,0.0050730277,0.019512491,0.00447071,0.08393536,0.88064975],"study_design_scores_gemma":[0.0008948585,0.002378646,0.020148274,0.0004193842,0.0013021866,0.0059143296,0.0007043546,0.5203539,0.15577151,0.051325403,0.24040361,0.00038348016],"about_ca_topic_score_codex":0.0029425665,"about_ca_topic_score_gemma":0.0070062927,"teacher_disagreement_score":0.024577932,"about_ca_system_score_codex":0.0007711392,"about_ca_system_score_gemma":0.003451458,"threshold_uncertainty_score":0.08222145},"labels":[],"label_agreement":null},{"id":"W3031217404","doi":"10.1587/transfun.2019eap1063","title":"Compression by Substring Enumeration Using Sorted Contingency Tables","year":2020,"lang":"en","type":"article","venue":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Substring; Lexicographical order; Upper and lower bounds; Enumeration; Algorithm; Mathematics; Encoding (memory); Computer science; Combinatorics; Data structure; Artificial intelligence","score_opus":0.047777007840325604,"score_gpt":0.28627400514538504,"score_spread":0.23849699730505944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031217404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06922777,0.001041871,0.9247512,0.00021867939,0.000088313776,0.00013205226,0.00040284827,0.001610006,0.0025272972],"genre_scores_gemma":[0.2804182,0.0006086591,0.7144292,0.00017598979,0.00007730465,0.00013037233,0.0013850606,0.00017113828,0.002604114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992459,0.00010995026,0.00009380601,0.00013549843,0.00034877568,0.00006617687],"domain_scores_gemma":[0.9979063,0.0010944245,0.0001541004,0.00042338533,0.00037664713,0.00004522001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058684224,0.00051466364,0.000690403,0.0019678476,0.00036368854,0.0007461033,0.0008423991,0.00038961723,0.0017902768],"category_scores_gemma":[0.0037185347,0.00024471694,0.00034370212,0.002191175,0.00046102758,0.0017994489,0.00066484546,0.0007202022,0.0004617117],"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":[0.00056203717,0.000119511904,0.0022145906,0.00021726792,0.00004339859,0.00029258855,0.00016706272,0.05726891,0.048379093,0.028911404,0.0032535538,0.85857064],"study_design_scores_gemma":[0.00010853772,0.0003489322,0.0023923134,0.00007527515,0.000058544785,0.0010523684,0.0001525054,0.82678086,0.124524474,0.028697066,0.01573288,0.000076196244],"about_ca_topic_score_codex":0.0019228844,"about_ca_topic_score_gemma":0.0027659396,"teacher_disagreement_score":0.0019678476,"about_ca_system_score_codex":0.0005128554,"about_ca_system_score_gemma":0.00093527226,"threshold_uncertainty_score":0.0059890747},"labels":[],"label_agreement":null},{"id":"W3033148464","doi":"10.1145/3386901.3396605","title":"Deduplicating future data transfer using data exchanged in the past to decrease mobile bandwidth usage","year":2020,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"","keywords":"Computer science; Download; Bandwidth (computing); Transfer (computing); Server; Computer network; Operating system; Order (exchange); Business","score_opus":0.12290832532610609,"score_gpt":0.3225025299580144,"score_spread":0.1995942046319083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033148464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38053218,0.011789122,0.5274074,0.005144285,0.008882938,0.0010977408,0.0068087555,0.015128858,0.04320869],"genre_scores_gemma":[0.71312547,0.0040403786,0.22668697,0.0013948834,0.0021843798,0.0005555341,0.008586525,0.0018117221,0.04161423],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992361,0.00007274846,0.00011274962,0.00018021204,0.00031856293,0.00007967666],"domain_scores_gemma":[0.9911616,0.0011525971,0.000404638,0.0049257125,0.0021013985,0.00025404236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014849048,0.00083870516,0.0008043017,0.002335917,0.0013337802,0.0020964374,0.0016461891,0.00081528205,0.0067596114],"category_scores_gemma":[0.00954069,0.00048001413,0.0004832289,0.0024551747,0.0006864278,0.0044274842,0.002184935,0.0012877353,0.0043584444],"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":[0.0014231054,0.0005512385,0.011451808,0.0012952691,0.0002111259,0.0021001308,0.0021987322,0.017951408,0.16486919,0.02074211,0.044835243,0.73237073],"study_design_scores_gemma":[0.00026063283,0.0011356216,0.015220154,0.0006840182,0.0003950994,0.00642564,0.0023565998,0.13492493,0.3579583,0.03533277,0.44496447,0.00034185697],"about_ca_topic_score_codex":0.0010886447,"about_ca_topic_score_gemma":0.001119937,"teacher_disagreement_score":0.0067596114,"about_ca_system_score_codex":0.0005113573,"about_ca_system_score_gemma":0.0009597072,"threshold_uncertainty_score":0.022613168},"labels":[],"label_agreement":null},{"id":"W3034373981","doi":"10.4230/lipics.cpm.2021.13","title":"A Fast and Small Subsampled R-Index","year":2020,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.03198763216395205,"score_gpt":0.25634886082708896,"score_spread":0.2243612286631369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034373981","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025267107,0.002983943,0.8828052,0.0009141923,0.00084799004,0.0005524734,0.007261424,0.06704502,0.012322607],"genre_scores_gemma":[0.06797004,0.00068499456,0.8895251,0.0006411357,0.0002846306,0.00061052165,0.01903319,0.004338296,0.016912187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997983,0.00018924376,0.00017274836,0.00042764764,0.0010539588,0.00017345657],"domain_scores_gemma":[0.9972459,0.00043507753,0.00017373076,0.0011921551,0.0007876542,0.00016543912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008173068,0.0017634187,0.001945003,0.002566265,0.0014125454,0.0023816412,0.00331614,0.0012450163,0.019540686],"category_scores_gemma":[0.007769736,0.0007224879,0.0014253876,0.004123377,0.0007924621,0.0043758377,0.003918101,0.0016244682,0.022841854],"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":[0.001275891,0.00026117425,0.0021100906,0.0005002707,0.00015902537,0.0005793625,0.00033725018,0.015130485,0.035234924,0.021026121,0.13585754,0.78752786],"study_design_scores_gemma":[0.0007510658,0.00083321054,0.0030063323,0.00017900558,0.00019977076,0.0023709321,0.0004445485,0.6185625,0.083440885,0.08038123,0.20940651,0.00042402447],"about_ca_topic_score_codex":0.00494125,"about_ca_topic_score_gemma":0.0070686266,"teacher_disagreement_score":0.019540686,"about_ca_system_score_codex":0.0010076531,"about_ca_system_score_gemma":0.002562434,"threshold_uncertainty_score":0.06537014},"labels":[],"label_agreement":null},{"id":"W3035862496","doi":"10.1007/978-3-030-59212-7_16","title":"Practical Random Access to SLP-Compressed Texts","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Grammar; Rule-based machine translation; Simple (philosophy); Encoding (memory); Random access; Process (computing); Compression (physics); Theoretical computer science; Data compression; Artificial intelligence; Programming language; Linguistics","score_opus":0.047602032211029904,"score_gpt":0.3466941386429499,"score_spread":0.29909210643191997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035862496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14033626,0.0011478914,0.8258551,0.0047259526,0.0005407604,0.000424147,0.0025616142,0.0060229665,0.018385299],"genre_scores_gemma":[0.7692018,0.000721433,0.20342316,0.0008951602,0.0010703416,0.00048373625,0.0036616942,0.00077102496,0.019771602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931772,0.0021723246,0.0005039332,0.0007950358,0.0024707,0.0008809107],"domain_scores_gemma":[0.9749312,0.014762295,0.0007252119,0.007022178,0.0021068172,0.00045227018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029827156,0.0009553454,0.0014791779,0.001212291,0.0009227291,0.002373168,0.0012799961,0.0019499506,0.017148444],"category_scores_gemma":[0.025828272,0.00071380415,0.00064136076,0.0021703236,0.0015590888,0.00389458,0.0054361057,0.0020156298,0.004915609],"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":[0.0077456473,0.00053157815,0.0017868911,0.0012042206,0.00020242712,0.0016068299,0.0008950535,0.08311617,0.06443833,0.16924646,0.043817528,0.6254089],"study_design_scores_gemma":[0.0005463071,0.0004120928,0.00068619155,0.00013919576,0.00009642131,0.0010258344,0.00032841275,0.6945882,0.06468734,0.22469911,0.012716876,0.00007402939],"about_ca_topic_score_codex":0.00085649703,"about_ca_topic_score_gemma":0.0015387646,"teacher_disagreement_score":0.017148444,"about_ca_system_score_codex":0.0007565207,"about_ca_system_score_gemma":0.001820787,"threshold_uncertainty_score":0.057367206},"labels":[],"label_agreement":null},{"id":"W3036015462","doi":"10.4230/lipics.esa.2020.54","title":"Fast Preprocessing for Optimal Orthogonal Range Reporting and Range Successor with Applications to Text Indexing","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Successor cardinal; Combinatorics; Search engine indexing; Data structure; Range (aeronautics); Word (group theory); Linear space; Mathematics; Space (punctuation); Preprocessor; Discrete mathematics; Algorithm; Computer science; Geometry; Mathematical analysis; Information retrieval; Artificial intelligence","score_opus":0.0965797822671465,"score_gpt":0.23505893292937236,"score_spread":0.13847915066222585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036015462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0449054,0.0009536533,0.9173777,0.0008908822,0.00017718702,0.00051068055,0.0021933776,0.024899783,0.008091433],"genre_scores_gemma":[0.1630533,0.00034270328,0.8259528,0.00030923713,0.00013532187,0.0005993501,0.0050873337,0.0011419847,0.0033779324],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972705,0.0003909378,0.00039590345,0.0006390789,0.0009437154,0.0003598405],"domain_scores_gemma":[0.992596,0.0024086977,0.000654717,0.0033207932,0.0008165863,0.00020329136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012279107,0.0012385112,0.0017878882,0.0023963556,0.001323567,0.003120492,0.0031110384,0.001190753,0.010638248],"category_scores_gemma":[0.009120146,0.00087641994,0.0017821471,0.006056468,0.0012255575,0.008612204,0.004001627,0.0016753592,0.00616256],"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":[0.0012112051,0.0004671057,0.0030529145,0.00081447273,0.00008144793,0.00024531945,0.00073581206,0.021345075,0.04224801,0.0641914,0.036199287,0.8294079],"study_design_scores_gemma":[0.00068348675,0.0010066022,0.002562824,0.00017684446,0.00018179876,0.001027928,0.00088245113,0.59857535,0.08992754,0.24560404,0.059064355,0.000306743],"about_ca_topic_score_codex":0.0032764205,"about_ca_topic_score_gemma":0.0051729726,"teacher_disagreement_score":0.010638248,"about_ca_system_score_codex":0.001311453,"about_ca_system_score_gemma":0.0033890603,"threshold_uncertainty_score":0.035588443},"labels":[],"label_agreement":null},{"id":"W3037080634","doi":"10.1016/j.disc.2020.112022","title":"Efficient universal cycle constructions for weak orders","year":2020,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea","keywords":"Mathematics; Transitive relation; Combinatorics; Rank (graph theory); Order (exchange); Construct (python library); Discrete mathematics; Event (particle physics); Computer science","score_opus":0.017558851393745693,"score_gpt":0.24588546281322898,"score_spread":0.2283266114194833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037080634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15932462,0.001366219,0.78214633,0.0016881642,0.00027247824,0.00028550706,0.0009613514,0.0021068451,0.051848408],"genre_scores_gemma":[0.7620946,0.0012646494,0.20922573,0.0005696059,0.00017826601,0.0004386061,0.0014917941,0.0012001023,0.023536606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986405,0.0002723462,0.00009809588,0.00019845791,0.00048283837,0.00030776425],"domain_scores_gemma":[0.99683565,0.0013354394,0.00013126306,0.0010897466,0.00039448324,0.00021334908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012304866,0.00089533284,0.0010743933,0.001872494,0.0017086425,0.003159387,0.0016022215,0.0009852026,0.009592341],"category_scores_gemma":[0.005458089,0.0007010183,0.0011271101,0.0027146898,0.0022215713,0.0075688125,0.005477573,0.002871934,0.0014356825],"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":[0.00013624199,0.000051418927,0.00031429974,0.0001312908,0.000011936739,0.000041330455,0.0002859015,0.0041409424,0.0024659615,0.94229627,0.0035543388,0.046569966],"study_design_scores_gemma":[0.000022391983,0.000031065105,0.00009276246,0.00005115243,0.000020336787,0.000038766222,0.00011097767,0.01612475,0.004887113,0.96784556,0.010755684,0.000019405925],"about_ca_topic_score_codex":0.0009189261,"about_ca_topic_score_gemma":0.0017947074,"teacher_disagreement_score":0.009592341,"about_ca_system_score_codex":0.001850567,"about_ca_system_score_gemma":0.0012547163,"threshold_uncertainty_score":0.03208965},"labels":[],"label_agreement":null},{"id":"W3037898113","doi":"","title":"Succinct Posets","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Partially ordered set; Combinatorics; Mathematics; Reachability; Transitive closure; Transitive relation; Oracle; Transitive reduction; Discrete mathematics; Graph; Directed graph; Line graph; Computer science; Voltage graph","score_opus":0.07447969489359674,"score_gpt":0.1852341618294131,"score_spread":0.11075446693581636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037898113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024031835,0.00051138055,0.9504471,0.0011221324,0.0001940347,0.00048434554,0.006914675,0.007436898,0.00885753],"genre_scores_gemma":[0.2345434,0.0007246928,0.7355512,0.0006988324,0.00020404148,0.0011464484,0.016945278,0.0011836892,0.0090024145],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963942,0.00058182224,0.0004083988,0.0006201717,0.001674479,0.00032096275],"domain_scores_gemma":[0.9929912,0.0023593097,0.00048136365,0.003033973,0.0009381965,0.0001960247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013634065,0.0012883702,0.0012826695,0.0021669432,0.00093668216,0.0032142345,0.0023214412,0.0010085279,0.016907018],"category_scores_gemma":[0.012010235,0.0008423939,0.0015267004,0.003596303,0.0016543556,0.009325211,0.0043782047,0.002809334,0.0037481776],"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":[0.00085726776,0.0002875439,0.0016685636,0.0007064603,0.00008011044,0.00048808995,0.00088600593,0.064885475,0.018474242,0.39029676,0.036513824,0.48485577],"study_design_scores_gemma":[0.00015581698,0.00025111865,0.00035570932,0.00020648478,0.000058609065,0.00062629953,0.0004332127,0.22366923,0.039719786,0.6634802,0.07094483,0.00009866723],"about_ca_topic_score_codex":0.0014399922,"about_ca_topic_score_gemma":0.0025596956,"teacher_disagreement_score":0.016907018,"about_ca_system_score_codex":0.0013712713,"about_ca_system_score_gemma":0.0019619772,"threshold_uncertainty_score":0.056559563},"labels":[],"label_agreement":null},{"id":"W3046751557","doi":"10.18280/isi.250315","title":"Classifying Limited Resource Data Using Semi-supervised SVM","year":2020,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Computer science; Resource (disambiguation); Artificial intelligence; Machine learning; Pattern recognition (psychology); Supervised learning; Data mining; Artificial neural network","score_opus":0.11936578616622559,"score_gpt":0.2811440190834783,"score_spread":0.1617782329172527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046751557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18700773,0.0004743319,0.8068017,0.00033327143,0.00009787422,0.0001742751,0.0006320015,0.0027510028,0.0017279006],"genre_scores_gemma":[0.81327266,0.0001894695,0.18194999,0.00011329279,0.000074154595,0.00018893614,0.002314076,0.00009294899,0.0018045597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986098,0.00043070564,0.00015164576,0.00029393428,0.00039965188,0.00011421916],"domain_scores_gemma":[0.9952884,0.0020373987,0.0004554552,0.0007920099,0.001310967,0.00011581805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016822226,0.0009125794,0.0011780278,0.0012872032,0.00037890582,0.0011955388,0.0013127952,0.0010805108,0.0010123657],"category_scores_gemma":[0.0054644058,0.00028625876,0.0007880834,0.000992191,0.0005452187,0.0016139462,0.0007350529,0.0011827479,0.00081811094],"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":[0.0007528524,0.0008803713,0.0068053375,0.0003102939,0.00019230534,0.0002500351,0.00022300704,0.35122377,0.026715638,0.0024073797,0.008406032,0.601833],"study_design_scores_gemma":[0.000005185287,0.000040004972,0.00058450655,0.0000057890984,0.0000048130446,0.000028376107,0.000024286142,0.9945903,0.0035227283,0.0009477764,0.00023921493,0.0000069778457],"about_ca_topic_score_codex":0.002110271,"about_ca_topic_score_gemma":0.0023660688,"teacher_disagreement_score":0.002110271,"about_ca_system_score_codex":0.00044633643,"about_ca_system_score_gemma":0.00090467045,"threshold_uncertainty_score":0.00889653},"labels":[],"label_agreement":null},{"id":"W3046970181","doi":"10.1016/j.tcs.2020.07.035","title":"Generating a Gray code for prefix normal words in amortized polylogarithmic time per word","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Prefix; Substring; Word (group theory); Amortized analysis; Gray code; Combinatorics; Prefix code; Mathematics; Arithmetic; Time complexity; Computer science; Discrete mathematics; Set (abstract data type); Algorithm; Data structure; Decoding methods; Linear code; Programming language; Linguistics","score_opus":0.013084670613608457,"score_gpt":0.2519275911630902,"score_spread":0.23884292054948175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046970181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2814513,0.00063162245,0.6844762,0.0021135055,0.00051995576,0.00050714676,0.0011562619,0.0077846423,0.021359378],"genre_scores_gemma":[0.6250413,0.00025580171,0.35436174,0.0007338035,0.0001946536,0.00056670234,0.0018840162,0.0013427358,0.015619318],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978903,0.00032331608,0.00015493788,0.0003924561,0.00086361956,0.00037545976],"domain_scores_gemma":[0.9948101,0.0025161742,0.0002675183,0.0014194581,0.0007759392,0.00021074752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076807657,0.0010199687,0.0010607137,0.0011747344,0.00095775194,0.0017953106,0.0013032648,0.001523882,0.009474707],"category_scores_gemma":[0.0073933983,0.00045275438,0.0010023286,0.0018839631,0.0016706914,0.0026871073,0.0036657627,0.0014189151,0.0027828563],"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":[0.0022638382,0.00055851886,0.003829373,0.000628882,0.00016274626,0.0010095262,0.00079638057,0.10877846,0.092066154,0.2123016,0.03335883,0.5442456],"study_design_scores_gemma":[0.00041992337,0.00042266768,0.00088800245,0.0000951818,0.00012613533,0.00060423417,0.00020473267,0.5563811,0.06212835,0.36728743,0.011363913,0.00007832974],"about_ca_topic_score_codex":0.001948037,"about_ca_topic_score_gemma":0.0030829783,"teacher_disagreement_score":0.009474707,"about_ca_system_score_codex":0.0017351874,"about_ca_system_score_gemma":0.0024055338,"threshold_uncertainty_score":0.03169602},"labels":[],"label_agreement":null},{"id":"W3047376977","doi":"10.1016/j.tcs.2020.07.042","title":"Exact algorithms for the repetition-bounded longest common subsequence problem","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Japan Science and Technology Agency; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Hong Kong Polytechnic University","keywords":"Subsequence; Longest common subsequence problem; Algorithm; Combinatorics; Longest increasing subsequence; Bounded function; Sequence (biology); Constraint (computer-aided design); Upper and lower bounds; Symbol (formal); Mathematics; Function (biology); Exponential time hypothesis; Exponential function; Time complexity; Discrete mathematics; Computer science","score_opus":0.0279039761775633,"score_gpt":0.2783191148854392,"score_spread":0.2504151387078759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047376977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018838895,0.0017900657,0.9676908,0.0007119815,0.00022413046,0.00033080217,0.00055270287,0.0044041723,0.0054564746],"genre_scores_gemma":[0.13630223,0.0008423559,0.8544878,0.00046853305,0.0003004482,0.0005492117,0.0021352088,0.00090989703,0.0040043076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99292725,0.0013171778,0.0005693646,0.0023570056,0.0017794869,0.0010497211],"domain_scores_gemma":[0.98777616,0.007747887,0.0010322835,0.0021862695,0.000970401,0.00028692253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036023157,0.0028869156,0.0027582664,0.0019979,0.0017426701,0.0026726744,0.0054916334,0.0026040422,0.009239518],"category_scores_gemma":[0.019296693,0.0011701403,0.0019716215,0.0045763203,0.0018935907,0.008414712,0.0032344118,0.0036689742,0.00346685],"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":[0.0014476305,0.00067542924,0.0021834879,0.0020816126,0.0003877573,0.00041020883,0.00077166833,0.37443322,0.011131636,0.12921524,0.032717973,0.44454417],"study_design_scores_gemma":[0.0003606501,0.00020784888,0.00033378453,0.00007927918,0.0000941014,0.00034489468,0.00018118584,0.76285994,0.004143566,0.22227728,0.009052931,0.000064625056],"about_ca_topic_score_codex":0.0035193812,"about_ca_topic_score_gemma":0.003927686,"teacher_disagreement_score":0.009239518,"about_ca_system_score_codex":0.0026216567,"about_ca_system_score_gemma":0.005093445,"threshold_uncertainty_score":0.0309093},"labels":[],"label_agreement":null},{"id":"W3082166776","doi":"10.1007/978-3-030-58150-3_47","title":"Even Better Fixed-Parameter Algorithms for Bicluster Editing","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Algorithm","score_opus":0.027015017549112483,"score_gpt":0.2637856606953823,"score_spread":0.2367706431462698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082166776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039349394,0.0007678784,0.982959,0.000458433,0.00046186204,0.000063507396,0.00024896444,0.0064353114,0.0046700607],"genre_scores_gemma":[0.031726263,0.00026554771,0.95403475,0.00049171236,0.00024630263,0.00013136379,0.0008985715,0.0028216813,0.009383846],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964623,0.0010575178,0.0002900917,0.0010325399,0.0009173,0.00024036286],"domain_scores_gemma":[0.9885443,0.0039028237,0.00027839816,0.005851453,0.0011474023,0.0002756243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002857739,0.0021797658,0.0020624725,0.0015890382,0.0012201709,0.0035582108,0.0041260077,0.003096258,0.038954735],"category_scores_gemma":[0.020802606,0.0010061944,0.0020013275,0.0033506148,0.0016894122,0.007737281,0.003069564,0.004766847,0.017966075],"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":[0.00096266915,0.00027097246,0.0005361081,0.00037150976,0.00017202404,0.00015470674,0.00034729752,0.046460263,0.019702084,0.062649004,0.051691014,0.81668234],"study_design_scores_gemma":[0.00037643386,0.00023969568,0.00061345595,0.00015620355,0.00012292402,0.0006662165,0.00025140852,0.64803606,0.030948237,0.24267554,0.07572799,0.00018579977],"about_ca_topic_score_codex":0.0019975244,"about_ca_topic_score_gemma":0.0048801024,"teacher_disagreement_score":0.038954735,"about_ca_system_score_codex":0.0010285738,"about_ca_system_score_gemma":0.0009653222,"threshold_uncertainty_score":0.13031656},"labels":[],"label_agreement":null},{"id":"W3084173750","doi":"","title":"Time-space tradeoffs for all-nearest-larger-neighbors problems","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Pointer (user interface); Upper and lower bounds; Monotone polygon; Mathematics; Combinatorics; Time complexity; Perfect hash function; Space (punctuation); String (physics); Computer science; Theoretical computer science; Discrete mathematics; Algorithm; Cryptography; Artificial intelligence","score_opus":0.01694174337681547,"score_gpt":0.23434066824576283,"score_spread":0.21739892486894735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084173750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18859158,0.0032863175,0.7642033,0.0066570058,0.00054783345,0.00050172163,0.00090540404,0.0029480392,0.032358725],"genre_scores_gemma":[0.4518479,0.0011676827,0.5316099,0.0008635436,0.0005118176,0.00050264195,0.0015964423,0.000842791,0.011057272],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99257773,0.0021029676,0.000518948,0.0016900608,0.0020826797,0.0010276706],"domain_scores_gemma":[0.9780241,0.014203374,0.0012247746,0.004795607,0.00105724,0.00069484423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046333517,0.0014755222,0.002112821,0.0010218619,0.0022577946,0.0039614025,0.004728367,0.0023942639,0.010765112],"category_scores_gemma":[0.024925113,0.0008726851,0.0014848999,0.0024323252,0.0024399874,0.016396478,0.0046292744,0.0036544844,0.0018598161],"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":[0.002652308,0.0013256293,0.003307189,0.0013379835,0.0001727113,0.00032233197,0.0013761614,0.3041469,0.013511132,0.23527338,0.032896757,0.40367752],"study_design_scores_gemma":[0.0003555573,0.00030436076,0.0007110573,0.000071266724,0.00008332059,0.00056372455,0.00067974045,0.7451168,0.009711839,0.22979802,0.012532011,0.00007236755],"about_ca_topic_score_codex":0.0021981576,"about_ca_topic_score_gemma":0.004068053,"teacher_disagreement_score":0.010765112,"about_ca_system_score_codex":0.0026733936,"about_ca_system_score_gemma":0.0026192563,"threshold_uncertainty_score":0.036012888},"labels":[],"label_agreement":null},{"id":"W3086212533","doi":"10.14778/3407790.3407861","title":"Suffix rank","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"University of Victoria; University of Toronto","funders":"","keywords":"Substring; Suffix array; Suffix; Generalized suffix tree; Computer science; Suffix tree; Compressed suffix array; Scalability; Rank (graph theory); Extension (predicate logic); Liveness; Algorithm; Context (archaeology); Parallelizable manifold; Auxiliary memory; Theoretical computer science; Data structure; Mathematics; Combinatorics; Database","score_opus":0.01641272735555164,"score_gpt":0.20674939338029258,"score_spread":0.19033666602474095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086212533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08433167,0.0024758205,0.8449347,0.002205421,0.0004948667,0.00047897387,0.005492691,0.0145609435,0.045024924],"genre_scores_gemma":[0.27593225,0.001334964,0.6801626,0.0007248614,0.0004983413,0.00038977177,0.009222846,0.001395304,0.030338997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979773,0.00023829978,0.0001960593,0.000489657,0.0008640319,0.00023465673],"domain_scores_gemma":[0.99469006,0.0019883073,0.00036593692,0.0016475677,0.0010976031,0.00021054874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176269,0.00092675735,0.0013555036,0.0017609148,0.0010974888,0.0026846894,0.0021150229,0.00117613,0.018303366],"category_scores_gemma":[0.010887719,0.00037677595,0.0006677226,0.0040359553,0.0008124274,0.0060689044,0.0023834466,0.0012739374,0.009032955],"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":[0.0006139627,0.00022789944,0.0032059,0.0006130693,0.00006407866,0.00026909873,0.00024148254,0.045197472,0.013310955,0.0635201,0.060971156,0.8117649],"study_design_scores_gemma":[0.00015452038,0.0006445854,0.001104409,0.00012023241,0.00007585423,0.0013066281,0.00046067475,0.68058234,0.04814653,0.17528723,0.09205285,0.00006418587],"about_ca_topic_score_codex":0.0014725849,"about_ca_topic_score_gemma":0.002310262,"teacher_disagreement_score":0.018303366,"about_ca_system_score_codex":0.00081078894,"about_ca_system_score_gemma":0.0017932934,"threshold_uncertainty_score":0.06123084},"labels":[],"label_agreement":null},{"id":"W3087695592","doi":"10.3390/a13090234","title":"More Time-Space Tradeoffs for Finding a Shortest Unique Substring","year":2020,"lang":"en","type":"article","venue":"Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Academy of Finland","keywords":"Substring; Combinatorics; Sublinear function; Binary logarithm; Mathematics; Generalization; Space (punctuation); Constant (computer programming); Workspace; Algorithm; Discrete mathematics; Computer science; Data structure; Artificial intelligence","score_opus":0.038314744892572784,"score_gpt":0.2697027902965243,"score_spread":0.2313880454039515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087695592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13574322,0.0056744376,0.8364112,0.005148958,0.0005306059,0.00022894627,0.0007372918,0.0028942763,0.012631026],"genre_scores_gemma":[0.42063382,0.0016788061,0.5663654,0.00083009264,0.0007962815,0.0003759623,0.0014059991,0.0009448428,0.006968758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98941165,0.0026289101,0.0013661641,0.002687092,0.0031175197,0.0007885369],"domain_scores_gemma":[0.9462426,0.03349225,0.0028692654,0.014091746,0.0022937185,0.0010103557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075361407,0.0017649771,0.0022504453,0.0029183575,0.0017622731,0.003985301,0.0035500624,0.0030726253,0.014820595],"category_scores_gemma":[0.04549723,0.0010100603,0.0026212714,0.0053505623,0.0027758293,0.024589712,0.0040470106,0.003928837,0.0030985374],"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":[0.003580821,0.0011670256,0.0068588075,0.0015514429,0.0003103901,0.0004930849,0.0016319801,0.18773308,0.045019887,0.21783952,0.014634243,0.5191797],"study_design_scores_gemma":[0.00034777884,0.0009075478,0.0017095392,0.000112093214,0.00016237704,0.0011096763,0.00039475234,0.67819226,0.023119338,0.28167188,0.012122629,0.00015009317],"about_ca_topic_score_codex":0.0014671184,"about_ca_topic_score_gemma":0.0023755222,"teacher_disagreement_score":0.014820595,"about_ca_system_score_codex":0.002886906,"about_ca_system_score_gemma":0.001794633,"threshold_uncertainty_score":0.04957986},"labels":[],"label_agreement":null},{"id":"W3087991744","doi":"10.3390/a13110294","title":"Computing Maximal Lyndon Substrings of a String","year":2020,"lang":"en","type":"article","venue":"Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Suffix array; Suffix tree; Algorithm; String (physics); Generalized suffix tree; Time complexity; Mathematics; Suffix; Combinatorics; Compressed suffix array; String searching algorithm; Sorting; Computer science; Discrete mathematics; Data structure","score_opus":0.027067470436966008,"score_gpt":0.24094479113280345,"score_spread":0.21387732069583745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087991744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09644933,0.0005593869,0.8887429,0.0002508037,0.00016491587,0.00012373817,0.00086904265,0.0053127087,0.00752713],"genre_scores_gemma":[0.33339062,0.0002762981,0.6539387,0.00026609746,0.00010766675,0.0001691716,0.0029486893,0.0010215176,0.007881163],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822956,0.00019144182,0.00026051333,0.0005956262,0.00043720283,0.0002856776],"domain_scores_gemma":[0.9968226,0.001453266,0.0002625326,0.00071763207,0.0005925964,0.00015141797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010553318,0.00088473834,0.0016842538,0.00197903,0.0012265192,0.0028934167,0.0012741382,0.0013186982,0.009185466],"category_scores_gemma":[0.009189859,0.00055248156,0.0016232012,0.0018937242,0.0015195735,0.0057226177,0.0023363193,0.0013105664,0.0042305086],"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":[0.0026757785,0.00026826735,0.009067236,0.0013645292,0.00019423227,0.0015983596,0.0022896228,0.0551142,0.10984993,0.2462787,0.009719708,0.56157947],"study_design_scores_gemma":[0.0001377365,0.0005842911,0.002289074,0.00033962677,0.00011353453,0.0009383694,0.0009794848,0.2964989,0.10075802,0.56372505,0.03341923,0.00021669756],"about_ca_topic_score_codex":0.00181665,"about_ca_topic_score_gemma":0.0032343655,"teacher_disagreement_score":0.009185466,"about_ca_system_score_codex":0.0010636835,"about_ca_system_score_gemma":0.0016790855,"threshold_uncertainty_score":0.03072846},"labels":[],"label_agreement":null},{"id":"W3089486988","doi":"10.1145/3412324","title":"Computing Autotopism Groups of Partial Latin Rectangles","year":2020,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","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":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Backtracking; Computation; Graph; Software; Group (periodic table); Theoretical computer science; Algorithm; Programming language","score_opus":0.035444555925030666,"score_gpt":0.2810990042413903,"score_spread":0.24565444831635963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089486988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4567426,0.00020261947,0.5226224,0.00014964635,0.000047998463,0.00009679649,0.00028376147,0.0055074985,0.014346569],"genre_scores_gemma":[0.6878049,0.000076657605,0.3070072,0.000071105795,0.00002805558,0.0000667306,0.0008589778,0.0005307067,0.0035557374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917173,0.000205356,0.00005563142,0.00024397002,0.00018807342,0.00013528875],"domain_scores_gemma":[0.9974661,0.001089149,0.00032841953,0.0007271783,0.00028049745,0.0001086156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008315643,0.0005180432,0.0006013047,0.001251464,0.00041744427,0.0013197655,0.0010370031,0.0005287046,0.0053201704],"category_scores_gemma":[0.003449115,0.00037628837,0.00092835125,0.00093678915,0.0010731438,0.0027521257,0.0014957557,0.00054535846,0.0012120318],"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":[0.0010850491,0.00023443597,0.020682326,0.0005796597,0.00016451554,0.00051076186,0.0014674463,0.23704281,0.051199608,0.17203322,0.007949302,0.5070509],"study_design_scores_gemma":[0.00015487634,0.00054199423,0.0036659946,0.00006731163,0.000055130196,0.00043545844,0.0007199768,0.80590385,0.054791857,0.12156877,0.012014654,0.00008015126],"about_ca_topic_score_codex":0.0018211207,"about_ca_topic_score_gemma":0.0022245096,"teacher_disagreement_score":0.0053201704,"about_ca_system_score_codex":0.0005440644,"about_ca_system_score_gemma":0.0008490697,"threshold_uncertainty_score":0.017797709},"labels":[],"label_agreement":null},{"id":"W3090465494","doi":"10.1007/978-3-030-59212-7_16","title":"Practical Random Access to SLP-Compressed Texts","year":2020,"lang":"en","type":"book-chapter","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Grammar; Random access; Rule-based machine translation; Simple (philosophy); Encoding (memory); Compression (physics); Process (computing); Data compression; Theoretical computer science; Artificial intelligence; Programming language; Linguistics","score_opus":0.13572451069910507,"score_gpt":0.3454069256700878,"score_spread":0.20968241497098272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090465494","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06082557,0.0011961652,0.89552647,0.0015674517,0.00035475983,0.0003077651,0.0013057403,0.0058728373,0.03304323],"genre_scores_gemma":[0.49567938,0.0013081186,0.44716427,0.0005696076,0.0008444173,0.00058115786,0.0039771753,0.0011940802,0.048681956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693775,0.0009903191,0.0001991077,0.00034071095,0.0011615527,0.0003705945],"domain_scores_gemma":[0.9912627,0.0051624025,0.00020785055,0.0024704544,0.00076177507,0.00013481386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016555381,0.0008201012,0.001030569,0.001119019,0.00081377866,0.0019602887,0.0011131846,0.0012926968,0.025055462],"category_scores_gemma":[0.012587532,0.0005616187,0.00053081405,0.002095438,0.0011024058,0.0030570854,0.0038105822,0.0014333199,0.007451408],"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":[0.0021179644,0.00020907226,0.00044833435,0.0006503898,0.00008011796,0.00067753985,0.0005061371,0.03456298,0.03998026,0.12878868,0.037986204,0.75399226],"study_design_scores_gemma":[0.00029753827,0.00036511378,0.0006485181,0.0001841055,0.000070087735,0.0013340667,0.00041839547,0.6407321,0.080822185,0.23794037,0.03711717,0.00007035527],"about_ca_topic_score_codex":0.00079530274,"about_ca_topic_score_gemma":0.0015228174,"teacher_disagreement_score":0.025055462,"about_ca_system_score_codex":0.0005724811,"about_ca_system_score_gemma":0.0010689099,"threshold_uncertainty_score":0.08381891},"labels":[],"label_agreement":null},{"id":"W3093219505","doi":"","title":"Lazy Search Trees","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Combinatorics; Binary search tree; Data structure; Priority queue; Binary logarithm; Log-log plot; Mathematics; Merge (version control); Upper and lower bounds; Partition (number theory); Pointer (user interface); Time complexity; Sequence (biology); Binary tree; Computer science; Discrete mathematics; Queue; Parallel computing","score_opus":0.1268476958281181,"score_gpt":0.20404729240036418,"score_spread":0.07719959657224607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093219505","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02216428,0.0040349104,0.9408719,0.0016106091,0.00051279913,0.00035556956,0.002050375,0.008800327,0.01959917],"genre_scores_gemma":[0.2478567,0.003026028,0.71603864,0.0015122228,0.0006049231,0.0007192569,0.004243363,0.002014112,0.023984876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965681,0.0005588768,0.00034456022,0.0006254168,0.0014322829,0.00047083673],"domain_scores_gemma":[0.99635726,0.0011520693,0.00033304232,0.0012214581,0.00065999443,0.0002760699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017282467,0.00074061466,0.0015270755,0.0022722809,0.0020195001,0.0044761226,0.002872151,0.0014600647,0.012401135],"category_scores_gemma":[0.009299477,0.00082395197,0.001248085,0.0038634753,0.0020422486,0.011707036,0.004601347,0.0025479514,0.0058078356],"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":[0.0004737515,0.00022325719,0.0026671903,0.00060254737,0.000090847665,0.00024270108,0.00076246046,0.032669656,0.0068645696,0.6168273,0.04586188,0.29271385],"study_design_scores_gemma":[0.00014926212,0.00025441244,0.0004160263,0.00016908278,0.00007378779,0.00045714172,0.00021890139,0.15407526,0.006321305,0.68913054,0.14863773,0.00009658038],"about_ca_topic_score_codex":0.0031374015,"about_ca_topic_score_gemma":0.004272659,"teacher_disagreement_score":0.012401135,"about_ca_system_score_codex":0.002176896,"about_ca_system_score_gemma":0.002839762,"threshold_uncertainty_score":0.041485906},"labels":[],"label_agreement":null},{"id":"W3098936105","doi":"","title":"Lyndon Array construction during Burrows-Wheeler inversion","year":2018,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Inversion (geology); Algorithm; Stack (abstract data type); Inverse; Time complexity; Mathematics; String (physics); Computer science; Binary logarithm; Representation (politics); Combinatorics; Running time; Geometry","score_opus":0.029725238711046657,"score_gpt":0.26681456415532795,"score_spread":0.2370893254442813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098936105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012804869,0.00022010373,0.95082015,0.00028894862,0.00041063986,0.00016922416,0.0009058975,0.014141961,0.020238273],"genre_scores_gemma":[0.115329236,0.00019413007,0.8437901,0.0003604626,0.00015564376,0.00046157674,0.0031964409,0.00644964,0.030062731],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99759644,0.00046096192,0.00020024255,0.00041321106,0.00091048994,0.00041869358],"domain_scores_gemma":[0.99646133,0.0006517236,0.00010570132,0.0013924654,0.0012854222,0.00010338104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015228115,0.001098552,0.0011324697,0.001851217,0.0017947305,0.0025224101,0.0022310843,0.0010686798,0.04046565],"category_scores_gemma":[0.009309195,0.0008149613,0.0010353413,0.0028336544,0.0009505987,0.0027837881,0.003229757,0.0022133517,0.025235211],"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":[0.0008667063,0.0001360802,0.0015545139,0.0003592807,0.00006197612,0.0003592324,0.00078096235,0.006258982,0.042393945,0.12568459,0.081676416,0.7398674],"study_design_scores_gemma":[0.00028827073,0.00036833592,0.0014664335,0.00023692158,0.00012625633,0.0007788615,0.0008481164,0.08905216,0.26892594,0.22926612,0.40841553,0.00022700937],"about_ca_topic_score_codex":0.002195601,"about_ca_topic_score_gemma":0.0047720075,"teacher_disagreement_score":0.04046565,"about_ca_system_score_codex":0.000939106,"about_ca_system_score_gemma":0.0028647128,"threshold_uncertainty_score":0.13537109},"labels":[],"label_agreement":null},{"id":"W3099878876","doi":"","title":"Array programming with NumPy","year":2020,"lang":"en","type":"review","venue":"TUScholarShare (Temple University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18805,"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; University of Toronto","funders":"","keywords":"Computer science","score_opus":0.055732417747156024,"score_gpt":0.2719552118369395,"score_spread":0.21622279408978345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099878876","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015548706,0.07629847,0.77594256,0.0056228787,0.0027900755,0.00042671684,0.008101626,0.055403728,0.073858954],"genre_scores_gemma":[0.030546159,0.14414956,0.72856534,0.0070778597,0.0025283836,0.003322498,0.01706895,0.027392358,0.039348885],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809355,0.00053255557,0.00022519896,0.00027407272,0.0007477188,0.00012688177],"domain_scores_gemma":[0.99730045,0.0013089789,0.00019457209,0.00037611419,0.0006369083,0.00018297942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00231303,0.0015746654,0.0019660168,0.0023587358,0.0007822433,0.003201129,0.003368858,0.001257622,0.045142435],"category_scores_gemma":[0.008432261,0.0008436229,0.0019245461,0.004449083,0.0010929222,0.0038126137,0.0027420656,0.0041745836,0.03897416],"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":[0.00015605816,0.00005586939,0.0004199962,0.006175043,0.00017965867,0.00023863511,0.00030643825,0.006310891,0.0033545475,0.1075193,0.35221598,0.5230676],"study_design_scores_gemma":[0.00003381457,0.000017642527,0.00014077155,0.00046739844,0.000029488361,0.00021497671,0.0000219525,0.0041361884,0.0024912516,0.032981098,0.959426,0.00003944188],"about_ca_topic_score_codex":0.0010435267,"about_ca_topic_score_gemma":0.0008176706,"teacher_disagreement_score":0.045142435,"about_ca_system_score_codex":0.00068426365,"about_ca_system_score_gemma":0.0022367705,"threshold_uncertainty_score":0.15101653},"labels":[],"label_agreement":null},{"id":"W3100079455","doi":"10.1016/j.tcs.2020.11.019","title":"Maximal unbordered factors of random strings","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Horizon 2020 Framework Programme; Israel Science Foundation; Danmarks Frie Forskningsfond; United States-Israel Binational Science Foundation","keywords":"Combinatorics; String (physics); Mathematics; Conjecture; Suffix; Prefix; Alphabet; Unary operation; Discrete mathematics","score_opus":0.014780486485901885,"score_gpt":0.23757626745817365,"score_spread":0.22279578097227176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100079455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55991685,0.0030684185,0.35133618,0.0020203174,0.0005133317,0.00017066995,0.0007569845,0.0012045737,0.08101259],"genre_scores_gemma":[0.9371785,0.00092263415,0.032930136,0.00038834036,0.00041195125,0.00015660589,0.00047811752,0.0005406658,0.02699302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99699676,0.0009903682,0.00019349837,0.0006114512,0.0006175303,0.00059034297],"domain_scores_gemma":[0.9915249,0.005550348,0.00068620505,0.001098246,0.0005737511,0.0005665564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017168402,0.0010761879,0.0012953392,0.0020110875,0.0014483788,0.003800271,0.0010394447,0.0013934332,0.010075475],"category_scores_gemma":[0.013877164,0.0006152798,0.0009580567,0.001611975,0.00282361,0.005941024,0.0027218175,0.0019915542,0.0023078716],"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":[0.00058504415,0.000060058363,0.0005293582,0.00012242666,0.000025751677,0.00024651678,0.0003897617,0.0027381063,0.0047206823,0.969753,0.002157265,0.018672027],"study_design_scores_gemma":[0.000055375323,0.000080517384,0.00031113334,0.00007183472,0.00003022355,0.00029421126,0.000093695046,0.011626858,0.0052178777,0.97633386,0.00585181,0.000032507927],"about_ca_topic_score_codex":0.0004125786,"about_ca_topic_score_gemma":0.00045242367,"teacher_disagreement_score":0.010075475,"about_ca_system_score_codex":0.001150151,"about_ca_system_score_gemma":0.0006110778,"threshold_uncertainty_score":0.03370583},"labels":[],"label_agreement":null},{"id":"W3101131846","doi":"","title":"A fast algorithm for Stalling’s folding process","year":2013,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":37,"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":"Folding (DSP implementation); Mathematics; Combinatorics; Process (computing); Finitely-generated abelian group; Algorithm; Word (group theory); Discrete mathematics; Computer science; Geometry","score_opus":0.014071502449857193,"score_gpt":0.26047429188755356,"score_spread":0.24640278943769636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101131846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011068408,0.00026804078,0.98094213,0.0001841548,0.00014360218,0.0000972041,0.00011483761,0.0041436176,0.0030379386],"genre_scores_gemma":[0.09940132,0.00024453923,0.8927383,0.00018645232,0.000100018355,0.00023178534,0.0007178998,0.0007908048,0.005588872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885666,0.00024515582,0.00010952417,0.00028081378,0.0003236264,0.00018416444],"domain_scores_gemma":[0.9982817,0.0004839017,0.0000724227,0.0006583219,0.0004410913,0.000062482424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012478282,0.0014511393,0.0010625047,0.0013912328,0.0012800619,0.0012454778,0.0015169631,0.0014048651,0.00854905],"category_scores_gemma":[0.0035393138,0.00055225857,0.0009950484,0.0017785187,0.0010233207,0.002513256,0.0019097251,0.0020280126,0.0045536533],"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":[0.00064145593,0.0001356023,0.0016867057,0.0003087158,0.000077878314,0.00030943353,0.00066775555,0.03164523,0.061216988,0.10409296,0.019888548,0.77932864],"study_design_scores_gemma":[0.00024255617,0.00055461196,0.0014433588,0.00014519799,0.00012607069,0.0011673814,0.00045899145,0.42212823,0.16464257,0.32493407,0.083936304,0.00022068167],"about_ca_topic_score_codex":0.0011084387,"about_ca_topic_score_gemma":0.0010753864,"teacher_disagreement_score":0.00854905,"about_ca_system_score_codex":0.0007859104,"about_ca_system_score_gemma":0.00082171196,"threshold_uncertainty_score":0.028599441},"labels":[],"label_agreement":null},{"id":"W3102870242","doi":"10.1109/dcc50243.2021.00027","title":"PHONI: Streamed Matching Statistics with Multi-Genome References","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; National Institutes of Health; IFP Energies Nouvelles","keywords":"Computer science; Pointer (user interface); Pattern matching; Matching (statistics); Task (project management); Data mining; Theoretical computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.03412598368677618,"score_gpt":0.27020908288134354,"score_spread":0.23608309919456735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102870242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013728891,0.0007503998,0.7222788,0.00057501905,0.0005079629,0.00028283044,0.009219251,0.247168,0.005488817],"genre_scores_gemma":[0.092013694,0.0003611147,0.8699385,0.00033535194,0.00019925814,0.0006145197,0.021610407,0.009311259,0.005615887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982981,0.00012671694,0.00017034724,0.00045202335,0.0007907353,0.00016222653],"domain_scores_gemma":[0.9967428,0.00084516924,0.00021881095,0.001533491,0.00050536427,0.00015439323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015091003,0.0016996129,0.0011503663,0.0038198123,0.0009827839,0.003412539,0.005070748,0.0015849438,0.014618487],"category_scores_gemma":[0.012845232,0.0012315712,0.0013202174,0.006047505,0.0009706463,0.0044080224,0.004669329,0.001986732,0.011113384],"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":[0.0011229033,0.00020434312,0.004380326,0.00047132475,0.00020151187,0.00041334148,0.0004521797,0.03368881,0.018682137,0.040607996,0.16714814,0.732627],"study_design_scores_gemma":[0.00044499157,0.00020790168,0.001997771,0.00011363404,0.000084613974,0.00070086267,0.00022408982,0.72167414,0.08409967,0.08875113,0.10153259,0.00016862743],"about_ca_topic_score_codex":0.0050449185,"about_ca_topic_score_gemma":0.0054774224,"teacher_disagreement_score":0.014618487,"about_ca_system_score_codex":0.001592484,"about_ca_system_score_gemma":0.0023654138,"threshold_uncertainty_score":0.048903704},"labels":[],"label_agreement":null},{"id":"W3103538977","doi":"10.1142/s1793830922500975","title":"An instance-based algorithm for deciding the bias of a coin","year":2022,"lang":"en","type":"article","venue":"Discrete Mathematics Algorithms and Applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Combinatorics; Discrete mathematics; Algorithm","score_opus":0.03360502915633542,"score_gpt":0.2895113734225701,"score_spread":0.2559063442662347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103538977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030750133,0.0006749946,0.95329005,0.0017079115,0.00029997012,0.00051770016,0.0007535288,0.0059455745,0.0060601756],"genre_scores_gemma":[0.23224816,0.00033000798,0.7601659,0.0010791289,0.0002830621,0.0005437773,0.0016544817,0.00048192337,0.0032135088],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99493355,0.0015033107,0.00048081495,0.0011697254,0.0013372985,0.0005753542],"domain_scores_gemma":[0.98703337,0.008563675,0.00065114006,0.0022278007,0.0011588094,0.00036524047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00439026,0.0013423535,0.0022852449,0.001426677,0.0011494894,0.0034018203,0.0037853513,0.003309573,0.007713072],"category_scores_gemma":[0.023452487,0.00082124694,0.0018508373,0.0019416921,0.0016012912,0.0053054364,0.0028893077,0.004056316,0.0022596181],"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":[0.0027743888,0.00070858764,0.005436379,0.00072756194,0.00044785376,0.00032830457,0.00030108684,0.09165172,0.017657436,0.09835144,0.031438395,0.7501768],"study_design_scores_gemma":[0.0006014288,0.00030977375,0.0010301826,0.00012946293,0.00022116172,0.0004735476,0.00010610828,0.8136661,0.017995983,0.15562855,0.009742942,0.00009466708],"about_ca_topic_score_codex":0.002107717,"about_ca_topic_score_gemma":0.0030771054,"teacher_disagreement_score":0.007713072,"about_ca_system_score_codex":0.0020529209,"about_ca_system_score_gemma":0.005221423,"threshold_uncertainty_score":0.02580285},"labels":[],"label_agreement":null},{"id":"W3105894878","doi":"","title":"Métodos de Otimização Combinatória Aplicados ao Problema de Compressão MultiFrases","year":2016,"lang":"pt","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Algorithms and Data Compression","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":"Polytechnique Montréal","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.014901102654040564,"score_gpt":0.23546506922847926,"score_spread":0.2205639665744387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105894878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14133011,0.0017306904,0.8072038,0.00131318,0.00028119015,0.00037670662,0.0009511197,0.0009257041,0.045887515],"genre_scores_gemma":[0.5906321,0.0016556692,0.3952647,0.00025177439,0.0002989778,0.00040890212,0.0007127137,0.00041160916,0.01036372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998575,0.00036893028,0.00011355266,0.00024729792,0.00050705724,0.00018808429],"domain_scores_gemma":[0.9942761,0.0036856234,0.00034581101,0.0007522917,0.0007383809,0.00020167498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016723626,0.00096131593,0.0010818354,0.002204601,0.0014586506,0.003069672,0.0012601491,0.0011254336,0.011386314],"category_scores_gemma":[0.01216166,0.00033356264,0.0009859871,0.0030352122,0.001014993,0.0022140846,0.001548374,0.0014985029,0.001030813],"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":[0.0014429046,0.00047040824,0.005371752,0.0022462115,0.00013139818,0.00046535616,0.00067363726,0.2446428,0.025124997,0.28872344,0.009311377,0.42139575],"study_design_scores_gemma":[0.00015509698,0.0002762314,0.0010308021,0.0001945632,0.00009025863,0.0006722299,0.00045878705,0.70467144,0.020200139,0.25489295,0.017308986,0.000048451817],"about_ca_topic_score_codex":0.002110449,"about_ca_topic_score_gemma":0.004406752,"teacher_disagreement_score":0.011386314,"about_ca_system_score_codex":0.0015016898,"about_ca_system_score_gemma":0.0016865236,"threshold_uncertainty_score":0.038091004},"labels":[],"label_agreement":null},{"id":"W3109410541","doi":"10.1145/3427761.3432348","title":"Prusti: deductive verification for Rust (keynote)","year":2020,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Rust (programming language); Computer science; Programming language","score_opus":0.04560935920623609,"score_gpt":0.2529029730463624,"score_spread":0.2072936138401263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109410541","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017198654,0.0007557214,0.9185612,0.0033791007,0.0009463622,0.00014595842,0.00089052453,0.03888332,0.03471782],"genre_scores_gemma":[0.121592835,0.0013531593,0.81718886,0.0039774086,0.0010129912,0.0005357566,0.0033643874,0.012617806,0.038356792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99571383,0.0013387456,0.00027142867,0.0006850028,0.0016761521,0.00031484294],"domain_scores_gemma":[0.99185973,0.004233278,0.00029730384,0.0019789282,0.0014560466,0.00017482125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067552933,0.001104475,0.00088593824,0.0019299523,0.0015326025,0.0034052364,0.0028397066,0.0016357866,0.05678015],"category_scores_gemma":[0.022273181,0.0014154615,0.0026209198,0.0012336299,0.0030756374,0.0089602,0.005688083,0.005338681,0.020073397],"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":[0.00026353585,0.000114670394,0.00084781996,0.0007435033,0.00009041429,0.00036702314,0.0005708918,0.005952855,0.0043548965,0.65565187,0.16084588,0.17019667],"study_design_scores_gemma":[0.00012637257,0.00008742985,0.00043684963,0.0003347488,0.00007905261,0.00046521742,0.00012221345,0.04671995,0.013333282,0.71031326,0.22788967,0.000091942915],"about_ca_topic_score_codex":0.0023793958,"about_ca_topic_score_gemma":0.0023262645,"teacher_disagreement_score":0.05678015,"about_ca_system_score_codex":0.0019914934,"about_ca_system_score_gemma":0.0018585684,"threshold_uncertainty_score":0.1899485},"labels":[],"label_agreement":null},{"id":"W3111910297","doi":"10.1007/978-3-642-22300-6","title":"Algorithms and Data Structures","year":2011,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Data structure; Theoretical computer science; Programming language","score_opus":0.03499058993141908,"score_gpt":0.27945401055225794,"score_spread":0.24446342062083887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111910297","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027339873,0.04905748,0.70054585,0.003162094,0.0037097943,0.00019925558,0.0013757168,0.004167777,0.2350481],"genre_scores_gemma":[0.050974187,0.05626008,0.49077883,0.002175392,0.0048652985,0.0007862029,0.005219263,0.0036279568,0.38531277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849296,0.00020097528,0.00012450856,0.00026630054,0.0008439327,0.00007137049],"domain_scores_gemma":[0.9987822,0.000418962,0.00004360776,0.0004983677,0.00021373267,0.000043201155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007774686,0.0019214108,0.0019924187,0.0028706533,0.0012018707,0.004741697,0.0018729726,0.0011829366,0.038805235],"category_scores_gemma":[0.0028284988,0.0010803615,0.0011578156,0.008136033,0.0024312378,0.006900465,0.0023586047,0.004061644,0.031738285],"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":[0.000028894814,0.000038792547,0.00010950507,0.0006342804,0.000038534516,0.000046136407,0.0001951774,0.002596733,0.0016024224,0.3866347,0.120233946,0.4878408],"study_design_scores_gemma":[0.000017018943,0.000031584594,0.00020473365,0.00019900064,0.000030411418,0.0003506723,0.000054020573,0.0071940487,0.0019761724,0.52365136,0.46626756,0.000023380459],"about_ca_topic_score_codex":0.0006177409,"about_ca_topic_score_gemma":0.0007094368,"teacher_disagreement_score":0.038805235,"about_ca_system_score_codex":0.0014154919,"about_ca_system_score_gemma":0.0013615289,"threshold_uncertainty_score":0.12981647},"labels":[],"label_agreement":null},{"id":"W3117285148","doi":"","title":"Simple KMP Pattern-Matching on Indeterminate Strings.","year":2020,"lang":"en","type":"article","venue":"Prague Stringology Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Simple (philosophy); Indeterminate; Computer science; Matching (statistics); Algorithm; Mathematics; Statistics; Philosophy","score_opus":0.0373691897122394,"score_gpt":0.2672908017011263,"score_spread":0.2299216119888869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117285148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08625396,0.0012328713,0.8790105,0.00051286764,0.00042001717,0.00017635126,0.0010751177,0.0033134741,0.028004952],"genre_scores_gemma":[0.6484825,0.0005520212,0.32975703,0.00038141277,0.00017116222,0.00016046726,0.0017830681,0.0005064023,0.01820595],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839056,0.00031052393,0.00020530193,0.00032095565,0.0005963791,0.00017631217],"domain_scores_gemma":[0.99729675,0.0007581376,0.00016250335,0.001317893,0.00038293083,0.00008171836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007409387,0.0004493497,0.0007281333,0.0011327628,0.00061503967,0.0016193512,0.0013777766,0.001083931,0.0074063293],"category_scores_gemma":[0.0074159126,0.000291504,0.000417302,0.0024691608,0.00087347673,0.0044116923,0.00239502,0.00082862494,0.0035910732],"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":[0.0010023556,0.00018780972,0.0018381262,0.00069814886,0.000079578866,0.00075928937,0.0003426961,0.016600316,0.03516626,0.32251638,0.017260423,0.6035486],"study_design_scores_gemma":[0.00008157391,0.00021705835,0.0012045493,0.00013355193,0.000055881086,0.0017196843,0.00016939024,0.19379853,0.061881,0.7024739,0.038200423,0.0000644325],"about_ca_topic_score_codex":0.0004172507,"about_ca_topic_score_gemma":0.00055035896,"teacher_disagreement_score":0.0074063293,"about_ca_system_score_codex":0.0004427126,"about_ca_system_score_gemma":0.00052257633,"threshold_uncertainty_score":0.024776638},"labels":[],"label_agreement":null},{"id":"W3119704926","doi":"10.1145/1508284.1508283","title":"Architectural support for SWAR text processing with parallel bit streams","year":2009,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Algorithms and Data Compression","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; SIMD; Operand; Parallel computing; Instruction set; Set (abstract data type); Addressing mode; Parsing; Regular expression; Computer architecture; Programming language; Instructions per cycle; Computer hardware","score_opus":0.018162188717529976,"score_gpt":0.2646916969588718,"score_spread":0.24652950824134182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119704926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1214676,0.00044576646,0.83629906,0.00048399073,0.00015509527,0.00015820962,0.0002685739,0.013000584,0.027721103],"genre_scores_gemma":[0.562387,0.0007091032,0.41869047,0.0005198028,0.00015613681,0.00026739322,0.0013093593,0.0009163154,0.015044341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969876,0.00004766073,0.00005108396,0.00004161692,0.00012504804,0.000035830824],"domain_scores_gemma":[0.9990858,0.0002285046,0.000092312934,0.00031259158,0.00024348093,0.000037326336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003017235,0.00041236135,0.00031798924,0.00065943395,0.0004195863,0.0010391972,0.0014926048,0.0003381032,0.005286507],"category_scores_gemma":[0.001476878,0.00036460362,0.00040737813,0.0007927578,0.00038736974,0.0017726894,0.0008053262,0.000954488,0.002024098],"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":[0.00078877364,0.00031556573,0.003900485,0.00062110525,0.00008317242,0.0007639004,0.0004577494,0.049926087,0.3473815,0.14770198,0.013906593,0.4341532],"study_design_scores_gemma":[0.00016306025,0.00071533106,0.001505755,0.00008990506,0.00012009637,0.0010273469,0.00014383333,0.5108031,0.3453837,0.061694354,0.07827205,0.00008143668],"about_ca_topic_score_codex":0.0004260358,"about_ca_topic_score_gemma":0.0014151018,"teacher_disagreement_score":0.005286507,"about_ca_system_score_codex":0.00035551842,"about_ca_system_score_gemma":0.00072000764,"threshold_uncertainty_score":0.017685175},"labels":[],"label_agreement":null},{"id":"W3120098135","doi":"10.1137/1.9781611976472.5","title":"PFP Compressed Suffix Trees","year":2021,"lang":"en","type":"article","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Agencia Nacional de Investigación y Desarrollo; Israel Institute for Biological Research; Research Center for Informatics, Czech Technical University in Prague; National Institutes of Health; National Science Foundation","keywords":"Compressed suffix array; Generalized suffix tree; Suffix tree; Computer science; String (physics); Parsing; Suffix array; Suffix; Concatenation (mathematics); Prefix; Computation; Data structure; Tree (set theory); Theoretical computer science; Algorithm; Combinatorics; Mathematics; Artificial intelligence; Programming language","score_opus":0.05496279510950445,"score_gpt":0.2515273967201858,"score_spread":0.19656460161068137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120098135","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03294778,0.0015295176,0.88826644,0.0012676949,0.0006962457,0.00049886864,0.019499652,0.035825957,0.019467793],"genre_scores_gemma":[0.13324393,0.0008581851,0.8126518,0.0005941431,0.0003061223,0.0007144719,0.04020484,0.0022291495,0.009197368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982526,0.00025945096,0.00021332942,0.0004020884,0.0006927078,0.00017979907],"domain_scores_gemma":[0.99584466,0.0013511954,0.00021827151,0.0014724191,0.0010018586,0.0001116422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008504616,0.00092260947,0.00097104214,0.0019391036,0.0011513974,0.0022899755,0.0023580468,0.0014342251,0.012355206],"category_scores_gemma":[0.011249922,0.0006013242,0.0009961834,0.005792564,0.00070895086,0.0046888315,0.002257771,0.0015808594,0.0077547044],"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":[0.0008713241,0.00019436907,0.0016186174,0.00077002944,0.00008726513,0.00083977054,0.00057469914,0.036881924,0.02383249,0.07363351,0.10475065,0.7559454],"study_design_scores_gemma":[0.00029232766,0.00031657508,0.0012506586,0.00024382137,0.00008867808,0.002079488,0.00047314665,0.46240655,0.056942005,0.25191578,0.2238699,0.00012114778],"about_ca_topic_score_codex":0.0022339607,"about_ca_topic_score_gemma":0.0026375167,"teacher_disagreement_score":0.012355206,"about_ca_system_score_codex":0.00086822914,"about_ca_system_score_gemma":0.0022608582,"threshold_uncertainty_score":0.041332304},"labels":[],"label_agreement":null},{"id":"W3124442824","doi":"","title":"SIMD Compression and the Intersection of Sorted Integers","year":2016,"lang":"en","type":"article","venue":"R-libre (Université Téluq)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"SIMD; Computer science; Parallel computing; Integer (computer science); Intersection (aeronautics); Compression (physics); Decoding methods; Data compression; State (computer science); Speedup; Compression ratio; Algorithm; Programming language","score_opus":0.003248471905147706,"score_gpt":0.1557511980705495,"score_spread":0.15250272616540178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124442824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25661108,0.0031062113,0.69450915,0.00083810097,0.00028332818,0.00025503826,0.0016449911,0.017385095,0.025366977],"genre_scores_gemma":[0.5752291,0.00094057084,0.4109557,0.00040027784,0.00016123083,0.0002773474,0.0027925475,0.0009393791,0.008303851],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807113,0.00026836814,0.00017625159,0.00027861836,0.0010320039,0.00017370928],"domain_scores_gemma":[0.99770385,0.0008325937,0.00018113815,0.0007986674,0.00043841643,0.000045388908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000863851,0.0006792218,0.0007037679,0.0019247613,0.00064771087,0.0014758026,0.0013712301,0.00045495972,0.0040705474],"category_scores_gemma":[0.0045090327,0.00033942505,0.0004563183,0.0045307516,0.0012192085,0.0030021872,0.0018442641,0.00064054894,0.0015040904],"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":[0.0017827216,0.00021373246,0.004550603,0.00031777538,0.00008296674,0.0004074863,0.00060561945,0.042815693,0.07660984,0.07882006,0.01970565,0.77408785],"study_design_scores_gemma":[0.00023343637,0.0006652616,0.0026086278,0.00010710872,0.000079589,0.0010126755,0.0005090488,0.49307883,0.36662552,0.0789128,0.056055956,0.000111173074],"about_ca_topic_score_codex":0.0024010818,"about_ca_topic_score_gemma":0.0026159326,"teacher_disagreement_score":0.0040705474,"about_ca_system_score_codex":0.0012091191,"about_ca_system_score_gemma":0.001067997,"threshold_uncertainty_score":0.013617337},"labels":[],"label_agreement":null},{"id":"W3125798661","doi":"10.20944/preprints202009.0557.v1","title":"Computing Maximal Lyndon Substrings of a String","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Suffix array; Suffix tree; Generalized suffix tree; String (physics); Algorithm; Time complexity; Suffix; Compressed suffix array; Mathematics; Combinatorics; String searching algorithm; Sorting; Computer science; Discrete mathematics; Data structure; Pattern matching; Artificial intelligence","score_opus":0.1394014060639709,"score_gpt":0.3351850256452111,"score_spread":0.1957836195812402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125798661","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1162954,0.00063133345,0.86880136,0.0002669848,0.0001647469,0.00013139166,0.0009329045,0.0050737024,0.007702167],"genre_scores_gemma":[0.3441857,0.00029481883,0.6436185,0.00024666367,0.00010397975,0.00017922178,0.002981904,0.0008246046,0.007564558],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842995,0.00016758035,0.0002287982,0.000544824,0.00039456552,0.0002343127],"domain_scores_gemma":[0.99722713,0.0012441851,0.00024746137,0.00059396814,0.00055200956,0.00013521308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095887814,0.0008489107,0.0016345971,0.00206314,0.0012681838,0.0027175185,0.0012140219,0.001328295,0.007966629],"category_scores_gemma":[0.008512985,0.0005396843,0.0015419283,0.00206866,0.0014549562,0.00539631,0.002138197,0.0012688483,0.0036420969],"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":[0.002412991,0.00027321605,0.009546382,0.0012926057,0.0002046071,0.0015540237,0.0023283837,0.057240587,0.09840176,0.23481627,0.009932103,0.581997],"study_design_scores_gemma":[0.00013457552,0.0006337585,0.0024917482,0.00032352487,0.00012375151,0.0009888802,0.0010181662,0.3259956,0.09030355,0.5433238,0.034464836,0.00019781555],"about_ca_topic_score_codex":0.001652719,"about_ca_topic_score_gemma":0.0029323366,"teacher_disagreement_score":0.007966629,"about_ca_system_score_codex":0.0010957061,"about_ca_system_score_gemma":0.0015821138,"threshold_uncertainty_score":0.026651084},"labels":[],"label_agreement":null},{"id":"W3126635520","doi":"10.1145/3394885.3431424","title":"Canonical Huffman Decoder on Fine-grain Many-core Processor Arrays","year":2021,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Huffman coding; Computer science; Parallel computing; Throughput; Byte; Efficient energy use; SIMD; Energy consumption; Multi-core processor; Decoding methods; Implementation; Massively parallel; Codec; Computer hardware; Embedded system; Data compression; Operating system; Algorithm; Wireless; Engineering","score_opus":0.02955209584054171,"score_gpt":0.2813810856165878,"score_spread":0.2518289897760461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126635520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.450769,0.0006663972,0.51403815,0.0003155477,0.00013443435,0.00013976266,0.0003300015,0.008149579,0.025457174],"genre_scores_gemma":[0.6822164,0.0002161025,0.3080661,0.00018876158,0.000025483687,0.00008912886,0.0005362514,0.00024906444,0.008412774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997087,0.000058132355,0.000019305488,0.000046332305,0.00012353068,0.0000439089],"domain_scores_gemma":[0.99944,0.00016596481,0.000037311875,0.00009607322,0.00023497199,0.000025682868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033302914,0.0003069525,0.00029496106,0.00041858116,0.00028147802,0.0005961228,0.0008006354,0.00027880128,0.002376034],"category_scores_gemma":[0.0013005239,0.00015194129,0.00016731738,0.0006442125,0.00038300286,0.00080426986,0.00036835426,0.0005103046,0.0006535654],"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":[0.0008990317,0.00022603116,0.005825347,0.0003069145,0.00008386239,0.00066949014,0.000258771,0.40701297,0.16172986,0.05680875,0.015660433,0.35051844],"study_design_scores_gemma":[0.00005527834,0.0002830827,0.00088618253,0.000019414832,0.000015754506,0.00015784096,0.000075943746,0.87909484,0.10554055,0.006399595,0.0074438504,0.00002759336],"about_ca_topic_score_codex":0.0055453503,"about_ca_topic_score_gemma":0.012588143,"teacher_disagreement_score":0.0055453503,"about_ca_system_score_codex":0.0007415328,"about_ca_system_score_gemma":0.001479439,"threshold_uncertainty_score":0.011026144},"labels":[],"label_agreement":null},{"id":"W3129088492","doi":"10.1007/978-3-030-75242-2_10","title":"Fragile Complexity of Adaptive Algorithms","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Fonds De La Recherche Scientifique - FNRS; Natural Sciences and Engineering Research Council of Canada; National Foundation for Science and Technology Development; Danmarks Frie Forskningsfond; National Science Foundation","keywords":"Parameterized complexity; Binary logarithm; Sequence (biology); Element (criminal law); Mathematics; Log-log plot; Sorting; Time complexity; Combinatorics; Computational complexity theory; Rank (graph theory); Algorithm; Worst-case complexity; Algorithmic complexity; Discrete mathematics; Computer science; Theoretical computer science","score_opus":0.043164411612213745,"score_gpt":0.28486172452057607,"score_spread":0.24169731290836233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129088492","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1343933,0.0014760636,0.8289927,0.0041730106,0.00033294977,0.0000867352,0.0003331232,0.00049472693,0.029717388],"genre_scores_gemma":[0.93633884,0.0007812267,0.050683588,0.00044835344,0.00049740996,0.00023110819,0.00029634664,0.00023158255,0.010491612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99656844,0.001108454,0.00014566872,0.00056089344,0.0012382419,0.00037832282],"domain_scores_gemma":[0.9458343,0.04522979,0.0020713394,0.003898858,0.0020413639,0.00092436327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034059694,0.00101428,0.0012022641,0.0019177801,0.0011803529,0.003914952,0.0018471314,0.0023222144,0.008117096],"category_scores_gemma":[0.050690215,0.0007378841,0.0008729666,0.00123178,0.0039126356,0.007345117,0.0037422832,0.0052965465,0.00083708996],"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":[0.00029917437,0.000049606697,0.00089180196,0.000121285564,0.000044165314,0.000089514506,0.00013229046,0.10141727,0.0024338218,0.871134,0.002948336,0.020438796],"study_design_scores_gemma":[0.00003425895,0.000048974838,0.0004418632,0.000021361535,0.000013411904,0.00007925919,0.000026111245,0.36924586,0.0011049057,0.6281015,0.0008581629,0.000024315088],"about_ca_topic_score_codex":0.0008629469,"about_ca_topic_score_gemma":0.000602907,"teacher_disagreement_score":0.008117096,"about_ca_system_score_codex":0.002211644,"about_ca_system_score_gemma":0.0014659342,"threshold_uncertainty_score":0.027154446},"labels":[],"label_agreement":null},{"id":"W3129775080","doi":"10.1101/2021.02.17.431713","title":"Compression for population genetic data through finite-state entropy","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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; Simon Fraser University; Universities Space Research Association","keywords":"Computation; Computer science; Population; Data compression; Entropy (arrow of time); Conditional entropy; Genome-wide association study; Algorithm; Data mining; Principle of maximum entropy; Artificial intelligence; Biology; Genetics","score_opus":0.034736498311073505,"score_gpt":0.2617207467837306,"score_spread":0.22698424847265708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129775080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08431086,0.00031247982,0.9090041,0.0005954578,0.00012327886,0.000056156452,0.00056036166,0.0030464854,0.0019908347],"genre_scores_gemma":[0.63178486,0.00030611252,0.36310673,0.00020103846,0.00010466865,0.00016219178,0.0015864795,0.00026469896,0.0024831926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993717,0.00016021624,0.000058054484,0.000082257655,0.0002805976,0.000047284288],"domain_scores_gemma":[0.99647516,0.0019904892,0.00014793583,0.0009326478,0.00040740788,0.000046358247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009483678,0.00035455532,0.00043159223,0.0010704319,0.00034201832,0.0010568565,0.00080205844,0.0004203091,0.002788718],"category_scores_gemma":[0.0057342853,0.00016045125,0.00030808683,0.0013506126,0.0007898483,0.0016027672,0.0009922349,0.0007392034,0.00064274675],"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":[0.00093973323,0.00018547021,0.0037407519,0.00020516296,0.0000692568,0.00037205277,0.0004142252,0.24021986,0.045860086,0.1343782,0.009675088,0.56394005],"study_design_scores_gemma":[0.00004112577,0.00005294486,0.0005708286,0.00002379889,0.000009259615,0.00012264897,0.000041764168,0.8931955,0.047000367,0.055894602,0.0030309125,0.000016395248],"about_ca_topic_score_codex":0.0010349714,"about_ca_topic_score_gemma":0.00089613243,"teacher_disagreement_score":0.002788718,"about_ca_system_score_codex":0.0005742222,"about_ca_system_score_gemma":0.000622768,"threshold_uncertainty_score":0.0093292},"labels":[],"label_agreement":null},{"id":"W3131672637","doi":"10.1007/s00453-022-01007-w","title":"Algorithms and Complexity on Indexing Founder Graphs","year":2022,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"H2020 European Research Council; Academy of Finland; Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta; European Commission; Helsingin Yliopisto","keywords":"Combinatorics; Cograph; Time complexity; Discrete mathematics; Mathematics; Chordal graph; Pathwidth; Parameterized complexity; Indifference graph; Computer science; Line graph; Graph","score_opus":0.04296810111341419,"score_gpt":0.2634721082878823,"score_spread":0.2205040071744681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131672637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29326126,0.0025674505,0.6374441,0.011658483,0.00039316432,0.001004167,0.008716582,0.019353935,0.025600916],"genre_scores_gemma":[0.42896736,0.0010900745,0.5386304,0.001381839,0.00029183674,0.00062848045,0.014512306,0.0026797256,0.011817918],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99013513,0.0020130856,0.00076300785,0.0031163914,0.002682258,0.0012901565],"domain_scores_gemma":[0.9551994,0.02944701,0.0022905201,0.009827364,0.0020876534,0.0011480799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004565897,0.0016207674,0.00263967,0.0024979098,0.0025989867,0.007370998,0.007359908,0.0035318881,0.013314137],"category_scores_gemma":[0.031476855,0.0014126888,0.0030884307,0.0064451825,0.0029193328,0.017195249,0.0052544903,0.0040693334,0.0030462341],"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":[0.001805902,0.0011763384,0.0087619275,0.0025921867,0.00036640387,0.00071279495,0.0025537028,0.19014803,0.017807232,0.2996193,0.06773815,0.40671808],"study_design_scores_gemma":[0.00031028263,0.00013717385,0.00088273827,0.00011435515,0.00016300162,0.00046599648,0.0005059963,0.431045,0.0069208173,0.549639,0.009751837,0.00006382371],"about_ca_topic_score_codex":0.006304863,"about_ca_topic_score_gemma":0.006926771,"teacher_disagreement_score":0.013314137,"about_ca_system_score_codex":0.005219081,"about_ca_system_score_gemma":0.0046596904,"threshold_uncertainty_score":0.044540167},"labels":[],"label_agreement":null},{"id":"W3133750907","doi":"10.4230/lipics.socg.2017.28","title":"Dynamic Orthogonal Range Searching on the RAM, Revisited","year":2017,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Combinatorics; Binary logarithm; Log-log plot; Range (aeronautics); Data structure; Mathematics; Upper and lower bounds; Computational geometry; Amortized analysis; Constant (computer programming); Word (group theory); Algorithm; Computer science; Geometry; Mathematical analysis","score_opus":0.025036970799697925,"score_gpt":0.29309773481931123,"score_spread":0.2680607640196133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133750907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12570919,0.0057719583,0.8400382,0.0033927502,0.00037422625,0.00015812014,0.0007538279,0.0027476454,0.021054063],"genre_scores_gemma":[0.6342789,0.0032093711,0.35003296,0.0009677081,0.00058572565,0.00028982005,0.00083559164,0.00044372902,0.009356193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738485,0.00066460576,0.00015870998,0.00059952843,0.0008176701,0.0003745718],"domain_scores_gemma":[0.993679,0.0024289219,0.0006369082,0.00268287,0.0003479909,0.00022427754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017735005,0.0009036745,0.0017388676,0.0015290173,0.0008619669,0.0026531543,0.0034864314,0.0012255261,0.005661551],"category_scores_gemma":[0.011202302,0.00067613344,0.00070473866,0.00427645,0.002470225,0.0135203665,0.005782412,0.0021404242,0.0018908171],"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":[0.0012154776,0.00033211202,0.0036596188,0.00061290554,0.0001092129,0.00045704786,0.0009127282,0.11200957,0.017983405,0.48456886,0.02220003,0.35593912],"study_design_scores_gemma":[0.0001180977,0.00051549025,0.0008442489,0.00012231806,0.00006581232,0.0011353237,0.00041404396,0.632917,0.014553306,0.3232883,0.025916098,0.000110032044],"about_ca_topic_score_codex":0.0013703208,"about_ca_topic_score_gemma":0.0012649345,"teacher_disagreement_score":0.005661551,"about_ca_system_score_codex":0.0009579449,"about_ca_system_score_gemma":0.0008059089,"threshold_uncertainty_score":0.018939734},"labels":[],"label_agreement":null},{"id":"W3134377377","doi":"10.1145/3477910","title":"A Simple Algorithm for Optimal Search Trees with Two-way Comparisons","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Hong Kong University of Science and Technology; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science Foundation","keywords":"Simple (philosophy); Correctness; Running time; Algorithm; Time complexity; Mathematics; Optimal binary search tree; Computer science; Search algorithm; SIMPLE algorithm; Search tree; Theoretical computer science; Interval tree","score_opus":0.035216390213666564,"score_gpt":0.3036884071578162,"score_spread":0.2684720169441496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134377377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033457768,0.00026913045,0.98979735,0.0001799752,0.00010912385,0.00019215315,0.0002254127,0.0031942332,0.0026869182],"genre_scores_gemma":[0.043835584,0.00012285843,0.9526762,0.00010775381,0.000052676325,0.00027486053,0.0005741285,0.00036254147,0.0019935523],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981908,0.0002699766,0.00016535333,0.0004177971,0.00071924645,0.0002367938],"domain_scores_gemma":[0.99840564,0.00056116434,0.000107779306,0.0005091477,0.0003440111,0.00007226057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097597786,0.0013537246,0.0013104298,0.0016375382,0.0010608026,0.001553122,0.0022714487,0.0017138167,0.016256813],"category_scores_gemma":[0.0052479766,0.00076142995,0.0011990223,0.0027104341,0.0010341234,0.004499091,0.0033279227,0.0021210893,0.0056190803],"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":[0.0003688556,0.0002968882,0.0007762483,0.0006168315,0.000105625695,0.00014992508,0.00021568181,0.027408011,0.02139824,0.08621456,0.031699993,0.8307492],"study_design_scores_gemma":[0.0009584457,0.0005238054,0.0011551221,0.00015476512,0.00016189358,0.0015654891,0.000270924,0.46347305,0.03610707,0.39812484,0.097284816,0.00021977907],"about_ca_topic_score_codex":0.0014618183,"about_ca_topic_score_gemma":0.0027992562,"teacher_disagreement_score":0.016256813,"about_ca_system_score_codex":0.00091265416,"about_ca_system_score_gemma":0.0022615562,"threshold_uncertainty_score":0.05438447},"labels":[],"label_agreement":null},{"id":"W3139224746","doi":"10.5383/juspn.15.01.002","title":"Multistage Arabic and Turkish Text Compression via Characters Encoding and 7-Zip","year":2021,"lang":"en","type":"article","venue":"Journal of Ubiquitous Systems and Pervasive Networks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lossless compression; Computer science; Unicode; Decoding methods; Byte; String (physics); Encoding (memory); Substring; Data compression; Speech recognition; Arithmetic; Algorithm; Artificial intelligence; Programming language; Data structure; Mathematics","score_opus":0.010972321794472703,"score_gpt":0.22537197065596018,"score_spread":0.2143996488614875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139224746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15913716,0.0015355591,0.80820656,0.0005035711,0.0006676433,0.00054873765,0.0010774225,0.009232772,0.019090505],"genre_scores_gemma":[0.4041232,0.0010705657,0.5598032,0.00020100204,0.00023135755,0.00029751635,0.0023689836,0.00049335003,0.03141084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996886,0.000025553647,0.000030237894,0.000055424436,0.00016375566,0.00003638194],"domain_scores_gemma":[0.9995284,0.00006298381,0.00004768489,0.00010536683,0.00023893706,0.00001675098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018160172,0.0007446794,0.00037302478,0.0013357722,0.0004943334,0.0006513722,0.00060272566,0.000506347,0.0034822444],"category_scores_gemma":[0.0008234776,0.00017931685,0.00053008774,0.0012732701,0.00028810554,0.000951877,0.00048912666,0.00057685113,0.0024219067],"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":[0.0006971024,0.00014157972,0.0009848864,0.00034960604,0.00004410178,0.0013209292,0.00025775714,0.011210888,0.35430586,0.013691737,0.00908747,0.607908],"study_design_scores_gemma":[0.000059136037,0.000520258,0.0026316345,0.000057435023,0.00007050871,0.0024765374,0.00013132796,0.188481,0.7472404,0.003543241,0.05470742,0.000081001155],"about_ca_topic_score_codex":0.0011347914,"about_ca_topic_score_gemma":0.0015123759,"teacher_disagreement_score":0.0034822444,"about_ca_system_score_codex":0.00037096793,"about_ca_system_score_gemma":0.0004715864,"threshold_uncertainty_score":0.011649311},"labels":[],"label_agreement":null},{"id":"W31398948","doi":"10.3390/s19163472","title":"Efficient Floating-point Based Block LU Decomposition on FPGAs.","year":2004,"lang":"en","type":"article","venue":"ERSA","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":36,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Block (permutation group theory); Parallel computing; Floating point; Computer science; Field-programmable gate array; Decomposition; Algorithm; Embedded system; Mathematics; Chemistry; Combinatorics","score_opus":0.008775050972881119,"score_gpt":0.24622955614445047,"score_spread":0.23745450517156935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W31398948","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028316544,0.0019456872,0.92053086,0.00028298827,0.00024058761,0.00031252482,0.0007788355,0.020370517,0.027221529],"genre_scores_gemma":[0.28790498,0.00077965955,0.6869874,0.00034238034,0.0000859133,0.0004962943,0.0019294937,0.00054259226,0.020931425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962914,0.000088750254,0.000026594242,0.000048426886,0.00014745026,0.000059657617],"domain_scores_gemma":[0.9996878,0.00009527866,0.000038089245,0.00005736793,0.000101608624,0.000019778125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039770114,0.001152845,0.0004382559,0.0006224037,0.0002823125,0.00093225803,0.0008392104,0.0003871595,0.021185286],"category_scores_gemma":[0.0009766235,0.00024456953,0.00027089,0.00071168836,0.00018989097,0.0006393654,0.0005373409,0.0005717921,0.010143699],"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":[0.0010057028,0.00018786867,0.0011859718,0.0006498146,0.00011839241,0.00036740935,0.00019999834,0.030646339,0.0719914,0.012738907,0.04305977,0.8378484],"study_design_scores_gemma":[0.00043406078,0.0009809465,0.0028146768,0.00023045586,0.000087697365,0.00076165656,0.00024334026,0.7887742,0.08733714,0.007355595,0.11090266,0.0000776118],"about_ca_topic_score_codex":0.0029596807,"about_ca_topic_score_gemma":0.0047372007,"teacher_disagreement_score":0.021185286,"about_ca_system_score_codex":0.00042905836,"about_ca_system_score_gemma":0.0005844134,"threshold_uncertainty_score":0.07087183},"labels":[],"label_agreement":null},{"id":"W3142663085","doi":"10.14778/3447689.3447695","title":"On the string matching with <i>k</i> differences in DNA databases","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"University of Winnipeg","funders":"","keywords":"Substring; Suffix tree; String (physics); String searching algorithm; Combinatorics; Pattern matching; Trie; Bounded function; Speedup; Sequence (biology); Tree (set theory); Computer science; Alphabet; Matching (statistics); Time complexity; Mathematics; Algorithm; Data structure; Artificial intelligence; Parallel computing; Biology","score_opus":0.024683335890819752,"score_gpt":0.22047070030775745,"score_spread":0.1957873644169377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142663085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019203395,0.0035676463,0.9724867,0.0006592704,0.00012713743,0.00017279896,0.00014705969,0.0016918165,0.0019441912],"genre_scores_gemma":[0.10399082,0.0029857967,0.8881436,0.00053732784,0.00030317446,0.00028823141,0.0006802765,0.00036910162,0.0027016918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931162,0.0016523938,0.0008150213,0.0017495478,0.0021066905,0.0005601773],"domain_scores_gemma":[0.9932326,0.0036904803,0.0006250975,0.001677863,0.0005588987,0.00021520295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035066113,0.0014408372,0.0022919234,0.003326591,0.0016494007,0.003285393,0.004348255,0.002403203,0.0029717023],"category_scores_gemma":[0.011895614,0.0010549513,0.0020217127,0.008600943,0.002655583,0.01582088,0.0044114515,0.00247032,0.0019205889],"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":[0.0011484831,0.00044606568,0.0036942305,0.0014524038,0.00019175753,0.0005685095,0.00087514584,0.06753888,0.031693194,0.13381058,0.011859404,0.74672145],"study_design_scores_gemma":[0.00023920811,0.00071537244,0.0021011294,0.00022882568,0.0002315095,0.0025312768,0.0004304843,0.6883934,0.04084031,0.2229141,0.04116912,0.00020529413],"about_ca_topic_score_codex":0.0028818564,"about_ca_topic_score_gemma":0.0016671988,"teacher_disagreement_score":0.004348255,"about_ca_system_score_codex":0.0019688602,"about_ca_system_score_gemma":0.0016948639,"threshold_uncertainty_score":0.018544972},"labels":[],"label_agreement":null},{"id":"W3144575570","doi":"10.1109/asonam49781.2020.9381370","title":"Compression for Very Sparse Big Social Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big data; Data compression; Compression (physics); Artificial intelligence; Data mining; Materials science","score_opus":0.20211951620590865,"score_gpt":0.3173468419974297,"score_spread":0.11522732579152103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144575570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13648227,0.0036144643,0.8472122,0.0025246881,0.00055515126,0.00030628775,0.0028994924,0.002704242,0.0037011919],"genre_scores_gemma":[0.57651067,0.0027394805,0.4081029,0.00070012745,0.00049989874,0.00057618984,0.006792388,0.00019816145,0.0038801623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989347,0.00020117025,0.000099545854,0.000110290566,0.0005676121,0.00008668008],"domain_scores_gemma":[0.9946966,0.0026968205,0.0003463894,0.0013840627,0.000768297,0.00010784638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010944975,0.0006962356,0.0007962002,0.0025323203,0.0006498614,0.00115643,0.0011391438,0.0009061059,0.0020756233],"category_scores_gemma":[0.011094561,0.00026104943,0.00058000244,0.0044489563,0.00074125297,0.0025972272,0.0017559797,0.001095237,0.0009471555],"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":[0.0012466491,0.00028026116,0.0058006314,0.00053390744,0.00014646124,0.00094658526,0.00077622494,0.1385298,0.020641895,0.02342557,0.02327185,0.7844001],"study_design_scores_gemma":[0.000072527655,0.00016486664,0.0023455548,0.00007317064,0.0000438144,0.00081144087,0.00037453024,0.92405826,0.01720913,0.044955395,0.009856361,0.000034976154],"about_ca_topic_score_codex":0.0021595932,"about_ca_topic_score_gemma":0.0019205523,"teacher_disagreement_score":0.0025323203,"about_ca_system_score_codex":0.0006243426,"about_ca_system_score_gemma":0.00074430904,"threshold_uncertainty_score":0.006943643},"labels":[],"label_agreement":null},{"id":"W3160701863","doi":"10.1093/imaiai/iaab007","title":"Distributed information-theoretic clustering","year":2021,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"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 de Montréal","funders":"Vienna Science and Technology Fund; Arizona State University","keywords":"Information bottleneck method; Mutual information; Constraint (computer-aided design); Cluster analysis; Encoder; Bottleneck; Computer science; Binary number; Combinatorics; Information theory; Characterization (materials science); Cardinality (data modeling); Independence (probability theory); Mathematics; Discrete mathematics; Algorithm; Data mining; Artificial intelligence; Statistics; Physics","score_opus":0.008085186106822037,"score_gpt":0.232273134839672,"score_spread":0.22418794873284995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160701863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033370066,0.0003945618,0.9608418,0.0008454148,0.000035361278,0.00008435166,0.0003892765,0.00019765002,0.0038414993],"genre_scores_gemma":[0.8559885,0.0005591553,0.13539515,0.0003499392,0.00019321698,0.0003365454,0.0011365592,0.0001312471,0.00590961],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954325,0.0021259526,0.00016839664,0.0010168124,0.0008865543,0.00036987566],"domain_scores_gemma":[0.98030967,0.0140300905,0.0012718497,0.0025964917,0.0013217516,0.00047026254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004597408,0.0009865058,0.002503986,0.0017961176,0.00092763593,0.002123721,0.003690494,0.0022287627,0.002643118],"category_scores_gemma":[0.022727543,0.00092843396,0.0009227079,0.0023707647,0.002724928,0.0038898718,0.0032797875,0.0020653827,0.0007767303],"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":[0.00016830774,0.000063295265,0.0006407036,0.0001274667,0.00008394078,0.00011977815,0.0001530225,0.75900465,0.0011823626,0.22108288,0.0022792697,0.015094342],"study_design_scores_gemma":[0.000016297943,0.00001393734,0.00011305272,0.000009526991,0.0000070765714,0.000023804185,0.000018732415,0.9025324,0.0004104626,0.09639133,0.00045043585,0.00001292536],"about_ca_topic_score_codex":0.0018288429,"about_ca_topic_score_gemma":0.0014720388,"teacher_disagreement_score":0.004597408,"about_ca_system_score_codex":0.0033042075,"about_ca_system_score_gemma":0.0015126235,"threshold_uncertainty_score":0.024313748},"labels":[],"label_agreement":null},{"id":"W3161267034","doi":"10.1109/dcc50243.2021.00027","title":"PHONI: Streamed Matching Statistics with Multi-Genome References","year":2021,"lang":"en","type":"article","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Israel Institute for Biological Research; Japan Society for the Promotion of Science; Agencia Nacional de Investigación y Desarrollo; IFP Energies Nouvelles; National Institutes of Health; National Science Foundation","keywords":"Computer science; Pointer (user interface); Pattern matching; Matching (statistics); Code (set theory); Source code; Data mining; Theoretical computer science; Artificial intelligence; Statistics; Programming language; Mathematics","score_opus":0.06942308776856505,"score_gpt":0.289860813260637,"score_spread":0.22043772549207197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161267034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01749999,0.0007934143,0.7361737,0.0005235785,0.00049025705,0.00035133035,0.008000399,0.22979052,0.0063768504],"genre_scores_gemma":[0.097094454,0.00032272105,0.8731238,0.0002627506,0.00016359177,0.00059101183,0.01637178,0.0062628747,0.005807016],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986444,0.000108094886,0.00014385303,0.00034380014,0.0006305946,0.00012931184],"domain_scores_gemma":[0.9972742,0.0007232833,0.00020178521,0.0012130084,0.00046146082,0.0001262063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013691228,0.0014819065,0.001029137,0.0036451675,0.00082797185,0.0027424332,0.0042866855,0.0012490127,0.01413512],"category_scores_gemma":[0.01041414,0.001006588,0.0011124595,0.0054944362,0.0007778784,0.0033818346,0.0038589933,0.0014858985,0.008097962],"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":[0.0011943658,0.00019356182,0.0042290892,0.0003735637,0.00017760825,0.00040495003,0.00037841348,0.027556278,0.017445374,0.02573394,0.12484114,0.79747164],"study_design_scores_gemma":[0.00044347602,0.0002564181,0.0022937357,0.000099816236,0.00008584084,0.000780536,0.00021296869,0.7639308,0.08558862,0.051043633,0.09512198,0.00014228017],"about_ca_topic_score_codex":0.004977029,"about_ca_topic_score_gemma":0.0055212188,"teacher_disagreement_score":0.01413512,"about_ca_system_score_codex":0.0015194193,"about_ca_system_score_gemma":0.002150422,"threshold_uncertainty_score":0.04728669},"labels":[],"label_agreement":null},{"id":"W3168081705","doi":"10.1109/rdaaps48126.2021.9452004","title":"An Overview of String Processing Applications to Data Analytics","year":2021,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Substring; Computer science; String (physics); Preprocessor; String searching algorithm; Pattern matching; Suffix array; Analytics; Trie; Suffix; Theoretical computer science; Data mining; Prefix; Data structure; Algorithm; Extension (predicate logic); Artificial intelligence; Programming language; Mathematics","score_opus":0.2149976140574002,"score_gpt":0.4038099789852354,"score_spread":0.1888123649278352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168081705","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019486325,0.058673687,0.89571905,0.0025803344,0.0011399572,0.0004133109,0.0022665407,0.007491027,0.029767439],"genre_scores_gemma":[0.014256931,0.109175146,0.85057294,0.0021762953,0.0024460428,0.0007501062,0.005000226,0.0015400304,0.014082214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99374855,0.0015880023,0.0011988386,0.00080756616,0.002455549,0.00020155567],"domain_scores_gemma":[0.9927261,0.0043082954,0.00039764552,0.0009972702,0.0013507002,0.00021995137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037512043,0.0021160084,0.0016601164,0.008874005,0.001377936,0.006319195,0.0028523945,0.0025224425,0.01849014],"category_scores_gemma":[0.011413114,0.0011934465,0.0022456474,0.023184773,0.0016565535,0.00753058,0.0030431964,0.0035331068,0.020352736],"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":[0.00010665814,0.000089409215,0.0012158244,0.0041425386,0.00009422895,0.00047425702,0.00039969117,0.0040909136,0.004422862,0.12965727,0.042126045,0.81318027],"study_design_scores_gemma":[0.00001791032,0.000104200575,0.0012724404,0.0013391281,0.00004950167,0.002026293,0.00019519843,0.020251857,0.0063368236,0.18642862,0.7818702,0.00010786298],"about_ca_topic_score_codex":0.000906583,"about_ca_topic_score_gemma":0.000582632,"teacher_disagreement_score":0.01849014,"about_ca_system_score_codex":0.0011818942,"about_ca_system_score_gemma":0.0017015461,"threshold_uncertainty_score":0.061855674},"labels":[],"label_agreement":null},{"id":"W3168693495","doi":"10.1137/1.9781611976830.17","title":"Multidimensional Included and Excluded Sums","year":2021,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Complement (music); Algorithm; Mathematics; Binary number; Operator (biology); Combinatorics; Discrete mathematics; Computer science; Arithmetic","score_opus":0.06407223245863318,"score_gpt":0.24944681646610353,"score_spread":0.18537458400747037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168693495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020442182,0.0007184902,0.95827675,0.00055366673,0.00032777697,0.00015287971,0.00039861343,0.001515368,0.017614324],"genre_scores_gemma":[0.16499867,0.0004613866,0.814467,0.0004539245,0.00023447754,0.0003547148,0.001293612,0.00078063307,0.016955528],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973379,0.00047695075,0.00019670693,0.0004546771,0.0012937755,0.00023990506],"domain_scores_gemma":[0.99700505,0.0011060414,0.00019520332,0.0008818854,0.0006753974,0.0001364924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014658518,0.0012951202,0.0014052457,0.0014543046,0.0017828787,0.0035558275,0.0030222638,0.0012368708,0.020340277],"category_scores_gemma":[0.008617177,0.0006551707,0.0017762167,0.001949919,0.0014914712,0.0060743974,0.0054877703,0.002421439,0.003884794],"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":[0.00051274896,0.00019035679,0.0013501936,0.0005564272,0.00011187207,0.00023691279,0.00028737413,0.06432862,0.006392761,0.45760965,0.02077973,0.44764337],"study_design_scores_gemma":[0.00014404512,0.00014711803,0.00041736444,0.00016068811,0.00007392806,0.0004434717,0.00019613616,0.4871458,0.018881883,0.43938974,0.052922253,0.00007752021],"about_ca_topic_score_codex":0.0015550642,"about_ca_topic_score_gemma":0.0025193226,"teacher_disagreement_score":0.020340277,"about_ca_system_score_codex":0.0011310547,"about_ca_system_score_gemma":0.0019221781,"threshold_uncertainty_score":0.06804496},"labels":[],"label_agreement":null},{"id":"W3174688402","doi":"10.1007/978-3-030-79987-8_23","title":"Complexity and Algorithms for MUL-Tree Pruning","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pruning; Tree (set theory); Parameterized complexity; Set (abstract data type); Heuristic; Computer science; Algorithm; Search tree; Tree rearrangement; Weight-balanced tree; K-ary tree; Combinatorics; Mathematics; Binary tree; Phylogenetic tree; Artificial intelligence; Tree structure; Binary search tree; Biology; Gene; Search algorithm; Botany","score_opus":0.04652306749869173,"score_gpt":0.28116399451586715,"score_spread":0.23464092701717543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174688402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01676988,0.0051727784,0.9115703,0.0032116538,0.0006030106,0.0002487828,0.001398871,0.0019450482,0.059079748],"genre_scores_gemma":[0.14604957,0.004964078,0.80032057,0.0009993396,0.0015607999,0.00079366483,0.0035063804,0.0017845544,0.04002106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99518824,0.00093347306,0.00034204763,0.00069206115,0.0023546915,0.0004894555],"domain_scores_gemma":[0.9800181,0.014520542,0.00052308134,0.003247863,0.0013880257,0.00030246208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026690022,0.0019457085,0.002659206,0.0031813886,0.0021243042,0.0077925944,0.005746466,0.0031241789,0.022302244],"category_scores_gemma":[0.02190671,0.0015235143,0.0031021587,0.0070114136,0.0031654225,0.017384443,0.004627776,0.008138208,0.005157188],"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":[0.00038737193,0.00020640121,0.0007657667,0.00072470744,0.00008728716,0.00012877933,0.0002868955,0.06493353,0.0027874438,0.6078733,0.043954663,0.27786383],"study_design_scores_gemma":[0.000043340828,0.000029329844,0.00025069815,0.000070692775,0.000052988467,0.00020676575,0.00005492375,0.17817016,0.0015002365,0.809786,0.009806701,0.000028115726],"about_ca_topic_score_codex":0.0025812185,"about_ca_topic_score_gemma":0.0033338447,"teacher_disagreement_score":0.022302244,"about_ca_system_score_codex":0.004291043,"about_ca_system_score_gemma":0.0023835746,"threshold_uncertainty_score":0.074608445},"labels":[],"label_agreement":null},{"id":"W3183156840","doi":"10.4230/lipics.wabi.2021.13","title":"Compressing and indexing aligned readsets","year":2021,"lang":"en","type":"preprint","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Search engine indexing; Information retrieval","score_opus":0.0704651181496647,"score_gpt":0.2999295147844821,"score_spread":0.22946439663481738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183156840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08788308,0.0052422113,0.8130474,0.0011631063,0.0029716261,0.0010779588,0.04488316,0.030868374,0.012862934],"genre_scores_gemma":[0.117786124,0.00301989,0.7718911,0.0004883703,0.0006966468,0.0010021084,0.089624986,0.004580968,0.010909727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704534,0.00029108918,0.0005942202,0.0005757858,0.0012631291,0.00023050384],"domain_scores_gemma":[0.9951746,0.0011776957,0.00037108536,0.0013758634,0.0017454274,0.00015533312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011980868,0.0013371921,0.0014494323,0.0044668,0.0009121604,0.0027143697,0.0020491797,0.0009910597,0.007565704],"category_scores_gemma":[0.011378835,0.0008021127,0.0013846693,0.010952075,0.0006795404,0.004107652,0.0026654317,0.002041449,0.007679445],"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":[0.0014777448,0.00023048569,0.0028433036,0.002314713,0.00020555378,0.0012762212,0.0010896218,0.027992703,0.099547654,0.030045338,0.05916983,0.7738069],"study_design_scores_gemma":[0.0003659336,0.00085657433,0.0063618077,0.00075560133,0.0002786393,0.0028106102,0.002060714,0.2590446,0.28146988,0.1232523,0.3223023,0.00044104384],"about_ca_topic_score_codex":0.0017504401,"about_ca_topic_score_gemma":0.0018804364,"teacher_disagreement_score":0.007565704,"about_ca_system_score_codex":0.0006128568,"about_ca_system_score_gemma":0.0017395854,"threshold_uncertainty_score":0.025309801},"labels":[],"label_agreement":null},{"id":"W3193102863","doi":"10.1007/978-3-030-83508-8_43","title":"A Universal Cycle for Strings with Fixed-Content (Which Are Also Known as Multiset Permutations)","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Multiset; Concatenation (mathematics); Combinatorics; Mathematics; Discrete mathematics; Fixed point; Binary number; Computer science; Arithmetic","score_opus":0.02066918100351257,"score_gpt":0.24744158913076997,"score_spread":0.2267724081272574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193102863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0661751,0.005259978,0.5184874,0.001380971,0.0032274735,0.0004631836,0.0014883527,0.0017500432,0.40176743],"genre_scores_gemma":[0.43454078,0.0050341953,0.29754278,0.001656104,0.0010834786,0.00095317693,0.0018636235,0.0021018428,0.25522408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994522,0.000089506946,0.000038005022,0.00019315089,0.00012307722,0.00010407722],"domain_scores_gemma":[0.99926263,0.00026763437,0.000057292968,0.00021922754,0.00011465563,0.00007848943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045964753,0.00067149475,0.0006787045,0.0021577873,0.0026898305,0.0028631343,0.0009600039,0.0016636549,0.021323668],"category_scores_gemma":[0.0018456558,0.00060532236,0.0014382806,0.0027830878,0.0024948712,0.005905731,0.002347553,0.0026013213,0.0049393303],"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":[0.000019739817,0.000010521759,0.000042821128,0.000070176204,0.0000034245652,0.000052120096,0.00014063786,0.00026040745,0.001310576,0.96565676,0.0026471633,0.02978559],"study_design_scores_gemma":[0.00000602023,0.000025026373,0.00007694357,0.000068501635,0.000009106615,0.00019759887,0.00006639837,0.0012551761,0.0021246637,0.94229937,0.05385319,0.000017997201],"about_ca_topic_score_codex":0.0007661854,"about_ca_topic_score_gemma":0.0008447873,"teacher_disagreement_score":0.021323668,"about_ca_system_score_codex":0.0010558758,"about_ca_system_score_gemma":0.00084968924,"threshold_uncertainty_score":0.07133484},"labels":[],"label_agreement":null},{"id":"W3193902159","doi":"10.1109/isit45174.2021.9517737","title":"Universal Graph Compression: Stochastic Block Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Sublinear function; Adjacency matrix; Entropy (arrow of time); Computer science; Cluster analysis; Graph; Theoretical computer science; Discrete mathematics; Mathematics; Combinatorics; Algorithm; Artificial intelligence","score_opus":0.020185879756363382,"score_gpt":0.22817250358596877,"score_spread":0.2079866238296054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193902159","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02754733,0.0010527153,0.9650343,0.0005434437,0.00007858072,0.00009174584,0.00036347663,0.00094282784,0.0043454464],"genre_scores_gemma":[0.70565635,0.0031709713,0.2744298,0.00060637214,0.0003330594,0.00039582534,0.001790924,0.0004536226,0.013163037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915814,0.00023210788,0.000039438153,0.00015266667,0.00031204172,0.000105617786],"domain_scores_gemma":[0.9971686,0.0014791762,0.00027080963,0.0006828292,0.0002991778,0.00009938446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010096985,0.0007519664,0.00092034345,0.0011090535,0.00041536943,0.000936691,0.0016450116,0.00093030586,0.0034624445],"category_scores_gemma":[0.0068066996,0.00040001408,0.0006014947,0.0018623866,0.00091187574,0.0028454089,0.0014163496,0.0013672378,0.0009535422],"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":[0.0003281537,0.00013556454,0.00095100317,0.00022904186,0.00005780006,0.00024088264,0.00021338474,0.5722259,0.008677008,0.23288384,0.009598533,0.17445883],"study_design_scores_gemma":[0.000009809137,0.0000261583,0.00009359137,0.000011050303,0.000007924433,0.000056207144,0.00001318493,0.96284133,0.0021093364,0.033232555,0.0015906951,0.000008074719],"about_ca_topic_score_codex":0.004384603,"about_ca_topic_score_gemma":0.0040135095,"teacher_disagreement_score":0.004384603,"about_ca_system_score_codex":0.0012472378,"about_ca_system_score_gemma":0.0010389453,"threshold_uncertainty_score":0.011582971},"labels":[],"label_agreement":null},{"id":"W3196499363","doi":"10.4230/lipics.esa.2021.70","title":"Hypersuccinct Trees - New Universal Tree Source Codes for Optimal Compressed Tree Data Structures and Range Minima","year":2021,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Optimal binary search tree; Random binary tree; Ternary search tree; Binary tree; Range tree; Tree (set theory); Data structure; Binary search tree; K-ary tree; Weight-balanced tree; Interval tree; Range (aeronautics); Random access; Computer science; Mathematics; Combinatorics; Discrete mathematics; Binary number; Search tree; Algorithm; Tree structure; Search algorithm; Arithmetic","score_opus":0.036877857656343445,"score_gpt":0.274961936432509,"score_spread":0.23808407877616555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196499363","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051025998,0.00072620186,0.9358101,0.0006299094,0.00013138953,0.00014157622,0.0017363669,0.0042786333,0.005519894],"genre_scores_gemma":[0.42729893,0.0007213174,0.55675775,0.000747551,0.00017017784,0.0007794557,0.005169978,0.001781452,0.0065733846],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99828964,0.00017798877,0.00012714099,0.00025042196,0.0009591657,0.00019565511],"domain_scores_gemma":[0.9961398,0.0011808941,0.00031497763,0.0013118013,0.0009263378,0.0001261556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007946062,0.00058338663,0.00070595136,0.0012925115,0.0007060727,0.0013036552,0.0012853282,0.0008339015,0.0041292887],"category_scores_gemma":[0.009421873,0.00036923995,0.00053236936,0.0022983185,0.0012712894,0.0037648396,0.0029774536,0.0016165214,0.0016888469],"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":[0.00058477215,0.00016903266,0.0030779347,0.0003881503,0.00005041714,0.00032945187,0.00074270676,0.09184779,0.0331742,0.36148036,0.024948427,0.48320678],"study_design_scores_gemma":[0.00008045276,0.00018157923,0.0006056891,0.00014645355,0.000027937795,0.00056619005,0.00019235794,0.65884876,0.04711946,0.26800054,0.024137847,0.00009270791],"about_ca_topic_score_codex":0.0022279613,"about_ca_topic_score_gemma":0.0030141885,"teacher_disagreement_score":0.0041292887,"about_ca_system_score_codex":0.0013311191,"about_ca_system_score_gemma":0.002309515,"threshold_uncertainty_score":0.013813853},"labels":[],"label_agreement":null},{"id":"W3200072832","doi":"","title":"A Note on Lempel-Ziv Parser Tails and Substring Lengths","year":2018,"lang":"en","type":"article","venue":"IEICE Proceedings Series","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Substring; Parsing; String (physics); Symbol (formal); Algorithm; Computer science; Bernoulli's principle; String searching algorithm; Combinatorics; Mathematics; Set (abstract data type); Artificial intelligence; Pattern matching; Physics","score_opus":0.012431326396758953,"score_gpt":0.24506940426851667,"score_spread":0.23263807787175772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200072832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012124899,0.0071799806,0.9630224,0.0028309103,0.00040113681,0.000068818124,0.00057890825,0.0013386795,0.012454248],"genre_scores_gemma":[0.30246958,0.016389739,0.64989185,0.0035453052,0.0047206064,0.0008389072,0.0024870606,0.0042833607,0.015373573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99074966,0.0027386153,0.0007397612,0.0015169934,0.0036279166,0.00062704476],"domain_scores_gemma":[0.9120358,0.07184183,0.0038365247,0.0078451475,0.0036967772,0.0007438577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011682583,0.0018712708,0.0017498079,0.0054764533,0.0017525294,0.004274897,0.0033906503,0.0030714832,0.005333579],"category_scores_gemma":[0.098859854,0.0017906493,0.0015449543,0.008001935,0.0064057996,0.013936761,0.0039168377,0.010354882,0.002627843],"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":[0.0002711353,0.00007149976,0.004137337,0.0002857917,0.00004889345,0.00052000175,0.00064536434,0.052587733,0.0049032513,0.7880908,0.011347267,0.13709083],"study_design_scores_gemma":[0.000022210352,0.00015245377,0.0024881368,0.00027015654,0.00003689582,0.0009212113,0.00010420157,0.16684647,0.013540394,0.7922221,0.023230197,0.0001657367],"about_ca_topic_score_codex":0.0026187769,"about_ca_topic_score_gemma":0.0015573195,"teacher_disagreement_score":0.011682583,"about_ca_system_score_codex":0.0036253072,"about_ca_system_score_gemma":0.0024340127,"threshold_uncertainty_score":0.06178415},"labels":[],"label_agreement":null},{"id":"W3201160209","doi":"10.1002/spe.3036","title":"Transcoding billions of Unicode characters per second with SIMD instructions","year":2021,"lang":"en","type":"preprint","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transcoding; Computer science; SIMD; Unicode; Software; Operating system; Artificial intelligence","score_opus":0.017942660879024883,"score_gpt":0.2716954210409309,"score_spread":0.253752760161906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201160209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09833076,0.001847837,0.842979,0.000860233,0.0018437426,0.00023864851,0.0018057782,0.02907062,0.023023354],"genre_scores_gemma":[0.3538951,0.0010620729,0.61263394,0.00053269335,0.00039948037,0.00031325582,0.0043319105,0.002898053,0.02393346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994099,0.000051969728,0.00006338788,0.000088787,0.00035067913,0.00003534405],"domain_scores_gemma":[0.99798065,0.0005324446,0.00009412211,0.0005542192,0.0007771972,0.000061363586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000463704,0.0009337136,0.00045110783,0.0016962336,0.00039175112,0.0010102345,0.00079871924,0.0005296963,0.012158847],"category_scores_gemma":[0.0046336576,0.0002502087,0.00034479695,0.001756345,0.0005825909,0.0011866145,0.0011526006,0.00076892093,0.0052587166],"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":[0.0007774851,0.0001299958,0.0017587114,0.00043812202,0.00010064599,0.0007074779,0.00054864347,0.020155352,0.124866,0.019795833,0.043090016,0.7876318],"study_design_scores_gemma":[0.00012701016,0.0002838195,0.0020176487,0.00017694494,0.00009029589,0.0017107873,0.00034895516,0.4198053,0.41465262,0.027840912,0.13285382,0.00009194625],"about_ca_topic_score_codex":0.0011394705,"about_ca_topic_score_gemma":0.0010606347,"teacher_disagreement_score":0.012158847,"about_ca_system_score_codex":0.00039949216,"about_ca_system_score_gemma":0.00036389404,"threshold_uncertainty_score":0.0406754},"labels":[],"label_agreement":null},{"id":"W3201573568","doi":"10.1007/978-3-030-85088-3_15","title":"Inside the Binary Reflected Gray Code: Flip-Swap Languages in 2-Gray Code Order","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Swap (finance); Gray code; Prefix; Binary number; Combinatorics; Computer science; Arithmetic; Discrete mathematics; Algorithm; Mathematics","score_opus":0.01933508492961864,"score_gpt":0.28034523455753396,"score_spread":0.2610101496279153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201573568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08840971,0.0017672235,0.7117098,0.0007583125,0.00079963444,0.00018014696,0.00034131517,0.0019020673,0.19413178],"genre_scores_gemma":[0.6045518,0.0020010571,0.28110486,0.0010671313,0.00037339827,0.00029007273,0.00036848045,0.0017359492,0.10850734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996892,0.00006447851,0.000017478313,0.000043320088,0.00011569642,0.00006978421],"domain_scores_gemma":[0.99966097,0.00012503067,0.000023605351,0.00009171172,0.00007426566,0.00002442286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031868333,0.00048777502,0.00039287872,0.0006570647,0.000573495,0.0018446811,0.0005904881,0.00068389496,0.009192061],"category_scores_gemma":[0.001098788,0.00030668837,0.00042078976,0.0011285482,0.0015490996,0.002505815,0.0008306495,0.0013987562,0.0025326707],"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":[0.000072131574,0.000026472331,0.00006321102,0.00007995889,0.0000035968408,0.00008118112,0.0002787352,0.0064344555,0.0071505164,0.92114055,0.004927259,0.059741993],"study_design_scores_gemma":[0.000019485378,0.000069515074,0.000104049606,0.000070346425,0.000007021175,0.00022165496,0.000079827376,0.031687394,0.013117333,0.905894,0.048688326,0.000040997118],"about_ca_topic_score_codex":0.0008234187,"about_ca_topic_score_gemma":0.0011679571,"teacher_disagreement_score":0.009192061,"about_ca_system_score_codex":0.0007276297,"about_ca_system_score_gemma":0.0007132041,"threshold_uncertainty_score":0.030750453},"labels":[],"label_agreement":null},{"id":"W3201936911","doi":"10.1142/s0219720021500268","title":"Compression for population genetic data through finite-state entropy","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data compression; Computation; Population; Entropy (arrow of time); Data mining; Theoretical computer science; Artificial intelligence; Algorithm","score_opus":0.03354631748808762,"score_gpt":0.3029123453269183,"score_spread":0.2693660278388307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201936911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03767535,0.0003923114,0.9551224,0.0005302071,0.00018588899,0.000060678267,0.0006050137,0.0027968509,0.0026312382],"genre_scores_gemma":[0.48431468,0.00074692396,0.50662494,0.00036133802,0.00020746751,0.00026024997,0.0028159223,0.00050903036,0.0041594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994404,0.00011335071,0.0000585886,0.00008147684,0.00026296658,0.00004318384],"domain_scores_gemma":[0.9970559,0.001567329,0.0001515755,0.0007572786,0.0004239138,0.00004396152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076551986,0.00044121192,0.00045299332,0.0010367241,0.00037775747,0.001201786,0.0008002998,0.0004306626,0.004180449],"category_scores_gemma":[0.0065906243,0.00015439665,0.00041452926,0.0016197097,0.0006860328,0.0018496228,0.0011667757,0.00094194984,0.0011695921],"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":[0.00053878967,0.00013469144,0.0036397676,0.00025334492,0.00006623643,0.00057794625,0.00044790015,0.17062452,0.034169976,0.13829254,0.012138605,0.63911575],"study_design_scores_gemma":[0.00004485581,0.000095944044,0.00078694744,0.00006331344,0.000022599872,0.000392933,0.00007782177,0.8273822,0.06540252,0.09632767,0.009368272,0.000034876415],"about_ca_topic_score_codex":0.0009667999,"about_ca_topic_score_gemma":0.0010420801,"teacher_disagreement_score":0.004180449,"about_ca_system_score_codex":0.00052084064,"about_ca_system_score_gemma":0.00073681463,"threshold_uncertainty_score":0.013985038},"labels":[],"label_agreement":null},{"id":"W3206410302","doi":"10.1002/spe.3036","title":"Transcoding Billions of Unicode Characters per Second with SIMD Instructions","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transcoding; Computer science; SIMD; Unicode; Software; Operating system; Artificial intelligence","score_opus":0.045504405716831946,"score_gpt":0.16068102922755104,"score_spread":0.11517662351071908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206410302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07744593,0.0021440755,0.84419066,0.0011167374,0.0027290985,0.00041025196,0.003677389,0.032351766,0.035934057],"genre_scores_gemma":[0.24038458,0.0015894278,0.70931494,0.0007417463,0.00054993783,0.00058136194,0.0077497805,0.0041177995,0.0349704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944586,0.000038690843,0.00006407099,0.00009391985,0.00031688373,0.000040480656],"domain_scores_gemma":[0.9984486,0.00035139621,0.0000663854,0.00045953598,0.0006285223,0.00004542825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004467357,0.0011505481,0.0005910908,0.0018891161,0.00051938876,0.0012904777,0.00091814727,0.0006383367,0.015508387],"category_scores_gemma":[0.0050525023,0.0003265257,0.00043907482,0.0022030168,0.0005864288,0.0014284226,0.0015515236,0.0009252033,0.008850073],"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":[0.0007184663,0.00012218818,0.00156471,0.00049527537,0.0001136221,0.0006699404,0.00069199374,0.010953052,0.110501684,0.02268759,0.06434719,0.78713435],"study_design_scores_gemma":[0.0001732682,0.00036682384,0.0026832926,0.0002783475,0.00013490886,0.002439321,0.0005967514,0.23673199,0.42031768,0.04088785,0.2952362,0.00015357067],"about_ca_topic_score_codex":0.0013781972,"about_ca_topic_score_gemma":0.0014664471,"teacher_disagreement_score":0.015508387,"about_ca_system_score_codex":0.00039035987,"about_ca_system_score_gemma":0.00042853985,"threshold_uncertainty_score":0.051880717},"labels":[],"label_agreement":null},{"id":"W3207612418","doi":"10.18653/v1/2022.acl-short.24","title":"Kronecker Decomposition for GPT Compression","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Kronecker delta; Decomposition; Computer science; Kronecker product; Volume (thermodynamics); Compression (physics); Linguistics; Philosophy; Physics","score_opus":0.02939809692835871,"score_gpt":0.3341453645357702,"score_spread":0.3047472676074115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207612418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014550721,0.0023470742,0.971184,0.0006280144,0.00036326432,0.000069389775,0.0006841997,0.0006964631,0.009476905],"genre_scores_gemma":[0.30252147,0.0047317743,0.66267425,0.00054886215,0.0007555123,0.000347617,0.0038362297,0.000598568,0.023985675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994112,0.00014475125,0.000052808395,0.00007771109,0.00025653845,0.000057044028],"domain_scores_gemma":[0.99902284,0.0002703635,0.00005607954,0.00030507386,0.00029621553,0.000049408347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006979686,0.00062044954,0.00053007156,0.0011141644,0.00035939197,0.0014690938,0.00052547693,0.00069219724,0.006943559],"category_scores_gemma":[0.0032744172,0.00024708066,0.0004675671,0.0015327338,0.0006362288,0.0015794166,0.0011158765,0.0012944253,0.0037733263],"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":[0.0003860528,0.00010854183,0.0007618276,0.00024750028,0.000060603867,0.00043866222,0.00017918578,0.076539606,0.02036297,0.2815207,0.032832157,0.5865622],"study_design_scores_gemma":[0.00004685477,0.00013642809,0.00071052776,0.000112261325,0.00003295435,0.00071542436,0.00010988053,0.7526376,0.013363517,0.20588091,0.026210058,0.00004359489],"about_ca_topic_score_codex":0.0012771575,"about_ca_topic_score_gemma":0.0016365687,"teacher_disagreement_score":0.006943559,"about_ca_system_score_codex":0.00035034824,"about_ca_system_score_gemma":0.0007177524,"threshold_uncertainty_score":0.023228526},"labels":[],"label_agreement":null},{"id":"W3208600296","doi":"10.1109/dcc52660.2022.00015","title":"Computing Matching Statistics on Repetitive Texts","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Matching (statistics); String (physics); String searching algorithm; Attractor; Measure (data warehouse); Pattern matching; Computer science; Sequence (biology); Space (punctuation); Theoretical computer science; Algorithm; Mathematics; Statistics; Data mining; Artificial intelligence","score_opus":0.020701567630761628,"score_gpt":0.2928627847955807,"score_spread":0.27216121716481906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208600296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4802894,0.0007928125,0.50380737,0.0008201854,0.00010600104,0.000117223964,0.0038866643,0.006550864,0.0036294386],"genre_scores_gemma":[0.7353642,0.00042957655,0.24897258,0.00021056471,0.00024524995,0.00020271797,0.010764865,0.00071423285,0.0030960557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997898,0.0002884345,0.0002927477,0.0005275897,0.0008081804,0.00018503325],"domain_scores_gemma":[0.9907432,0.0045910054,0.0012484579,0.0019777347,0.0010802401,0.0003593802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011533365,0.00050911016,0.0013646964,0.0033034112,0.0006555395,0.0022082238,0.0013541481,0.0011436837,0.0031750211],"category_scores_gemma":[0.019117158,0.00036448948,0.0006465991,0.0057820748,0.0010792217,0.0048697665,0.0020377394,0.0009269582,0.0020309254],"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":[0.0024648116,0.00031249318,0.020040125,0.00069808355,0.00018774111,0.00086336624,0.0007483924,0.17681581,0.077972084,0.08171128,0.0133983735,0.6247874],"study_design_scores_gemma":[0.00009418867,0.00033009506,0.0053843004,0.00004262943,0.000054748332,0.0004548978,0.00035163327,0.7886965,0.05627364,0.14245136,0.005808111,0.00005775963],"about_ca_topic_score_codex":0.0011661408,"about_ca_topic_score_gemma":0.0013961105,"teacher_disagreement_score":0.0033034112,"about_ca_system_score_codex":0.00091257767,"about_ca_system_score_gemma":0.0014747487,"threshold_uncertainty_score":0.010621488},"labels":[],"label_agreement":null},{"id":"W3210513213","doi":"10.5281/zenodo.3774509","title":"a-callahan/MechWolf_Pull 0.1.1","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"L'Alliance Boviteq","funders":"","keywords":"Business","score_opus":0.04685238860346433,"score_gpt":0.23587485689257418,"score_spread":0.18902246828910985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210513213","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027370946,0.0007515085,0.1296146,0.0010361669,0.0010509294,0.00049831177,0.0650064,0.63125634,0.16804872],"genre_scores_gemma":[0.023585917,0.0012987219,0.07588372,0.0009439062,0.00046028316,0.0010635577,0.21306531,0.40583807,0.2778607],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984162,0.00013412251,0.00011283409,0.00036294316,0.000716693,0.00025720024],"domain_scores_gemma":[0.996014,0.0005822474,0.00016332995,0.001992932,0.00056288764,0.00068460347],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017037286,0.0027296348,0.001940759,0.0035520552,0.0011810615,0.004639703,0.00670033,0.0034268233,0.61793214],"category_scores_gemma":[0.006150179,0.0021876518,0.0017050616,0.0023015453,0.00094192737,0.0046202745,0.0057162424,0.0031774412,0.74140894],"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":[0.0007995665,0.00018864046,0.00072805205,0.0009967885,0.000063466076,0.00026081214,0.00013704711,0.0012917388,0.020228371,0.017365552,0.7980148,0.15992507],"study_design_scores_gemma":[0.00011162217,0.00008442341,0.0006242687,0.00014509846,0.000024514642,0.00044408723,0.00003670676,0.0032560423,0.016921509,0.009750434,0.96850294,0.00009837018],"about_ca_topic_score_codex":0.0015487389,"about_ca_topic_score_gemma":0.0010077519,"teacher_disagreement_score":0.38206786,"about_ca_system_score_codex":0.0007556587,"about_ca_system_score_gemma":0.0011419768,"threshold_uncertainty_score":0.5449734},"labels":[],"label_agreement":null},{"id":"W3211412965","doi":"10.54216/fpa.060103","title":"Design of Effective Lossless Data Compression Technique for Multiple Genomic DNA Sequences","year":2021,"lang":"en","type":"article","venue":"Fusion Practice and Applications","topic":"Algorithms and Data Compression","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":"École de Technologie Supérieure","funders":"","keywords":"Huffman coding; Arithmetic coding; Lossless compression; Computer science; Data compression; Context-adaptive binary arithmetic coding; Coding (social sciences); Data compression ratio; Compression ratio; Algorithm; Tunstall coding; Image compression; Artificial intelligence; Mathematics; Image processing; Engineering","score_opus":0.04651959199295155,"score_gpt":0.33012893887607814,"score_spread":0.28360934688312656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211412965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022255773,0.00050541153,0.97480357,0.00019856878,0.000057810405,0.00010404781,0.000051416555,0.00040593997,0.0016174234],"genre_scores_gemma":[0.40990466,0.0010254284,0.58434993,0.00022729933,0.00008724541,0.00035284538,0.00024800515,0.000047398647,0.0037572663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971884,0.000028314395,0.000017310784,0.00006625797,0.00014820918,0.000021037918],"domain_scores_gemma":[0.9996253,0.000096598305,0.00006294752,0.000028759181,0.00017047745,0.000015908554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003666327,0.00044678443,0.00040216593,0.00072230404,0.00030189188,0.0005466541,0.0010077913,0.0005399992,0.0011892515],"category_scores_gemma":[0.0009284087,0.00019159328,0.0003036211,0.00065182615,0.00033224552,0.0007852643,0.00030932293,0.00034366644,0.00046862237],"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":[0.00036971163,0.0001546324,0.0013657387,0.00037747968,0.00006888818,0.0004471843,0.00025959848,0.07499477,0.41372666,0.01648031,0.0036533433,0.4881016],"study_design_scores_gemma":[0.00004643972,0.0004083725,0.0006644429,0.00003511149,0.000046662404,0.0007120605,0.00005610864,0.83247447,0.15608385,0.0020793835,0.007362341,0.000030678162],"about_ca_topic_score_codex":0.0009396537,"about_ca_topic_score_gemma":0.0006920703,"teacher_disagreement_score":0.0011892515,"about_ca_system_score_codex":0.00045729414,"about_ca_system_score_gemma":0.0005598411,"threshold_uncertainty_score":0.003978491},"labels":[],"label_agreement":null},{"id":"W329186049","doi":"10.1007/978-1-4614-0992-2_5","title":"Data-Centric and Multimedia Components","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Multimedia; Human–computer interaction","score_opus":0.0816367066051823,"score_gpt":0.251425063484379,"score_spread":0.1697883568791967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W329186049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037513196,0.060503915,0.68403816,0.001332686,0.0028088158,0.00016414587,0.0003761158,0.0022644873,0.24476042],"genre_scores_gemma":[0.057363912,0.066032045,0.35301867,0.0011104454,0.002171981,0.00026511078,0.0011421557,0.001436786,0.5174589],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996885,0.000025545065,0.000015049973,0.00005224529,0.00019958816,0.000019107025],"domain_scores_gemma":[0.99961,0.00012920574,0.0000151116255,0.00010522099,0.0001249224,0.00001560514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027209442,0.0012023281,0.00053986494,0.0016283356,0.00038425822,0.0022685844,0.0012937216,0.00074597925,0.019757112],"category_scores_gemma":[0.0009662303,0.00048277422,0.00032343125,0.0029603748,0.00089002063,0.003158654,0.0008320819,0.001315498,0.008013734],"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":[0.000033309534,0.000028333887,0.00007414228,0.00047241186,0.000016880032,0.00008690981,0.000110520676,0.003863384,0.008490595,0.27511483,0.04408134,0.6676273],"study_design_scores_gemma":[0.000009349625,0.000043603563,0.00026476156,0.00025559554,0.0000377832,0.0008390483,0.00006002555,0.018928347,0.01784091,0.1469873,0.81470585,0.000027429493],"about_ca_topic_score_codex":0.0005984745,"about_ca_topic_score_gemma":0.0008041948,"teacher_disagreement_score":0.019757112,"about_ca_system_score_codex":0.0008444436,"about_ca_system_score_gemma":0.0005574296,"threshold_uncertainty_score":0.06609416},"labels":[],"label_agreement":null},{"id":"W334537367","doi":"10.4310/cdm.2014.v2014.n1.a4","title":"Introduction to the SK model","year":2014,"lang":"en","type":"preprint","venue":"Current Developments in Mathematics","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.041854447188982964,"score_gpt":0.30611692186208533,"score_spread":0.2642624746731024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W334537367","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016598303,0.049884535,0.40728247,0.016807875,0.0051474813,0.00020249115,0.0063155987,0.0015856432,0.49617562],"genre_scores_gemma":[0.46562254,0.07664228,0.13958642,0.010294871,0.010132079,0.0007497778,0.008294525,0.0016863487,0.28699115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996563,0.00007370368,0.000025126594,0.00008586893,0.00010791721,0.000050961655],"domain_scores_gemma":[0.99967146,0.000108510605,0.000028148497,0.000071751565,0.00008240846,0.00003766204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043859275,0.0007910757,0.0007395071,0.0011847866,0.0007595301,0.0017032056,0.0011839534,0.0015170468,0.026454696],"category_scores_gemma":[0.0015848541,0.00034588014,0.000943822,0.00171886,0.0012824703,0.0028855419,0.0017378822,0.0026324876,0.010994328],"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":[0.000020478472,0.000018620414,0.00016115788,0.00015379787,0.000010018737,0.00010284333,0.00011470234,0.0035088158,0.00057660043,0.9493331,0.022806164,0.02319356],"study_design_scores_gemma":[0.00000915973,0.000020267536,0.00015957608,0.000111799476,0.00001131927,0.0002580341,0.000034034892,0.009899563,0.00022884087,0.798656,0.19059093,0.000020510864],"about_ca_topic_score_codex":0.003604211,"about_ca_topic_score_gemma":0.0024295673,"teacher_disagreement_score":0.026454696,"about_ca_system_score_codex":0.001109698,"about_ca_system_score_gemma":0.001086396,"threshold_uncertainty_score":0.088499725},"labels":[],"label_agreement":null},{"id":"W34256809","doi":"10.1186/s13059-021-02408-w","title":"Encoding Quadrilateral Meshes in 2.40 bits per Vertex.","year":2004,"lang":"en","type":"article","venue":"Indian Conference on Computer Vision, Graphics and Image Processing","topic":"Algorithms and Data Compression","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":"University of Windsor; University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Vertex (graph theory); Polygon mesh; Quadrilateral; Encoding (memory); Coding (social sciences); Computer science; Combinatorics; Mathematics; Algorithm; Discrete mathematics; Arithmetic; Artificial intelligence; Physics; Computer graphics (images); Statistics","score_opus":0.017847779439898657,"score_gpt":0.2720468687869445,"score_spread":0.2541990893470458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34256809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033515085,0.0020728752,0.8522221,0.001346782,0.0011560909,0.00033110287,0.013503741,0.030140076,0.06571213],"genre_scores_gemma":[0.37835333,0.0011492347,0.5640706,0.0006602647,0.0001266542,0.0005379632,0.018726936,0.0026306708,0.033744376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996419,0.00006872999,0.00003808074,0.000048865215,0.00013983715,0.000062547144],"domain_scores_gemma":[0.9992674,0.00027306293,0.000039115857,0.0001997771,0.00019150457,0.000029141578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027067057,0.0008027087,0.0005476006,0.0007734292,0.00038573326,0.0012911477,0.0010760203,0.00091610197,0.044110663],"category_scores_gemma":[0.0029868206,0.0003656543,0.0006487559,0.0015357886,0.00035169802,0.0017712808,0.0013596797,0.00078592723,0.009091229],"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":[0.001291266,0.00014650146,0.0012214262,0.0008984073,0.00008570035,0.00041727934,0.0003576198,0.05958882,0.023157049,0.06287753,0.121904366,0.72805405],"study_design_scores_gemma":[0.0003044151,0.000326205,0.00083814765,0.0003494401,0.00007119405,0.00053417904,0.0005420289,0.46980134,0.050838776,0.16328031,0.31301722,0.00009673013],"about_ca_topic_score_codex":0.002574033,"about_ca_topic_score_gemma":0.006209296,"teacher_disagreement_score":0.044110663,"about_ca_system_score_codex":0.0005301155,"about_ca_system_score_gemma":0.00043356267,"threshold_uncertainty_score":0.14756483},"labels":[],"label_agreement":null},{"id":"W344868967","doi":"","title":"Agriculture Canada Central Saskatchewan Vector Soils Data","year":2000,"lang":"en","type":"article","venue":"NASA Technical Reports Server (NASA)","topic":"Algorithms and Data Compression","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":"","keywords":"Soil water; Data set; Soil survey; Polygon (computer graphics); Agriculture; Soil map; Geology; Soil science; Database; Geography; Computer science; Artificial intelligence","score_opus":0.013705955082560433,"score_gpt":0.23002194476449805,"score_spread":0.21631598968193763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W344868967","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016198395,0.00026311612,0.001812989,0.00060176215,0.000115609626,0.00030343572,0.88277906,0.0012922765,0.09663329],"genre_scores_gemma":[0.058541264,0.0011517926,0.009239454,0.00046614645,0.000021189615,0.00059625105,0.7361494,0.0006209965,0.19321354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990103,0.00005745527,0.000056255394,0.00018840817,0.0005069247,0.00018062016],"domain_scores_gemma":[0.99572986,0.00016700702,0.00013058771,0.00029378984,0.003438686,0.00024007168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051254925,0.00082373497,0.0005803674,0.0043584695,0.0017564554,0.0026754541,0.0011048124,0.00034704112,0.1051011],"category_scores_gemma":[0.002301739,0.00059018226,0.00031549737,0.013785825,0.00044446046,0.000922138,0.00080618844,0.00080448674,0.03549882],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028913195,0.0001081469,0.032437135,0.00033597965,0.00007592152,0.0002291348,0.00032179293,0.002802025,0.0014052927,0.0058737304,0.8455931,0.1105286],"study_design_scores_gemma":[0.00007289348,0.0000243511,0.06999201,0.00018092844,0.000034350218,0.000074278236,0.0013601999,0.0027291765,0.0019058955,0.0016472246,0.92188644,0.000092287846],"about_ca_topic_score_codex":0.95503855,"about_ca_topic_score_gemma":0.97770727,"teacher_disagreement_score":0.1051011,"about_ca_system_score_codex":0.014707095,"about_ca_system_score_gemma":0.03817222,"threshold_uncertainty_score":0.35159826},"labels":[],"label_agreement":null},{"id":"W34504510","doi":"10.1007/978-3-319-15612-5_24","title":"Non-repetitive Strings over Alphabet Lists","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Alphabet; Computer science; Generality; Extension (predicate logic); Combinatorics on words; Symbol (formal); Word (group theory); Combinatorics; Algorithm; Discrete mathematics; Theoretical computer science; Mathematics; Linguistics; Programming language","score_opus":0.019235466901796998,"score_gpt":0.26398280817754954,"score_spread":0.24474734127575254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34504510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06122838,0.017397285,0.6878457,0.0014623493,0.0022267278,0.00015293447,0.0012542725,0.004071411,0.22436097],"genre_scores_gemma":[0.41073233,0.017981393,0.27769214,0.0010283379,0.0019275573,0.00030813014,0.003688171,0.001798739,0.2848432],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99949634,0.00006778775,0.000054251457,0.00007532435,0.00025753008,0.000048790916],"domain_scores_gemma":[0.99869907,0.00071097363,0.00009158032,0.00026020224,0.00020136808,0.00003688873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029307287,0.0005093366,0.00055438635,0.0015117329,0.00056073215,0.001277135,0.0010934804,0.00056583335,0.017166827],"category_scores_gemma":[0.002480497,0.0003216214,0.00034087704,0.0035071748,0.00059457286,0.0029227997,0.0010385119,0.0009138209,0.0073110512],"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":[0.00012808735,0.000045912184,0.00027269043,0.0010863518,0.000027571768,0.00045377185,0.00034554082,0.0064164754,0.012851408,0.41999123,0.020976447,0.5374046],"study_design_scores_gemma":[0.00002731452,0.00014409679,0.00056031195,0.00046018366,0.000042225503,0.0020382255,0.00017002343,0.022780959,0.025202528,0.72875696,0.21977037,0.000046729387],"about_ca_topic_score_codex":0.00017295456,"about_ca_topic_score_gemma":0.00025305816,"teacher_disagreement_score":0.017166827,"about_ca_system_score_codex":0.00044530755,"about_ca_system_score_gemma":0.000481672,"threshold_uncertainty_score":0.057428718},"labels":[],"label_agreement":null},{"id":"W402333417","doi":"10.1007/978-3-319-09955-2_11","title":"Efficient Computation of the Outer Hull of a Discrete Path","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Intersection (aeronautics); Convex hull; Path (computing); Hull; Algorithm; Traverse; Plane (geometry); Computation; Data structure; Mathematics; Code (set theory); Time complexity; Space (punctuation); Linear space; Computer science; Regular polygon; Topology (electrical circuits); Geometry; Combinatorics; Engineering","score_opus":0.010684282420554107,"score_gpt":0.23573714037302668,"score_spread":0.22505285795247257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W402333417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13613418,0.00015878398,0.84658957,0.00015042414,0.00008052644,0.000093479954,0.0006902203,0.002239907,0.013862902],"genre_scores_gemma":[0.5156483,0.0001618199,0.47216207,0.000041301846,0.000038650513,0.000073408846,0.0019108831,0.0006987876,0.009264773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996427,0.00003136962,0.000016600121,0.000060949547,0.00018710972,0.00006132784],"domain_scores_gemma":[0.9990533,0.0004939871,0.000058313668,0.00015944464,0.00015081123,0.000084164334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028455188,0.0008352101,0.0010126135,0.0011876713,0.00057212735,0.0018140449,0.0010188314,0.0006536209,0.01048724],"category_scores_gemma":[0.0023467822,0.00042407896,0.0006625392,0.00095504604,0.0008614952,0.0019016323,0.0022044857,0.0013710101,0.0017923359],"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":[0.0011081577,0.00021597273,0.0037577495,0.00082796765,0.000080811005,0.0006033191,0.00096093345,0.25194162,0.045286864,0.18846916,0.014485026,0.49226245],"study_design_scores_gemma":[0.00004558931,0.00012614412,0.0008292168,0.000039476658,0.000019708938,0.00014680036,0.0002619816,0.8913324,0.011616298,0.087649584,0.007907456,0.000025444813],"about_ca_topic_score_codex":0.0020376425,"about_ca_topic_score_gemma":0.0036637487,"teacher_disagreement_score":0.01048724,"about_ca_system_score_codex":0.0007111351,"about_ca_system_score_gemma":0.00070319965,"threshold_uncertainty_score":0.035083294},"labels":[],"label_agreement":null},{"id":"W4200200253","doi":"10.1080/17459737.2021.2002956","title":"Grammar-based compression and its use in symbolic music analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Mathematics and Music","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"String (physics); Computer science; Rule-based machine translation; Set (abstract data type); Theoretical computer science; Context (archaeology); String searching algorithm; Code (set theory); Musical; Natural language processing; Artificial intelligence; Mathematics; Programming language; Pattern matching; Art","score_opus":0.04493639046317889,"score_gpt":0.25745125415817643,"score_spread":0.21251486369499756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200200253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038093902,0.00044711572,0.95896024,0.00026113816,0.000034225985,0.00005368152,0.00015961015,0.00075257756,0.0012375993],"genre_scores_gemma":[0.5539722,0.00071415165,0.44247255,0.0002312216,0.000111574016,0.00019994631,0.0006302697,0.00035248912,0.0013155242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808705,0.0006145127,0.00012423951,0.00032643313,0.00073599047,0.00011178586],"domain_scores_gemma":[0.9924285,0.005478664,0.0005054614,0.0009285658,0.00052928174,0.0001295414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001862563,0.00067353866,0.0008926789,0.0034234864,0.00053529715,0.0010511456,0.0010773261,0.0010413493,0.0011842704],"category_scores_gemma":[0.013205953,0.00036285527,0.0009824801,0.003032332,0.0022601248,0.0017966297,0.0012972567,0.0012565426,0.00022721812],"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":[0.0001331377,0.000090322224,0.0038446898,0.0002129732,0.00010113275,0.00045267033,0.0004329558,0.6029349,0.017916752,0.17239052,0.0011300769,0.20035979],"study_design_scores_gemma":[0.000009583186,0.000041998504,0.0006219969,0.000025068815,0.000015779944,0.00012921814,0.000028900959,0.8937119,0.006055599,0.098089375,0.0012438165,0.000026676762],"about_ca_topic_score_codex":0.0032207677,"about_ca_topic_score_gemma":0.0021888097,"teacher_disagreement_score":0.0034234864,"about_ca_system_score_codex":0.001168674,"about_ca_system_score_gemma":0.0011699297,"threshold_uncertainty_score":0.009850264},"labels":[],"label_agreement":null},{"id":"W4200412035","doi":"10.1186/s40537-021-00547-2","title":"Dynamic order Markov model for categorical sequence clustering","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Markov chain; Markov model; Sequence (biology); Categorical variable; Suffix tree; Data mining; Artificial intelligence; Algorithm; Data structure; Machine learning","score_opus":0.13437511965790933,"score_gpt":0.3358048966184071,"score_spread":0.2014297769604978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200412035","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012558269,0.00043491475,0.9834715,0.00036340757,0.000056595054,0.00008828669,0.00065981917,0.000537543,0.0018296464],"genre_scores_gemma":[0.64599186,0.0014845912,0.3329063,0.0004724401,0.00022216454,0.00088418863,0.004150235,0.00023998288,0.013648258],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985197,0.0003150997,0.00008644565,0.0005578768,0.00035496667,0.00016597193],"domain_scores_gemma":[0.9977367,0.0012656514,0.00029502474,0.000250079,0.00035103015,0.000101554026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014156443,0.00076474954,0.0014654832,0.0016997511,0.0009260456,0.0012666362,0.0033406836,0.0017356293,0.004077865],"category_scores_gemma":[0.004908535,0.0005168018,0.0015038155,0.0025589387,0.0011050001,0.0023327996,0.0012770401,0.0020983068,0.0014004828],"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":[0.0001252697,0.00007909784,0.0039426247,0.00017255248,0.00008611458,0.0002608136,0.0003930384,0.74494857,0.0027386337,0.18090917,0.0037333183,0.06261088],"study_design_scores_gemma":[0.00000511762,0.000011370731,0.00021460827,0.0000058569476,0.000008022006,0.00004007436,0.000013008453,0.9643211,0.00017573845,0.034030024,0.0011630725,0.000012007411],"about_ca_topic_score_codex":0.016214117,"about_ca_topic_score_gemma":0.016365523,"teacher_disagreement_score":0.016214117,"about_ca_system_score_codex":0.0022096206,"about_ca_system_score_gemma":0.0020094707,"threshold_uncertainty_score":0.032239497},"labels":[],"label_agreement":null},{"id":"W4205648267","doi":"10.1145/3487351.3489472","title":"Compressing and mining social network data","year":2021,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Social network (sociolinguistics); Computer science; Data science; Data mining; Social network analysis; Big data; Compression (physics); Social media; World Wide Web","score_opus":0.06670866820619328,"score_gpt":0.29848016694577445,"score_spread":0.23177149873958117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205648267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2704109,0.001205995,0.71873194,0.0017235308,0.00016518563,0.00035881333,0.0028707231,0.0016214853,0.0029114564],"genre_scores_gemma":[0.58881205,0.0014602444,0.40024036,0.00016420169,0.00019837373,0.00037124412,0.006670905,0.000114627095,0.0019679987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875844,0.00032408623,0.00010790195,0.00017624667,0.00053329294,0.000100128935],"domain_scores_gemma":[0.9968225,0.0015922211,0.00033857307,0.0006874086,0.00048779265,0.00007159712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010913309,0.00073835993,0.0006994348,0.0044081435,0.00062982645,0.00094252615,0.0009071248,0.0006929368,0.00090588274],"category_scores_gemma":[0.0092565445,0.00026926547,0.00063266157,0.004197743,0.0006411759,0.002164325,0.0012062219,0.00076917314,0.00048215088],"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":[0.0005176611,0.0002655918,0.016905922,0.00046486294,0.00017431346,0.0008914926,0.0012252098,0.18169017,0.02531179,0.021218272,0.00923031,0.7421044],"study_design_scores_gemma":[0.000027569726,0.00011431651,0.0048081107,0.00004519846,0.000055147313,0.00046869004,0.0006467642,0.928825,0.0161097,0.040398713,0.008474227,0.000026551832],"about_ca_topic_score_codex":0.003035306,"about_ca_topic_score_gemma":0.0026872864,"teacher_disagreement_score":0.0044081435,"about_ca_system_score_codex":0.00055278285,"about_ca_system_score_gemma":0.00071844284,"threshold_uncertainty_score":0.0060352683},"labels":[],"label_agreement":null},{"id":"W4206308010","doi":"10.1137/1.9781611977073.78","title":"Selectable Heaps and Optimal Lazy Search Trees","year":2022,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Heap (data structure); Priority queue; Amortized analysis; Merge (version control); Combinatorics; Queue; Binary logarithm; Binary search tree; Data structure; Mathematics; Time complexity; Computer science; Discrete mathematics; Parallel computing; Algorithm; Binary tree; Programming language","score_opus":0.05916056070832934,"score_gpt":0.24760370635386003,"score_spread":0.1884431456455307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206308010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09226381,0.0014328876,0.8927423,0.00036618309,0.00008779958,0.000115937786,0.00046355833,0.0051505654,0.0073769577],"genre_scores_gemma":[0.357506,0.0006129255,0.6355728,0.00019049105,0.00009458056,0.00026400053,0.0006328977,0.0006488442,0.0044774967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985475,0.00017901693,0.00018690346,0.00026919105,0.0005726693,0.0002446776],"domain_scores_gemma":[0.9977558,0.00082481396,0.00036311065,0.00071771163,0.00024130254,0.00009724218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010171192,0.0003819531,0.0006033145,0.0009903762,0.00082199735,0.0023447948,0.0020185586,0.00058949867,0.0036984417],"category_scores_gemma":[0.0046031466,0.0005175442,0.00059866445,0.0018182149,0.0013877995,0.004892876,0.0018201156,0.001135674,0.0012989239],"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":[0.0011601708,0.00024904587,0.0041622743,0.00071850093,0.00008588634,0.00024548918,0.0006615433,0.072297834,0.045503113,0.3953631,0.008930541,0.47062245],"study_design_scores_gemma":[0.00030486233,0.00062682567,0.001644231,0.00015670223,0.00017008274,0.00054024457,0.0002998335,0.39412656,0.08121819,0.4783996,0.042360436,0.00015242034],"about_ca_topic_score_codex":0.0013673375,"about_ca_topic_score_gemma":0.0024941294,"teacher_disagreement_score":0.0036984417,"about_ca_system_score_codex":0.0011893112,"about_ca_system_score_gemma":0.0015901619,"threshold_uncertainty_score":0.012372494},"labels":[],"label_agreement":null},{"id":"W4206903088","doi":"10.1101/2022.01.20.477098","title":"Image-centric compression of protein structures improves space savings","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lossless compression; Huffman coding; Computer science; Data compression; Image compression; Compression (physics); Compression ratio; Image file formats; Encoding (memory); Computational science; File size; Gas compressor; File format; Image (mathematics); Computer graphics (images); Algorithm; Theoretical computer science; Computer engineering; Computer vision; Image processing; Artificial intelligence; Database","score_opus":0.009245792001998163,"score_gpt":0.2183854240670093,"score_spread":0.20913963206501116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206903088","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5083333,0.0038802102,0.41689995,0.0014327298,0.00041168102,0.00025646598,0.0023235714,0.05031649,0.016145587],"genre_scores_gemma":[0.74805415,0.001148731,0.24000975,0.00043862133,0.00012537203,0.00012961072,0.003709714,0.0016172649,0.00476673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995727,0.000026212836,0.00002504865,0.00007226947,0.00024939518,0.00005434519],"domain_scores_gemma":[0.9990497,0.00025698377,0.00008512008,0.0002336332,0.00032524322,0.00004929709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032379283,0.00071419275,0.0004712676,0.0009197136,0.00025131015,0.0008674692,0.0015270459,0.0006006901,0.0044364054],"category_scores_gemma":[0.0017277441,0.00018247044,0.00027307807,0.0014166327,0.00046042,0.0012705657,0.0007423975,0.0005225173,0.0013484579],"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":[0.0013144859,0.00033562683,0.0040513077,0.00067489676,0.00008458109,0.0006767555,0.000347778,0.044016164,0.3663588,0.0071310843,0.036654327,0.53835416],"study_design_scores_gemma":[0.00009562715,0.00027300077,0.002804222,0.00005078749,0.000041926003,0.0006370837,0.00007876584,0.34373656,0.6336818,0.0017149912,0.01683241,0.000052925483],"about_ca_topic_score_codex":0.0018281396,"about_ca_topic_score_gemma":0.0011998478,"teacher_disagreement_score":0.0044364054,"about_ca_system_score_codex":0.0005823852,"about_ca_system_score_gemma":0.00042176442,"threshold_uncertainty_score":0.0148412585},"labels":[],"label_agreement":null},{"id":"W4206998859","doi":"10.1016/j.ic.2022.104867","title":"Compact representation of graphs with bounded bandwidth or treedepth","year":2022,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Oracle; Bounded function; Combinatorics; Bandwidth (computing); Adjacency list; Constant (computer programming); Binary logarithm; Discrete mathematics; Mathematics; Complement (music); Computer science; Graph; Computer network","score_opus":0.01989807263903853,"score_gpt":0.26926125506010395,"score_spread":0.24936318242106542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206998859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069578335,0.0008789836,0.9173163,0.0005423494,0.00012896075,0.00007782265,0.0018178623,0.0017400854,0.007919314],"genre_scores_gemma":[0.62005824,0.0013492681,0.36597025,0.00025015883,0.00011620382,0.00020089999,0.0034446588,0.0005350149,0.008075311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997713,0.000045454606,0.000015467496,0.00004937732,0.00007976733,0.000038615584],"domain_scores_gemma":[0.99894613,0.0003505381,0.0001176643,0.00035445456,0.000169071,0.00006218979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021072567,0.00053079886,0.0005821824,0.0012952838,0.00030726873,0.001638729,0.00087591365,0.00074508897,0.005774547],"category_scores_gemma":[0.0027734332,0.00026318664,0.00030603938,0.0020675117,0.00043430974,0.0027260105,0.00087674294,0.0009909931,0.0011134725],"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":[0.0006326727,0.00013507878,0.00087868486,0.00054637174,0.000038012455,0.00037829086,0.0005434279,0.16027889,0.028662538,0.42672053,0.017400878,0.36378458],"study_design_scores_gemma":[0.000047786034,0.00009282817,0.00047132146,0.00010612488,0.00003184888,0.00032203633,0.00019137787,0.5315364,0.009151731,0.43908414,0.018936342,0.000028095068],"about_ca_topic_score_codex":0.001166143,"about_ca_topic_score_gemma":0.00179461,"teacher_disagreement_score":0.005774547,"about_ca_system_score_codex":0.00056891004,"about_ca_system_score_gemma":0.00040740546,"threshold_uncertainty_score":0.019317806},"labels":[],"label_agreement":null},{"id":"W4210384668","doi":"10.1002/0471219282.eot397","title":"<scp>H</scp> uffman Coding","year":2003,"lang":"en","type":"other","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Huffman coding; Shannon–Fano coding; Tunstall coding; Computer science; Golomb coding; Coding (social sciences); Canonical Huffman code; Prefix code; Variable-length code; Theoretical computer science; Algorithm; Mathematics; Data compression; Block code; Artificial intelligence; Linear code; Statistics; Decoding methods","score_opus":0.015299634843572104,"score_gpt":0.23840256131610005,"score_spread":0.22310292647252794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210384668","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068080747,0.015202702,0.20395103,0.012484781,0.006236737,0.00027169846,0.0027416088,0.0013270255,0.7509764],"genre_scores_gemma":[0.2805886,0.023938235,0.1459502,0.0064486456,0.006853215,0.0007762847,0.0062451623,0.0008692576,0.5283305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940443,0.00013015285,0.000031133543,0.00008021713,0.0002960507,0.000057991867],"domain_scores_gemma":[0.9989949,0.00025444524,0.0000657502,0.00023789756,0.0004095044,0.000037532605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066755107,0.0005487467,0.00059814606,0.0019770062,0.00088845525,0.0017421145,0.0009115639,0.0012108404,0.04563443],"category_scores_gemma":[0.002693489,0.00018627175,0.0003060951,0.003262572,0.0012772949,0.0011977929,0.0011805979,0.0013733519,0.015332802],"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":[0.00006683005,0.000015538859,0.0002366901,0.00021429428,0.000012149666,0.00026300343,0.000088853216,0.0034652578,0.0015883759,0.44901827,0.24217208,0.3028587],"study_design_scores_gemma":[0.000016537753,0.000023415729,0.0006702887,0.00022205188,0.000013140771,0.0006047736,0.000045095418,0.018734246,0.0040376326,0.28176388,0.6938283,0.000040714676],"about_ca_topic_score_codex":0.006993095,"about_ca_topic_score_gemma":0.0060904687,"teacher_disagreement_score":0.04563443,"about_ca_system_score_codex":0.0020262287,"about_ca_system_score_gemma":0.00094425736,"threshold_uncertainty_score":0.15266234},"labels":[],"label_agreement":null},{"id":"W4212901485","doi":"10.1109/icaml54311.2021.00033","title":"Software and Hardware Integrated Accelerators for Hadoop Appliance","year":2021,"lang":"en","type":"article","venue":"2021 3rd International Conference on Applied Machine Learning (ICAML)","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science; Throughput; Scalability; Computer hardware; Field-programmable gate array; Data compression; Lossless compression; Software; Embedded system; Hardware acceleration; Hardware architecture; Computer architecture; Operating system; Wireless","score_opus":0.03219858722064655,"score_gpt":0.27996815088798743,"score_spread":0.24776956366734088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212901485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12361423,0.0011962081,0.8338091,0.0006281175,0.0006972726,0.00047580645,0.00056524674,0.018308336,0.020705687],"genre_scores_gemma":[0.65506905,0.00039144425,0.32958284,0.00028593902,0.00012076481,0.00027369216,0.0009599627,0.00039571698,0.01292057],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99971265,0.000026962944,0.000018903222,0.000044381686,0.0001579415,0.000039181235],"domain_scores_gemma":[0.9995977,0.000068514135,0.00003364981,0.00007455219,0.00019243782,0.000033212003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033408488,0.0004162984,0.0002426436,0.00048387374,0.00031549134,0.00062829343,0.0011174333,0.0002769592,0.004816909],"category_scores_gemma":[0.00080497214,0.00022224168,0.00030089277,0.00048524557,0.00017636754,0.000788489,0.00040117383,0.00059714494,0.0010802246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017778303,0.0004045092,0.0063017593,0.00071490457,0.00019994735,0.00060354633,0.00030730263,0.046546802,0.2841191,0.02611378,0.042124096,0.5907864],"study_design_scores_gemma":[0.00034687552,0.0013464428,0.00512761,0.000092015296,0.00015377483,0.0008949621,0.00015391552,0.62730086,0.25508317,0.0098947985,0.09947801,0.00012758086],"about_ca_topic_score_codex":0.0013890695,"about_ca_topic_score_gemma":0.001816612,"teacher_disagreement_score":0.004816909,"about_ca_system_score_codex":0.0004931072,"about_ca_system_score_gemma":0.0009050075,"threshold_uncertainty_score":0.016114175},"labels":[],"label_agreement":null},{"id":"W4212950046","doi":"10.1007/978-3-030-83508-8_48","title":"Correction to: Algorithms and Data Structures","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Alberta; University of Waterloo","funders":"","keywords":"Computer science; Volume (thermodynamics); Algorithm; Information retrieval","score_opus":0.026530653083448676,"score_gpt":0.27889382068523627,"score_spread":0.2523631676017876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212950046","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024314219,0.0013397497,0.0063823024,0.051616646,0.9298448,0.000055702505,0.001140184,0.0027193797,0.0066581485],"genre_scores_gemma":[0.023708226,0.006863468,0.029778076,0.07710357,0.38681194,0.00038600122,0.004288741,0.008366022,0.46269384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907231,0.001308743,0.0011866139,0.0013779424,0.0045235553,0.0008799869],"domain_scores_gemma":[0.95160484,0.0057106623,0.0015465193,0.0068271826,0.032741096,0.0015696987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034663542,0.0033967718,0.0041547325,0.0069927974,0.005478851,0.006296149,0.006093344,0.010979355,0.14228122],"category_scores_gemma":[0.06175659,0.0020804717,0.003035456,0.0059273876,0.0037522162,0.0052308585,0.003522692,0.011457536,0.10690283],"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":[0.000034495333,0.000008661237,0.000041986284,0.00011085158,0.000014313561,0.000103124294,0.000018165687,0.00010650278,0.0000990286,0.0022343644,0.9880646,0.009164048],"study_design_scores_gemma":[0.0000322276,0.000025415939,0.00035403823,0.00016130129,0.00003298874,0.00041665303,0.000050157825,0.0011532803,0.00092955097,0.006340665,0.990457,0.00004665296],"about_ca_topic_score_codex":0.012504405,"about_ca_topic_score_gemma":0.016090006,"teacher_disagreement_score":0.14228122,"about_ca_system_score_codex":0.0064745196,"about_ca_system_score_gemma":0.0053186766,"threshold_uncertainty_score":0.47597808},"labels":[],"label_agreement":null},{"id":"W4221005009","doi":"10.29173/cais1295","title":"Signature searching: theory and applications","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Signature (topology); Computer science; Mathematics; Geometry","score_opus":0.014173614004397182,"score_gpt":0.24340057402853077,"score_spread":0.2292269600241336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221005009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011250845,0.01849245,0.85350335,0.0065601105,0.0019026004,0.00022368853,0.0013245584,0.002329808,0.10441271],"genre_scores_gemma":[0.3793259,0.03230201,0.43379194,0.0037527238,0.0068741865,0.00084617944,0.003949675,0.001716441,0.13744083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962405,0.00073204015,0.0002267853,0.0007664088,0.001654806,0.00037942716],"domain_scores_gemma":[0.9909009,0.0048108087,0.0005574744,0.0018851708,0.0015298497,0.00031592097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019754479,0.0013524255,0.0022405356,0.007195518,0.0030358906,0.0075982613,0.0031641526,0.003789666,0.029233925],"category_scores_gemma":[0.017979018,0.0013954823,0.0014765321,0.0147444615,0.0044246735,0.012052819,0.004029593,0.0044839317,0.013946874],"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":[0.000088023604,0.00007966282,0.00055231084,0.00030137465,0.000029286228,0.000080617014,0.00016060167,0.008817674,0.0008078991,0.75146484,0.050781094,0.18683669],"study_design_scores_gemma":[0.000023565468,0.000034364388,0.00019159897,0.00011150416,0.000029380863,0.000442902,0.00006604355,0.05601708,0.0013718136,0.9093123,0.03235641,0.00004294205],"about_ca_topic_score_codex":0.0016621399,"about_ca_topic_score_gemma":0.0010898878,"teacher_disagreement_score":0.029233925,"about_ca_system_score_codex":0.003616008,"about_ca_system_score_gemma":0.003305475,"threshold_uncertainty_score":0.097797275},"labels":[],"label_agreement":null},{"id":"W4225747430","doi":"10.48550/arxiv.2204.00986","title":"Comparability digraphs: An analogue of comparability graphs","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Comparability; Digraph; Lemma (botany); Mathematics; Combinatorics; Correctness; Class (philosophy); Comparability graph; Discrete mathematics; Graph; Computer science; Algorithm; Pathwidth; Artificial intelligence; Line graph; Biology","score_opus":0.10931099194586234,"score_gpt":0.21934406348558866,"score_spread":0.11003307153972632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225747430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08718071,0.0005651039,0.86929655,0.0010072514,0.00021468865,0.0002913085,0.001718916,0.0013133222,0.038412187],"genre_scores_gemma":[0.7038044,0.00088334136,0.2746538,0.0010418772,0.00025701258,0.00042285398,0.002977152,0.00040487503,0.015554758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986002,0.00023736083,0.00009926125,0.00056119927,0.00033735405,0.00016459012],"domain_scores_gemma":[0.99549943,0.0018379962,0.0006483545,0.0011068494,0.00062517764,0.00028221376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007167954,0.00048186188,0.00039005853,0.0016084802,0.0010588847,0.00209985,0.0010545483,0.0007844899,0.008534423],"category_scores_gemma":[0.004793399,0.00038815418,0.00062237045,0.0022259029,0.0019987843,0.0057161422,0.0012285197,0.0018340207,0.0008128657],"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":[0.00011354566,0.00010637899,0.0021138836,0.00022215648,0.000025965875,0.000442597,0.0004844769,0.009006214,0.0062148687,0.89615655,0.0038841802,0.0812291],"study_design_scores_gemma":[0.00002798852,0.000086701795,0.0015609605,0.00005332015,0.00002418327,0.00077708426,0.00026425623,0.029836372,0.0057398467,0.9031293,0.058472965,0.000027032007],"about_ca_topic_score_codex":0.0017088751,"about_ca_topic_score_gemma":0.00193721,"teacher_disagreement_score":0.008534423,"about_ca_system_score_codex":0.001476319,"about_ca_system_score_gemma":0.0008127743,"threshold_uncertainty_score":0.028550506},"labels":[],"label_agreement":null},{"id":"W4226238874","doi":"10.1016/j.tcs.2022.01.010","title":"Efficient and compact representations of some non-canonical prefix-free codes","year":2022,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Prefix code; Code word; Lexicographical order; Prefix; ENCODE; Word (group theory); Constant (computer programming); Mathematics; Code (set theory); Decoding methods; Encoding (memory); Combinatorics; Discrete mathematics; Alphabet; Universal code; Order (exchange); Computer science; Arithmetic; Algorithm; Code rate; Linear code; Systematic code; Block code","score_opus":0.01079473506623293,"score_gpt":0.26916367326847823,"score_spread":0.2583689382022453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226238874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27510437,0.0013694125,0.69271404,0.0013165047,0.00033248714,0.00013613036,0.0011250072,0.00076585636,0.02713613],"genre_scores_gemma":[0.8268398,0.0009829495,0.15752822,0.00028880368,0.00026340838,0.0002556511,0.0013467192,0.00027688858,0.012217707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998833,0.0002899984,0.00007386371,0.00014523565,0.00046454978,0.00019346691],"domain_scores_gemma":[0.99680895,0.0014303356,0.00030263272,0.00068207073,0.00061647117,0.00015949419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007198982,0.0007051925,0.00059000787,0.0010879413,0.00061196496,0.0017341939,0.00076983677,0.00096936076,0.003317043],"category_scores_gemma":[0.006077626,0.00028274485,0.00036731755,0.0015342553,0.0011106747,0.002090949,0.0015168281,0.0016339996,0.0009679413],"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":[0.0003652752,0.000081669365,0.0005785084,0.00014194276,0.00001799396,0.0003563428,0.00034715887,0.03005708,0.011599844,0.86218363,0.0047195978,0.08955092],"study_design_scores_gemma":[0.000067423876,0.00014465362,0.00038048124,0.0000669443,0.000024951118,0.00068696775,0.00018313804,0.2439357,0.012088794,0.73284745,0.0095214,0.000052132644],"about_ca_topic_score_codex":0.0005003063,"about_ca_topic_score_gemma":0.00069863803,"teacher_disagreement_score":0.003317043,"about_ca_system_score_codex":0.0006011153,"about_ca_system_score_gemma":0.0012585128,"threshold_uncertainty_score":0.011096537},"labels":[],"label_agreement":null},{"id":"W4229699668","doi":"10.24124/2008/bpgub560","title":"Entropy of printed Bengali language texts.","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","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":"Library and Archives Canada","funders":"","keywords":"Bengali; Linguistics; Natural language processing; Art; Computer science; Artificial intelligence; Philosophy","score_opus":0.008812604859882393,"score_gpt":0.2624486692435804,"score_spread":0.253636064383698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229699668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8914798,0.0027918927,0.032697268,0.000822728,0.00054612977,0.00008565814,0.020082343,0.0013272162,0.050166946],"genre_scores_gemma":[0.9804529,0.0003625571,0.0035986209,0.000021074653,0.00012605937,0.00003329186,0.007470584,0.00010914409,0.007825727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928266,0.00015611303,0.000074853364,0.00013396358,0.00026100915,0.00009150398],"domain_scores_gemma":[0.9972584,0.0015471822,0.00023816514,0.00036827562,0.0005048114,0.00008317209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046657378,0.00022713453,0.00027074,0.0033214744,0.00033210585,0.0011675685,0.00024083453,0.00016697343,0.006415063],"category_scores_gemma":[0.0072054924,0.0000985941,0.0002316418,0.0030901986,0.00047081657,0.0009077464,0.0005847254,0.00026818734,0.0024715848],"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":[0.0026953428,0.00014989405,0.09530522,0.0017448689,0.0004478532,0.0018067205,0.005033326,0.027387708,0.09365243,0.042925596,0.03258535,0.6962657],"study_design_scores_gemma":[0.000040438914,0.00025280614,0.7049573,0.0001232134,0.0001977916,0.0019756905,0.0022969218,0.13185087,0.089247435,0.023656227,0.04524561,0.00015566454],"about_ca_topic_score_codex":0.0039971503,"about_ca_topic_score_gemma":0.005285652,"teacher_disagreement_score":0.006415063,"about_ca_system_score_codex":0.0009011556,"about_ca_system_score_gemma":0.00035469545,"threshold_uncertainty_score":0.021460533},"labels":[],"label_agreement":null},{"id":"W4230056407","doi":"10.1145/634636.586103","title":"STEP","year":2002,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Computer science; Tracing; Compiler; Programming language; Java; TRACE (psycholinguistics); Reuse; Interface (matter); Software engineering; Encoding (memory); Set (abstract data type); Operating system; Artificial intelligence","score_opus":0.020129771845525606,"score_gpt":0.21088840323944483,"score_spread":0.19075863139391921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230056407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018080806,0.00065350544,0.49240705,0.0010923875,0.0012027269,0.0014418622,0.023720834,0.16915737,0.29224345],"genre_scores_gemma":[0.1073593,0.0008378418,0.39490727,0.0021139346,0.0002536983,0.0014548065,0.06395819,0.020498263,0.40861672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987717,0.00013913887,0.00010952696,0.00034895245,0.00047026324,0.00016037878],"domain_scores_gemma":[0.99782145,0.00024584457,0.00009677784,0.0009910599,0.0007289631,0.000115890456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009480481,0.0010355173,0.0006257596,0.0014644265,0.0010180154,0.0030283977,0.0018894739,0.0011035227,0.13382567],"category_scores_gemma":[0.0036756825,0.0005244451,0.0007624828,0.0012021221,0.00047835105,0.0035791122,0.003563269,0.0013258632,0.120853335],"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":[0.0010753804,0.00024497573,0.0032069143,0.00083275075,0.00007064374,0.00037531456,0.0005311204,0.0017880906,0.022521215,0.06766059,0.28924736,0.61244565],"study_design_scores_gemma":[0.00009848703,0.0001446018,0.0011598462,0.000109384586,0.00003969801,0.00050650164,0.00019900562,0.009088435,0.0408722,0.018546375,0.9291783,0.00005713428],"about_ca_topic_score_codex":0.0013606015,"about_ca_topic_score_gemma":0.0021129942,"teacher_disagreement_score":0.13382567,"about_ca_system_score_codex":0.0006014059,"about_ca_system_score_gemma":0.0018907143,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4231751464","doi":"10.1007/978-3-319-26408-0_6","title":"OpenCL","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alterra Power (Canada)","funders":"","keywords":"Computer science","score_opus":0.020872942910439434,"score_gpt":0.23020995105973155,"score_spread":0.20933700814929213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231751464","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009362431,0.006477802,0.18134876,0.0015349387,0.0019795708,0.00019813605,0.012416082,0.072902456,0.72220606],"genre_scores_gemma":[0.004496579,0.0037709994,0.056692205,0.00066515297,0.0007304179,0.00028156128,0.0209854,0.022127533,0.89025015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988991,0.000076213,0.00006613965,0.00023982732,0.00061819225,0.00010062534],"domain_scores_gemma":[0.99873346,0.00026499317,0.000045049415,0.0004298254,0.00040515547,0.000121538586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005702113,0.0028760047,0.0018094546,0.005294311,0.0013782431,0.005343238,0.0037991663,0.0014488264,0.5015856],"category_scores_gemma":[0.003012054,0.0013018053,0.0012583062,0.007869856,0.0007707716,0.0055539976,0.0032721767,0.002871942,0.5355774],"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":[0.000028836335,0.000034560202,0.00005601164,0.00031718623,0.000009924012,0.000028842087,0.00004744249,0.00046904592,0.00096757564,0.018465362,0.5962239,0.38335136],"study_design_scores_gemma":[0.00001422636,0.0000101560445,0.000121039324,0.00014936957,0.00001067518,0.00016081952,0.000028277338,0.0014259646,0.0016941802,0.034989845,0.96137047,0.000025017163],"about_ca_topic_score_codex":0.002158465,"about_ca_topic_score_gemma":0.0051575354,"teacher_disagreement_score":0.5015856,"about_ca_system_score_codex":0.0014677207,"about_ca_system_score_gemma":0.0017406961,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4231848803","doi":"10.1109/dpds.1990.113706","title":"Voting class-an approach to achieving high availability for replicated data","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Memorial University of Newfoundland","funders":"","keywords":"Voting; Class (philosophy); Replica; Computer science; Scheme (mathematics); Theoretical computer science; Weighted voting; Simple (philosophy); Data mining; Computer security; Artificial intelligence; Mathematics","score_opus":0.12790558698744933,"score_gpt":0.29965962201255114,"score_spread":0.1717540350251018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231848803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008377712,0.00011474723,0.9874423,0.00013688084,0.000055392808,0.00012663878,0.00003929632,0.00042320872,0.003283714],"genre_scores_gemma":[0.436813,0.0002648517,0.5538448,0.00022626719,0.00018922421,0.00041227406,0.0001318851,0.0002602756,0.007857369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974075,0.0006956444,0.00018923944,0.0003936697,0.0010370272,0.00027681224],"domain_scores_gemma":[0.9941451,0.0020621049,0.00041563317,0.0020085026,0.0010919269,0.00027669047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036220418,0.00053713506,0.0009957255,0.0010391135,0.0015553375,0.0029489486,0.0025494013,0.0010585045,0.004783655],"category_scores_gemma":[0.0073690056,0.00034478022,0.0009113185,0.0010143081,0.0016805673,0.004513082,0.0020162247,0.0018423253,0.00072186854],"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":[0.00046472848,0.00021060467,0.0010138007,0.00016179791,0.0000801326,0.00011935511,0.00028293484,0.09700437,0.028656581,0.62422705,0.004577634,0.2432011],"study_design_scores_gemma":[0.000112162976,0.00032084627,0.00034624818,0.000037686445,0.00005741183,0.00027636133,0.00008233274,0.6871711,0.031882968,0.25593245,0.023704523,0.00007592113],"about_ca_topic_score_codex":0.0009820285,"about_ca_topic_score_gemma":0.0014482375,"teacher_disagreement_score":0.004783655,"about_ca_system_score_codex":0.0015846716,"about_ca_system_score_gemma":0.0016536446,"threshold_uncertainty_score":0.019155383},"labels":[],"label_agreement":null},{"id":"W4232286640","doi":"10.1002/dac.943","title":"An efficient compression scheme for data communication which uses a new family of self‐organizing binary search trees","year":2008,"lang":"en","type":"article","venue":"International Journal of Communication Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Instituto de Sistemas Complejos de Ingeniería","keywords":"Computer science; Decoding methods; Huffman coding; Binary tree; Fano plane; Algorithm; Binary number; Coding (social sciences); Encoding (memory); Theoretical computer science; Data compression; Tree (set theory); Adaptive coding; Lossless compression; Tree structure; Artificial intelligence; Mathematics; Arithmetic","score_opus":0.11674254211507488,"score_gpt":0.36150142307126976,"score_spread":0.24475888095619486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232286640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074743286,0.000679881,0.91946566,0.0002380608,0.000101573285,0.00013899583,0.00020781108,0.000967166,0.0034575104],"genre_scores_gemma":[0.48591977,0.00047871447,0.5097822,0.00018527606,0.00007458441,0.00019413914,0.0004980051,0.000112495116,0.0027547234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971455,0.00006138947,0.000023448989,0.000039884162,0.00013241361,0.000028302233],"domain_scores_gemma":[0.99903417,0.00035719492,0.00007863104,0.0002482476,0.00024522163,0.00003659132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004579738,0.0002616901,0.00028787932,0.0010858203,0.000426495,0.0005616969,0.0007245091,0.00038607555,0.001205089],"category_scores_gemma":[0.0021089972,0.00012724247,0.00020595556,0.0014812646,0.00048355607,0.0013822359,0.0005210787,0.0004634733,0.00035034088],"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":[0.0003322446,0.00013430574,0.0014678547,0.00022768244,0.000041790292,0.00023815969,0.00036293242,0.10098875,0.0751057,0.08999019,0.007998921,0.72311157],"study_design_scores_gemma":[0.00005725001,0.00021551497,0.0009319938,0.000041692754,0.000029671015,0.00046231408,0.000093257084,0.8952178,0.051433757,0.03612883,0.015341843,0.000046035377],"about_ca_topic_score_codex":0.0011701554,"about_ca_topic_score_gemma":0.0013793258,"teacher_disagreement_score":0.001205089,"about_ca_system_score_codex":0.0004368078,"about_ca_system_score_gemma":0.000535202,"threshold_uncertainty_score":0.0040314198},"labels":[],"label_agreement":null},{"id":"W4233898425","doi":"10.1007/978-0-85729-277-3_6","title":"Automata","year":2011,"lang":"en","type":"book-chapter","venue":"Texts in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Symbol (formal); Automaton; String (physics); Finite-state machine; State (computer science); Set (abstract data type); Sequence (biology); Abstract state machines; Theoretical computer science; Programming language; Abstraction; Büchi automaton; Algorithm; Deterministic automaton; Mathematics","score_opus":0.030437797452608707,"score_gpt":0.25238077727392455,"score_spread":0.22194297982131583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233898425","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007671835,0.003150772,0.26284763,0.002445388,0.0019993423,0.00013381032,0.0032311245,0.0039298334,0.71459025],"genre_scores_gemma":[0.2386366,0.0033803692,0.09602492,0.001980708,0.00090727967,0.00056418363,0.005927799,0.002361633,0.65021646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999438,0.00008195147,0.000040494277,0.00021843472,0.00016599153,0.0000550896],"domain_scores_gemma":[0.99939203,0.00019187949,0.0000221009,0.00020278111,0.0001543653,0.000036792793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027133746,0.0010073177,0.0007455411,0.0013760364,0.0015464431,0.0033953018,0.0010236738,0.0010461152,0.09892164],"category_scores_gemma":[0.0019162145,0.00049443333,0.00086450396,0.0013541578,0.0015321362,0.0042159543,0.0017343872,0.0019473762,0.03911129],"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":[0.000021547241,0.000019683945,0.00010536453,0.00009844179,0.000008842971,0.000046995243,0.0001742615,0.0010652286,0.0008342643,0.89172816,0.04265729,0.063240014],"study_design_scores_gemma":[0.000011249433,0.000011094308,0.00007055137,0.00003976156,0.00001107,0.00012399309,0.000067556684,0.0032251924,0.001124784,0.7521638,0.24313857,0.000012335611],"about_ca_topic_score_codex":0.0013058032,"about_ca_topic_score_gemma":0.0012775365,"teacher_disagreement_score":0.09892164,"about_ca_system_score_codex":0.0010183045,"about_ca_system_score_gemma":0.00075110234,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4234765999","doi":"10.1017/cbo9781139195768.014","title":"Densities","year":2009,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Algorithms and Data Compression","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":"Université du Québec à Montréal","funders":"","keywords":"Probabilistic logic; Computer science; Mathematics; Statistics","score_opus":0.019442508932057106,"score_gpt":0.18942772414769726,"score_spread":0.16998521521564017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234765999","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008621111,0.008745877,0.6383619,0.0039593754,0.0011304845,0.000101339996,0.0016397161,0.00067665003,0.33676362],"genre_scores_gemma":[0.38030142,0.03104258,0.2005284,0.0035342767,0.0028748214,0.0006381346,0.0047832904,0.0014922146,0.3748049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904734,0.00017932241,0.000038592585,0.00026322668,0.00039138753,0.00008016147],"domain_scores_gemma":[0.9986308,0.0006151484,0.00007190829,0.00024483996,0.00036847533,0.00006879445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006448461,0.0006711262,0.00062447623,0.0014717333,0.0012305008,0.0028001426,0.0011340745,0.001250447,0.04129593],"category_scores_gemma":[0.0059119044,0.0004342998,0.0006522089,0.0014988533,0.0016693464,0.004665231,0.0017604153,0.002254049,0.012313132],"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":[0.000004529506,0.000006091804,0.00010862317,0.000051114403,0.0000050988815,0.000036939593,0.00007370343,0.0014272332,0.00027153504,0.9722955,0.009973667,0.015745817],"study_design_scores_gemma":[0.000004146826,0.00000892077,0.00026756927,0.000054934975,0.0000068760505,0.0003900745,0.00007367929,0.0101962425,0.00056326744,0.87292314,0.11549739,0.0000136989365],"about_ca_topic_score_codex":0.0020017456,"about_ca_topic_score_gemma":0.0012852522,"teacher_disagreement_score":0.04129593,"about_ca_system_score_codex":0.0013572456,"about_ca_system_score_gemma":0.00080144603,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4235493345","doi":"10.1007/978-0-387-39940-9_2245","title":"Compressed Suffix Tree","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Computer science; Tree (set theory); Suffix tree; Mathematics; Linguistics; Combinatorics; Philosophy","score_opus":0.016232136642738534,"score_gpt":0.2306315574741651,"score_spread":0.21439942083142657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235493345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014977936,0.009672249,0.694793,0.002558368,0.0031715245,0.00057364214,0.016448077,0.025768407,0.23203692],"genre_scores_gemma":[0.09088906,0.0076961173,0.60310334,0.0016198561,0.0010805654,0.00047689534,0.052990597,0.0042838636,0.23785971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946445,0.000051262003,0.00004449691,0.00009816071,0.0003001759,0.00004154983],"domain_scores_gemma":[0.99904746,0.00018730332,0.00003280528,0.0003093082,0.00038346514,0.000039713363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033927706,0.00071373687,0.0007851349,0.0017947083,0.000773109,0.0017093485,0.0015211276,0.0009556395,0.054351505],"category_scores_gemma":[0.0024034602,0.00041541836,0.00047424246,0.0037350047,0.00050069677,0.0028381313,0.0016026145,0.0012397942,0.035734713],"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":[0.00018497498,0.00008743276,0.00017754904,0.00040299966,0.000028836608,0.0002579778,0.00010762909,0.0041651474,0.016946483,0.046111643,0.15141104,0.7801182],"study_design_scores_gemma":[0.00007663962,0.00014500573,0.0005017033,0.00026429966,0.0000698002,0.0023354802,0.00012573793,0.04712285,0.04107283,0.12154421,0.78667176,0.00006971605],"about_ca_topic_score_codex":0.0009232782,"about_ca_topic_score_gemma":0.0013888638,"teacher_disagreement_score":0.054351505,"about_ca_system_score_codex":0.00055493304,"about_ca_system_score_gemma":0.0012815899,"threshold_uncertainty_score":0.18182391},"labels":[],"label_agreement":null},{"id":"W4236660591","doi":"10.32388/brkvc1","title":"Flat-Coated Retriever","year":2020,"lang":"en","type":"reference-entry","venue":"Definitions","topic":"Algorithms and Data Compression","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":"","keywords":"Labrador Retriever; Geology; Medicine; Surgery","score_opus":0.08142975212551755,"score_gpt":0.26381958393572225,"score_spread":0.18238983181020468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236660591","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03110833,0.0027835784,0.38728398,0.0014264159,0.0030350415,0.0011064219,0.015295346,0.14252521,0.4154357],"genre_scores_gemma":[0.16630864,0.0017154898,0.22780417,0.0032316062,0.0009659436,0.0004393325,0.036795277,0.027435947,0.53530365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975762,0.00011576973,0.0001540841,0.00043821905,0.0013544493,0.00036127208],"domain_scores_gemma":[0.9962823,0.00022651705,0.00007993328,0.0020623894,0.0012073716,0.00014149494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001012712,0.0016099779,0.0012332181,0.0024147343,0.0014423679,0.003938302,0.002484398,0.0017974192,0.11385321],"category_scores_gemma":[0.0030423556,0.0010500111,0.0011585591,0.0025276213,0.0010229625,0.0049772137,0.0037044343,0.0013310214,0.14022422],"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":[0.0014599402,0.00024810983,0.0013671702,0.00070516946,0.00014450299,0.0006044668,0.00026682933,0.0024947112,0.088806935,0.035158567,0.4619057,0.40683794],"study_design_scores_gemma":[0.00025078398,0.00032420756,0.0029839443,0.00017163047,0.00018359676,0.0020730612,0.00027747662,0.039214905,0.26535892,0.02452214,0.6643692,0.0002701083],"about_ca_topic_score_codex":0.004259058,"about_ca_topic_score_gemma":0.0054342914,"teacher_disagreement_score":0.11385321,"about_ca_system_score_codex":0.0011476754,"about_ca_system_score_gemma":0.0015775784,"threshold_uncertainty_score":0.38087696},"labels":[],"label_agreement":null},{"id":"W4236766735","doi":"10.1007/978-3-662-44185-5_100809","title":"Nucleic Acid Pool of Random Sequence","year":2015,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Astrobiology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Nucleic acid; Sequence (biology); Computational biology; Random sequence; Computer science; Biology; Chemistry; Genetics; Mathematics","score_opus":0.024243358795722158,"score_gpt":0.2512105331943473,"score_spread":0.22696717439862513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236766735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050387047,0.015645405,0.84322447,0.0014661639,0.0018533914,0.00053994276,0.0077554295,0.006401196,0.07272691],"genre_scores_gemma":[0.19557714,0.014480061,0.62183094,0.0014231079,0.00072345,0.0016357097,0.028562523,0.0015232192,0.13424385],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996326,0.0000696186,0.000025047046,0.00012423054,0.00011967548,0.0000288243],"domain_scores_gemma":[0.9996629,0.00007137811,0.000018529714,0.00013934777,0.000077121775,0.00003082593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000622114,0.0007239411,0.0011021785,0.0014116539,0.00076104584,0.00095046643,0.0011001686,0.0007177209,0.0120161725],"category_scores_gemma":[0.0015159653,0.0004316805,0.00056684704,0.0014669298,0.0004556094,0.0015249171,0.0015540805,0.00089754886,0.014610939],"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":[0.00072883023,0.00012764765,0.0006191819,0.0014239697,0.00008585974,0.0009817292,0.00032591465,0.021619946,0.26517808,0.18112099,0.044100296,0.48368758],"study_design_scores_gemma":[0.00012385713,0.00039843115,0.0008363901,0.00033398526,0.00014931132,0.0016414516,0.00013297363,0.092898,0.23230642,0.1576181,0.51343215,0.00012895525],"about_ca_topic_score_codex":0.00044382518,"about_ca_topic_score_gemma":0.0005222482,"teacher_disagreement_score":0.0120161725,"about_ca_system_score_codex":0.0004326663,"about_ca_system_score_gemma":0.0009775558,"threshold_uncertainty_score":0.040198088},"labels":[],"label_agreement":null},{"id":"W4237598456","doi":"10.1109/fscs.1990.89556","title":"Permuting","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo; University of Toronto","funders":"","keywords":"Permutation (music); Combinatorics; Binary logarithm; Amortized analysis; Computer science; Mathematics; Inverse; Discrete mathematics; Time complexity; Order (exchange); Data structure; Algorithm","score_opus":0.025578650455104008,"score_gpt":0.2082091002842866,"score_spread":0.18263044982918258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237598456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023766419,0.00085996056,0.9256208,0.001023287,0.0013051146,0.0004606535,0.0011338616,0.0045243893,0.04130546],"genre_scores_gemma":[0.15704902,0.0013605185,0.78063333,0.0009972597,0.00048117086,0.000516396,0.003769467,0.0024930318,0.052699883],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976255,0.00045450343,0.00022759754,0.00079357263,0.00067080604,0.00022792464],"domain_scores_gemma":[0.99600863,0.0008704262,0.00026909367,0.00206604,0.0006562087,0.00012955336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011434664,0.0010797463,0.0011960748,0.0014208617,0.00160833,0.002741441,0.0015600184,0.0007680367,0.028171323],"category_scores_gemma":[0.0071132034,0.0005431411,0.0010135015,0.002404639,0.0017992664,0.005133836,0.0030031307,0.0015028401,0.013031605],"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":[0.0004476082,0.00012008377,0.001267103,0.0004144572,0.000067318695,0.00042649958,0.0005612725,0.007922121,0.022028092,0.1924587,0.033244565,0.7410421],"study_design_scores_gemma":[0.00007856659,0.00032492046,0.000825735,0.00019128533,0.000105079984,0.0013886997,0.00066609296,0.048848517,0.05464279,0.5622179,0.3305977,0.00011275072],"about_ca_topic_score_codex":0.0008378337,"about_ca_topic_score_gemma":0.0012456765,"teacher_disagreement_score":0.028171323,"about_ca_system_score_codex":0.0007706125,"about_ca_system_score_gemma":0.0010647547,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4239142364","doi":"10.4018/978-1-60566-026-4.ch302","title":"Indexing Textual Information","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Algorithms and Data Compression","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":"","keywords":"Search engine indexing; Computer science; Information retrieval; String (physics); Data structure; Representation (politics); Implementation; World Wide Web; Mathematics; Programming language","score_opus":0.013208433049296888,"score_gpt":0.23186070739766598,"score_spread":0.2186522743483691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239142364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03706382,0.025065629,0.44825873,0.005381084,0.0043076086,0.0034126707,0.12458199,0.030197024,0.32173148],"genre_scores_gemma":[0.15360016,0.021632724,0.48190543,0.0022859948,0.0027665368,0.0017345442,0.16323844,0.005221994,0.16761419],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984712,0.00026643317,0.00022657566,0.00028454262,0.000651229,0.00009996963],"domain_scores_gemma":[0.99449784,0.0024271926,0.0004435992,0.0010772971,0.0013651678,0.00018895156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011080328,0.0010418886,0.0009881557,0.014036328,0.0013530833,0.004513742,0.0017019908,0.0009777457,0.069554426],"category_scores_gemma":[0.010946653,0.0004203804,0.00073822803,0.016585063,0.00088338164,0.006452069,0.0027691901,0.0008847927,0.04331986],"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":[0.00017344883,0.000116092764,0.0006883502,0.0022057213,0.000048922557,0.00031756994,0.00075130287,0.00090725115,0.011371816,0.03931341,0.14295995,0.80114603],"study_design_scores_gemma":[0.000051440325,0.00012653264,0.0019751436,0.00096878776,0.00012205542,0.0014471589,0.00091565016,0.011552158,0.020814573,0.05597971,0.9059472,0.000099660065],"about_ca_topic_score_codex":0.0017004358,"about_ca_topic_score_gemma":0.0020356432,"teacher_disagreement_score":0.069554426,"about_ca_system_score_codex":0.0013672651,"about_ca_system_score_gemma":0.0016465026,"threshold_uncertainty_score":0.2326827},"labels":[],"label_agreement":null},{"id":"W4239151891","doi":"10.32920/14638191.v1","title":"Application of grammar-based codes for lossless compression of digital mammograms","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Huffman coding; Lossless compression; Grammar; Natural language processing; Artificial intelligence; Data compression; Theoretical computer science; Algorithm; Speech recognition; Linguistics","score_opus":0.021552396878466926,"score_gpt":0.2779393611962962,"score_spread":0.25638696431782926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239151891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024366947,0.00040869796,0.9731836,0.00022012327,0.000048462785,0.000054372416,0.00004800253,0.0005238275,0.0011459207],"genre_scores_gemma":[0.38605356,0.00095378223,0.61010146,0.0002520986,0.00010694029,0.00012471613,0.00019247709,0.000149381,0.0020655058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994128,0.0001328707,0.000035054585,0.00006249346,0.00032071915,0.000036075497],"domain_scores_gemma":[0.9990181,0.0005066761,0.00006803075,0.00018274528,0.00019984579,0.000024671413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006023176,0.00035681378,0.0003473122,0.0011093483,0.0002395297,0.0004986585,0.0006331381,0.00066347065,0.00064675225],"category_scores_gemma":[0.0032203177,0.00017108343,0.00035161374,0.00085557165,0.0009947242,0.00065892946,0.0007407138,0.000778597,0.00022610235],"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":[0.00028981437,0.000080043974,0.0011175853,0.00020354314,0.00004789618,0.0007322855,0.00037828778,0.25297794,0.1265515,0.18928072,0.0025039972,0.4258363],"study_design_scores_gemma":[0.000035513716,0.000090255875,0.00033166457,0.00002338811,0.000017823253,0.0004492624,0.00002193316,0.8884737,0.06791602,0.037599795,0.005013479,0.000027138029],"about_ca_topic_score_codex":0.0011581144,"about_ca_topic_score_gemma":0.00078967254,"teacher_disagreement_score":0.0011581144,"about_ca_system_score_codex":0.00063774164,"about_ca_system_score_gemma":0.00090028753,"threshold_uncertainty_score":0.004627168},"labels":[],"label_agreement":null},{"id":"W4239270184","doi":"10.1109/asonam.2016.7752351","title":"Frequent and non-frequent pattern detection in big data streams: An experimental simulation in 1 trillion data points","year":2016,"lang":"en","type":"article","venue":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Big data; String (physics); Suffix; Data mining; Data stream mining; Point (geometry); Data structure; Data modeling; Database; Operating system","score_opus":0.08813651274119436,"score_gpt":0.365066864245738,"score_spread":0.2769303515045436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239270184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979575,0.00026690602,0.017142827,0.00032964908,0.00011473279,0.00013218263,0.0007577303,0.00068853144,0.000992362],"genre_scores_gemma":[0.96820503,0.00016606905,0.029013176,0.00007961653,0.00002844593,0.0001397627,0.0016391991,0.000040882485,0.0006878039],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844754,0.00040802805,0.00013998557,0.00026324883,0.0005073298,0.000233956],"domain_scores_gemma":[0.9870935,0.009103874,0.0004598091,0.0012015228,0.0015819994,0.00055929524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021908497,0.0006189452,0.00080661115,0.0010057503,0.00059025147,0.00074713497,0.0012125352,0.0010195756,0.0013836768],"category_scores_gemma":[0.011652034,0.0002831055,0.000694452,0.0014520849,0.0007580554,0.0013386908,0.0007729488,0.0012595814,0.000325456],"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":[0.0060923444,0.006237814,0.07239095,0.00089729956,0.00050667144,0.0019379286,0.00102379,0.73052394,0.029023279,0.007109474,0.011948721,0.13230771],"study_design_scores_gemma":[0.000121162404,0.0006724235,0.006225909,0.00001437593,0.000029282739,0.00017424738,0.00021905013,0.98130804,0.008784307,0.0017929112,0.00063890155,0.00001939312],"about_ca_topic_score_codex":0.0048022536,"about_ca_topic_score_gemma":0.0036416415,"teacher_disagreement_score":0.0048022536,"about_ca_system_score_codex":0.000585261,"about_ca_system_score_gemma":0.0008081075,"threshold_uncertainty_score":0.011586428},"labels":[],"label_agreement":null},{"id":"W4240594398","doi":"10.1109/isit.2000.866596","title":"Universal lossless data compression with side information by using a conditional MPM grammar transform","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Lossless compression; Data compression; Algorithm; Computer science; Data compression ratio; Theoretical computer science; Mathematics; Image compression; Artificial intelligence; Image processing; Image (mathematics)","score_opus":0.034147209757063396,"score_gpt":0.2343408044179957,"score_spread":0.2001935946609323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240594398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015029476,0.00011841875,0.98281085,0.00014913219,0.000021944785,0.000025986541,0.0000427002,0.00033456425,0.0014669478],"genre_scores_gemma":[0.42481193,0.00034258512,0.5712313,0.00029394383,0.00009159817,0.00014658802,0.0002487447,0.00016182731,0.0026713833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995191,0.00012919644,0.000035708654,0.00007748236,0.00019750842,0.00004092163],"domain_scores_gemma":[0.9989416,0.0004996077,0.000086437154,0.00030184467,0.00014091215,0.000029613677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007991555,0.000361709,0.00045574014,0.00066858577,0.00028905502,0.00060956867,0.0007600395,0.0005846268,0.0010335024],"category_scores_gemma":[0.003469444,0.00018268841,0.00040054327,0.0007403179,0.0010724784,0.001248299,0.0016500823,0.00090898277,0.00041614842],"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":[0.0002548444,0.00007113468,0.0008611078,0.0001623792,0.000042408537,0.0005510727,0.00025214526,0.15148695,0.09647646,0.37279323,0.0032139814,0.37383425],"study_design_scores_gemma":[0.000028026225,0.00008785312,0.00024478234,0.00002249987,0.000019914474,0.0005741871,0.000024046518,0.82088536,0.07141696,0.10231848,0.0043544695,0.000023402454],"about_ca_topic_score_codex":0.0002974195,"about_ca_topic_score_gemma":0.00031202417,"teacher_disagreement_score":0.0010335024,"about_ca_system_score_codex":0.00035119377,"about_ca_system_score_gemma":0.00058093964,"threshold_uncertainty_score":0.004226327},"labels":[],"label_agreement":null},{"id":"W4240666804","doi":"10.32920/14638191","title":"Application of grammar-based codes for lossless compression of digital mammograms","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Huffman coding; Lossless compression; Grammar; Natural language processing; Arithmetic coding; Artificial intelligence; Data compression; Theoretical computer science; Speech recognition; Algorithm; Arithmetic; Context-adaptive binary arithmetic coding; Mathematics; Linguistics","score_opus":0.021552396878466926,"score_gpt":0.2779393611962962,"score_spread":0.25638696431782926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240666804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024366947,0.00040869796,0.9731836,0.00022012327,0.000048462785,0.000054372416,0.00004800253,0.0005238275,0.0011459207],"genre_scores_gemma":[0.38605356,0.00095378223,0.61010146,0.0002520986,0.00010694029,0.00012471613,0.00019247709,0.000149381,0.0020655058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994128,0.0001328707,0.000035054585,0.00006249346,0.00032071915,0.000036075497],"domain_scores_gemma":[0.9990181,0.0005066761,0.00006803075,0.00018274528,0.00019984579,0.000024671413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006023176,0.00035681378,0.0003473122,0.0011093483,0.0002395297,0.0004986585,0.0006331381,0.00066347065,0.00064675225],"category_scores_gemma":[0.0032203177,0.00017108343,0.00035161374,0.00085557165,0.0009947242,0.00065892946,0.0007407138,0.000778597,0.00022610235],"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":[0.00028981437,0.000080043974,0.0011175853,0.00020354314,0.00004789618,0.0007322855,0.00037828778,0.25297794,0.1265515,0.18928072,0.0025039972,0.4258363],"study_design_scores_gemma":[0.000035513716,0.000090255875,0.00033166457,0.00002338811,0.000017823253,0.0004492624,0.00002193316,0.8884737,0.06791602,0.037599795,0.005013479,0.000027138029],"about_ca_topic_score_codex":0.0011581144,"about_ca_topic_score_gemma":0.00078967254,"teacher_disagreement_score":0.0011581144,"about_ca_system_score_codex":0.00063774164,"about_ca_system_score_gemma":0.00090028753,"threshold_uncertainty_score":0.004627168},"labels":[],"label_agreement":null},{"id":"W4242856398","doi":"10.1145/564913.564916","title":"Parallel dynamic programming for solving the string editing problem on a CGM/BSP","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Substring; Computer science; Dynamic programming; Parallel computing; String (physics); Bulk synchronous parallel; Computation; Parallel algorithm; Graph; Grid; Algorithm; Theoretical computer science; Data structure; Mathematics; Programming language","score_opus":0.02497960470590364,"score_gpt":0.2521034068286063,"score_spread":0.2271238021227027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242856398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00946947,0.00006559315,0.9868803,0.00018096434,0.000029077017,0.00006657522,0.000055797133,0.0009901533,0.0022620696],"genre_scores_gemma":[0.12262602,0.000098919096,0.87256694,0.00015184289,0.00005065783,0.00038655257,0.0002821059,0.00026060618,0.003576466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911076,0.00020798045,0.000037158843,0.0002222627,0.0002998657,0.00012187147],"domain_scores_gemma":[0.999146,0.00045438198,0.00006450435,0.00017398197,0.00011723383,0.00004391919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008319613,0.0008646198,0.0010664333,0.0008161515,0.00093432586,0.00092948636,0.0017220507,0.0009559746,0.0042470386],"category_scores_gemma":[0.003141762,0.0003772734,0.0006774383,0.0015611189,0.0011399258,0.0015371111,0.0016203568,0.0017692199,0.0010677339],"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":[0.00020544989,0.0001352888,0.0005552924,0.00016214603,0.00004344016,0.00014878901,0.00014711196,0.6600031,0.0075364644,0.081969485,0.0059830565,0.24311036],"study_design_scores_gemma":[0.000038573788,0.000025103387,0.000062888634,0.0000036944255,0.0000067082738,0.000026170743,0.000022342538,0.9519377,0.0021409711,0.043349676,0.0023801967,0.0000060313373],"about_ca_topic_score_codex":0.0067389035,"about_ca_topic_score_gemma":0.007855632,"teacher_disagreement_score":0.0067389035,"about_ca_system_score_codex":0.0011811312,"about_ca_system_score_gemma":0.0015350868,"threshold_uncertainty_score":0.01420778},"labels":[],"label_agreement":null},{"id":"W4244284466","doi":"10.1109/ase.2004.1342740","title":"Automatic method completion","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Completion (oil and gas wells); Engineering","score_opus":0.01838206770465592,"score_gpt":0.2915312788505185,"score_spread":0.27314921114586255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244284466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056435177,0.0003368786,0.980142,0.00017340314,0.00020881492,0.00014357486,0.00040890783,0.010592979,0.0023498787],"genre_scores_gemma":[0.069582455,0.00032706122,0.91408265,0.00018134303,0.00015362917,0.0002495701,0.003445013,0.0032416233,0.008736638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912828,0.0017789329,0.0007734019,0.0019845658,0.003708069,0.0004721412],"domain_scores_gemma":[0.9723994,0.0077610128,0.0017281106,0.0105092,0.0070594475,0.0005427255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051520267,0.0016303781,0.0016753745,0.0040368713,0.0015402914,0.0028702316,0.0028566986,0.0015105021,0.0128180515],"category_scores_gemma":[0.030903805,0.0009239761,0.0021331252,0.002944261,0.0016872712,0.004424829,0.004085085,0.0038365854,0.009952221],"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":[0.0006409653,0.00020128016,0.0023536885,0.00078380253,0.00008014752,0.00027650356,0.0006861513,0.015462262,0.030716093,0.040475685,0.031697366,0.87662613],"study_design_scores_gemma":[0.00017549256,0.00029570176,0.0025893315,0.00032277577,0.000108678745,0.0015824605,0.0004952755,0.45533186,0.14836682,0.17903303,0.21148327,0.00021527322],"about_ca_topic_score_codex":0.0020830105,"about_ca_topic_score_gemma":0.001966233,"teacher_disagreement_score":0.0128180515,"about_ca_system_score_codex":0.0009767727,"about_ca_system_score_gemma":0.0038554168,"threshold_uncertainty_score":0.042880595},"labels":[],"label_agreement":null},{"id":"W4245009066","doi":"10.1016/j.ipl.2003.07.005","title":"Depth-First Discovery Algorithm for incremental topological sorting of directed acyclic graphs","year":2003,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Topological sorting; Cover (algebra); Sorting; Directed acyclic graph; Algorithm; Node (physics); Bounded function; Mathematics; Computational complexity theory; Computer science; Combinatorics; Discrete mathematics","score_opus":0.014654559237537848,"score_gpt":0.24698117496591082,"score_spread":0.232326615728373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245009066","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03145603,0.00087124563,0.95862544,0.0005533091,0.00012086107,0.00034900912,0.0010828138,0.004024348,0.0029170052],"genre_scores_gemma":[0.11278667,0.00035779184,0.8806113,0.00016433447,0.00005013725,0.00020741792,0.0026381286,0.00024080067,0.0029434566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987478,0.00021589064,0.00013233276,0.00025425665,0.00044487632,0.00020475955],"domain_scores_gemma":[0.99493045,0.0026854996,0.00036662698,0.0008916036,0.000862042,0.00026384267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015533683,0.001111439,0.002221153,0.0066200695,0.0019385149,0.0025937275,0.00348239,0.001664448,0.0047891135],"category_scores_gemma":[0.007900411,0.0009117989,0.0011751368,0.005951975,0.00107697,0.0039860187,0.002559177,0.0019685773,0.001324116],"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":[0.00076799246,0.00040573074,0.0022091211,0.000587654,0.00011872732,0.00016565777,0.00041600922,0.07270363,0.009403979,0.050950438,0.01774342,0.84452766],"study_design_scores_gemma":[0.0002447706,0.00026824887,0.0009557528,0.0000901528,0.00013356186,0.0003276664,0.0002597955,0.8576761,0.015637288,0.11046279,0.013862664,0.0000811847],"about_ca_topic_score_codex":0.009694192,"about_ca_topic_score_gemma":0.016099332,"teacher_disagreement_score":0.009694192,"about_ca_system_score_codex":0.002147414,"about_ca_system_score_gemma":0.005470211,"threshold_uncertainty_score":0.019275546},"labels":[],"label_agreement":null},{"id":"W4245950408","doi":"10.1109/iembs.2006.4398772","title":"Hardware Accelerator for Genomic Sequence Alignment","year":2006,"lang":"en","type":"article","venue":"Conference proceedings","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Smith–Waterman algorithm; Field-programmable gate array; Computer science; Parallel computing; Software; Sequence (biology); Hardware acceleration; Sequence alignment; Simple (philosophy); Function (biology); Algorithm; Computer hardware; Programming language; Biology","score_opus":0.04476237056101543,"score_gpt":0.26541876229729927,"score_spread":0.22065639173628385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245950408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07981071,0.0021794254,0.8130118,0.0008978876,0.0011250885,0.00047408103,0.002378344,0.03251834,0.06760427],"genre_scores_gemma":[0.3376463,0.0010099232,0.5959372,0.0008385794,0.00020583047,0.00065897347,0.0052975067,0.00057408545,0.05783167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997527,0.000033050816,0.000018403656,0.000046400848,0.00011027398,0.000039300427],"domain_scores_gemma":[0.9996271,0.0001104681,0.000028192007,0.00007510559,0.00013261786,0.000026462934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030408317,0.00047303838,0.00036399186,0.0006448618,0.00030946927,0.0006532827,0.0011153532,0.00042028486,0.04165293],"category_scores_gemma":[0.00094656955,0.00022095222,0.00025303353,0.0011261919,0.0001250776,0.00057625293,0.00042117503,0.00069071323,0.011810661],"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":[0.0015502635,0.000263655,0.004040754,0.00076251174,0.00014233895,0.00091415667,0.0002515413,0.0167943,0.19607137,0.03673814,0.13299261,0.6094783],"study_design_scores_gemma":[0.0006467113,0.0014908701,0.0070893695,0.00023354792,0.00016655173,0.0021197854,0.00021746753,0.30377057,0.20772082,0.013591266,0.46280465,0.00014843086],"about_ca_topic_score_codex":0.0011791397,"about_ca_topic_score_gemma":0.0014500914,"teacher_disagreement_score":0.04165293,"about_ca_system_score_codex":0.0005383221,"about_ca_system_score_gemma":0.00055402424,"threshold_uncertainty_score":0.1393429},"labels":[],"label_agreement":null},{"id":"W4246177186","doi":"10.1007/978-0-387-39940-9_2246","title":"Compressing XML","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; XML; World Wide Web","score_opus":0.017640278246583103,"score_gpt":0.23755033196447817,"score_spread":0.21991005371789507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246177186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028578803,0.02492414,0.75722307,0.0025438475,0.0036133751,0.0005842892,0.0056147072,0.016038746,0.16087899],"genre_scores_gemma":[0.11090553,0.0282189,0.58927035,0.0012775215,0.0012012465,0.00047356624,0.020129483,0.0032734035,0.24525],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948406,0.000040590294,0.000040747917,0.00007859311,0.0003225198,0.00003344689],"domain_scores_gemma":[0.99937797,0.00017400376,0.000025074025,0.00021847681,0.0001865044,0.000018067689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039825577,0.0011128654,0.0006482725,0.0026523543,0.0005402986,0.0015801332,0.0010760665,0.0006509921,0.026999453],"category_scores_gemma":[0.0019594643,0.00039997802,0.00054334535,0.0041785003,0.00058132235,0.002615782,0.0012625734,0.0011271042,0.011869088],"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":[0.00011007193,0.000054479107,0.00023866292,0.0005986068,0.00003688066,0.00026689444,0.0001985543,0.004123936,0.02546799,0.033103827,0.056898296,0.8789018],"study_design_scores_gemma":[0.000060666654,0.00021563483,0.0015842908,0.00050206174,0.00012406366,0.0029182336,0.0002946103,0.05576379,0.1651489,0.07765673,0.69563764,0.00009332729],"about_ca_topic_score_codex":0.0010567845,"about_ca_topic_score_gemma":0.0011962085,"teacher_disagreement_score":0.026999453,"about_ca_system_score_codex":0.0004647576,"about_ca_system_score_gemma":0.0005995579,"threshold_uncertainty_score":0.09032214},"labels":[],"label_agreement":null},{"id":"W4247213193","doi":"10.1002/spe.763","title":"Incremental frequency count—a post BWT‐stage for the Burrows–Wheeler compression algorithm","year":2006,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"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":"Stage (stratigraphy); Algorithm; Context (archaeology); Entropy (arrow of time); Data compression; Entropy encoding; Compression (physics); Computer science; Coding (social sciences); Mathematics; Statistics; Physics; Biology","score_opus":0.012877545573040378,"score_gpt":0.2808044728283498,"score_spread":0.2679269272553094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247213193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047900274,0.0004112665,0.939219,0.00024412415,0.00018096907,0.0003132184,0.00033315478,0.0055762976,0.0058216793],"genre_scores_gemma":[0.11832797,0.00020573582,0.86878175,0.00011574539,0.00012878218,0.00017234996,0.0011514861,0.0009469179,0.0101693515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991584,0.000100132165,0.00006552271,0.00013883585,0.00045289722,0.000084326006],"domain_scores_gemma":[0.9981667,0.0006152499,0.00014508396,0.00047650433,0.00053253694,0.00006398301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008136856,0.0007801928,0.0005056339,0.0019008694,0.0005425885,0.0015687526,0.0013589743,0.00074381806,0.012654918],"category_scores_gemma":[0.00419919,0.00040216208,0.00047272936,0.0014767935,0.00083427306,0.0019812617,0.001033652,0.0013807038,0.005537971],"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":[0.00057614286,0.00011706715,0.0010757403,0.00013416173,0.000029362565,0.00021657383,0.0001984681,0.0056493,0.10246091,0.017719585,0.0077066775,0.86411595],"study_design_scores_gemma":[0.00022602521,0.0008499173,0.007943677,0.000107016094,0.00011340857,0.0015162413,0.0002501012,0.38110927,0.5135723,0.020575829,0.073571324,0.00016490168],"about_ca_topic_score_codex":0.002770092,"about_ca_topic_score_gemma":0.004490808,"teacher_disagreement_score":0.012654918,"about_ca_system_score_codex":0.0005287799,"about_ca_system_score_gemma":0.00084415,"threshold_uncertainty_score":0.042334974},"labels":[],"label_agreement":null},{"id":"W4247715116","doi":"10.5539/mas.v12n11p387","title":"CRUSH: A New Lossless Compression Algorithm","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Algorithm; Huffman coding; Golomb coding; Lossless compression; Entropy encoding; Lossy compression; Data compression; Arithmetic coding; Context-adaptive binary arithmetic coding; Image compression; Artificial intelligence","score_opus":0.017197513408559906,"score_gpt":0.2607266086218073,"score_spread":0.2435290952132474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247715116","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011689239,0.0016956315,0.9785985,0.0003284153,0.00019061861,0.000118201104,0.00022210443,0.0028258706,0.00433146],"genre_scores_gemma":[0.13508579,0.0017952413,0.84011394,0.0005059224,0.000288517,0.0002458552,0.0014659608,0.0005090542,0.019989785],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99952364,0.00003708829,0.00003154067,0.0000632434,0.00030339122,0.000041050254],"domain_scores_gemma":[0.999587,0.000102028214,0.00004016173,0.0000762673,0.00017309813,0.000021397049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046103288,0.0006491795,0.0005429061,0.001805089,0.00046912674,0.0010351031,0.0011165955,0.0008361074,0.003251363],"category_scores_gemma":[0.0012915651,0.00023909684,0.00043980015,0.0014019668,0.00067624333,0.0018743656,0.0009581192,0.0011872483,0.0016825179],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046545547,0.00007531539,0.0006406309,0.00019512163,0.00005607366,0.00025968908,0.0001485812,0.031053811,0.051588535,0.02812046,0.016509239,0.87088716],"study_design_scores_gemma":[0.00014992076,0.00039867044,0.0009808003,0.00009273614,0.000058807313,0.0016994025,0.0000918041,0.7998383,0.10256174,0.019707145,0.07432774,0.00009297736],"about_ca_topic_score_codex":0.0018521759,"about_ca_topic_score_gemma":0.0013811266,"teacher_disagreement_score":0.003251363,"about_ca_system_score_codex":0.00051059655,"about_ca_system_score_gemma":0.0007113642,"threshold_uncertainty_score":0.010876954},"labels":[],"label_agreement":null},{"id":"W4251561142","doi":"10.1109/isit.2000.866306","title":"Universal lossless coding of sources with large and unbounded alphabets","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Arithmetic coding; Independent and identically distributed random variables; Distributed source coding; Alphabet; Lossless compression; Variable-length code; Asymptotically optimal algorithm; ENCODE; Shannon's source coding theorem; Entropy (arrow of time); Shannon–Fano coding; Mathematics; Entropy encoding; Computer science; Tunstall coding; Algorithm; Discrete mathematics; Huffman coding; Coding (social sciences); Context-adaptive binary arithmetic coding; Data compression; Decoding methods; Principle of maximum entropy; Binary entropy function; Random variable; Statistics","score_opus":0.012502576199859812,"score_gpt":0.19715825715724644,"score_spread":0.18465568095738663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251561142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035654426,0.00038796823,0.9606929,0.00026593736,0.000045114444,0.000021743677,0.00009834149,0.00026689595,0.0025666207],"genre_scores_gemma":[0.7349557,0.0006429434,0.26025593,0.00020499853,0.00012426107,0.00009665619,0.00025225698,0.00007436183,0.0033929097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995715,0.000112637405,0.000030522002,0.00005470047,0.00015491972,0.000075750955],"domain_scores_gemma":[0.99844116,0.0008631393,0.0001700736,0.0002917871,0.00018257428,0.00005130454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006964427,0.00041605244,0.00054176885,0.00082204904,0.00037176162,0.0008511118,0.0009974844,0.00061844045,0.001001877],"category_scores_gemma":[0.0041896915,0.0002221148,0.0003574871,0.0007918755,0.0009949526,0.0018495681,0.001504268,0.00094487105,0.00028085156],"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":[0.0003727223,0.000044882952,0.00038250478,0.0001589813,0.00002711629,0.00027202073,0.00025462505,0.19841193,0.037577182,0.5768101,0.0019386525,0.18374933],"study_design_scores_gemma":[0.000022969021,0.00005372476,0.00012430668,0.000037361417,0.000014555301,0.00013975336,0.000023600793,0.81880194,0.018359449,0.16005285,0.0023480977,0.00002140254],"about_ca_topic_score_codex":0.00049307174,"about_ca_topic_score_gemma":0.0005382426,"teacher_disagreement_score":0.001001877,"about_ca_system_score_codex":0.00050496706,"about_ca_system_score_gemma":0.0005088797,"threshold_uncertainty_score":0.0036831498},"labels":[],"label_agreement":null},{"id":"W4251692740","doi":"10.1007/978-0-387-39940-9_3907","title":"Uniform Resource Identifier","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identifier; Computer science; Resource (disambiguation); Computer network","score_opus":0.014526782772308238,"score_gpt":0.23002688236345797,"score_spread":0.21550009959114974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251692740","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018223429,0.0013999857,0.009629076,0.0015863994,0.0037054014,0.0007967968,0.12823491,0.0131235225,0.84134173],"genre_scores_gemma":[0.0010350258,0.0023601274,0.0047687367,0.0010945383,0.0006303052,0.0007724819,0.08406485,0.003926356,0.9013475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814105,0.00025981094,0.0002747015,0.00040485835,0.0006959357,0.00022352913],"domain_scores_gemma":[0.9924119,0.0012560752,0.0003885236,0.0016537687,0.0035894832,0.000700193],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017183144,0.002090176,0.004895256,0.0070069795,0.0013918199,0.0076546236,0.005181379,0.0023789292,0.87850666],"category_scores_gemma":[0.012062385,0.0009984262,0.0009628311,0.015863813,0.0011029395,0.0055094594,0.0037763282,0.0022489405,0.8924771],"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":[0.000017533011,0.000022285847,0.000035562043,0.0003546055,0.000004194309,0.000019518884,0.000030225936,0.0000902984,0.00023980736,0.004162772,0.95504117,0.0399822],"study_design_scores_gemma":[0.000012093922,0.000007726075,0.00010451062,0.0001724723,0.000004418395,0.000028868515,0.000019550354,0.00007764911,0.000095428724,0.0017788361,0.997686,0.000012491254],"about_ca_topic_score_codex":0.0056070155,"about_ca_topic_score_gemma":0.0055480096,"teacher_disagreement_score":0.87850666,"about_ca_system_score_codex":0.0016477808,"about_ca_system_score_gemma":0.0037999805,"threshold_uncertainty_score":0.17329544},"labels":[],"label_agreement":null},{"id":"W4252400262","doi":"10.1016/j.scico.2004.07.005","title":"Generation of fast interpreters for Huffman compressed bytecode","year":2005,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Opcode; Computer science; Bytecode; Operand; Byte; Huffman coding; Operating system; Just-in-time compilation; Virtual memory; Virtual machine; Parallel computing; Programming language; Algorithm; Memory management; Data compression","score_opus":0.03493034153137976,"score_gpt":0.29447289235625357,"score_spread":0.2595425508248738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252400262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12578781,0.00055719994,0.83837503,0.0003658886,0.00049272476,0.00035319783,0.00064196595,0.022466704,0.010959526],"genre_scores_gemma":[0.42764938,0.00031842108,0.5591213,0.0001915908,0.00011744472,0.00033838834,0.0017880697,0.0044252235,0.00605011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920017,0.00016911479,0.00006194714,0.000111228816,0.00033166565,0.00012597411],"domain_scores_gemma":[0.99722445,0.0013066728,0.00015475773,0.00042277697,0.0008139817,0.00007740894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010310335,0.00081603054,0.00068809406,0.0010705808,0.0006428163,0.0011850817,0.0013867109,0.000869952,0.005888665],"category_scores_gemma":[0.005117833,0.0007387094,0.0007686375,0.0007135818,0.000904707,0.0013921248,0.0011962228,0.0013074833,0.0012795482],"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":[0.0012088029,0.00029474677,0.0032962195,0.0010679206,0.00013403529,0.0013116464,0.0013656067,0.09807191,0.1490402,0.16854165,0.029604191,0.54606307],"study_design_scores_gemma":[0.00029017858,0.0003101906,0.0006876991,0.00014349369,0.000105330604,0.00040092846,0.00020775085,0.66394335,0.25917658,0.049994573,0.024651775,0.00008828838],"about_ca_topic_score_codex":0.000754813,"about_ca_topic_score_gemma":0.0012525533,"teacher_disagreement_score":0.005888665,"about_ca_system_score_codex":0.00091452565,"about_ca_system_score_gemma":0.0013817692,"threshold_uncertainty_score":0.019699574},"labels":[],"label_agreement":null},{"id":"W4252592952","doi":"10.1145/1109557.1109605","title":"Asymmetric balanced allocation with simple hash functions","year":2006,"lang":"en","type":"article","venue":"Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm - SODA '06","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hash function; Computer science; Simple (philosophy); Extension (predicate logic); Hash table; Double hashing; Function (biology); Scheme (mathematics); Hash chain; Theoretical computer science; Algorithm; Mathematics","score_opus":0.006219280445767619,"score_gpt":0.21952164956945983,"score_spread":0.21330236912369221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252592952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066469766,0.0005558283,0.9134891,0.00041688356,0.00024202773,0.00023180968,0.00019876502,0.0011863285,0.017209603],"genre_scores_gemma":[0.7628538,0.00050322927,0.21593672,0.00035210943,0.00028016474,0.00043201708,0.00033885453,0.00029809473,0.019005064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964089,0.00079918856,0.00023184478,0.0004459616,0.0014824043,0.0006317203],"domain_scores_gemma":[0.9947349,0.00110911,0.00039292668,0.0030083554,0.00052790804,0.00022679073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023993065,0.00077980064,0.0011167316,0.00093149045,0.0014726733,0.0022105365,0.0023657638,0.0013946746,0.009335534],"category_scores_gemma":[0.007960805,0.00048531796,0.00044635643,0.001666841,0.0019759443,0.0075320946,0.005716812,0.0015195248,0.004216805],"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":[0.0016063685,0.00027193927,0.0011574437,0.00021005774,0.00004828632,0.00025209246,0.0003587723,0.052619334,0.029890109,0.7202071,0.008253293,0.18512523],"study_design_scores_gemma":[0.00031452114,0.0003367809,0.00047422983,0.000061826315,0.000059255693,0.00071191345,0.000090204936,0.40272123,0.041018102,0.5169528,0.037156694,0.000102470425],"about_ca_topic_score_codex":0.00044798688,"about_ca_topic_score_gemma":0.0003403221,"teacher_disagreement_score":0.009335534,"about_ca_system_score_codex":0.0012342341,"about_ca_system_score_gemma":0.0012925946,"threshold_uncertainty_score":0.03123051},"labels":[],"label_agreement":null},{"id":"W4252763813","doi":"10.4018/9781591405603.ch121","title":"An XML Multi-Tier Pattern Dissemination System","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Algorithms and Data Compression","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":"Concordia University","funders":"","keywords":"XML; Computer science; World Wide Web","score_opus":0.021626237808141498,"score_gpt":0.26002171047625156,"score_spread":0.23839547266811006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252763813","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069591217,0.0008731924,0.70656365,0.001020444,0.00040040427,0.0008002982,0.011918515,0.24044299,0.031021412],"genre_scores_gemma":[0.09221382,0.0021924658,0.663196,0.0019147651,0.00024774295,0.0011021193,0.06384712,0.023831366,0.15145458],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990226,0.00018617352,0.00020631206,0.0001581302,0.00036548506,0.00006133066],"domain_scores_gemma":[0.9977331,0.000554612,0.00011069963,0.0009661063,0.00047067605,0.00016476368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025400708,0.00088408263,0.0008140346,0.002658038,0.0008620236,0.0037999065,0.0022660615,0.0018399793,0.03928529],"category_scores_gemma":[0.005183105,0.0006959195,0.0010009024,0.0030133703,0.00047809622,0.0050114538,0.0033781517,0.0012334419,0.026500937],"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":[0.0008807507,0.00034542062,0.0019573502,0.0009940683,0.00010981105,0.00083296996,0.0008390561,0.0042786775,0.026447648,0.054392044,0.23889875,0.6700234],"study_design_scores_gemma":[0.0002577749,0.0002143221,0.0014832845,0.00022451491,0.00008298524,0.0012505276,0.00026322002,0.05606741,0.030978154,0.039158918,0.8698805,0.00013844289],"about_ca_topic_score_codex":0.0020957005,"about_ca_topic_score_gemma":0.0020587328,"teacher_disagreement_score":0.03928529,"about_ca_system_score_codex":0.00088226,"about_ca_system_score_gemma":0.0010088927,"threshold_uncertainty_score":0.1314224},"labels":[],"label_agreement":null},{"id":"W4253257261","doi":"10.1007/978-3-030-62124-7_7","title":"Lossless Compression Algorithms","year":2021,"lang":"en","type":"book-chapter","venue":"Texts in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Lossless compression; Lossy compression; Huffman coding; Arithmetic coding; Entropy encoding; Adaptive coding; Data compression; Computer science; Tunstall coding; Algorithm; Context-adaptive binary arithmetic coding; Golomb coding; Theoretical computer science; Image compression; Artificial intelligence; Image processing; Image (mathematics)","score_opus":0.02523300491218078,"score_gpt":0.26866145456374724,"score_spread":0.24342844965156646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253257261","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027082819,0.022496235,0.74786454,0.0012660698,0.002018075,0.0001961773,0.001103752,0.00504034,0.21730652],"genre_scores_gemma":[0.048270676,0.02826075,0.39786565,0.0017514024,0.002351517,0.00037087407,0.0045052175,0.0022170278,0.51440686],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994136,0.00004533948,0.000024923555,0.00008855224,0.000394196,0.000033420303],"domain_scores_gemma":[0.9994808,0.00016949915,0.000020700725,0.0001924386,0.00012083974,0.000015707976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038610573,0.0014215166,0.0008598325,0.0019392883,0.00058035104,0.0020132698,0.0014012561,0.0011375974,0.046654407],"category_scores_gemma":[0.0015279504,0.00049445336,0.0004442588,0.0027193958,0.0010215883,0.0026930035,0.0012097129,0.0022917467,0.035085544],"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":[0.00005317619,0.00005870881,0.000060757677,0.00033978766,0.000020998752,0.00005997234,0.000056635945,0.0057226554,0.00907182,0.1099676,0.09638313,0.77820474],"study_design_scores_gemma":[0.000037747242,0.00012017885,0.00049053755,0.00032168505,0.00004026493,0.0013604127,0.000047176676,0.06509269,0.04191454,0.20758411,0.6829293,0.0000614544],"about_ca_topic_score_codex":0.00029937222,"about_ca_topic_score_gemma":0.00041859053,"teacher_disagreement_score":0.046654407,"about_ca_system_score_codex":0.0005654085,"about_ca_system_score_gemma":0.0004579312,"threshold_uncertainty_score":0.15607452},"labels":[],"label_agreement":null},{"id":"W4253384962","doi":"10.1145/381694.378827","title":"Bytecode compression via profiled grammar rewriting","year":2001,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bytecode; Computer science; Programming language; Grammar; Rewriting; Interpreter; Linguistics","score_opus":0.023822481168956956,"score_gpt":0.26405382660562954,"score_spread":0.24023134543667257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253384962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013414106,0.00017930543,0.9664128,0.00015654891,0.000073760275,0.00016961199,0.0002733698,0.014696631,0.0046239244],"genre_scores_gemma":[0.19178228,0.00039685014,0.7926973,0.00027190754,0.00008561443,0.00036337532,0.0019476374,0.0049413103,0.007513721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817777,0.00028362309,0.0001520033,0.0003392252,0.0008895234,0.00015796814],"domain_scores_gemma":[0.99713504,0.0008671598,0.00018132845,0.0011180844,0.0006489424,0.000049495346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084966613,0.0008503784,0.00076557713,0.0010146778,0.00051650486,0.0010941473,0.0015953872,0.0005641002,0.0035172596],"category_scores_gemma":[0.004981362,0.0006005069,0.000802696,0.0009711388,0.0010675463,0.0020331135,0.001769138,0.0014245076,0.0019473425],"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":[0.0003294278,0.00014051015,0.0014909277,0.00043541924,0.000059364364,0.0008389952,0.0012244912,0.056581166,0.09666581,0.124192715,0.015702283,0.7023389],"study_design_scores_gemma":[0.00010009744,0.00014622613,0.00066098844,0.000125684,0.00007574495,0.0012807817,0.00017898035,0.432193,0.37397486,0.09809538,0.093067355,0.00010090877],"about_ca_topic_score_codex":0.0016951375,"about_ca_topic_score_gemma":0.0019180677,"teacher_disagreement_score":0.0035172596,"about_ca_system_score_codex":0.0008980275,"about_ca_system_score_gemma":0.00122034,"threshold_uncertainty_score":0.011766434},"labels":[],"label_agreement":null},{"id":"W4253565581","doi":"10.1109/isit.2003.1228064","title":"On the university of grammar-based codes for sources with countably infinite alphabets","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Lossless compression; Computer science; Grammar; Data compression; Alphabet; Theoretical computer science; Mathematics; Discrete mathematics; Algorithm; Linguistics","score_opus":0.013934141409887617,"score_gpt":0.20079427884771409,"score_spread":0.18686013743782648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253565581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0626888,0.005578245,0.8920828,0.0031762898,0.0003544484,0.00005624401,0.00025303493,0.00042055032,0.035389636],"genre_scores_gemma":[0.7339701,0.008089681,0.2363,0.0016665919,0.0018579244,0.0002673456,0.0006345968,0.0005232978,0.01669047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976803,0.00060202705,0.00016247532,0.00044576035,0.00090884994,0.00020051701],"domain_scores_gemma":[0.98258245,0.012986648,0.0009133148,0.001977556,0.0012338861,0.00030621083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021996922,0.00073605875,0.0010220088,0.0025787961,0.0012585657,0.0022221252,0.0011942999,0.0018115892,0.0025987963],"category_scores_gemma":[0.020563513,0.00060686877,0.0010853378,0.001908226,0.0056884126,0.0058455197,0.0034489299,0.0034515054,0.00059815694],"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":[0.000032222393,0.000011022159,0.00022735166,0.00005929058,0.000008467488,0.00008169594,0.00018251207,0.01442475,0.0006761879,0.9680738,0.0009909429,0.015231709],"study_design_scores_gemma":[0.00000920693,0.000019865398,0.00010319138,0.00003912686,0.000007117937,0.00012281458,0.000021564589,0.058563083,0.0007970526,0.93600357,0.0042955773,0.000017875711],"about_ca_topic_score_codex":0.0013424839,"about_ca_topic_score_gemma":0.00071559416,"teacher_disagreement_score":0.0025987963,"about_ca_system_score_codex":0.001859447,"about_ca_system_score_gemma":0.0011079632,"threshold_uncertainty_score":0.013491273},"labels":[],"label_agreement":null},{"id":"W4253860495","doi":"10.1109/isit.1993.748587","title":"Bidirectional Sequential Decoding","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Decoding methods; Computer science; Block (permutation group theory); Tree (set theory); Computational complexity theory; Stack (abstract data type); Algorithm; Code (set theory); Parallel computing; Exponent; Theoretical computer science; Mathematics; Set (abstract data type)","score_opus":0.023290150205219715,"score_gpt":0.2698416952788272,"score_spread":0.24655154507360746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253860495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011382739,0.00050918286,0.97887677,0.00009837711,0.00006929276,0.00005694434,0.000108438384,0.00060021476,0.008298041],"genre_scores_gemma":[0.27239305,0.0011103249,0.7137264,0.00021064104,0.0000996444,0.00016467959,0.00048877526,0.00029297566,0.011513433],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920374,0.00016376087,0.000054584063,0.000102082224,0.00038184086,0.000093989474],"domain_scores_gemma":[0.9987765,0.00039656766,0.00009547493,0.00036455062,0.00032646616,0.000040419494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000650735,0.0008266502,0.00064168114,0.00080900086,0.00054031407,0.000977709,0.00079256523,0.00058321346,0.0040374026],"category_scores_gemma":[0.0024906415,0.00025684404,0.00043703476,0.0009975448,0.0005072979,0.0012761592,0.0013072274,0.00061948196,0.0021681737],"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":[0.00045744298,0.00012517131,0.0013048718,0.00029097928,0.000084370666,0.00020563157,0.00016959454,0.092730105,0.048993703,0.14482428,0.005281192,0.7055326],"study_design_scores_gemma":[0.00006209805,0.00021907284,0.0003521259,0.00006725025,0.000060718936,0.0010673143,0.00007059888,0.8171219,0.07505312,0.06835726,0.037516613,0.000051901836],"about_ca_topic_score_codex":0.0014657918,"about_ca_topic_score_gemma":0.0030258303,"teacher_disagreement_score":0.0040374026,"about_ca_system_score_codex":0.00043528996,"about_ca_system_score_gemma":0.0013947908,"threshold_uncertainty_score":0.013506472},"labels":[],"label_agreement":null},{"id":"W4254363650","doi":"10.1145/2858965.2814305","title":"Incremental computation with names","year":2015,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"Defense Advanced Research Projects Agency; Center for Selective C-H Functionalization, National Science Foundation","keywords":"Computation; Computer science; Class (philosophy); Scratch; Probabilistic logic; Theoretical computer science; Functional programming; State (computer science); Programming language; Artificial intelligence","score_opus":0.0406810661610968,"score_gpt":0.2739843194412407,"score_spread":0.2333032532801439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254363650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010949923,0.0001896846,0.9737124,0.0004455355,0.00012307431,0.00008724538,0.00017064458,0.0069309077,0.007390627],"genre_scores_gemma":[0.27295044,0.00040761626,0.70837665,0.0005271788,0.0001858817,0.0003494171,0.00060658186,0.0023517546,0.014244497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99706393,0.0007445195,0.00022256316,0.0005639105,0.0010792386,0.00032586878],"domain_scores_gemma":[0.9944423,0.0023625658,0.00025343284,0.0020083962,0.00076037063,0.00017297639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027698749,0.00058419065,0.0007196863,0.0011817646,0.0015092965,0.0032384573,0.0026370485,0.00090814044,0.006175023],"category_scores_gemma":[0.01257804,0.00077460665,0.0017353881,0.0013475138,0.0034680082,0.008937418,0.0060681594,0.0020911281,0.0014316754],"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":[0.00031962252,0.000052184358,0.0015527656,0.0002217762,0.00005113277,0.0002257321,0.0010426933,0.025372172,0.006595007,0.82736856,0.008553873,0.12864442],"study_design_scores_gemma":[0.000059128943,0.00007496443,0.00028804794,0.00008294958,0.00010514679,0.00026006217,0.00015767086,0.23083621,0.021313407,0.66911465,0.0776368,0.00007096339],"about_ca_topic_score_codex":0.0027229618,"about_ca_topic_score_gemma":0.004135415,"teacher_disagreement_score":0.006175023,"about_ca_system_score_codex":0.0015369238,"about_ca_system_score_gemma":0.002324081,"threshold_uncertainty_score":0.02065748},"labels":[],"label_agreement":null},{"id":"W4254694878","doi":"10.32920/14638791.v1","title":"Efficient computation of spaced seeds","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Heuristic; Computer science; Software; Computation; Quadratic equation; Algorithm; Speedup; Range (aeronautics); Artificial intelligence; Mathematics; Parallel computing; Engineering; Programming language","score_opus":0.019085961423225644,"score_gpt":0.2688779504802859,"score_spread":0.24979198905706027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254694878","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06541418,0.0003593238,0.92495406,0.00019975918,0.000114943,0.00008800504,0.000240143,0.003871111,0.004758393],"genre_scores_gemma":[0.2894131,0.00017706079,0.70623237,0.00009825562,0.000046741643,0.0001353007,0.0006677497,0.0010135126,0.0022158788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998626,0.00024842983,0.00009302395,0.00026622962,0.000647353,0.00011906206],"domain_scores_gemma":[0.99502206,0.0025770364,0.00040136953,0.00077203556,0.0009547042,0.00027280205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012634516,0.0010388453,0.001392823,0.0020582087,0.0009863249,0.0016882996,0.001867549,0.0014295296,0.0075819506],"category_scores_gemma":[0.012836522,0.0006984417,0.00079992577,0.0021474867,0.0011018552,0.0025692899,0.0018110779,0.0011506584,0.002274722],"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":[0.00074759993,0.00021902416,0.0062645585,0.0006440469,0.00012369214,0.0008591272,0.00057583227,0.48873425,0.042426553,0.12918201,0.01464754,0.31557572],"study_design_scores_gemma":[0.000055321416,0.00009237958,0.00045309315,0.000029713656,0.000018273207,0.00022044714,0.000050744773,0.9053918,0.013796145,0.07524273,0.0046223747,0.000026924658],"about_ca_topic_score_codex":0.0013685275,"about_ca_topic_score_gemma":0.001550136,"teacher_disagreement_score":0.0075819506,"about_ca_system_score_codex":0.0011086732,"about_ca_system_score_gemma":0.0014010392,"threshold_uncertainty_score":0.02536416},"labels":[],"label_agreement":null},{"id":"W4254779780","doi":"10.1145/1109557.1109599","title":"Rank/select operations on large alphabets","year":2006,"lang":"en","type":"article","venue":"Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm - SODA '06","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Rank (graph theory); Generalization; String (physics); Alphabet; Variety (cybernetics); Representation (politics); Computer science; Combinatorics; Binary number; Binary search algorithm; Theoretical computer science; Mathematics; Algorithm; Search algorithm; Arithmetic; Information retrieval; Artificial intelligence","score_opus":0.006358395880270913,"score_gpt":0.23519723564458858,"score_spread":0.22883883976431768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254779780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23012811,0.00129481,0.7352485,0.0024220843,0.0003011656,0.0003582899,0.002374929,0.0073021576,0.020569913],"genre_scores_gemma":[0.6165663,0.00080941006,0.35925528,0.0007935178,0.0005201496,0.00030749704,0.0027179257,0.00068419735,0.018345635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972264,0.00048381698,0.00025012592,0.00047979472,0.0010905917,0.00046922613],"domain_scores_gemma":[0.99140704,0.00416594,0.0006882462,0.0028198403,0.0005971694,0.00032178857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014594669,0.00061988505,0.0017559739,0.0012658396,0.0013483916,0.0025370764,0.0017715598,0.0014745333,0.012366417],"category_scores_gemma":[0.009729339,0.00040794318,0.00073847995,0.003232681,0.001338231,0.008518698,0.0027574701,0.0016386658,0.003829368],"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":[0.003091218,0.00059780956,0.00227008,0.00081662345,0.00006490247,0.00092703116,0.0007937951,0.07352174,0.042607345,0.21578568,0.040493898,0.6190299],"study_design_scores_gemma":[0.00042834348,0.00089771335,0.000764027,0.00011362569,0.00008632644,0.0014498684,0.0008940404,0.46785176,0.07605795,0.41093087,0.0403974,0.00012803052],"about_ca_topic_score_codex":0.0010320963,"about_ca_topic_score_gemma":0.0014626544,"teacher_disagreement_score":0.012366417,"about_ca_system_score_codex":0.0006898492,"about_ca_system_score_gemma":0.0010901687,"threshold_uncertainty_score":0.041369796},"labels":[],"label_agreement":null},{"id":"W4281288662","doi":"10.1101/2022.05.19.492613","title":"Succinct <i>k</i> -mer Sets Using Subset Rank Queries on the Spectral Burrows-Wheeler Transform <sup>*</sup>","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Academy of Finland","keywords":"Substring; Lossless compression; String (physics); Suffix tree; Combinatorics; Data structure; Mathematics; Entropy (arrow of time); Computer science; Data compression; Discrete mathematics; Theoretical computer science; Algorithm","score_opus":0.020760521518102905,"score_gpt":0.23065981035379793,"score_spread":0.20989928883569503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281288662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37379593,0.00077444554,0.5968926,0.0019288526,0.00014440384,0.0007078745,0.0061048153,0.009540889,0.010110186],"genre_scores_gemma":[0.6428116,0.00028613093,0.34239584,0.00039203136,0.0001289917,0.00043540265,0.009305037,0.0005453241,0.0036996326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615484,0.0005961478,0.00042044136,0.00044893293,0.0020342194,0.0003453722],"domain_scores_gemma":[0.99085534,0.0035871835,0.0007347098,0.0033359772,0.0011142492,0.00037258395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020175031,0.0007800934,0.0022385153,0.002339814,0.0011456284,0.0033200553,0.0020581863,0.0014121978,0.0039710477],"category_scores_gemma":[0.0145946145,0.0005429747,0.00086394494,0.0044267094,0.0013278802,0.007712572,0.003868827,0.0015142587,0.001835992],"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":[0.00310189,0.0011622434,0.01141804,0.00072790904,0.00014352569,0.0012802681,0.0023142677,0.14610831,0.100800015,0.18452193,0.037095133,0.5113265],"study_design_scores_gemma":[0.00017380847,0.00047623724,0.001317492,0.00006284567,0.0000414833,0.00059566007,0.0009714188,0.8156393,0.04944918,0.11967902,0.011508984,0.00008457687],"about_ca_topic_score_codex":0.0018008925,"about_ca_topic_score_gemma":0.0023168493,"teacher_disagreement_score":0.0039710477,"about_ca_system_score_codex":0.0013908539,"about_ca_system_score_gemma":0.0014597435,"threshold_uncertainty_score":0.013284445},"labels":[],"label_agreement":null},{"id":"W4281773586","doi":"10.1038/s41598-022-12843-9","title":"Flexible protein database based on amino acid k-mers","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Computer science; Identification (biology); Computational biology; Database; Biology","score_opus":0.019002802780977917,"score_gpt":0.24644319685890337,"score_spread":0.22744039407792546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281773586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11428439,0.0048922566,0.76023453,0.00044908724,0.00033127796,0.00040770162,0.03402697,0.074021496,0.011352268],"genre_scores_gemma":[0.25934094,0.002061272,0.6668938,0.0002765025,0.00008927198,0.00045755753,0.06301641,0.0019533066,0.0059109177],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99915326,0.000091064714,0.00017640866,0.00028214636,0.00023281972,0.000064283435],"domain_scores_gemma":[0.99883574,0.0002059961,0.00012803377,0.0004623734,0.0002627526,0.00010511763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009639384,0.0007132347,0.0013033344,0.0028975166,0.0006596508,0.0017577091,0.0016780044,0.000599497,0.0032710573],"category_scores_gemma":[0.002552925,0.00043908344,0.0006110604,0.0038691703,0.0003884379,0.002753217,0.0017771815,0.0009095619,0.0033695514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058114324,0.00039263684,0.0068431348,0.0017245088,0.0003389602,0.0017867954,0.00062841637,0.016235704,0.20783179,0.057556946,0.060327664,0.6405221],"study_design_scores_gemma":[0.0006293606,0.0009259732,0.011454073,0.00045650575,0.00026381953,0.0068548713,0.0004349885,0.25057828,0.2743266,0.09573717,0.35784274,0.00049572473],"about_ca_topic_score_codex":0.00066836085,"about_ca_topic_score_gemma":0.00062735577,"teacher_disagreement_score":0.0032710573,"about_ca_system_score_codex":0.0004236026,"about_ca_system_score_gemma":0.000677911,"threshold_uncertainty_score":0.010942757},"labels":[],"label_agreement":null},{"id":"W4282920194","doi":"10.1139/cjfas-2022-0049","title":"Fixed mesh shape reduces variability in codend size selection","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Biology; Fishery; Environmental science; Statistics; Mathematics; Computer science; Artificial intelligence","score_opus":0.018123662934539847,"score_gpt":0.22717271509247974,"score_spread":0.2090490521579399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282920194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88614064,0.00036786185,0.10688534,0.00014387678,0.00011700346,0.00010619639,0.00035080072,0.000834898,0.0050533367],"genre_scores_gemma":[0.94846845,0.00011038757,0.049626622,0.00006533371,0.000011645921,0.00008752477,0.00031182828,0.00015683135,0.001161471],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994373,0.00008906462,0.000050093884,0.00016673774,0.00019718643,0.000059693797],"domain_scores_gemma":[0.9963536,0.0018433341,0.00035562128,0.00071601366,0.00062079675,0.00011062883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006445325,0.00039061412,0.0003897729,0.0006600642,0.00030725848,0.00068976334,0.0007446858,0.0004992147,0.0016278295],"category_scores_gemma":[0.00864055,0.00015942307,0.00023612296,0.0005253597,0.0005127388,0.0007220302,0.0008439324,0.0003648265,0.0004159533],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026668499,0.000497983,0.04346452,0.00053266285,0.00010400572,0.0004095722,0.0005151527,0.14907071,0.45829847,0.0048986315,0.00273122,0.33681017],"study_design_scores_gemma":[0.00018143948,0.002382014,0.072207525,0.00011202515,0.00017873368,0.00072778657,0.00043073526,0.62125194,0.28250957,0.005721608,0.014122821,0.00017382063],"about_ca_topic_score_codex":0.0018118306,"about_ca_topic_score_gemma":0.002718523,"teacher_disagreement_score":0.0018118306,"about_ca_system_score_codex":0.000386195,"about_ca_system_score_gemma":0.00039813167,"threshold_uncertainty_score":0.005445659},"labels":[],"label_agreement":null},{"id":"W4283012608","doi":"10.1186/s12863-022-01053-x","title":"Parallel and private generalized suffix tree construction and query on genomic data","year":2022,"lang":"en","type":"article","venue":"BMC Genomic Data","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Suffix tree; Suffix; Computer science; Tree (set theory); Mathematics; Combinatorics; Data structure; Programming language; Linguistics; Philosophy","score_opus":0.06667293420759444,"score_gpt":0.26940896959497374,"score_spread":0.20273603538737928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283012608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098646395,0.00068992155,0.8864881,0.00076554366,0.00014161349,0.0003457341,0.0018541456,0.0071750865,0.00389356],"genre_scores_gemma":[0.4624915,0.0004330909,0.52605927,0.00024483405,0.000114134666,0.0003277295,0.0051070717,0.0004193395,0.0048030615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99701995,0.00052332866,0.00027011673,0.0006338483,0.0011706423,0.00038212765],"domain_scores_gemma":[0.9962392,0.00083770097,0.00023382665,0.002010073,0.0005332631,0.00014589484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013353582,0.0005595496,0.00092031626,0.00080537883,0.0010976607,0.0016118629,0.0016419605,0.001132727,0.003720031],"category_scores_gemma":[0.005302297,0.00032274774,0.0010616174,0.0031496705,0.00094223116,0.004073359,0.0031180528,0.0010902721,0.002172975],"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":[0.0017810493,0.00040638333,0.006609786,0.0007424621,0.00015802165,0.0010466331,0.0014538725,0.09900415,0.11160672,0.078889504,0.027417172,0.67088413],"study_design_scores_gemma":[0.00021856677,0.00045270124,0.0022265362,0.00004134551,0.000064878106,0.001610952,0.000840558,0.801581,0.08034186,0.088728465,0.023811605,0.000081417595],"about_ca_topic_score_codex":0.0021679858,"about_ca_topic_score_gemma":0.0021889491,"teacher_disagreement_score":0.003720031,"about_ca_system_score_codex":0.0008949451,"about_ca_system_score_gemma":0.0024344574,"threshold_uncertainty_score":0.012444794},"labels":[],"label_agreement":null},{"id":"W4283820596","doi":"10.1109/dcc52660.2022.00017","title":"CSTs for Terabyte-Sized Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Terabyte; Computer science; Scalability; Parsing; Suffix; Trie; String (physics); Phrase; Prefix; Information retrieval; Data mining; Artificial intelligence; Data structure; Database; Programming language","score_opus":0.06483453739719433,"score_gpt":0.303747243356867,"score_spread":0.23891270595967265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283820596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03243187,0.0011465427,0.8559415,0.0014087022,0.00086819124,0.0004247163,0.04269841,0.058670323,0.0064098244],"genre_scores_gemma":[0.07013741,0.00093939615,0.82924414,0.00047881066,0.00025217718,0.00086338364,0.08763228,0.004728196,0.0057240976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983432,0.0001971886,0.00026934114,0.00040494444,0.0006706992,0.00011460783],"domain_scores_gemma":[0.9903162,0.0031437245,0.0005725044,0.003848928,0.0018972969,0.0002214999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012634745,0.00096481456,0.00083362666,0.0030070723,0.0010373906,0.002403492,0.0015831641,0.0013308281,0.014272203],"category_scores_gemma":[0.018708022,0.00055414945,0.0013910056,0.007922674,0.00075687986,0.00455879,0.0027245472,0.0024350248,0.01306704],"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":[0.00066408934,0.00014838822,0.0036233251,0.0013463806,0.00021893227,0.00087580003,0.0010181174,0.024294915,0.0597537,0.043731283,0.16196474,0.70236045],"study_design_scores_gemma":[0.00020474855,0.00030183638,0.003965276,0.0003557431,0.00011379334,0.0025033355,0.0012593932,0.3194804,0.15904282,0.1580896,0.3545143,0.00016889298],"about_ca_topic_score_codex":0.0012563433,"about_ca_topic_score_gemma":0.002706887,"teacher_disagreement_score":0.014272203,"about_ca_system_score_codex":0.00072422536,"about_ca_system_score_gemma":0.0019667954,"threshold_uncertainty_score":0.047745287},"labels":[],"label_agreement":null},{"id":"W4284974261","doi":"10.14778/3551793.3551848","title":"Are updatable learned indexes ready?","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"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; Concurrency; Robustness (evolution); Software deployment; Space (punctuation); Data science; Software engineering; Distributed computing; Operating system","score_opus":0.026758491041296073,"score_gpt":0.24009395904235964,"score_spread":0.21333546800106357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284974261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3633968,0.022354197,0.47088975,0.019404318,0.004094361,0.0012436664,0.007905696,0.07137203,0.039339148],"genre_scores_gemma":[0.6488403,0.0045995754,0.31407735,0.0024724293,0.00091977464,0.00039642514,0.013423552,0.0042915177,0.010979048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99203134,0.0017564328,0.0008897298,0.0012836772,0.0033264346,0.00071238825],"domain_scores_gemma":[0.9561834,0.010562959,0.0018254367,0.024061821,0.006403298,0.00096315204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070725833,0.0012371158,0.0016393788,0.0015189121,0.0012283548,0.0069376035,0.004508027,0.0015324638,0.006525167],"category_scores_gemma":[0.064660005,0.0010963598,0.0007364938,0.0034062525,0.0022029162,0.024533208,0.00370661,0.0029133165,0.0048400895],"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":[0.002071271,0.00060837035,0.019656643,0.000811663,0.000277145,0.000506092,0.0009396094,0.02866819,0.016903318,0.031251177,0.07640499,0.8219015],"study_design_scores_gemma":[0.0006659661,0.0016793202,0.012348234,0.00076643925,0.00035352918,0.0022290351,0.0030200088,0.48837098,0.089437634,0.12124235,0.2794678,0.00041870872],"about_ca_topic_score_codex":0.0031056392,"about_ca_topic_score_gemma":0.005492373,"teacher_disagreement_score":0.0070725833,"about_ca_system_score_codex":0.0014968885,"about_ca_system_score_gemma":0.0035186468,"threshold_uncertainty_score":0.037403822},"labels":[],"label_agreement":null},{"id":"W4285249993","doi":"10.2991/assehr.k.220504.321","title":"A Review of JavaScript Object Notation in Data Analysis","year":2022,"lang":"en","type":"review","venue":"Advances in Social Science, Education and Humanities Research/Advances in social science, education and humanities research","topic":"Algorithms and Data Compression","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":"Queen's University","funders":"","keywords":"Computer science; JavaScript; Programming language; Notation; Object (grammar); Artificial intelligence; Mathematics; Arithmetic","score_opus":0.25593040097104797,"score_gpt":0.5436327883129625,"score_spread":0.2877023873419145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285249993","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014931975,0.98322695,0.0093339,0.0014811627,0.001062817,0.000045606877,0.00014223019,0.00015818366,0.004399878],"genre_scores_gemma":[0.0011587566,0.98281,0.011623393,0.0013348226,0.0010079667,0.00009303859,0.0002472365,0.00012969873,0.0015951401],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959377,0.0011272689,0.0008274092,0.00055522,0.0014289914,0.0001234851],"domain_scores_gemma":[0.9884857,0.00822229,0.0007076454,0.00040548487,0.0019815145,0.00019738558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055959797,0.0013224953,0.0016965551,0.0084362235,0.0006336799,0.003155995,0.0021914272,0.0017209019,0.0042733382],"category_scores_gemma":[0.0131662125,0.0009843741,0.0015370847,0.014071531,0.0020039196,0.0048518335,0.0014452003,0.0030917563,0.004990074],"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":[0.000042670865,0.000067627596,0.0005644667,0.018626753,0.00009829422,0.00012554566,0.00028362905,0.0005370008,0.00094340084,0.020955428,0.060201377,0.89755374],"study_design_scores_gemma":[0.0000071814775,0.000031153024,0.00063579844,0.0053197453,0.000055652814,0.00039677008,0.00007863551,0.0002399301,0.00052516593,0.0058669355,0.9868053,0.000037797254],"about_ca_topic_score_codex":0.0034521634,"about_ca_topic_score_gemma":0.0031224296,"teacher_disagreement_score":0.0084362235,"about_ca_system_score_codex":0.0014238626,"about_ca_system_score_gemma":0.0038688597,"threshold_uncertainty_score":0.02959472},"labels":[],"label_agreement":null},{"id":"W4285580083","doi":"10.4230/lipics.sea.2022.16","title":"RLBWT Tricks","year":2021,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Row; Permutation (music); Table (database); Constant (computer programming); Computer science; Speedup; Limiting; Algorithm; Rank (graph theory); Compression (physics); Computation; Combinatorics; Parallel computing; Mathematics; Database; Physics; Programming language","score_opus":0.020076732669350592,"score_gpt":0.2675891314586799,"score_spread":0.24751239878932932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285580083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057382914,0.0016815297,0.9347969,0.0017101157,0.0009978195,0.00028199411,0.0010387017,0.013870842,0.039883826],"genre_scores_gemma":[0.076872215,0.0015871566,0.8707255,0.0021209822,0.0008658423,0.0008342187,0.0027644385,0.007935609,0.03629399],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99558014,0.0006809812,0.00037688404,0.000709777,0.0021343436,0.0005178048],"domain_scores_gemma":[0.99576557,0.0012071863,0.00016635554,0.0022366561,0.0005205549,0.000103750885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022038722,0.0016983463,0.0014818142,0.0025110096,0.0015353624,0.0036589894,0.0040696277,0.0016039297,0.054098334],"category_scores_gemma":[0.012099604,0.0011477382,0.0022785703,0.003646444,0.0018199693,0.0085975155,0.0079677785,0.0051927366,0.033048112],"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":[0.0004696033,0.00020019188,0.0005613621,0.0006092996,0.000092135655,0.00040746396,0.0003965204,0.0055126958,0.011782973,0.34757987,0.11287424,0.51951367],"study_design_scores_gemma":[0.00032707507,0.0002104612,0.00045243456,0.0002501411,0.00009607767,0.0016618117,0.0002401675,0.10340893,0.029471403,0.56010526,0.30363265,0.0001435593],"about_ca_topic_score_codex":0.0013117453,"about_ca_topic_score_gemma":0.0013647232,"teacher_disagreement_score":0.054098334,"about_ca_system_score_codex":0.0012037256,"about_ca_system_score_gemma":0.0011460547,"threshold_uncertainty_score":0.18097699},"labels":[],"label_agreement":null},{"id":"W4286449765","doi":"10.18280/isi.270319","title":"Cryptography and Reference Sequence Based DNA/RNA Sequence Compression Algorithms","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lossless compression; Lossy compression; Algorithm; Compression ratio; Computer science; Data compression; Hash function; Compression (physics); Data compression ratio; Cryptography; Sequence (biology); Theoretical computer science; Image compression; Artificial intelligence; Physics","score_opus":0.03546943030200968,"score_gpt":0.2581358804469704,"score_spread":0.22266645014496073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286449765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027742246,0.006050767,0.95601064,0.00069901475,0.0003001167,0.00017197114,0.00016959666,0.0012095892,0.0076461043],"genre_scores_gemma":[0.32582712,0.0046082367,0.65172887,0.00059706974,0.0005083109,0.00029637764,0.0008933237,0.00021916466,0.015321556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827576,0.00025470744,0.00010680028,0.0002295321,0.0010122836,0.000121008576],"domain_scores_gemma":[0.99780303,0.0007070008,0.00028951457,0.000681053,0.00046961542,0.00004983842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011278812,0.0007176758,0.00055192155,0.0021799973,0.0005857046,0.0011478405,0.0014388497,0.0011661702,0.0039066155],"category_scores_gemma":[0.004153172,0.00029567367,0.000572775,0.0020150093,0.0010939946,0.002770748,0.0012466534,0.0014634075,0.002142298],"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":[0.0008005751,0.0001621378,0.0010895916,0.00060466956,0.00009522304,0.00037368695,0.0002884735,0.041797463,0.096301734,0.14873956,0.005075163,0.70467186],"study_design_scores_gemma":[0.0002024171,0.0012363878,0.0017566774,0.00030956836,0.00012274232,0.0052790716,0.0001770391,0.3751673,0.4730483,0.06659716,0.07592105,0.00018223506],"about_ca_topic_score_codex":0.00041370143,"about_ca_topic_score_gemma":0.00037206247,"teacher_disagreement_score":0.0039066155,"about_ca_system_score_codex":0.0008440719,"about_ca_system_score_gemma":0.0006960455,"threshold_uncertainty_score":0.013068914},"labels":[],"label_agreement":null},{"id":"W4286981455","doi":"10.5281/zenodo.5497475","title":"Design of Effective Lossless Data Compression Technique for Multiple Genomic DNA Sequences","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"École de Technologie Supérieure","funders":"","keywords":"Lossless compression; Computer science; Compression (physics); Data compression; Computational biology; DNA; Biology; Genetics; Algorithm; Materials science","score_opus":0.070212820007856,"score_gpt":0.2792934986412024,"score_spread":0.2090806786333464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286981455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013535852,0.0005325691,0.98338175,0.0001758489,0.000057961883,0.00006997268,0.000057975205,0.0005240734,0.0016639715],"genre_scores_gemma":[0.25692287,0.00081919064,0.73644453,0.00024801272,0.00010235718,0.00027917017,0.00037800442,0.00007613587,0.004729742],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971765,0.000037368078,0.000019392683,0.000070832466,0.00013267579,0.000022030332],"domain_scores_gemma":[0.9996997,0.00007211464,0.000046836343,0.000039426504,0.00012769437,0.000014292631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034808603,0.000549125,0.00039756653,0.0005546583,0.00032622856,0.00070836593,0.0009327737,0.0005672543,0.0019719903],"category_scores_gemma":[0.00069367123,0.00023569001,0.0003359732,0.00041278434,0.00026851895,0.00059639243,0.0003443801,0.0003586855,0.0012732022],"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":[0.000390998,0.00009026546,0.00081733154,0.00027569215,0.00007851537,0.00022648358,0.00015136685,0.020826537,0.49065116,0.013268597,0.00490428,0.4683188],"study_design_scores_gemma":[0.000080374106,0.00069617154,0.0010029987,0.000048248865,0.000105822095,0.0014298756,0.000059081365,0.52210885,0.447612,0.0036807004,0.02313164,0.000044230157],"about_ca_topic_score_codex":0.00038646202,"about_ca_topic_score_gemma":0.0005278805,"teacher_disagreement_score":0.0019719903,"about_ca_system_score_codex":0.00040040186,"about_ca_system_score_gemma":0.0004902857,"threshold_uncertainty_score":0.0065969825},"labels":[],"label_agreement":null},{"id":"W4287549685","doi":"10.5281/zenodo.4386962","title":"Demonstrating the utility of flexible sequence queries against indexed short reads with FlexTyper","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"","keywords":"Sequence (biology); Computer science; Information retrieval; Biology; Genetics","score_opus":0.0796312605441998,"score_gpt":0.2603976221947847,"score_spread":0.18076636165058488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287549685","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034890823,0.0012095292,0.345814,0.00322517,0.0018373416,0.0007282856,0.2346662,0.35625002,0.021378662],"genre_scores_gemma":[0.130307,0.000705825,0.501933,0.0035784584,0.00029428492,0.001958476,0.24942695,0.10128101,0.010515071],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99239975,0.002114854,0.0011348539,0.0015180034,0.0024168564,0.00041567063],"domain_scores_gemma":[0.9833477,0.011947069,0.0005584517,0.0024005782,0.0013970396,0.0003490729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010528237,0.002349004,0.0012578856,0.0015213955,0.001312535,0.0032292968,0.003979591,0.0023501273,0.06905813],"category_scores_gemma":[0.029941585,0.0011833683,0.002316965,0.0023998853,0.00089486624,0.0034166607,0.0028785465,0.0030570535,0.046713077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0072983503,0.0004962193,0.013692755,0.0057640816,0.00095763063,0.0021894767,0.0015412843,0.030266223,0.082005195,0.017778711,0.6638716,0.17413853],"study_design_scores_gemma":[0.0018505506,0.0012625987,0.014071684,0.00126777,0.00026341918,0.002586183,0.0014749059,0.32871053,0.2776985,0.03920607,0.33064902,0.00095873873],"about_ca_topic_score_codex":0.004109166,"about_ca_topic_score_gemma":0.0061190943,"teacher_disagreement_score":0.06905813,"about_ca_system_score_codex":0.00090834167,"about_ca_system_score_gemma":0.0022532116,"threshold_uncertainty_score":0.23102242},"labels":[],"label_agreement":null},{"id":"W4290660596","doi":"10.1089/cmb.2021.0520","title":"Computing Maximal Covers for Protein Sequences","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Substring; Cover (algebra); String (physics); Context (archaeology); Computer science; Software; Fragment (logic); Sequence (biology); Theoretical computer science; Biology; Algorithm; Mathematics; Data structure; Genetics; Programming language; Engineering","score_opus":0.021160806813030897,"score_gpt":0.2910424347732892,"score_spread":0.26988162796025833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290660596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19461569,0.0014394232,0.7853441,0.00038506894,0.00007027006,0.00013010208,0.004173029,0.0079176435,0.005924541],"genre_scores_gemma":[0.465532,0.00073699217,0.5139869,0.00020855221,0.00013137923,0.0003334289,0.014484532,0.0013972803,0.0031890208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986852,0.00023371214,0.0001114595,0.00033293405,0.0004907498,0.00014598995],"domain_scores_gemma":[0.99660134,0.0022054554,0.0002531191,0.0005398432,0.0002757641,0.00012442803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009878475,0.00095813384,0.0011304682,0.002669867,0.0008003417,0.0016148307,0.0011013678,0.0011959336,0.004591714],"category_scores_gemma":[0.009361102,0.0006852758,0.0013528082,0.0027062704,0.0010401461,0.0038043167,0.0023765652,0.0008065822,0.0016297766],"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":[0.0018240652,0.0001506955,0.012896297,0.001599775,0.000326553,0.0008819152,0.0013979207,0.32416558,0.039569393,0.09619051,0.02684402,0.4941533],"study_design_scores_gemma":[0.0000568112,0.00018153944,0.0016447044,0.00011800936,0.000059363403,0.000634087,0.0003138846,0.7622413,0.030568622,0.18967764,0.014460875,0.00004316535],"about_ca_topic_score_codex":0.0008881722,"about_ca_topic_score_gemma":0.0014399608,"teacher_disagreement_score":0.004591714,"about_ca_system_score_codex":0.0008426403,"about_ca_system_score_gemma":0.0010059442,"threshold_uncertainty_score":0.015360773},"labels":[],"label_agreement":null},{"id":"W4291000643","doi":"10.1101/2022.08.09.503358","title":"MONI- <i>k</i> : An index for efficient pangenome-to-pangenome comparison","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Microelectromechanical systems; Substring; Index (typography); Genome; Algorithm; Computer science; Mathematics; Physics; Materials science; Nanotechnology; Biology; Data structure; Genetics; Gene; Programming language","score_opus":0.023632132179778907,"score_gpt":0.25738832418455276,"score_spread":0.23375619200477385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291000643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10652469,0.0025563156,0.8463584,0.0010215185,0.00046964805,0.00032019702,0.011849402,0.020225937,0.010673839],"genre_scores_gemma":[0.21287501,0.00043715833,0.76736355,0.00027357598,0.00020253399,0.00042738236,0.013981532,0.0017944382,0.0026448197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832207,0.00028229743,0.00030333412,0.00038883442,0.00052233157,0.00018109506],"domain_scores_gemma":[0.9950251,0.0013294533,0.0006539712,0.0018806228,0.00079706486,0.00031379663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018763944,0.00074178714,0.0014051809,0.0046798787,0.0010492421,0.0024790366,0.002028638,0.0008715114,0.0045179604],"category_scores_gemma":[0.012902957,0.0004797749,0.00069424923,0.005689032,0.0009043473,0.004451838,0.0031432556,0.0011036289,0.002865962],"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":[0.0027384346,0.00034696527,0.01654615,0.0012654444,0.00023803156,0.00040303354,0.00068729796,0.018488683,0.08313987,0.09286544,0.07163141,0.71164936],"study_design_scores_gemma":[0.00021416877,0.000768748,0.011602443,0.00032936988,0.00017246569,0.001955848,0.0008009465,0.48734415,0.142428,0.20766182,0.14646281,0.00025917316],"about_ca_topic_score_codex":0.00090835895,"about_ca_topic_score_gemma":0.0017132383,"teacher_disagreement_score":0.0046798787,"about_ca_system_score_codex":0.0011754485,"about_ca_system_score_gemma":0.0016766909,"threshold_uncertainty_score":0.015114129},"labels":[],"label_agreement":null},{"id":"W4291319443","doi":"10.48550/arxiv.1605.06615","title":"Efficient and Compact Representations of Some Non-Canonical Prefix-Free Codes","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Xunta de Galicia; European Commission; Gruppo Nazionale per il Calcolo Scientifico; Universidade da Coruña; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; Agencia Nacional de Investigación y Desarrollo; Helsingin Yliopisto","keywords":"Prefix code; Code word; Prefix; Lexicographical order; Word (group theory); Code (set theory); Combinatorics; Mathematics; Constant (computer programming); Alphabet; Order (exchange); Decoding methods; Discrete mathematics; Binary logarithm; ENCODE; Sigma; Encoding (memory); Computer science; Algorithm; Linear code; Physics; Block code","score_opus":0.053019039424823555,"score_gpt":0.215923996379469,"score_spread":0.16290495695464544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291319443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0879034,0.00083113153,0.8909877,0.00082373846,0.00023509454,0.0001425325,0.0012096859,0.0015783225,0.016288407],"genre_scores_gemma":[0.4733038,0.001095493,0.50884104,0.00045108612,0.0002297554,0.00049776235,0.002616338,0.0005071284,0.012457686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986952,0.00020196408,0.00010922787,0.00018417418,0.0006084641,0.00020101617],"domain_scores_gemma":[0.99746346,0.000623916,0.00024584195,0.00081551657,0.0007515893,0.00009962606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056597573,0.00069547107,0.0005598192,0.0011448517,0.00058297114,0.0017079049,0.0010019429,0.0007611097,0.003336209],"category_scores_gemma":[0.004887757,0.00033550317,0.00043801972,0.0020246028,0.0009820636,0.002692408,0.0011810485,0.0015507429,0.001310129],"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":[0.00038214173,0.00012244668,0.0006982553,0.00020552987,0.000027198426,0.00039773833,0.00038837787,0.0899126,0.024065912,0.6788635,0.0102817435,0.19465454],"study_design_scores_gemma":[0.000090150395,0.00022463429,0.00033797036,0.00007675989,0.00003557781,0.0005743781,0.00017620032,0.48373744,0.0330525,0.4544351,0.027167173,0.00009213752],"about_ca_topic_score_codex":0.0012541858,"about_ca_topic_score_gemma":0.0019944953,"teacher_disagreement_score":0.003336209,"about_ca_system_score_codex":0.0008726399,"about_ca_system_score_gemma":0.0015614273,"threshold_uncertainty_score":0.011160791},"labels":[],"label_agreement":null},{"id":"W4292961172","doi":"10.1093/bioinformatics/btac564","title":"ntHash2: recursive spaced seed hashing for nucleotide sequences","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","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":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health","keywords":"Hash function; Computer science; Dynamic perfect hashing; Universal hashing; Sequence (biology); Linear hashing; Algorithm; Hash table; Theoretical computer science; Perfect hash function; Double hashing; Biology; Genetics; Programming language","score_opus":0.022581972130463614,"score_gpt":0.25195325326204365,"score_spread":0.22937128113158003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292961172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030408397,0.00085474347,0.9366002,0.00021866671,0.00030201455,0.00026509236,0.002947528,0.024628434,0.0037750888],"genre_scores_gemma":[0.21274559,0.00035026605,0.7678595,0.00021578114,0.00010773331,0.0004405181,0.008409044,0.0021054603,0.0077660847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988795,0.00017886465,0.00010832066,0.00024280767,0.0005035585,0.00008686992],"domain_scores_gemma":[0.9982431,0.0004753008,0.00013888856,0.0006269772,0.0003962083,0.000119645636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011736227,0.00079421065,0.0007444144,0.0009913014,0.0006988385,0.0010551,0.0019822773,0.00078646815,0.00946551],"category_scores_gemma":[0.0062016323,0.0005283648,0.000631374,0.0014721763,0.00081626466,0.0020252457,0.0023827767,0.00092418387,0.007543378],"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":[0.002676787,0.00018449883,0.007167232,0.0011847613,0.00015096345,0.00042157678,0.0007402276,0.038655747,0.13678755,0.041584693,0.07070463,0.6997413],"study_design_scores_gemma":[0.00040041868,0.0006469808,0.0029357204,0.00014613521,0.000069172056,0.0013916076,0.00026307398,0.61319715,0.23794708,0.05439419,0.08838964,0.00021887789],"about_ca_topic_score_codex":0.0014817521,"about_ca_topic_score_gemma":0.0023990853,"teacher_disagreement_score":0.00946551,"about_ca_system_score_codex":0.0006495165,"about_ca_system_score_gemma":0.0014081937,"threshold_uncertainty_score":0.031665325},"labels":[],"label_agreement":null},{"id":"W4293568415","doi":"10.1007/978-3-642-27848-8_631-1","title":"Orthogonal Range Searching on Discrete Grids","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Range (aeronautics); Computer science; Computational science; Engineering; Aerospace engineering","score_opus":0.013828863155994233,"score_gpt":0.2463296812034269,"score_spread":0.23250081804743267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293568415","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02378719,0.0025657772,0.92254597,0.0003224983,0.00024690607,0.000043990603,0.00018330327,0.00088096154,0.049423385],"genre_scores_gemma":[0.31029448,0.004515061,0.6460999,0.00020179695,0.00021160304,0.0001445441,0.0006898046,0.0004940781,0.037348654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99974316,0.000045933753,0.000014568657,0.000032468295,0.00013818375,0.000025722087],"domain_scores_gemma":[0.99970824,0.0001421476,0.000017840266,0.000073577525,0.000042148706,0.000015933847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017811023,0.000315399,0.0006211885,0.00059126015,0.00022739673,0.0007169716,0.00068223657,0.00031710372,0.007203684],"category_scores_gemma":[0.0012043151,0.00023705912,0.00020337578,0.0015906708,0.00052911066,0.0011434414,0.0015122073,0.0006943938,0.0015812289],"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":[0.0001633061,0.000050444763,0.00031179245,0.00033033034,0.00001899008,0.00009422516,0.00012283595,0.10969149,0.010876014,0.29346594,0.019046485,0.56582814],"study_design_scores_gemma":[0.00005355929,0.000059345377,0.00023582211,0.00006105916,0.0000097804,0.00032708762,0.00007948168,0.7360143,0.00682302,0.21928889,0.037022896,0.000024852385],"about_ca_topic_score_codex":0.0006229865,"about_ca_topic_score_gemma":0.0005834461,"teacher_disagreement_score":0.007203684,"about_ca_system_score_codex":0.00028761593,"about_ca_system_score_gemma":0.0003090544,"threshold_uncertainty_score":0.024098754},"labels":[],"label_agreement":null},{"id":"W4293833158","doi":"","title":"A Central Limit Theorem for the Length of the Longest Common Subsequence in Random Words","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Longest increasing subsequence; Limit (mathematics); Longest common subsequence problem; Subsequence; Central limit theorem; Mathematics; Combinatorics; Discrete mathematics; Statistics; Mathematical analysis","score_opus":0.02277497908642127,"score_gpt":0.2591781459211234,"score_spread":0.23640316683470217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293833158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025920518,0.0032758838,0.96198696,0.001144621,0.0003135028,0.00012617,0.00035016748,0.00048238895,0.0063997977],"genre_scores_gemma":[0.65684557,0.008653063,0.30554205,0.002411855,0.0029451966,0.003233754,0.0015112828,0.0011297088,0.017727548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99201703,0.0027623526,0.00044421348,0.0018426452,0.0021196525,0.0008141344],"domain_scores_gemma":[0.92096907,0.06004979,0.004245207,0.00492013,0.007767723,0.0020481448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021061763,0.0017398363,0.0028822443,0.0060062627,0.0021212315,0.0054076104,0.005783259,0.0027283358,0.006920237],"category_scores_gemma":[0.0933056,0.0012700054,0.0029494774,0.0050853468,0.009700039,0.011785866,0.0046442547,0.006052853,0.0020018304],"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":[0.00015773758,0.00006658011,0.0013530429,0.0002984773,0.00013126647,0.00029569396,0.0005009891,0.016741017,0.001983249,0.96047246,0.0018157936,0.01618372],"study_design_scores_gemma":[0.000101231606,0.00016003495,0.0009320368,0.00016318669,0.00007979035,0.00043925035,0.00012616934,0.2088711,0.0021708782,0.78253055,0.0043135737,0.000112129615],"about_ca_topic_score_codex":0.0022833983,"about_ca_topic_score_gemma":0.0015012758,"teacher_disagreement_score":0.021061763,"about_ca_system_score_codex":0.003637592,"about_ca_system_score_gemma":0.00449162,"threshold_uncertainty_score":0.1113866},"labels":[],"label_agreement":null},{"id":"W4294770181","doi":"10.1016/j.tcs.2022.08.024","title":"Flip-swap languages in binary reflected Gray code order","year":2022,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Swap (finance); Prefix; Gray code; Combinatorics; Mathematics; Binary number; Arithmetic; Discrete mathematics; Computer science; Algorithm; Linguistics","score_opus":0.00985672457405275,"score_gpt":0.2807230356109046,"score_spread":0.2708663110368519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294770181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4483702,0.00048415246,0.47773412,0.0013815924,0.00031688224,0.00022342746,0.0005049059,0.0016240354,0.0693607],"genre_scores_gemma":[0.91453314,0.0002952692,0.060030278,0.0005973675,0.00010144837,0.00019018432,0.00025311485,0.0004474964,0.02355171],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999172,0.0001942778,0.00006767863,0.00009733545,0.00025596828,0.0002128428],"domain_scores_gemma":[0.9978667,0.00095325796,0.00018303895,0.000490399,0.00036257206,0.00014408233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077027665,0.000332499,0.0004763826,0.0009437199,0.0009836362,0.0023572484,0.0007191498,0.0008342059,0.007168664],"category_scores_gemma":[0.0033991425,0.00027666337,0.0004907659,0.0011737953,0.0019729168,0.002975856,0.0013576432,0.0015561078,0.0010117013],"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":[0.00011382866,0.00004031366,0.00014195661,0.00003508496,0.000004054567,0.000098565375,0.00021823912,0.006495161,0.0028372388,0.975037,0.0013650266,0.013613514],"study_design_scores_gemma":[0.000034373836,0.00007001604,0.00010489534,0.00003316151,0.000009678662,0.00013087332,0.000101066944,0.042066656,0.007007978,0.94567347,0.004737073,0.000030835967],"about_ca_topic_score_codex":0.00094250956,"about_ca_topic_score_gemma":0.0012385165,"teacher_disagreement_score":0.007168664,"about_ca_system_score_codex":0.0011227193,"about_ca_system_score_gemma":0.0012628452,"threshold_uncertainty_score":0.023981512},"labels":[],"label_agreement":null},{"id":"W4294904134","doi":"10.14778/3547305.3547321","title":"Improving matrix-vector multiplication via lossless grammar-compressed matrices","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Lossless compression; Computer science; Matrix (chemical analysis); Algorithm; Matrix multiplication; Linear algebra; Data compression ratio; Data compression; Theoretical computer science; Mathematics; Image compression; Artificial intelligence; Image processing","score_opus":0.008123292950760374,"score_gpt":0.222613248707195,"score_spread":0.21448995575643465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294904134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069741935,0.0006324595,0.91415507,0.00051469763,0.0001481108,0.00013098786,0.00048939773,0.0096247215,0.0045625614],"genre_scores_gemma":[0.37059373,0.00050469977,0.6182547,0.00035887994,0.0001763467,0.00022577867,0.0019636054,0.0009036587,0.007018499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987173,0.00018591671,0.00007035677,0.00016099634,0.0007443072,0.00012114433],"domain_scores_gemma":[0.9977029,0.0008188065,0.00018202547,0.0007477517,0.0004715554,0.00007704166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006714058,0.0010308675,0.00057863473,0.0011443065,0.0005004141,0.0010909396,0.0011368255,0.0005480724,0.004060425],"category_scores_gemma":[0.0049965107,0.00025869216,0.00043061867,0.0015969899,0.00088942004,0.0031196184,0.0015542014,0.0011386664,0.0019203529],"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":[0.0010241633,0.00034790064,0.0016089373,0.00043566892,0.00007487089,0.00049830787,0.00047741595,0.10054779,0.12282374,0.070163995,0.020889066,0.6811082],"study_design_scores_gemma":[0.00012360334,0.00041720906,0.0006147608,0.00004099345,0.000036778474,0.00057130505,0.00016201925,0.7710693,0.16792466,0.04370766,0.015287629,0.000044076292],"about_ca_topic_score_codex":0.0020212221,"about_ca_topic_score_gemma":0.00314099,"teacher_disagreement_score":0.004060425,"about_ca_system_score_codex":0.0006304985,"about_ca_system_score_gemma":0.0012227811,"threshold_uncertainty_score":0.013583422},"labels":[],"label_agreement":null},{"id":"W4296665498","doi":"","title":"IMPROVED ALGORITHMS FOR THE RANGE NEXT VALUE PROBLEM AND APPLICATIONS","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Bangladesh University of Engineering and Technology; Commonwealth Scholarship Commission; Engineering and Physical Sciences Research Council; McMaster University","keywords":"Computer science; Range (aeronautics); Algorithm; Value (mathematics); Materials science; Machine learning","score_opus":0.0342351237147538,"score_gpt":0.2603761640192419,"score_spread":0.22614104030448812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296665498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008921186,0.0018621867,0.9748266,0.0012406002,0.00029802986,0.000211432,0.00022482917,0.0019274163,0.01048774],"genre_scores_gemma":[0.08814483,0.0007661464,0.9016661,0.00055825367,0.00046801707,0.00046998487,0.0009895844,0.0005604471,0.0063766763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926864,0.0021564676,0.0004609269,0.0014214361,0.0025619152,0.0007128525],"domain_scores_gemma":[0.9905261,0.0051256833,0.00042442392,0.002140284,0.0015463904,0.00023718238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003611297,0.0015579469,0.0025605701,0.0028858713,0.0011710598,0.003068925,0.0049640345,0.0028440184,0.016811306],"category_scores_gemma":[0.022492038,0.0009277252,0.002120181,0.005250342,0.001506759,0.0081736455,0.0049356124,0.005336276,0.0041283593],"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":[0.00068175764,0.00068892154,0.001215083,0.00062479137,0.00011996818,0.00017225585,0.00039784968,0.13858022,0.0048403507,0.20180534,0.047989126,0.6028843],"study_design_scores_gemma":[0.00024188613,0.00010120529,0.00045318325,0.00008071669,0.000044938195,0.0002792439,0.000099051314,0.76107997,0.0026859313,0.21499872,0.019893605,0.000041610372],"about_ca_topic_score_codex":0.0037581301,"about_ca_topic_score_gemma":0.0038421424,"teacher_disagreement_score":0.016811306,"about_ca_system_score_codex":0.0026678792,"about_ca_system_score_gemma":0.0019031224,"threshold_uncertainty_score":0.056239426},"labels":[],"label_agreement":null},{"id":"W4297018352","doi":"10.32920/14638791.v2","title":"Efficient computation of spaced seeds","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Heuristic; Computer science; Software; Computation; Quadratic equation; Algorithm; Speedup; Range (aeronautics); Theoretical computer science; Artificial intelligence; Mathematics; Parallel computing; Programming language; Engineering","score_opus":0.020819351019854975,"score_gpt":0.27875347953564006,"score_spread":0.25793412851578507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297018352","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06591887,0.00036073415,0.9244197,0.0002005087,0.000115515526,0.000088195775,0.00024102614,0.0038823318,0.0047731753],"genre_scores_gemma":[0.29123825,0.00017723379,0.7044048,0.0000987022,0.000046836816,0.0001356075,0.0006690567,0.001013996,0.0022155016],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862754,0.00024792043,0.00009295226,0.0002656543,0.00064655626,0.00011936922],"domain_scores_gemma":[0.995038,0.0025670466,0.00040061647,0.000769622,0.0009517767,0.00027297012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012610994,0.0010385796,0.0013924649,0.002056562,0.000986635,0.0016896294,0.001865061,0.0014305495,0.007564401],"category_scores_gemma":[0.012812785,0.0006985146,0.0008011349,0.0021450785,0.0011013293,0.0025691434,0.0018095813,0.001149893,0.0022675272],"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":[0.000748077,0.00021877418,0.0062725893,0.0006438884,0.00012377319,0.0008607506,0.0005764902,0.48959586,0.042377938,0.12910123,0.014622221,0.31485838],"study_design_scores_gemma":[0.000055397613,0.00009262493,0.0004531713,0.000029695953,0.00001826861,0.00022022276,0.000050760613,0.9054395,0.013778127,0.07523031,0.0046050115,0.000026953026],"about_ca_topic_score_codex":0.0013689643,"about_ca_topic_score_gemma":0.0015481949,"teacher_disagreement_score":0.007564401,"about_ca_system_score_codex":0.0011088179,"about_ca_system_score_gemma":0.0014048391,"threshold_uncertainty_score":0.02530545},"labels":[],"label_agreement":null},{"id":"W4297821307","doi":"10.4230/lipics.itcs.2023.73","title":"Recovery from Non-Decomposable Distance Oracles","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Hamming distance; Sequence (biology); Edit distance; Mathematics; Combinatorics; Earth mover's distance; Function (biology); Dynamic time warping; Set (abstract data type); Estimator; Alphabet; Distance measures; Algorithm; Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.046217412863475284,"score_gpt":0.1844938963805448,"score_spread":0.13827648351706953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297821307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107004374,0.0019579341,0.8740222,0.005307029,0.0002676015,0.0002414463,0.002348704,0.003693438,0.0051572565],"genre_scores_gemma":[0.8286609,0.0008560409,0.15715066,0.0016419216,0.0003683806,0.0002983032,0.0041767843,0.000556561,0.00629048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.983312,0.005027822,0.0015834147,0.0045015262,0.0040532653,0.0015220387],"domain_scores_gemma":[0.9242228,0.049053486,0.0035247495,0.019489713,0.0024369014,0.0012723572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007895469,0.0021542145,0.003502134,0.0013815206,0.0014666043,0.0035860175,0.0055521335,0.005185606,0.005477051],"category_scores_gemma":[0.07709054,0.0010050102,0.0014566428,0.0027127066,0.0029523377,0.01422655,0.008823491,0.007845371,0.0022781563],"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":[0.004275698,0.00071475276,0.0077334377,0.001802645,0.00040601642,0.0017841398,0.0017168003,0.2866693,0.019854907,0.31696042,0.027497813,0.33058414],"study_design_scores_gemma":[0.00019380162,0.0002601517,0.00082287414,0.0001237155,0.00006376526,0.0009709827,0.00040891848,0.5512528,0.012437862,0.42899725,0.0043841503,0.00008372797],"about_ca_topic_score_codex":0.0012726809,"about_ca_topic_score_gemma":0.0012069299,"teacher_disagreement_score":0.007895469,"about_ca_system_score_codex":0.0022625765,"about_ca_system_score_gemma":0.0025488154,"threshold_uncertainty_score":0.041755736},"labels":[],"label_agreement":null},{"id":"W4298348569","doi":"","title":"A simple algorithm for computing the lempel ziv factorization","year":2008,"lang":"en","type":"preprint","venue":"Murdoch Research Repository (Murdoch University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Simple (philosophy); Algorithm; Factorization; Algorithm design; Theoretical computer science","score_opus":0.0710573492295642,"score_gpt":0.3180441600262308,"score_spread":0.24698681079666662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298348569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006758092,0.00054328464,0.9780864,0.00035669626,0.00021694598,0.00028963186,0.0006315611,0.0048445314,0.008272788],"genre_scores_gemma":[0.089971624,0.00034883572,0.8974664,0.000380877,0.00016094082,0.0005879733,0.0023496726,0.0005690111,0.008164634],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998324,0.00022568746,0.00013189958,0.00033145287,0.00070280954,0.00028422626],"domain_scores_gemma":[0.99845624,0.00050030876,0.00010409197,0.0004992871,0.00036758636,0.00007242333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009005046,0.001603154,0.0014240919,0.0021420931,0.0013191146,0.0017437488,0.0014692477,0.0016062411,0.026500333],"category_scores_gemma":[0.006019435,0.0005516015,0.0013417496,0.0022172357,0.0010933423,0.0034158244,0.0032760687,0.0018763007,0.013896053],"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":[0.00050142745,0.00020144587,0.00069659774,0.00059025176,0.00008125089,0.00029444654,0.00034170502,0.013790552,0.03676589,0.0952419,0.038421184,0.81307334],"study_design_scores_gemma":[0.000507644,0.00065120903,0.0014155997,0.00025344602,0.00013761026,0.0017048933,0.00046593015,0.24292548,0.07362906,0.57371396,0.10432536,0.00026985377],"about_ca_topic_score_codex":0.0011984468,"about_ca_topic_score_gemma":0.0021055208,"teacher_disagreement_score":0.026500333,"about_ca_system_score_codex":0.0010281125,"about_ca_system_score_gemma":0.0015074299,"threshold_uncertainty_score":0.08865249},"labels":[],"label_agreement":null},{"id":"W4298392132","doi":"10.1007/978-3-031-01885-5_2","title":"External Construction of Suffix Trees","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Generalized suffix tree; Suffix; Computer science; Suffix tree; Section (typography); Scalability; Compressed suffix array; Auxiliary memory; Algorithm; Theoretical computer science; Brute force; Data structure; Programming language; Database","score_opus":0.03614112577618683,"score_gpt":0.24932231780882308,"score_spread":0.21318119203263625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298392132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009582135,0.00071680895,0.8823618,0.00029316926,0.00054816424,0.00010022669,0.00074005034,0.004182188,0.10147533],"genre_scores_gemma":[0.14152685,0.0018372973,0.73454624,0.0003630179,0.0004909295,0.00033161437,0.0069815363,0.005323603,0.10859893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991743,0.00014116101,0.00007443097,0.00020974939,0.0003272228,0.00007312721],"domain_scores_gemma":[0.99873036,0.0003239103,0.000039980936,0.00055048027,0.00030111647,0.000054189517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070822693,0.0008323288,0.00073673006,0.0012370788,0.0011758041,0.0029815473,0.0014196715,0.0007986272,0.02735121],"category_scores_gemma":[0.0028698563,0.00073329505,0.0012562877,0.00244109,0.0013622891,0.003784735,0.003328614,0.0018678842,0.016416878],"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":[0.000094400246,0.000057692065,0.0003782185,0.0004605101,0.000034169556,0.0002218609,0.0004885879,0.004535416,0.017075047,0.5496728,0.026303954,0.40067738],"study_design_scores_gemma":[0.000027015212,0.0000676712,0.0003273591,0.0001980143,0.00005784687,0.0007298411,0.00016073571,0.030900916,0.040983252,0.5515384,0.3749656,0.000043392753],"about_ca_topic_score_codex":0.00021942407,"about_ca_topic_score_gemma":0.0003370958,"teacher_disagreement_score":0.02735121,"about_ca_system_score_codex":0.00060519803,"about_ca_system_score_gemma":0.0005420767,"threshold_uncertainty_score":0.09149885},"labels":[],"label_agreement":null},{"id":"W4298396669","doi":"10.48550/arxiv.2204.07327","title":"Data structures for computing unique palindromes in static and non-static strings","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Japan Society for the Promotion of Science; University of Waterloo","keywords":"Substring; Palindrome; String (physics); Combinatorics; Sigma; Algorithm; Data structure; Mathematics; Discrete mathematics; Physics; Computer science","score_opus":0.10538270996034702,"score_gpt":0.2377525895886624,"score_spread":0.1323698796283154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298396669","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17610691,0.0049573816,0.73741186,0.0031206592,0.00061265804,0.0010438913,0.028101776,0.037448894,0.011195896],"genre_scores_gemma":[0.30919382,0.00084017706,0.650374,0.0007252481,0.00024861644,0.0011569079,0.030004367,0.0016352814,0.00582155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968413,0.00023738334,0.0005516889,0.0010993314,0.00088074466,0.00038948262],"domain_scores_gemma":[0.9899154,0.0029961062,0.0011771228,0.004499689,0.001011181,0.00040055008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016284239,0.001735137,0.0025534967,0.0026981167,0.0019355309,0.0031182081,0.005283015,0.002139118,0.0097281085],"category_scores_gemma":[0.0106851645,0.0015118748,0.0024992789,0.007075015,0.0017041513,0.013478734,0.004998403,0.0032239305,0.0040364116],"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":[0.0037955232,0.0009292096,0.017048722,0.0036042286,0.00035946502,0.0008886846,0.002770316,0.036825534,0.047037102,0.17806152,0.0687394,0.63994026],"study_design_scores_gemma":[0.00095569174,0.0010359142,0.004712099,0.0005870345,0.00044402044,0.0016821676,0.0019406598,0.36311597,0.087084,0.43467832,0.103418656,0.00034551637],"about_ca_topic_score_codex":0.0027629882,"about_ca_topic_score_gemma":0.0068271197,"teacher_disagreement_score":0.0097281085,"about_ca_system_score_codex":0.0027490177,"about_ca_system_score_gemma":0.0040023914,"threshold_uncertainty_score":0.03254378},"labels":[],"label_agreement":null},{"id":"W4299119775","doi":"10.1007/978-3-642-27848-8_628-1","title":"Intersections of Inverted Lists","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.012987725323710736,"score_gpt":0.23064366175689216,"score_spread":0.21765593643318143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299119775","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0290235,0.009317925,0.4500739,0.001388052,0.0012258427,0.00024931063,0.0045192325,0.005211847,0.49899045],"genre_scores_gemma":[0.25516894,0.011937174,0.42147306,0.0008111845,0.0016743563,0.0004960175,0.016479962,0.0028139094,0.28914544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866045,0.00012447815,0.00010487371,0.0002888595,0.0006891905,0.00013211237],"domain_scores_gemma":[0.9984597,0.00048153385,0.0001320494,0.00032003887,0.00052903953,0.00007768287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043446565,0.0007861051,0.0008375978,0.004710116,0.001903937,0.004764988,0.0017243762,0.0008817649,0.045243785],"category_scores_gemma":[0.0033949278,0.00085206155,0.00075319386,0.0065236455,0.0013355224,0.008216133,0.0028272578,0.0019887828,0.017464833],"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":[0.000084163934,0.000037272548,0.00040957038,0.00030370458,0.000017462364,0.00015209934,0.00027605795,0.001666593,0.002227047,0.69021016,0.035339277,0.26927653],"study_design_scores_gemma":[0.000014398288,0.0000545604,0.00032572,0.00016293605,0.00002970525,0.00083924737,0.00024171661,0.008313049,0.00824019,0.67863333,0.30310297,0.00004219061],"about_ca_topic_score_codex":0.0007149047,"about_ca_topic_score_gemma":0.0009359969,"teacher_disagreement_score":0.045243785,"about_ca_system_score_codex":0.0011675956,"about_ca_system_score_gemma":0.0013389718,"threshold_uncertainty_score":0.1513555},"labels":[],"label_agreement":null},{"id":"W4299475857","doi":"10.1007/978-3-031-01885-5_1","title":"Structures for Indexing Substrings","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Substring; Search engine indexing; Computer science; Information retrieval; Programming language; Data structure","score_opus":0.06175335427616284,"score_gpt":0.2722009832694912,"score_spread":0.21044762899332836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299475857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007619075,0.015987044,0.83124256,0.001994725,0.00258208,0.00031859247,0.0037446816,0.009142503,0.12736876],"genre_scores_gemma":[0.068348244,0.014546532,0.753335,0.0011456806,0.002011529,0.0007406557,0.011505706,0.0031283745,0.14523832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989396,0.00010018779,0.00014729236,0.0002188914,0.00051400816,0.0000800329],"domain_scores_gemma":[0.99857545,0.00039322212,0.00008198279,0.0006301564,0.00026097446,0.00005820279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074930827,0.0013334595,0.0013318374,0.0045606378,0.0014048236,0.0046005603,0.0026335735,0.0011959221,0.03267192],"category_scores_gemma":[0.003680271,0.0009760016,0.0010967092,0.008771432,0.0021271533,0.009691102,0.0032520567,0.0020364637,0.019947438],"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":[0.000052237025,0.000034113807,0.00012908423,0.0005501024,0.000021336191,0.00006787382,0.00034470702,0.0011644473,0.0043274146,0.40945768,0.05557659,0.5282744],"study_design_scores_gemma":[0.00002445009,0.000055510092,0.00019584961,0.00029728765,0.000043086384,0.00047285,0.00014509544,0.0075480985,0.007721409,0.60713416,0.3763176,0.00004459451],"about_ca_topic_score_codex":0.00093658577,"about_ca_topic_score_gemma":0.0011854442,"teacher_disagreement_score":0.03267192,"about_ca_system_score_codex":0.0013577329,"about_ca_system_score_gemma":0.0010501952,"threshold_uncertainty_score":0.10929847},"labels":[],"label_agreement":null},{"id":"W4300128205","doi":"10.1007/978-3-031-01885-5","title":"Full-Text (Substring) Indexes in External Memory","year":2012,"lang":"en","type":"book","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Substring; Computer science; Type (biology); Natural language processing; Information retrieval; Data structure; Programming language; Biology","score_opus":0.031759205710675927,"score_gpt":0.25630779246615987,"score_spread":0.22454858675548395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300128205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018871753,0.034344524,0.707536,0.0011940738,0.0048183035,0.00022933871,0.003048449,0.023020504,0.20693707],"genre_scores_gemma":[0.09143351,0.016047629,0.41591927,0.00094265275,0.0022174842,0.00026975843,0.007229793,0.0059535513,0.45998645],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995192,0.000043268217,0.00006361126,0.00008001957,0.0002430983,0.000050820236],"domain_scores_gemma":[0.9991098,0.00024959157,0.000048356884,0.00031266708,0.00023273077,0.00004687209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043149496,0.0013571125,0.00095355127,0.0017679544,0.00058328017,0.0026704497,0.0017364946,0.00057708786,0.04549244],"category_scores_gemma":[0.0019189771,0.00048229127,0.00045556834,0.0048606107,0.000648335,0.0047009927,0.0015540133,0.00090183935,0.026771855],"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":[0.00021942442,0.000057657708,0.00019655522,0.0006108915,0.000036146434,0.00020447087,0.00013606974,0.0027389228,0.01994489,0.058789667,0.09621038,0.82085496],"study_design_scores_gemma":[0.000075636104,0.00019461718,0.000685325,0.0004377893,0.00010335913,0.0012452976,0.000121167715,0.0228303,0.09073034,0.14105162,0.74244523,0.00007937625],"about_ca_topic_score_codex":0.0005264462,"about_ca_topic_score_gemma":0.0007794073,"teacher_disagreement_score":0.04549244,"about_ca_system_score_codex":0.00057246257,"about_ca_system_score_gemma":0.00059414573,"threshold_uncertainty_score":0.15218735},"labels":[],"label_agreement":null},{"id":"W4300181884","doi":"10.1145/1328911.1328925","title":"Hierarchical bin buffering","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bin; Computer science; Mathematics; Theoretical computer science; Algorithm","score_opus":0.033526213156717014,"score_gpt":0.2591905613860787,"score_spread":0.2256643482293617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300181884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037994966,0.00085122156,0.93315923,0.0004135195,0.0002116467,0.00032575233,0.0013648234,0.013067845,0.012610949],"genre_scores_gemma":[0.32997462,0.0005046361,0.6514653,0.00046829082,0.00013562365,0.00037690054,0.0030260833,0.0007889427,0.013259604],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991443,0.0000791118,0.00008470888,0.00019404004,0.0003232994,0.00017454606],"domain_scores_gemma":[0.9978504,0.00048498414,0.00018786502,0.0009438149,0.00037935123,0.00015364274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056307175,0.0008607854,0.0008320565,0.0012473185,0.0011572461,0.0023926105,0.0025897475,0.0006642324,0.014852175],"category_scores_gemma":[0.0037543434,0.00046396817,0.00044170744,0.0030530496,0.0006191635,0.003881227,0.0032303713,0.0007732994,0.0036709548],"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":[0.0023924168,0.00041304014,0.005706862,0.0005022651,0.000093005445,0.0003027705,0.00068089325,0.04574272,0.058976498,0.10014649,0.053426832,0.7316162],"study_design_scores_gemma":[0.0002615404,0.0004373266,0.0027536044,0.00012846201,0.00010213763,0.00084993354,0.0006088454,0.65409005,0.11874171,0.11996105,0.10191223,0.00015309823],"about_ca_topic_score_codex":0.004242455,"about_ca_topic_score_gemma":0.004883753,"teacher_disagreement_score":0.014852175,"about_ca_system_score_codex":0.0011038991,"about_ca_system_score_gemma":0.0016403658,"threshold_uncertainty_score":0.04968542},"labels":[],"label_agreement":null},{"id":"W4300667769","doi":"10.1007/978-3-031-01885-5_3","title":"Scaling Up: When the Input Exceeds the Main Memory","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Suffix; String (physics); Computer science; Generalized suffix tree; Suffix tree; Auxiliary memory; Random access; Compressed suffix array; Algorithm; Scaling; Theoretical computer science; Parallel computing; Data structure; Mathematics; Programming language; Computer hardware","score_opus":0.04826054880005584,"score_gpt":0.250437980547949,"score_spread":0.20217743174789318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300667769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26718,0.015297204,0.37441766,0.008270953,0.0056437408,0.0008659441,0.0049199653,0.079094164,0.24431041],"genre_scores_gemma":[0.7630432,0.0042491783,0.11404228,0.0040163537,0.0017896474,0.0006461319,0.0035272457,0.012572868,0.096112974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988482,0.000090135014,0.000088611254,0.00028307777,0.0004913422,0.0001987013],"domain_scores_gemma":[0.99514455,0.0017569497,0.00020043335,0.0015650213,0.001040085,0.00029290232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008882851,0.0019689735,0.0015110946,0.0012690744,0.0011148338,0.0035503272,0.001948957,0.0017116397,0.03799129],"category_scores_gemma":[0.009914193,0.0010584374,0.0006763838,0.0017858539,0.0010769694,0.010882688,0.0027337603,0.002797139,0.011903581],"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":[0.0017065962,0.0003154406,0.0045244824,0.0011315435,0.00006529636,0.0022460239,0.0012339439,0.010083857,0.2156731,0.02553831,0.096442595,0.6410387],"study_design_scores_gemma":[0.0001704721,0.0009604744,0.009154959,0.0010575668,0.00025286034,0.0040448285,0.0017825724,0.20116323,0.3984038,0.12581408,0.2569084,0.00028678201],"about_ca_topic_score_codex":0.00094487163,"about_ca_topic_score_gemma":0.0010578719,"teacher_disagreement_score":0.03799129,"about_ca_system_score_codex":0.0007476987,"about_ca_system_score_gemma":0.000787317,"threshold_uncertainty_score":0.1270935},"labels":[],"label_agreement":null},{"id":"W4300785191","doi":"","title":"A d-step approach to the maximum number of distinct Squares and runs in strings","year":2014,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Combinatorics; Algorithm; Computer science","score_opus":0.010689480337099093,"score_gpt":0.23688023521318313,"score_spread":0.22619075487608403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300785191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002388303,0.00019427932,0.9941233,0.0002937587,0.00005838644,0.000042682306,0.000078480596,0.00036086584,0.0024600313],"genre_scores_gemma":[0.039180703,0.00022346634,0.9541333,0.00032782674,0.000121223275,0.00020027974,0.00025204843,0.00036216088,0.0051989947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961593,0.001520813,0.00030429693,0.000641555,0.001164252,0.00020980964],"domain_scores_gemma":[0.9889683,0.0069805793,0.00022741634,0.0023111477,0.0012404824,0.0002720525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030994418,0.0013620523,0.0012342981,0.002730725,0.0010617535,0.002216491,0.0040009962,0.0026502674,0.01077296],"category_scores_gemma":[0.018111369,0.0010683968,0.0017965159,0.002685734,0.0023940657,0.0053138835,0.0059296833,0.004960223,0.004451305],"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":[0.00071208016,0.00024888988,0.0010584571,0.00048119714,0.00011441506,0.00022039427,0.00040431114,0.11113645,0.014787817,0.32789278,0.015323426,0.5276198],"study_design_scores_gemma":[0.000069264745,0.00012023346,0.00020165101,0.00008374267,0.000035905057,0.0002739489,0.00008601823,0.7030615,0.010259726,0.27369684,0.012066538,0.00004463223],"about_ca_topic_score_codex":0.0010878034,"about_ca_topic_score_gemma":0.0021902618,"teacher_disagreement_score":0.01077296,"about_ca_system_score_codex":0.0010260777,"about_ca_system_score_gemma":0.001896763,"threshold_uncertainty_score":0.036039174},"labels":[],"label_agreement":null},{"id":"W4300957756","doi":"10.48550/arxiv.1703.10731","title":"An analysis of budgeted parallel search on conditional Galton-Watson\\n trees","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Limit (mathematics); Overhead (engineering); Simple (philosophy); Set (abstract data type); Computer science; Tree (set theory); Process (computing); Mathematics; Combinatorics","score_opus":0.09572846714589092,"score_gpt":0.2439817270328835,"score_spread":0.1482532598869926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300957756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4834331,0.0027581796,0.49484158,0.0019027145,0.00008550144,0.00015894584,0.00030878876,0.0010378337,0.015473201],"genre_scores_gemma":[0.9055979,0.00093313656,0.08831279,0.00020622625,0.00009103785,0.00022811015,0.00032470285,0.00032064092,0.00398555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983267,0.00063281483,0.00007674492,0.00019576823,0.00045859514,0.0003093584],"domain_scores_gemma":[0.9884723,0.008724131,0.00069296744,0.0009936028,0.0006810464,0.00043587363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034039773,0.00061420555,0.001009047,0.0012057774,0.00090258813,0.001427103,0.0018763586,0.00089402427,0.0049578818],"category_scores_gemma":[0.023773644,0.0005967069,0.00056324166,0.0016962361,0.0020351587,0.0037558277,0.0019788314,0.0013820075,0.00043620798],"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":[0.0007377819,0.00014125736,0.003903696,0.00022555646,0.00007508149,0.00017026204,0.00034444593,0.7312113,0.006529349,0.20609522,0.0039949473,0.046571143],"study_design_scores_gemma":[0.00002419372,0.000030607098,0.00025334654,0.0000132814375,0.000010466679,0.000030306246,0.000018922292,0.9584458,0.0008552441,0.0398074,0.0005044807,0.000005883729],"about_ca_topic_score_codex":0.003938352,"about_ca_topic_score_gemma":0.003400941,"teacher_disagreement_score":0.0049578818,"about_ca_system_score_codex":0.0022396648,"about_ca_system_score_gemma":0.0017108276,"threshold_uncertainty_score":0.018002152},"labels":[],"label_agreement":null},{"id":"W4301775964","doi":"10.1007/3-540-45123-4","title":"Combinatorial Pattern Matching","year":2000,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Matching (statistics); Computer science; Mathematics; Statistics","score_opus":0.009172885170588025,"score_gpt":0.23714737469962857,"score_spread":0.22797448952904054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301775964","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031217072,0.005358043,0.44390914,0.0020741988,0.0012423623,0.00038813255,0.0028041184,0.0030021605,0.5100049],"genre_scores_gemma":[0.34661934,0.006455844,0.3529506,0.0012014036,0.0010673375,0.00056216633,0.012261773,0.0015445022,0.27733704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993925,0.00008183153,0.000035313045,0.00018222978,0.0002442351,0.00006386432],"domain_scores_gemma":[0.9993937,0.00014497597,0.00003996798,0.00027695298,0.000097544034,0.000046872803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003690566,0.00077630894,0.0010101632,0.0018140828,0.0008546009,0.0020711273,0.0017018465,0.00094844826,0.041628983],"category_scores_gemma":[0.0017519931,0.00048471737,0.0008544233,0.003674022,0.0007328102,0.003155393,0.0018378637,0.001471486,0.013156897],"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":[0.000121693825,0.00015083636,0.0003559504,0.0003553782,0.000053955082,0.00011034509,0.00006608105,0.0064395103,0.0050759786,0.37633884,0.07254419,0.53838724],"study_design_scores_gemma":[0.000037084832,0.000070159935,0.0005508671,0.00007630852,0.000056110766,0.00061194616,0.00006107367,0.028035432,0.006175429,0.8308151,0.1334873,0.000023158034],"about_ca_topic_score_codex":0.00040007068,"about_ca_topic_score_gemma":0.00058954896,"teacher_disagreement_score":0.041628983,"about_ca_system_score_codex":0.0007830686,"about_ca_system_score_gemma":0.0007129768,"threshold_uncertainty_score":0.13926286},"labels":[],"label_agreement":null},{"id":"W4301905878","doi":"10.1007/978-3-642-27848-8_646-1","title":"Compressed Representations of Graphs","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Computer science; Combinatorics","score_opus":0.013866660270896551,"score_gpt":0.2479936810213288,"score_spread":0.23412702075043224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301905878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01615059,0.008754526,0.8779288,0.0020795665,0.0015997969,0.00017592136,0.0056096357,0.0055920654,0.08210906],"genre_scores_gemma":[0.22626688,0.017054552,0.60315245,0.0012154053,0.0017047361,0.00048333217,0.027855882,0.0026324585,0.11963429],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996233,0.00007401054,0.000018408857,0.000067604866,0.00018765182,0.000029029166],"domain_scores_gemma":[0.99938715,0.00018511685,0.00003031602,0.00025431436,0.00011778217,0.000025351152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021507221,0.00092156796,0.0006572351,0.0017294348,0.00031314977,0.0015725289,0.0011567908,0.00082626747,0.026041692],"category_scores_gemma":[0.0020680577,0.00040215807,0.0004391858,0.0026887986,0.0005533788,0.0022582158,0.0013712405,0.0015480741,0.0074968063],"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":[0.00013945324,0.00006542827,0.000122036465,0.0004204065,0.000040169736,0.0001645008,0.00014084607,0.04460162,0.010566485,0.18660624,0.1141683,0.6429645],"study_design_scores_gemma":[0.00005777671,0.00009455127,0.000508127,0.0002571829,0.00004023318,0.0008788879,0.00016507256,0.30498636,0.01834552,0.46927857,0.20533112,0.000056530476],"about_ca_topic_score_codex":0.00093280035,"about_ca_topic_score_gemma":0.0014106662,"teacher_disagreement_score":0.026041692,"about_ca_system_score_codex":0.0005023724,"about_ca_system_score_gemma":0.00046973262,"threshold_uncertainty_score":0.08711815},"labels":[],"label_agreement":null},{"id":"W4302411531","doi":"10.1007/978-3-031-01885-5_5","title":"Conclusions and Open Problems","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Substring; Search engine indexing; Computer science; Scalability; Field (mathematics); Sequence (biology); Theoretical computer science; Information retrieval; Data mining; Data structure; Database; Programming language; Mathematics; Biology","score_opus":0.07604548345264996,"score_gpt":0.2840277626762075,"score_spread":0.20798227922355755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302411531","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004482712,0.043884333,0.059729684,0.2378815,0.044800885,0.000083984545,0.0014617256,0.00093077443,0.60674447],"genre_scores_gemma":[0.10610855,0.051018726,0.05119633,0.05911071,0.04578345,0.00045408317,0.0039246366,0.0015068759,0.6808966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976877,0.00070045586,0.00009019409,0.00047689676,0.00072686974,0.00031788976],"domain_scores_gemma":[0.99507457,0.0016120244,0.0001455833,0.0007629402,0.001813806,0.0005911044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003066277,0.0011124908,0.001021186,0.00172322,0.002839061,0.006515961,0.0027431,0.002836074,0.14814353],"category_scores_gemma":[0.012023834,0.0003282483,0.0011550472,0.0021848308,0.0032666512,0.013107763,0.003910219,0.0047973706,0.0430702],"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":[0.00008949279,0.00009118793,0.00015850175,0.00037564494,0.000015935788,0.00006287076,0.0002669772,0.0008656362,0.00021852955,0.55808246,0.3573683,0.082404435],"study_design_scores_gemma":[0.00001357803,0.000010541464,0.00011191401,0.00022705086,0.0000079576,0.000041600433,0.000425049,0.0006110647,0.00016118077,0.71427023,0.2841096,0.00001022437],"about_ca_topic_score_codex":0.0023954166,"about_ca_topic_score_gemma":0.0017893253,"teacher_disagreement_score":0.14814353,"about_ca_system_score_codex":0.0026231396,"about_ca_system_score_gemma":0.0025142843,"threshold_uncertainty_score":0.4955895},"labels":[],"label_agreement":null},{"id":"W4303453263","doi":"10.21203/rs.3.rs-2122747/v1","title":"Data structures for computing unique palindromes in static and non-static strings","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Japan Society for the Promotion of Science; University of Waterloo","keywords":"Substring; String (physics); Palindrome; Combinatorics; Time complexity; Interval (graph theory); Algorithm; Upper and lower bounds; Data structure; Mathematics; Discrete mathematics; Computer science","score_opus":0.13432537633294178,"score_gpt":0.44590751184760885,"score_spread":0.31158213551466707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303453263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45129043,0.003273598,0.50460905,0.0016694695,0.00043617634,0.00055108254,0.012129909,0.020762583,0.0052777547],"genre_scores_gemma":[0.5566585,0.00036831823,0.4260437,0.00028672238,0.0001744862,0.00046411212,0.012899204,0.0007482825,0.0023568154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99728954,0.00019012709,0.0005204142,0.0009837993,0.00071893504,0.00029730005],"domain_scores_gemma":[0.9906392,0.0028654335,0.0011722351,0.0037841313,0.0010348441,0.000504224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013680812,0.0011211049,0.0022391928,0.0025963208,0.0013298114,0.0024228906,0.0037570912,0.0014330967,0.005141555],"category_scores_gemma":[0.009666783,0.0010740904,0.0017090158,0.005830677,0.0011756988,0.009346539,0.003322013,0.0019895118,0.0015558397],"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":[0.005586708,0.0011376279,0.035557713,0.002867214,0.00039712206,0.001216737,0.0027942986,0.06324761,0.0922254,0.12837993,0.031522546,0.63506705],"study_design_scores_gemma":[0.0007225907,0.0012776222,0.0056999307,0.00033519618,0.0003192939,0.0010892522,0.0013023259,0.642405,0.09078387,0.22428197,0.031595875,0.00018708235],"about_ca_topic_score_codex":0.001928419,"about_ca_topic_score_gemma":0.0036671862,"teacher_disagreement_score":0.005141555,"about_ca_system_score_codex":0.0018144533,"about_ca_system_score_gemma":0.0027094074,"threshold_uncertainty_score":0.017200232},"labels":[],"label_agreement":null},{"id":"W4304080305","doi":"10.1145/3503161.3548413","title":"Accelerating General-purpose Lossless Compression via Simple and Scalable Parameterization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 30th ACM International Conference on Multimedia","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Lossless compression; Computer science; Data compression; Data compression ratio; Lossy compression; Scalability; Compression ratio; Recurrent neural network; Artificial intelligence; Compression (physics); Deep learning; Artificial neural network; Perceptron; Algorithm; Image compression; Engineering","score_opus":0.047140418896523754,"score_gpt":0.28509327659083566,"score_spread":0.2379528576943119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304080305","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04461788,0.0008282909,0.9435127,0.00030524825,0.00009294873,0.0001018077,0.00018462844,0.0063324017,0.0040241485],"genre_scores_gemma":[0.67078835,0.0008137681,0.3217227,0.00023633822,0.000074424526,0.00022363938,0.00063290505,0.00043416326,0.0050737825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997719,0.000020583542,0.000015959607,0.000041032894,0.00012176246,0.000028762712],"domain_scores_gemma":[0.9995946,0.0001335069,0.000038679445,0.00012560797,0.000089011475,0.000018499528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003600835,0.00087622134,0.0005070393,0.000542575,0.0002475442,0.0006230509,0.0012366475,0.00045864744,0.002392516],"category_scores_gemma":[0.00173674,0.00025221557,0.00035446795,0.0005680253,0.0006301906,0.0024651063,0.00090628985,0.0012868654,0.0010290444],"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":[0.00036935112,0.00016031171,0.0012072705,0.00021032683,0.000046459074,0.00025618155,0.00014012834,0.317515,0.1104302,0.018860027,0.0072003705,0.5436043],"study_design_scores_gemma":[0.000009679444,0.0000363986,0.00015963204,0.000007799058,0.0000077858895,0.000058268783,0.000009736139,0.97054803,0.02417777,0.002647229,0.0023281302,0.00000945816],"about_ca_topic_score_codex":0.0029590926,"about_ca_topic_score_gemma":0.0043594628,"teacher_disagreement_score":0.0029590926,"about_ca_system_score_codex":0.00061193836,"about_ca_system_score_gemma":0.00070540997,"threshold_uncertainty_score":0.008003831},"labels":[],"label_agreement":null},{"id":"W43054317","doi":"10.1007/978-3-319-05290-8_10","title":"Basic Video Compression Techniques","year":2014,"lang":"en","type":"book-chapter","venue":"Texts in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Motion compensation; Video compression picture types; Computer science; Data compression; Redundancy (engineering); Block-matching algorithm; Digital video; Computer vision; Multiview Video Coding; Artificial intelligence; Video processing; Reference frame; Quarter-pixel motion; Video tracking; Computer graphics (images); Frame (networking); Telecommunications","score_opus":0.01726415522513679,"score_gpt":0.2577497740908926,"score_spread":0.2404856188657558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W43054317","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005528462,0.092580855,0.48043227,0.0012060482,0.002735125,0.00042268902,0.0013660823,0.0034196125,0.4123088],"genre_scores_gemma":[0.04026603,0.10815083,0.23231328,0.0011276017,0.0028933547,0.0004472616,0.003417273,0.0010251398,0.6103594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997669,0.000010113678,0.00001058363,0.00004053415,0.00015377614,0.00001807117],"domain_scores_gemma":[0.99981636,0.000049468814,0.000008972312,0.000031690794,0.00008328766,0.000010230064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017523137,0.0013340502,0.0006237389,0.0022981293,0.0003955797,0.0010392106,0.0009410183,0.00088599947,0.03350983],"category_scores_gemma":[0.00052510435,0.00040468413,0.0004448555,0.0023735147,0.0005551266,0.0016996816,0.0006110234,0.0014988297,0.024521718],"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":[0.000050581566,0.00005817141,0.000062965635,0.00068993814,0.000014330049,0.000104335435,0.00008608302,0.0012461115,0.030665247,0.028923348,0.052106883,0.88599205],"study_design_scores_gemma":[0.00002497352,0.00017186497,0.0011542772,0.00064349844,0.000041310934,0.0022192707,0.00007080276,0.011685287,0.06438538,0.03880457,0.88073635,0.00006247046],"about_ca_topic_score_codex":0.0004353879,"about_ca_topic_score_gemma":0.0005072762,"teacher_disagreement_score":0.03350983,"about_ca_system_score_codex":0.00035896976,"about_ca_system_score_gemma":0.00036355213,"threshold_uncertainty_score":0.112101495},"labels":[],"label_agreement":null},{"id":"W4309867048","doi":"10.3233/fi-222164","title":"String Covering: A Survey","year":2023,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"String (physics); Cover (algebra); Superstring theory; Simple (philosophy); Computer science; Field (mathematics); Theoretical computer science; Theoretical physics; Mathematics; Pure mathematics; Physics; Engineering; Epistemology; Supersymmetry; Philosophy","score_opus":0.04640812418772218,"score_gpt":0.2787424031324345,"score_spread":0.2323342789447123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309867048","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01065753,0.88209224,0.036043394,0.0022827408,0.0009900773,0.0000653527,0.00049637485,0.00030324794,0.06706913],"genre_scores_gemma":[0.045732845,0.92056125,0.020884123,0.0009448777,0.0017497158,0.0000805772,0.0011482119,0.00017024681,0.008728161],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999119,0.00015758179,0.000074883515,0.00020500683,0.00035407854,0.00008937842],"domain_scores_gemma":[0.9980386,0.0013684736,0.000104009145,0.0001883885,0.00021736055,0.000083177474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000830948,0.0008535644,0.0010129893,0.0038632425,0.0007679899,0.00245882,0.0011041057,0.0014047461,0.0072006537],"category_scores_gemma":[0.0036171523,0.00060663687,0.0007331116,0.0070515918,0.0011791443,0.005031614,0.0015532261,0.0013548797,0.0032837852],"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":[0.000061781,0.000085224536,0.0014594591,0.0039684796,0.00004198907,0.00020967366,0.00026030105,0.0035908206,0.0016833906,0.13946423,0.022864709,0.8263099],"study_design_scores_gemma":[0.000011893105,0.00013493636,0.0019661144,0.0017292893,0.00004731542,0.0022569513,0.00019908362,0.005355477,0.0028060745,0.09043271,0.8950157,0.000044444612],"about_ca_topic_score_codex":0.00096052163,"about_ca_topic_score_gemma":0.00059434964,"teacher_disagreement_score":0.0072006537,"about_ca_system_score_codex":0.0010927556,"about_ca_system_score_gemma":0.0010484467,"threshold_uncertainty_score":0.024088621},"labels":[],"label_agreement":null},{"id":"W4310930449","doi":"10.22541/au.167061324.41772807/v1","title":"Transcoding Unicode Characters with AVX-512 Instructions","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Université TÉLUQ","funders":"","keywords":"Computer science; Transcoding; Unicode; Parallel computing; Software; Operating system; Artificial intelligence","score_opus":0.020828125217756926,"score_gpt":0.24157772947168835,"score_spread":0.22074960425393142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310930449","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084354416,0.0013392096,0.8415108,0.00050248345,0.0017657232,0.0003372118,0.0033416525,0.040476702,0.02637185],"genre_scores_gemma":[0.20699573,0.0007868503,0.74093324,0.0003331221,0.00024276011,0.0003931364,0.008862714,0.0059829797,0.035469532],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99965286,0.00002036655,0.000044187975,0.00007264109,0.00017242807,0.000037446458],"domain_scores_gemma":[0.9992537,0.0001279006,0.00003388285,0.00024100814,0.00031603727,0.000027527181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025198387,0.0009902376,0.000475769,0.0012885132,0.00039324613,0.0009246731,0.00084666855,0.00051978545,0.015490392],"category_scores_gemma":[0.0027154079,0.00024853344,0.00036986877,0.0012902459,0.00037402197,0.0009154253,0.000940076,0.0008587463,0.008235727],"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":[0.00045600208,0.00008834205,0.0011002946,0.00036685236,0.00004678616,0.00046995538,0.00035213004,0.0036476774,0.1668918,0.015201389,0.048380222,0.7629985],"study_design_scores_gemma":[0.00009482105,0.00021677448,0.0022835971,0.000111187386,0.00006207768,0.0014959407,0.00023821557,0.09514214,0.6849724,0.0189405,0.1963596,0.00008269705],"about_ca_topic_score_codex":0.0009772917,"about_ca_topic_score_gemma":0.0012472388,"teacher_disagreement_score":0.015490392,"about_ca_system_score_codex":0.00028189106,"about_ca_system_score_gemma":0.00031418924,"threshold_uncertainty_score":0.051820517},"labels":[],"label_agreement":null},{"id":"W4313012597","doi":"10.1007/978-3-031-20643-6_14","title":"KATKA: A KRAKEN-Like Tool with k Given at Query Time","year":2022,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute","keywords":"Computer science","score_opus":0.00698868901094241,"score_gpt":0.21366641605087144,"score_spread":0.20667772703992904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313012597","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008479607,0.00036246044,0.6675118,0.0004717713,0.00029846336,0.0001856411,0.0035762056,0.31074968,0.008364317],"genre_scores_gemma":[0.26127276,0.00052122993,0.6234809,0.0012890915,0.00019598992,0.0007230428,0.008717619,0.082177475,0.02162182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996847,0.0005776328,0.00043731154,0.000735729,0.0009850251,0.00041730487],"domain_scores_gemma":[0.9907155,0.0037836847,0.00040211465,0.0040896563,0.00065626483,0.00035273688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025294228,0.0018640794,0.001629834,0.0019930208,0.0010613686,0.00296611,0.0043501775,0.002104483,0.04320794],"category_scores_gemma":[0.014004548,0.0017060473,0.0016551787,0.0024861535,0.0020843798,0.010399777,0.0070172795,0.0026698478,0.018755317],"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":[0.0056687673,0.00037532763,0.0039630895,0.0032772142,0.0003793385,0.00091711193,0.0018963192,0.008845383,0.058726132,0.11358256,0.22536583,0.577003],"study_design_scores_gemma":[0.0010631249,0.0005865623,0.0019166929,0.00068206235,0.00029522978,0.0021584616,0.0009879067,0.12731795,0.19005544,0.24565789,0.42851824,0.0007603896],"about_ca_topic_score_codex":0.0015196529,"about_ca_topic_score_gemma":0.0026747263,"teacher_disagreement_score":0.04320794,"about_ca_system_score_codex":0.00086924277,"about_ca_system_score_gemma":0.0013240863,"threshold_uncertainty_score":0.14454496},"labels":[],"label_agreement":null},{"id":"W4313023011","doi":"10.1007/978-3-031-20643-6_16","title":"Internal Masked Prefix Sums and Its Connection to Fully Internal Measurement Queries","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Waterloo","funders":"","keywords":"Prefix; Intersection (aeronautics); Generalization; Connection (principal bundle); String (physics); Set (abstract data type); Bit array; Mathematics; Boolean function; Computer science; Discrete mathematics; Algorithm; Combinatorics","score_opus":0.026209781236246375,"score_gpt":0.24438124650076518,"score_spread":0.2181714652645188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313023011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043942746,0.0011008166,0.9210726,0.0016652347,0.0004135916,0.00010002419,0.00045399033,0.0014718324,0.029779164],"genre_scores_gemma":[0.73071676,0.00090929004,0.24197333,0.0013222039,0.0013021389,0.00036077955,0.00085032365,0.0012844825,0.021280607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99463886,0.0014457471,0.00042810157,0.00083132874,0.0020874622,0.00056847185],"domain_scores_gemma":[0.9807735,0.010969941,0.0010273776,0.0057150144,0.0011121396,0.0004020597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031376637,0.0009304304,0.001833455,0.0015408017,0.0017317333,0.0055806474,0.002801092,0.0023640548,0.0071927183],"category_scores_gemma":[0.02308323,0.00090692815,0.0010302563,0.0040547135,0.0038600455,0.012606328,0.0074729132,0.0043516154,0.0017104285],"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":[0.00017718284,0.00004625786,0.00030901737,0.00007841429,0.000017492122,0.0001652936,0.0002585946,0.006722207,0.0023300431,0.9517277,0.0033968354,0.034770865],"study_design_scores_gemma":[0.000008432046,0.0000131649485,0.000063519234,0.000012723706,0.000009256623,0.00015572034,0.00002436538,0.040394347,0.0016369144,0.9556079,0.0020566918,0.000016951479],"about_ca_topic_score_codex":0.00045961028,"about_ca_topic_score_gemma":0.00036613812,"teacher_disagreement_score":0.0071927183,"about_ca_system_score_codex":0.0013223309,"about_ca_system_score_gemma":0.001082626,"threshold_uncertainty_score":0.024062097},"labels":[],"label_agreement":null},{"id":"W4317600672","doi":"10.1101/2023.01.18.524557","title":"Recursive Prefix-Free Parsing for Building Big BWTs","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Israel Institute for Biological Research; National Institutes of Health; National Science Foundation","keywords":"Prefix; Parsing; Computer science; Arithmetic; Artificial intelligence; Mathematics; Linguistics; Philosophy","score_opus":0.03721075118758353,"score_gpt":0.25272614449496855,"score_spread":0.215515393307385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317600672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012556855,0.0004347214,0.93567175,0.0003063768,0.00016224629,0.00016967935,0.0016687404,0.043519963,0.005509638],"genre_scores_gemma":[0.09915007,0.00025094117,0.88118064,0.0002782175,0.00007967547,0.0002947856,0.0063845413,0.007871495,0.0045096395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970151,0.00053997565,0.0003185401,0.00069781084,0.0010640537,0.0003644766],"domain_scores_gemma":[0.9928617,0.0034836668,0.00033849114,0.0020982015,0.0010232257,0.00019469117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017808895,0.0018445388,0.0012558462,0.0018621436,0.0013929894,0.0031559812,0.0035842238,0.0017380567,0.017281767],"category_scores_gemma":[0.014365224,0.0010272333,0.00216477,0.004011465,0.0018538806,0.0071520233,0.0036887445,0.0030672667,0.009984573],"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":[0.00082951976,0.00030692935,0.0028043804,0.0015198664,0.00015371418,0.0010363654,0.0011504133,0.060502455,0.049095105,0.1420643,0.06646577,0.67407113],"study_design_scores_gemma":[0.0001947209,0.00021829906,0.0006904469,0.00025297838,0.00013681327,0.0006891423,0.0003663241,0.481085,0.09915515,0.34086832,0.07620616,0.00013668534],"about_ca_topic_score_codex":0.003220786,"about_ca_topic_score_gemma":0.005038599,"teacher_disagreement_score":0.017281767,"about_ca_system_score_codex":0.001745207,"about_ca_system_score_gemma":0.0028902488,"threshold_uncertainty_score":0.057813287},"labels":[],"label_agreement":null},{"id":"W4317860139","doi":"10.5281/zenodo.7566229","title":"Computing the Tandem Duplication Distance is NP-Hard","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem; Data deduplication; Computer science; Gene duplication; Tandem exon duplication; Parallel computing; Database; Biology; Engineering; Genetics","score_opus":0.03280414356947456,"score_gpt":0.24400393128110529,"score_spread":0.21119978771163073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317860139","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21927913,0.009714762,0.5158995,0.032345764,0.0017639678,0.0009800517,0.033323903,0.011172749,0.17552023],"genre_scores_gemma":[0.6176478,0.00557507,0.25262517,0.0029517233,0.0015307337,0.00087947503,0.038172208,0.0026950522,0.07792279],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810517,0.0002742448,0.00010932555,0.0007938353,0.00045053315,0.00026675136],"domain_scores_gemma":[0.99060225,0.0072544497,0.00044123814,0.0007644089,0.0006317783,0.00030589086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001149773,0.0014096355,0.0027399852,0.0014476859,0.0017480021,0.0056661996,0.002457985,0.002609878,0.029140212],"category_scores_gemma":[0.009814644,0.0009199953,0.0013834988,0.003912221,0.0015286366,0.00574016,0.0022023795,0.004627295,0.009382737],"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":[0.0008105871,0.0005642054,0.0067893015,0.0024512873,0.00051355467,0.0008804665,0.00052090775,0.23857832,0.0076902537,0.09888581,0.27494425,0.36737105],"study_design_scores_gemma":[0.00033300885,0.00012971315,0.002160433,0.0001612051,0.00016304887,0.00090931606,0.00039593552,0.4405817,0.004022711,0.51767963,0.033397075,0.000066082765],"about_ca_topic_score_codex":0.005980211,"about_ca_topic_score_gemma":0.008945007,"teacher_disagreement_score":0.029140212,"about_ca_system_score_codex":0.003074066,"about_ca_system_score_gemma":0.003361372,"threshold_uncertainty_score":0.097483695},"labels":[],"label_agreement":null},{"id":"W4320729805","doi":"10.54097/hset.v31i.5152","title":"Application of Random Walks in Data Processing","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Random walk; Random field; Computer science; Field (mathematics); Random walker algorithm; Markov process; Stochastic process; Markov chain; Algorithm; Statistical physics; Theoretical computer science; Mathematics; Artificial intelligence; Statistics; Machine learning; Physics","score_opus":0.011618138993300475,"score_gpt":0.25135807751314393,"score_spread":0.23973993851984346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320729805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033853038,0.015052663,0.9735902,0.0011025277,0.0003386878,0.00008019477,0.00020003632,0.0004008676,0.0058493786],"genre_scores_gemma":[0.26047587,0.04651535,0.677963,0.0012582389,0.0017040182,0.0004867257,0.0010356928,0.00030330627,0.0102577405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975516,0.0008687404,0.00023489288,0.0005253547,0.0007216009,0.00009781479],"domain_scores_gemma":[0.9969764,0.0020748707,0.00020372478,0.00030139825,0.00037567155,0.000067967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016767842,0.0009347938,0.0013220707,0.002588222,0.00062639924,0.0021560888,0.0011077588,0.0018011343,0.0029758303],"category_scores_gemma":[0.006698433,0.0004656141,0.0013110664,0.004162009,0.0014568397,0.0027427843,0.0015699093,0.0020670502,0.0015982814],"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":[0.000088816516,0.000101334954,0.0029795521,0.0012559209,0.00026269554,0.0006188665,0.0003469647,0.1425995,0.0049526184,0.5216656,0.011115294,0.3140128],"study_design_scores_gemma":[0.000017676546,0.000087734334,0.0007253001,0.00029349665,0.000056245743,0.0006428022,0.00007775596,0.47057647,0.0024840003,0.47988936,0.04507598,0.00007314995],"about_ca_topic_score_codex":0.0018680443,"about_ca_topic_score_gemma":0.0011916369,"teacher_disagreement_score":0.0029758303,"about_ca_system_score_codex":0.0008305803,"about_ca_system_score_gemma":0.0010945465,"threshold_uncertainty_score":0.009955108},"labels":[],"label_agreement":null},{"id":"W4360980788","doi":"10.1007/s42979-023-01690-8","title":"On the Multiple Pattern String Matching in DNA Databases","year":2023,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Winnipeg","funders":"School of Natural Sciences, Mathematics, and Engineering, California State University, Bakersfield","keywords":"Substring; String searching algorithm; Pattern matching; Suffix tree; Search engine indexing; Computer science; String (physics); Character (mathematics); Transformation (genetics); Tree (set theory); Set (abstract data type); Matching (statistics); Combinatorics; Algorithm; Mathematics; Artificial intelligence; Data structure; Programming language","score_opus":0.04220773460392502,"score_gpt":0.2763246664326198,"score_spread":0.2341169318286948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360980788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017795324,0.0083489735,0.9656276,0.0023214144,0.00073818344,0.000106294414,0.00026252327,0.0006157005,0.004183885],"genre_scores_gemma":[0.26193854,0.019363483,0.6971942,0.0017994294,0.0025517931,0.00029080105,0.0013676804,0.00039944632,0.015094621],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99494463,0.001714424,0.00061124255,0.00072076457,0.0017478372,0.00026104972],"domain_scores_gemma":[0.9880343,0.008547062,0.00038446797,0.0017251952,0.0011139888,0.00019503037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042385976,0.00071954634,0.0019433275,0.0041532116,0.0010475048,0.0029240253,0.0026208314,0.0022166956,0.00523337],"category_scores_gemma":[0.021120185,0.0006941781,0.001164727,0.008550298,0.0025092391,0.009280956,0.0027421333,0.0025968712,0.0020316811],"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":[0.0006635442,0.00020049028,0.0015286907,0.000525119,0.0001296684,0.00038303318,0.00021795311,0.068073794,0.005687084,0.15069431,0.0135955755,0.7583007],"study_design_scores_gemma":[0.00007307671,0.00019986075,0.00087268377,0.00018082849,0.00008558613,0.0006694187,0.00015101439,0.6283498,0.0071837674,0.34366065,0.018522114,0.00005121041],"about_ca_topic_score_codex":0.002723361,"about_ca_topic_score_gemma":0.0016179811,"teacher_disagreement_score":0.00523337,"about_ca_system_score_codex":0.0010494036,"about_ca_system_score_gemma":0.0015515058,"threshold_uncertainty_score":0.022416055},"labels":[],"label_agreement":null},{"id":"W4376167123","doi":"10.48550/arxiv.2305.05893","title":"Acceleration of FM-index Queries Through Prefix-free Parsing","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"National Human Genome Research Institute; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Prefix; Computer science; Parsing; Word (group theory); Suffix; Suffix array; Search engine indexing; Trie; Sorting; Suffix tree; Character (mathematics); Index (typography); String (physics); Code (set theory); Artificial intelligence; Data structure; Algorithm; Programming language; Set (abstract data type); Mathematics","score_opus":0.1616371602638194,"score_gpt":0.21602451136400638,"score_spread":0.05438735110018697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376167123","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070643894,0.0019704532,0.7643266,0.00087692443,0.0005591449,0.0003580142,0.005568511,0.139444,0.016252544],"genre_scores_gemma":[0.1576209,0.00045439965,0.8091441,0.00044435423,0.0002116209,0.00039673306,0.016065594,0.007228633,0.008433697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730563,0.00032395573,0.00031857882,0.0005826634,0.0011873406,0.0002817315],"domain_scores_gemma":[0.99578506,0.0016758229,0.00018739287,0.0014046106,0.00082269474,0.0001243598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001425484,0.0018645223,0.001306913,0.0029581336,0.0009892659,0.0027280126,0.0031567223,0.0013967601,0.0117283845],"category_scores_gemma":[0.010495725,0.00067408197,0.0011835261,0.005527081,0.0008319772,0.0052048424,0.002825141,0.0014595913,0.009990982],"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":[0.0010610302,0.0003683611,0.0036778487,0.0006084001,0.0001316296,0.00027167072,0.00058277824,0.015198505,0.05444314,0.01978066,0.07431727,0.82955873],"study_design_scores_gemma":[0.00042144264,0.00033342798,0.0035940886,0.00011310438,0.00011743085,0.0009968999,0.00053970196,0.69947994,0.14706942,0.057198443,0.089957125,0.00017896558],"about_ca_topic_score_codex":0.0041749026,"about_ca_topic_score_gemma":0.004722442,"teacher_disagreement_score":0.0117283845,"about_ca_system_score_codex":0.0012188618,"about_ca_system_score_gemma":0.002029138,"threshold_uncertainty_score":0.039235353},"labels":[],"label_agreement":null},{"id":"W4376279832","doi":"10.56726/irjmets38585","title":"BIG DATA OVER A DETECTED COMMUNITY","year":2023,"lang":"en","type":"article","venue":"International Research Journal of Modernization in Engineering Technology and Science","topic":"Algorithms and Data Compression","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":"","keywords":"Big data; Data science; Political science; Computer science; Data mining","score_opus":0.13076995752769202,"score_gpt":0.3824572958505498,"score_spread":0.25168733832285783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376279832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52486104,0.0063188532,0.3504329,0.006983259,0.0012916751,0.0007069026,0.08861685,0.011258275,0.009530243],"genre_scores_gemma":[0.8356663,0.0013473495,0.11197117,0.00053231133,0.0007502019,0.00042619155,0.04739673,0.00015744338,0.0017523131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968822,0.00046081905,0.00030324145,0.00089648133,0.0011998271,0.00025749125],"domain_scores_gemma":[0.9890571,0.0043358374,0.0014243921,0.0022530137,0.0023620978,0.0005674587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028359243,0.0011323446,0.0011320437,0.006052916,0.000969618,0.0018810191,0.0015179218,0.0016658899,0.0012834918],"category_scores_gemma":[0.016059546,0.00039455362,0.00070366764,0.009958956,0.0009162381,0.0038421534,0.0015614845,0.0012747754,0.00067863753],"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":[0.0034149035,0.0009310842,0.1996482,0.002841276,0.0009597897,0.0035598914,0.0013479409,0.17629974,0.037665002,0.028843027,0.08066323,0.46382585],"study_design_scores_gemma":[0.000114130446,0.00040175338,0.12165463,0.00029722083,0.00023252609,0.0018745492,0.0013289757,0.733969,0.025027297,0.07036844,0.04458302,0.00014845014],"about_ca_topic_score_codex":0.0040645828,"about_ca_topic_score_gemma":0.0046253977,"teacher_disagreement_score":0.006052916,"about_ca_system_score_codex":0.0011897531,"about_ca_system_score_gemma":0.00061015424,"threshold_uncertainty_score":0.014998019},"labels":[],"label_agreement":null},{"id":"W4377086801","doi":"10.1093/bioinformatics/btad328","title":"GIL: a python package for designing custom indexing primers","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Western Canada Research Grid; Stem Cell Network; Canadian Institutes of Health Research; Compute Canada","keywords":"Python (programming language); Search engine indexing; Programming language; Computer science; R package; Information retrieval","score_opus":0.03511654673081748,"score_gpt":0.27567387795689735,"score_spread":0.24055733122607986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377086801","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027940895,0.00045917023,0.38707474,0.0003529647,0.00037481976,0.0005444239,0.07480764,0.5257096,0.007882605],"genre_scores_gemma":[0.02003827,0.00057997956,0.6616293,0.0018648304,0.00017121629,0.0037127275,0.10013275,0.19496727,0.016903637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976471,0.0003665561,0.00030384306,0.00069950084,0.00070119195,0.00028181108],"domain_scores_gemma":[0.997265,0.0012945719,0.00028017463,0.0004997454,0.0004749397,0.00018557766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003295685,0.0025025597,0.0018788644,0.001977601,0.0013047627,0.002957051,0.0037199764,0.0011011903,0.10738149],"category_scores_gemma":[0.0098484745,0.0024744926,0.0019220219,0.0017726287,0.0009301091,0.002436275,0.0030222652,0.0036384265,0.08335165],"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":[0.00101522,0.0001792398,0.0033286023,0.0036746748,0.00037066633,0.00039484704,0.0006104719,0.0060386886,0.04110224,0.013795565,0.7296231,0.19986655],"study_design_scores_gemma":[0.00039197085,0.00017650147,0.0032033448,0.00045435995,0.00017787596,0.00077126065,0.00016160366,0.04582868,0.090352476,0.03811494,0.81998676,0.00038021637],"about_ca_topic_score_codex":0.0022429724,"about_ca_topic_score_gemma":0.0034498512,"teacher_disagreement_score":0.10738149,"about_ca_system_score_codex":0.0011500753,"about_ca_system_score_gemma":0.0030387219,"threshold_uncertainty_score":0.35922688},"labels":[],"label_agreement":null},{"id":"W4378505355","doi":"10.48550/arxiv.2305.15140","title":"Polynomial-Time Pseudodeterministic Construction of Primes","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Engineering and Physical Sciences Research Council; Simons Institute for the Theory of Computing, University of California Berkeley; Natural Sciences and Engineering Research Council of Canada; University of Warwick; National Science Foundation","keywords":"Mathematics; Time complexity; Polynomial; Randomized algorithm; Prime (order theory); Randomness; Bootstrapping (finance); Discrete mathematics; Combinatorics","score_opus":0.0645481934173141,"score_gpt":0.19178489611618124,"score_spread":0.12723670269886714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378505355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07675288,0.00033868183,0.9050469,0.0023907935,0.00012631688,0.00021491875,0.00039898406,0.0020738363,0.0126567995],"genre_scores_gemma":[0.7087975,0.00030447633,0.28080252,0.0007965997,0.00018669588,0.00060792034,0.00064784597,0.0006421314,0.0072142463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99256706,0.0026410518,0.00041444824,0.0017953842,0.0018790925,0.00070297834],"domain_scores_gemma":[0.9747863,0.015186427,0.001040218,0.0074104653,0.0011098352,0.00046677684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047178203,0.0007653736,0.0012437559,0.0008202251,0.0017967478,0.0024843356,0.0026252999,0.0015565634,0.004679934],"category_scores_gemma":[0.026422957,0.0008470179,0.0018909223,0.0012991162,0.004332656,0.0070923306,0.005526662,0.004711996,0.0014101154],"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":[0.0004853408,0.00017212775,0.0016823289,0.00019989212,0.000058596364,0.00014833431,0.000442635,0.036276557,0.010518548,0.9012381,0.004290102,0.04448735],"study_design_scores_gemma":[0.00016732115,0.00013704483,0.00030938655,0.00004875903,0.00005627587,0.00024148995,0.00007434815,0.19328144,0.02022381,0.77717245,0.008219147,0.00006853709],"about_ca_topic_score_codex":0.00043762007,"about_ca_topic_score_gemma":0.0006214707,"teacher_disagreement_score":0.0047178203,"about_ca_system_score_codex":0.001754217,"about_ca_system_score_gemma":0.0025460047,"threshold_uncertainty_score":0.024950564},"labels":[],"label_agreement":null},{"id":"W4378652164","doi":"10.1007/s00026-023-00648-0","title":"Folding Rotationally Symmetric Tableaux via Webs","year":2023,"lang":"en","type":"article","venue":"Annals of Combinatorics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Mathematics; Folding (DSP implementation); Young tableau; Symmetric group; Engineering","score_opus":0.05881549500033758,"score_gpt":0.31459645918067025,"score_spread":0.2557809641803327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378652164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42021886,0.00064411905,0.47326377,0.0012007591,0.0011976106,0.00019381671,0.00079143944,0.0042438214,0.09824581],"genre_scores_gemma":[0.84083736,0.00064923795,0.119769156,0.00051497895,0.00023465409,0.00015580788,0.00067195966,0.0013200142,0.035846896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994772,0.00011762709,0.000039227147,0.00010398369,0.0001683939,0.00009360054],"domain_scores_gemma":[0.99910164,0.0003482371,0.000061119295,0.0003366579,0.0000862982,0.000066011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041634386,0.0006847108,0.00086941343,0.0010412679,0.0010511776,0.0022007853,0.0007818882,0.00095597596,0.016359515],"category_scores_gemma":[0.0020181283,0.00051027857,0.0007691141,0.0013094142,0.0011792441,0.0028282716,0.0016649003,0.0013933145,0.0040078084],"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":[0.00014555365,0.00009290025,0.0003188597,0.00008066458,0.00001684485,0.00026609554,0.0002483052,0.011809923,0.010629174,0.90065473,0.0070773163,0.068659626],"study_design_scores_gemma":[0.000033429464,0.000059381317,0.00013671706,0.000032091244,0.000015643796,0.00018405277,0.00012130285,0.039301943,0.007721252,0.94223523,0.010132668,0.000026274543],"about_ca_topic_score_codex":0.00048565504,"about_ca_topic_score_gemma":0.00088591164,"teacher_disagreement_score":0.016359515,"about_ca_system_score_codex":0.00068775873,"about_ca_system_score_gemma":0.0003897948,"threshold_uncertainty_score":0.05472803},"labels":[],"label_agreement":null},{"id":"W4379031450","doi":"10.1007/978-3-031-34171-7_29","title":"Local Maximal Equality-Free Periodicities","year":2023,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Integer (computer science); Mathematics; Combinatorics; Sequence (biology); Position (finance); String (physics); Space (punctuation); Discrete mathematics; Computer science; Biology; Mathematical physics; Economics; Genetics","score_opus":0.014676683752620484,"score_gpt":0.25815151493261745,"score_spread":0.24347483117999696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379031450","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20231928,0.0020954404,0.12320432,0.0010442358,0.0006004376,0.000070056914,0.0004481708,0.00047498115,0.66974306],"genre_scores_gemma":[0.881761,0.0010807357,0.015251758,0.0003327439,0.00044412244,0.000122024525,0.000447885,0.00027631514,0.10028334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997285,0.000036477544,0.000015225111,0.00006734209,0.00007382186,0.00007862658],"domain_scores_gemma":[0.99956244,0.00019967437,0.000039893497,0.00009049414,0.000049640967,0.000057797286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031220153,0.00044797148,0.0005711265,0.00081281725,0.0011182459,0.0016140783,0.0006709117,0.00050602347,0.015954996],"category_scores_gemma":[0.0013220551,0.00035624328,0.0003638923,0.00073799834,0.0016552379,0.0024248369,0.0019476996,0.001587667,0.0021209235],"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":[0.00006738789,0.000015006145,0.00007574637,0.00007839283,0.0000049097953,0.000093902076,0.000192683,0.0005594263,0.002906962,0.97974235,0.0031246487,0.013138649],"study_design_scores_gemma":[0.00002823037,0.00002411436,0.00026499867,0.000029877103,0.000009118556,0.00030300242,0.00014773585,0.0026980687,0.0038452535,0.9791676,0.013468176,0.000013835435],"about_ca_topic_score_codex":0.00021996051,"about_ca_topic_score_gemma":0.00029474968,"teacher_disagreement_score":0.015954996,"about_ca_system_score_codex":0.00046607436,"about_ca_system_score_gemma":0.00027057822,"threshold_uncertainty_score":0.053374767},"labels":[],"label_agreement":null},{"id":"W4379162524","doi":"10.22541/au.168571970.03060289/v1","title":"Parsing Millions of URLs per Second","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Université TÉLUQ","funders":"","keywords":"Computer science; Parsing; Node (physics); Programming language; Operating system; Physics","score_opus":0.05754635032976943,"score_gpt":0.29229181773387625,"score_spread":0.23474546740410682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379162524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08537401,0.0034390225,0.44432467,0.0025077695,0.0034144733,0.0006168592,0.07633914,0.35541955,0.028564509],"genre_scores_gemma":[0.25872812,0.0021162133,0.5099768,0.0010644961,0.0010240324,0.0009090264,0.16096115,0.027835209,0.037385028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550134,0.00033918725,0.00053394475,0.0009854945,0.0023586566,0.0002814048],"domain_scores_gemma":[0.99220395,0.0019493301,0.00040975647,0.0022090182,0.0030027982,0.00022519857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017884711,0.0020015019,0.0013106682,0.00544336,0.00084033905,0.003029328,0.00173991,0.0015220447,0.018220812],"category_scores_gemma":[0.018597735,0.0012619946,0.00096018816,0.0067350585,0.0006715159,0.0034951563,0.0020338441,0.0017671334,0.019444175],"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":[0.00071601913,0.00017022507,0.0072148466,0.0007169026,0.00016670511,0.0007387657,0.0007054987,0.009505282,0.035301372,0.016302098,0.37814054,0.5503217],"study_design_scores_gemma":[0.00018219788,0.00019072062,0.015219901,0.0003476601,0.00016174931,0.0016935798,0.00068768015,0.25639725,0.12623811,0.06777389,0.5308371,0.0002701212],"about_ca_topic_score_codex":0.00464414,"about_ca_topic_score_gemma":0.0028320192,"teacher_disagreement_score":0.018220812,"about_ca_system_score_codex":0.0008986707,"about_ca_system_score_gemma":0.001185775,"threshold_uncertainty_score":0.06095469},"labels":[],"label_agreement":null},{"id":"W4381303311","doi":"10.1007/978-3-031-33180-0_3","title":"On the Number of Distinct Squares in Finite Sequences: Some Old and New Results","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Word (group theory); Bounded function; Square (algebra); Combinatorics; Mathematics; Finite set; Discrete mathematics; Mathematical analysis; Geometry","score_opus":0.03482014820222165,"score_gpt":0.26890963523137035,"score_spread":0.2340894870291487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381303311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07815468,0.048364155,0.7192092,0.008480932,0.0038961198,0.00010957575,0.00081077364,0.0005886177,0.14038593],"genre_scores_gemma":[0.53043294,0.050302062,0.31763345,0.004571806,0.016467836,0.00049667986,0.0014380626,0.0013263217,0.07733071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973801,0.0005464993,0.00023243911,0.00077864074,0.00081235217,0.00025001087],"domain_scores_gemma":[0.96809375,0.02640704,0.0010355171,0.0019716206,0.0014793733,0.001012638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004350345,0.0024232825,0.0028397632,0.0048449314,0.0024049948,0.0043185083,0.0042162407,0.0031391631,0.008300205],"category_scores_gemma":[0.021279847,0.0015088408,0.0021558446,0.0069825603,0.012093559,0.024077002,0.0050236755,0.009372871,0.0022583564],"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":[0.00021439051,0.000101390644,0.00096867885,0.00057416083,0.000040494593,0.00017445591,0.00045063216,0.008692556,0.002589217,0.91325295,0.008873656,0.06406759],"study_design_scores_gemma":[0.000018780056,0.000039792274,0.0003819372,0.00006678356,0.000025639298,0.00026816753,0.000079233054,0.013239519,0.00082802016,0.9770626,0.007955269,0.000034293997],"about_ca_topic_score_codex":0.0010991949,"about_ca_topic_score_gemma":0.0009310109,"teacher_disagreement_score":0.008300205,"about_ca_system_score_codex":0.0019897372,"about_ca_system_score_gemma":0.0010916725,"threshold_uncertainty_score":0.027767003},"labels":[],"label_agreement":null},{"id":"W4382893966","doi":"10.5121/ijnlc.2023.12301","title":"Testing Different Log Bases for Vector Model Weighting Technique","year":2023,"lang":"en","type":"article","venue":"International Journal on Natural Language Computing","topic":"Algorithms and Data Compression","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":"Workers Compensation Board of Alberta; Alberta Biodiversity Monitoring Institute","funders":"","keywords":"Weighting; tf–idf; Computer science; Term (time); Logarithm; Information retrieval; Vector space model; Range (aeronautics); Data mining; Base (topology); Algorithm; Mathematics","score_opus":0.028884587050035247,"score_gpt":0.31812667251522087,"score_spread":0.2892420854651856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382893966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82733977,0.0017713424,0.15456128,0.0008218553,0.00035348535,0.0006598325,0.0017718012,0.0044844057,0.008236199],"genre_scores_gemma":[0.8601011,0.0005316556,0.13066033,0.00022750656,0.00007225935,0.00054891576,0.0040268875,0.00039770285,0.0034335875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939944,0.0025395544,0.0005261831,0.0007052721,0.0019344342,0.00030014568],"domain_scores_gemma":[0.9675983,0.022486601,0.0011152871,0.0038186037,0.0045829583,0.00039822154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068013025,0.0008529514,0.00072965876,0.0021519277,0.0006952875,0.0014964632,0.0014985265,0.0013043563,0.0027674616],"category_scores_gemma":[0.053055212,0.0003118288,0.0006936309,0.0023128793,0.00070989534,0.0034506463,0.0013442315,0.0015591141,0.0009641856],"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":[0.0065515293,0.0041306405,0.032166168,0.0012488078,0.00062550796,0.0003105731,0.00064843416,0.20111078,0.030937692,0.013794932,0.018259393,0.6902155],"study_design_scores_gemma":[0.00039968474,0.0030605434,0.015417164,0.00012124283,0.00016507889,0.0004814015,0.0006994578,0.9232418,0.03864157,0.01031295,0.007318796,0.00014033986],"about_ca_topic_score_codex":0.005425026,"about_ca_topic_score_gemma":0.0034134667,"teacher_disagreement_score":0.0068013025,"about_ca_system_score_codex":0.0011678871,"about_ca_system_score_gemma":0.0009790657,"threshold_uncertainty_score":0.035969198},"labels":[],"label_agreement":null},{"id":"W4384303994","doi":"10.1109/access.2023.3295434","title":"On Nonlinear Learned String Indexing","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"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":"Ministero dell'Università e della Ricerca; Università di Pisa; European Commission; University of Toronto; Università degli Studi di Milano","keywords":"Computer science; Search engine indexing; String (physics); Nonlinear system; Artificial intelligence; Mathematics; Physics","score_opus":0.07732365033119193,"score_gpt":0.3572774839214188,"score_spread":0.27995383359022685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384303994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11662299,0.0025388303,0.8582997,0.0021507477,0.00030685047,0.00017020346,0.001310211,0.0043683406,0.014232198],"genre_scores_gemma":[0.62478137,0.0016829293,0.35061696,0.00096755463,0.0003808207,0.00031987377,0.0031456598,0.00042643148,0.01767839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998922,0.00027029854,0.00009084302,0.0002771921,0.00031933383,0.00012032119],"domain_scores_gemma":[0.99534804,0.0024418093,0.00031377992,0.0010736816,0.00069930794,0.00012344943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018297136,0.00066017243,0.0012831998,0.0015377641,0.00048694393,0.0021049478,0.0021845242,0.0017260704,0.00568777],"category_scores_gemma":[0.014234899,0.0003460881,0.00051155087,0.003270821,0.0011847707,0.007396769,0.0021382938,0.0018952579,0.0018032256],"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":[0.00032475378,0.00027490724,0.0020535146,0.00023329539,0.00006167244,0.00014077677,0.00018499166,0.50840175,0.0026721582,0.06274297,0.0103736445,0.41253555],"study_design_scores_gemma":[0.00001123046,0.0000380456,0.0001272991,0.000014770525,0.0000046675627,0.000036854595,0.00002689878,0.97164536,0.0009938048,0.02589913,0.0011940058,0.000007898932],"about_ca_topic_score_codex":0.005061129,"about_ca_topic_score_gemma":0.0044939294,"teacher_disagreement_score":0.00568777,"about_ca_system_score_codex":0.0016265373,"about_ca_system_score_gemma":0.0013928243,"threshold_uncertainty_score":0.019027472},"labels":[],"label_agreement":null},{"id":"W4385367617","doi":"10.1007/978-3-031-38906-1_30","title":"Adaptive Data Structures for 2D Dominance Colored Range Counting","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Colored; Computer science; Data structure; Range (aeronautics); Rank (graph theory); Algorithm; Combinatorics; Mathematics","score_opus":0.05003904904023604,"score_gpt":0.28370346675285135,"score_spread":0.2336644177126153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385367617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023378205,0.0005447913,0.95819473,0.00024807543,0.00018223717,0.00011050028,0.0007101718,0.002259553,0.014371747],"genre_scores_gemma":[0.30490857,0.000578268,0.67367107,0.00043692216,0.00022356315,0.00052809005,0.0018272405,0.0010595426,0.01676667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878424,0.00019451436,0.00010396195,0.0001940343,0.0005438486,0.0001793554],"domain_scores_gemma":[0.99768484,0.0008604497,0.00012451556,0.0008121108,0.00039808213,0.00012000049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006866378,0.0007317477,0.0010696484,0.0016624279,0.0009531784,0.0024186682,0.0020770126,0.0007605517,0.009217292],"category_scores_gemma":[0.0040541743,0.00050604757,0.0007119376,0.003001081,0.0009258448,0.0033222258,0.003432446,0.0018134345,0.0019660522],"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":[0.00031857472,0.00015160356,0.0006253138,0.00024565225,0.000031848158,0.000094680916,0.00020885606,0.05280617,0.016401269,0.6035852,0.018490192,0.30704066],"study_design_scores_gemma":[0.00005606522,0.00008064065,0.00026808024,0.000067542096,0.000020620188,0.00015389636,0.00007049612,0.3747696,0.01145109,0.5897795,0.02322997,0.000052611726],"about_ca_topic_score_codex":0.0012346468,"about_ca_topic_score_gemma":0.002355911,"teacher_disagreement_score":0.009217292,"about_ca_system_score_codex":0.0012728063,"about_ca_system_score_gemma":0.001011287,"threshold_uncertainty_score":0.030834913},"labels":[],"label_agreement":null},{"id":"W4385434808","doi":"10.2139/ssrn.4526745","title":"An Approximation Algorithm for High-Dimensional Table Compression on Balanced K-Partite Graph","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Compression (physics); Table (database); Graph; Algorithm; Computer science; Mathematics; Combinatorics; Discrete mathematics; Data mining; Physics","score_opus":0.017197753718501303,"score_gpt":0.27138489270447336,"score_spread":0.25418713898597206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385434808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10211146,0.0020654078,0.8647719,0.001787003,0.00053017103,0.0004910323,0.0031294073,0.009605345,0.015508394],"genre_scores_gemma":[0.2913978,0.00072955975,0.690176,0.00042167262,0.00026385218,0.00055712485,0.0056880866,0.0005595452,0.010206352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900264,0.00012618727,0.000076575794,0.0001993204,0.00040470404,0.00019066012],"domain_scores_gemma":[0.9980488,0.0006349415,0.00011245445,0.00080990215,0.0002939858,0.000099964505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005283036,0.0011691817,0.0015585856,0.0021700542,0.0010563572,0.0024355438,0.0025111386,0.0015474298,0.0117844045],"category_scores_gemma":[0.0039460906,0.0005305176,0.00091773144,0.0057509365,0.00066901435,0.0034704728,0.0023513315,0.001544274,0.0035739462],"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":[0.001029494,0.00042321565,0.0015985753,0.00040450858,0.000105268366,0.0001977032,0.00033791026,0.10614678,0.012097513,0.02966368,0.051614996,0.79638046],"study_design_scores_gemma":[0.00029348492,0.00023174053,0.0007816236,0.00005066167,0.000083626364,0.00045039615,0.00025766154,0.919521,0.009338601,0.059289925,0.009660508,0.000040717194],"about_ca_topic_score_codex":0.0049552526,"about_ca_topic_score_gemma":0.007955294,"teacher_disagreement_score":0.0117844045,"about_ca_system_score_codex":0.001658805,"about_ca_system_score_gemma":0.0022356417,"threshold_uncertainty_score":0.03942275},"labels":[],"label_agreement":null},{"id":"W4385849427","doi":"10.4230/lipics.itcs.2023.73","title":"Recovery from Non-Decomposable Distance Oracles","year":2023,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Hamming distance; Sequence (biology); Combinatorics; Edit distance; Function (biology); Mathematics; Earth mover's distance; Dynamic time warping; Set (abstract data type); Alphabet; Estimator; Algorithm; Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.02600066608497223,"score_gpt":0.27197818908609694,"score_spread":0.24597752300112471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385849427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12298472,0.0014828206,0.86411667,0.003535634,0.00017189007,0.00020968725,0.0013646529,0.002969064,0.0031648548],"genre_scores_gemma":[0.78353816,0.000710215,0.20515692,0.0011656675,0.000274003,0.0002449167,0.0029264414,0.00051544135,0.0054682246],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9864049,0.0044297758,0.0012140526,0.0035460808,0.003273253,0.0011319264],"domain_scores_gemma":[0.9208339,0.053984486,0.0036096221,0.017962225,0.002312533,0.0012971807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007818488,0.0018900685,0.003702161,0.0012211656,0.0010176396,0.0032002297,0.0049886727,0.0041542808,0.004827549],"category_scores_gemma":[0.070506744,0.00084009813,0.0013249258,0.0023107962,0.0022617327,0.012660645,0.0068568187,0.006713787,0.0018551092],"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":[0.00475349,0.0008078185,0.008340429,0.0015458746,0.00036851733,0.0015240504,0.0013426611,0.3653674,0.029900787,0.18657203,0.01733278,0.38214424],"study_design_scores_gemma":[0.00015497213,0.00033154522,0.0010004422,0.00008768367,0.00005103469,0.00093484315,0.00039132376,0.7351485,0.015138939,0.24371734,0.00297246,0.00007095364],"about_ca_topic_score_codex":0.0010710148,"about_ca_topic_score_gemma":0.0010328571,"teacher_disagreement_score":0.007818488,"about_ca_system_score_codex":0.0018935069,"about_ca_system_score_gemma":0.00227168,"threshold_uncertainty_score":0.041348636},"labels":[],"label_agreement":null},{"id":"W4385859907","doi":"10.2139/ssrn.4543219","title":"Reconstructing Parameterized Strings from Parameterized Suffix and Lcp Arrays","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Parameterized complexity; Suffix; Computer science; Theoretical computer science; Mathematics; Combinatorics; Algorithm; Linguistics; Philosophy","score_opus":0.027518745345525914,"score_gpt":0.25605279039130624,"score_spread":0.22853404504578032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385859907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08075708,0.00051692635,0.9078742,0.00039475271,0.00015860793,0.00006622667,0.001491995,0.005127488,0.0036126084],"genre_scores_gemma":[0.40600607,0.000681705,0.5773995,0.00023125939,0.00021160723,0.0002230208,0.0064813504,0.0012864535,0.0074789114],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985915,0.0002340723,0.00014215709,0.00025677893,0.00064520125,0.00013026458],"domain_scores_gemma":[0.99381703,0.0023676963,0.0003568317,0.0026468127,0.00071632373,0.00009532602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071894896,0.0009209768,0.0012323444,0.001224291,0.0005390697,0.0018061996,0.0013607596,0.0017249779,0.0040674517],"category_scores_gemma":[0.009426881,0.0006123349,0.0007222019,0.0047693676,0.0008491987,0.004180842,0.002113006,0.0017775706,0.0025670181],"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":[0.0012285259,0.00016399546,0.0030628953,0.00041428342,0.00008929613,0.001074532,0.00041378767,0.1296403,0.05307234,0.054801956,0.014257308,0.7417808],"study_design_scores_gemma":[0.00006461697,0.0001809684,0.00081187097,0.0000690971,0.0000507618,0.0008139529,0.00031080726,0.81958663,0.06971348,0.09718526,0.011163163,0.00004931361],"about_ca_topic_score_codex":0.00092952483,"about_ca_topic_score_gemma":0.0012153034,"teacher_disagreement_score":0.0040674517,"about_ca_system_score_codex":0.00064904435,"about_ca_system_score_gemma":0.0011946191,"threshold_uncertainty_score":0.013606966},"labels":[],"label_agreement":null},{"id":"W4386057567","doi":"10.1109/isit54713.2023.10206482","title":"Variable-Length Insertion-Based Noisy Sorting","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of British Columbia","funders":"Research and Development","keywords":"Upper and lower bounds; Sorting; sort; Generalization; Algorithm; Variable (mathematics); Sorting algorithm; Random variable; Mathematics; Pairwise comparison; Computer science; Combinatorics; Statistics; Arithmetic","score_opus":0.018834741055162724,"score_gpt":0.247500060530457,"score_spread":0.22866531947529428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386057567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10209643,0.00054873864,0.89342123,0.0007286016,0.000055500233,0.00006728311,0.00023792045,0.00057178753,0.0022725156],"genre_scores_gemma":[0.8230366,0.00044935985,0.17225897,0.0003212372,0.00014832085,0.00016603801,0.0003838622,0.0001498124,0.003085782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99536705,0.0013947645,0.00027218476,0.0009396245,0.0014901604,0.0005361281],"domain_scores_gemma":[0.9722225,0.019515743,0.0031881668,0.002899193,0.0016854113,0.0004890033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038118837,0.0008530713,0.0017152359,0.0010440995,0.001197599,0.002279978,0.0034503383,0.0021039385,0.001621106],"category_scores_gemma":[0.029381854,0.00064907345,0.00064952264,0.0028764668,0.0030973696,0.006529629,0.00231819,0.0016486478,0.00050166226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012082093,0.00013421578,0.0020723278,0.00037330476,0.00007464222,0.0002055289,0.00041015932,0.77694154,0.012917283,0.15612748,0.0015351456,0.048000265],"study_design_scores_gemma":[0.000029903775,0.00011995459,0.00026590287,0.00002079467,0.000019579473,0.00012185429,0.000050564147,0.9346514,0.008019327,0.055892576,0.0007788779,0.00002933699],"about_ca_topic_score_codex":0.0013896186,"about_ca_topic_score_gemma":0.0010820146,"teacher_disagreement_score":0.0038118837,"about_ca_system_score_codex":0.0028346288,"about_ca_system_score_gemma":0.0020692241,"threshold_uncertainty_score":0.020566821},"labels":[],"label_agreement":null},{"id":"W4386204710","doi":"10.1145/3603719.3603731","title":"LearnedSort as a learning-augmented SampleSort: Analysis and Parallelization","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Sorting; Parallel computing; Sorting algorithm; Artificial intelligence; Machine learning; Algorithm","score_opus":0.014163461194530746,"score_gpt":0.26675791890903194,"score_spread":0.2525944577145012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386204710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03765986,0.0007577105,0.93087053,0.00079566304,0.0003788045,0.00023610692,0.0005192676,0.019690963,0.00909109],"genre_scores_gemma":[0.26524633,0.000515474,0.72138834,0.0005246992,0.00022608801,0.00039226562,0.0017430347,0.0033324268,0.0066312766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682474,0.00054622965,0.00023389449,0.0005704954,0.0014979937,0.0003266536],"domain_scores_gemma":[0.9935489,0.00240087,0.0003305925,0.002301325,0.0011996281,0.00021869426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025367166,0.0013763589,0.0011161233,0.0013482736,0.00082504255,0.0032255626,0.003023261,0.00094286026,0.0076048793],"category_scores_gemma":[0.0146054,0.00057887135,0.0011332002,0.0025915354,0.0015926249,0.0058765877,0.0020045415,0.0023389894,0.0025604165],"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":[0.0009921992,0.00035042898,0.0037727754,0.0003801838,0.00013765556,0.00020952449,0.00029144308,0.28110132,0.007957189,0.120831855,0.0300399,0.5539355],"study_design_scores_gemma":[0.00009848193,0.000099921715,0.00025973094,0.00003057862,0.00002832006,0.00012421673,0.00006324984,0.9270291,0.011413813,0.050123923,0.010705237,0.000023562628],"about_ca_topic_score_codex":0.005208333,"about_ca_topic_score_gemma":0.007927111,"teacher_disagreement_score":0.0076048793,"about_ca_system_score_codex":0.0024694426,"about_ca_system_score_gemma":0.0055674375,"threshold_uncertainty_score":0.025440812},"labels":[],"label_agreement":null},{"id":"W4386512674","doi":"10.2139/ssrn.4564689","title":"On Suffix Tree Detection","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Tree (set theory); Suffix tree; Computer science; Mathematics; Linguistics; Combinatorics; Philosophy","score_opus":0.017018526587958768,"score_gpt":0.2568507696630004,"score_spread":0.23983224307504164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386512674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024108518,0.0032355906,0.9564677,0.0014327256,0.0008650491,0.00012977215,0.000571596,0.0033509368,0.00983816],"genre_scores_gemma":[0.2236293,0.0034103894,0.7349882,0.0012746066,0.001826103,0.00026474145,0.0035546923,0.0010533726,0.029998554],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964439,0.00078145746,0.00029483472,0.00071027194,0.0015175164,0.0002520951],"domain_scores_gemma":[0.991025,0.0047340845,0.0002889488,0.0023284308,0.0014233515,0.00020021312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018826419,0.0014916842,0.002219278,0.00442055,0.0016158543,0.0032753556,0.002298357,0.0028366041,0.010813408],"category_scores_gemma":[0.014957635,0.0009842085,0.0009684114,0.006635626,0.0015702089,0.005764022,0.0041464446,0.0021665175,0.006136088],"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":[0.0005183059,0.00013590886,0.001363463,0.00022966634,0.00009624762,0.0002301362,0.00013905359,0.018257871,0.016598387,0.034960065,0.019270474,0.90820044],"study_design_scores_gemma":[0.00006635257,0.00023269218,0.0016093029,0.00012883185,0.00012385457,0.0013333041,0.00016754708,0.70887107,0.03428059,0.21907157,0.034042582,0.00007228011],"about_ca_topic_score_codex":0.0017859584,"about_ca_topic_score_gemma":0.0019510355,"teacher_disagreement_score":0.010813408,"about_ca_system_score_codex":0.0007718774,"about_ca_system_score_gemma":0.0013635058,"threshold_uncertainty_score":0.036174476},"labels":[],"label_agreement":null},{"id":"W4386834334","doi":"10.18280/ria.370417","title":"Parallelizing Depth-First Search for Pathway Finding: A Comprehensive Investigation","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.14476380060569244,"score_gpt":0.3224520307446102,"score_spread":0.17768823013891777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386834334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08079428,0.006615842,0.9050594,0.0006146006,0.00005543005,0.00027015412,0.00018851741,0.00086533866,0.005536467],"genre_scores_gemma":[0.20311064,0.005656252,0.7890092,0.00011865751,0.00003762893,0.00016227161,0.00035979014,0.00012302428,0.0014225363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994929,0.00014068274,0.000030050478,0.00009611752,0.00020590019,0.00003438044],"domain_scores_gemma":[0.998458,0.0010499499,0.00010383883,0.0001646546,0.00018952189,0.0000341231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010392372,0.00056602183,0.0007847419,0.0011957114,0.00051875226,0.0010138056,0.00080289604,0.00058554776,0.0014124581],"category_scores_gemma":[0.0046765367,0.00034304464,0.0005314129,0.0020105084,0.00052025536,0.0014862092,0.0006785292,0.0007075378,0.00028080924],"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":[0.00021653685,0.00018812418,0.002481484,0.0009156199,0.00010111297,0.00018467601,0.00023247745,0.2872056,0.024195835,0.027491543,0.001816549,0.6549704],"study_design_scores_gemma":[0.000082152765,0.00022320407,0.0011081109,0.00005957608,0.000061610786,0.00042906482,0.00013260497,0.9451832,0.016203806,0.025998306,0.010488067,0.000030258936],"about_ca_topic_score_codex":0.0034787694,"about_ca_topic_score_gemma":0.0047420417,"teacher_disagreement_score":0.0034787694,"about_ca_system_score_codex":0.0008333375,"about_ca_system_score_gemma":0.0021977006,"threshold_uncertainty_score":0.0069170594},"labels":[],"label_agreement":null},{"id":"W4386843758","doi":"10.1109/dcc55655.2023.00023","title":"Computing matching statistics on Wheeler DFAs","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"HORIZON EUROPE Health; National Human Genome Research Institute; Science and Engineering Research Council; National Institute of Allergy and Infectious Diseases; Gruppo Nazionale per il Calcolo Scientifico; National Institutes of Health; EGI; Israel Institute for Biological Research; Natural Sciences and Engineering Research Council of Canada; European Commission; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; National Science Foundation","keywords":"Computer science; String searching algorithm; Suffix tree; Compressed suffix array; Deterministic finite automaton; Automaton; Pattern matching; Prefix; Tree (set theory); Matching (statistics); Subroutine; Algorithm; Theoretical computer science; Approximate string matching; String (physics); Suffix; Data structure; Mathematics; Combinatorics; Artificial intelligence; Programming language; Statistics","score_opus":0.023919021054752465,"score_gpt":0.2826896403153684,"score_spread":0.25877061926061595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386843758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07415304,0.00027161645,0.9164064,0.00019198029,0.000062207575,0.00009845114,0.0016509476,0.004698219,0.0024673138],"genre_scores_gemma":[0.51171625,0.00029263497,0.47787905,0.00027061367,0.00007597213,0.00038090834,0.004276784,0.0007574415,0.004350423],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975539,0.00036335632,0.00029498784,0.00075138797,0.0007917679,0.00024457634],"domain_scores_gemma":[0.99354666,0.003277353,0.0006372839,0.0014939149,0.00087636494,0.00016837746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011860727,0.0006396936,0.001359722,0.0037368345,0.0008995874,0.002417965,0.0018559572,0.0014829851,0.004011158],"category_scores_gemma":[0.016711174,0.0005409466,0.00086395803,0.0049899486,0.0013094379,0.0066599282,0.002165623,0.0011016116,0.0019340052],"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":[0.0005966457,0.00018258212,0.008744922,0.00028501754,0.00013468991,0.00039902882,0.0005060555,0.26690638,0.030769655,0.30683956,0.0057370844,0.37889835],"study_design_scores_gemma":[0.000021679087,0.00006941206,0.0007791145,0.000029490026,0.000025919686,0.00012766673,0.000108870045,0.67205566,0.018403562,0.30265194,0.0056792363,0.000047402584],"about_ca_topic_score_codex":0.0039397255,"about_ca_topic_score_gemma":0.0060282485,"teacher_disagreement_score":0.004011158,"about_ca_system_score_codex":0.0019746772,"about_ca_system_score_gemma":0.0014765328,"threshold_uncertainty_score":0.014327288},"labels":[],"label_agreement":null},{"id":"W4386870585","doi":"10.1007/978-3-031-43980-3_18","title":"Dynamic Compact Planar Embeddings","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Planar; Vertex (graph theory); Computer science; Planar graph; Combinatorics; Polygon (computer graphics); Simple (philosophy); Enhanced Data Rates for GSM Evolution; Face (sociological concept); Planar straight-line graph; Graph; Set (abstract data type); Mathematics; 1-planar graph; Artificial intelligence; Computer graphics (images); Chordal graph; Telecommunications","score_opus":0.01652075080171293,"score_gpt":0.26229441082069027,"score_spread":0.24577366001897735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386870585","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068971485,0.0047115143,0.2810504,0.0022124837,0.0010940895,0.00009203142,0.0019204434,0.0015834075,0.6383641],"genre_scores_gemma":[0.47583655,0.008446029,0.08882142,0.00069684035,0.0007953262,0.000199706,0.005170861,0.0021295655,0.41790378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99976414,0.000022414119,0.000008440349,0.00006052031,0.00010718437,0.000037359518],"domain_scores_gemma":[0.999762,0.00005206281,0.000027123793,0.000071569644,0.0000509825,0.000036184876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001437884,0.0009969501,0.00051584136,0.0011903316,0.00070115697,0.0018958405,0.0007630687,0.0006358854,0.031129258],"category_scores_gemma":[0.00095586665,0.0005054674,0.00035177177,0.0014840184,0.0008399976,0.00408726,0.0027755573,0.002271359,0.008988032],"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":[0.000101071746,0.00003103584,0.00011285221,0.00014434928,0.000011048096,0.000106188476,0.00022270577,0.0042226017,0.0056432486,0.8234711,0.03302859,0.13290519],"study_design_scores_gemma":[0.000022140692,0.00005255704,0.0002699159,0.00007312531,0.00001756166,0.00060786126,0.00034171512,0.012979393,0.004837554,0.7555098,0.22526531,0.000023028231],"about_ca_topic_score_codex":0.0005041502,"about_ca_topic_score_gemma":0.0005690926,"teacher_disagreement_score":0.031129258,"about_ca_system_score_codex":0.0006854923,"about_ca_system_score_gemma":0.00025062723,"threshold_uncertainty_score":0.10413778},"labels":[],"label_agreement":null},{"id":"W4386870861","doi":"10.1007/978-3-031-43980-3_12","title":"Space-Time Trade-Offs for the LCP Array of Wheeler DFAs","year":2023,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute","keywords":"De Bruijn sequence; Computer science; Logarithm; De Bruijn graph; Time complexity; Alphabet; Matching (statistics); Algorithm; Graph; Discrete mathematics; Theoretical computer science; Mathematics","score_opus":0.017885274966969542,"score_gpt":0.2613994950617137,"score_spread":0.2435142200947442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386870861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3058998,0.0037214903,0.57945025,0.0020844117,0.0003218285,0.00010626723,0.00065009843,0.002529449,0.10523646],"genre_scores_gemma":[0.91915536,0.0004239872,0.0686243,0.00015218437,0.0000738631,0.00006194135,0.00017817982,0.00021883869,0.011111304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99897075,0.00029404,0.000041741892,0.00013121968,0.0003229354,0.00023928455],"domain_scores_gemma":[0.9945334,0.0037091523,0.0002225985,0.0006083441,0.0007120081,0.0002143634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012488723,0.00044747622,0.00061663706,0.0008345819,0.0009485382,0.0020369396,0.0010140998,0.0011476704,0.020794846],"category_scores_gemma":[0.00924561,0.00021569179,0.00028879472,0.0013183741,0.00066237827,0.0026243948,0.0010440144,0.00070537336,0.002436445],"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":[0.0025591105,0.00019333322,0.0024211789,0.00038335766,0.00007020085,0.00022617563,0.00026103682,0.29737264,0.04736881,0.36711955,0.014596775,0.2674279],"study_design_scores_gemma":[0.00006088926,0.00031652817,0.00060837803,0.00005967159,0.000044400866,0.0003855505,0.00020833271,0.8823804,0.017113525,0.0908344,0.007942499,0.000045402205],"about_ca_topic_score_codex":0.0014943179,"about_ca_topic_score_gemma":0.0022501873,"teacher_disagreement_score":0.020794846,"about_ca_system_score_codex":0.0012924728,"about_ca_system_score_gemma":0.0007194054,"threshold_uncertainty_score":0.069565654},"labels":[],"label_agreement":null},{"id":"W4386870921","doi":"10.1007/978-3-031-43980-3_19","title":"A Simple Grammar-Based Index for Finding Approximately Longest Common Substrings","year":2023,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; Agencia Nacional de Investigación y Desarrollo; National Institutes of Health; National Science Foundation","keywords":"Substring; Combinatorics; Correctness; Grammar; Computer science; Simple (philosophy); Mathematics; Algorithm; Data structure; Programming language; Linguistics","score_opus":0.030039597999010327,"score_gpt":0.2919689418882067,"score_spread":0.26192934388919636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386870921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11495471,0.0015381157,0.8617038,0.00032348945,0.00032766524,0.00059421954,0.0059534973,0.009509221,0.005095233],"genre_scores_gemma":[0.18002044,0.0004990074,0.8037736,0.00020916964,0.00020985317,0.0003696187,0.010449564,0.00084485544,0.003623891],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853384,0.00014819822,0.00021579457,0.00034749266,0.0006518843,0.0001028594],"domain_scores_gemma":[0.9958444,0.0015690154,0.0003182823,0.001003094,0.0010318456,0.0002333932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077573804,0.0007537966,0.0019960809,0.006608822,0.0010229718,0.0017955131,0.0019442638,0.0009955055,0.0051366864],"category_scores_gemma":[0.0061799767,0.0005114653,0.00087924465,0.0069479262,0.00079312874,0.0032022928,0.0021382223,0.0008884807,0.00291249],"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":[0.0008995932,0.0004219243,0.0055555156,0.0006663097,0.00015483405,0.0006169552,0.00051020505,0.011523455,0.095663086,0.017123964,0.01841738,0.8484467],"study_design_scores_gemma":[0.00069345953,0.0017201438,0.011299821,0.00023740734,0.00063393806,0.003912911,0.0009929581,0.6508189,0.08248269,0.18438093,0.062494513,0.00033240332],"about_ca_topic_score_codex":0.002040235,"about_ca_topic_score_gemma":0.0045100236,"teacher_disagreement_score":0.006608822,"about_ca_system_score_codex":0.00064911676,"about_ca_system_score_gemma":0.0025004845,"threshold_uncertainty_score":0.01718396},"labels":[],"label_agreement":null},{"id":"W4386870944","doi":"10.1007/978-3-031-43980-3_2","title":"On Suffix Tree Detection","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalized suffix tree; Suffix tree; Compressed suffix array; Suffix; String (physics); Time complexity; K-ary tree; Combinatorics; Tree (set theory); Data structure; Computer science; Mathematics; Binary tree; Algorithm; Discrete mathematics; Tree structure","score_opus":0.018697022966807312,"score_gpt":0.24320110693476188,"score_spread":0.22450408396795457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386870944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008092179,0.0029762888,0.9660045,0.00060017966,0.0007560896,0.00014124723,0.00062400295,0.0059657,0.014839786],"genre_scores_gemma":[0.074969865,0.0029631483,0.8769959,0.0007126794,0.0009468845,0.00021275693,0.003940787,0.0010218782,0.03823615],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980975,0.0002913755,0.00014210657,0.00044570823,0.0008874142,0.00013603736],"domain_scores_gemma":[0.9967843,0.0012975056,0.00009889535,0.0009993117,0.00072954147,0.000090447335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010747833,0.0014512014,0.0019463125,0.0033125454,0.0013374055,0.0026845566,0.00259901,0.0018779874,0.018408135],"category_scores_gemma":[0.0063608694,0.00088500214,0.0010351287,0.005167562,0.0009930922,0.004520016,0.003296396,0.0015385477,0.012316159],"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":[0.0001887469,0.00008270368,0.00051822327,0.00016446695,0.000050907518,0.00012176076,0.00006376228,0.0064687445,0.013865234,0.02058422,0.023483412,0.93440783],"study_design_scores_gemma":[0.00006193137,0.00026616864,0.001955384,0.00017898506,0.00014879067,0.002460477,0.00019534976,0.58886456,0.054835074,0.22830382,0.122618355,0.00011109239],"about_ca_topic_score_codex":0.0021558714,"about_ca_topic_score_gemma":0.003013922,"teacher_disagreement_score":0.018408135,"about_ca_system_score_codex":0.00066408585,"about_ca_system_score_gemma":0.0011620794,"threshold_uncertainty_score":0.061581373},"labels":[],"label_agreement":null},{"id":"W4387043540","doi":"10.48009/1_iis_2023_113","title":"ELLIPTIC CURVE CRYPTOGRAPHY: IMPLEMENTATION USING GOOGLE APPS SCRIPT (GAS)","year":2023,"lang":"en","type":"article","venue":"Issues in Information Systems","topic":"Algorithms and Data Compression","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":"Kwantlen Polytechnic University","funders":"","keywords":"Elliptic curve cryptography; Cryptography; Computer science; Elliptic Curve Digital Signature Algorithm; Elliptic curve; World Wide Web; Computer security; Public-key cryptography; Mathematics; Encryption; Pure mathematics","score_opus":0.030576825278949244,"score_gpt":0.3245916267998608,"score_spread":0.2940148015209116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387043540","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072133034,0.0007930662,0.39012134,0.0011317063,0.0006106751,0.0016819027,0.0043505873,0.4265366,0.10264114],"genre_scores_gemma":[0.5681626,0.0013315543,0.32288653,0.0010767013,0.00015354526,0.0015903534,0.009146481,0.034992073,0.06066014],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992047,0.00012575788,0.000078138335,0.00007805895,0.0003481203,0.00016522463],"domain_scores_gemma":[0.9987238,0.0003319264,0.00007660124,0.00028232893,0.00050655083,0.00007878464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078201527,0.0008254365,0.00048443745,0.0008299134,0.00045850384,0.0013486878,0.0015211941,0.00095610984,0.021862313],"category_scores_gemma":[0.0035109029,0.0006243634,0.00066055515,0.00094416115,0.0005959811,0.002107334,0.0014404441,0.0011554373,0.014082106],"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":[0.0038687824,0.0006183594,0.009551916,0.0018013641,0.00016492807,0.0035478913,0.0023231886,0.020659842,0.038437206,0.06880507,0.32778892,0.52243245],"study_design_scores_gemma":[0.0008655985,0.0008271635,0.005301197,0.00054357585,0.00014507172,0.002503539,0.00065236003,0.25237474,0.14010783,0.031081004,0.5652449,0.0003530409],"about_ca_topic_score_codex":0.002861183,"about_ca_topic_score_gemma":0.0020145646,"teacher_disagreement_score":0.021862313,"about_ca_system_score_codex":0.0004884243,"about_ca_system_score_gemma":0.0009431892,"threshold_uncertainty_score":0.07313669},"labels":[],"label_agreement":null},{"id":"W4387466501","doi":"10.1007/978-3-031-38700-5_4","title":"More Complex Rules","year":2023,"lang":"en","type":"book-chapter","venue":"Understanding complex systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Decomposition; Computer science; Mathematics; Algorithm; Chemistry","score_opus":0.22929924075184518,"score_gpt":0.2966105017859472,"score_spread":0.06731126103410204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387466501","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00568148,0.0021304798,0.23168226,0.0033285972,0.0013108754,0.00010532024,0.00064384507,0.00089868816,0.7542184],"genre_scores_gemma":[0.11619158,0.0043850834,0.19584641,0.0031160114,0.0013192261,0.00021640134,0.0024802766,0.0014168802,0.6750282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989097,0.00017055469,0.00007396468,0.0003182069,0.00046696502,0.000060635997],"domain_scores_gemma":[0.9982169,0.0006504341,0.000067361,0.00077367696,0.00023182842,0.00005974818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009673449,0.00082262896,0.00084425695,0.0013205563,0.00097507954,0.0054895612,0.001388452,0.001327963,0.09106505],"category_scores_gemma":[0.004673799,0.00053838623,0.0010249751,0.001492568,0.0029750483,0.010133567,0.0022016817,0.003637419,0.025090465],"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":[0.00002276824,0.000041230473,0.00011433528,0.00013282693,0.00001714662,0.000079640435,0.00038042,0.002033936,0.0012119552,0.8615901,0.029168416,0.105207294],"study_design_scores_gemma":[0.000010070584,0.000015936355,0.00014599157,0.000085281354,0.000016618365,0.00017564774,0.00012653315,0.005537821,0.0009140656,0.65491724,0.33803856,0.000016211603],"about_ca_topic_score_codex":0.0016146116,"about_ca_topic_score_gemma":0.0018756177,"teacher_disagreement_score":0.09106505,"about_ca_system_score_codex":0.0009395114,"about_ca_system_score_gemma":0.000786828,"threshold_uncertainty_score":0.30464292},"labels":[],"label_agreement":null},{"id":"W4387466535","doi":"10.1007/978-3-031-38700-5_6","title":"Rules with Additive Invariants","year":2023,"lang":"en","type":"book-chapter","venue":"Understanding complex systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Finite-state machine; Representation (politics); Mathematics; Order (exchange); State (computer science); Discrete mathematics; Pure mathematics; Algebra over a field; Algorithm","score_opus":0.15089610602052972,"score_gpt":0.2572988326939254,"score_spread":0.10640272667339568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387466535","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005503135,0.0016895685,0.4338919,0.00089712156,0.0011207963,0.000099565485,0.00039283046,0.0012614696,0.5551436],"genre_scores_gemma":[0.2858333,0.0035371804,0.32060817,0.0015332258,0.0013654303,0.00032147142,0.0017230352,0.0017480823,0.3833301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988813,0.00016554585,0.00009535026,0.0002795136,0.00048388305,0.000094365496],"domain_scores_gemma":[0.99916637,0.0003394417,0.00003588792,0.00027665717,0.00014566287,0.000036076788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072803133,0.0008670019,0.0007242233,0.0017984204,0.001334561,0.004228904,0.0012617824,0.0008071624,0.021024397],"category_scores_gemma":[0.0027306655,0.0006236448,0.0011089732,0.0015957534,0.0035601216,0.005892147,0.0022521527,0.0033166886,0.009260691],"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":[0.000007822646,0.000013087855,0.0000371156,0.00004508961,0.0000056939193,0.00003484797,0.00014634314,0.00050927047,0.00043936516,0.9474414,0.0072087497,0.044111162],"study_design_scores_gemma":[0.0000034399552,0.0000068869176,0.000050674156,0.00002715731,0.0000109569755,0.000078429555,0.000043550954,0.0019349915,0.0010385211,0.9237728,0.07302352,0.000009028878],"about_ca_topic_score_codex":0.0008932486,"about_ca_topic_score_gemma":0.0009780951,"teacher_disagreement_score":0.021024397,"about_ca_system_score_codex":0.0009875218,"about_ca_system_score_gemma":0.0005642914,"threshold_uncertainty_score":0.07033366},"labels":[],"label_agreement":null},{"id":"W4387565284","doi":"10.20944/preprints202310.0408.v1","title":"Two-way Linear Probing Revisited","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hash function; Hash table; Matching (statistics); Mathematics; Constant (computer programming); Construct (python library); Combinatorics; Cluster (spacecraft); Binary logarithm; Discrete mathematics; Algorithm; Computer science; Statistics","score_opus":0.16658087791112158,"score_gpt":0.36691611365995097,"score_spread":0.2003352357488294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387565284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024350904,0.0010089041,0.96394104,0.00092061365,0.00018136327,0.0001312736,0.00014681194,0.0019399296,0.0073791067],"genre_scores_gemma":[0.63189656,0.00087780517,0.3520481,0.00096981105,0.00019299443,0.0004920168,0.00036676647,0.00038170812,0.012774179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99573576,0.0012979356,0.00021343301,0.00071054394,0.001354365,0.0006879092],"domain_scores_gemma":[0.99146795,0.0024664148,0.0004958275,0.0045367796,0.00073632883,0.00029668293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002423489,0.00086325244,0.0010768997,0.0008875998,0.0011214964,0.0025875375,0.003529741,0.0021777041,0.006995354],"category_scores_gemma":[0.010753199,0.000834347,0.0008556523,0.002473403,0.003352671,0.009204129,0.0061591472,0.003531472,0.0024010695],"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":[0.0011521939,0.00029309746,0.0022068643,0.00067758374,0.00010478306,0.00034793175,0.0009917109,0.06371089,0.04060943,0.644219,0.010645184,0.23504129],"study_design_scores_gemma":[0.00020547524,0.00054370053,0.000621272,0.00009630532,0.00006212616,0.0014025945,0.0002826969,0.5173884,0.055284463,0.38971472,0.03420783,0.00019036965],"about_ca_topic_score_codex":0.00051434856,"about_ca_topic_score_gemma":0.00035846757,"teacher_disagreement_score":0.006995354,"about_ca_system_score_codex":0.0014002756,"about_ca_system_score_gemma":0.0012107961,"threshold_uncertainty_score":0.023401797},"labels":[],"label_agreement":null},{"id":"W4388023877","doi":"10.3390/a16110500","title":"Two-Way Linear Probing Revisited","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear hashing; Hash function; Computer science; Hash table; Algorithm; Sequence (biology); Cluster (spacecraft); Cluster analysis; Mathematics; Perfect hash function; Statistics","score_opus":0.02678644394421046,"score_gpt":0.2875815398217454,"score_spread":0.2607950958775349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388023877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045195684,0.0008326151,0.9456241,0.0007730292,0.000077574514,0.00014153402,0.00009592283,0.0012117093,0.0060478733],"genre_scores_gemma":[0.74966973,0.0006660489,0.2402077,0.0005154219,0.00011231946,0.00041045534,0.00020977795,0.00023499595,0.007973455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99542505,0.001508897,0.00023057565,0.0007518567,0.0013937567,0.0006899201],"domain_scores_gemma":[0.98686814,0.005934943,0.0008504385,0.0047941958,0.0011483509,0.0004039517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003335583,0.00062408444,0.0011662102,0.00091177115,0.0012805754,0.002577944,0.0030593448,0.0018145709,0.0043180306],"category_scores_gemma":[0.016591217,0.00071216805,0.0008196087,0.002487016,0.003025724,0.008978824,0.006024173,0.0024654123,0.0012529494],"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":[0.0012324535,0.00028977852,0.0055802846,0.0007709291,0.00013550313,0.00054448214,0.0014965174,0.088414975,0.03061151,0.5582793,0.007198459,0.3054459],"study_design_scores_gemma":[0.00013800092,0.0005648269,0.0010195225,0.000078879544,0.00006594763,0.0022413759,0.00047867984,0.6414569,0.0346099,0.30157536,0.017652266,0.000118216674],"about_ca_topic_score_codex":0.00048598036,"about_ca_topic_score_gemma":0.0003743723,"teacher_disagreement_score":0.0043180306,"about_ca_system_score_codex":0.001333554,"about_ca_system_score_gemma":0.0012167733,"threshold_uncertainty_score":0.017640471},"labels":[],"label_agreement":null},{"id":"W4388399378","doi":"10.1101/2023.11.04.565615","title":"Movi: a fast and cache-efficient full-text pangenome index","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University; National Institutes of Health; National Science Foundation","keywords":"Cache; Computer science; Index (typography); Matching (statistics); Nanopore sequencing; Algorithm; Locality; Latency (audio); Interval (graph theory); Parallel computing; Mathematics; Statistics; Combinatorics; DNA sequencing; Programming language","score_opus":0.01870896721342896,"score_gpt":0.22117607506938886,"score_spread":0.2024671078559599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388399378","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06292057,0.006652065,0.5964432,0.0012029337,0.0008954,0.00074662827,0.035007473,0.2812864,0.014845316],"genre_scores_gemma":[0.1783708,0.0020418852,0.6873871,0.000937088,0.00041472397,0.0010984135,0.106928505,0.00983787,0.012983679],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998922,0.0000811578,0.000121217694,0.00026627452,0.00048015098,0.0001292039],"domain_scores_gemma":[0.9984219,0.00041229778,0.00017300094,0.00042906316,0.00040694812,0.00015673306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010046292,0.0013523438,0.0013081913,0.002906377,0.00094409403,0.002219263,0.0038096264,0.0012842653,0.007605297],"category_scores_gemma":[0.004978333,0.0008977623,0.0010116406,0.004646724,0.00065781793,0.004699465,0.0033076277,0.0014371742,0.005265588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024091317,0.0003120355,0.0055710617,0.0015375179,0.00028240777,0.0005263716,0.0007290512,0.013143231,0.118327096,0.017224737,0.19625255,0.64368474],"study_design_scores_gemma":[0.0010039633,0.0010056469,0.0071886904,0.00023246309,0.00026418592,0.0012185697,0.00045535513,0.43848145,0.22129527,0.03193435,0.29638734,0.00053275103],"about_ca_topic_score_codex":0.004233935,"about_ca_topic_score_gemma":0.0048046154,"teacher_disagreement_score":0.007605297,"about_ca_system_score_codex":0.0010955944,"about_ca_system_score_gemma":0.0020174715,"threshold_uncertainty_score":0.025442183},"labels":[],"label_agreement":null},{"id":"W4388470009","doi":"10.1137/1.9781611977509","title":"Computational Discovery on Jupyter","year":2023,"lang":"en","type":"book","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","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":"Impact; Western University","funders":"","keywords":"Computer science","score_opus":0.06086778104871948,"score_gpt":0.25914641425711454,"score_spread":0.19827863320839506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388470009","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059155732,0.014650908,0.19532554,0.03875877,0.005283006,0.00015355337,0.0013287733,0.00407743,0.6812663],"genre_scores_gemma":[0.6033949,0.006005906,0.13504823,0.0046716426,0.0022561823,0.00028442466,0.001467069,0.0016099161,0.24526171],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901736,0.0003728527,0.000027288854,0.00019696172,0.00025076396,0.00013470413],"domain_scores_gemma":[0.99853384,0.0009562608,0.000057094483,0.0002028092,0.00014262483,0.000107363485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012998037,0.000565353,0.0006521306,0.0017411727,0.004049077,0.0036857037,0.0009882055,0.0011072261,0.021532618],"category_scores_gemma":[0.0061062835,0.00042998674,0.0009417179,0.0017780461,0.005470766,0.0068211183,0.004646651,0.0030282824,0.0028156221],"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":[0.000046522455,0.000010108168,0.00014449273,0.000042417592,0.000007008805,0.00012664714,0.00048663514,0.0016672802,0.0001488852,0.9613514,0.022686819,0.013281902],"study_design_scores_gemma":[0.00002124463,0.000016897233,0.00031677252,0.000066726236,0.00000829654,0.00012437424,0.00012630045,0.0073991376,0.0004482848,0.77558464,0.21586537,0.000021957085],"about_ca_topic_score_codex":0.0052855187,"about_ca_topic_score_gemma":0.0046467,"teacher_disagreement_score":0.021532618,"about_ca_system_score_codex":0.0026595134,"about_ca_system_score_gemma":0.0012773843,"threshold_uncertainty_score":0.07203382},"labels":[],"label_agreement":null},{"id":"W4388498153","doi":"10.18280/ria.370506","title":"BBMA-MDS: Binary Biology Migration Algorithm for Multi-Document Text Summarization","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Binary number; Multi-document summarization; Computational biology; Information retrieval; Biology; Mathematics; Arithmetic","score_opus":0.06135140567480775,"score_gpt":0.3224059651195136,"score_spread":0.26105455944470585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388498153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015089387,0.0012083673,0.97883224,0.0003708836,0.00022223144,0.000184593,0.00025175087,0.0024969622,0.0013435243],"genre_scores_gemma":[0.10783006,0.00054201484,0.884967,0.00024843216,0.00015376974,0.0004686835,0.0011350597,0.00018489659,0.004470094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942786,0.00011272222,0.000060343453,0.0001474515,0.00020442331,0.00004722349],"domain_scores_gemma":[0.9992822,0.00029326254,0.00009418269,0.00006792217,0.00022281999,0.000039660543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008735895,0.0011102485,0.0011201334,0.0021490678,0.00081636925,0.0010474095,0.0012614765,0.0013017544,0.0024713944],"category_scores_gemma":[0.0028198455,0.000321799,0.0008730286,0.00173614,0.00049442786,0.0012034035,0.0008519032,0.0010404553,0.0013470126],"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":[0.00028281662,0.00013453756,0.0008425126,0.00029089424,0.00008858195,0.0001224335,0.00024997856,0.11610658,0.028268479,0.005819661,0.009432784,0.8383606],"study_design_scores_gemma":[0.00010464126,0.00024042842,0.0006897855,0.000034328794,0.00005036842,0.00018054612,0.00011865146,0.95958054,0.015918339,0.008242947,0.01480815,0.00003121368],"about_ca_topic_score_codex":0.0035156608,"about_ca_topic_score_gemma":0.0038623048,"teacher_disagreement_score":0.0035156608,"about_ca_system_score_codex":0.0007547976,"about_ca_system_score_gemma":0.0013841512,"threshold_uncertainty_score":0.008267641},"labels":[],"label_agreement":null},{"id":"W4388866605","doi":"10.1186/s12859-023-05570-z","title":"Image-centric compression of protein structures improves space savings","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Computer science; Compression (physics); Image compression; Computational biology; Artificial intelligence; Computer graphics (images); Image (mathematics); Computer vision; Image processing; Biology; Genetics; Gene; Materials science; Gene expression; Composite material","score_opus":0.015107522464248383,"score_gpt":0.24591595228719174,"score_spread":0.23080842982294336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388866605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43760732,0.0059567178,0.49517715,0.001912664,0.00038641057,0.00024337234,0.0037480837,0.036435593,0.018532729],"genre_scores_gemma":[0.6756203,0.002730502,0.30742458,0.00060174684,0.00018754113,0.00018273818,0.005901539,0.0017589345,0.0055920472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959785,0.000027857219,0.000024924368,0.000064510445,0.00023541308,0.000049443384],"domain_scores_gemma":[0.99907684,0.00028260655,0.00009234311,0.00022473674,0.00028685143,0.000036616693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033420403,0.00091362506,0.00046935419,0.0011012204,0.00027693782,0.0008991213,0.0013727746,0.0007082104,0.004931974],"category_scores_gemma":[0.0019833304,0.00019026342,0.00033974185,0.001931051,0.00045928164,0.0014407735,0.0008533124,0.0006757714,0.0017301819],"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":[0.001120956,0.00030946368,0.00358696,0.00092657696,0.00009308179,0.00063928287,0.00037581,0.047559354,0.30744204,0.008873757,0.03376553,0.5953073],"study_design_scores_gemma":[0.000118051736,0.00033331334,0.003530037,0.00008653686,0.00007044736,0.0010779803,0.00012810546,0.3061678,0.65992564,0.0044055074,0.024094133,0.0000623345],"about_ca_topic_score_codex":0.001574176,"about_ca_topic_score_gemma":0.0011477655,"teacher_disagreement_score":0.004931974,"about_ca_system_score_codex":0.00058922457,"about_ca_system_score_gemma":0.0004683256,"threshold_uncertainty_score":0.016499162},"labels":[],"label_agreement":null},{"id":"W4388926444","doi":"10.1145/3618307","title":"ART-Owen Scrambling","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Scrambling; Computer science; Scalability; Theoretical computer science; Context (archaeology); Binary tree; Algorithm; Symbol (formal); Tree (set theory); Code (set theory); Parallel computing; Mathematics; Programming language","score_opus":0.04069691141845598,"score_gpt":0.2840182207735879,"score_spread":0.2433213093551319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388926444","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076566874,0.00007456079,0.9885853,0.000036947316,0.000044560547,0.000036139238,0.000032925833,0.0009012289,0.0026317243],"genre_scores_gemma":[0.13126004,0.00008859669,0.8624972,0.00011829661,0.000029957682,0.00010087421,0.00013222515,0.00037982204,0.005393034],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996513,0.00005058454,0.000023924496,0.000071993316,0.00015933467,0.000042865086],"domain_scores_gemma":[0.99939644,0.00018107069,0.00004574858,0.00021678083,0.00012423034,0.000035740726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046910596,0.00045740465,0.000552012,0.00063931756,0.00048381236,0.00081088516,0.0009586959,0.00059385586,0.0038912355],"category_scores_gemma":[0.001918705,0.00028643513,0.0005463397,0.0004370758,0.0008124986,0.0008453538,0.001305741,0.00078466814,0.0013030221],"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":[0.0003070792,0.000092396345,0.00091389555,0.00026252304,0.00006539622,0.00031406264,0.0005132506,0.1317353,0.088369556,0.19912656,0.0074260645,0.57087386],"study_design_scores_gemma":[0.00004922075,0.000103923245,0.0002658677,0.000032593114,0.00002522158,0.00031169274,0.00004852702,0.85903376,0.074831605,0.043323826,0.021927375,0.00004633785],"about_ca_topic_score_codex":0.0011836878,"about_ca_topic_score_gemma":0.0020509046,"teacher_disagreement_score":0.0038912355,"about_ca_system_score_codex":0.00039784733,"about_ca_system_score_gemma":0.0007882148,"threshold_uncertainty_score":0.013017476},"labels":[],"label_agreement":null},{"id":"W4389083264","doi":"10.1007/978-3-031-47627-3_1","title":"Introduction","year":2023,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Byte; Computer science; Search engine indexing; Information retrieval; Programming language","score_opus":0.019141679756785226,"score_gpt":0.23880186077521234,"score_spread":0.2196601810184271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389083264","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032432374,0.0032591973,0.005160794,0.0032863498,0.007368783,0.00014769926,0.002300302,0.0011561014,0.9769965],"genre_scores_gemma":[0.0009662143,0.0017106822,0.001234427,0.0012068802,0.0010152376,0.00007554697,0.0015329003,0.00028522764,0.9919729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999328,0.000066082284,0.000022911596,0.00013362744,0.00037800585,0.000071479786],"domain_scores_gemma":[0.9989918,0.00014131556,0.000035451234,0.00015026145,0.00044767832,0.00023342767],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006738812,0.0010100997,0.00060727727,0.0018410315,0.0013164148,0.004350118,0.0016781426,0.0017621615,0.658438],"category_scores_gemma":[0.0025437109,0.00034134093,0.00056575134,0.0016986189,0.00060071214,0.0031645526,0.002728419,0.0018742498,0.58934647],"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":[0.0000231627,0.00003084461,0.00007516303,0.00014872747,0.0000019374165,0.00003929863,0.000080817554,0.00009479993,0.0003686786,0.024199216,0.8080832,0.16685417],"study_design_scores_gemma":[0.0000014425144,0.0000049539667,0.00004315394,0.000046770176,6.661477e-7,0.000023745028,0.000020701185,0.000016147209,0.000054495853,0.0025756164,0.9972103,0.0000019778533],"about_ca_topic_score_codex":0.0018166051,"about_ca_topic_score_gemma":0.0028047562,"teacher_disagreement_score":0.34156197,"about_ca_system_score_codex":0.0011205124,"about_ca_system_score_gemma":0.0018398681,"threshold_uncertainty_score":0.48719668},"labels":[],"label_agreement":null},{"id":"W4389478736","doi":"10.1007/978-3-031-49611-0_34","title":"V-Words, Lyndon Words and Substring circ-UMFFs","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Lexicographical order; Combinatorics; Order (exchange); Factorization; Generalization; String (physics); Mathematics; Discrete mathematics; Computer science; Algorithm; Data structure","score_opus":0.02012152762160887,"score_gpt":0.24442877931744555,"score_spread":0.22430725169583668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389478736","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19891678,0.02083188,0.33119953,0.0014231852,0.0032529193,0.00012473209,0.00050185795,0.0014053073,0.4423439],"genre_scores_gemma":[0.76655734,0.0051307254,0.07354768,0.0009605172,0.0013201848,0.00018638899,0.00075844495,0.0006116739,0.15092704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996039,0.00008157291,0.000030469157,0.00008039958,0.00012555189,0.00007798274],"domain_scores_gemma":[0.99925536,0.00035632175,0.0000836522,0.00011230953,0.00012455409,0.00006774917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046504082,0.0005781314,0.0006916875,0.0020538883,0.0016738366,0.0022378147,0.00073810143,0.0009573943,0.008904762],"category_scores_gemma":[0.0026684236,0.0003213094,0.00047732846,0.0023950883,0.0024330379,0.0026247045,0.0013192308,0.0013024868,0.0025407935],"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":[0.00005782478,0.00001298335,0.00019992107,0.0000821761,0.0000056049735,0.00019437574,0.00026047236,0.00052494736,0.0019646918,0.9473245,0.004219425,0.045153048],"study_design_scores_gemma":[0.00000623444,0.000030645457,0.00018583008,0.00004802718,0.000008327817,0.00043648315,0.000119537544,0.0021951613,0.0014044866,0.9685979,0.026952773,0.000014592167],"about_ca_topic_score_codex":0.0007566026,"about_ca_topic_score_gemma":0.0009787855,"teacher_disagreement_score":0.008904762,"about_ca_system_score_codex":0.0008378401,"about_ca_system_score_gemma":0.00045506767,"threshold_uncertainty_score":0.029789388},"labels":[],"label_agreement":null},{"id":"W4389489786","doi":"10.1007/978-3-031-49611-0_32","title":"The Longest Subsequence-Repeated Subsequence Problem","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Subsequence; Longest increasing subsequence; Longest common subsequence problem; Substring; Combinatorics; Sequence (biology); Algorithm; Mathematics; Discrete mathematics; Computer science; Data structure; Bounded function","score_opus":0.023278613772194513,"score_gpt":0.24747296539501,"score_spread":0.22419435162281548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389489786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037494797,0.0063775466,0.92016923,0.003825059,0.0012254321,0.00016066837,0.0018082986,0.0012665829,0.02767243],"genre_scores_gemma":[0.3369946,0.009019367,0.5915171,0.0014603949,0.0039570937,0.00045264018,0.009471278,0.0011080905,0.046019476],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839056,0.00039053222,0.00015262813,0.00051538803,0.00042563933,0.00012541289],"domain_scores_gemma":[0.9946977,0.00362643,0.00040788722,0.00073864573,0.0003885313,0.00014077793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014760308,0.0008774791,0.0020175166,0.0013925531,0.00096405245,0.0020275589,0.0024230902,0.0026835788,0.009183075],"category_scores_gemma":[0.010108359,0.0006372292,0.0012905195,0.0037017653,0.001391517,0.0050141555,0.0019797091,0.002074319,0.003082845],"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":[0.00070502906,0.0003054226,0.0012582989,0.0014681041,0.0003023067,0.0013380504,0.00032306067,0.11774706,0.007849457,0.3021649,0.068531916,0.4980064],"study_design_scores_gemma":[0.00010552474,0.0001204046,0.00045922305,0.00009635023,0.00006557062,0.0009893455,0.0001709381,0.22129326,0.0036130047,0.75206363,0.020981705,0.00004109598],"about_ca_topic_score_codex":0.0006342693,"about_ca_topic_score_gemma":0.00044242907,"teacher_disagreement_score":0.009183075,"about_ca_system_score_codex":0.0005224202,"about_ca_system_score_gemma":0.0010860689,"threshold_uncertainty_score":0.030720472},"labels":[],"label_agreement":null},{"id":"W4390062883","doi":"10.1190/geo2023-0161.1","title":"Ordering cross-spread gathers","year":2023,"lang":"en","type":"article","venue":"Geophysics","topic":"Algorithms and Data Compression","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":"Bayer (Canada)","funders":"","keywords":"Computer science; Java; Single line; Line (geometry); Graph; Source code; Diagram; Algorithm; Code (set theory); Data mining; Theoretical computer science; Programming language; Set (abstract data type); Database; Geometry; Engineering drawing; Mathematics","score_opus":0.01875315268895514,"score_gpt":0.27801877869754066,"score_spread":0.2592656260085855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390062883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28548196,0.00043483629,0.69572824,0.0003000598,0.00017036295,0.0001759389,0.0015509912,0.0037973586,0.012360288],"genre_scores_gemma":[0.6603974,0.0004174303,0.32499605,0.00009511426,0.00008266933,0.00007746995,0.004909135,0.0009470185,0.008077722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995134,0.000063171385,0.000027835162,0.00009923035,0.00021908607,0.00007726984],"domain_scores_gemma":[0.9980178,0.00048335595,0.00015709917,0.00050294516,0.00072525145,0.0001136288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004920137,0.0005685786,0.00049797236,0.002515374,0.000533932,0.0010120647,0.00041934635,0.0003571836,0.004933257],"category_scores_gemma":[0.0028132575,0.00041665928,0.00030540017,0.0025812935,0.00051142677,0.001172082,0.0015277141,0.0005945519,0.0017591614],"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":[0.0012441176,0.0002283442,0.02191383,0.0004190123,0.00017847089,0.00067729555,0.0013994995,0.13405277,0.12365346,0.033027634,0.016356051,0.6668495],"study_design_scores_gemma":[0.00009111294,0.00044112626,0.025281992,0.00012847195,0.00010707711,0.0005147104,0.0015974259,0.7607286,0.07824783,0.07443745,0.058330137,0.00009416049],"about_ca_topic_score_codex":0.00437088,"about_ca_topic_score_gemma":0.011198991,"teacher_disagreement_score":0.004933257,"about_ca_system_score_codex":0.00038584706,"about_ca_system_score_gemma":0.00073156715,"threshold_uncertainty_score":0.016503453},"labels":[],"label_agreement":null},{"id":"W4390117639","doi":"10.29137/umagd.1294273","title":"İstatiksel Kodlama Yöntemlerinin Türkçe ve İngilizce Metinlerde Sıkıştırma Başarımı Karşılaştırma Örneği","year":2023,"lang":"tr","type":"article","venue":"Uluslararası mühendislik araştırma ve geliştirme dergisi","topic":"Algorithms and Data Compression","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":"","keywords":"Physics; Mathematics","score_opus":0.026294905774610078,"score_gpt":0.2755927664724364,"score_spread":0.24929786069782633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390117639","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18555814,0.021634668,0.06137215,0.02341498,0.003377197,0.00049844524,0.0026737684,0.0022090927,0.6992616],"genre_scores_gemma":[0.68673295,0.015516323,0.034320947,0.002495953,0.00058660045,0.00030036003,0.002454465,0.00073678483,0.25685564],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99726605,0.0005304362,0.0001739669,0.00044228174,0.0011554059,0.000431882],"domain_scores_gemma":[0.9962924,0.00065497897,0.0005322035,0.00041964435,0.0017211965,0.00037961744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002106506,0.0012410614,0.0007798954,0.0017754042,0.0040913736,0.008951442,0.0011770631,0.0023214046,0.04589554],"category_scores_gemma":[0.005055149,0.000597787,0.0010014881,0.0021871189,0.0032815682,0.0052079028,0.0035231037,0.0027341465,0.015545064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076960144,0.0004868567,0.04307971,0.0033714734,0.00023961424,0.0039508594,0.024412451,0.00417272,0.015173559,0.21257116,0.10535648,0.58641547],"study_design_scores_gemma":[0.00004087132,0.0002620982,0.03566404,0.0014040545,0.00015377894,0.002209508,0.02503548,0.0023014657,0.0098779425,0.030728923,0.8920983,0.00022358514],"about_ca_topic_score_codex":0.012459008,"about_ca_topic_score_gemma":0.017388817,"teacher_disagreement_score":0.04589554,"about_ca_system_score_codex":0.0033851585,"about_ca_system_score_gemma":0.005704222,"threshold_uncertainty_score":0.1535359},"labels":[],"label_agreement":null},{"id":"W4390204032","doi":"10.1109/tce.2023.3347229","title":"Accelerating Huffman Encoding Using 512-Bit SIMD Instructions","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"National Natural Science Foundation of China","keywords":"Huffman coding; SIMD; Computer science; Canonical Huffman code; Parallel computing; Table (database); Initialization; Lookup table; Encoding (memory); Arithmetic; Arithmetic coding; Data compression; Algorithm; Decoding methods; Context-adaptive binary arithmetic coding; Operating system; Programming language; Mathematics; Code rate; Database; Systematic code; Artificial intelligence","score_opus":0.04897455348123104,"score_gpt":0.28754801795707347,"score_spread":0.23857346447584243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390204032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10748917,0.0011244047,0.8723005,0.00021721897,0.00015057359,0.00020067203,0.0005864432,0.009138993,0.008791951],"genre_scores_gemma":[0.33733803,0.00057483744,0.6548159,0.00020114309,0.000053568503,0.00014966656,0.002207241,0.00018459425,0.0044750352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996908,0.000033381304,0.000028159406,0.000047818336,0.00016147742,0.000038499],"domain_scores_gemma":[0.9995801,0.00009133154,0.00003625604,0.00010186263,0.00017715433,0.000013357213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034452984,0.00040593994,0.00032828804,0.0010073162,0.00033230634,0.00045595827,0.0006978306,0.00025393453,0.001844978],"category_scores_gemma":[0.0011912464,0.00018586761,0.00031753635,0.0014084573,0.00029344612,0.00082467584,0.0003471333,0.00035393322,0.00065653265],"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":[0.00061548105,0.0001537352,0.0041583604,0.00029887157,0.00008445518,0.00027410206,0.00019869137,0.0360368,0.1519819,0.022926277,0.009859431,0.7734119],"study_design_scores_gemma":[0.00010364062,0.00049931055,0.0027873032,0.000044632823,0.00008346226,0.0004711301,0.00007539368,0.52463394,0.4322414,0.0071512056,0.031838857,0.000069663074],"about_ca_topic_score_codex":0.004350188,"about_ca_topic_score_gemma":0.00419081,"teacher_disagreement_score":0.004350188,"about_ca_system_score_codex":0.0006197719,"about_ca_system_score_gemma":0.0010316093,"threshold_uncertainty_score":0.008649707},"labels":[],"label_agreement":null},{"id":"W4390331298","doi":"10.1371/journal.pgen.1011104","title":"SparsePro: An efficient fine-mapping method integrating summary statistics and functional annotations","year":2023,"lang":"en","type":"article","venue":"PLoS Genetics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada First Research Excellence Fund; Compute Canada","keywords":"Biology; Computational biology; Statistics; Mathematics","score_opus":0.061134174458812966,"score_gpt":0.29735521048612384,"score_spread":0.23622103602731087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390331298","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026105007,0.00010173999,0.99447304,0.00009128946,0.000019049716,0.000036742724,0.0003537534,0.002009634,0.000304192],"genre_scores_gemma":[0.08598025,0.00029936188,0.90596217,0.0003398043,0.000094098825,0.0003557181,0.0031237854,0.0015757085,0.0022691642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999019,0.00042592356,0.00005262712,0.0002094168,0.00023722182,0.00005578063],"domain_scores_gemma":[0.99649423,0.0025427274,0.00016828631,0.00036498584,0.00032630123,0.00010335093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031623617,0.0009839789,0.0014455933,0.0015995465,0.00060253043,0.0013037137,0.002290284,0.001279915,0.0064079273],"category_scores_gemma":[0.012745609,0.0009682342,0.0015977715,0.0014141486,0.0008200223,0.0017324531,0.0021582916,0.0020274404,0.001810941],"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":[0.00047039456,0.00017047541,0.005561964,0.0006076998,0.00042274408,0.00045916715,0.00038521746,0.41391546,0.013428194,0.059387747,0.025479024,0.47971192],"study_design_scores_gemma":[0.00007235859,0.00003393106,0.0006018306,0.000023528924,0.00003088586,0.00013604316,0.000018674644,0.950231,0.0017127701,0.042036623,0.0050712335,0.000031144198],"about_ca_topic_score_codex":0.0057077906,"about_ca_topic_score_gemma":0.009567081,"teacher_disagreement_score":0.0064079273,"about_ca_system_score_codex":0.00056211837,"about_ca_system_score_gemma":0.0021770047,"threshold_uncertainty_score":0.021436632},"labels":[],"label_agreement":null},{"id":"W4390349396","doi":"10.17504/protocols.io.kxygx3qx4g8j/v1","title":"Native Barcoding (SQK-NBD114) gDNA for Adaptive Sampling using Oxford Nanopore Technologies v1","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"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":"Canadian Institutes of Health Research; Medical Research Council; Michael J. Fox Foundation for Parkinson's Research","keywords":"genomic DNA; Nanopore; Nanopore sequencing; DNA barcoding; Sampling (signal processing); Computational biology; DNA; DNA sequencer; Biology; DNA sequencing; Evolutionary biology; Computer science; Genetics; Nanotechnology; Materials science; Telecommunications","score_opus":0.18256407768203306,"score_gpt":0.3496197608024758,"score_spread":0.16705568312044275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390349396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03792913,0.002301246,0.90254897,0.00051710353,0.00071421836,0.0014800598,0.013606919,0.020880144,0.020022156],"genre_scores_gemma":[0.06966177,0.0018884608,0.8417405,0.0008463579,0.00009400389,0.0037551625,0.03386035,0.0057104677,0.042443007],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838233,0.00022651964,0.00016319082,0.00045338308,0.00057996105,0.00019461753],"domain_scores_gemma":[0.99850595,0.00036794346,0.000116772,0.0005798956,0.00030397793,0.0001254434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014350893,0.0011510536,0.0010020034,0.0013387027,0.0009482074,0.00092389336,0.0013266349,0.0009954618,0.024449416],"category_scores_gemma":[0.0022235138,0.0012870516,0.0006155138,0.00091610814,0.0007552203,0.0009918328,0.0013735187,0.0021177179,0.02524531],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001976732,0.000061411636,0.00053069217,0.0006055882,0.000035085053,0.00015763489,0.00025452644,0.0005177643,0.9201957,0.005206647,0.017284919,0.05495238],"study_design_scores_gemma":[0.000032280896,0.00011813458,0.0010086674,0.00007516306,0.000022938331,0.00044428057,0.000051029805,0.0025652475,0.8185716,0.0017401107,0.17530416,0.00006637913],"about_ca_topic_score_codex":0.0012698935,"about_ca_topic_score_gemma":0.004566443,"teacher_disagreement_score":0.024449416,"about_ca_system_score_codex":0.000642039,"about_ca_system_score_gemma":0.0010301964,"threshold_uncertainty_score":0.0817914},"labels":[],"label_agreement":null},{"id":"W4391363562","doi":"10.1007/978-3-031-38684-8_1","title":"Introduction","year":2024,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on computer architecture","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.007678838646377735,"score_gpt":0.20632551898835427,"score_spread":0.19864668034197655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391363562","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038409358,0.002767086,0.0060409005,0.0027000813,0.005942338,0.00013947266,0.002231087,0.0012183058,0.9785766],"genre_scores_gemma":[0.0008878036,0.0011628043,0.00116446,0.0007502479,0.0006934869,0.00006014414,0.0012566308,0.0002290498,0.9937954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994765,0.0000430385,0.000015624379,0.00010745982,0.00029977298,0.000057643585],"domain_scores_gemma":[0.99925977,0.00008884861,0.000023119903,0.00009930939,0.0003532804,0.00017565438],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00050992705,0.0009750973,0.0005759068,0.0015722151,0.0011922732,0.003410908,0.0014365276,0.001503628,0.6367463],"category_scores_gemma":[0.0018364422,0.0003241842,0.00048782155,0.0013024304,0.0004696881,0.0024643969,0.0021509186,0.0016154774,0.5758157],"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":[0.000023775641,0.000034160345,0.00007585803,0.00012979815,0.0000019235738,0.000037196733,0.00006804892,0.00012415192,0.0005378327,0.020658795,0.80193466,0.17637372],"study_design_scores_gemma":[0.0000017324938,0.0000061947803,0.000051999014,0.000041994022,7.6552647e-7,0.000024150488,0.000019836381,0.000024127905,0.00008432565,0.002642877,0.9971,0.0000021087676],"about_ca_topic_score_codex":0.0017000813,"about_ca_topic_score_gemma":0.0030838447,"teacher_disagreement_score":0.3632537,"about_ca_system_score_codex":0.0011148279,"about_ca_system_score_gemma":0.0016570947,"threshold_uncertainty_score":0.51813734},"labels":[],"label_agreement":null},{"id":"W4392348843","doi":"10.18280/ts.410147","title":"Enhanced Security Through Integrated Morse Code Encryption and LSB Steganography in Digital Communications","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Morse code; Steganography; Encryption; Least significant bit; Computer science; Code (set theory); Steganalysis; Steganography tools; Computer security; Telecommunications; Artificial intelligence; Embedding; Operating system; Programming language","score_opus":0.018821164892821353,"score_gpt":0.2665546240012023,"score_spread":0.24773345910838093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392348843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49485752,0.0042812824,0.4867821,0.0005483188,0.00015580477,0.00008470248,0.000046101373,0.0013233868,0.011920785],"genre_scores_gemma":[0.9040295,0.0011374365,0.09096047,0.00010142681,0.000042413692,0.000020175392,0.00005145024,0.00004111174,0.0036159463],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996196,0.00007951349,0.000015268994,0.00004481656,0.00019878233,0.0000420115],"domain_scores_gemma":[0.99979025,0.0000621982,0.000028519897,0.000041805433,0.0000682098,0.000009161366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031353036,0.00031842975,0.00034077905,0.00047981058,0.00015623227,0.00048611913,0.00027279314,0.00053432374,0.0007655137],"category_scores_gemma":[0.00057166483,0.00014886091,0.00024727365,0.00031285672,0.0003430685,0.00082367915,0.00060517323,0.0004583522,0.0003963284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038761052,0.00015561645,0.0012998801,0.00023101894,0.000064668915,0.00041802652,0.00016941954,0.041603222,0.7625859,0.013274609,0.0006782717,0.17913178],"study_design_scores_gemma":[0.00002308645,0.0006309992,0.0023388646,0.000051418032,0.000045629422,0.00092378346,0.00005240992,0.54261374,0.4410346,0.0027814067,0.009452337,0.000051706684],"about_ca_topic_score_codex":0.00055217254,"about_ca_topic_score_gemma":0.0006999456,"teacher_disagreement_score":0.0007655137,"about_ca_system_score_codex":0.00022305283,"about_ca_system_score_gemma":0.00026779925,"threshold_uncertainty_score":0.002560854},"labels":[],"label_agreement":null},{"id":"W4392452252","doi":"10.1007/978-3-031-55598-5_10","title":"Space-Efficient Conversions from SLPs","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Space (punctuation); Programming language; Theoretical computer science; Operating system","score_opus":0.013574039413714422,"score_gpt":0.23569562362226765,"score_spread":0.2221215842085532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392452252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07114472,0.0018062427,0.7550056,0.00051986985,0.0009900471,0.00024238341,0.0016114811,0.014454174,0.15422548],"genre_scores_gemma":[0.5510517,0.0017168153,0.36548918,0.0004725098,0.0003201677,0.0003104942,0.0035175565,0.0041468055,0.07297482],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999537,0.00005592928,0.000039685336,0.000077868215,0.00019976357,0.00008967766],"domain_scores_gemma":[0.99936694,0.00021561487,0.000022535782,0.0002726129,0.00010475711,0.000017616368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022203878,0.0008193619,0.0004986915,0.0011484661,0.00060227374,0.0015944487,0.00091791764,0.0005506329,0.022442512],"category_scores_gemma":[0.0013479437,0.00038323697,0.000642462,0.0019229449,0.0007543758,0.0022634207,0.0020455362,0.0011274026,0.00771016],"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":[0.00028296327,0.00011490786,0.00022295778,0.0005213495,0.000033272197,0.0005385015,0.00040281078,0.014978324,0.038946833,0.272822,0.03241977,0.63871634],"study_design_scores_gemma":[0.00008350484,0.00021396994,0.0004996248,0.0002034412,0.000074667456,0.001502974,0.00041772594,0.07837744,0.16951483,0.53959954,0.2094328,0.00007954847],"about_ca_topic_score_codex":0.00053335645,"about_ca_topic_score_gemma":0.0009484139,"teacher_disagreement_score":0.022442512,"about_ca_system_score_codex":0.0004198344,"about_ca_system_score_gemma":0.0003991408,"threshold_uncertainty_score":0.07507771},"labels":[],"label_agreement":null},{"id":"W4392452275","doi":"10.1007/978-3-031-55598-5_12","title":"Wheeler Maps","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.014642321592585715,"score_gpt":0.24242317495175786,"score_spread":0.22778085335917214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392452275","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060492163,0.0021699117,0.08184999,0.0009699536,0.0011599258,0.0000774132,0.0014022359,0.0014771948,0.9048442],"genre_scores_gemma":[0.06386706,0.0024604788,0.02667911,0.00038271348,0.00030502118,0.00010400329,0.002018933,0.0010834179,0.90309936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999645,0.000032708314,0.000014675963,0.00009185529,0.00016163055,0.000054210184],"domain_scores_gemma":[0.99975497,0.00004037811,0.000010952825,0.00006433373,0.00009374484,0.00003551698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018647932,0.0007190751,0.00059721747,0.002247965,0.001417298,0.0026141342,0.00086773786,0.00080607284,0.09502953],"category_scores_gemma":[0.0011248314,0.0004275059,0.0005119975,0.0018759159,0.0008509892,0.0028611228,0.0017764363,0.0015965862,0.049275193],"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":[0.00004173048,0.000025192046,0.000106475054,0.00008842486,0.000008683484,0.00007658812,0.00021874951,0.00080987625,0.0018540693,0.7318665,0.08647212,0.17843156],"study_design_scores_gemma":[0.0000069293883,0.000013715597,0.00018240033,0.000041896423,0.000009215359,0.0001929376,0.00011412591,0.001446032,0.0020907158,0.3164525,0.67943555,0.000014012788],"about_ca_topic_score_codex":0.0031863872,"about_ca_topic_score_gemma":0.003259517,"teacher_disagreement_score":0.09502953,"about_ca_system_score_codex":0.0010090802,"about_ca_system_score_gemma":0.00079182687,"threshold_uncertainty_score":0.3179055},"labels":[],"label_agreement":null},{"id":"W4393299898","doi":"10.1007/jhep05(2024)255","title":"Advanced tools for basis decompositions of genus-one string integrals","year":2024,"lang":"en","type":"preprint","venue":"Journal of High Energy Physics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Perimeter Institute","funders":"Institut Périmètre de physique théorique; Knut och Alice Wallenbergs Stiftelse; Government of Canada; Ministry of Colleges and Universities; Innovation, Science and Economic Development Canada","keywords":"Genus; Basis (linear algebra); String (physics); Mathematics; Computer science; Pure mathematics; Mathematical physics; Zoology; Geometry; Biology","score_opus":0.030662302766952684,"score_gpt":0.28317882057875976,"score_spread":0.25251651781180706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393299898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036407437,0.0008207766,0.94829726,0.0004303822,0.00012981427,0.000062996936,0.00020228156,0.00040450005,0.013244618],"genre_scores_gemma":[0.34443998,0.0016260915,0.6437675,0.00028486177,0.00034641466,0.00035770563,0.000745743,0.00063988817,0.0077918186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923563,0.00026240773,0.00006225149,0.00007926721,0.00029875647,0.000061664876],"domain_scores_gemma":[0.99847525,0.0005781867,0.000117308184,0.00047029587,0.00026352238,0.00009535924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014383203,0.00078259147,0.0005706493,0.0033483382,0.0006904609,0.0022713114,0.0011793149,0.0007490977,0.004423426],"category_scores_gemma":[0.006654341,0.00034594032,0.00065638503,0.0021916118,0.0017246866,0.0031228617,0.0023959556,0.0027072474,0.0016296632],"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":[0.000022310427,0.00003429793,0.00030344998,0.000043026706,0.0000072886605,0.000060433096,0.00017586506,0.010302896,0.0025374552,0.9443161,0.0012189167,0.040977877],"study_design_scores_gemma":[0.0000064031155,0.000014901739,0.00010027235,0.00003369052,0.0000034581772,0.00006314643,0.00005709027,0.11056711,0.0017989094,0.882609,0.004734923,0.000011068204],"about_ca_topic_score_codex":0.0003480842,"about_ca_topic_score_gemma":0.00041667002,"teacher_disagreement_score":0.004423426,"about_ca_system_score_codex":0.0005972047,"about_ca_system_score_gemma":0.00057417376,"threshold_uncertainty_score":0.014797866},"labels":[],"label_agreement":null},{"id":"W4393870960","doi":"10.1007/978-3-031-57246-3_3","title":"TaSSAT: Transfer and Share SAT","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Transfer (computing); Theoretical computer science; Parallel computing","score_opus":0.015569451711534812,"score_gpt":0.2382465355388882,"score_spread":0.22267708382735338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393870960","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03586481,0.0014781284,0.8827025,0.001202004,0.00039147667,0.00026504023,0.0010175565,0.010817602,0.06626087],"genre_scores_gemma":[0.48207375,0.0013518299,0.4605427,0.00071074005,0.0003905871,0.0005760553,0.0041217157,0.0030458525,0.047186684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917954,0.0002014838,0.00003836832,0.00014340729,0.00034542423,0.00009175668],"domain_scores_gemma":[0.9993911,0.00025027373,0.000040814044,0.00020280239,0.000074542746,0.0000403946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008533408,0.000711611,0.00061595807,0.000711411,0.0004617183,0.0018789737,0.0023153257,0.0007933321,0.030949248],"category_scores_gemma":[0.00257389,0.00045908088,0.00084344525,0.0019443829,0.0009479126,0.0029581052,0.0029047485,0.0018438183,0.0055574887],"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":[0.00047624577,0.0003209023,0.0007896044,0.0006316257,0.00015966877,0.00030715473,0.00022086654,0.17781802,0.0135275675,0.22218484,0.08305293,0.5005106],"study_design_scores_gemma":[0.00026058516,0.0001718789,0.00045038477,0.00008185737,0.00008220401,0.00026986861,0.00009638341,0.6948823,0.018410841,0.1988418,0.08642066,0.00003121797],"about_ca_topic_score_codex":0.0010148654,"about_ca_topic_score_gemma":0.0016656155,"teacher_disagreement_score":0.030949248,"about_ca_system_score_codex":0.00083388836,"about_ca_system_score_gemma":0.0011583918,"threshold_uncertainty_score":0.10353553},"labels":[],"label_agreement":null},{"id":"W4394051677","doi":"10.5281/zenodo.3560149","title":"AmpliconTagger pipeline databases","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"National Research Council Canada","funders":"","keywords":"Database; Pipeline (software); Computer science; Programming language","score_opus":0.06094851598872665,"score_gpt":0.28171643740063645,"score_spread":0.22076792141190982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394051677","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036654912,0.00008617258,0.0012653044,0.0000763106,0.000048376525,0.000050071783,0.9841801,0.011732799,0.0021942176],"genre_scores_gemma":[0.00051419676,0.0000379991,0.0014205078,0.000043476077,0.000006479544,0.00013993314,0.9958962,0.0010033834,0.00093774754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828964,0.00016092189,0.00027645423,0.000567818,0.00049391063,0.00021123834],"domain_scores_gemma":[0.9969766,0.00069685455,0.00022237352,0.0010368096,0.0008804477,0.00018694057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001399431,0.0028147334,0.0016259669,0.0046739276,0.0013573084,0.0027782617,0.0041817655,0.0017311771,0.092707686],"category_scores_gemma":[0.006594968,0.0010443954,0.0012968421,0.0055384566,0.00049798924,0.0024824243,0.002700073,0.0018539954,0.17352325],"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":[0.00013417995,0.000030052359,0.00046171295,0.0005203277,0.000025066309,0.000034807792,0.000045793968,0.00022078103,0.0010545548,0.00092184695,0.9895566,0.006994244],"study_design_scores_gemma":[0.00013381394,0.000035829104,0.0020123294,0.00014382355,0.000040030103,0.00015818766,0.000092127244,0.001324772,0.0049237283,0.0033728569,0.9877038,0.00005871544],"about_ca_topic_score_codex":0.008815724,"about_ca_topic_score_gemma":0.013412756,"teacher_disagreement_score":0.092707686,"about_ca_system_score_codex":0.0014735325,"about_ca_system_score_gemma":0.0021310395,"threshold_uncertainty_score":0.3101381},"labels":[],"label_agreement":null},{"id":"W4394115452","doi":"10.6084/m9.figshare.4747318","title":"16S Sequences","year":2017,"lang":"en","type":"dataset","venue":"Figshare","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science","score_opus":0.05967643132135508,"score_gpt":0.31992595589847783,"score_spread":0.26024952457712275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394115452","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006437161,0.00015684881,0.00020672298,0.00003294977,0.000031639716,0.00004128872,0.99783367,0.0002528083,0.0008003486],"genre_scores_gemma":[0.0006442641,0.000096608564,0.00064109324,0.000042098065,0.000008464191,0.00018867422,0.9976914,0.000083327075,0.00060421973],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698573,0.00029833318,0.00051845727,0.0010230407,0.00073029724,0.00044418205],"domain_scores_gemma":[0.9958865,0.00064517674,0.00060651917,0.0010833284,0.0014133786,0.00036504585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020881004,0.0025934833,0.0025772403,0.008214284,0.0019647211,0.002662125,0.0025405334,0.0025251687,0.06186359],"category_scores_gemma":[0.008261325,0.0007803674,0.0016331311,0.011777915,0.0008671837,0.0014043609,0.0021022593,0.0033204562,0.10720495],"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":[0.0008467647,0.000107236185,0.0073691076,0.005358175,0.00018672257,0.00019088188,0.00024869115,0.0009156172,0.01045395,0.0020581535,0.95402694,0.018237777],"study_design_scores_gemma":[0.0002768109,0.000069354224,0.012576731,0.00058675924,0.00007583209,0.00009782566,0.00017470437,0.00022010187,0.0020746847,0.0017489926,0.9820369,0.00006140215],"about_ca_topic_score_codex":0.01197062,"about_ca_topic_score_gemma":0.019487916,"teacher_disagreement_score":0.06186359,"about_ca_system_score_codex":0.0017213156,"about_ca_system_score_gemma":0.005670731,"threshold_uncertainty_score":0.2069543},"labels":[],"label_agreement":null},{"id":"W4394236522","doi":"10.6084/m9.figshare.4833149","title":"2003 CCHS Dataset and Codeset","year":2017,"lang":"en","type":"dataset","venue":"Figshare","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science","score_opus":0.048809853894771785,"score_gpt":0.3173978766780006,"score_spread":0.26858802278322885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394236522","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000593039,0.000025425537,0.00002791954,0.000030358613,0.0000152986,0.000013959523,0.9994579,0.00010059708,0.00026919763],"genre_scores_gemma":[0.00027453105,0.000035489014,0.00012824318,0.000030455021,0.000005006832,0.00006489151,0.9989048,0.000054392796,0.0005021309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977496,0.00024137582,0.0002920425,0.0004687985,0.00077488605,0.00047330672],"domain_scores_gemma":[0.98911124,0.0021088843,0.0005338918,0.0016243695,0.005723621,0.0008979908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020903004,0.00223211,0.0020338595,0.010853582,0.0015992846,0.0026205822,0.004681509,0.0019053647,0.09222871],"category_scores_gemma":[0.020353356,0.00088846125,0.0021009312,0.020806512,0.0007249805,0.001138315,0.0016018205,0.0026410802,0.061003145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033949585,0.000008224721,0.00037620345,0.00020905891,0.000017819186,0.000007743575,0.00000667482,0.00017668845,0.000014686809,0.00016935791,0.99796057,0.0010190001],"study_design_scores_gemma":[0.00041138445,0.000017979659,0.014193062,0.00064030977,0.00007937894,0.000064906926,0.00016519413,0.0009190642,0.00026671443,0.0013553735,0.98181874,0.000067887275],"about_ca_topic_score_codex":0.67742544,"about_ca_topic_score_gemma":0.7218663,"teacher_disagreement_score":0.32257456,"about_ca_system_score_codex":0.008679768,"about_ca_system_score_gemma":0.022790303,"threshold_uncertainty_score":0.64894855},"labels":[],"label_agreement":null},{"id":"W4394591182","doi":"10.4230/lipics.socg.2025.63","title":"The Maximum Clique Problem in a Disk Graph Made Easy","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Clique; Clique graph; Graph; Combinatorics; Block graph; Computer science; Clique problem; Simplex graph; Split graph; Mathematics; Line graph; Pathwidth; Voltage graph","score_opus":0.038480277469860574,"score_gpt":0.18726597955343094,"score_spread":0.14878570208357036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394591182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2094892,0.0015220608,0.7093666,0.006121931,0.0003754635,0.0006728061,0.0051690703,0.0024680018,0.06481478],"genre_scores_gemma":[0.54576397,0.0011192817,0.41991696,0.0008217918,0.00035743444,0.0005290504,0.006880002,0.000796213,0.023815265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985733,0.0003703823,0.000046013127,0.00056167407,0.00022466804,0.00022390165],"domain_scores_gemma":[0.9972083,0.0016059426,0.00020231718,0.00056010374,0.00019166226,0.00023170265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069524406,0.00095064257,0.0010452813,0.0007913233,0.0025401975,0.002060657,0.0020482605,0.0015134118,0.0114471875],"category_scores_gemma":[0.0043602968,0.0007466538,0.0015091713,0.0019824556,0.0013094597,0.0051399963,0.0018516222,0.001964236,0.002066168],"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":[0.0011241656,0.0006160607,0.002349897,0.001359242,0.00033412818,0.0012158549,0.0012240869,0.17448288,0.023635667,0.5336351,0.08848516,0.17153789],"study_design_scores_gemma":[0.00023739572,0.0001609543,0.0017007453,0.000095929165,0.00011897003,0.0006115085,0.00056358794,0.39382643,0.008973806,0.5370425,0.056601644,0.000066493834],"about_ca_topic_score_codex":0.0050032362,"about_ca_topic_score_gemma":0.007177232,"teacher_disagreement_score":0.0114471875,"about_ca_system_score_codex":0.001296416,"about_ca_system_score_gemma":0.001344293,"threshold_uncertainty_score":0.038294673},"labels":[],"label_agreement":null},{"id":"W4394688386","doi":"10.1186/s13015-024-00260-8","title":"Pfp-fm: an accelerated FM-index","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; Japan Society for the Promotion of Science; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Computer science; Parsing; Suffix; Word (group theory); Sorting; Search engine indexing; Prefix; Character (mathematics); Suffix array; Index (typography); Algorithm; Artificial intelligence; Natural language processing; Data structure; Programming language; Mathematics","score_opus":0.03292274683587503,"score_gpt":0.3461846779970787,"score_spread":0.31326193116120366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394688386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03900819,0.0022157251,0.73498005,0.0007430591,0.0008491033,0.0005293011,0.006515872,0.20147474,0.013683956],"genre_scores_gemma":[0.119742624,0.00038366756,0.8451272,0.0004049069,0.0002692019,0.0005004718,0.014995858,0.0058043646,0.012771661],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868995,0.00011476348,0.000106198095,0.00033068954,0.00059583125,0.00016250517],"domain_scores_gemma":[0.9984372,0.00040807112,0.00010253057,0.000507244,0.00041955188,0.00012545045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074673636,0.001884546,0.0011122397,0.0025427095,0.0011084203,0.0019110062,0.0047758706,0.0013258499,0.018011864],"category_scores_gemma":[0.0042141513,0.000700842,0.0010378284,0.0037088187,0.00063399435,0.00365726,0.0024692111,0.001331249,0.009234801],"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":[0.001409681,0.00032402168,0.0026007483,0.0006118346,0.00009986639,0.00028897962,0.00020054598,0.018371591,0.03265528,0.010451048,0.16927066,0.7637158],"study_design_scores_gemma":[0.0005596659,0.00043236537,0.0024001463,0.000099148056,0.00007761067,0.00074055453,0.00013213229,0.76821285,0.070489354,0.018882742,0.13779825,0.00017509694],"about_ca_topic_score_codex":0.009960888,"about_ca_topic_score_gemma":0.0061245225,"teacher_disagreement_score":0.018011864,"about_ca_system_score_codex":0.0015087288,"about_ca_system_score_gemma":0.0021254849,"threshold_uncertainty_score":0.060255706},"labels":[],"label_agreement":null},{"id":"W4394944952","doi":"10.1016/j.dam.2024.04.006","title":"Polynomial-time equivalences and refined algorithms for longest common subsequence variants","year":2024,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Japan Science and Technology Agency; Japan Society for the Promotion of Science; Core Research for Evolutional Science and Technology; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Longest common subsequence problem; Longest increasing subsequence; Time complexity; Combinatorics; Subsequence; Algorithm; Discrete mathematics","score_opus":0.025046929772513573,"score_gpt":0.285335616274388,"score_spread":0.2602886865018745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394944952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022150194,0.00054274837,0.9701413,0.00037067485,0.0001746532,0.0001453934,0.00028778697,0.0011945869,0.0049926727],"genre_scores_gemma":[0.3378974,0.0007961639,0.6481951,0.00046401762,0.00052422215,0.00039177836,0.0024221682,0.0013893836,0.007919807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98777676,0.0025226923,0.0010361868,0.0033794378,0.004157757,0.0011271563],"domain_scores_gemma":[0.97101015,0.014832379,0.0012729156,0.009141668,0.003129087,0.0006137774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004846189,0.0015743665,0.0020746319,0.0031928641,0.0016994261,0.0044153067,0.005601281,0.0017855944,0.007675613],"category_scores_gemma":[0.034997936,0.0012068661,0.002921724,0.0057897107,0.0038177224,0.012865812,0.0053833523,0.007074663,0.0021554756],"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":[0.001176229,0.00037974733,0.0013614255,0.00043955466,0.00015228562,0.00027857008,0.00088179996,0.071224496,0.008398934,0.6781884,0.0077248416,0.22979362],"study_design_scores_gemma":[0.00009617605,0.0001089434,0.00029799662,0.000043164342,0.00007820504,0.00018176992,0.00014015063,0.14902408,0.0055226497,0.8384763,0.0059865415,0.000043982243],"about_ca_topic_score_codex":0.0028392542,"about_ca_topic_score_gemma":0.0035422896,"teacher_disagreement_score":0.007675613,"about_ca_system_score_codex":0.00261167,"about_ca_system_score_gemma":0.0026239294,"threshold_uncertainty_score":0.025677502},"labels":[],"label_agreement":null},{"id":"W4395959037","doi":"10.1145/3649411.3649416","title":"Regular Expressions on Modern GPGPUs","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Parallel computing","score_opus":0.01355430905800326,"score_gpt":0.2550901091952594,"score_spread":0.24153580013725612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395959037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07084494,0.0012546248,0.86367583,0.00083825114,0.00027617122,0.00025130523,0.0011137653,0.022862803,0.038882285],"genre_scores_gemma":[0.3017081,0.0008502969,0.66555333,0.0010251052,0.00010790474,0.00056160043,0.0031361578,0.004213707,0.022843903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988236,0.00018882567,0.00008966135,0.00019626263,0.00056052324,0.00014105024],"domain_scores_gemma":[0.9988888,0.00033758563,0.000059905113,0.00036244464,0.00030912666,0.000042136653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073165435,0.0006615228,0.00057573774,0.00074560894,0.0004905328,0.0016897388,0.002069749,0.00063916703,0.010009213],"category_scores_gemma":[0.0035456459,0.0004755224,0.00072816317,0.0015012044,0.0007842772,0.0021841521,0.00114919,0.001493032,0.004259697],"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":[0.0008980063,0.00023829374,0.0028289421,0.0007262913,0.00014208179,0.0006326871,0.0005703508,0.1488849,0.036375538,0.22866139,0.09038818,0.48965335],"study_design_scores_gemma":[0.00015195446,0.0001993227,0.0009098636,0.00010365231,0.000046619214,0.0002537763,0.0001515504,0.7524582,0.037138745,0.08363355,0.124898516,0.000054239506],"about_ca_topic_score_codex":0.0036866828,"about_ca_topic_score_gemma":0.0044860905,"teacher_disagreement_score":0.010009213,"about_ca_system_score_codex":0.0011596871,"about_ca_system_score_gemma":0.0012411689,"threshold_uncertainty_score":0.0334841},"labels":[],"label_agreement":null},{"id":"W4396882544","doi":"","title":"Model-Independent Description of $B\\rightarrow D \\pi \\ell \\nu$ Decays","year":2024,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Alexander von Humboldt-Stiftung; Fermilab; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Pi; Physics; Particle physics; Nuclear physics; Mathematics; Geometry","score_opus":0.07868762439233411,"score_gpt":0.18560955272678117,"score_spread":0.10692192833444707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396882544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03785282,0.00073694275,0.9500362,0.00038802414,0.000094281364,0.00006547673,0.0006560874,0.00036969225,0.009800457],"genre_scores_gemma":[0.67477924,0.0029703707,0.29669896,0.0005210399,0.00022959376,0.00060441287,0.0024376498,0.00054978067,0.021208936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997247,0.000057060723,0.000018959854,0.000047175028,0.00011790389,0.00003421628],"domain_scores_gemma":[0.9995161,0.00014897402,0.000041912834,0.00018703751,0.00007911891,0.000026801225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046981388,0.00069212826,0.000824164,0.00075426046,0.00065028766,0.0017326798,0.0020947135,0.0010977001,0.0028752033],"category_scores_gemma":[0.0013997656,0.00030399708,0.00090068387,0.0008505945,0.00047825213,0.0023030534,0.0010489483,0.0014660995,0.001431107],"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":[0.0001872145,0.00014221428,0.0018751735,0.00018658137,0.00007957423,0.00064908486,0.00016543086,0.5239791,0.016440343,0.39144236,0.004552539,0.06030033],"study_design_scores_gemma":[0.0000071362783,0.000012530483,0.00014493529,0.000008342278,0.00000927358,0.00015114369,0.000019947493,0.9257381,0.0025221384,0.068158895,0.003213801,0.000013852902],"about_ca_topic_score_codex":0.0008988339,"about_ca_topic_score_gemma":0.0011591282,"teacher_disagreement_score":0.0028752033,"about_ca_system_score_codex":0.00056698674,"about_ca_system_score_gemma":0.0008965766,"threshold_uncertainty_score":0.009618521},"labels":[],"label_agreement":null},{"id":"W4396921228","doi":"10.1016/j.aam.2024.102721","title":"Automatic sequences and the Glaisher–Kinkelin constant","year":2024,"lang":"en","type":"article","venue":"Advances in Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Killam Trusts","keywords":"Mathematics; Constant (computer programming); Combinatorics; Computer science","score_opus":0.008344055255536602,"score_gpt":0.2605381709525949,"score_spread":0.2521941156970583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396921228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3735332,0.006655777,0.46424776,0.0042880815,0.0010298941,0.00007259801,0.00029901322,0.0008520905,0.14902152],"genre_scores_gemma":[0.936445,0.0013103125,0.037059072,0.00054552977,0.00046206499,0.000074397896,0.000119690325,0.00025107973,0.023732819],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994295,0.00017213935,0.000027078673,0.00012748307,0.00015018658,0.00009351694],"domain_scores_gemma":[0.9979826,0.0012462795,0.00021890915,0.00020668365,0.00021905094,0.00012647724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007515985,0.00049698935,0.0004962466,0.0024751602,0.0011355744,0.0015293675,0.00076675625,0.0011844599,0.007687033],"category_scores_gemma":[0.007238268,0.0002662026,0.00038827036,0.0015197275,0.0026300875,0.003522342,0.0014867363,0.0021402347,0.0013497028],"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":[0.000039683237,0.000012237872,0.00017602557,0.00002930521,0.000004645433,0.00006480796,0.00015546397,0.0022847268,0.0009603221,0.9759867,0.0012310739,0.019055039],"study_design_scores_gemma":[0.000010272836,0.0000133419335,0.00023770158,0.000016240405,0.0000033945198,0.00011323545,0.00004427084,0.012478968,0.0007215416,0.98243433,0.0039087213,0.000018023871],"about_ca_topic_score_codex":0.00085677946,"about_ca_topic_score_gemma":0.0006592297,"teacher_disagreement_score":0.007687033,"about_ca_system_score_codex":0.0010339115,"about_ca_system_score_gemma":0.0005988231,"threshold_uncertainty_score":0.025715709},"labels":[],"label_agreement":null},{"id":"W4398163615","doi":"10.1109/dcc58796.2024.00020","title":"Faster Maximal Exact Matches with Lazy LCP Evaluation","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Research and Development; National Human Genome Research Institute; Ministry of Education","keywords":"Computer science","score_opus":0.02493870012300955,"score_gpt":0.2722633383496262,"score_spread":0.24732463822661663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398163615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10719762,0.0015143562,0.828634,0.000727495,0.0003061319,0.00043605993,0.0020778915,0.04541561,0.013690779],"genre_scores_gemma":[0.41152784,0.00031491718,0.5688301,0.0005251083,0.0002786823,0.00045671433,0.0057818433,0.0036593028,0.008625514],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99543875,0.00061404414,0.0004569699,0.0007268671,0.0021404873,0.0006229138],"domain_scores_gemma":[0.99410003,0.0022470118,0.00040452945,0.0021617028,0.0008899291,0.00019662034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022418,0.0014315459,0.0015135874,0.0029764078,0.0010746927,0.0036628644,0.0030294547,0.0012581048,0.010520407],"category_scores_gemma":[0.012349179,0.00078002067,0.0010211164,0.004935519,0.0016786068,0.0075313775,0.004844299,0.0015208292,0.005109929],"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":[0.0029304055,0.0004921808,0.0063989284,0.00063675625,0.00015427632,0.0006244462,0.0008017578,0.02745737,0.07630716,0.047293384,0.033233877,0.80366945],"study_design_scores_gemma":[0.00058022514,0.0005680532,0.002852922,0.00013081219,0.00017790083,0.0011579138,0.00051783776,0.6813588,0.16686364,0.105302,0.040308896,0.00018102404],"about_ca_topic_score_codex":0.0053887167,"about_ca_topic_score_gemma":0.00651265,"teacher_disagreement_score":0.010520407,"about_ca_system_score_codex":0.0022831713,"about_ca_system_score_gemma":0.004062712,"threshold_uncertainty_score":0.03519422},"labels":[],"label_agreement":null},{"id":"W4398163643","doi":"10.1109/dcc58796.2024.00057","title":"Succinct Data Structures for Path Graphs and Chordal Graphs Revisited","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Waterloo; Dalhousie University","funders":"","keywords":"Combinatorics; Binary logarithm; Neighbourhood (mathematics); Mathematics; Data structure; Chordal graph; Vertex (graph theory); Longest path problem; Adjacency list; Shortest path problem; Path (computing); Log-log plot; Intersection (aeronautics); Induced path; Discrete mathematics; Graph; Computer science","score_opus":0.02761929996222112,"score_gpt":0.2909809107088401,"score_spread":0.26336161074661896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398163643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0300709,0.0013584152,0.9428669,0.0028440238,0.00049704546,0.00046371922,0.006460932,0.009179063,0.0062589557],"genre_scores_gemma":[0.299192,0.0012996782,0.67292714,0.0018633016,0.00034916587,0.0010861527,0.012888248,0.0015399951,0.008854313],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947231,0.00083929626,0.00080122193,0.0007613982,0.002380199,0.00049484393],"domain_scores_gemma":[0.9792367,0.004237566,0.0015197038,0.011619809,0.0030076478,0.00037847308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00219955,0.0011858224,0.001435822,0.002477259,0.0011232268,0.0036897648,0.0042466833,0.0013618149,0.011823685],"category_scores_gemma":[0.019928053,0.0010852576,0.0012073893,0.006087603,0.0020012418,0.016057556,0.0048362142,0.004352138,0.0034058448],"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":[0.0017877695,0.00045571645,0.0036217684,0.0010459889,0.0001117745,0.00033073203,0.0009056493,0.04603089,0.024494475,0.3690211,0.05677122,0.495423],"study_design_scores_gemma":[0.00049748784,0.0010544008,0.0014333887,0.00052158657,0.00015987673,0.0011753653,0.00078462146,0.22865987,0.07341711,0.53161466,0.16034111,0.00034051505],"about_ca_topic_score_codex":0.003275225,"about_ca_topic_score_gemma":0.0046464484,"teacher_disagreement_score":0.011823685,"about_ca_system_score_codex":0.002474515,"about_ca_system_score_gemma":0.0032185456,"threshold_uncertainty_score":0.03955418},"labels":[],"label_agreement":null},{"id":"W4398163961","doi":"10.1109/dcc58796.2024.00033","title":"Space-Efficient Data Structures for Polyominoes and Bar Graphs","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polyomino; Bar (unit); Space (punctuation); Computer science; Data structure; Combinatorics; Discrete mathematics; Mathematics; Theoretical computer science; Geometry; Programming language; Geography","score_opus":0.030151343223033422,"score_gpt":0.28963347900922354,"score_spread":0.2594821357861901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398163961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03404859,0.0012467991,0.9378924,0.0014193084,0.00032519974,0.00051994453,0.009969277,0.008343636,0.0062348736],"genre_scores_gemma":[0.2535369,0.0010925978,0.7154406,0.00088315917,0.00022534124,0.001948542,0.017612452,0.0012657574,0.007994624],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99775594,0.0002719314,0.00043405435,0.00040791265,0.0008836352,0.00024658212],"domain_scores_gemma":[0.9911951,0.0021479886,0.0010216113,0.004129075,0.0012802006,0.00022612554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010626009,0.0010347541,0.0013665643,0.0021046344,0.0014013401,0.0034156784,0.0027251795,0.0012217846,0.009489019],"category_scores_gemma":[0.010797486,0.0008045811,0.0011630374,0.0051811794,0.0015530534,0.009232585,0.0033467761,0.0026992464,0.003077635],"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":[0.0014495323,0.00046773738,0.0033627718,0.0012827481,0.000087845285,0.0003455342,0.0008850485,0.05841915,0.028379329,0.3468041,0.053444874,0.5050712],"study_design_scores_gemma":[0.0003226568,0.0007491432,0.0013993047,0.0006578652,0.000104273204,0.0008585796,0.0007098223,0.28908682,0.06469178,0.5019759,0.13914871,0.00029515024],"about_ca_topic_score_codex":0.00229463,"about_ca_topic_score_gemma":0.003955804,"teacher_disagreement_score":0.009489019,"about_ca_system_score_codex":0.0020394118,"about_ca_system_score_gemma":0.002438233,"threshold_uncertainty_score":0.031743944},"labels":[],"label_agreement":null},{"id":"W4398168374","doi":"10.1101/2024.05.16.594622","title":"Enhanced Thompson Sampling by Roulette Wheel Selection for Screening Ultra-Large Combinatorial Libraries","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"AstraZeneca (Canada)","funders":"","keywords":"Roulette; Selection (genetic algorithm); Sampling (signal processing); Fitness proportionate selection; Computer science; Artificial intelligence; Statistics; Machine learning; Mathematics; Computer vision; Genetic algorithm","score_opus":0.016022517426089445,"score_gpt":0.2384339786619829,"score_spread":0.22241146123589345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398168374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10164511,0.00046938867,0.8913702,0.00032275278,0.00007469497,0.00019654635,0.0002029936,0.0036411376,0.0020772433],"genre_scores_gemma":[0.5836887,0.00015902157,0.4124953,0.0002677884,0.000059352184,0.0005078969,0.00062002946,0.00023443114,0.0019675018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982174,0.00084905326,0.00007869581,0.00018926221,0.0005108623,0.00015477095],"domain_scores_gemma":[0.9971738,0.0016840164,0.00016473194,0.00047728882,0.00038333994,0.000116710435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022272037,0.00066890597,0.0015269432,0.001302666,0.00047017948,0.00083091675,0.0018706236,0.0009598177,0.0016693408],"category_scores_gemma":[0.006153986,0.00035110756,0.00061528914,0.0015196668,0.00066991814,0.0009286352,0.0009944589,0.0008458674,0.0006093761],"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":[0.0008219442,0.0002986109,0.0029738075,0.00012536136,0.00011266871,0.0002034315,0.0001082346,0.7120581,0.01796665,0.0128229745,0.004752593,0.24775563],"study_design_scores_gemma":[0.00003237853,0.000035564222,0.00018333003,0.0000027275432,0.000006576185,0.000017597542,0.0000041022076,0.99479586,0.0024157737,0.0021377672,0.00036156864,0.0000068087957],"about_ca_topic_score_codex":0.004369813,"about_ca_topic_score_gemma":0.005593568,"teacher_disagreement_score":0.004369813,"about_ca_system_score_codex":0.00089715514,"about_ca_system_score_gemma":0.0014372524,"threshold_uncertainty_score":0.011778712},"labels":[],"label_agreement":null},{"id":"W4398662437","doi":"10.7910/dvn/itvlik/fv9uwq","title":"gde-1-1-15.zip","year":2020,"lang":"zh","type":"dataset","venue":"Harvard Dataverse","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Zip code; Computer science; Database","score_opus":0.02274588612559614,"score_gpt":0.24468668487405637,"score_spread":0.22194079874846023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398662437","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002286714,0.00007851514,0.00014721717,0.00013494855,0.0000654213,0.00002915791,0.99412656,0.0030777692,0.0021117956],"genre_scores_gemma":[0.00063132495,0.00006294646,0.00045465172,0.000084659136,0.000018238208,0.00007331069,0.99691427,0.0004555141,0.0013050562],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988236,0.0001404864,0.000111538015,0.00031641682,0.00031930816,0.00028862496],"domain_scores_gemma":[0.99730057,0.00046345283,0.0001543967,0.0010820756,0.0006821586,0.00031730247],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012455021,0.0031749983,0.0017344516,0.0037799624,0.0010192833,0.0033254626,0.004615347,0.0025291808,0.22584113],"category_scores_gemma":[0.0068601384,0.0008996543,0.0011983493,0.0064986176,0.0007156108,0.0024923899,0.0028626292,0.0018603711,0.30616358],"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":[0.00005105147,0.000019562258,0.00016042282,0.00022839634,0.00000855986,0.000006051546,0.000008322994,0.00012547402,0.0001059682,0.00034876072,0.9967704,0.0021671501],"study_design_scores_gemma":[0.00049834605,0.000058390906,0.0016840182,0.00018329332,0.000013151863,0.000056374087,0.00006401334,0.0010278388,0.0012184435,0.002546484,0.99262285,0.000026676715],"about_ca_topic_score_codex":0.010282797,"about_ca_topic_score_gemma":0.015949037,"teacher_disagreement_score":0.77415884,"about_ca_system_score_codex":0.0017832596,"about_ca_system_score_gemma":0.0017915699,"threshold_uncertainty_score":0.75551385},"labels":[],"label_agreement":null},{"id":"W4398714422","doi":"10.7910/dvn/hbikkv/ba9fba","title":"RunA.nc","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Computer science","score_opus":0.016802948319129752,"score_gpt":0.2352101464485778,"score_spread":0.21840719812944803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398714422","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027829257,0.0001811468,0.0012984072,0.0002049552,0.00019940216,0.000064590444,0.934222,0.056687888,0.0068633556],"genre_scores_gemma":[0.0012623051,0.00018816417,0.003540867,0.00017952181,0.000064871405,0.0003057193,0.9803683,0.009644472,0.004445692],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985135,0.00017707875,0.00012335814,0.0006348259,0.00032093946,0.0002303379],"domain_scores_gemma":[0.9971194,0.00059613015,0.00014669148,0.001258846,0.0006033866,0.00027558507],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017351963,0.0044699903,0.0025703167,0.0036984996,0.0013307813,0.0051196986,0.004777931,0.0017758784,0.32335117],"category_scores_gemma":[0.0080732675,0.0017855759,0.0023154665,0.0057782163,0.0007434042,0.0027877884,0.0029807223,0.002440629,0.5399203],"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":[0.00007155417,0.000019555982,0.00021701823,0.0002605404,0.000034953497,0.0000050867675,0.00001598547,0.00014520367,0.00014925064,0.00044736284,0.9937735,0.004859932],"study_design_scores_gemma":[0.00032896057,0.000028279215,0.0010638915,0.00010337027,0.000037058602,0.000026723561,0.000027648483,0.0012096539,0.0012842622,0.0028565696,0.9929938,0.000039744315],"about_ca_topic_score_codex":0.012491759,"about_ca_topic_score_gemma":0.015470611,"teacher_disagreement_score":0.67664886,"about_ca_system_score_codex":0.0012227562,"about_ca_system_score_gemma":0.0027326453,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4399276121","doi":"10.1101/2024.05.30.596587","title":"b-move: faster bidirectional character extensions in a run-length compressed index","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institutes of Health; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Overhead (engineering); Index (typography); Character (mathematics); Search engine indexing; Algorithm; Parallel computing; Cache; Closing (real estate); Matching (statistics); Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.01461162305871094,"score_gpt":0.22956977823168817,"score_spread":0.21495815517297723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399276121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13874862,0.0035799916,0.67089784,0.0008541506,0.0008070394,0.00065421767,0.0082980655,0.15173696,0.024423126],"genre_scores_gemma":[0.30485648,0.0006012005,0.65322596,0.0006744276,0.00016393866,0.00059983315,0.020183368,0.006738831,0.012956042],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866545,0.00014035382,0.00015308785,0.00026598305,0.00059749157,0.00017764296],"domain_scores_gemma":[0.9980205,0.00039616306,0.00015967374,0.0008431577,0.00043435206,0.00014608366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000753644,0.0011538442,0.00091110414,0.0015250657,0.00075905723,0.0018263818,0.0029521836,0.0008685179,0.009346018],"category_scores_gemma":[0.0049505057,0.0005895256,0.00079724524,0.0030723743,0.0006955618,0.0044255345,0.0032334893,0.0011438194,0.0073576192],"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":[0.0034210382,0.0006623838,0.0051206243,0.0011595567,0.00018535256,0.0007526313,0.0009287421,0.017899463,0.13521037,0.037865818,0.13274512,0.6640489],"study_design_scores_gemma":[0.0008922975,0.0012444522,0.0027207683,0.00034085737,0.00017466264,0.0013935742,0.0007206741,0.49110973,0.21208008,0.035963103,0.2530243,0.0003355098],"about_ca_topic_score_codex":0.0038293737,"about_ca_topic_score_gemma":0.005013059,"teacher_disagreement_score":0.009346018,"about_ca_system_score_codex":0.000837609,"about_ca_system_score_gemma":0.0012778345,"threshold_uncertainty_score":0.031265497},"labels":[],"label_agreement":null},{"id":"W4399370999","doi":"10.7155/jgaa.v28i1.2933","title":"Distance-Preserving Graph Compression Techniques","year":2024,"lang":"en","type":"article","venue":"Journal of Graph Algorithms and Applications","topic":"Algorithms and Data Compression","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":"Carleton University","funders":"","keywords":"Computer science; Compression (physics); Graph; Theoretical computer science; Materials science; Composite material","score_opus":0.012441054180522498,"score_gpt":0.27545003469494855,"score_spread":0.26300898051442606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399370999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037741635,0.0013883127,0.95644337,0.00041532883,0.00007062816,0.00010387084,0.00014401012,0.0005254155,0.0031674393],"genre_scores_gemma":[0.36135963,0.0020797946,0.62899977,0.00028982727,0.00019037905,0.00021823017,0.000759747,0.0002992119,0.0058035427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998767,0.000209507,0.00007132298,0.0002126484,0.0006404619,0.00009905427],"domain_scores_gemma":[0.9974388,0.0012279836,0.00026450533,0.00068287057,0.00032836135,0.000057412395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009943529,0.00089426583,0.0008077672,0.0018883646,0.0004779402,0.0009829473,0.0019210842,0.0011001126,0.0019760863],"category_scores_gemma":[0.0056713843,0.00034676943,0.0006118334,0.0032708086,0.0009961317,0.0033011166,0.0016155652,0.0012571303,0.0007009595],"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":[0.00025778174,0.00017198318,0.00090911106,0.00047024156,0.000096597374,0.00031002073,0.0003361144,0.2832721,0.024825078,0.0873012,0.0052008945,0.59684885],"study_design_scores_gemma":[0.000046764464,0.00026247615,0.00050630624,0.000058802074,0.000048732178,0.0008884273,0.00014752054,0.8575749,0.030439511,0.10233612,0.0076629315,0.00002753586],"about_ca_topic_score_codex":0.0007590641,"about_ca_topic_score_gemma":0.0007813482,"teacher_disagreement_score":0.0019760863,"about_ca_system_score_codex":0.0006779391,"about_ca_system_score_gemma":0.00065138616,"threshold_uncertainty_score":0.006610632},"labels":[],"label_agreement":null},{"id":"W4399636642","doi":"10.32614/cran.package.r5r","title":"r5r: Rapid Realistic Routing with 'R5'","year":2020,"lang":"en","type":"dataset","venue":"","topic":"Algorithms and Data Compression","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 Toronto","funders":"","keywords":"Computer science; Routing (electronic design automation); Computer network","score_opus":0.01800830907805613,"score_gpt":0.2364991988832204,"score_spread":0.2184908898051643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399636642","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002111674,0.00046832918,0.42198455,0.0010627661,0.0010119803,0.00027406536,0.09658537,0.4537677,0.022733582],"genre_scores_gemma":[0.032968845,0.0010245134,0.37518758,0.0013747879,0.0002216159,0.0017538938,0.17105155,0.39056948,0.02584778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736196,0.00082273403,0.00020836423,0.00053694425,0.00080993166,0.00026000186],"domain_scores_gemma":[0.9927008,0.0038250145,0.00040291293,0.0015148539,0.0013104654,0.00024580144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051293005,0.003453325,0.0023165902,0.0016413946,0.00084357744,0.004401987,0.0067625283,0.002592684,0.1945693],"category_scores_gemma":[0.022961682,0.0037422476,0.0043570506,0.0018904966,0.0007639395,0.004153113,0.0035746712,0.00499911,0.1321086],"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":[0.00016337378,0.00004867986,0.00091745704,0.0011321219,0.00024962277,0.00014038323,0.0001857684,0.032228403,0.0013848605,0.018184176,0.9134617,0.031903572],"study_design_scores_gemma":[0.0005170918,0.000110235975,0.0011273768,0.00041717797,0.00021363625,0.00026412023,0.00011536853,0.1546829,0.006971647,0.039361954,0.79590297,0.00031552263],"about_ca_topic_score_codex":0.014098414,"about_ca_topic_score_gemma":0.014094345,"teacher_disagreement_score":0.1945693,"about_ca_system_score_codex":0.0013613974,"about_ca_system_score_gemma":0.0030450805,"threshold_uncertainty_score":0.6508992},"labels":[],"label_agreement":null},{"id":"W4399908098","doi":"10.21105/joss.06598","title":"Delta-Rice: A HDF5 Compression Plugin optimized forDigitized Detector Data","year":2024,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Algorithms and Data Compression","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":"University of Winnipeg; University of Manitoba","funders":"Workforce Development for Teachers and Scientists; Nuclear Physics; Georgia Institute of Technology; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Computer science; Throughput; Detector; Filter (signal processing); Plug-in; Data compression; Coding (social sciences); Computer hardware; Operating system; Artificial intelligence; Telecommunications; Computer vision; Mathematics","score_opus":0.05151814030549124,"score_gpt":0.32671001849447373,"score_spread":0.2751918781889825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399908098","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02195709,0.0004920799,0.3309246,0.00030435759,0.000383917,0.00042262257,0.037757955,0.59971744,0.0080399625],"genre_scores_gemma":[0.11247469,0.00079229294,0.571433,0.0007186971,0.00014589448,0.0018851471,0.15955943,0.11929676,0.033694126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940336,0.000036222158,0.000047841528,0.00011297278,0.00031260093,0.00008694217],"domain_scores_gemma":[0.9990565,0.00025045473,0.000057546767,0.00024348543,0.00034575313,0.000046289628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009515129,0.0017281175,0.00066322094,0.0019880855,0.0005275337,0.0014263571,0.0021926214,0.0007432912,0.04543961],"category_scores_gemma":[0.004551542,0.00062218576,0.00073451584,0.001937742,0.00038212741,0.0015437257,0.0013628457,0.001208145,0.021053217],"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":[0.0012354858,0.00016558393,0.0034653312,0.00088366953,0.0001632722,0.0005324858,0.0005423828,0.006115804,0.066567145,0.005119279,0.4829389,0.43227062],"study_design_scores_gemma":[0.0003302132,0.00025745176,0.008922094,0.00017197504,0.00006781588,0.0009990106,0.00031413152,0.15214661,0.39635122,0.008088889,0.4321046,0.0002459986],"about_ca_topic_score_codex":0.0027679908,"about_ca_topic_score_gemma":0.0044748434,"teacher_disagreement_score":0.04543961,"about_ca_system_score_codex":0.0007022357,"about_ca_system_score_gemma":0.00087201933,"threshold_uncertainty_score":0.15201062},"labels":[],"label_agreement":null},{"id":"W4400365517","doi":"10.14722/spacesec.2024.23015","title":"Connecting the Dots in the Sky: Website Fingerprinting in Low Earth Orbit Satellite Internet","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; UK Research and Innovation","keywords":"Satellite; Low earth orbit; Sky; The Internet; Geocentric orbit; Computer science; Orbit (dynamics); Astrobiology; Astronomy; Remote sensing; Physics; Geology; World Wide Web; Aerospace engineering; Engineering","score_opus":0.01356171241672951,"score_gpt":0.24928842936708712,"score_spread":0.2357267169503576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400365517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973489,0.000038020793,0.0021046426,0.000034619516,0.0000062540435,0.000016043718,0.00004638412,0.000093991424,0.0003111427],"genre_scores_gemma":[0.99822265,0.000029009869,0.0015099578,0.000014543101,0.0000033690199,0.0000059270637,0.00006880851,0.000008405487,0.0001374391],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988018,0.00049194205,0.000063377105,0.00019373337,0.00030965416,0.00013943821],"domain_scores_gemma":[0.9934035,0.0031641836,0.0012859021,0.0012941214,0.0005382988,0.00031395577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010029122,0.00024075786,0.0002747259,0.00075397803,0.00063355244,0.0005819275,0.00042629175,0.00067870383,0.0004721671],"category_scores_gemma":[0.0060188896,0.00015103156,0.0001642174,0.0006647973,0.0008291123,0.0012834368,0.00066671625,0.0004820741,0.00014791319],"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":[0.004877954,0.003543795,0.456226,0.0005543153,0.0003600441,0.0045830864,0.005224788,0.1424386,0.16275734,0.008061076,0.007917704,0.20345533],"study_design_scores_gemma":[0.00013841568,0.003958266,0.24173401,0.00010212558,0.00018177937,0.0048295027,0.0046665715,0.5790642,0.15677467,0.0041143894,0.004296184,0.00013993873],"about_ca_topic_score_codex":0.0020012846,"about_ca_topic_score_gemma":0.0022055977,"teacher_disagreement_score":0.0020012846,"about_ca_system_score_codex":0.00038927546,"about_ca_system_score_gemma":0.00022877743,"threshold_uncertainty_score":0.0053039193},"labels":[],"label_agreement":null},{"id":"W4400506586","doi":"10.2139/ssrn.4890602","title":"Total Variation Distance for Product Distributions is #P-Complete","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Variation (astronomy); Product (mathematics); Mathematics; Statistics; Physics; Geometry; Astrophysics","score_opus":0.01363191873816765,"score_gpt":0.2624145223677131,"score_spread":0.24878260362954546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400506586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0410364,0.003075677,0.91910684,0.0054017375,0.00034306681,0.00010382831,0.0023684278,0.0010851906,0.02747886],"genre_scores_gemma":[0.678074,0.006603401,0.22863038,0.0031330804,0.0022568968,0.00078255363,0.00942841,0.002619556,0.06847174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954646,0.0011799205,0.00028753065,0.0011744061,0.0015347111,0.00035882698],"domain_scores_gemma":[0.9716905,0.020731691,0.0011143731,0.003483004,0.002357288,0.00062328984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038604394,0.0020300692,0.003189568,0.0030100986,0.00169395,0.006409431,0.005476391,0.0024953636,0.011612496],"category_scores_gemma":[0.025360666,0.0012688555,0.0022228474,0.005371875,0.003868261,0.012961263,0.005738223,0.0063012736,0.002987893],"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":[0.00033955168,0.00012775933,0.00089262327,0.0006464208,0.00015559989,0.00020176836,0.0003085918,0.03613591,0.0016141215,0.80227774,0.026836634,0.13046327],"study_design_scores_gemma":[0.000021726606,0.000038129125,0.00028894006,0.00002461421,0.000018882161,0.00016567971,0.00003558787,0.071425974,0.0007373517,0.9225495,0.004669333,0.000024210287],"about_ca_topic_score_codex":0.0020077855,"about_ca_topic_score_gemma":0.0015102755,"teacher_disagreement_score":0.011612496,"about_ca_system_score_codex":0.002509566,"about_ca_system_score_gemma":0.0020017733,"threshold_uncertainty_score":0.038847685},"labels":[],"label_agreement":null},{"id":"W4400571454","doi":"10.1016/j.tcs.2024.114728","title":"On suffix tree detection","year":2024,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Israel Science Foundation; United States-Israel Binational Science Foundation","keywords":"Generalized suffix tree; Suffix tree; Compressed suffix array; Suffix; String (physics); Time complexity; Mathematics; K-ary tree; Combinatorics; Tree (set theory); Data structure; Algorithm; Discrete mathematics; Binary tree; Tree structure; Computer science","score_opus":0.007287958903204772,"score_gpt":0.2471090558013316,"score_spread":0.23982109689812683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400571454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024636045,0.0035137855,0.95477724,0.0016637408,0.0008334602,0.00012253782,0.000437946,0.0026281148,0.011387157],"genre_scores_gemma":[0.24463281,0.0037223606,0.718825,0.001382364,0.0019660613,0.00024590502,0.0027275372,0.00079639803,0.025701605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963337,0.00084814633,0.00026898235,0.0007197126,0.0015710017,0.0002583755],"domain_scores_gemma":[0.989555,0.005677189,0.00032491368,0.0024513905,0.0017628907,0.00022876168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020349217,0.0012310205,0.0020087126,0.0040789032,0.0016822818,0.002942049,0.0023557553,0.0024749846,0.007992485],"category_scores_gemma":[0.015881928,0.00089076767,0.0008859535,0.0061199297,0.0017019218,0.0062894667,0.0038423394,0.0021070354,0.004315663],"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":[0.00058648706,0.00015487807,0.0019098944,0.00023345444,0.00010280763,0.00023744651,0.00018032773,0.02149893,0.015612981,0.06492753,0.0204623,0.87409294],"study_design_scores_gemma":[0.00006130202,0.0002071494,0.0015017586,0.00011450978,0.000106763146,0.0012160771,0.00015612453,0.6733366,0.024205118,0.26421666,0.03480858,0.00006929537],"about_ca_topic_score_codex":0.0021154245,"about_ca_topic_score_gemma":0.0024733031,"teacher_disagreement_score":0.007992485,"about_ca_system_score_codex":0.0009340967,"about_ca_system_score_gemma":0.0015648184,"threshold_uncertainty_score":0.026737511},"labels":[],"label_agreement":null},{"id":"W4400771146","doi":"10.1109/eiceeai60672.2023.10590243","title":"Feature Selection for Robust Spoofing Detection: A Chi-Square-based Machine Learning Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Selection (genetic algorithm); Machine learning; Spoofing attack; Feature (linguistics); Robustness (evolution); Algorithm","score_opus":0.025425338819382446,"score_gpt":0.23855649310737786,"score_spread":0.21313115428799542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400771146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113743186,0.0022670485,0.878205,0.0008943383,0.00031974487,0.00019959534,0.00028318967,0.0031700423,0.0009179004],"genre_scores_gemma":[0.8126654,0.0005329457,0.18212567,0.0006465257,0.0003123098,0.00026638948,0.0011211834,0.00021158991,0.0021178846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767476,0.00061317906,0.0001749236,0.0005640311,0.0006989311,0.0002741464],"domain_scores_gemma":[0.9954131,0.0024838638,0.00027511688,0.00019668488,0.0014642461,0.00016693735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040246546,0.0014962857,0.0031906248,0.0032550537,0.0009738815,0.0011111086,0.0021737576,0.0014934737,0.0014304142],"category_scores_gemma":[0.006956483,0.00046483715,0.0018320063,0.0024627787,0.0008469042,0.001228656,0.0007983194,0.0021629147,0.00087531755],"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":[0.0011665593,0.0009934271,0.030242221,0.00040691334,0.00073236064,0.0003259254,0.000313318,0.27276134,0.014324402,0.0025151283,0.010627413,0.66559106],"study_design_scores_gemma":[0.000019312305,0.00013185674,0.0019742802,0.000012774882,0.00004737197,0.00006810981,0.000034370263,0.99451494,0.0017816806,0.0007963432,0.0006019599,0.000016945707],"about_ca_topic_score_codex":0.008762079,"about_ca_topic_score_gemma":0.0050634514,"teacher_disagreement_score":0.008762079,"about_ca_system_score_codex":0.0008726323,"about_ca_system_score_gemma":0.0015091003,"threshold_uncertainty_score":0.02128464},"labels":[],"label_agreement":null},{"id":"W4401034109","doi":"10.1007/978-3-031-66159-4_10","title":"How to Find Long Maximal Exact Matches and Ignore Short Ones","year":2024,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Human Genome Research Institute; Università degli Studi di Milano-Bicocca","keywords":"Computer science; Algorithm; Theoretical computer science","score_opus":0.01619052697209217,"score_gpt":0.2570697544311087,"score_spread":0.24087922745901652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401034109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12942442,0.0030688324,0.8345103,0.0035824163,0.0013750725,0.00089113956,0.003534364,0.011699308,0.011914115],"genre_scores_gemma":[0.13431987,0.000816752,0.84373254,0.0007385252,0.0003768618,0.00020696764,0.004615972,0.002134835,0.013057699],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996167,0.0003255846,0.00037037404,0.0010365704,0.0015867961,0.0005136958],"domain_scores_gemma":[0.9914675,0.003061833,0.0005018006,0.0021147034,0.0023038941,0.0005501867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024097369,0.0013729942,0.0029788099,0.0044107665,0.0021123285,0.0037674445,0.0029443437,0.0025995085,0.016074063],"category_scores_gemma":[0.016789975,0.0012671236,0.0017701463,0.004360419,0.0011932645,0.009182259,0.003527147,0.0023680665,0.0097458875],"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":[0.0014303376,0.00042866566,0.008025685,0.0007797939,0.00026425297,0.00044516058,0.0002795887,0.011251522,0.026018212,0.0126680285,0.04226068,0.896148],"study_design_scores_gemma":[0.0005321234,0.000741058,0.006550313,0.00044791,0.00081826455,0.0038938334,0.0023634925,0.49514273,0.13400231,0.2569482,0.098246105,0.0003136356],"about_ca_topic_score_codex":0.003657203,"about_ca_topic_score_gemma":0.007776981,"teacher_disagreement_score":0.016074063,"about_ca_system_score_codex":0.00075500546,"about_ca_system_score_gemma":0.0037587956,"threshold_uncertainty_score":0.053773105},"labels":[],"label_agreement":null},{"id":"W4401180879","doi":"10.18280/mmep.110719","title":"Reaction and Kinetics in Immobilized Glucose Isomerase of Packed-Bed Reactors Using Akbari-Ganji’s Method","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Kinetics; Glucose-6-phosphate isomerase; Chemistry; Chemical engineering; Chromatography; Biochemistry; Enzyme; Engineering; Physics","score_opus":0.028802874473353255,"score_gpt":0.26073572453890065,"score_spread":0.2319328500655474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401180879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05105908,0.0021247538,0.94303644,0.00016014838,0.00011302866,0.00005942904,0.000056431687,0.00042510577,0.002965558],"genre_scores_gemma":[0.48069635,0.0033430415,0.50694364,0.000096816526,0.00004341704,0.00029736222,0.00011099021,0.000079916426,0.008388454],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997048,0.00007198679,0.000025513393,0.00006484526,0.00011134465,0.000021515638],"domain_scores_gemma":[0.9997695,0.00013908182,0.000024154673,0.000016683969,0.000042703996,0.000007876411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058537285,0.0005752948,0.0007735397,0.00043864126,0.00022240002,0.00043716145,0.0010323328,0.00071283214,0.00061277184],"category_scores_gemma":[0.0005797653,0.0004144362,0.0007746942,0.0004924538,0.00037541855,0.0007027083,0.00030792766,0.0010146145,0.00033770502],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023432585,0.00022770729,0.0013369208,0.00145811,0.00011080593,0.0005070011,0.00033707675,0.22273423,0.6217732,0.0449279,0.0008739274,0.10547883],"study_design_scores_gemma":[0.000010333132,0.00004591941,0.0003216911,0.0000073878286,0.000019937932,0.00007782713,0.000012924118,0.95683384,0.03968102,0.0017110249,0.0012538276,0.000024153584],"about_ca_topic_score_codex":0.0023703193,"about_ca_topic_score_gemma":0.001662102,"teacher_disagreement_score":0.0023703193,"about_ca_system_score_codex":0.0006107649,"about_ca_system_score_gemma":0.0004972912,"threshold_uncertainty_score":0.004712999},"labels":[],"label_agreement":null},{"id":"W4401198969","doi":"10.1142/s0129054124430019","title":"Repetition Factorization of Automatic Sequences","year":2024,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Factorization; Repetition (rhetorical device); Computer science; Mathematics; Theoretical computer science; Algorithm; Linguistics","score_opus":0.016683348424025496,"score_gpt":0.3159330991453174,"score_spread":0.2992497507212919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401198969","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43678012,0.0016338904,0.4951434,0.00055600924,0.00045792112,0.00014768538,0.00038033587,0.00074111915,0.06415944],"genre_scores_gemma":[0.85649484,0.00060008356,0.119876556,0.00029021633,0.00039760015,0.00015070489,0.0004261187,0.0001915984,0.02157239],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990914,0.00015470892,0.000073299256,0.00023677925,0.0002679992,0.0001759121],"domain_scores_gemma":[0.99853003,0.00053067773,0.00025988024,0.00020003009,0.00036973064,0.000109664536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005991143,0.0005194016,0.00039140994,0.0013359962,0.0010324572,0.00090851606,0.00035077168,0.0005800273,0.006426035],"category_scores_gemma":[0.0029340896,0.0002799493,0.00069439184,0.0007589145,0.0017764524,0.0024582855,0.0010863349,0.000859226,0.0014662106],"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":[0.00012775483,0.00002850204,0.00085496996,0.000120398705,0.000012009212,0.00052817684,0.0008956382,0.0037062448,0.015991278,0.9406192,0.0018681439,0.035247777],"study_design_scores_gemma":[0.000026945028,0.00019141694,0.0008449055,0.00006007695,0.000018309089,0.0009661735,0.00030068654,0.024950668,0.012236247,0.9393984,0.020932363,0.00007383575],"about_ca_topic_score_codex":0.00072847796,"about_ca_topic_score_gemma":0.0007195776,"teacher_disagreement_score":0.006426035,"about_ca_system_score_codex":0.00052459334,"about_ca_system_score_gemma":0.00047680232,"threshold_uncertainty_score":0.02149725},"labels":[],"label_agreement":null},{"id":"W4401250709","doi":"10.1007/978-981-97-3523-5_29","title":"Forest in the Clouds: Navigating Big Data with GRP and RFC","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Big data; Forestry; Geography; Computer science; Operating system","score_opus":0.03249361413212772,"score_gpt":0.24884895951293204,"score_spread":0.2163553453808043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401250709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02984633,0.0027556233,0.9397358,0.0012840682,0.0005306598,0.00013166267,0.0016021321,0.013006252,0.011107429],"genre_scores_gemma":[0.17834951,0.0016692276,0.8108546,0.00035402688,0.00017684243,0.00011061282,0.0021958898,0.0018445365,0.0044447985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962234,0.0000649629,0.000015730637,0.0000917004,0.00015049113,0.000054730805],"domain_scores_gemma":[0.9993012,0.00031715826,0.000026956011,0.00019004173,0.000103592654,0.000060985225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000689767,0.00090027635,0.0011180786,0.001221371,0.0010764535,0.0018456578,0.002135582,0.0010244382,0.00521918],"category_scores_gemma":[0.0030445117,0.0006997412,0.0008888999,0.002806549,0.0009142944,0.0033684387,0.002685463,0.0015037582,0.0021046675],"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":[0.00032906083,0.00015265391,0.0021605254,0.0003462002,0.000132251,0.00039894623,0.000584876,0.34999597,0.006798819,0.033308245,0.07881226,0.52698016],"study_design_scores_gemma":[0.000022017075,0.000025358228,0.00038496614,0.00003336151,0.00001913309,0.0001058812,0.00017203236,0.93185693,0.002164928,0.051605556,0.013585566,0.000024335866],"about_ca_topic_score_codex":0.021727253,"about_ca_topic_score_gemma":0.027385177,"teacher_disagreement_score":0.021727253,"about_ca_system_score_codex":0.00053298473,"about_ca_system_score_gemma":0.0009001542,"threshold_uncertainty_score":0.043201566},"labels":[],"label_agreement":null},{"id":"W4401250847","doi":"10.1109/jcsse61278.2024.10613658","title":"Bit-Level Affixation Text Compression Algorithms","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Computer science; Data compression; Bit (key); Compression (physics); Algorithm; Arithmetic; Theoretical computer science; Mathematics; Materials science; Computer network","score_opus":0.03729456618354854,"score_gpt":0.28375144655452883,"score_spread":0.2464568803709803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401250847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049393848,0.002455765,0.93257195,0.0002841693,0.00028858762,0.00038897755,0.00081100897,0.0050771134,0.008728585],"genre_scores_gemma":[0.16163908,0.0017612521,0.8235822,0.00022997962,0.0001552281,0.00039549224,0.0019897602,0.00031421182,0.0099328505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999585,0.000040392188,0.00005036064,0.00008007049,0.00020831368,0.00003587677],"domain_scores_gemma":[0.9993119,0.00017934665,0.00006468602,0.00014568743,0.00028410353,0.00001418694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033903326,0.0006597561,0.00042067005,0.0015142397,0.00037705337,0.0008823516,0.0008810712,0.0006151672,0.0053165234],"category_scores_gemma":[0.0019578477,0.0001361282,0.00034105434,0.0019324125,0.00037772054,0.00095557986,0.0005202737,0.00058826944,0.0032886378],"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":[0.00020999933,0.00006432733,0.0008753177,0.00024599853,0.00003351144,0.00012626502,0.00010349534,0.0128443,0.06393958,0.011255446,0.0047951406,0.90550655],"study_design_scores_gemma":[0.00012885082,0.00040748058,0.0043502273,0.000136458,0.00010431154,0.002386595,0.00017390498,0.49110273,0.41304338,0.02007551,0.06800307,0.0000875435],"about_ca_topic_score_codex":0.001042669,"about_ca_topic_score_gemma":0.0011985924,"teacher_disagreement_score":0.0053165234,"about_ca_system_score_codex":0.00033909967,"about_ca_system_score_gemma":0.00052198896,"threshold_uncertainty_score":0.01778555},"labels":[],"label_agreement":null},{"id":"W4401353529","doi":"10.14778/3675034.3675050","title":"DEX: Scalable Range Indexing on Disaggregated Memory","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"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":"Search engine indexing; Scalability; Range (aeronautics); Computer science; Parallel computing; Information retrieval; Database; Engineering","score_opus":0.01133561931545859,"score_gpt":0.2271684346161253,"score_spread":0.2158328153006667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401353529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14323203,0.006406331,0.78670186,0.0006783484,0.00038609977,0.00037965953,0.0033328237,0.036859874,0.022023024],"genre_scores_gemma":[0.54559034,0.0015738178,0.43568414,0.00044273635,0.00015162976,0.0003088389,0.006426105,0.0009898838,0.008832618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992951,0.00007350729,0.00007202533,0.00009037232,0.00037329085,0.000095558215],"domain_scores_gemma":[0.9984446,0.0003087462,0.0001046241,0.0007325537,0.00030852103,0.00010101617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045826047,0.0005680234,0.0007851438,0.0013009643,0.00056551874,0.0012698089,0.0015411262,0.00044299712,0.003611249],"category_scores_gemma":[0.002787534,0.0002967041,0.00030482362,0.0032278725,0.0003854373,0.0034964038,0.002389834,0.00067727844,0.0017513726],"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":[0.0011656752,0.00025963536,0.003939004,0.0004378997,0.00009754077,0.00033031098,0.00038188373,0.04408745,0.06987282,0.025080595,0.055286624,0.7990605],"study_design_scores_gemma":[0.00032555076,0.0005777157,0.0037030745,0.000107738015,0.00007455744,0.0010326682,0.0005399312,0.77231133,0.08203579,0.047272433,0.091913275,0.000105961626],"about_ca_topic_score_codex":0.0030842875,"about_ca_topic_score_gemma":0.004327853,"teacher_disagreement_score":0.003611249,"about_ca_system_score_codex":0.00050009985,"about_ca_system_score_gemma":0.00081278745,"threshold_uncertainty_score":0.012080789},"labels":[],"label_agreement":null},{"id":"W4401422447","doi":"10.1145/3677608","title":"Tight Bounds for Monotone Minimal Perfect Hashing","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"Air Force Research Laboratory; Hertz Foundation","keywords":"Combinatorics; Upper and lower bounds; Bounded function; Mathematics; Hash function; Perfect hash function; Monotone polygon; Omega; Binary logarithm; Discrete mathematics; Chromatic scale; Hash table; Physics; Computer science","score_opus":0.02788054483978671,"score_gpt":0.29489105201843646,"score_spread":0.26701050717864977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401422447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12960207,0.015156202,0.7353678,0.019419698,0.001341579,0.0007808574,0.0051733013,0.00873135,0.08442711],"genre_scores_gemma":[0.74594873,0.004641063,0.2123833,0.0054162713,0.0020810862,0.0014132747,0.005720172,0.0023555376,0.02004056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98072296,0.0042630304,0.0011109087,0.0034022543,0.006650661,0.0038502363],"domain_scores_gemma":[0.94556165,0.034975715,0.002136316,0.012768308,0.0027043347,0.0018536877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009705191,0.002659004,0.004084955,0.0022824577,0.0032799544,0.007495543,0.0074177096,0.0040052854,0.019877467],"category_scores_gemma":[0.060030147,0.002038074,0.0027979733,0.0049246973,0.0056379214,0.03345823,0.0126431445,0.009349816,0.0055795657],"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":[0.0037565094,0.0007277122,0.003533212,0.0019766558,0.0002793249,0.00039261955,0.0011401417,0.07967494,0.013572866,0.69399434,0.047720324,0.15323138],"study_design_scores_gemma":[0.0002655968,0.00037028926,0.0007029215,0.00021126472,0.00017442703,0.0003813495,0.0002382796,0.18898638,0.0063652094,0.7884351,0.013768553,0.00010069427],"about_ca_topic_score_codex":0.002642794,"about_ca_topic_score_gemma":0.0031106432,"teacher_disagreement_score":0.019877467,"about_ca_system_score_codex":0.006432535,"about_ca_system_score_gemma":0.0049153566,"threshold_uncertainty_score":0.06649673},"labels":[],"label_agreement":null},{"id":"W4401769635","doi":"10.18280/isi.290434","title":"Candidate Best Optimizations Sequences for Code Size Reduction","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reduction (mathematics); Code (set theory); Computer science; Mathematics; Programming language; Set (abstract data type)","score_opus":0.02719312972631786,"score_gpt":0.2754569559368548,"score_spread":0.24826382621053697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5560746,0.0045190435,0.4170252,0.000859612,0.00023189966,0.00090052973,0.002218014,0.008967987,0.009203066],"genre_scores_gemma":[0.50732774,0.00083281583,0.48085475,0.00020124546,0.000060368977,0.00054256123,0.0048645176,0.00071757863,0.0045985426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992986,0.00016183409,0.000057495094,0.00018319048,0.0002133675,0.00008553404],"domain_scores_gemma":[0.99868983,0.0004887437,0.00018440535,0.00018269412,0.00039584166,0.000058418947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059346965,0.0013160914,0.0006401309,0.002538048,0.0005886831,0.0005791793,0.00071736495,0.0005654379,0.003418509],"category_scores_gemma":[0.0033256698,0.00032229084,0.0007952277,0.0011949058,0.00040292193,0.0007232119,0.00039989053,0.00059778785,0.0010434914],"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":[0.00117577,0.0007542655,0.017093008,0.00085584127,0.00011045078,0.000403735,0.00026240965,0.109127894,0.0887337,0.0040444336,0.010597563,0.766841],"study_design_scores_gemma":[0.00022651728,0.0014624296,0.011884436,0.00017056632,0.00030409952,0.0007169334,0.00048244192,0.8740187,0.084433764,0.007768183,0.018459713,0.00007223844],"about_ca_topic_score_codex":0.002029083,"about_ca_topic_score_gemma":0.0041659237,"teacher_disagreement_score":0.003418509,"about_ca_system_score_codex":0.0004772971,"about_ca_system_score_gemma":0.0022468676,"threshold_uncertainty_score":0.011436045},"labels":[],"label_agreement":null},{"id":"W4401908847","doi":"10.22541/au.172477347.74689772/v1","title":"Batched Ranged Random Integer Generation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Université TÉLUQ","funders":"","keywords":"Integer (computer science); Integer programming; Mathematics; Computer science; Algorithm; Programming language","score_opus":0.032682550526843795,"score_gpt":0.27418628310142784,"score_spread":0.24150373257458405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401908847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022499245,0.00026661382,0.9647748,0.00015338199,0.00021816781,0.0004200479,0.0009177188,0.0044995034,0.0062505086],"genre_scores_gemma":[0.26308957,0.00017202355,0.7183577,0.00029906226,0.00011300304,0.0012301939,0.0021684123,0.000787348,0.013782639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977665,0.00055441266,0.00017105433,0.0005617732,0.0007478984,0.00019835895],"domain_scores_gemma":[0.99585706,0.0014717544,0.00020166286,0.0015808356,0.000741584,0.00014700247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015707413,0.00052164274,0.000882971,0.0007445354,0.00052931975,0.0011313958,0.0019018232,0.00081526506,0.009786463],"category_scores_gemma":[0.007286428,0.00042745456,0.0005224235,0.0009669754,0.00071402016,0.001509788,0.0016349645,0.0011528933,0.004800775],"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":[0.0022626664,0.00036781398,0.003264768,0.0005039899,0.00013091031,0.0007648135,0.00038114536,0.13428725,0.1439451,0.21979819,0.035318144,0.45897526],"study_design_scores_gemma":[0.0003795872,0.00039180697,0.0007852549,0.00006156478,0.00005647282,0.00076117215,0.00006119186,0.7385577,0.1333212,0.08794061,0.037555493,0.00012802197],"about_ca_topic_score_codex":0.00035819478,"about_ca_topic_score_gemma":0.000620485,"teacher_disagreement_score":0.009786463,"about_ca_system_score_codex":0.0005547833,"about_ca_system_score_gemma":0.0009431533,"threshold_uncertainty_score":0.032738984},"labels":[],"label_agreement":null},{"id":"W4402187268","doi":"10.1109/tit.2024.3454119","title":"Reconstruction From Noisy Substrings","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Substring; Computer science; Algorithm; Artificial intelligence; Mathematics; Data structure","score_opus":0.007290395334684244,"score_gpt":0.21114702613363967,"score_spread":0.20385663079895544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402187268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14845508,0.0017200873,0.84544206,0.00064567564,0.00009631678,0.000033417266,0.00031795926,0.00029944346,0.002989976],"genre_scores_gemma":[0.83680266,0.0019272298,0.15576608,0.00019785036,0.00017495935,0.00008942239,0.00087254465,0.00014244429,0.004026758],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998546,0.00046366444,0.00008941249,0.00032597053,0.00044332497,0.00013165238],"domain_scores_gemma":[0.99056256,0.0069929524,0.00076315453,0.0010127597,0.0005245927,0.00014381978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019074943,0.0006059327,0.0015084422,0.00079158845,0.00047063528,0.0010453172,0.0011748866,0.001522286,0.0011706678],"category_scores_gemma":[0.016268225,0.0006108988,0.0004987614,0.0009609858,0.0018827092,0.0033588316,0.0014792214,0.0013463841,0.000560092],"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":[0.001048417,0.00007778845,0.0025275778,0.00071855856,0.00009858716,0.0005747232,0.00043917733,0.7078966,0.03519225,0.16820343,0.0016024725,0.08162048],"study_design_scores_gemma":[0.000039078703,0.00007227093,0.0004887394,0.000054849057,0.0000188038,0.000275635,0.00008736472,0.90129143,0.01975451,0.07636204,0.0015149649,0.000040191167],"about_ca_topic_score_codex":0.0006575154,"about_ca_topic_score_gemma":0.00044633663,"teacher_disagreement_score":0.0019074943,"about_ca_system_score_codex":0.0006042617,"about_ca_system_score_gemma":0.0005006388,"threshold_uncertainty_score":0.010087907},"labels":[],"label_agreement":null},{"id":"W4402205433","doi":"10.1007/978-3-031-71112-1_14","title":"State Complexity of the Minimal Star Basis","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; State (computer science); Basis (linear algebra); Star (game theory); Theoretical computer science; Algorithm; Mathematics; Geometry","score_opus":0.02902338772168808,"score_gpt":0.25449557590671984,"score_spread":0.22547218818503176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402205433","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4676944,0.0011244775,0.3492663,0.004743351,0.00023883618,0.00015318822,0.0026920587,0.0007254884,0.1733619],"genre_scores_gemma":[0.93907714,0.00070887647,0.02977845,0.00031688757,0.00023054292,0.00015927384,0.001541382,0.00024800512,0.02793958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990663,0.00020332859,0.000054758297,0.00014364779,0.00033969202,0.00019231845],"domain_scores_gemma":[0.99613476,0.0027142717,0.00015843428,0.00048391463,0.0003538056,0.00015493724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008557127,0.0004503218,0.0010893283,0.00089013815,0.0011678927,0.0037747212,0.0013474007,0.0010691972,0.016540458],"category_scores_gemma":[0.004731833,0.0005010627,0.0011891475,0.0016171634,0.001751391,0.0058808564,0.0019927248,0.0030938175,0.0015034891],"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":[0.00010453185,0.000042187145,0.00022760742,0.00007674315,0.000011770538,0.000028967519,0.00013600227,0.008364818,0.00091100944,0.9757027,0.003053185,0.011340513],"study_design_scores_gemma":[0.000010579988,0.000011188792,0.000089896115,0.0000068691115,0.0000067741958,0.000017604303,0.000021824184,0.021953613,0.00046238693,0.97646683,0.00094556145,0.0000069555326],"about_ca_topic_score_codex":0.0018595603,"about_ca_topic_score_gemma":0.0016888268,"teacher_disagreement_score":0.016540458,"about_ca_system_score_codex":0.00171606,"about_ca_system_score_gemma":0.0014680059,"threshold_uncertainty_score":0.055333376},"labels":[],"label_agreement":null},{"id":"W4402205987","doi":"10.1016/j.matcom.2024.08.034","title":"An asymptotically optimal algorithm for generating bin cardinalities","year":2024,"lang":"en","type":"article","venue":"Mathematics and Computers in Simulation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; London Mathematical Society","keywords":"Bin; Algorithm; Quadratic equation; Asymptotically optimal algorithm; Block (permutation group theory); Mathematics; Combinatorics; Running time; Computer science; Discrete mathematics; Geometry","score_opus":0.02082205146525806,"score_gpt":0.2988153315810264,"score_spread":0.27799328011576835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402205987","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022424817,0.0002638907,0.96490365,0.00064605,0.00012313158,0.0002351762,0.0006465493,0.0032543126,0.0075024455],"genre_scores_gemma":[0.17633311,0.00018397602,0.81437325,0.000295402,0.000088297245,0.00053451967,0.0015326708,0.00059796404,0.006060776],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99689484,0.00087237125,0.00023783254,0.00053481304,0.0011036596,0.00035653796],"domain_scores_gemma":[0.9916278,0.004512347,0.00029627862,0.00212933,0.0010988588,0.00033535805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024811896,0.0010696138,0.0015580701,0.0027161646,0.0015175209,0.0028599764,0.0026499373,0.0016899494,0.0106683625],"category_scores_gemma":[0.016694611,0.0009523414,0.0012133626,0.0036546078,0.0014640731,0.004217446,0.0050195465,0.003010857,0.0031990132],"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":[0.0017379173,0.0004489636,0.0024752757,0.0003455755,0.000112672635,0.00010656221,0.00043541507,0.10379526,0.012509595,0.22312927,0.023209449,0.631694],"study_design_scores_gemma":[0.00025545424,0.00010504277,0.0005642638,0.00006633082,0.00004926304,0.00018482849,0.0001207401,0.6539745,0.007750171,0.33037627,0.0065072128,0.00004597442],"about_ca_topic_score_codex":0.0031120765,"about_ca_topic_score_gemma":0.00578788,"teacher_disagreement_score":0.0106683625,"about_ca_system_score_codex":0.002747366,"about_ca_system_score_gemma":0.0045914594,"threshold_uncertainty_score":0.035689235},"labels":[],"label_agreement":null},{"id":"W4402310150","doi":"10.1103/physreve.110.034305","title":"Network compression with configuration models and the minimum description length","year":2024,"lang":"en","type":"article","venue":"Physical review. E","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Minimum description length; Computer science; Compression (physics); Algorithm; Physics","score_opus":0.028655374773177773,"score_gpt":0.2913401408968319,"score_spread":0.26268476612365416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402310150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1024048,0.001500788,0.8901298,0.0015215476,0.000060772752,0.00012295897,0.00094039686,0.0007163243,0.0026026093],"genre_scores_gemma":[0.77324414,0.0013316934,0.21994777,0.00043776687,0.00014538894,0.00058542483,0.0024733027,0.00033257809,0.0015019389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777406,0.0011680971,0.00014224435,0.00029846377,0.00048179555,0.00013527548],"domain_scores_gemma":[0.9750302,0.019418092,0.0017052497,0.0025841366,0.00092245825,0.00033988993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005846642,0.0008060126,0.0012336569,0.0032101383,0.0008543354,0.0020937847,0.0024805027,0.0019303609,0.0015750141],"category_scores_gemma":[0.037233226,0.0005966349,0.00130765,0.002758765,0.0017357077,0.0054962994,0.0021190513,0.002122964,0.0003961552],"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":[0.000145618,0.00005281555,0.0054941354,0.00017431285,0.00011796611,0.00023366336,0.00018284406,0.84600973,0.0010914884,0.10920779,0.0027831441,0.0345064],"study_design_scores_gemma":[0.0000103202,0.000024399124,0.00038827167,0.000021389806,0.000009293439,0.00007165039,0.000021105152,0.9073775,0.00045623648,0.091149405,0.00045620077,0.000014266059],"about_ca_topic_score_codex":0.0028670821,"about_ca_topic_score_gemma":0.0023240226,"teacher_disagreement_score":0.005846642,"about_ca_system_score_codex":0.002269337,"about_ca_system_score_gemma":0.001354301,"threshold_uncertainty_score":0.030920327},"labels":[],"label_agreement":null},{"id":"W4402322653","doi":"10.22541/au.172559703.36231063/v1","title":"Parsing Millions of DNS Records per Second","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","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":"Université TÉLUQ","funders":"","keywords":"Parsing; Computer science; Natural language processing; Artificial intelligence","score_opus":0.024412233614441323,"score_gpt":0.2758149636939008,"score_spread":0.25140273007945946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402322653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2482833,0.001967461,0.43565035,0.0031488745,0.0018959128,0.0006502617,0.04056703,0.23448935,0.033347487],"genre_scores_gemma":[0.49828795,0.0010957107,0.39785078,0.0006921381,0.0003979999,0.00045407866,0.07215073,0.004593539,0.024477134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972072,0.00024620292,0.00026729843,0.00068857404,0.0013513401,0.00023920657],"domain_scores_gemma":[0.9957445,0.0010257574,0.00020627874,0.0016541053,0.0012292841,0.0001399779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001192054,0.0010854226,0.0008435485,0.0032297831,0.00083236536,0.0020376162,0.0013852556,0.0009097921,0.010930876],"category_scores_gemma":[0.008927384,0.00071496767,0.0004975164,0.0042324113,0.0004933357,0.0022487307,0.0015746938,0.00090634456,0.0077808714],"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":[0.0010094518,0.00028343155,0.013073897,0.00043215102,0.00020399396,0.0006229473,0.0005620504,0.02380084,0.04848154,0.020092042,0.19405766,0.69738],"study_design_scores_gemma":[0.00019601281,0.00020027037,0.017800074,0.0001297757,0.0001270008,0.001461408,0.0009782535,0.5344281,0.16666874,0.037183583,0.24065535,0.0001714448],"about_ca_topic_score_codex":0.0055712853,"about_ca_topic_score_gemma":0.0042405864,"teacher_disagreement_score":0.010930876,"about_ca_system_score_codex":0.00092784764,"about_ca_system_score_gemma":0.0015679081,"threshold_uncertainty_score":0.03656739},"labels":[],"label_agreement":null},{"id":"W4402324748","doi":"10.21203/rs.3.rs-4735292/v1","title":"Understanding is Compression","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Compression (physics); Computer science; Materials science; Composite material","score_opus":0.3424040391933133,"score_gpt":0.445944742894267,"score_spread":0.1035407037009537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402324748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024772892,0.027957872,0.59587604,0.048048697,0.0029848814,0.00013082076,0.00067471666,0.0008212026,0.29873282],"genre_scores_gemma":[0.6902511,0.039630715,0.15677483,0.007278166,0.0107335495,0.00036044364,0.0015896756,0.0007236559,0.09265774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816495,0.00054133043,0.00008841478,0.0002948509,0.0007917975,0.00011865861],"domain_scores_gemma":[0.99512297,0.0026313118,0.0002295781,0.0011103181,0.0008076403,0.00009818218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015121836,0.0008291431,0.00070467754,0.0032913147,0.0009742555,0.0054731537,0.0010939019,0.0024112575,0.01413492],"category_scores_gemma":[0.008910747,0.00036515685,0.00046261086,0.0035993117,0.005844553,0.019436045,0.0019646138,0.0031518107,0.003037126],"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":[0.0000134789525,0.000012078779,0.00011821981,0.000094990115,0.0000066673942,0.000024767862,0.00020133932,0.0011619794,0.00040385526,0.94881034,0.006024615,0.043127593],"study_design_scores_gemma":[0.000003556975,0.000008571251,0.00012036002,0.000052597694,0.0000051595093,0.0001148665,0.0001194433,0.0052524437,0.0008715225,0.95550185,0.037942786,0.000006899941],"about_ca_topic_score_codex":0.0008487829,"about_ca_topic_score_gemma":0.00034429884,"teacher_disagreement_score":0.01413492,"about_ca_system_score_codex":0.0012090085,"about_ca_system_score_gemma":0.00082235935,"threshold_uncertainty_score":0.047285974},"labels":[],"label_agreement":null},{"id":"W4402391085","doi":"10.23889/ijpds.v9i5.2801","title":"Using Polars to Improve String Similarity Performance in Python","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Algorithms and Data Compression","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":"University of Guelph","funders":"","keywords":"Python (programming language); Computer science; String (physics); Similarity (geometry); Programming language; Physics; Artificial intelligence; Theoretical physics","score_opus":0.10142318949889507,"score_gpt":0.41633512492248737,"score_spread":0.3149119354235923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402391085","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012819659,0.00034482047,0.2853724,0.0004996428,0.00044622913,0.00025640576,0.015206306,0.67516285,0.009891641],"genre_scores_gemma":[0.11276769,0.0006123392,0.6377954,0.0010058833,0.00023037374,0.0013072334,0.07865972,0.15176782,0.015853653],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9925391,0.0010213004,0.00095040514,0.0013336482,0.003550568,0.0006049765],"domain_scores_gemma":[0.99367887,0.0016275478,0.00056775636,0.0018154555,0.001914187,0.00039619382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050023175,0.0025946838,0.0014703318,0.0029968512,0.0018201191,0.0051641264,0.005328964,0.0008902933,0.040328335],"category_scores_gemma":[0.024285128,0.0015713958,0.0031249153,0.006007712,0.0014454143,0.00840081,0.0071363533,0.0032382463,0.031276226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019140556,0.00045680415,0.014703673,0.0025974861,0.0005576542,0.0005247522,0.0014779381,0.02526682,0.014044112,0.034910228,0.4652791,0.43826747],"study_design_scores_gemma":[0.0005630521,0.00044230346,0.007939671,0.00043213452,0.0001812919,0.0006364257,0.00060525286,0.38383237,0.08427584,0.08982948,0.43076468,0.0004975178],"about_ca_topic_score_codex":0.0065342425,"about_ca_topic_score_gemma":0.005043691,"teacher_disagreement_score":0.040328335,"about_ca_system_score_codex":0.0019758285,"about_ca_system_score_gemma":0.0047024144,"threshold_uncertainty_score":0.13491166},"labels":[],"label_agreement":null},{"id":"W4402467995","doi":"10.1016/j.isci.2024.110933","title":"Building a pangenome alignment index via recursive prefix-free parsing","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; Directorate for Biological Sciences; National Science Foundation; National Institutes of Health; Seattle Children’s Hospital; Seattle Children's Research Institute","keywords":"Prefix; Index (typography); Parsing; Computer science; Natural language processing; Linguistics; Programming language; Philosophy","score_opus":0.017559461771339175,"score_gpt":0.26910872125666524,"score_spread":0.2515492594853261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402467995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015553339,0.00039835722,0.9583086,0.00019408735,0.00011340184,0.00015373486,0.0027700579,0.01972238,0.0027859933],"genre_scores_gemma":[0.04199411,0.00027814903,0.94181514,0.00013445845,0.00006176326,0.00027894464,0.01191275,0.0015937098,0.0019310733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884737,0.00013305363,0.00019814498,0.00034812774,0.0003589869,0.00011427009],"domain_scores_gemma":[0.99787843,0.00056543946,0.00013596365,0.00067080266,0.00066168606,0.00008771979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011796318,0.0009505035,0.0011819381,0.004120539,0.0010365902,0.0021618796,0.0019590652,0.0010054441,0.0048422744],"category_scores_gemma":[0.0062234304,0.00077748456,0.0010279558,0.006481747,0.0006471314,0.0039406875,0.003001592,0.0016539444,0.004350504],"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":[0.000442783,0.00017584713,0.0037336973,0.0004330892,0.00011727347,0.00038254666,0.000529997,0.02637286,0.060303994,0.03712685,0.03316154,0.83721954],"study_design_scores_gemma":[0.00014765981,0.0002852599,0.0037105393,0.00012580966,0.00015758966,0.0008989645,0.00036739153,0.65449965,0.12224692,0.10519856,0.11216855,0.00019311659],"about_ca_topic_score_codex":0.0022698434,"about_ca_topic_score_gemma":0.003981665,"teacher_disagreement_score":0.0048422744,"about_ca_system_score_codex":0.00077734416,"about_ca_system_score_gemma":0.0023053796,"threshold_uncertainty_score":0.016199052},"labels":[],"label_agreement":null},{"id":"W4402586402","doi":"10.1007/978-3-031-72200-4_10","title":"Simultaneously Building and Reconciling a Synteny Tree","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Tree (set theory); Synteny; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.014818269479631068,"score_gpt":0.2471356584624695,"score_spread":0.2323173889828384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402586402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23909414,0.0011678566,0.74429464,0.0009888004,0.00015171073,0.00022583995,0.0027669303,0.0067524062,0.0045576156],"genre_scores_gemma":[0.47167903,0.00022359414,0.5162429,0.00034381333,0.000059585673,0.0001364618,0.0081167035,0.00090919505,0.00228869],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826044,0.0005584693,0.000099963785,0.00055348634,0.0003772662,0.00015043624],"domain_scores_gemma":[0.99595165,0.0020857172,0.0002472106,0.000996887,0.00057677896,0.00014178765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002726625,0.001165873,0.0016215267,0.0027459892,0.0013393468,0.0016030198,0.0020679613,0.0016989473,0.0039208787],"category_scores_gemma":[0.0077173356,0.00083841383,0.0017979754,0.002240188,0.0010222952,0.0035175052,0.0024706023,0.0013432192,0.0011604306],"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":[0.001222652,0.0003064911,0.015024911,0.0007709251,0.00053977995,0.0013692713,0.0009758379,0.43317783,0.019699031,0.034116365,0.015809406,0.47698748],"study_design_scores_gemma":[0.00006731332,0.00016257705,0.0018913142,0.00005793492,0.000121568024,0.00032891118,0.00022767588,0.9167761,0.009331943,0.063412115,0.00758271,0.000039845327],"about_ca_topic_score_codex":0.0013662396,"about_ca_topic_score_gemma":0.0023444614,"teacher_disagreement_score":0.0039208787,"about_ca_system_score_codex":0.00065075076,"about_ca_system_score_gemma":0.0013002651,"threshold_uncertainty_score":0.014419973},"labels":[],"label_agreement":null},{"id":"W4402586538","doi":"10.1007/978-3-031-72200-4_14","title":"Another Virtue of Wavelet Forests","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Wavelet; Virtue; Artificial intelligence; Epistemology; Philosophy","score_opus":0.013386263150824718,"score_gpt":0.24323989722368372,"score_spread":0.229853634072859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402586538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010609404,0.0037756027,0.81974727,0.0057378435,0.0019559837,0.00002706812,0.0002288317,0.0008312016,0.15708685],"genre_scores_gemma":[0.3511296,0.007020615,0.5051805,0.0048197987,0.005028693,0.00014973982,0.00059471227,0.0016559503,0.12442047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99924064,0.0001638483,0.00003743137,0.00017628435,0.00032266,0.00005913025],"domain_scores_gemma":[0.9979081,0.00088830583,0.00009919189,0.0006865533,0.00030533157,0.00011251905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001020602,0.00038519452,0.0005368796,0.0007687247,0.00089234556,0.0022554575,0.00070527924,0.0011377198,0.007590778],"category_scores_gemma":[0.005165653,0.00035719207,0.00041163125,0.0011214451,0.0025464138,0.0038544757,0.0017271865,0.0028356817,0.004069832],"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":[0.000034698463,0.000014998558,0.00018556416,0.00006777303,0.000012195882,0.000045872483,0.000075122145,0.0010628281,0.0036916814,0.902616,0.011280171,0.080913186],"study_design_scores_gemma":[0.000016631466,0.00002281603,0.0003011103,0.000033239736,0.000014072859,0.0005774449,0.000041080606,0.007180003,0.0029606582,0.88034946,0.108489096,0.000014494855],"about_ca_topic_score_codex":0.00035124432,"about_ca_topic_score_gemma":0.00049907813,"teacher_disagreement_score":0.007590778,"about_ca_system_score_codex":0.0001888974,"about_ca_system_score_gemma":0.00046859376,"threshold_uncertainty_score":0.025393665},"labels":[],"label_agreement":null},{"id":"W4402916713","doi":"10.1109/icip51287.2024.10648249","title":"Learned Compression of Encoding Distributions","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Encoding (memory); Computer science; Compression (physics); Data compression; Artificial intelligence; Materials science","score_opus":0.0297064461025144,"score_gpt":0.2981554495130548,"score_spread":0.2684490034105404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402916713","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037775554,0.00032650187,0.95590353,0.00034645956,0.00010447028,0.000077182085,0.0003626733,0.0022443368,0.0028592336],"genre_scores_gemma":[0.5811313,0.00061814033,0.40598613,0.0003943263,0.0001691084,0.0002791319,0.001792787,0.0006701124,0.008958983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993649,0.00013108668,0.000038975006,0.0001425936,0.0002504279,0.00007204115],"domain_scores_gemma":[0.99820244,0.00062445324,0.000101139136,0.0006565975,0.0003621683,0.00005312506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075818907,0.0009935838,0.0006017582,0.0006902566,0.00029819176,0.0008423538,0.0010653808,0.0007462753,0.0040357616],"category_scores_gemma":[0.0061275074,0.00031641757,0.00043149164,0.00090599887,0.0007179364,0.0022075977,0.0014372214,0.0015620979,0.0014374098],"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":[0.0005425159,0.00018391703,0.0018026542,0.00016014319,0.00005927311,0.00030428075,0.00023270684,0.29953757,0.04436433,0.050316196,0.009333765,0.59316266],"study_design_scores_gemma":[0.000024245219,0.000059676942,0.00031868537,0.0000210868,0.000011484119,0.00018105302,0.000027363165,0.95028687,0.027305081,0.018642059,0.0031046283,0.000017749127],"about_ca_topic_score_codex":0.0015309448,"about_ca_topic_score_gemma":0.0019418935,"teacher_disagreement_score":0.0040357616,"about_ca_system_score_codex":0.0007880376,"about_ca_system_score_gemma":0.0009074589,"threshold_uncertainty_score":0.0135009885},"labels":[],"label_agreement":null},{"id":"W4403210527","doi":"10.1109/cibcb58642.2024.10702154","title":"Driving Evolution Towards Discovery of Patterns in Sets of Weakly-Conserved DNA Sequences","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Brock University; University of Guelph","funders":"","keywords":"Evolutionary biology; Computational biology; Computer science; DNA; Biology; Genetics","score_opus":0.01638325990382289,"score_gpt":0.2645488632226152,"score_spread":0.24816560331879234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403210527","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55030936,0.00015131911,0.44600773,0.00035541158,0.00003077443,0.00017689915,0.00010029281,0.0007823094,0.0020859565],"genre_scores_gemma":[0.63306606,0.00009064853,0.36463678,0.00015823501,0.000012715092,0.00022210872,0.00028573227,0.00009103595,0.0014367952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916196,0.00022579075,0.00006303678,0.0002597666,0.00020687185,0.00008258353],"domain_scores_gemma":[0.99671376,0.0020137632,0.00028694578,0.00032604614,0.00053836673,0.000121100005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018850501,0.00050880405,0.0007060102,0.0011541623,0.0005524989,0.0009918239,0.0011870933,0.00097384665,0.00093806064],"category_scores_gemma":[0.0073603014,0.00049623597,0.0007327833,0.0006572188,0.0009860867,0.0011251721,0.00092891307,0.000950956,0.00029204728],"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":[0.00044001522,0.00066653016,0.051196646,0.00047207237,0.0003145991,0.00069635035,0.0013713972,0.47799277,0.13787882,0.041292414,0.0013734677,0.28630483],"study_design_scores_gemma":[0.000027891996,0.0001263209,0.0014339534,0.000016462856,0.00003019159,0.00012598427,0.000096818025,0.97339654,0.013660552,0.01012104,0.0009508926,0.00001334602],"about_ca_topic_score_codex":0.0014510667,"about_ca_topic_score_gemma":0.0018463728,"teacher_disagreement_score":0.0018850501,"about_ca_system_score_codex":0.0007005245,"about_ca_system_score_gemma":0.0010162174,"threshold_uncertainty_score":0.0099692345},"labels":[],"label_agreement":null},{"id":"W4403248961","doi":"10.1016/j.dam.2024.09.034","title":"Sequence saturation","year":2024,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Science and Technology, Taiwan","keywords":"Mathematics; Sequence (biology); Combinatorics; Saturation (graph theory); Algorithm; Chemistry","score_opus":0.023562439140389378,"score_gpt":0.2774487977528039,"score_spread":0.25388635861241454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403248961","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049025763,0.0010550162,0.40293658,0.0037354697,0.0012278276,0.00026534343,0.0010239043,0.0018350609,0.5388951],"genre_scores_gemma":[0.65221554,0.0015854776,0.06785961,0.0023274184,0.0008850344,0.00046331485,0.002003941,0.0015287437,0.27113086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985983,0.0002788615,0.000073291936,0.00037118877,0.00041959475,0.0002586799],"domain_scores_gemma":[0.9964684,0.001472257,0.00012036977,0.0006085827,0.0010054667,0.00032493856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010095302,0.0009959637,0.000957164,0.0019033862,0.0021117567,0.0022833277,0.0009991479,0.0013519942,0.046375677],"category_scores_gemma":[0.0071314764,0.0005020603,0.0010302186,0.0012711649,0.0024512585,0.0059070326,0.003990085,0.0032441267,0.01004983],"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":[0.00008303984,0.00002445389,0.00009364957,0.00007875449,0.000007546755,0.00008362292,0.00019191157,0.0006929705,0.0022758495,0.9763049,0.005485904,0.014677373],"study_design_scores_gemma":[0.00001647402,0.000029431709,0.00006771872,0.000024952249,0.000006706213,0.00016773657,0.00010250442,0.0051538628,0.0041053,0.9664397,0.02387424,0.00001128429],"about_ca_topic_score_codex":0.00089837576,"about_ca_topic_score_gemma":0.000562188,"teacher_disagreement_score":0.046375677,"about_ca_system_score_codex":0.0016673313,"about_ca_system_score_gemma":0.0014146159,"threshold_uncertainty_score":0.15514207},"labels":[],"label_agreement":null},{"id":"W4403305692","doi":"10.1017/9781009302180.036","title":"Key Concepts Summary: Greedy Algorithms and Dynamic Programming","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Algorithms and Data Compression","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":"York University","funders":"","keywords":"Key (lock); Computer science; Greedy algorithm; Dynamic programming; Algorithm; Theoretical computer science; Computer security","score_opus":0.015546342703395487,"score_gpt":0.2245591922269321,"score_spread":0.2090128495235366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403305692","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014698162,0.038050815,0.40877098,0.013209796,0.00983997,0.00035449982,0.0029829436,0.0048601227,0.52046096],"genre_scores_gemma":[0.017905409,0.034693085,0.23753391,0.0074191536,0.005507609,0.0008017509,0.0058708643,0.0040462515,0.68622184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947673,0.000068362264,0.000032134267,0.00012156061,0.00026478607,0.000036443464],"domain_scores_gemma":[0.99928904,0.0003064065,0.000033300843,0.00006915749,0.0002513537,0.000050699968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054248737,0.001538577,0.00080855266,0.0011355673,0.0005273804,0.0030390846,0.0011991063,0.0012963007,0.086832784],"category_scores_gemma":[0.0031992777,0.00046615902,0.000663685,0.0022238132,0.00087402615,0.0038146318,0.0010851383,0.0029634687,0.07290637],"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":[0.000028626959,0.0000463276,0.000073455114,0.0005700926,0.000012064089,0.000048255068,0.00011156751,0.0030675759,0.00070523197,0.1209495,0.6381503,0.23623694],"study_design_scores_gemma":[0.000010557528,0.000026642761,0.00023091726,0.00028698516,0.000008256069,0.00019830123,0.000043147633,0.0033171843,0.0004845196,0.095288575,0.90008825,0.00001675267],"about_ca_topic_score_codex":0.00095524895,"about_ca_topic_score_gemma":0.0011499872,"teacher_disagreement_score":0.086832784,"about_ca_system_score_codex":0.0011882331,"about_ca_system_score_gemma":0.0012040443,"threshold_uncertainty_score":0.2904846},"labels":[],"label_agreement":null},{"id":"W4403427149","doi":"10.1016/j.ic.2024.105230","title":"Perspective on complexity measures targeting read-once branching programs","year":2024,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Perspective (graphical); Branching (polymer chemistry); Computer science; Psychology; Artificial intelligence; Chemistry","score_opus":0.03311892894640224,"score_gpt":0.29883273690946316,"score_spread":0.26571380796306093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403427149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020310469,0.0070343073,0.897003,0.014453137,0.0007904424,0.000065520755,0.0002363229,0.0005456078,0.05956117],"genre_scores_gemma":[0.62044245,0.011512035,0.3229016,0.0044187,0.006238308,0.00041532514,0.00050869957,0.0010728894,0.032489963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99557036,0.0013280461,0.00018158548,0.0006692613,0.0018971141,0.00035367897],"domain_scores_gemma":[0.97682536,0.01547542,0.0011088854,0.0034059677,0.0024269314,0.0007573098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004078967,0.0015275525,0.0019114383,0.0034577241,0.0015849672,0.0061220294,0.003443881,0.0041164453,0.008281402],"category_scores_gemma":[0.019113837,0.0007455489,0.0012415532,0.0037838486,0.0061254455,0.018357566,0.0031443331,0.008233917,0.0015985933],"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":[0.00001416841,0.000022007316,0.00007376215,0.000041246567,0.0000049277173,0.000013710444,0.000033965633,0.0035864154,0.00041473587,0.98737633,0.0011214032,0.007297409],"study_design_scores_gemma":[0.000005199689,0.000023206983,0.00008123635,0.000027591635,0.0000065318677,0.000038992206,0.000024080455,0.020549903,0.0008849737,0.97390443,0.004442166,0.000011644569],"about_ca_topic_score_codex":0.0011300488,"about_ca_topic_score_gemma":0.0007381053,"teacher_disagreement_score":0.008281402,"about_ca_system_score_codex":0.0044541527,"about_ca_system_score_gemma":0.0015524043,"threshold_uncertainty_score":0.03231728},"labels":[],"label_agreement":null},{"id":"W4403582486","doi":"10.1145/3627673.3679729","title":"No Query Left Behind: Query Refinement via Backtranslation","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Windsor","funders":"","keywords":"Query optimization; Computer science; Sargable; Query expansion; RDF query language; Web search query; Query language; Information retrieval; Query by Example; Web query classification; Database; Search engine","score_opus":0.01025811830274832,"score_gpt":0.24443556918386,"score_spread":0.2341774508811117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403582486","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.405568,0.0032620912,0.46404478,0.002109784,0.00061319687,0.0034460186,0.01436228,0.09523638,0.011357464],"genre_scores_gemma":[0.5030676,0.00054116844,0.4367123,0.0017549298,0.00019468578,0.0012785785,0.047110956,0.0036669795,0.005672754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98381084,0.0070980196,0.0017583078,0.003516904,0.0031368402,0.0006790492],"domain_scores_gemma":[0.9718677,0.010488234,0.0013319569,0.011271102,0.004605656,0.0004353154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008173641,0.0023781836,0.0018250507,0.0027423513,0.0012769136,0.0022081838,0.0030760453,0.0015435324,0.0029196467],"category_scores_gemma":[0.038131446,0.00072882685,0.0022190697,0.0032028062,0.0018730272,0.0062268963,0.0045383475,0.002688024,0.0037696823],"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":[0.0039287577,0.0018506035,0.023546897,0.0032800948,0.0006564918,0.0015100744,0.007680776,0.044639897,0.1810869,0.010079809,0.071522005,0.6502178],"study_design_scores_gemma":[0.0012206023,0.003101386,0.01860969,0.00025072196,0.0006211974,0.003516483,0.003546599,0.62972534,0.18388747,0.027846308,0.12698373,0.00069044577],"about_ca_topic_score_codex":0.008777395,"about_ca_topic_score_gemma":0.009267142,"teacher_disagreement_score":0.008777395,"about_ca_system_score_codex":0.0011705585,"about_ca_system_score_gemma":0.0024012455,"threshold_uncertainty_score":0.043226898},"labels":[],"label_agreement":null},{"id":"W4404492911","doi":"10.21203/rs.3.rs-5367343/v1","title":"b-move: Faster Lossless Approximate Pattern Matching in a Run-Length Compressed Index","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Lossless compression; Index (typography); Computer science; Matching (statistics); Algorithm; Mathematics; Data compression; Statistics; World Wide Web","score_opus":0.05159588203190445,"score_gpt":0.3708995698269282,"score_spread":0.3193036877950237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404492911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07022029,0.0021249305,0.89658433,0.00082934514,0.00058505824,0.00036692523,0.0014472882,0.01928804,0.008553819],"genre_scores_gemma":[0.259731,0.0005429863,0.7211235,0.0005575548,0.00025845264,0.00040537977,0.0026083183,0.0011661273,0.013606611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831545,0.000190809,0.00010545778,0.00024292665,0.001003768,0.00014170975],"domain_scores_gemma":[0.99812657,0.0005683344,0.00013723216,0.0008047795,0.0002666172,0.00009647804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008238903,0.0009127537,0.0013348853,0.0020338392,0.00076028437,0.0018854558,0.0023245069,0.0012812152,0.010090486],"category_scores_gemma":[0.004762298,0.00045532177,0.0005470302,0.0037484074,0.00080315664,0.0038098723,0.0028386968,0.0013212495,0.0038163916],"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":[0.0024011955,0.000405582,0.001215546,0.00034465804,0.00011467435,0.00026159582,0.00024560923,0.020944742,0.04916499,0.021369103,0.0370169,0.8665154],"study_design_scores_gemma":[0.0006434669,0.0007815898,0.0012133076,0.00009418134,0.000103010134,0.0008240368,0.00023984266,0.8258129,0.0992273,0.041256707,0.02972167,0.00008197551],"about_ca_topic_score_codex":0.004325115,"about_ca_topic_score_gemma":0.0060260743,"teacher_disagreement_score":0.010090486,"about_ca_system_score_codex":0.0010025444,"about_ca_system_score_gemma":0.0017548433,"threshold_uncertainty_score":0.033756077},"labels":[],"label_agreement":null},{"id":"W4404770452","doi":"10.1016/j.isci.2024.111464","title":"Movi: A fast and cache-efficient full-text pangenome index","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University; National Institutes of Health; National Science Foundation; National Human Genome Research Institute; National Institute of Health Sciences","keywords":"Index (typography); Cache; Computer science; Parallel computing; World Wide Web","score_opus":0.013272116085123664,"score_gpt":0.2465614735406449,"score_spread":0.23328935745552123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404770452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08985977,0.0050011245,0.6916055,0.000861854,0.0006734683,0.0006034522,0.017371316,0.1811036,0.012919805],"genre_scores_gemma":[0.22819649,0.0014133359,0.6982527,0.0005387469,0.00035329763,0.00082310394,0.05151744,0.0055013,0.013403637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993444,0.00004764066,0.000057089517,0.00015526489,0.00031130918,0.00008426838],"domain_scores_gemma":[0.99914,0.00022552023,0.000088981855,0.00023276136,0.00022222236,0.00009049265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006198496,0.0010443854,0.0010065146,0.00219445,0.000746462,0.0014389347,0.0029215824,0.0007953228,0.0063218665],"category_scores_gemma":[0.0028152422,0.00057033065,0.0006734081,0.0035562092,0.00048662472,0.0027889144,0.0022893036,0.0009476683,0.0034384811],"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":[0.0018807035,0.00023555821,0.0033022962,0.00072399585,0.00016223203,0.00034284111,0.0003344428,0.012033623,0.12908886,0.012163325,0.11243016,0.72730213],"study_design_scores_gemma":[0.00072048174,0.0009831804,0.006003599,0.00011441576,0.00017244216,0.0010831897,0.0002951476,0.5364033,0.27239877,0.020122,0.16137739,0.00032616858],"about_ca_topic_score_codex":0.0033550444,"about_ca_topic_score_gemma":0.004610038,"teacher_disagreement_score":0.0063218665,"about_ca_system_score_codex":0.00091522915,"about_ca_system_score_gemma":0.0014051803,"threshold_uncertainty_score":0.0211488},"labels":[],"label_agreement":null},{"id":"W4404781191","doi":"10.18653/v1/2024.findings-emnlp.677","title":"A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Automatic summarization; Decoding methods; Computer science; Algorithm; List decoding; Directed acyclic graph; Transformer; Artificial intelligence; Concatenated error correction code; Block code; Voltage; Engineering; Electrical engineering","score_opus":0.010836186859907922,"score_gpt":0.2540388349982392,"score_spread":0.24320264813833128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404781191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051036966,0.00031190104,0.9899524,0.00013792931,0.00006713752,0.00009541546,0.00056600006,0.0029122867,0.00085330626],"genre_scores_gemma":[0.103059135,0.00046705545,0.8862307,0.00021529848,0.00012853742,0.0002279981,0.004294905,0.0006443472,0.004732063],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990932,0.00020787945,0.00010943628,0.00025251356,0.0002667306,0.00007016771],"domain_scores_gemma":[0.9978835,0.00095831475,0.00015498322,0.00028915465,0.000644206,0.00006989412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091069145,0.001257316,0.0009906844,0.0027963358,0.0006910418,0.0010151279,0.0012441949,0.0010473935,0.0037230453],"category_scores_gemma":[0.0055502225,0.00039179818,0.0007717913,0.0027461865,0.0006501758,0.0019735731,0.0010607404,0.0015402179,0.002731641],"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":[0.00026994865,0.00008426907,0.0006554816,0.00026250625,0.000056851793,0.00020347898,0.00022154482,0.054148424,0.027871918,0.021176334,0.015957022,0.8790923],"study_design_scores_gemma":[0.000105401305,0.0002015378,0.00045032747,0.000045775876,0.00007291868,0.00040118705,0.00013932968,0.90131664,0.032323737,0.04905404,0.015831305,0.000057863643],"about_ca_topic_score_codex":0.0033621101,"about_ca_topic_score_gemma":0.0051531703,"teacher_disagreement_score":0.0037230453,"about_ca_system_score_codex":0.00077132956,"about_ca_system_score_gemma":0.0018401046,"threshold_uncertainty_score":0.012454867},"labels":[],"label_agreement":null},{"id":"W4404818373","doi":"10.1007/978-981-96-0579-8_20","title":"Enhancing RAG’s Retrieval via Query Backtranslations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Information retrieval; Query expansion; Query optimization; Database","score_opus":0.01386813357093654,"score_gpt":0.2496014352438606,"score_spread":0.23573330167292406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404818373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12622517,0.0069109797,0.752584,0.0022798253,0.0017230375,0.0006331746,0.0036321536,0.06159307,0.044418674],"genre_scores_gemma":[0.4675839,0.0023892985,0.46986407,0.0015331183,0.0012606276,0.00018841875,0.0093080485,0.0039493307,0.043923203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857247,0.0003741724,0.00010880464,0.00021054265,0.0005602805,0.00017372395],"domain_scores_gemma":[0.99745065,0.0008748815,0.00009328523,0.0009452758,0.000576487,0.000059402333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010415799,0.0012604989,0.0013434445,0.0024315685,0.00071864587,0.0024321896,0.0013709592,0.001288677,0.020847771],"category_scores_gemma":[0.004780991,0.0003709778,0.0009361454,0.002415866,0.0009392939,0.0035272161,0.0019078727,0.0009490539,0.015383092],"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":[0.0012404581,0.0004142512,0.00072977593,0.00077251764,0.00012272468,0.0006851539,0.0004915771,0.010718806,0.153775,0.017774329,0.07828082,0.7349946],"study_design_scores_gemma":[0.00028343376,0.00082085293,0.0017265714,0.00010948167,0.0003941994,0.0030695978,0.0007907768,0.46129504,0.31959403,0.03563466,0.17608102,0.00020043243],"about_ca_topic_score_codex":0.0026736902,"about_ca_topic_score_gemma":0.002777543,"teacher_disagreement_score":0.020847771,"about_ca_system_score_codex":0.00061122724,"about_ca_system_score_gemma":0.0007413663,"threshold_uncertainty_score":0.06974274},"labels":[],"label_agreement":null},{"id":"W4404868618","doi":"10.1101/2024.11.26.625346","title":"Brisk: Exact resource-efficient dictionary for <i>k</i> -mers","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"Canadian Nautical Research Society","funders":"","keywords":"Computer science; Resource (disambiguation); Computer network","score_opus":0.012919366249122594,"score_gpt":0.22504016480189531,"score_spread":0.21212079855277272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404868618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13954572,0.0032845337,0.77930164,0.00081275345,0.000942361,0.0004924182,0.0072640628,0.053938307,0.014418139],"genre_scores_gemma":[0.2742897,0.00092154724,0.6930357,0.0004490303,0.00019426766,0.0006148311,0.015062613,0.0031080102,0.012324346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936646,0.00006262457,0.00006859555,0.00012084147,0.00029940685,0.00008205148],"domain_scores_gemma":[0.9988017,0.00018628029,0.00012513163,0.00049463956,0.00027956892,0.00011268449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046713228,0.00062541885,0.0009859923,0.0010009058,0.00065396295,0.0011979064,0.0025063488,0.00070703664,0.0070926063],"category_scores_gemma":[0.0025930083,0.00037382983,0.0005152377,0.0018223822,0.00051435496,0.0022373258,0.0021385746,0.0008915747,0.006768312],"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":[0.0020918986,0.00050545915,0.0043835407,0.0015262424,0.00010937692,0.00049447967,0.00054188876,0.028861504,0.18849464,0.036590382,0.10698543,0.62941515],"study_design_scores_gemma":[0.0006798473,0.0018800764,0.0018583481,0.00021585728,0.0000881852,0.0011677747,0.00040768628,0.5408879,0.24637593,0.03796528,0.16815904,0.00031406316],"about_ca_topic_score_codex":0.0011010079,"about_ca_topic_score_gemma":0.0023731864,"teacher_disagreement_score":0.0070926063,"about_ca_system_score_codex":0.00045690656,"about_ca_system_score_gemma":0.0012513221,"threshold_uncertainty_score":0.023727119},"labels":[],"label_agreement":null},{"id":"W4405252251","doi":"10.1007/978-3-031-80311-6_8","title":"Isogeny Interpolation and the Computation of Isogenies from Higher Dimensional Representations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Isogeny; Computation; Computer science; Interpolation (computer graphics); Algebra over a field; Mathematics; Algorithm; Artificial intelligence; Pure mathematics; Elliptic curve","score_opus":0.015308444134003426,"score_gpt":0.26135148503467587,"score_spread":0.24604304090067244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405252251","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04802218,0.0020745501,0.92305046,0.00037071647,0.00041203387,0.000058711317,0.0002499896,0.0011401046,0.024621237],"genre_scores_gemma":[0.3788011,0.00270922,0.5911852,0.00025261028,0.00047224702,0.00012734343,0.0010138504,0.0013764126,0.024062127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993111,0.00018120775,0.00003948951,0.00010777648,0.00029373058,0.000066756125],"domain_scores_gemma":[0.99881303,0.0005003606,0.00007373717,0.00038951606,0.00017646689,0.000046946734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011535112,0.0007011099,0.001235432,0.0027619451,0.0007801731,0.0025959662,0.0012294832,0.00081815384,0.009281648],"category_scores_gemma":[0.0059243483,0.000410185,0.0009952281,0.003144169,0.0020715138,0.0039205714,0.0029575357,0.002423648,0.0026266912],"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":[0.00017182449,0.000042297856,0.00045506496,0.00019341808,0.000028482655,0.00014003819,0.00027330365,0.014142113,0.0036452182,0.72030866,0.005477504,0.255122],"study_design_scores_gemma":[0.000021347783,0.00005596068,0.00034964085,0.000045563615,0.000013536647,0.00018228403,0.00010201568,0.07334931,0.0042936956,0.90271324,0.01884676,0.00002658919],"about_ca_topic_score_codex":0.0005720082,"about_ca_topic_score_gemma":0.00074392435,"teacher_disagreement_score":0.009281648,"about_ca_system_score_codex":0.0006331297,"about_ca_system_score_gemma":0.00040314166,"threshold_uncertainty_score":0.031050146},"labels":[],"label_agreement":null},{"id":"W4405259879","doi":"10.1017/s095679682400011x","title":"An example of goal-directed, calculational proof","year":2024,"lang":"en","type":"article","venue":"Journal of Functional Programming","topic":"Algorithms and Data Compression","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":"Brock University","funders":"","keywords":"Computer science; Proof of concept; Programming language","score_opus":0.0351478444025809,"score_gpt":0.277750935814294,"score_spread":0.2426030914117131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405259879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009467951,0.0002515614,0.8872389,0.002955283,0.0002318164,0.00033003232,0.00047605348,0.004389029,0.094659336],"genre_scores_gemma":[0.24068274,0.0003608808,0.7372251,0.0007151098,0.000084575266,0.00033590663,0.0006994569,0.0010407222,0.018855514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979956,0.0008295538,0.00011592328,0.00018659132,0.0006851398,0.00018727394],"domain_scores_gemma":[0.9956519,0.0026988958,0.00009861808,0.00072668964,0.00066747144,0.00015643587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023947374,0.0005385369,0.0003595916,0.0014244628,0.0019827527,0.0025806134,0.0018513438,0.0010759255,0.017552724],"category_scores_gemma":[0.007314433,0.0004020371,0.0010757011,0.0012608531,0.0025736194,0.0026237334,0.0031196747,0.0016229299,0.0029107041],"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":[0.000043849694,0.00007877311,0.00018277329,0.00020619796,0.000015736454,0.00037119424,0.00041767696,0.004205899,0.0022562472,0.95571995,0.009646792,0.02685505],"study_design_scores_gemma":[0.00008464042,0.000034468307,0.00016462112,0.00009289277,0.000023774708,0.00024440073,0.00017340458,0.03702591,0.0057134307,0.8359526,0.12045786,0.000031938653],"about_ca_topic_score_codex":0.002911749,"about_ca_topic_score_gemma":0.0041323015,"teacher_disagreement_score":0.017552724,"about_ca_system_score_codex":0.001390899,"about_ca_system_score_gemma":0.001588551,"threshold_uncertainty_score":0.058719754},"labels":[],"label_agreement":null},{"id":"W4406308961","doi":"10.1016/j.laa.2025.01.010","title":"A low-complexity algorithm to search for Legendre pairs","year":2025,"lang":"en","type":"article","venue":"Linear Algebra and its Applications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Division of Electrical, Communications and Cyber Systems; National Science Foundation","keywords":"Mathematics; Legendre polynomials; Algorithm; Search algorithm; Combinatorics; Mathematical optimization; Mathematical analysis","score_opus":0.02699690164220393,"score_gpt":0.3060585453568677,"score_spread":0.2790616437146638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406308961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010912137,0.00037106982,0.9808977,0.00028463444,0.00019814978,0.0001385611,0.00019716955,0.002129555,0.004871117],"genre_scores_gemma":[0.07460713,0.00017695836,0.9184071,0.00022308234,0.00010588818,0.00021240956,0.0007773696,0.0003298374,0.0051602586],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891233,0.00023076858,0.000088905006,0.00021775549,0.00041982738,0.00013032494],"domain_scores_gemma":[0.9984478,0.00064768543,0.00009319006,0.00040729647,0.00032353128,0.00008053398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087089505,0.0012381049,0.001254199,0.0027880378,0.0011527939,0.001900164,0.0017510767,0.0012454926,0.013423025],"category_scores_gemma":[0.006467383,0.00057514594,0.00082686014,0.003008764,0.00097449817,0.003010787,0.0027508498,0.0018757632,0.006939437],"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":[0.00042853245,0.00020862705,0.0008003849,0.00027708162,0.0000823986,0.0001546619,0.00022299496,0.013896559,0.023131149,0.094594546,0.027980547,0.83822256],"study_design_scores_gemma":[0.00033249756,0.00043162322,0.00094350596,0.00011374018,0.000110449226,0.0012436399,0.00037421583,0.5694969,0.040157583,0.34588656,0.040728215,0.00018106219],"about_ca_topic_score_codex":0.0012816235,"about_ca_topic_score_gemma":0.002336195,"teacher_disagreement_score":0.013423025,"about_ca_system_score_codex":0.0006507899,"about_ca_system_score_gemma":0.0015887718,"threshold_uncertainty_score":0.04490447},"labels":[],"label_agreement":null},{"id":"W4406309980","doi":"10.1016/j.ipl.2025.106557","title":"String searching with mismatches using AVX2 and AVX-512 instructions","year":2025,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","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":"Sheridan College","funders":"","keywords":"Computer science; String (physics); Programming language; Parallel computing; Algorithm; Theoretical computer science; Arithmetic; Physics; Mathematics; Theoretical physics","score_opus":0.0071819911603793075,"score_gpt":0.22879901375158454,"score_spread":0.22161702259120522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406309980","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074817374,0.0006084787,0.9093702,0.00029184716,0.00016328575,0.0001559057,0.00047354464,0.0074313153,0.0066880626],"genre_scores_gemma":[0.2842892,0.00018353322,0.70598763,0.00026020818,0.000049959275,0.00019775111,0.0020388495,0.00042986058,0.006562957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749494,0.00027631002,0.00038822522,0.0004944908,0.0011595871,0.00018646783],"domain_scores_gemma":[0.99755245,0.00054297794,0.00022064331,0.001164237,0.0004521911,0.00006746224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094989466,0.0007698811,0.00092579983,0.0016286821,0.00086761557,0.0016891451,0.0020824147,0.0011098847,0.0053914106],"category_scores_gemma":[0.0067657065,0.00049701636,0.00061175675,0.0031529705,0.00069588074,0.00342306,0.0026231296,0.00088710064,0.0018785275],"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":[0.0009137053,0.00020725679,0.0053607393,0.00021630609,0.00008874975,0.00021798142,0.00026985302,0.046454776,0.029596712,0.03776659,0.01042764,0.86847967],"study_design_scores_gemma":[0.00017928044,0.000453556,0.0021666887,0.0000727179,0.000051585022,0.0008988882,0.00032413224,0.7872893,0.102793686,0.07663816,0.029034698,0.00009723384],"about_ca_topic_score_codex":0.002599329,"about_ca_topic_score_gemma":0.0028901622,"teacher_disagreement_score":0.0053914106,"about_ca_system_score_codex":0.0009885771,"about_ca_system_score_gemma":0.001737691,"threshold_uncertainty_score":0.018036067},"labels":[],"label_agreement":null},{"id":"W4406469218","doi":"10.1016/j.aim.2025.110113","title":"Bumpless pipe dreams meet puzzles","year":2025,"lang":"en","type":"article","venue":"Advances in Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; Peking University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Calculus (dental); Mathematical economics; Algebra over a field; Pure mathematics; Medicine","score_opus":0.009262990509366471,"score_gpt":0.29030721210328836,"score_spread":0.2810442215939219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406469218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023577906,0.021002058,0.42677286,0.32694796,0.014714256,0.00011649957,0.0015211191,0.0055192965,0.17982805],"genre_scores_gemma":[0.49261686,0.022158572,0.19779406,0.04224065,0.015985042,0.0006028809,0.0018938351,0.0073735397,0.21933459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854064,0.00035529723,0.00004861534,0.00024198522,0.00069439877,0.00011905995],"domain_scores_gemma":[0.9921732,0.0034209637,0.00023406777,0.0019121425,0.0014137985,0.0008458872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028970854,0.0008963622,0.0009787001,0.0014268033,0.0027969743,0.0044459794,0.0022311723,0.0044324454,0.032824177],"category_scores_gemma":[0.024501735,0.0007748832,0.0005285834,0.0011761356,0.008999567,0.030581556,0.005507218,0.009626789,0.012177987],"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":[0.00019364257,0.000046059016,0.00020567075,0.00016477105,0.000019249133,0.00009120651,0.0005660557,0.0017085514,0.00095464493,0.77541035,0.15525693,0.06538283],"study_design_scores_gemma":[0.00002724876,0.000032398908,0.000070460526,0.00007309232,0.00000574401,0.00009013826,0.00024347339,0.0034549723,0.00057081686,0.8735802,0.1218281,0.00002329288],"about_ca_topic_score_codex":0.0008483188,"about_ca_topic_score_gemma":0.0007891084,"teacher_disagreement_score":0.032824177,"about_ca_system_score_codex":0.0010945658,"about_ca_system_score_gemma":0.0011838824,"threshold_uncertainty_score":0.10980785},"labels":[],"label_agreement":null},{"id":"W4406578063","doi":"10.1016/s1544-8800(08)70257-4","title":"10.1016/s1544-8800(08)70257-4","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Side effect (computer science); Adenosine; Medicine; Internal medicine; Computer science","score_opus":0.005688050015750785,"score_gpt":0.17532611091898065,"score_spread":0.16963806090322986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406578063","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060427946,0.0004839591,0.0015004704,0.0004366035,0.00032954177,0.00014725458,0.0012386634,0.0016981937,0.99356115],"genre_scores_gemma":[0.0007796163,0.00021851069,0.0006913064,0.00020949775,0.00006910433,0.00006598889,0.000668885,0.00025858296,0.9970386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992623,0.00005465477,0.000057912875,0.000263838,0.00019999397,0.00016137495],"domain_scores_gemma":[0.99741876,0.00070464524,0.00016751028,0.00036311848,0.0005951384,0.0007508131],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012224808,0.00311833,0.0017616248,0.0031454498,0.0022425787,0.004068209,0.0036066363,0.0053851963,0.98829424],"category_scores_gemma":[0.0018541093,0.00095032336,0.0013650429,0.0033986014,0.0020716516,0.0052918657,0.0031597326,0.0026742101,0.9922963],"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":[0.00038854007,0.00021212232,0.0008533758,0.000541189,0.000046782323,0.0002606825,0.00009264482,0.00056633534,0.0029185133,0.006180555,0.35898432,0.628955],"study_design_scores_gemma":[0.00006563041,0.00012044865,0.00069055764,0.00029717715,0.00001699098,0.0003188637,0.000111278394,0.0004709544,0.0007363819,0.00075445825,0.99638665,0.000030621206],"about_ca_topic_score_codex":0.0043959348,"about_ca_topic_score_gemma":0.0031668954,"teacher_disagreement_score":0.011705756,"about_ca_system_score_codex":0.0013475264,"about_ca_system_score_gemma":0.0010677594,"threshold_uncertainty_score":0.016696751},"labels":[],"label_agreement":null},{"id":"W4406660008","doi":"10.1016/j.ipl.2025.106560","title":"Total variation distance for product distributions is <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.svg\"> <mml:mi mathvariant=\"normal\">#</mml:mi> <mml:mi mathvariant=\"sans-serif\">P</mml:mi> </mml:math> -complete","year":2025,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Institute for the Theory of Computing, University of California Berkeley; National Research Foundation Singapore; Science and Engineering Research Board; Amazon Web Services; National Science Foundation","keywords":"Product (mathematics); Variation (astronomy); Mathematics; Combinatorics; Discrete mathematics; Computer science; Physics; Geometry","score_opus":0.012970238517820323,"score_gpt":0.2337184539889568,"score_spread":0.2207482154711365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406660008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011146539,0.0010776347,0.9633771,0.0007950715,0.00022624175,0.000059232225,0.0020730908,0.0014947429,0.01975039],"genre_scores_gemma":[0.43569055,0.0050460612,0.4415173,0.0011436135,0.00092446397,0.0005465099,0.018194376,0.005037099,0.091900036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99709034,0.0006852851,0.00021362757,0.0007307746,0.0010370217,0.00024291864],"domain_scores_gemma":[0.99330115,0.003110066,0.00034379837,0.0017827428,0.0012485827,0.00021360202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025524357,0.001095989,0.00096480956,0.003083903,0.0007720606,0.0030931528,0.0018491864,0.001022491,0.019714493],"category_scores_gemma":[0.013630494,0.00044298213,0.0011990269,0.0031715082,0.0016824212,0.004258787,0.001962656,0.0016097579,0.010735229],"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":[0.00021784905,0.00009487551,0.0013655118,0.00035930992,0.00011775691,0.00018468694,0.00020576475,0.025025051,0.0032847235,0.64550894,0.044458386,0.27917713],"study_design_scores_gemma":[0.0000275195,0.00014503066,0.0028311866,0.00008609696,0.00004002605,0.00085492677,0.00011649451,0.1784893,0.0072343512,0.74603015,0.064054534,0.000090297355],"about_ca_topic_score_codex":0.0027126702,"about_ca_topic_score_gemma":0.0027351205,"teacher_disagreement_score":0.019714493,"about_ca_system_score_codex":0.0012888507,"about_ca_system_score_gemma":0.0013983279,"threshold_uncertainty_score":0.065951586},"labels":[],"label_agreement":null},{"id":"W4406774579","doi":"10.3389/fbinf.2024.1489704","title":"A novel lossless encoding algorithm for data compression–genomics data as an exemplar","year":2025,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"","keywords":"Computer science; Data compression; Lossless compression; Encoding (memory); Benchmark (surveying); Entropy encoding; Algorithm; Data mining; Compression (physics); Entropy (arrow of time); Bin; Artificial intelligence","score_opus":0.04953632431663978,"score_gpt":0.3138358221403895,"score_spread":0.26429949782374973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406774579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011921725,0.0008980245,0.98371375,0.0003778188,0.00020404374,0.00008369315,0.00018965699,0.0010084934,0.0016029191],"genre_scores_gemma":[0.11263906,0.0011339828,0.8786436,0.00037776705,0.00020474983,0.00020667832,0.0011128347,0.00017642697,0.0055049267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934834,0.00008093153,0.000056132714,0.00010525356,0.00036436002,0.000045001983],"domain_scores_gemma":[0.9992156,0.00025975084,0.00006941418,0.00017160902,0.00025401768,0.00002955329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062536664,0.00071840105,0.0005743508,0.001163291,0.0004236911,0.0010315434,0.00093961076,0.0008527369,0.0019808675],"category_scores_gemma":[0.0027323451,0.00020295811,0.00042752587,0.0016912364,0.0006379587,0.001735568,0.0008922784,0.0013299393,0.0015733354],"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":[0.00040123085,0.0001337253,0.00074391987,0.00026483877,0.00004359685,0.00028977345,0.00019941723,0.03546631,0.09754638,0.027584298,0.008793931,0.82853264],"study_design_scores_gemma":[0.00007488942,0.0003933581,0.00095151045,0.00009251121,0.000042787415,0.0020154286,0.00011521598,0.78225815,0.16073656,0.017588826,0.035666663,0.000064152366],"about_ca_topic_score_codex":0.0006689076,"about_ca_topic_score_gemma":0.0006583165,"teacher_disagreement_score":0.0019808675,"about_ca_system_score_codex":0.00044799838,"about_ca_system_score_gemma":0.00066194724,"threshold_uncertainty_score":0.0066266656},"labels":[],"label_agreement":null},{"id":"W4406796286","doi":"10.1016/j.ic.2024.105165","title":"Preface to “Computation over Compressed Data” at DCC 2022","year":2025,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Computation; Algorithm","score_opus":0.016247767896694177,"score_gpt":0.2959883687082094,"score_spread":0.2797406008115152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406796286","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007903055,0.023866799,0.02463601,0.07817178,0.6665556,0.00036142435,0.0019669246,0.0010145111,0.20263666],"genre_scores_gemma":[0.012960247,0.012662082,0.007322351,0.024941443,0.38971418,0.00030508227,0.001815194,0.0019981344,0.5482813],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99756205,0.00045435442,0.00009037042,0.000394648,0.0013426312,0.00015599634],"domain_scores_gemma":[0.9938869,0.0013275982,0.0001772709,0.000503195,0.003128021,0.0009771286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026216991,0.0019917835,0.0011614154,0.004055424,0.0027115326,0.004762992,0.0012796822,0.0030776819,0.10330568],"category_scores_gemma":[0.012490758,0.0004950511,0.0008945893,0.0025750592,0.0012333919,0.0029797095,0.0019739293,0.0061612586,0.05469986],"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":[0.00003371266,0.000022045064,0.000036239286,0.000073516494,0.0000050223116,0.000025408293,0.000010576137,0.0002514747,0.00020915136,0.008495999,0.9710419,0.01979503],"study_design_scores_gemma":[0.000018722649,0.000033988254,0.00028812233,0.00019767205,0.000008524863,0.00007201513,0.000015536536,0.0012137902,0.00055728055,0.011853081,0.9857178,0.000023601448],"about_ca_topic_score_codex":0.00521026,"about_ca_topic_score_gemma":0.0060661524,"teacher_disagreement_score":0.10330568,"about_ca_system_score_codex":0.0051039862,"about_ca_system_score_gemma":0.0021398733,"threshold_uncertainty_score":0.34559196},"labels":[],"label_agreement":null},{"id":"W4407368399","doi":"10.1051/ps/2025002","title":"Broadcasting in random recursive dags","year":2025,"lang":"en","type":"article","venue":"ESAIM Probability and Statistics","topic":"Algorithms and Data Compression","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":"McGill University","funders":"Agencia Estatal de Investigación; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; Fundación BBVA","keywords":"Broadcasting (networking); Mathematics; Computer science; Computer network","score_opus":0.011544217819248581,"score_gpt":0.258693878083522,"score_spread":0.24714966026427343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407368399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10146596,0.00053155766,0.8920201,0.00042561305,0.000048725255,0.0000770524,0.00037139896,0.0012251089,0.0038344192],"genre_scores_gemma":[0.8337165,0.00047415492,0.15840074,0.00026333975,0.000060765957,0.00020124983,0.0006745433,0.0002586096,0.0059502022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99754333,0.0009856521,0.00014664711,0.00042896267,0.0004783164,0.00041713865],"domain_scores_gemma":[0.989716,0.0062143956,0.00091365125,0.0021341888,0.00074793963,0.00027385994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028331373,0.00049512944,0.0011171321,0.0016129507,0.0010375896,0.0013687179,0.0020080302,0.0010542932,0.0023411224],"category_scores_gemma":[0.019375132,0.0006001407,0.0006464974,0.0019913341,0.002099762,0.0031108756,0.0018542398,0.0009266531,0.000689697],"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":[0.0003082568,0.000050267674,0.0025379932,0.00017435403,0.00003762857,0.00032469508,0.00036892403,0.5166155,0.004261494,0.39366066,0.003421907,0.07823837],"study_design_scores_gemma":[0.000026237736,0.000032949472,0.00036145234,0.000016191492,0.00001194241,0.0001244575,0.00003663174,0.8266515,0.0019896096,0.16908182,0.0016475663,0.000019714169],"about_ca_topic_score_codex":0.0054460606,"about_ca_topic_score_gemma":0.0070849606,"teacher_disagreement_score":0.0054460606,"about_ca_system_score_codex":0.0024399373,"about_ca_system_score_gemma":0.0013631106,"threshold_uncertainty_score":0.017702997},"labels":[],"label_agreement":null},{"id":"W4407626151","doi":"10.1016/j.ssmph.2025.101763","title":"Variance partition that eludes intuition","year":2025,"lang":"en","type":"article","venue":"SSM - Population Health","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Intuition; Mathematics; Partition (number theory); Mathematical economics; Econometrics; Statistics; Philosophy; Epistemology; Combinatorics","score_opus":0.03019258129303116,"score_gpt":0.33137660846880485,"score_spread":0.3011840271757737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407626151","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009012514,0.0008114017,0.9551778,0.010198408,0.0006798102,0.000043304786,0.00013999114,0.0003859228,0.02355093],"genre_scores_gemma":[0.6788902,0.0013275914,0.28877935,0.008870802,0.0035216864,0.00024982725,0.0003228368,0.0005112394,0.017526465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956344,0.001728891,0.00019556005,0.00097216136,0.0012691794,0.00019981021],"domain_scores_gemma":[0.977665,0.015365872,0.00043424923,0.0042421557,0.0020199858,0.0002727332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00791772,0.001103384,0.0015158808,0.0015122873,0.0015607614,0.0033986664,0.0018477311,0.002318137,0.0061698663],"category_scores_gemma":[0.0472012,0.00066079816,0.0010596955,0.001044191,0.006830027,0.009246894,0.0035968155,0.0068171006,0.0016853365],"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":[0.00011695503,0.000048019676,0.0007833139,0.00009629712,0.00005424602,0.00008311581,0.00035670804,0.011124533,0.00050850207,0.9329594,0.010419745,0.043449167],"study_design_scores_gemma":[0.000017859462,0.00001847463,0.00019656756,0.000032620777,0.000009415172,0.00009294195,0.000050467563,0.045877364,0.0004216206,0.9497025,0.0035657613,0.000014438308],"about_ca_topic_score_codex":0.0017320259,"about_ca_topic_score_gemma":0.0012156062,"teacher_disagreement_score":0.00791772,"about_ca_system_score_codex":0.0014340599,"about_ca_system_score_gemma":0.0013013019,"threshold_uncertainty_score":0.041873395},"labels":[],"label_agreement":null},{"id":"W4407736999","doi":"10.1109/ickg63256.2024.00052","title":"OrbitSI: An Orbit-based Algorithm for the Subgraph Isomorphism Search Problem","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Tezpur University; Queen's University; Engineering and Physical Sciences Research Council; Ministry of Education; Queen's University Belfast","keywords":"Subgraph isomorphism problem; Induced subgraph isomorphism problem; Isomorphism (crystallography); Computer science; Orbit (dynamics); Mathematics; Theoretical computer science; Engineering; Aerospace engineering","score_opus":0.02838795631835037,"score_gpt":0.2904489951535391,"score_spread":0.2620610388351887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407736999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026768282,0.0008657094,0.9444027,0.0006785285,0.00030575655,0.0005182433,0.0018600024,0.015464548,0.0091362],"genre_scores_gemma":[0.07585415,0.00034893485,0.90994567,0.00023808182,0.000104735285,0.0004806089,0.007195962,0.0012406867,0.0045911893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989046,0.00018071131,0.000105491854,0.00028056142,0.0004026556,0.00012605436],"domain_scores_gemma":[0.9984169,0.00065410836,0.00012728033,0.00045817753,0.00025770767,0.00008587098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011891956,0.0017304536,0.0016213506,0.0043997513,0.0013039433,0.002038244,0.0028414705,0.0016809539,0.008717159],"category_scores_gemma":[0.005715221,0.00067451503,0.0016024855,0.0052752476,0.001194701,0.00429678,0.002765437,0.0019331494,0.003626553],"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":[0.00057693844,0.00037838102,0.003539901,0.0005729474,0.0002070312,0.00016471012,0.0003449699,0.10082427,0.0075366506,0.035675474,0.05747906,0.7926996],"study_design_scores_gemma":[0.0001985469,0.00016705426,0.00065376196,0.000054591335,0.000057320944,0.00025135253,0.00023430242,0.9160553,0.006518921,0.055967033,0.01980219,0.0000396604],"about_ca_topic_score_codex":0.0070847427,"about_ca_topic_score_gemma":0.013202684,"teacher_disagreement_score":0.008717159,"about_ca_system_score_codex":0.0018119869,"about_ca_system_score_gemma":0.0037513091,"threshold_uncertainty_score":0.029161751},"labels":[],"label_agreement":null},{"id":"W4407768278","doi":"10.1007/978-981-96-2845-2_19","title":"Maximize the Rightmost Digit:Gray Codes for Restricted Growth Strings","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Gray (unit); Numerical digit; Arithmetic; Algorithm; Theoretical computer science; Mathematics","score_opus":0.013009798828538192,"score_gpt":0.23848302900245344,"score_spread":0.22547323017391524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407768278","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11506484,0.0023121084,0.7788461,0.0019013934,0.0003027688,0.00014095857,0.00076274655,0.00218469,0.09848442],"genre_scores_gemma":[0.69616467,0.0017224989,0.25627747,0.00070473424,0.00022884597,0.00023002159,0.0005530454,0.0012148541,0.042903773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995635,0.00010479171,0.00002308949,0.00007240471,0.00015772633,0.00007844435],"domain_scores_gemma":[0.99877816,0.0007239838,0.00007511541,0.00023980995,0.000126489,0.00005640744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051324564,0.00049925345,0.00054623454,0.0007537811,0.00041953914,0.0013626446,0.0007238477,0.00093548157,0.0077436347],"category_scores_gemma":[0.0045139478,0.00027847558,0.00026145516,0.0011802579,0.0011367048,0.0018957324,0.0013811127,0.0012569005,0.0023988604],"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":[0.0003536122,0.000047441874,0.00035244165,0.00023730422,0.000014085772,0.00016913157,0.00021005409,0.044881627,0.01679423,0.67256147,0.013007521,0.251371],"study_design_scores_gemma":[0.000034404795,0.00006518176,0.00023095215,0.000116199044,0.000012978595,0.000276941,0.000051402712,0.13191663,0.015594743,0.8393077,0.012361466,0.000031387768],"about_ca_topic_score_codex":0.0006021988,"about_ca_topic_score_gemma":0.0007833768,"teacher_disagreement_score":0.0077436347,"about_ca_system_score_codex":0.0007315863,"about_ca_system_score_gemma":0.0007540344,"threshold_uncertainty_score":0.025905013},"labels":[],"label_agreement":null},{"id":"W4407974294","doi":"10.1145/3720542","title":"A Hybrid Statistical and Rule-based Approach to Extremely Low-resource Machine Transliteration","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Algorithms and Data Compression","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":"University of Prince Edward Island","funders":"","keywords":"Transliteration; Computer science; Artificial intelligence; Rule-based system; Resource (disambiguation); Natural language processing; Machine learning; Data mining","score_opus":0.005748411853017093,"score_gpt":0.23077370589083876,"score_spread":0.22502529403782168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407974294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011737227,0.00043916257,0.9760543,0.00032132945,0.000089599715,0.00011515302,0.000444331,0.0088704275,0.0019284291],"genre_scores_gemma":[0.14058004,0.00035818602,0.8498511,0.00048087674,0.0001713339,0.0003271618,0.0030181685,0.0006744171,0.00453875],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959306,0.00093112036,0.00039102812,0.0010563914,0.0015392597,0.00015160165],"domain_scores_gemma":[0.99266785,0.0027215884,0.00036038907,0.002482222,0.0016367034,0.00013128805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024751213,0.0010568253,0.0014634689,0.0028666405,0.000791579,0.0025591285,0.0034819613,0.0013211904,0.0026186907],"category_scores_gemma":[0.010418058,0.0005567497,0.0010841081,0.0040851803,0.0015064484,0.003204772,0.0023089184,0.002456186,0.0049341912],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027247082,0.0003201584,0.002150466,0.00022923763,0.00013978551,0.00035356445,0.00030510672,0.08076621,0.025499452,0.015290992,0.010202179,0.86447036],"study_design_scores_gemma":[0.000065441076,0.00015162445,0.00064990076,0.00002460691,0.00005231472,0.00042533092,0.0000946471,0.93447083,0.026024114,0.02658449,0.011403231,0.000053510357],"about_ca_topic_score_codex":0.0035547568,"about_ca_topic_score_gemma":0.0059404694,"teacher_disagreement_score":0.0035547568,"about_ca_system_score_codex":0.00070720987,"about_ca_system_score_gemma":0.0024083068,"threshold_uncertainty_score":0.013089895},"labels":[],"label_agreement":null},{"id":"W4408324787","doi":"10.1109/globecom52923.2024.10901387","title":"Joint Precoding and Probabilistic Constellation Shaping using Arithmetic Distribution Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Ciena (Canada); University of Ottawa","funders":"","keywords":"Precoding; Constellation; Probabilistic logic; Joint (building); Computer science; Matching (statistics); Arithmetic; Algorithm; Theoretical computer science; Mathematics; Artificial intelligence; Statistics; Telecommunications; MIMO; Engineering","score_opus":0.061342940732675204,"score_gpt":0.2800383950466268,"score_spread":0.2186954543139516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408324787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00843461,0.00007013053,0.99016386,0.00007866414,0.000009727208,0.00001384337,0.00001366927,0.000059380225,0.0011561038],"genre_scores_gemma":[0.6427327,0.00037352488,0.3513891,0.0001303738,0.00009532903,0.000094170166,0.00012677857,0.000084232655,0.0049737957],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894506,0.00033174007,0.000041457406,0.00018821897,0.00037834328,0.000115238676],"domain_scores_gemma":[0.9983,0.0011070002,0.0001825716,0.0002236863,0.00014958654,0.000037166104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013197063,0.00057455176,0.0007623157,0.0005256535,0.0003433203,0.00075780915,0.00096621044,0.0008602762,0.0012045904],"category_scores_gemma":[0.005074979,0.00038531228,0.0005056228,0.0010270405,0.0011717081,0.0016423467,0.0013454221,0.00089159474,0.0002933323],"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":[0.0001225934,0.000038450184,0.00036081823,0.000057760983,0.00003182672,0.00008186411,0.00009410755,0.76106703,0.0068556084,0.13956454,0.0006343458,0.09109098],"study_design_scores_gemma":[0.000012389843,0.000040856914,0.000095091615,0.0000057397424,0.0000068497507,0.00006680011,0.000008926664,0.95234305,0.0027544515,0.043934617,0.0007208848,0.000010347836],"about_ca_topic_score_codex":0.0008279458,"about_ca_topic_score_gemma":0.0007753892,"teacher_disagreement_score":0.0013197063,"about_ca_system_score_codex":0.00069125986,"about_ca_system_score_gemma":0.0010022518,"threshold_uncertainty_score":0.0069793463},"labels":[],"label_agreement":null},{"id":"W4408359848","doi":"10.1016/j.dam.2025.02.032","title":"Practical KMP/BM style pattern-matching on indeterminate strings","year":2025,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indeterminate; Mathematics; Matching (statistics); Style (visual arts); Arithmetic; Algorithm; Statistics; Pure mathematics; Literature; Art","score_opus":0.017829833761205553,"score_gpt":0.3005822650504465,"score_spread":0.28275243128924094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408359848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07729774,0.0003340369,0.89094186,0.00064259116,0.00026747104,0.00017155982,0.00076259207,0.0032797395,0.02630241],"genre_scores_gemma":[0.47811422,0.00024206839,0.49948215,0.00053326046,0.0001285612,0.00018299415,0.0013157421,0.00070990075,0.01929103],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99789435,0.0005087004,0.00020708994,0.00040366026,0.0007236764,0.0002626229],"domain_scores_gemma":[0.99812883,0.00047679897,0.00008089647,0.0009703152,0.00028096957,0.00006227073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019012,0.00060012523,0.0007463038,0.0008801722,0.0007204789,0.0015095788,0.0013009314,0.0013687825,0.013236404],"category_scores_gemma":[0.005429966,0.0003296957,0.00053078926,0.0022821103,0.00068063935,0.0027050455,0.0023119696,0.0010438483,0.0046202526],"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":[0.0012886109,0.00019736052,0.0011771782,0.0005061846,0.00006658279,0.0004847414,0.00024164014,0.027912898,0.03923227,0.20476256,0.021719912,0.70241004],"study_design_scores_gemma":[0.00015315232,0.0002814132,0.00075183646,0.00009304256,0.00005515892,0.0010707735,0.00022126212,0.34194723,0.06948101,0.55891895,0.026967952,0.00005814597],"about_ca_topic_score_codex":0.0004904404,"about_ca_topic_score_gemma":0.00070207,"teacher_disagreement_score":0.013236404,"about_ca_system_score_codex":0.0005159333,"about_ca_system_score_gemma":0.00067744247,"threshold_uncertainty_score":0.04428017},"labels":[],"label_agreement":null},{"id":"W4408867802","doi":"10.2139/ssrn.5193979","title":"V-Words, Lyndon Words and Galois Words","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Computer science; Natural language processing; Linguistics; Arithmetic; Philosophy","score_opus":0.008411261213417329,"score_gpt":0.25285905319510116,"score_spread":0.24444779198168382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408867802","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44933966,0.01602998,0.4214863,0.0025299275,0.0013118953,0.00010869939,0.00052882446,0.0009494894,0.10771521],"genre_scores_gemma":[0.9437901,0.0025578928,0.02634182,0.0007392666,0.000534955,0.00010040317,0.00035837552,0.00018909536,0.025388138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902177,0.0003125015,0.00006494746,0.00016962955,0.00026673218,0.00016438599],"domain_scores_gemma":[0.9984818,0.0008249801,0.00018092619,0.000250245,0.00013541005,0.00012661172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077052956,0.0006745221,0.00065971207,0.0026058585,0.0008865919,0.0032611191,0.0006155534,0.0013089041,0.006407387],"category_scores_gemma":[0.005288997,0.00034488508,0.0004058122,0.002590463,0.0029888363,0.0041783494,0.002303733,0.0013928993,0.0013247505],"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":[0.0003201147,0.000026568128,0.0008181551,0.00012293897,0.000018460949,0.00022627924,0.0003755466,0.0027332725,0.0039674104,0.9272554,0.0025073034,0.06162859],"study_design_scores_gemma":[0.000016416076,0.000040890893,0.00020730573,0.000036575864,0.000009121834,0.00019543986,0.00015416353,0.0050938143,0.0016437698,0.98697424,0.005613444,0.000014697086],"about_ca_topic_score_codex":0.00034535935,"about_ca_topic_score_gemma":0.00035882436,"teacher_disagreement_score":0.006407387,"about_ca_system_score_codex":0.0007218699,"about_ca_system_score_gemma":0.00036423362,"threshold_uncertainty_score":0.021434844},"labels":[],"label_agreement":null},{"id":"W4409027996","doi":"10.1101/2025.03.26.645543","title":"Columba: Fast Approximate Pattern Matching with Optimized Search Schemes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Matching (statistics); Computer science; Mathematics; Algorithm; Pattern recognition (psychology); Artificial intelligence; Statistics","score_opus":0.013308487106193121,"score_gpt":0.22823955772810464,"score_spread":0.21493107062191152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409027996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0080627045,0.00037419752,0.9668951,0.00015410145,0.00010836209,0.00014036075,0.0008787301,0.021186464,0.0021999732],"genre_scores_gemma":[0.08080186,0.00016214016,0.9092447,0.00018587084,0.00004180688,0.000512989,0.0031137096,0.001844804,0.0040921215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986304,0.00033523742,0.000095936266,0.00023001056,0.00059733074,0.000111015375],"domain_scores_gemma":[0.99847347,0.0006130458,0.00012521558,0.00048630132,0.0002378995,0.00006405604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014504609,0.0010599893,0.0009962227,0.0019011264,0.00083914207,0.0019955253,0.0032697716,0.0016976123,0.015762167],"category_scores_gemma":[0.007850911,0.0006898768,0.0008084733,0.0036403355,0.00061355345,0.0026199128,0.0024467828,0.0014621706,0.0069053844],"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":[0.0017029211,0.00033303615,0.0013697318,0.0006121312,0.00018341978,0.00022839307,0.00017735708,0.12105103,0.03262365,0.04611204,0.074764326,0.72084194],"study_design_scores_gemma":[0.0002622216,0.00011224821,0.000409751,0.000028118015,0.000017480948,0.00016138467,0.00004362814,0.93274295,0.012851887,0.033198845,0.020127593,0.000043903114],"about_ca_topic_score_codex":0.004362778,"about_ca_topic_score_gemma":0.005946721,"teacher_disagreement_score":0.015762167,"about_ca_system_score_codex":0.0012049783,"about_ca_system_score_gemma":0.002083754,"threshold_uncertainty_score":0.052729726},"labels":[],"label_agreement":null},{"id":"W4409350685","doi":"10.1007/s10878-025-01279-2","title":"An improved approximation algorithm for covering vertices by $$4^+$$-paths","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Optimization","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Theory of computation; Approximation algorithm; Combinatorics; Mathematics; Algorithm; Discrete mathematics; Computer science","score_opus":0.00530167464961042,"score_gpt":0.2531190343717903,"score_spread":0.24781735972217986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409350685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09863346,0.0010560881,0.8697698,0.0012340823,0.0004854807,0.00082206074,0.0020656427,0.005774952,0.02015842],"genre_scores_gemma":[0.14599954,0.0003201012,0.8417723,0.00031475432,0.00010235123,0.00045867136,0.0029178462,0.00039608238,0.0077182543],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870634,0.00020962876,0.00007634348,0.0002891528,0.0004066776,0.00031181052],"domain_scores_gemma":[0.9982153,0.0007840611,0.00010114122,0.00051437813,0.00024833975,0.00013673578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007167431,0.0018709849,0.0021455348,0.0019925514,0.0011979418,0.0020929608,0.0038808417,0.0019697945,0.016946904],"category_scores_gemma":[0.00376878,0.0008626518,0.0017901761,0.004334701,0.0007691984,0.0028964148,0.0028552643,0.0020172545,0.003052797],"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":[0.0012014491,0.00073433056,0.0019436395,0.00052596483,0.00016876255,0.00025628466,0.0002486262,0.25982976,0.011557205,0.030107353,0.037803426,0.6556232],"study_design_scores_gemma":[0.00020789292,0.00017308045,0.00048662355,0.00003841963,0.00006712168,0.00024572658,0.00010972356,0.9655574,0.0037483447,0.022694098,0.00664691,0.000024708397],"about_ca_topic_score_codex":0.009040045,"about_ca_topic_score_gemma":0.013221896,"teacher_disagreement_score":0.016946904,"about_ca_system_score_codex":0.0020887195,"about_ca_system_score_gemma":0.003295325,"threshold_uncertainty_score":0.056693077},"labels":[],"label_agreement":null},{"id":"W4409642825","doi":"10.1109/icaisc64594.2025.10959692","title":"Performance and Implementation Comparison of Knuth-Morris-Pratt and Boyer-Moore String Search Algorithms","year":2025,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"University of Calgary","funders":"","keywords":"Computer science; Algorithm; Boyer–Moore string search algorithm; String (physics); Theoretical computer science; String searching algorithm; Commentz-Walter algorithm; Mathematics; Programming language; Data structure","score_opus":0.023021055929503088,"score_gpt":0.34917183969187054,"score_spread":0.32615078376236745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409642825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8292185,0.006412496,0.12279756,0.0012761585,0.00043606857,0.00029082774,0.0012868895,0.011375107,0.02690651],"genre_scores_gemma":[0.7450954,0.0017460898,0.24008627,0.00029507544,0.00008685049,0.0002449762,0.0029897257,0.00055180606,0.0089038005],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99773836,0.0005587543,0.0003770049,0.00034153182,0.00073107134,0.00025313784],"domain_scores_gemma":[0.9950132,0.0026437696,0.00024619434,0.0006286307,0.0012867248,0.00018148385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018317315,0.00061315566,0.0006808048,0.0021223905,0.0006620144,0.0017151968,0.0023291416,0.0012684115,0.0047965506],"category_scores_gemma":[0.0102929585,0.00029233337,0.00047863982,0.0040432187,0.0005647541,0.00254839,0.0006864203,0.00074940716,0.0016131987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050539975,0.0009109489,0.015352163,0.00089937187,0.0003428609,0.00043509263,0.00066433795,0.21949142,0.02748826,0.02178859,0.024184205,0.6833887],"study_design_scores_gemma":[0.0004584534,0.0012692622,0.0062321243,0.0000981409,0.00012438456,0.0005415919,0.0004258918,0.91692877,0.053728804,0.006338923,0.013767919,0.000085761894],"about_ca_topic_score_codex":0.0067012953,"about_ca_topic_score_gemma":0.0058142236,"teacher_disagreement_score":0.0067012953,"about_ca_system_score_codex":0.0013719936,"about_ca_system_score_gemma":0.00199024,"threshold_uncertainty_score":0.016046107},"labels":[],"label_agreement":null},{"id":"W4409665822","doi":"10.1007/978-3-031-85930-4_3","title":"A Novel Simple Data Structure for Selecting, Inserting, and Deleting in Square Root Time","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Square root; Simple (philosophy); Root (linguistics); Computer science; Square (algebra); Algorithm; Mathematics; Geometry; Philosophy","score_opus":0.041574504631492266,"score_gpt":0.3129840639268332,"score_spread":0.27140955929534094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409665822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040333737,0.0004894325,0.96638405,0.0002684594,0.00039531643,0.0002641197,0.00137939,0.021641338,0.005144486],"genre_scores_gemma":[0.03999067,0.00032064083,0.93314314,0.000568965,0.00026387573,0.0006016748,0.0036327322,0.002808861,0.018669331],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99746513,0.00030578102,0.0003639418,0.0005059855,0.0011543005,0.00020482155],"domain_scores_gemma":[0.99243414,0.0021325597,0.00054285006,0.0032896774,0.0013338627,0.00026695832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013725393,0.001999688,0.0021128373,0.0027968278,0.0017721199,0.0037107999,0.0042535793,0.0015238944,0.022840604],"category_scores_gemma":[0.007589278,0.0011378949,0.001074814,0.0053668125,0.0016181121,0.006275339,0.0038931095,0.0023685293,0.014312833],"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":[0.0012697765,0.00028872633,0.0010463541,0.0005013199,0.000069142065,0.0003498195,0.00047062317,0.009676551,0.038096655,0.07911185,0.07930289,0.7898164],"study_design_scores_gemma":[0.00075053767,0.0011855265,0.0011344583,0.0002657044,0.00022227646,0.002206133,0.0004688792,0.29082847,0.1492052,0.2280181,0.32531965,0.00039514122],"about_ca_topic_score_codex":0.0026881183,"about_ca_topic_score_gemma":0.0054535638,"teacher_disagreement_score":0.022840604,"about_ca_system_score_codex":0.0013721419,"about_ca_system_score_gemma":0.0027808999,"threshold_uncertainty_score":0.0764094},"labels":[],"label_agreement":null},{"id":"W4410007609","doi":"10.1038/s42256-025-01033-7","title":"Lossless data compression by large models","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lossless compression; Compression (physics); Computer science; Data compression; Materials science; Algorithm; Composite material","score_opus":0.01614885772911826,"score_gpt":0.32290467102190135,"score_spread":0.30675581329278306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410007609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021758197,0.0012352535,0.97160417,0.0013547653,0.00024042868,0.00004841395,0.00033120794,0.0014196708,0.0020078348],"genre_scores_gemma":[0.70114064,0.0023135243,0.28083402,0.0008345205,0.0004915086,0.0002396492,0.00132316,0.00037276425,0.012450208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926573,0.0001983944,0.00003995082,0.00011125723,0.0003312654,0.000053444353],"domain_scores_gemma":[0.9978096,0.0011095682,0.000103534156,0.00075398415,0.00018021547,0.000043142336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010010994,0.0006673971,0.0008393795,0.0008013926,0.00036757468,0.0012097389,0.0010571248,0.0010523339,0.0025095171],"category_scores_gemma":[0.005935116,0.00042716903,0.00062149705,0.0012192822,0.000966026,0.0035309352,0.0013557205,0.002011273,0.0012930527],"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":[0.0006623317,0.00018670072,0.0011775842,0.00028963594,0.00011276773,0.0003007894,0.000119281736,0.48237416,0.021902028,0.060919452,0.01327254,0.41868275],"study_design_scores_gemma":[0.00000927728,0.000025609823,0.000117010655,0.000011185094,0.00000835789,0.00006454255,0.000009104238,0.9768463,0.0047223405,0.016843894,0.0013358716,0.0000064648666],"about_ca_topic_score_codex":0.0013008044,"about_ca_topic_score_gemma":0.0014866741,"teacher_disagreement_score":0.0025095171,"about_ca_system_score_codex":0.0006765382,"about_ca_system_score_gemma":0.0005354142,"threshold_uncertainty_score":0.008395135},"labels":[],"label_agreement":null},{"id":"W4410357473","doi":"10.1145/3672608.3707872","title":"Sampling Frequent and Diversified Patterns Through Compression","year":2025,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Sampling (signal processing); Compression (physics); Computer vision; Materials science","score_opus":0.03062066750026527,"score_gpt":0.2912145977021486,"score_spread":0.2605939302018833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410357473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058253583,0.0010607595,0.9364669,0.0003832131,0.00008408943,0.00019785656,0.00032549028,0.0014547008,0.001773432],"genre_scores_gemma":[0.35426384,0.0015478553,0.63740057,0.0003986415,0.00020864626,0.00036942385,0.0014707459,0.00028905034,0.0040512704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998181,0.00033917098,0.00019964349,0.00030821993,0.0008490041,0.00012293582],"domain_scores_gemma":[0.9928104,0.0034226011,0.00047947923,0.0020662767,0.0010987935,0.00012239385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016402612,0.00088602566,0.0012174126,0.0031651484,0.00052391674,0.0015857416,0.0012487527,0.00083996763,0.0016119911],"category_scores_gemma":[0.009187198,0.00044941783,0.0005437194,0.0040477486,0.0008536629,0.0023060804,0.0014409601,0.0009616388,0.0010041756],"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":[0.00049251295,0.00018951992,0.0042562946,0.0003046587,0.00007333395,0.0003777609,0.0003990308,0.042668518,0.03666943,0.011398133,0.0043883706,0.89878243],"study_design_scores_gemma":[0.00009658285,0.00028590776,0.0027832577,0.00012456863,0.000075436044,0.0014563167,0.0002730655,0.8734194,0.06315592,0.046406563,0.011867258,0.00005573254],"about_ca_topic_score_codex":0.000819315,"about_ca_topic_score_gemma":0.0010923726,"teacher_disagreement_score":0.0031651484,"about_ca_system_score_codex":0.00037099054,"about_ca_system_score_gemma":0.00069244695,"threshold_uncertainty_score":0.008674622},"labels":[],"label_agreement":null},{"id":"W4410400500","doi":"10.1145/3728179.3728181","title":"Accelerating Learned Join with FPGAs in Relational Databases","year":2025,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Join (topology); Computer science; Relational database; Database; Field-programmable gate array; Operating system","score_opus":0.06430838450198197,"score_gpt":0.29996229540121044,"score_spread":0.2356539108992285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410400500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27865744,0.004192746,0.68669516,0.00080925913,0.0006937134,0.00012782511,0.0005417081,0.013739613,0.014542659],"genre_scores_gemma":[0.6752667,0.0006662039,0.31535274,0.00025076207,0.00016072512,0.00008067421,0.0006771073,0.00023952221,0.007305419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992508,0.00014068006,0.000056274843,0.00016210887,0.0002887955,0.000101382946],"domain_scores_gemma":[0.99904066,0.00042632554,0.000055644545,0.0002729669,0.00015047172,0.000053983076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061477453,0.0004962332,0.00056413567,0.00076058216,0.00042897146,0.0012913229,0.0013069254,0.0004668683,0.00667528],"category_scores_gemma":[0.0023837073,0.00033363866,0.00034017419,0.0011639217,0.00042813946,0.0021117327,0.000978592,0.00083948387,0.0013788004],"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":[0.0024888234,0.00038564455,0.0044551305,0.00032933432,0.00016607068,0.00030060075,0.000276351,0.07406908,0.03319984,0.027665764,0.01940807,0.8372553],"study_design_scores_gemma":[0.000298907,0.00087169884,0.0018977383,0.00006099665,0.000098610064,0.0004836928,0.00026868592,0.8843212,0.063647225,0.02950096,0.018511523,0.000038872535],"about_ca_topic_score_codex":0.0023289798,"about_ca_topic_score_gemma":0.004556916,"teacher_disagreement_score":0.00667528,"about_ca_system_score_codex":0.0005905959,"about_ca_system_score_gemma":0.000836942,"threshold_uncertainty_score":0.022331},"labels":[],"label_agreement":null},{"id":"W4410451621","doi":"10.5376/tgmb.2024.14.0011","title":"From Leaves to Roots: Mapping the Full Genome of Trees and Decoding Their Functions","year":2024,"lang":"en","type":"article","venue":"Tree Genetics and Molecular Breeding","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decoding methods; Genome; Biology; Computational biology; Botany; Genetics; Evolutionary biology; Computer science; Gene; Algorithm","score_opus":0.026104592480986816,"score_gpt":0.23196741274098112,"score_spread":0.2058628202599943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410451621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15813532,0.010726214,0.8089498,0.002838021,0.00034507172,0.000071430346,0.007498941,0.006169832,0.0052654026],"genre_scores_gemma":[0.25802925,0.0066131735,0.7174703,0.00058292516,0.00018048262,0.00014146761,0.012003074,0.0010856286,0.0038937484],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99963903,0.000086778506,0.000019965473,0.00013790083,0.00008381851,0.000032470794],"domain_scores_gemma":[0.99921715,0.00037561244,0.000068864254,0.0001924609,0.00010935147,0.000036547448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000598632,0.0006885047,0.0006332552,0.0013230313,0.00043943853,0.001303921,0.000675498,0.0008863785,0.0023873432],"category_scores_gemma":[0.0032564278,0.0003723868,0.00047224903,0.002027503,0.00048315868,0.0018608209,0.00097395515,0.0010052612,0.0023036804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000523017,0.00007226334,0.0073708678,0.0005112848,0.000067952555,0.000210292,0.00044022274,0.021615889,0.19244055,0.015297679,0.009612029,0.7518379],"study_design_scores_gemma":[0.00014888922,0.00045291331,0.049133424,0.0006474198,0.00027861353,0.0014593377,0.0016511517,0.3952674,0.14529562,0.26598787,0.1394718,0.00020559393],"about_ca_topic_score_codex":0.0033237247,"about_ca_topic_score_gemma":0.004920042,"teacher_disagreement_score":0.0033237247,"about_ca_system_score_codex":0.00043802077,"about_ca_system_score_gemma":0.00075421017,"threshold_uncertainty_score":0.007986486},"labels":[],"label_agreement":null},{"id":"W4410616320","doi":"10.1016/j.jcss.2025.103679","title":"An FPT algorithm for timeline cover","year":2025,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Timeline; Cover (algebra); Computer science; Algorithm; Mathematics; Engineering; Statistics","score_opus":0.012408226805731665,"score_gpt":0.28855826537174345,"score_spread":0.2761500385660118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410616320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04415751,0.0012239,0.92836946,0.0021392973,0.00026203456,0.00047199728,0.0017655988,0.0063333535,0.015276916],"genre_scores_gemma":[0.2727307,0.00053385907,0.71418256,0.00083327666,0.00023053649,0.0005801073,0.0037270363,0.0007255523,0.006456409],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99799466,0.00024105732,0.00012552705,0.0005725611,0.0007138816,0.00035223874],"domain_scores_gemma":[0.9958851,0.0027308594,0.00019278722,0.0006429122,0.00041596591,0.00013237013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010538574,0.0012560765,0.0014715189,0.0011932435,0.0011134635,0.002099681,0.0021676167,0.0022868393,0.007263678],"category_scores_gemma":[0.007376784,0.00047634853,0.0015503524,0.0023342662,0.0011827135,0.0039464994,0.002041212,0.0024059492,0.001443237],"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":[0.0008635764,0.0005078229,0.0018591873,0.00074151455,0.00014816917,0.0007730248,0.0005850488,0.17588712,0.017150896,0.115692176,0.050624248,0.63516724],"study_design_scores_gemma":[0.00022478293,0.0002413513,0.00048345234,0.00007455674,0.00010076748,0.00095087587,0.0002003905,0.7667186,0.011819743,0.20249721,0.016639302,0.000048901802],"about_ca_topic_score_codex":0.0030872328,"about_ca_topic_score_gemma":0.0029871545,"teacher_disagreement_score":0.007263678,"about_ca_system_score_codex":0.0023454754,"about_ca_system_score_gemma":0.00215448,"threshold_uncertainty_score":0.024299443},"labels":[],"label_agreement":null},{"id":"W4410830018","doi":"10.1145/3736756","title":"Efficient Parallel Boolean Expression Matching","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","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":"University of Toronto","funders":"Science and Technology Commission of Shanghai Municipality","keywords":"Computer science; Boolean expression; Expression (computer science); Matching (statistics); Regular expression; Theoretical computer science; Boolean function; Algorithm; Programming language; Mathematics","score_opus":0.01736739543533445,"score_gpt":0.26725246816992965,"score_spread":0.2498850727345952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410830018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04689043,0.00069160113,0.9331259,0.00045682804,0.000104310566,0.00030232494,0.0010915006,0.008818247,0.008518941],"genre_scores_gemma":[0.3570755,0.0005356852,0.6255549,0.0005622661,0.000084977895,0.00034041016,0.005157297,0.00085803034,0.009830938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980222,0.0002004943,0.0002242284,0.00043027266,0.000861285,0.00026158665],"domain_scores_gemma":[0.99871016,0.00042135248,0.00010835912,0.00037168697,0.00034110094,0.00004741739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008107847,0.0008546436,0.0010890181,0.0015686435,0.0007826638,0.0015531894,0.0018237247,0.0006562033,0.0053553274],"category_scores_gemma":[0.004309177,0.00031247607,0.0010380064,0.0037342352,0.00055199757,0.0038654506,0.0019581788,0.00078834966,0.0017980138],"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":[0.00044979152,0.00030251849,0.0028366682,0.0003580634,0.00007490815,0.00029714606,0.00028394925,0.033836182,0.052697234,0.03842133,0.02133904,0.8491033],"study_design_scores_gemma":[0.000136705,0.00022910051,0.00123843,0.000030339585,0.00009163177,0.0006357789,0.00025023503,0.7879449,0.10017872,0.0777259,0.031481866,0.000056483444],"about_ca_topic_score_codex":0.0029563732,"about_ca_topic_score_gemma":0.0035578671,"teacher_disagreement_score":0.0053553274,"about_ca_system_score_codex":0.001040266,"about_ca_system_score_gemma":0.0016738487,"threshold_uncertainty_score":0.017915368},"labels":[],"label_agreement":null},{"id":"W4411089206","doi":"10.1016/j.ic.2025.105313","title":"The longest subsequence-duplicated subsequence and related problems","year":2025,"lang":"en","type":"article","venue":"Information and Computation","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Longest increasing subsequence; Subsequence; Longest common subsequence problem; Combinatorics; Computer science; Mathematics","score_opus":0.007996093520544739,"score_gpt":0.2384342259044898,"score_spread":0.23043813238394506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411089206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04200187,0.028651997,0.90679467,0.007366955,0.0023385156,0.00016490136,0.0011403625,0.0005227367,0.0110179745],"genre_scores_gemma":[0.5103266,0.034366734,0.41216084,0.0020318553,0.011956126,0.0005089959,0.004281737,0.0006754139,0.023691606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99513996,0.0010944277,0.00058701745,0.0013458657,0.0015782494,0.00025446923],"domain_scores_gemma":[0.97573495,0.017083053,0.0019287601,0.0028283258,0.0020618308,0.0003630586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045766854,0.001127116,0.0026747608,0.0048307693,0.0025233172,0.0034204037,0.0047583063,0.00414265,0.0052395947],"category_scores_gemma":[0.03251399,0.0008432693,0.0017107445,0.014101676,0.0044773063,0.01052,0.0030002967,0.0030561148,0.0012929154],"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":[0.0005445187,0.0002581743,0.0038574855,0.0015233251,0.00023261805,0.0017130962,0.00046573064,0.10462529,0.0019456442,0.48129496,0.031461097,0.37207803],"study_design_scores_gemma":[0.000046294226,0.00006601371,0.000609779,0.00011772267,0.000084800056,0.0012943846,0.00018922887,0.18411489,0.0022753952,0.801076,0.0100757,0.000049886963],"about_ca_topic_score_codex":0.0019460281,"about_ca_topic_score_gemma":0.0009711102,"teacher_disagreement_score":0.0052395947,"about_ca_system_score_codex":0.0017475021,"about_ca_system_score_gemma":0.0020014504,"threshold_uncertainty_score":0.024204075},"labels":[],"label_agreement":null},{"id":"W4411301048","doi":"10.1007/978-981-96-8170-9_15","title":"Sampling Frequent and Diverse Patterns Through Compression","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Sampling (signal processing); Data compression; Artificial intelligence; Computer vision","score_opus":0.02990545936019222,"score_gpt":0.2783769681445482,"score_spread":0.24847150878435598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411301048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041067038,0.0010966772,0.9512404,0.00032865003,0.00018171167,0.00018919187,0.0006461817,0.0016232944,0.0036268502],"genre_scores_gemma":[0.2938071,0.0018904312,0.6861131,0.0003907919,0.00058015995,0.00034975095,0.0039012292,0.00042732302,0.012540058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872273,0.00020652413,0.000084062056,0.00025640722,0.00063002843,0.00010017311],"domain_scores_gemma":[0.995167,0.0027177497,0.00020690284,0.0012257408,0.00055301515,0.00012948723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010163191,0.0007679035,0.0012722289,0.0038978744,0.0005627791,0.0014475494,0.0013614006,0.00089595915,0.0039143343],"category_scores_gemma":[0.008701367,0.00050042383,0.0007383209,0.005218356,0.00084892486,0.0018406984,0.0018629124,0.0010833018,0.002136567],"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":[0.0003836499,0.00013826907,0.0027371598,0.00023127352,0.000081708786,0.0004836157,0.0002872706,0.032635197,0.022256372,0.021024095,0.009766726,0.9099746],"study_design_scores_gemma":[0.00006326074,0.00019674537,0.0025576367,0.00007643097,0.00007986618,0.0019115172,0.00028239941,0.8572904,0.020107822,0.10466545,0.01272306,0.000045392728],"about_ca_topic_score_codex":0.0008594663,"about_ca_topic_score_gemma":0.0013218977,"teacher_disagreement_score":0.0039143343,"about_ca_system_score_codex":0.0003685329,"about_ca_system_score_gemma":0.00054774916,"threshold_uncertainty_score":0.013094723},"labels":[],"label_agreement":null},{"id":"W4411440062","doi":"10.1007/978-3-662-69359-9_415","title":"Non-uniform Random Variate Generation","year":2025,"lang":"en","type":"book-chapter","venue":"International Encyclopedia of Statistical Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Random variate; Convolution random number generator; Mathematics; Computer science; Statistics; Random variable","score_opus":0.011891182187138579,"score_gpt":0.2676001458674118,"score_spread":0.25570896368027324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411440062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055552833,0.0007966806,0.9807778,0.00019193355,0.0002494299,0.000088824665,0.00013181717,0.00065882504,0.0115494765],"genre_scores_gemma":[0.38892114,0.0014303757,0.5393078,0.00074224046,0.0003936894,0.0005745545,0.001087469,0.0006265148,0.066916145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999,0.000417601,0.000037118425,0.00016828574,0.0003204265,0.000056531946],"domain_scores_gemma":[0.9970193,0.0018794581,0.000108172775,0.0006815611,0.00026627013,0.000045309218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011435454,0.00046687768,0.0007588671,0.0006226455,0.0003830693,0.00091527443,0.001354659,0.0008239932,0.012209604],"category_scores_gemma":[0.005137285,0.0003036741,0.0004954384,0.0010404305,0.0007998892,0.0012187005,0.0014370778,0.0009150451,0.0042756703],"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":[0.00033928372,0.00008092054,0.000987236,0.00033601682,0.00007868207,0.00041803558,0.00013185729,0.122847766,0.009609459,0.4715811,0.020427259,0.37316245],"study_design_scores_gemma":[0.00006586446,0.000077044926,0.00045714152,0.00006859762,0.000034841512,0.0010421787,0.000020366178,0.7769173,0.010270772,0.18748564,0.023513045,0.000047257236],"about_ca_topic_score_codex":0.00014234822,"about_ca_topic_score_gemma":0.00023353877,"teacher_disagreement_score":0.012209604,"about_ca_system_score_codex":0.0004289831,"about_ca_system_score_gemma":0.0003592363,"threshold_uncertainty_score":0.040845156},"labels":[],"label_agreement":null},{"id":"W4413071359","doi":"10.1007/978-3-031-98740-3_17","title":"A Space-Efficient Algorithm for Longest Common Almost Increasing Subsequence of Two Sequences","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Longest common subsequence problem; Computer science; Longest increasing subsequence; Subsequence; Algorithm; Space (punctuation); Theoretical computer science; Mathematics","score_opus":0.01818424227148864,"score_gpt":0.2780371640264606,"score_spread":0.259852921754972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413071359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015799038,0.00057292264,0.9756588,0.000124291,0.00020201526,0.0002786649,0.00044041916,0.00428855,0.0026352622],"genre_scores_gemma":[0.036839478,0.00017392662,0.95703685,0.000049836177,0.00005133319,0.00022454583,0.0014587174,0.00022465637,0.003940585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987166,0.00013692166,0.00014296608,0.00037178828,0.0005053136,0.00012651354],"domain_scores_gemma":[0.9985683,0.00046278792,0.00009091529,0.00034055975,0.0004652277,0.00007221158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000755321,0.0014384257,0.0014544637,0.0028691387,0.0012862687,0.0016490434,0.0020803132,0.0011543246,0.009587023],"category_scores_gemma":[0.0031201402,0.00058808277,0.001273124,0.0043731895,0.0006375572,0.0025159325,0.0021168564,0.0013696372,0.0048707905],"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":[0.00037458856,0.00018976274,0.00060262205,0.00027824027,0.000068785404,0.00018492318,0.00021163326,0.013521181,0.042152833,0.018308172,0.011147005,0.91296023],"study_design_scores_gemma":[0.00041806436,0.0008699398,0.0018768052,0.00012324157,0.00017302962,0.0020539588,0.00059191335,0.75557476,0.09385884,0.0822195,0.062103543,0.00013643291],"about_ca_topic_score_codex":0.0024647487,"about_ca_topic_score_gemma":0.0033432867,"teacher_disagreement_score":0.009587023,"about_ca_system_score_codex":0.00084602786,"about_ca_system_score_gemma":0.0024426233,"threshold_uncertainty_score":0.03207177},"labels":[],"label_agreement":null},{"id":"W4413110219","doi":"10.1186/s13015-025-00281-x","title":"b-move: faster lossless approximate pattern matching in a run-length compressed index","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institutes of Health; National Human Genome Research Institute; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Search engine indexing; Lossless compression; Index (typography); RefSeq; Memory footprint; Pattern matching; Scalability; Matching (statistics); Overhead (engineering); Theoretical computer science; Data mining; Genome; Algorithm; Data compression; Information retrieval; Mathematics; Artificial intelligence; Database","score_opus":0.01169109429062735,"score_gpt":0.2933725954004427,"score_spread":0.2816815011098153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413110219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08655799,0.0034979945,0.8442172,0.0005339556,0.0005471045,0.00042041874,0.0030019209,0.04745845,0.013764913],"genre_scores_gemma":[0.24938445,0.0009340763,0.7227748,0.00057426054,0.00019188854,0.0005558466,0.012183164,0.002046409,0.011355139],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863666,0.00011602451,0.00011538166,0.00025392938,0.00074768346,0.00013033024],"domain_scores_gemma":[0.99886584,0.0002485649,0.00011635434,0.00044601562,0.0002399875,0.00008332775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062305183,0.0009995074,0.0011530422,0.0016161989,0.00064650545,0.0016812659,0.0025693988,0.00083748926,0.0064414158],"category_scores_gemma":[0.0038558943,0.00048646936,0.00071576325,0.003522665,0.0005898811,0.0041830027,0.0026436702,0.001095511,0.0054587466],"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":[0.0019148288,0.0004930982,0.0032353394,0.0006676341,0.00015178465,0.00054728996,0.0005701106,0.020440396,0.10515807,0.027188959,0.06370567,0.77592677],"study_design_scores_gemma":[0.00063736114,0.0010903422,0.0022405477,0.00012622283,0.00014292245,0.0017012852,0.0004779919,0.70949125,0.1484904,0.030196274,0.1051889,0.00021650734],"about_ca_topic_score_codex":0.004679794,"about_ca_topic_score_gemma":0.00520448,"teacher_disagreement_score":0.0064414158,"about_ca_system_score_codex":0.000778043,"about_ca_system_score_gemma":0.0016581416,"threshold_uncertainty_score":0.021548688},"labels":[],"label_agreement":null},{"id":"W4413212050","doi":"10.1109/icjece.2025.3587644","title":"A New Text Compression Algorithm Based on Index Permutation and Suffix Coding","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Suffix; Permutation (music); Compression (physics); Combinatorics; Computer science; Index (typography); Algorithm; Coding (social sciences); Mathematics; Physics; Statistics; Philosophy; Linguistics; Programming language","score_opus":0.0038143154638581294,"score_gpt":0.18905608465707915,"score_spread":0.18524176919322102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413212050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02520735,0.0010203844,0.9638707,0.00032478536,0.0004427842,0.00031313684,0.00076778367,0.0036847892,0.0043682964],"genre_scores_gemma":[0.084430836,0.0008345123,0.89975846,0.00034375704,0.00021824721,0.0004067538,0.002981004,0.0003460354,0.010680484],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994603,0.000045120483,0.00005997032,0.00009116744,0.0003027399,0.000040708568],"domain_scores_gemma":[0.9992188,0.00019788907,0.00006406273,0.00019113072,0.0002975683,0.000030531926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004515813,0.0007942727,0.0006118556,0.001829319,0.0005759367,0.0010038448,0.001057951,0.0007594201,0.0031957594],"category_scores_gemma":[0.0024442424,0.00022232118,0.0005386894,0.0023049158,0.00058522355,0.0018105194,0.0011281703,0.0009732424,0.002567669],"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":[0.00028952016,0.00010121599,0.0006257853,0.00019975072,0.00004890562,0.0002706576,0.00019569711,0.014060045,0.109420806,0.012786729,0.011045142,0.8509558],"study_design_scores_gemma":[0.00019932276,0.0006778534,0.0019930804,0.00010255365,0.000092356626,0.0028255899,0.00021353664,0.5114373,0.36982536,0.016501285,0.09599824,0.00013351432],"about_ca_topic_score_codex":0.0015138029,"about_ca_topic_score_gemma":0.0019259469,"teacher_disagreement_score":0.0031957594,"about_ca_system_score_codex":0.0004256954,"about_ca_system_score_gemma":0.0013200665,"threshold_uncertainty_score":0.010690868},"labels":[],"label_agreement":null},{"id":"W4413279381","doi":"10.1145/3750729","title":"Fast and Small Subsampled R-indexes","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"Agencia Nacional de Investigación y Desarrollo","keywords":"Mathematics; Computer science; Combinatorics; Statistics","score_opus":0.01821862947291441,"score_gpt":0.25692759636670964,"score_spread":0.23870896689379523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413279381","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1420917,0.004630333,0.8156568,0.0010763296,0.00050431443,0.00056973164,0.0045296503,0.021177137,0.009764068],"genre_scores_gemma":[0.23867895,0.0010790005,0.7427128,0.00046408718,0.0003567888,0.0005260878,0.008717945,0.0014233534,0.0060410392],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969778,0.00042596043,0.00027310714,0.00056937325,0.0015483275,0.00020543534],"domain_scores_gemma":[0.99314547,0.0020827367,0.0005119761,0.0028595629,0.0011946146,0.0002057417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012241891,0.0010945826,0.0015675223,0.0026158914,0.0009166656,0.0021570493,0.0023652168,0.001097655,0.003603016],"category_scores_gemma":[0.01469197,0.0005654128,0.0008587488,0.004641762,0.0011139606,0.0049674744,0.0027248247,0.0012697865,0.0047663497],"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":[0.001585329,0.000379686,0.004572113,0.0005332912,0.00013611258,0.0005798129,0.00071488816,0.035183996,0.08071911,0.037141908,0.0402561,0.7981977],"study_design_scores_gemma":[0.0004602025,0.0009039322,0.0042127036,0.000120859186,0.00013603072,0.0022306473,0.00068710867,0.75537837,0.10320156,0.06721236,0.065245606,0.0002106228],"about_ca_topic_score_codex":0.003086442,"about_ca_topic_score_gemma":0.0041847015,"teacher_disagreement_score":0.003603016,"about_ca_system_score_codex":0.0008494739,"about_ca_system_score_gemma":0.0021724487,"threshold_uncertainty_score":0.012053251},"labels":[],"label_agreement":null},{"id":"W4413998513","doi":"10.3389/fbinf.2025.1577324","title":"A novel linear indexing method for strings under all internal nodes in a suffix tree","year":2025,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Algorithms and Data Compression","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":"McMaster University","funders":"University of Connecticut","keywords":"Search engine indexing; Suffix; Generalized suffix tree; Computer science; Tree (set theory); Compressed suffix array; Suffix tree; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Data structure; Combinatorics; Programming language","score_opus":0.019749279133473994,"score_gpt":0.30205323189460714,"score_spread":0.2823039527611331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413998513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004277341,0.0002883412,0.99168175,0.00010623201,0.00013389968,0.00009847265,0.00029549276,0.0018405371,0.0012778459],"genre_scores_gemma":[0.025965992,0.00031134815,0.96912473,0.00010515665,0.00015688763,0.00018746253,0.0012635598,0.00030624008,0.0025785505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982893,0.00017165345,0.00023914731,0.0003944249,0.000773414,0.00013196531],"domain_scores_gemma":[0.99730515,0.0007505404,0.0002530359,0.00073882047,0.0008117823,0.00014067514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008759871,0.00078477553,0.0013191333,0.0026455203,0.0012713489,0.0022112539,0.0017873257,0.0010102787,0.0050235637],"category_scores_gemma":[0.0056971516,0.00046329421,0.0009434853,0.005278647,0.0008630284,0.0055316985,0.0023157662,0.0014040398,0.0053704362],"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":[0.00029406237,0.00018950131,0.000975518,0.00042845638,0.000052716896,0.00018620734,0.00046489327,0.010488418,0.05486055,0.049132846,0.013626072,0.8693008],"study_design_scores_gemma":[0.00026785265,0.00079330185,0.0013551768,0.00016314384,0.00015607712,0.0025053169,0.0005768951,0.659881,0.10610722,0.13076426,0.09720081,0.00022892523],"about_ca_topic_score_codex":0.0014491065,"about_ca_topic_score_gemma":0.0020152933,"teacher_disagreement_score":0.0050235637,"about_ca_system_score_codex":0.0006898725,"about_ca_system_score_gemma":0.0026773938,"threshold_uncertainty_score":0.01680553},"labels":[],"label_agreement":null},{"id":"W4414001959","doi":"10.1016/j.tcs.2025.115537","title":"Succinct encodings of binary trees with application to AVL trees","year":2025,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weight-balanced tree; Binary tree; Binary number; Binary search tree; Mathematics; Random binary tree; Computer science; Combinatorics; Arithmetic","score_opus":0.004659458754043663,"score_gpt":0.24415116376089935,"score_spread":0.23949170500685568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414001959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08561357,0.00050767686,0.8987682,0.0010996137,0.00013572817,0.00012383047,0.0007757902,0.0016726309,0.011302907],"genre_scores_gemma":[0.6399019,0.0005861094,0.3509071,0.00048078207,0.00019773093,0.00034427646,0.0017725873,0.000608062,0.005201469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984465,0.00031745754,0.00011959392,0.00019937461,0.00071723026,0.00019977163],"domain_scores_gemma":[0.99300694,0.0032877156,0.0005279835,0.0020971622,0.0008350285,0.00024519232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013854576,0.00041783784,0.0006290223,0.0016455742,0.00076117023,0.0026115794,0.0014803164,0.00088717625,0.003791616],"category_scores_gemma":[0.01263096,0.00051724684,0.0006326974,0.0021879487,0.0015625703,0.0057173455,0.003175877,0.002088797,0.0010903348],"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":[0.00028906693,0.00017943527,0.0011450463,0.00020441579,0.000016560007,0.00025764047,0.0007148948,0.0701222,0.021864701,0.7458237,0.00731133,0.15207098],"study_design_scores_gemma":[0.000054301614,0.000098718,0.00030167235,0.000101903635,0.000020338672,0.00031692826,0.00014566621,0.47932327,0.02287097,0.4848839,0.011837136,0.00004525117],"about_ca_topic_score_codex":0.0006895679,"about_ca_topic_score_gemma":0.0010903983,"teacher_disagreement_score":0.003791616,"about_ca_system_score_codex":0.0018045281,"about_ca_system_score_gemma":0.0009627045,"threshold_uncertainty_score":0.0130928755},"labels":[],"label_agreement":null},{"id":"W4414453679","doi":"10.1007/978-3-032-05228-5_6","title":"Prefix-Free Parsing for Merging Big BWTs","year":2025,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Parsing; Footprint; Memory footprint; Big data; Word (group theory)","score_opus":0.01648811670444234,"score_gpt":0.27417186861625253,"score_spread":0.2576837519118102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414453679","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023398284,0.00076163583,0.94162166,0.00038070846,0.00035432162,0.00019603714,0.0022398608,0.0214681,0.009579351],"genre_scores_gemma":[0.20542094,0.0004965876,0.7630963,0.0003984758,0.00018089799,0.00029600598,0.009658618,0.009053258,0.011398974],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971507,0.0005138124,0.0004157281,0.00065457314,0.0009031192,0.0003620031],"domain_scores_gemma":[0.99081504,0.0036964477,0.00030695577,0.0038055945,0.0011851249,0.00019072864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021386398,0.0014053074,0.0015938529,0.002878946,0.0017696341,0.0034387999,0.0030970767,0.002252637,0.021279525],"category_scores_gemma":[0.011127263,0.0017166573,0.0016976236,0.005992792,0.0018557125,0.008481305,0.0056044664,0.0026900736,0.0075888103],"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":[0.0014214457,0.0002788119,0.002257753,0.0011852066,0.0002464829,0.001325304,0.0013529042,0.02905958,0.045631137,0.15292038,0.048314974,0.716006],"study_design_scores_gemma":[0.0001863789,0.0002878432,0.0012294558,0.0003297848,0.0003209439,0.0009017316,0.0008483661,0.24935701,0.111507416,0.53216815,0.10262924,0.00023372962],"about_ca_topic_score_codex":0.0024856983,"about_ca_topic_score_gemma":0.004601342,"teacher_disagreement_score":0.021279525,"about_ca_system_score_codex":0.0010077069,"about_ca_system_score_gemma":0.0022441575,"threshold_uncertainty_score":0.07118708},"labels":[],"label_agreement":null},{"id":"W4414453687","doi":"10.1007/978-3-032-05228-5_2","title":"KeBaB: k-mer Based Breaking for Finding Long MEMs","year":2025,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Substring; Microelectromechanical systems; Bloom filter; Filter (signal processing); Sequence (biology); Matching (statistics)","score_opus":0.016424890271891354,"score_gpt":0.2892989182554494,"score_spread":0.27287402798355803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414453687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034297787,0.00089631847,0.9152046,0.0004646883,0.0007447758,0.00024313756,0.001980647,0.037028268,0.009139851],"genre_scores_gemma":[0.20811726,0.00031755405,0.7607987,0.0005129448,0.00015032783,0.00037417255,0.004885551,0.0043550213,0.020488562],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998792,0.00011351194,0.00007649769,0.00022215449,0.000628418,0.0001674711],"domain_scores_gemma":[0.9980563,0.00044101043,0.00018535262,0.0008240133,0.00037544844,0.00011791014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076281274,0.0017773279,0.0017226426,0.002055792,0.0018834531,0.0018478552,0.0025992116,0.0022295935,0.032637764],"category_scores_gemma":[0.003999049,0.0009209057,0.0010752968,0.0020601528,0.0007516354,0.0026587965,0.0033464215,0.0022997383,0.014322092],"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":[0.0017164518,0.00026258934,0.002996396,0.0007578695,0.00026010218,0.00037638316,0.0003338648,0.012554401,0.13067235,0.020082014,0.07681213,0.75317544],"study_design_scores_gemma":[0.0004116114,0.0010559997,0.0041116513,0.0002442965,0.0002131235,0.001316433,0.0008387444,0.5435933,0.21564767,0.12121551,0.111025594,0.00032599884],"about_ca_topic_score_codex":0.0009566429,"about_ca_topic_score_gemma":0.0025295937,"teacher_disagreement_score":0.032637764,"about_ca_system_score_codex":0.0005921817,"about_ca_system_score_gemma":0.0007173028,"threshold_uncertainty_score":0.109184206},"labels":[],"label_agreement":null},{"id":"W4414454332","doi":"10.1007/978-3-032-05228-5_15","title":"Efficient Computation of Closed Substrings","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Suffix array; Suffix; Compressed suffix array; Fibonacci number; String (physics); Prefix; Simple (philosophy); Computation","score_opus":0.01179840861047333,"score_gpt":0.24627157148211692,"score_spread":0.2344731628716436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414454332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08503591,0.0022676382,0.8648038,0.00052852463,0.00060923555,0.0002726297,0.0024735346,0.009548411,0.03446035],"genre_scores_gemma":[0.20998481,0.00099132,0.7473895,0.00023003436,0.00027934054,0.00023382361,0.006959662,0.001641348,0.0322902],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989767,0.0000837157,0.00009230286,0.0002269653,0.0005020136,0.00011830657],"domain_scores_gemma":[0.99758375,0.0010487225,0.00011676222,0.00063651375,0.000516955,0.0000972166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047782724,0.0010987154,0.0015921298,0.002411481,0.0011207733,0.002766046,0.0022934864,0.0009495323,0.01914638],"category_scores_gemma":[0.0043172413,0.000606499,0.0011350088,0.0040898775,0.0009758241,0.004636689,0.0031718444,0.0012120953,0.00692582],"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":[0.00049407134,0.00012584751,0.00091656967,0.0006763835,0.000063649364,0.00035150218,0.0004232001,0.0092900265,0.030508634,0.10161014,0.025814332,0.8297257],"study_design_scores_gemma":[0.00017082234,0.00040042636,0.001647487,0.0002833751,0.00017154441,0.0014139047,0.0007096567,0.2739376,0.08865682,0.5331113,0.09940189,0.00009516032],"about_ca_topic_score_codex":0.0009017448,"about_ca_topic_score_gemma":0.0019154222,"teacher_disagreement_score":0.01914638,"about_ca_system_score_codex":0.0009052563,"about_ca_system_score_gemma":0.0009574444,"threshold_uncertainty_score":0.06405103},"labels":[],"label_agreement":null},{"id":"W4414607743","doi":"10.1007/s10959-025-01452-7","title":"The Generalized Alice HH Vs Bob HT Problem","year":2025,"lang":"en","type":"article","venue":"Journal of Theoretical Probability","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Vetenskapsrådet; Natural Sciences and Engineering Research Council of Canada; Knut och Alice Wallenbergs Stiftelse","keywords":"Substring; String (physics); Sequence (biology); Counterintuitive; Markov chain; Set (abstract data type); Simple (philosophy); Finite set","score_opus":0.007932117649655832,"score_gpt":0.26022387205164466,"score_spread":0.2522917544019888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414607743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27588457,0.004330199,0.4764497,0.06490675,0.0013883826,0.00038023695,0.0035589267,0.0006545671,0.17244658],"genre_scores_gemma":[0.94076926,0.0013391947,0.024767611,0.0030187308,0.0012259088,0.00018201924,0.0007712665,0.00022966419,0.027696386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974375,0.0013829127,0.000059926107,0.00039804247,0.00033986848,0.00038183734],"domain_scores_gemma":[0.98406106,0.013017537,0.00062072644,0.0012188014,0.00050896185,0.0005729363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003521049,0.00072575576,0.0020317836,0.00087866385,0.0016969831,0.003251499,0.0025399704,0.005328681,0.018609632],"category_scores_gemma":[0.019278988,0.0005885925,0.00078682497,0.0016607787,0.0048793056,0.00799876,0.003817726,0.0037256605,0.0010046044],"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":[0.0005667178,0.000089608795,0.0005715686,0.00025513614,0.00007083841,0.00030431664,0.00023635602,0.039952286,0.0005429989,0.9050174,0.026369248,0.026023433],"study_design_scores_gemma":[0.000088714965,0.000018687937,0.00023991059,0.000030054032,0.000015214773,0.00011915213,0.00009641147,0.057639904,0.00024585347,0.9398128,0.0016776338,0.000015675227],"about_ca_topic_score_codex":0.0018113469,"about_ca_topic_score_gemma":0.0010455004,"teacher_disagreement_score":0.018609632,"about_ca_system_score_codex":0.0017623286,"about_ca_system_score_gemma":0.0022356268,"threshold_uncertainty_score":0.062255442},"labels":[],"label_agreement":null},{"id":"W4414624944","doi":"10.1093/bib/bbaf512","title":"A novel pairwise sequence alignment algorithm for similarity search in massive datasets","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Algorithms and Data Compression","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":"Princess Margaret Cancer Centre","funders":"","keywords":"Pairwise comparison; Multiple sequence alignment; Preprocessor; Sequence (biology); Sequence alignment; Similarity (geometry); Alignment-free sequence analysis; Range (aeronautics)","score_opus":0.03438104331734072,"score_gpt":0.305489804256393,"score_spread":0.2711087609390523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414624944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059995083,0.001133222,0.9881449,0.00014440548,0.00015187204,0.0002131063,0.00052977167,0.0028402442,0.0008430354],"genre_scores_gemma":[0.028409814,0.00059338124,0.967031,0.00009889933,0.00010664978,0.00040611567,0.0021046682,0.00016192108,0.0010875529],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741036,0.00052383874,0.00030016954,0.0004927333,0.0011470758,0.0001258268],"domain_scores_gemma":[0.9988587,0.00039923278,0.00011903213,0.00022906788,0.0003356372,0.00005825501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014819885,0.0014723773,0.0019034632,0.003697231,0.0011793482,0.0012956292,0.0024748493,0.0011965209,0.0034740204],"category_scores_gemma":[0.0055666617,0.0005159687,0.0012762437,0.0076113353,0.0005518871,0.0034304908,0.0018901799,0.0017378067,0.0029203729],"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":[0.00033331904,0.00020823453,0.0014966187,0.00048045293,0.0002467266,0.00030215594,0.00016193243,0.04111282,0.022270529,0.013016515,0.019064395,0.9013063],"study_design_scores_gemma":[0.0002101924,0.00043721418,0.0015918831,0.000067596884,0.00008951,0.0015293697,0.00014647773,0.9046914,0.020337246,0.030755043,0.040054146,0.00008991605],"about_ca_topic_score_codex":0.0025374491,"about_ca_topic_score_gemma":0.0032252455,"teacher_disagreement_score":0.003697231,"about_ca_system_score_codex":0.00056466344,"about_ca_system_score_gemma":0.0021406484,"threshold_uncertainty_score":0.011621773},"labels":[],"label_agreement":null},{"id":"W4414726848","doi":"10.1145/3737902.3768352","title":"WiP: Efficient Speculative Decoding for AI PCs via Hierarchical N-Gram Retrieval","year":2025,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"Advanced Micro Devices (Canada)","funders":"","keywords":"Decoding methods; Speedup; Inference; Look-ahead; Quality (philosophy); Face (sociological concept)","score_opus":0.011827161235240614,"score_gpt":0.2985599656614644,"score_spread":0.2867328044262238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414726848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036057808,0.0009887473,0.8566634,0.00044126713,0.00023859397,0.00022641018,0.0020612986,0.098278865,0.0050436435],"genre_scores_gemma":[0.24787319,0.0005033967,0.7281922,0.00062032626,0.00016374324,0.00030196167,0.008855934,0.0031858732,0.010303411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990791,0.00012064612,0.00008841511,0.00025938463,0.0003421948,0.00011032723],"domain_scores_gemma":[0.99794835,0.00063272193,0.000108058695,0.0008158842,0.00041017059,0.000084848514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007804493,0.0015982982,0.0008515733,0.0010493466,0.0008368061,0.001725635,0.002909748,0.0010086198,0.005507341],"category_scores_gemma":[0.0057904082,0.00056449603,0.00077370036,0.0015542322,0.0008371881,0.003876783,0.002374607,0.0015538172,0.0060961777],"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":[0.0014147724,0.00028510301,0.0040239515,0.000490054,0.00017799262,0.0007193329,0.0005497903,0.0457654,0.07082906,0.0147769535,0.058619805,0.8023477],"study_design_scores_gemma":[0.00014054852,0.00020559783,0.0008174908,0.000034170687,0.000059690414,0.00030771928,0.00017343364,0.89330685,0.06538359,0.019583464,0.019912856,0.000074542964],"about_ca_topic_score_codex":0.012196408,"about_ca_topic_score_gemma":0.022753568,"teacher_disagreement_score":0.012196408,"about_ca_system_score_codex":0.0008638992,"about_ca_system_score_gemma":0.0033426068,"threshold_uncertainty_score":0.024250865},"labels":[],"label_agreement":null},{"id":"W4415007625","doi":"10.1145/3763174","title":"AutoVerus: Automated Proof Generation for Rust Code","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Algorithms and Data Compression","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 Toronto","funders":"","keywords":"Correctness; Mathematical proof; Debugging; Code (set theory); Proof of concept; Suite; Benchmark (surveying); Rust (programming language); Automated theorem proving","score_opus":0.020264518341811207,"score_gpt":0.30608110901859026,"score_spread":0.28581659067677906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415007625","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014540714,0.00040844857,0.90458167,0.00040807071,0.00009837454,0.00029264507,0.00092291244,0.07282961,0.0059175296],"genre_scores_gemma":[0.18074346,0.00038668676,0.80054253,0.00033306284,0.00004715104,0.00034718655,0.003072695,0.011213172,0.0033140809],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623317,0.00146582,0.00022884303,0.00045035357,0.0014135721,0.00020824217],"domain_scores_gemma":[0.9842461,0.009826516,0.0006828907,0.003444162,0.001592206,0.00020821745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038970136,0.0010533545,0.0005557426,0.0018589381,0.00061843864,0.0016602854,0.00224407,0.0010024952,0.0130175315],"category_scores_gemma":[0.020270675,0.0008879031,0.001401471,0.0007778654,0.0018635445,0.0025494145,0.0031280003,0.001526603,0.0030707724],"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":[0.00064120616,0.00038858384,0.003768337,0.002243288,0.0002098857,0.0009840003,0.0010223459,0.09939758,0.046131294,0.12620775,0.06466213,0.65434355],"study_design_scores_gemma":[0.00040235,0.00033805482,0.0009084113,0.00041432364,0.00006714062,0.0011252591,0.00019202047,0.7176665,0.092020415,0.10290837,0.08385533,0.00010182882],"about_ca_topic_score_codex":0.001570941,"about_ca_topic_score_gemma":0.0020706651,"teacher_disagreement_score":0.0130175315,"about_ca_system_score_codex":0.0009082966,"about_ca_system_score_gemma":0.002491988,"threshold_uncertainty_score":0.043547988},"labels":[],"label_agreement":null},{"id":"W4415312698","doi":"10.48550/arxiv.2506.14734","title":"Compressing Suffix Trees by Path Decompositions","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Suffix tree; Suffix; Compressed suffix array; Generalized suffix tree; Path (computing); String (physics); Bounded function; Time complexity","score_opus":0.02930179587211001,"score_gpt":0.28691854578231557,"score_spread":0.25761674991020556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415312698","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057667896,0.00084742793,0.93158656,0.00028610663,0.00011771695,0.00015961361,0.0007573062,0.003092779,0.0054845894],"genre_scores_gemma":[0.3333376,0.0012319353,0.6542239,0.00035625734,0.00021516324,0.00036991577,0.0031948732,0.00091053086,0.0061598704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902594,0.00014253042,0.00008264398,0.00022352001,0.00038964444,0.0001356941],"domain_scores_gemma":[0.99767166,0.0009781551,0.00020110817,0.00071497046,0.00033709293,0.00009707369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005971657,0.00078602985,0.0007476185,0.0011907343,0.0005411338,0.0015415311,0.0010239196,0.00074379856,0.004833821],"category_scores_gemma":[0.0058980626,0.00045605068,0.0009109284,0.0022010533,0.00081639184,0.0036082305,0.0017424254,0.0014360866,0.002851479],"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":[0.0006639406,0.00025390484,0.003438179,0.0006426228,0.00008616552,0.0005773391,0.0008678863,0.15085024,0.05927786,0.2194156,0.0165229,0.54740334],"study_design_scores_gemma":[0.000071909235,0.00020000347,0.0005194585,0.00008338037,0.000045426477,0.00040901924,0.0001598335,0.6996348,0.019631641,0.2612017,0.018010275,0.000032545715],"about_ca_topic_score_codex":0.0009868963,"about_ca_topic_score_gemma":0.0020195434,"teacher_disagreement_score":0.004833821,"about_ca_system_score_codex":0.0006925905,"about_ca_system_score_gemma":0.0012132977,"threshold_uncertainty_score":0.01617074},"labels":[],"label_agreement":null},{"id":"W4415434066","doi":"10.1007/s11009-025-10210-5","title":"Correction to: Distributions of the Number of Records and the Waiting time Distributions for the Rth Record","year":2025,"lang":"en","type":"article","venue":"Methodology And Computing In Applied Probability","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Distribution (mathematics); Gamma distribution; Order statistic; Probability distribution","score_opus":0.03477996213089051,"score_gpt":0.32052114980754,"score_spread":0.28574118767664947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415434066","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037409243,0.0008466819,0.0047939853,0.031160586,0.9539746,0.000037490514,0.0053262184,0.0014620466,0.002024291],"genre_scores_gemma":[0.051941033,0.007871538,0.035655554,0.06502618,0.51440686,0.00066214014,0.019585859,0.012563274,0.29228762],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99004143,0.0016299336,0.0022787598,0.0015898191,0.0037087959,0.00075124216],"domain_scores_gemma":[0.82921636,0.035880666,0.0063486816,0.015632702,0.10816272,0.0047589256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069306786,0.0027729361,0.0029723733,0.007350209,0.0032288881,0.005649605,0.004920245,0.0062951823,0.1173061],"category_scores_gemma":[0.17868638,0.0022699968,0.0025228816,0.006706747,0.0027867958,0.003785497,0.002897785,0.011398489,0.058399018],"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":[0.0000988823,0.000010534466,0.00017986394,0.00025830205,0.000036215184,0.00020574631,0.000058805643,0.00022189632,0.00012284023,0.002483961,0.9879287,0.0083944015],"study_design_scores_gemma":[0.00013449357,0.000039558046,0.0017393627,0.0004025909,0.000084827916,0.00087568647,0.000113722606,0.0016607803,0.00080417737,0.0056929914,0.9883513,0.00010049432],"about_ca_topic_score_codex":0.023538532,"about_ca_topic_score_gemma":0.021810634,"teacher_disagreement_score":0.1173061,"about_ca_system_score_codex":0.0056361766,"about_ca_system_score_gemma":0.008198034,"threshold_uncertainty_score":0.39242798},"labels":[],"label_agreement":null},{"id":"W4416035096","doi":"10.18653/v1/2025.findings-emnlp.110","title":"Test-Time Steering for Lossless Text Compression via Weighted Product of Experts","year":2025,"lang":"","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research; Vector Institute; University of British Columbia; Government of Canada","keywords":"Lossless compression; Leverage (statistics); Data compression; Compression (physics); Data compression ratio; Autoregressive model; Product (mathematics)","score_opus":0.01072432134418797,"score_gpt":0.26113564574445497,"score_spread":0.250411324400267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009781054,0.00010897129,0.98765045,0.00009659092,0.00002573375,0.00005724411,0.000047194048,0.0015273324,0.00070531794],"genre_scores_gemma":[0.4450266,0.00030721427,0.54348266,0.00046937194,0.00016357953,0.0003440651,0.0007074791,0.00060150493,0.0088974275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858594,0.00035450576,0.00008380283,0.0002971643,0.0005470867,0.00013153203],"domain_scores_gemma":[0.99575484,0.002134249,0.0002858976,0.00070771744,0.00089042116,0.00022682936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00226083,0.0013392946,0.0010514946,0.0007465346,0.0004416342,0.00088900485,0.0021962465,0.0013936012,0.0043882034],"category_scores_gemma":[0.010455333,0.0006138266,0.00070633285,0.0007664749,0.0012364214,0.0026187967,0.0025681965,0.0023306678,0.002119737],"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":[0.0008790485,0.0002580322,0.0014682013,0.00021802218,0.0000888224,0.00035052001,0.00027733418,0.25439358,0.04091827,0.013466579,0.0072782543,0.6804033],"study_design_scores_gemma":[0.000015483574,0.00006779556,0.00010290002,0.0000070040173,0.000007989278,0.00007940593,0.000016739325,0.98131645,0.012387793,0.0052009597,0.0007852724,0.000012175052],"about_ca_topic_score_codex":0.0019839457,"about_ca_topic_score_gemma":0.0027938732,"teacher_disagreement_score":0.0043882034,"about_ca_system_score_codex":0.00050572667,"about_ca_system_score_gemma":0.0012781535,"threshold_uncertainty_score":0.014680028},"labels":[],"label_agreement":null},{"id":"W4416053825","doi":"10.4230/lipics.cpm.2025.19","title":"The Trie Measure, Revisited","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Trie; Cardinality (data modeling); Encoding (memory); Monotone polygon; Binary number; Sequence (biology); Integer (computer science); Counterexample; Focus (optics)","score_opus":0.0478541446944817,"score_gpt":0.285105885156909,"score_spread":0.23725174046242728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416053825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120180234,0.012231346,0.68574554,0.008254671,0.0010063308,0.00020532095,0.0012314499,0.0012106106,0.1699345],"genre_scores_gemma":[0.73811907,0.0053444635,0.20933668,0.0020425932,0.0016610742,0.00054699776,0.0011219674,0.0012355645,0.04059161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655825,0.0010700892,0.00016091694,0.0008436484,0.0009354956,0.00043148],"domain_scores_gemma":[0.9915141,0.005181253,0.0007690214,0.0012139718,0.0007137702,0.00060790614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023163655,0.0013379591,0.0016592464,0.0023861795,0.002025134,0.004524302,0.0034315048,0.0029199438,0.013701755],"category_scores_gemma":[0.016465133,0.00079733715,0.001494182,0.0038651016,0.0047486667,0.011399833,0.003630013,0.0045465003,0.0022316363],"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":[0.000052580763,0.000042109124,0.00032586316,0.00014275074,0.000028435697,0.000060745428,0.00016053893,0.011894007,0.00096053025,0.96458465,0.004833995,0.016913831],"study_design_scores_gemma":[0.000032123917,0.00011458642,0.00027208473,0.000059421767,0.000034977664,0.00029006915,0.00015296567,0.08021047,0.0015518861,0.9020115,0.0152325155,0.00003734252],"about_ca_topic_score_codex":0.0013132202,"about_ca_topic_score_gemma":0.0011757195,"teacher_disagreement_score":0.013701755,"about_ca_system_score_codex":0.0028773411,"about_ca_system_score_gemma":0.0014371914,"threshold_uncertainty_score":0.045836985},"labels":[],"label_agreement":null},{"id":"W4416667301","doi":"10.4230/lipics.cpm.2026.16","title":"Merging RLBWTs Adaptively","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Merge (version control); Data compression; Uncompressed video; Compression (physics); Space (punctuation)","score_opus":0.02805261305278434,"score_gpt":0.2692146262349556,"score_spread":0.2411620131821713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416667301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08072849,0.000709105,0.89825284,0.00038506684,0.000485504,0.00018835628,0.0005267581,0.0071018515,0.011622098],"genre_scores_gemma":[0.33106983,0.0003731188,0.6472157,0.00043346686,0.00022305218,0.0003092535,0.0034134649,0.002180548,0.014781515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860567,0.0001539417,0.00010613021,0.00025841306,0.00069726666,0.00017859168],"domain_scores_gemma":[0.9983016,0.00037012706,0.00007682815,0.00070160313,0.0004752249,0.000074592695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072039367,0.0008917306,0.0008093528,0.0014971095,0.00058962364,0.0015378051,0.0012192804,0.0008896001,0.011862138],"category_scores_gemma":[0.0063157473,0.0004249887,0.0007972798,0.002009794,0.00076235016,0.0030978716,0.003330549,0.0014353188,0.0064378735],"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":[0.0010573122,0.00025111498,0.001979387,0.00029452288,0.00011605687,0.00075897947,0.00074809644,0.030196982,0.14818022,0.036269058,0.015661102,0.76448715],"study_design_scores_gemma":[0.00017856185,0.00055720547,0.002282406,0.00012890423,0.0001578264,0.0017022346,0.0009014694,0.50044066,0.33794677,0.07592446,0.07962094,0.00015865096],"about_ca_topic_score_codex":0.0011565187,"about_ca_topic_score_gemma":0.0015849167,"teacher_disagreement_score":0.011862138,"about_ca_system_score_codex":0.00040506397,"about_ca_system_score_gemma":0.00084078556,"threshold_uncertainty_score":0.039682746},"labels":[],"label_agreement":null},{"id":"W4417201807","doi":"10.1109/tcbbio.2025.3620157","title":"On the Size of the Neighborhoods of a Word","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Biology and Bioinformatics","topic":"Algorithms and Data Compression","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":"Unary operation; Word (group theory); Matching (statistics); Upper and lower bounds; Set (abstract data type)","score_opus":0.009262899016023196,"score_gpt":0.2510928146470164,"score_spread":0.24182991563099318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417201807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48740235,0.004339881,0.4673647,0.0031326467,0.00022623476,0.00017160502,0.0025839198,0.0008518003,0.033926833],"genre_scores_gemma":[0.91083074,0.0017766255,0.08078668,0.00029362238,0.00029664353,0.0003532263,0.0013387429,0.0002590242,0.00406473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830186,0.00030012484,0.00011674958,0.00046618667,0.0005452835,0.00026977496],"domain_scores_gemma":[0.97697306,0.018578883,0.0008476899,0.0017009347,0.0011829329,0.00071642903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013659676,0.0005510739,0.0011079963,0.0014775174,0.0010520894,0.0025087616,0.0022229785,0.0010240434,0.004287402],"category_scores_gemma":[0.024283689,0.0007286359,0.0006718875,0.0011420932,0.0024176545,0.007165624,0.0033903667,0.0018637177,0.0007428101],"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":[0.001265887,0.00025818168,0.017619796,0.0009480874,0.0001330894,0.00080847036,0.0017880833,0.16379733,0.05562924,0.61493903,0.013876358,0.1289364],"study_design_scores_gemma":[0.00006910061,0.0001849918,0.0054111453,0.00014722343,0.000081261715,0.00096017204,0.0004717826,0.48873907,0.02329781,0.47206047,0.008473263,0.00010370797],"about_ca_topic_score_codex":0.0010888807,"about_ca_topic_score_gemma":0.0013507637,"teacher_disagreement_score":0.004287402,"about_ca_system_score_codex":0.001335981,"about_ca_system_score_gemma":0.00085991854,"threshold_uncertainty_score":0.014342725},"labels":[],"label_agreement":null},{"id":"W48700190","doi":"10.1023/a:1005292125553","title":"Efficient Regular Polygon Dissections","year":2000,"lang":"en","type":"article","venue":"Geometriae Dedicata","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Combinatorics; Mathematics; Polygon (computer graphics); Square (algebra); Geometry; Computer science","score_opus":0.008109718669203689,"score_gpt":0.2266723744751535,"score_spread":0.21856265580594983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W48700190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14400627,0.0010668999,0.79170847,0.00052190997,0.0001936982,0.00017671408,0.00065219775,0.0025341809,0.059139725],"genre_scores_gemma":[0.49120992,0.0011431993,0.47064304,0.00015710275,0.00011306519,0.00012579098,0.0013642344,0.0007546145,0.03448906],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940515,0.000067813635,0.00003720675,0.0001090861,0.00029996375,0.00008084572],"domain_scores_gemma":[0.9993814,0.00022730014,0.000042724318,0.00024016199,0.000070242066,0.00003800349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033437103,0.00075614674,0.0008164343,0.0014877624,0.00050674553,0.0014509445,0.000940709,0.00051895453,0.012701504],"category_scores_gemma":[0.0018584126,0.0004432643,0.0005034176,0.0015393947,0.0006670341,0.002135405,0.0028208927,0.0011096579,0.0030958182],"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":[0.00044453156,0.00014970105,0.000934993,0.00026795047,0.000046554243,0.0003315696,0.00044649024,0.0487956,0.029422808,0.20321901,0.01750714,0.6984337],"study_design_scores_gemma":[0.00019293625,0.00033632768,0.0012888792,0.00012843595,0.00009033685,0.0014539614,0.0005276915,0.43776223,0.058393493,0.41243538,0.087325886,0.0000644993],"about_ca_topic_score_codex":0.00033922886,"about_ca_topic_score_gemma":0.00095280475,"teacher_disagreement_score":0.012701504,"about_ca_system_score_codex":0.00055211433,"about_ca_system_score_gemma":0.00032316003,"threshold_uncertainty_score":0.04249078},"labels":[],"label_agreement":null},{"id":"W49738050","doi":"10.1007/978-3-319-08783-2_9","title":"On the Smoothed Heights of Trie and Patricia Index Trees","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Trie; Combinatorics; String (physics); Bernoulli's principle; Tree (set theory); Binary tree; Set (abstract data type); Mathematics; Computer science; Discrete mathematics; Algorithm; Data structure; Physics; Mathematical physics","score_opus":0.012151331383586907,"score_gpt":0.22109468771910346,"score_spread":0.20894335633551656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W49738050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26520628,0.0050547877,0.6458998,0.0020453283,0.0008566819,0.0001167703,0.0011637936,0.0030001712,0.0766564],"genre_scores_gemma":[0.7873022,0.0021813512,0.17968068,0.0005059744,0.00080902386,0.00011139647,0.0014602287,0.0010728594,0.026876338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940395,0.000106593456,0.000031674153,0.00010356477,0.00023820704,0.000116031304],"domain_scores_gemma":[0.9971631,0.0013324148,0.00023642957,0.0006880903,0.00033984773,0.0002400438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084135664,0.00044488537,0.00095361855,0.0023739259,0.0011052355,0.0022377688,0.0015366363,0.00093907875,0.009506713],"category_scores_gemma":[0.009655345,0.0006242087,0.0005323031,0.0026690594,0.0016643624,0.0038780167,0.0020693147,0.0026976678,0.0022647209],"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":[0.00026010897,0.00007130126,0.0013917234,0.00014119643,0.000035111327,0.00015351421,0.0006550848,0.025329374,0.0054887594,0.8007533,0.015217191,0.15050338],"study_design_scores_gemma":[0.000040425253,0.00007355905,0.0013141067,0.000049088543,0.000030018731,0.0003277034,0.0002412893,0.12179767,0.0020891689,0.8553288,0.018663878,0.000044370903],"about_ca_topic_score_codex":0.0016523933,"about_ca_topic_score_gemma":0.002636458,"teacher_disagreement_score":0.009506713,"about_ca_system_score_codex":0.00083928474,"about_ca_system_score_gemma":0.00052865973,"threshold_uncertainty_score":0.03180307},"labels":[],"label_agreement":null},{"id":"W571300759","doi":"10.1007/s11047-015-9502-9","title":"Pseudo-inversion: closure properties and decidability","year":2015,"lang":"en","type":"article","venue":"Natural Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Decidability; Nondeterministic algorithm; Inversion (geology); Context-free language; Iterated function; Computer science; Regular language; Formal language; Mathematics; Discrete mathematics; Algorithm; Theoretical computer science; Automaton; Rule-based machine translation; Artificial intelligence","score_opus":0.04490257803118486,"score_gpt":0.25005473572062437,"score_spread":0.2051521576894395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W571300759","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1149091,0.0015811691,0.83364135,0.011560582,0.00045087194,0.00029748143,0.0013132959,0.0013264236,0.034919724],"genre_scores_gemma":[0.79544985,0.0011051676,0.18824203,0.002280939,0.00093397894,0.0005710102,0.0023294026,0.0007425877,0.008345039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99129874,0.0026088413,0.0008783746,0.002085892,0.0019982858,0.0011299063],"domain_scores_gemma":[0.92313325,0.065931715,0.0015456835,0.0049893274,0.003346164,0.0010537993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0085286675,0.0009602682,0.0013505014,0.0015720984,0.0032617315,0.007185861,0.003144834,0.0025644263,0.0067256074],"category_scores_gemma":[0.04148904,0.0015167991,0.004410306,0.002155377,0.008810256,0.022585554,0.005017354,0.010602494,0.00066112005],"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":[0.00019991951,0.00019785587,0.0012713724,0.00025914598,0.000045885594,0.0002893012,0.0010102999,0.0042677387,0.0013697856,0.9670853,0.003384084,0.020619426],"study_design_scores_gemma":[0.00004961009,0.00001420296,0.00009909749,0.000025490417,0.000026642287,0.00014974379,0.00013767616,0.012419964,0.0014155875,0.984055,0.0015887695,0.000018367939],"about_ca_topic_score_codex":0.0030314068,"about_ca_topic_score_gemma":0.0028058966,"teacher_disagreement_score":0.0085286675,"about_ca_system_score_codex":0.0027550862,"about_ca_system_score_gemma":0.004034679,"threshold_uncertainty_score":0.045104444},"labels":[],"label_agreement":null},{"id":"W610025348","doi":"10.1007/978-3-319-13075-0_43","title":"Tradeoff Between Label Space and Auxiliary Space for Representation of Equivalence Classes","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Equivalence class (music); Equivalence (formal languages); Space (punctuation); Data structure; Combinatorics; Representation (politics); Discrete mathematics; Set (abstract data type); Quotient space (topology); Mathematics; Equivalence relation; Class (philosophy); Computer science; Artificial intelligence","score_opus":0.03940161434373402,"score_gpt":0.2984906770929197,"score_spread":0.2590890627491857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W610025348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06123121,0.0017823518,0.9181419,0.0016398121,0.000115485105,0.00015439148,0.00088841846,0.0019545308,0.014091915],"genre_scores_gemma":[0.58852565,0.002101754,0.39581293,0.000538976,0.0003702177,0.0005364392,0.0021001603,0.0010936734,0.008920171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956618,0.0021122831,0.00022101308,0.00048161036,0.0012080969,0.00031530394],"domain_scores_gemma":[0.9796417,0.012396308,0.00044290247,0.0054310667,0.0016073796,0.00048065378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032357264,0.00086767465,0.0016211115,0.0015985842,0.0009844501,0.004988263,0.0026856689,0.0019904408,0.016211083],"category_scores_gemma":[0.022630487,0.0005524992,0.0008521253,0.0031268052,0.0017836415,0.011675687,0.0046507176,0.0030923162,0.0029838954],"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":[0.0017469807,0.00040597876,0.0010313052,0.0006054274,0.000055324374,0.00011139663,0.00063033856,0.045130398,0.020248182,0.359142,0.011593792,0.55929893],"study_design_scores_gemma":[0.0001385992,0.00032559,0.00088284095,0.00018071108,0.00007853562,0.0003651582,0.00042814185,0.4491174,0.015410083,0.52091974,0.012093304,0.000059922044],"about_ca_topic_score_codex":0.0008462963,"about_ca_topic_score_gemma":0.0012770924,"teacher_disagreement_score":0.016211083,"about_ca_system_score_codex":0.0013531897,"about_ca_system_score_gemma":0.0011823192,"threshold_uncertainty_score":0.054231524},"labels":[],"label_agreement":null},{"id":"W61744817","doi":"10.1007/978-3-642-33293-7_24","title":"Enumerating Neighbour and Closest Strings","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Parameterized complexity; String (physics); Alphabet; Combinatorics; Mathematics; Enumeration; Constant (computer programming); Running time; String searching algorithm; Upper and lower bounds; Commentz-Walter algorithm; Discrete mathematics; Algorithm; Pattern matching; Computer science; Mathematical analysis","score_opus":0.014964112829556363,"score_gpt":0.23735948376744867,"score_spread":0.2223953709378923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W61744817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03712713,0.0023284499,0.9063199,0.0007342237,0.0006542455,0.00015332561,0.0013255979,0.002037568,0.049319666],"genre_scores_gemma":[0.13912313,0.0020168836,0.80889183,0.00037786053,0.00036141012,0.0002536856,0.005223375,0.001161952,0.04258988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974221,0.00044641364,0.0002476514,0.0005221768,0.0011921877,0.00016941542],"domain_scores_gemma":[0.9942339,0.0031569109,0.00021561208,0.0015739511,0.00066831574,0.0001512349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011145847,0.00074476347,0.0018544226,0.003649883,0.0014766017,0.002906355,0.0031932858,0.0018403358,0.014839795],"category_scores_gemma":[0.015699847,0.0007651592,0.0013263362,0.0057576774,0.001696462,0.007629975,0.004546707,0.002318524,0.006457827],"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":[0.00029245942,0.00010977477,0.0011034493,0.00075072446,0.000056478064,0.00019296653,0.0006450007,0.023474107,0.005052766,0.3668787,0.022343373,0.57910013],"study_design_scores_gemma":[0.000028859971,0.000067751025,0.0003606769,0.0001989178,0.00005230647,0.00082203624,0.00022795296,0.08451544,0.0058096643,0.8707556,0.03711236,0.000048396712],"about_ca_topic_score_codex":0.0008306974,"about_ca_topic_score_gemma":0.0013560742,"teacher_disagreement_score":0.014839795,"about_ca_system_score_codex":0.0010272763,"about_ca_system_score_gemma":0.0009746133,"threshold_uncertainty_score":0.049644053},"labels":[],"label_agreement":null},{"id":"W65034588","doi":"10.1007/978-1-4939-2864-4_628","title":"Intersections of Inverted Lists","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.013912597166559282,"score_gpt":0.2344966190011312,"score_spread":0.2205840218345719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W65034588","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030399283,0.008885241,0.45933887,0.0014157767,0.0012495347,0.0002547885,0.0047943164,0.0053625833,0.48829958],"genre_scores_gemma":[0.2687132,0.011418675,0.41665706,0.0008323195,0.0017216909,0.0005008992,0.017511148,0.0029063458,0.27973866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985678,0.00013482224,0.000116192125,0.0003170017,0.0007241586,0.00014008791],"domain_scores_gemma":[0.998324,0.00052000023,0.0001483431,0.00035444656,0.0005679621,0.000085308624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046563853,0.0008021482,0.0008501674,0.0048433314,0.0019577136,0.0050326665,0.0017559981,0.0009210864,0.045626912],"category_scores_gemma":[0.003709799,0.0008672713,0.0007839301,0.006525429,0.0013923866,0.008572126,0.002988035,0.00203339,0.01795389],"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":[0.000086506916,0.000037170088,0.0004230939,0.00030556787,0.000017828079,0.00015209579,0.00027421952,0.0016348565,0.002125642,0.7094122,0.033137046,0.25239375],"study_design_scores_gemma":[0.000014277296,0.000053570333,0.00030970573,0.00015741127,0.000029657509,0.0008025195,0.00023052367,0.008159302,0.0078573385,0.70582414,0.27652088,0.000040765506],"about_ca_topic_score_codex":0.00071075704,"about_ca_topic_score_gemma":0.00090301473,"teacher_disagreement_score":0.045626912,"about_ca_system_score_codex":0.0011708444,"about_ca_system_score_gemma":0.0014013255,"threshold_uncertainty_score":0.15263724},"labels":[],"label_agreement":null},{"id":"W65241029","doi":"10.1007/978-1-84628-726-8_10","title":"Arabic Cheque Processing System: Issues and Future Trends","year":2007,"lang":"en","type":"book-chapter","venue":"Advances in pattern recognition","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Cheque; Arabic; Computer science; World Wide Web; Linguistics; Philosophy","score_opus":0.023733559794887955,"score_gpt":0.28366393877264096,"score_spread":0.259930378977753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W65241029","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063335426,0.09028014,0.5032627,0.018183665,0.0071423575,0.0006471866,0.0022850216,0.020936813,0.29392663],"genre_scores_gemma":[0.118435115,0.04244323,0.42518398,0.003688461,0.0034750158,0.00031669537,0.0040500667,0.001616837,0.4007906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997285,0.000049989536,0.000019844792,0.000050794435,0.00012339489,0.000027398093],"domain_scores_gemma":[0.99867517,0.00019891295,0.000022716062,0.000110509296,0.00089848356,0.000094175935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010587783,0.0006699143,0.00061616884,0.0011516348,0.00050476304,0.002672134,0.0015211332,0.00128602,0.042475596],"category_scores_gemma":[0.0013689193,0.00021103895,0.00031789346,0.001431081,0.0006383446,0.0027316604,0.0003825544,0.0008767278,0.020055631],"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":[0.00031840242,0.0001239705,0.00082097144,0.0002976755,0.000020274794,0.0001103458,0.00014242691,0.0007113845,0.012705188,0.009854994,0.06951574,0.9053786],"study_design_scores_gemma":[0.00006185216,0.00034866895,0.002696158,0.00019976826,0.000104478146,0.0011847065,0.0004856154,0.03750057,0.02906695,0.012911264,0.9153354,0.000104546125],"about_ca_topic_score_codex":0.003441633,"about_ca_topic_score_gemma":0.00375518,"teacher_disagreement_score":0.042475596,"about_ca_system_score_codex":0.0006916994,"about_ca_system_score_gemma":0.0011126524,"threshold_uncertainty_score":0.14209509},"labels":[],"label_agreement":null},{"id":"W6891614947","doi":"10.4230/lipics.wabi.2025.3","title":"Approximability of Longest Run Subsequence and Complementary Minimization Problems","year":2025,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Subsequence; Substring; Longest increasing subsequence; Longest common subsequence problem; String (physics); Symbol (formal)","score_opus":0.014477793212230188,"score_gpt":0.2575422535346263,"score_spread":0.2430644603223961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891614947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13720341,0.0022986538,0.8472252,0.0017975731,0.0002536649,0.00014911068,0.0008722727,0.0016793727,0.008520677],"genre_scores_gemma":[0.68050694,0.0014194807,0.30477944,0.0006701217,0.00057305425,0.0003964912,0.0031332492,0.00086595974,0.0076552574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964079,0.0009561551,0.00020391567,0.0012365469,0.0007014306,0.0004940077],"domain_scores_gemma":[0.98712337,0.010275286,0.0008633625,0.0007507396,0.0005968451,0.00039042372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027441944,0.0022341933,0.00236447,0.0011249679,0.0008067475,0.0022206297,0.0031216922,0.0019783108,0.004590579],"category_scores_gemma":[0.020913418,0.0007720463,0.0025993143,0.0015908221,0.0019665388,0.0049633635,0.002384761,0.0034518302,0.00070919713],"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":[0.0010020809,0.0005794253,0.0029940382,0.0013837924,0.0003718012,0.00042232109,0.00046126256,0.77553546,0.004430923,0.12820667,0.008813028,0.07579909],"study_design_scores_gemma":[0.00007622171,0.00012456393,0.00023508725,0.000036111534,0.000050445244,0.00014446996,0.000057895686,0.85248274,0.0011845492,0.14429586,0.0012952965,0.0000167343],"about_ca_topic_score_codex":0.0031518242,"about_ca_topic_score_gemma":0.0024193907,"teacher_disagreement_score":0.004590579,"about_ca_system_score_codex":0.001857066,"about_ca_system_score_gemma":0.002282409,"threshold_uncertainty_score":0.0153570175},"labels":[],"label_agreement":null},{"id":"W6891678007","doi":"10.4230/lipics.cpm.2023.2","title":"Approximation Algorithms for the Longest Run Subsequence Problem","year":2023,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Subsequence; Longest increasing subsequence; Longest common subsequence problem; String (physics); Symbol (formal); Sequence (biology); Bounded function","score_opus":0.036994911951309994,"score_gpt":0.2847968448206783,"score_spread":0.2478019328693683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891678007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03891581,0.0027421745,0.9479781,0.0010936761,0.00021739675,0.00016204795,0.00064997113,0.0029183768,0.0053224005],"genre_scores_gemma":[0.33562753,0.002181089,0.6511598,0.00056070957,0.0005103766,0.00055181736,0.0036196506,0.00085570355,0.004933334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964455,0.0008280355,0.0002989685,0.0009567731,0.0008987036,0.0005719777],"domain_scores_gemma":[0.991823,0.0055776206,0.0006247544,0.0012063291,0.000536359,0.00023192438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025610232,0.0022382725,0.002495346,0.0019495265,0.0010393759,0.002491438,0.0035742603,0.002019578,0.004417579],"category_scores_gemma":[0.016167574,0.00077960675,0.0018213106,0.0038974688,0.00128828,0.005577809,0.002234324,0.003631724,0.0015602197],"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":[0.0010906335,0.0005875996,0.0028473337,0.0009999857,0.0003169741,0.00033287893,0.0005100078,0.6388187,0.005301556,0.072157115,0.017834162,0.25920302],"study_design_scores_gemma":[0.00011079678,0.00011184236,0.00023882513,0.000044607536,0.000042986783,0.0001694957,0.00006872059,0.9041402,0.0015434703,0.09103243,0.0024777853,0.000018835171],"about_ca_topic_score_codex":0.0030405717,"about_ca_topic_score_gemma":0.0028934486,"teacher_disagreement_score":0.004417579,"about_ca_system_score_codex":0.002106957,"about_ca_system_score_gemma":0.0026412045,"threshold_uncertainty_score":0.015287042},"labels":[],"label_agreement":null},{"id":"W6898513472","doi":"10.57745/makf40","title":"WW_Marginales_Means.rds","year":2025,"lang":"en","type":"dataset","venue":"Recherche Data Gouv France","topic":"Algorithms and Data Compression","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":"Canadian Nautical Research Society","funders":"","keywords":"Terminal (telecommunication); Product (mathematics); Term (time)","score_opus":0.17328423002437526,"score_gpt":0.3931723481725965,"score_spread":0.21988811814822123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6898513472","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007887059,0.00011386228,0.00044590025,0.00006561267,0.00009625234,0.000029885252,0.9956197,0.0020952,0.0007448541],"genre_scores_gemma":[0.0016630604,0.00006264338,0.0016565603,0.000051110044,0.0000219319,0.00018857582,0.9948401,0.00041276906,0.0011033287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979747,0.00034549864,0.00019860781,0.00081288844,0.00038650972,0.00028189045],"domain_scores_gemma":[0.9969952,0.0010796147,0.00016687688,0.0010456566,0.0005926312,0.00012011728],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026193634,0.0035592066,0.0018474347,0.0037072122,0.0013124701,0.002983626,0.003753534,0.0021489493,0.066629745],"category_scores_gemma":[0.009638662,0.0009189892,0.0030713768,0.004582278,0.0008313468,0.0011871487,0.0018918297,0.002527892,0.08757752],"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":[0.0002481023,0.00007831658,0.0025039553,0.0011357793,0.00016783537,0.00003892842,0.000063735504,0.00075946824,0.00082484086,0.0007065355,0.9850091,0.008463461],"study_design_scores_gemma":[0.0008092365,0.00008453425,0.013049242,0.00024327933,0.00013814565,0.00016309855,0.00019491471,0.0018785218,0.0027222815,0.0031290727,0.9775054,0.00008220875],"about_ca_topic_score_codex":0.015995594,"about_ca_topic_score_gemma":0.032842036,"teacher_disagreement_score":0.93337023,"about_ca_system_score_codex":0.0014038366,"about_ca_system_score_gemma":0.0023595507,"threshold_uncertainty_score":0.22289866},"labels":[],"label_agreement":null},{"id":"W6910360012","doi":"10.4230/lipics.wabi.2024.10","title":"b-move: Faster Bidirectional Character Extensions in a Run-Length Compressed Index","year":2024,"lang":"en","type":"article","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"National Institutes of Health; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"RefSeq; Search engine indexing; Scalability; Lossless compression; Pattern matching; Matching (statistics); Character (mathematics); Data compression; Overhead (engineering)","score_opus":0.015642449668003468,"score_gpt":0.22136533537671757,"score_spread":0.2057228857087141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6910360012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102066785,0.003524058,0.6737766,0.0007731688,0.00080737023,0.00068636937,0.010520447,0.181475,0.026370121],"genre_scores_gemma":[0.23047955,0.0007883207,0.71271205,0.0007663442,0.00018198763,0.00078344916,0.02910982,0.009908472,0.015269995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986546,0.00012382386,0.00016285904,0.00027666768,0.0005968208,0.00018518062],"domain_scores_gemma":[0.99813336,0.0003651284,0.00014724409,0.0008230383,0.00039476855,0.0001365588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078190985,0.0014701434,0.001041509,0.0016499589,0.000782455,0.0020399352,0.0032178008,0.00096787227,0.0112923635],"category_scores_gemma":[0.005388157,0.0007454338,0.001004658,0.0031432915,0.0007198698,0.005240957,0.003797422,0.001322732,0.009632533],"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":[0.0031039014,0.00060380425,0.0049392325,0.0012326961,0.00019081803,0.00065470487,0.0010501259,0.013366315,0.119435415,0.03471238,0.13561307,0.68509746],"study_design_scores_gemma":[0.0011471816,0.0013447208,0.0031155045,0.0003860918,0.00021383163,0.0017707648,0.0009117895,0.39495555,0.21309179,0.041884046,0.34075075,0.0004278968],"about_ca_topic_score_codex":0.004056083,"about_ca_topic_score_gemma":0.0059825783,"teacher_disagreement_score":0.0112923635,"about_ca_system_score_codex":0.00083994004,"about_ca_system_score_gemma":0.0014308671,"threshold_uncertainty_score":0.03777671},"labels":[],"label_agreement":null},{"id":"W6910493891","doi":"10.4230/lipics.cpm.2021.15","title":"Data Structures for Categorical Path Counting Queries","year":2021,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Categorical variable; Path (computing); Range query (database); Tree (set theory); Data structure; Range (aeronautics); Tree structure; Matrix (chemical analysis)","score_opus":0.03914755067280152,"score_gpt":0.2941442570978527,"score_spread":0.2549967064250512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6910493891","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043476935,0.00070866616,0.9103114,0.0023553777,0.00022052959,0.00059368805,0.012226876,0.024441611,0.0056648515],"genre_scores_gemma":[0.23205997,0.00036070542,0.7385356,0.00084760966,0.00022374163,0.0016269109,0.0190595,0.0020630148,0.005222898],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943388,0.0008250211,0.0011747304,0.0012358533,0.001824463,0.0006011941],"domain_scores_gemma":[0.97848004,0.007013962,0.0014788737,0.009777076,0.0025737295,0.00067629333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030465862,0.0014280777,0.0021653108,0.0022502942,0.0017878092,0.0048938696,0.004872723,0.002460315,0.013604023],"category_scores_gemma":[0.025090568,0.0013038589,0.0018650086,0.007890955,0.0016039739,0.01861083,0.005645288,0.003756843,0.005288049],"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":[0.0029524355,0.0007622375,0.0087842895,0.0015517158,0.00017340755,0.0005547306,0.0014726208,0.057893515,0.03744151,0.30671716,0.09689537,0.48480102],"study_design_scores_gemma":[0.00046608172,0.00055691885,0.001430599,0.00022053334,0.00011354347,0.00075353164,0.0008684696,0.42384344,0.035006657,0.45222968,0.084292956,0.00021754457],"about_ca_topic_score_codex":0.0027618732,"about_ca_topic_score_gemma":0.003975754,"teacher_disagreement_score":0.013604023,"about_ca_system_score_codex":0.0030367654,"about_ca_system_score_gemma":0.0029980722,"threshold_uncertainty_score":0.045509994},"labels":[],"label_agreement":null},{"id":"W6921022441","doi":"10.6084/m9.figshare.26596100","title":"Additional file 6 of Matchtigs: minimum plain text representation of k-mer sets","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Representation (politics); Set (abstract data type); Plain text; Window (computing)","score_opus":0.030383551008181395,"score_gpt":0.2753442938230059,"score_spread":0.2449607428148245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921022441","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001330061,0.0003958614,0.0011089694,0.000717168,0.0004556,0.00017873688,0.9894456,0.0027609963,0.0048040505],"genre_scores_gemma":[0.0047923625,0.0012665695,0.0087747695,0.0016897179,0.00093263347,0.0014004373,0.93865716,0.0066745374,0.035811864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997869,0.00034431348,0.0003670452,0.0005078936,0.0007094738,0.00020222295],"domain_scores_gemma":[0.9674457,0.018897088,0.0018262854,0.0035203984,0.0071256906,0.0011848185],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034379011,0.0013932952,0.002286489,0.005571655,0.0013154674,0.0036425397,0.003829963,0.0020368584,0.8934869],"category_scores_gemma":[0.05068258,0.0012248391,0.0017725747,0.0073354826,0.00048895885,0.004480021,0.0020810915,0.001655892,0.47136983],"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":[0.00015246915,0.0000141322635,0.00017304078,0.0020206599,0.000026285545,0.000024038805,0.000019220171,0.00006994234,0.00013176532,0.0004565241,0.98891187,0.00800007],"study_design_scores_gemma":[0.000531782,0.000067759414,0.0023787254,0.001343265,0.00009079775,0.0002471823,0.00006104663,0.0002537666,0.00088776293,0.003860226,0.9902113,0.0000663782],"about_ca_topic_score_codex":0.0038629598,"about_ca_topic_score_gemma":0.0063135657,"teacher_disagreement_score":0.8934869,"about_ca_system_score_codex":0.0017048467,"about_ca_system_score_gemma":0.0029700198,"threshold_uncertainty_score":0.15192801},"labels":[],"label_agreement":null},{"id":"W6921126819","doi":"10.6084/m9.figshare.26596085.v1","title":"Additional file 1 of Matchtigs: minimum plain text representation of k-mer sets","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Focus (optics); Representation (politics); Window (computing); Simple (philosophy)","score_opus":0.031034960986225924,"score_gpt":0.275710049284035,"score_spread":0.24467508829780904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921126819","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005733221,0.00004260944,0.0025762124,0.00015553634,0.00009815197,0.00011097368,0.9888276,0.005789904,0.0018257658],"genre_scores_gemma":[0.0074254517,0.00006905132,0.013574941,0.0003313738,0.00009024131,0.0007855543,0.9654006,0.0070816493,0.005241071],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984653,0.00016205976,0.00016346546,0.00048536074,0.0005194649,0.00020445834],"domain_scores_gemma":[0.9901799,0.006101435,0.00038887333,0.0018472382,0.0011489699,0.00033362934],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016535658,0.0021598048,0.0020037156,0.0015463282,0.0014228061,0.0019891604,0.0036524378,0.0015714616,0.78906524],"category_scores_gemma":[0.02233517,0.0011405244,0.0012150795,0.0036848828,0.00052534544,0.0028941624,0.0016209702,0.0018638133,0.2954627],"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":[0.0006705154,0.0001708217,0.0007894242,0.001939053,0.000057194262,0.00004678136,0.00003848625,0.0007690595,0.0016265897,0.0010612626,0.98211205,0.010718663],"study_design_scores_gemma":[0.005903189,0.00083561894,0.0102922525,0.0010001747,0.0002527485,0.00091444294,0.00026485036,0.018073147,0.024905363,0.026465079,0.91078633,0.00030678642],"about_ca_topic_score_codex":0.0023891951,"about_ca_topic_score_gemma":0.004644246,"teacher_disagreement_score":0.78906524,"about_ca_system_score_codex":0.0011151651,"about_ca_system_score_gemma":0.001792231,"threshold_uncertainty_score":0.3008728},"labels":[],"label_agreement":null},{"id":"W6925550645","doi":"10.18712/nsd-nsd2584-2-v2","title":"Travel and Holiday Survey, 2017, 2nd quarter","year":2019,"lang":"en","type":"dataset","venue":"NSD – Norsk senter for forskningsdata","topic":"Algorithms and Data Compression","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":"","keywords":"Quarter (Canadian coin); The Internet; Norwegian; Work (physics); Internet access; Public health","score_opus":0.04568687940054511,"score_gpt":0.2956417376834944,"score_spread":0.24995485828294928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925550645","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004593735,0.000046321442,0.00003283583,0.000048848968,0.00003596062,0.000013041151,0.9989083,0.0000609916,0.00039429814],"genre_scores_gemma":[0.00071538094,0.0000487258,0.00011609115,0.000023002154,0.000010413634,0.00006776285,0.9983063,0.000022667211,0.00068962685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988599,0.00019211137,0.00019720393,0.0002962799,0.000270945,0.00018360702],"domain_scores_gemma":[0.9979779,0.00027173886,0.00026511058,0.00031063694,0.0009682141,0.00020650969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333179,0.0016567222,0.0011355538,0.0026072776,0.0006580449,0.0017510843,0.0017989024,0.0008795757,0.026093215],"category_scores_gemma":[0.0063236402,0.0005657352,0.0008582416,0.005495661,0.0003222358,0.0011123483,0.0013339155,0.0013025922,0.040027216],"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":[0.00009795349,0.000028533588,0.0033687945,0.00035494915,0.000026967566,0.00002064735,0.000034005905,0.00015329848,0.000057597725,0.00022665836,0.99369365,0.0019368314],"study_design_scores_gemma":[0.0004358616,0.000061671104,0.0590232,0.0006147718,0.00005996433,0.00012129289,0.0006758129,0.00081683305,0.00045213086,0.00062275573,0.9370555,0.000060262784],"about_ca_topic_score_codex":0.083434865,"about_ca_topic_score_gemma":0.10147502,"teacher_disagreement_score":0.083434865,"about_ca_system_score_codex":0.001724047,"about_ca_system_score_gemma":0.0025121265,"threshold_uncertainty_score":0.16589844},"labels":[],"label_agreement":null},{"id":"W6926550038","doi":"10.25318/9810001101-eng","title":"Population and dwelling counts: Canada and population centres","year":2022,"lang":"en","type":"dataset","venue":"Statistics Canada Dissemination","topic":"Algorithms and Data Compression","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":"","keywords":"Population; Population density; Table (database); Rural population; Census","score_opus":0.004613235186051738,"score_gpt":0.22864946876547812,"score_spread":0.22403623357942637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926550038","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004340063,0.00004310919,0.00002151064,0.000057197933,0.0000131700235,0.000009310249,0.9986112,0.00007148147,0.00073900324],"genre_scores_gemma":[0.0023378457,0.00013006636,0.00016077266,0.00004183683,0.0000073608244,0.000047394,0.9959791,0.000036298447,0.001259285],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988795,0.000041559186,0.000108207285,0.00019366754,0.00046840982,0.0003086348],"domain_scores_gemma":[0.99356997,0.00039281906,0.00034829366,0.00038446634,0.004835422,0.0004689209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048365656,0.0013096799,0.0012629481,0.0057898704,0.0013064538,0.002276813,0.0018449366,0.0008177267,0.032175045],"category_scores_gemma":[0.007297159,0.0005239547,0.0010239981,0.020446405,0.00047047986,0.00087849976,0.0011819375,0.0020032742,0.019247077],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005684417,0.000019205638,0.008119576,0.00029696574,0.000029137676,0.000018273513,0.00003879527,0.00049757474,0.00004090999,0.0005545649,0.98578656,0.004541516],"study_design_scores_gemma":[0.00015795858,0.000016846247,0.11648018,0.0005150517,0.000039478462,0.00011283172,0.0004659585,0.0016229728,0.00044962135,0.0008554513,0.87920064,0.00008290503],"about_ca_topic_score_codex":0.93408084,"about_ca_topic_score_gemma":0.9441493,"teacher_disagreement_score":0.06591916,"about_ca_system_score_codex":0.010325093,"about_ca_system_score_gemma":0.023046417,"threshold_uncertainty_score":0.13261467},"labels":[],"label_agreement":null},{"id":"W6929546648","doi":"10.5167/uzh-126446","title":"Analysis and dissipation of the antiparasitic agent ivermectin in cattle dung under different field conditions","year":2016,"lang":"en","type":"article","venue":"Zurich Open Repository and Archive (University of Zurich)","topic":"Algorithms and Data Compression","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":"","keywords":"Ivermectin; Extraction (chemistry); Antiparasitic agent; Solid phase extraction; Pesticide; Molluscicide","score_opus":0.009532386987704974,"score_gpt":0.22444513756927217,"score_spread":0.2149127505815672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929546648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9986694,0.00016403191,0.00078732613,0.00000713721,0.0000030718106,0.0000046469386,0.00013064538,0.00001622493,0.00021746682],"genre_scores_gemma":[0.9937196,0.0004102489,0.0039784177,0.000018442714,0.0000039171546,0.000017533399,0.00076305127,0.000013490226,0.0010752772],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99987376,0.00001643208,0.000005729863,0.000032688607,0.000047887792,0.000023471543],"domain_scores_gemma":[0.9998518,0.000046697394,0.000033626657,0.000011008856,0.000045985344,0.000010784154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013297802,0.00021746045,0.00022224424,0.0005790187,0.00021775215,0.00035540288,0.00014004824,0.0002501295,0.0005041379],"category_scores_gemma":[0.0002981349,0.00010280427,0.00013476769,0.0005045848,0.0001765469,0.0001560008,0.00012368413,0.00014849217,0.0000979377],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057966134,0.00007833638,0.019843712,0.00009075816,0.000038241946,0.00011171624,0.00012141704,0.00065038505,0.9508292,0.000019099312,0.000080830985,0.027556656],"study_design_scores_gemma":[0.000017480932,0.0009123118,0.39291033,0.000011041648,0.00005512811,0.00035309067,0.00031798639,0.005524961,0.5984369,0.000040345316,0.0014009586,0.000019533365],"about_ca_topic_score_codex":0.005846839,"about_ca_topic_score_gemma":0.0075626113,"teacher_disagreement_score":0.005846839,"about_ca_system_score_codex":0.0003657727,"about_ca_system_score_gemma":0.000111599555,"threshold_uncertainty_score":0.011625588},"labels":[],"label_agreement":null},{"id":"W6931119086","doi":"10.5281/zenodo.15748796","title":"Spiophanes japonicum Imajima 1991","year":2003,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"","keywords":"Bass (fish); Single specimen; Type specimen; Taxonomy (biology)","score_opus":0.027015919039426635,"score_gpt":0.2373469656746031,"score_spread":0.21033104663517646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931119086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56148636,0.00654645,0.0029048421,0.00052003574,0.00024908732,0.00025258944,0.0018679913,0.0003322132,0.42584047],"genre_scores_gemma":[0.9537229,0.003350223,0.0040953984,0.0002799791,0.00010293051,0.00009482521,0.0026022342,0.000054813096,0.03569673],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9999161,0.0000054993434,0.000009428787,0.000022098995,0.000026331802,0.000020555513],"domain_scores_gemma":[0.9999399,0.000004308407,0.000021752212,0.000005370399,0.000015020431,0.000013659678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009123385,0.0005251509,0.00025326043,0.0008606813,0.0015485407,0.0003496389,0.00032758305,0.00022506286,0.01054212],"category_scores_gemma":[0.0001820695,0.00019177167,0.00013380068,0.0011319607,0.0003793057,0.00082450255,0.0008732063,0.0006756886,0.0022906524],"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":[0.00067017815,0.00037404906,0.04588622,0.0019694476,0.00009446012,0.007332538,0.0056565353,0.0008880235,0.091781646,0.011743023,0.029194698,0.80440915],"study_design_scores_gemma":[0.00009981696,0.0003600702,0.45588234,0.00044792405,0.00017195928,0.009516901,0.0033408774,0.0008138743,0.007634676,0.002737298,0.5189501,0.000044253225],"about_ca_topic_score_codex":0.005205569,"about_ca_topic_score_gemma":0.012099218,"teacher_disagreement_score":0.01054212,"about_ca_system_score_codex":0.00042259126,"about_ca_system_score_gemma":0.00040450483,"threshold_uncertainty_score":0.035266936},"labels":[],"label_agreement":null},{"id":"W6931262841","doi":"10.5281/zenodo.7487536","title":"Covid-19'un Türkiye'nin Dış Ticaret Taşıma Türlerine Etkisinin İncelenmesi","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","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":"","keywords":"Turkish; Quarter (Canadian coin); Shock (circulatory); Economic impact analysis; Pandemic; Order (exchange); Supply chain; Air transport","score_opus":0.039784667092293086,"score_gpt":0.2599889607646066,"score_spread":0.2202042936723135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931262841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733167,0.0063188947,0.00097043545,0.0027805336,0.0003616982,0.00009715619,0.002362158,0.0000373123,0.0137551725],"genre_scores_gemma":[0.9864383,0.004798167,0.00101185,0.0005430283,0.00011539604,0.000095401374,0.0027561218,0.000012788504,0.004228978],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99941456,0.00013294065,0.00007567177,0.000091751135,0.00014133102,0.0001438114],"domain_scores_gemma":[0.9992112,0.00016356808,0.00025890805,0.000029100504,0.000268849,0.00006834619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076876057,0.0004854359,0.00043892884,0.0007036425,0.0008203114,0.0013270146,0.00033147229,0.0004830334,0.0050409306],"category_scores_gemma":[0.0016578678,0.0002102328,0.00048283985,0.00096223044,0.00054672523,0.00085863756,0.00085498247,0.000828747,0.0009078001],"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":[0.0018850483,0.00046489883,0.83479387,0.0013621488,0.00027487086,0.0085671395,0.0046539726,0.0018422886,0.0024522676,0.0047647064,0.026167206,0.112771586],"study_design_scores_gemma":[0.00007717656,0.0010559973,0.88872063,0.0010474388,0.00035880765,0.009388111,0.025935568,0.0035494755,0.0031293149,0.0020181432,0.06460017,0.00011918826],"about_ca_topic_score_codex":0.014095849,"about_ca_topic_score_gemma":0.011658734,"teacher_disagreement_score":0.014095849,"about_ca_system_score_codex":0.0013237629,"about_ca_system_score_gemma":0.0016705627,"threshold_uncertainty_score":0.028027594},"labels":[],"label_agreement":null},{"id":"W6939656592","doi":"10.6084/m9.figshare.20098337.v1","title":"Additional file 1 of Parallel and private generalized suffix tree construction and query on genomic data","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"University of Manitoba","funders":"","keywords":"Suffix; Suffix tree; Tree (set theory); Query language; Query optimization; Set (abstract data type)","score_opus":0.04240883657829025,"score_gpt":0.23555091601449654,"score_spread":0.1931420794362063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939656592","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042210828,0.00003322624,0.0030880866,0.00012867826,0.00007091928,0.00011918466,0.98722047,0.0069927936,0.0019244502],"genre_scores_gemma":[0.009084016,0.00012427915,0.02397799,0.0004931516,0.00010373103,0.0010950661,0.9474826,0.011264924,0.006374207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989083,0.00014621306,0.00013521529,0.00035053954,0.00030804472,0.0001516503],"domain_scores_gemma":[0.98697346,0.008960753,0.00040832197,0.001777295,0.0014767852,0.00040339885],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016778191,0.0015759104,0.0012925245,0.0023898555,0.00093287276,0.0021940938,0.0026670485,0.0013539335,0.80471814],"category_scores_gemma":[0.027487831,0.0010751407,0.0009791851,0.004707615,0.0006043303,0.0018804069,0.001584301,0.0015908683,0.30580258],"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":[0.00041149234,0.0000894889,0.0009319472,0.0012646565,0.000036371584,0.00008391774,0.00005569835,0.0010408636,0.0010251938,0.0013795089,0.9779694,0.015711427],"study_design_scores_gemma":[0.004490476,0.00033214156,0.01057841,0.00093000376,0.00021125718,0.0008496728,0.0004248591,0.01873909,0.015575569,0.04244333,0.905131,0.00029419098],"about_ca_topic_score_codex":0.00504568,"about_ca_topic_score_gemma":0.006877281,"teacher_disagreement_score":0.80471814,"about_ca_system_score_codex":0.0013992585,"about_ca_system_score_gemma":0.0023000217,"threshold_uncertainty_score":0.2785458},"labels":[],"label_agreement":null},{"id":"W6958288425","doi":"10.6084/m9.figshare.19703846.v1","title":"Additional file 3 of KnotAli: informed energy minimization through the use of evolutionary information","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Section (typography); Table (database); Minification; Sequence (biology); Energy (signal processing)","score_opus":0.041123620084784006,"score_gpt":0.21958311180942572,"score_spread":0.1784594917246417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958288425","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004172472,0.000097325305,0.0052633868,0.00025415584,0.00016646786,0.00010125473,0.9823077,0.00788449,0.003507966],"genre_scores_gemma":[0.009941103,0.00023815206,0.025372889,0.0007503953,0.00023747663,0.0012055247,0.9269174,0.02176746,0.013569632],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990415,0.00020804777,0.00009360454,0.00028526093,0.0002475279,0.00012405768],"domain_scores_gemma":[0.9891712,0.007980048,0.0003818032,0.001012683,0.0011315249,0.00032267993],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021671362,0.0021074696,0.0019375657,0.0021267687,0.0013949688,0.0030690155,0.0041088657,0.0019371436,0.863711],"category_scores_gemma":[0.027073232,0.0010584273,0.0015109939,0.003468765,0.00047272103,0.002757145,0.0018750749,0.0021623785,0.3383354],"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":[0.00036205788,0.00006691651,0.00072756887,0.001529175,0.000075865835,0.00006544212,0.00004165248,0.0011606017,0.00027630414,0.0015934247,0.9827626,0.011338419],"study_design_scores_gemma":[0.0031631156,0.00026522926,0.0057007778,0.0014419076,0.00027719917,0.000504117,0.00021910513,0.011624979,0.003897153,0.044353247,0.9283506,0.00020247993],"about_ca_topic_score_codex":0.0038677226,"about_ca_topic_score_gemma":0.0075086085,"teacher_disagreement_score":0.863711,"about_ca_system_score_codex":0.0010663738,"about_ca_system_score_gemma":0.0019140298,"threshold_uncertainty_score":0.19439965},"labels":[],"label_agreement":null},{"id":"W6958394214","doi":"10.6084/m9.figshare.19703846","title":"Additional file 3 of KnotAli: informed energy minimization through the use of evolutionary information","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"University of Victoria","funders":"","keywords":"Section (typography); Table (database); Minification; Sequence (biology); Energy (signal processing)","score_opus":0.041123620084784006,"score_gpt":0.21958311180942572,"score_spread":0.1784594917246417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958394214","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004172472,0.000097325305,0.0052633868,0.00025415584,0.00016646786,0.00010125473,0.9823077,0.00788449,0.003507966],"genre_scores_gemma":[0.009941103,0.00023815206,0.025372889,0.0007503953,0.00023747663,0.0012055247,0.9269174,0.02176746,0.013569632],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990415,0.00020804777,0.00009360454,0.00028526093,0.0002475279,0.00012405768],"domain_scores_gemma":[0.9891712,0.007980048,0.0003818032,0.001012683,0.0011315249,0.00032267993],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021671362,0.0021074696,0.0019375657,0.0021267687,0.0013949688,0.0030690155,0.0041088657,0.0019371436,0.863711],"category_scores_gemma":[0.027073232,0.0010584273,0.0015109939,0.003468765,0.00047272103,0.002757145,0.0018750749,0.0021623785,0.3383354],"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":[0.00036205788,0.00006691651,0.00072756887,0.001529175,0.000075865835,0.00006544212,0.00004165248,0.0011606017,0.00027630414,0.0015934247,0.9827626,0.011338419],"study_design_scores_gemma":[0.0031631156,0.00026522926,0.0057007778,0.0014419076,0.00027719917,0.000504117,0.00021910513,0.011624979,0.003897153,0.044353247,0.9283506,0.00020247993],"about_ca_topic_score_codex":0.0038677226,"about_ca_topic_score_gemma":0.0075086085,"teacher_disagreement_score":0.863711,"about_ca_system_score_codex":0.0010663738,"about_ca_system_score_gemma":0.0019140298,"threshold_uncertainty_score":0.19439965},"labels":[],"label_agreement":null},{"id":"W6958521047","doi":"10.6084/m9.figshare.26637144.v1","title":"Additional file 1 of Evidence-based practice confidence and behavior throughout the curriculum of four physical therapy education programs: a longitudinal study","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","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":"University of Toronto; University Health Network","funders":"","keywords":"Longitudinal study; Curriculum; Physical education; Longitudinal data; Qualitative research","score_opus":0.1350320400712253,"score_gpt":0.3902371420049281,"score_spread":0.2552051019337028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958521047","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025293783,0.000030134905,0.00038512415,0.00017237512,0.00003602018,0.0006073145,0.99468213,0.000120076555,0.0014375217],"genre_scores_gemma":[0.0757584,0.00026021455,0.011399834,0.0011991041,0.0001572125,0.028953442,0.84761447,0.00073838385,0.033918984],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869066,0.00027384967,0.0003286017,0.0002658566,0.000287932,0.00015304385],"domain_scores_gemma":[0.9445754,0.040350046,0.004455983,0.0026604298,0.006807596,0.0011504616],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022345632,0.00087462977,0.0015273475,0.0025192376,0.0018374266,0.0017282902,0.002284812,0.0014587062,0.7967085],"category_scores_gemma":[0.0642765,0.00072827487,0.0012221757,0.0043245833,0.00037629856,0.002291317,0.001191142,0.0014689092,0.08129449],"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":[0.0017141647,0.0013314962,0.01927619,0.003785255,0.00016661959,0.00008719637,0.00037948744,0.00057648536,0.00006106918,0.0013484152,0.939409,0.03186453],"study_design_scores_gemma":[0.033082597,0.003815301,0.51852185,0.013855192,0.0010957354,0.0012149736,0.004643803,0.0066787526,0.0014404646,0.017390927,0.39755195,0.00070851145],"about_ca_topic_score_codex":0.02208351,"about_ca_topic_score_gemma":0.023150597,"teacher_disagreement_score":0.7967085,"about_ca_system_score_codex":0.0019732257,"about_ca_system_score_gemma":0.003322837,"threshold_uncertainty_score":0.28997058},"labels":[],"label_agreement":null},{"id":"W6962823767","doi":"10.17605/osf.io/ugfzx","title":"SharingToddlers Registration","year":2019,"lang":"ceb","type":"other","venue":"Open Science Framework","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Identification (biology); Process (computing); Feature (linguistics); Focus (optics)","score_opus":0.03805406298458122,"score_gpt":0.33657319561662474,"score_spread":0.29851913263204355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6962823767","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008099108,0.0009183569,0.4357813,0.0030828915,0.004435024,0.0012556318,0.00953222,0.10676561,0.4301298],"genre_scores_gemma":[0.17120464,0.001274286,0.20031798,0.0026772826,0.001855145,0.0014861117,0.048773438,0.042165935,0.5302451],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99071044,0.0015684076,0.000554352,0.0014228665,0.004215356,0.0015285036],"domain_scores_gemma":[0.97838587,0.0010641704,0.00043017737,0.016548714,0.002495175,0.0010759903],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00605507,0.001618243,0.0023139534,0.0038578697,0.0035281929,0.009090022,0.005436655,0.0031392376,0.2007149],"category_scores_gemma":[0.01765612,0.0010240556,0.0024132633,0.0030857804,0.002194714,0.009300874,0.0195474,0.003793349,0.1368328],"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":[0.0009237518,0.00038331465,0.0008277671,0.0003156984,0.00007202894,0.0001844786,0.00036265797,0.0028422126,0.0053096735,0.18764201,0.4582318,0.34290466],"study_design_scores_gemma":[0.00009247264,0.000076609744,0.0003606886,0.00010244216,0.000030656596,0.00022806755,0.00012077097,0.012073142,0.009188508,0.06924827,0.90839714,0.00008127968],"about_ca_topic_score_codex":0.004617144,"about_ca_topic_score_gemma":0.004213675,"teacher_disagreement_score":0.7992851,"about_ca_system_score_codex":0.0021105623,"about_ca_system_score_gemma":0.0057493276,"threshold_uncertainty_score":0.67145824},"labels":[],"label_agreement":null},{"id":"W6966632337","doi":"10.4230/lipics.sea.2023.19","title":"Exact and Approximate Range Mode Query Data Structures in Practice","year":2023,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Range (aeronautics); Mode (computer interface); Range query (database); Space (punctuation); Data structure; Element (criminal law)","score_opus":0.03281440660623704,"score_gpt":0.3182803132095328,"score_spread":0.2854659066032958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966632337","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47982484,0.006968119,0.4523817,0.0063631227,0.00062733586,0.0011027816,0.0049211006,0.015781207,0.032029804],"genre_scores_gemma":[0.48133877,0.00093143084,0.5064047,0.0010727883,0.00015133509,0.00072789175,0.0047691986,0.0010637415,0.003540247],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9697206,0.007864299,0.0027351673,0.0051691695,0.012016319,0.0024943484],"domain_scores_gemma":[0.93848115,0.033128213,0.002578692,0.020285472,0.0045389244,0.0009875752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009453237,0.0019752767,0.0023053566,0.0018046243,0.0019477385,0.0044267806,0.0049748146,0.004007481,0.009420867],"category_scores_gemma":[0.061072372,0.0012635263,0.0015795527,0.0061017307,0.0024580036,0.01771116,0.004572243,0.0037484374,0.0025030025],"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":[0.006486821,0.0044853524,0.016296921,0.0027297297,0.00047655002,0.0005770293,0.002229779,0.3256858,0.03178726,0.08614723,0.07593535,0.44716215],"study_design_scores_gemma":[0.0011329879,0.0013796781,0.00256493,0.00011740591,0.00012318017,0.00097519346,0.0014045069,0.86280984,0.016976953,0.090773985,0.021624468,0.000116866235],"about_ca_topic_score_codex":0.0063439785,"about_ca_topic_score_gemma":0.0065134335,"teacher_disagreement_score":0.009453237,"about_ca_system_score_codex":0.0034748574,"about_ca_system_score_gemma":0.0051122666,"threshold_uncertainty_score":0.04999411},"labels":[],"label_agreement":null},{"id":"W6976862645","doi":"10.6084/m9.figshare.21151961.v1","title":"Additional file 1 of The role of DNA demethylation in liver to pancreas transdifferentiation","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"DNA methylation; Methylation; Demethylation; Transdifferentiation; DNA; DNA demethylation; Value (mathematics)","score_opus":0.011919635299578415,"score_gpt":0.1984411089602654,"score_spread":0.186521473660687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976862645","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001745151,0.000027142216,0.000423196,0.00008422677,0.00003422803,0.00007567815,0.99787974,0.00035702312,0.00094417215],"genre_scores_gemma":[0.008566702,0.00021600992,0.0048797554,0.0006826218,0.00013509335,0.0021588062,0.96824604,0.0018050208,0.013309922],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990243,0.00014888353,0.00014551567,0.0002736573,0.00025081736,0.00015687743],"domain_scores_gemma":[0.98244804,0.013254834,0.0008677711,0.0010036671,0.0018530007,0.0005727489],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017259595,0.0013449154,0.0015288767,0.0021059697,0.0010450667,0.002155613,0.0021566418,0.0012445718,0.9003256],"category_scores_gemma":[0.027079439,0.0007680269,0.0010467431,0.0034196882,0.00033659543,0.0016571278,0.0009778547,0.0012097987,0.23614024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053042447,0.00012968683,0.0028086253,0.0025918675,0.000055075914,0.000105009676,0.00006189694,0.0005723768,0.0002915242,0.0007940726,0.9811157,0.010943715],"study_design_scores_gemma":[0.00709659,0.00057808735,0.040115852,0.004009537,0.00031275811,0.0011642369,0.0003839797,0.0037139151,0.0027735732,0.016570974,0.9230401,0.00024022956],"about_ca_topic_score_codex":0.0067341942,"about_ca_topic_score_gemma":0.009722432,"teacher_disagreement_score":0.9003256,"about_ca_system_score_codex":0.0010753635,"about_ca_system_score_gemma":0.0022589518,"threshold_uncertainty_score":0.14217347},"labels":[],"label_agreement":null},{"id":"W6978370893","doi":"10.7939/r3-4c8r-a922","title":"Road Erosion, Sediment Delivery, and Consequence in the Simonette Watershed West-Central Alberta","year":2022,"lang":"en","type":"dissertation","venue":"University of Alberta Library","topic":"Algorithms and Data Compression","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":"","keywords":"Sediment; Watershed; Hydrology (agriculture); Erosion; Foothills; STREAMS; Silt; Surface runoff; Sedimentary budget","score_opus":0.006694693072841878,"score_gpt":0.18478618875138042,"score_spread":0.17809149567853855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6978370893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983211,0.000061171806,0.000051833864,0.000042084044,0.0000011945602,0.000010635501,0.00018445053,0.0000075197513,0.0013200036],"genre_scores_gemma":[0.9975898,0.0001543786,0.00022082272,0.000017709312,0.0000015227695,0.0000073030014,0.00028206295,0.000002546985,0.0017238044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99968576,0.000023563494,0.000011737117,0.00004403042,0.00012842375,0.00010649851],"domain_scores_gemma":[0.9996431,0.00004043655,0.00006784958,0.000008544354,0.00014907225,0.00009101314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029795448,0.000270482,0.00023682327,0.0011655677,0.0015545638,0.0012434551,0.0005396491,0.00024037756,0.0010409222],"category_scores_gemma":[0.00063692586,0.0001619468,0.00016017977,0.0023991799,0.0008913047,0.00021600256,0.00057806197,0.00025768927,0.00012188484],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031712142,0.00019427757,0.96277076,0.000053689993,0.000058218495,0.0011539467,0.0036279752,0.0039850357,0.0024763693,0.0007214952,0.0012005189,0.023440663],"study_design_scores_gemma":[0.000006077309,0.000025890133,0.9939044,0.000008589616,0.000011597106,0.000051720814,0.003670097,0.0013404719,0.00017655663,0.00007126712,0.0007253247,0.000007986988],"about_ca_topic_score_codex":0.9748581,"about_ca_topic_score_gemma":0.99254507,"teacher_disagreement_score":0.025141895,"about_ca_system_score_codex":0.018847996,"about_ca_system_score_gemma":0.01172986,"threshold_uncertainty_score":0.13675243},"labels":[],"label_agreement":null},{"id":"W7001086108","doi":"","title":"Integrated Fabry-Perot optical space switches","year":2009,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Optical switch; Optical burst switching; Optical performance monitoring; Transmission (telecommunications); Optical cross-connect; Waveguide; Scalability; Optical communication; Flexibility (engineering); Planar; Packet switching","score_opus":0.0033554100467383806,"score_gpt":0.14398989544184398,"score_spread":0.1406344853951056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001086108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8709404,0.002003283,0.11289763,0.00014302821,0.0002875349,0.00010614267,0.00028675472,0.0011529624,0.012182293],"genre_scores_gemma":[0.9243518,0.00062177697,0.06642622,0.00004920716,0.00003487886,0.00005352462,0.00013281904,0.000032927543,0.00829672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99964666,0.000017460108,0.000011859298,0.00008599388,0.00016349522,0.00007448932],"domain_scores_gemma":[0.9998123,0.000035268833,0.000056594265,0.000029493345,0.0000495745,0.000016798489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019011181,0.00043704204,0.0003199339,0.000272879,0.00021445156,0.0008654675,0.00079933985,0.0005786452,0.00133014],"category_scores_gemma":[0.00024809476,0.0002473359,0.0003093958,0.0002596039,0.00024369177,0.0007091475,0.00027201997,0.00031245017,0.0003839038],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002678974,0.00008801857,0.0006255512,0.00009240116,0.000027579115,0.00009357178,0.00006896275,0.0037313777,0.96636236,0.004086208,0.00041491215,0.02414123],"study_design_scores_gemma":[0.000046908015,0.0007429482,0.002106295,0.0000108040185,0.000054694516,0.000276477,0.000034213965,0.030576259,0.95383036,0.0005370688,0.011747253,0.000036681937],"about_ca_topic_score_codex":0.0008004797,"about_ca_topic_score_gemma":0.0012928629,"teacher_disagreement_score":0.00133014,"about_ca_system_score_codex":0.00067264,"about_ca_system_score_gemma":0.00031567906,"threshold_uncertainty_score":0.0048803687},"labels":[],"label_agreement":null},{"id":"W7008917920","doi":"","title":"Computing probabilities for common substrings in random strings","year":2006,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Algorithms and Data Compression","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":"","keywords":"Substring; Set (abstract data type); Feature (linguistics); Term (time)","score_opus":0.014404604584592041,"score_gpt":0.2451875548206702,"score_spread":0.23078295023607817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008917920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26001802,0.0013581292,0.7293226,0.0010466154,0.00022941698,0.00022834241,0.002163455,0.0022444883,0.0033890102],"genre_scores_gemma":[0.7597697,0.0012733936,0.2260132,0.00024507564,0.00043598303,0.00031171023,0.007181064,0.0005326119,0.0042372565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925729,0.0016233465,0.00092863187,0.002046348,0.0022371258,0.00059160264],"domain_scores_gemma":[0.9565475,0.034655105,0.0021334218,0.003707773,0.002312155,0.00064400316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004064764,0.0007338134,0.0013282639,0.0097282,0.0011754059,0.003916075,0.0018399328,0.0024509754,0.0044306405],"category_scores_gemma":[0.057051092,0.0008639724,0.0018274923,0.00546059,0.0021867529,0.0071671745,0.002818568,0.0019764944,0.00204115],"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":[0.0021184515,0.00043651016,0.057728678,0.0010417643,0.0005257044,0.001768395,0.0014449925,0.16955802,0.017826235,0.11216775,0.012215614,0.623168],"study_design_scores_gemma":[0.000076344404,0.00024095557,0.01031237,0.00016740512,0.00012568208,0.001174789,0.00037080387,0.7486836,0.010624313,0.22445731,0.0036703078,0.00009616384],"about_ca_topic_score_codex":0.0019783813,"about_ca_topic_score_gemma":0.0028642223,"teacher_disagreement_score":0.0097282,"about_ca_system_score_codex":0.0013183396,"about_ca_system_score_gemma":0.0015472134,"threshold_uncertainty_score":0.021496832},"labels":[],"label_agreement":null},{"id":"W7011243628","doi":"","title":"Measurements of multijet event isotropies using optimal transport with the ATLAS detector","year":2022,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"European Social Fund; Fundação para a Ciência e a Tecnologia; Institut National de Physique Nucléaire et de Physique des Particules; Agencia Nacional de Promoción Científica y Tecnológica; Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada; Narodowa Agencja Wymiany Akademickiej; Centre National pour la Recherche Scientifique et Technique; Centre National de la Recherche Scientifique; Israel Science Foundation; Japan Society for the Promotion of Science; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Bundesministerium für Wissenschaft, Forschung und Wirtschaft; Generalitat Valenciana; Austrian Science Fund; European Regional Development Fund; Bundesministerium für Bildung und Forschung; Ministerstvo Školství, Mládeže a Tělovýchovy; U.S. Department of Energy; National Natural Science Foundation of China; Fundação de Amparo à Pesquisa do Estado de São Paulo; H2020 Marie Skłodowska-Curie Actions; Javna Agencija za Raziskovalno Dejavnost RS; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Ministry of Education, Culture, Sports, Science and Technology; Agence Nationale de la Recherche; National Science Foundation; Alexander von Humboldt-Stiftung; TRIUMF; Compute Canada; Max-Planck-Gesellschaft; Royal Society; Danmarks Grundforskningsfond; British Columbia Knowledge Development Fund; Türkiye Enerji, Nükleer ve Maden Araştırma Kurumu; Agencia Nacional de Investigación y Desarrollo; Generalitat de Catalunya; Canarie; Deutsche Forschungsgemeinschaft; Centres de Recerca de Catalunya; CERN; Leverhulme Trust; Ministerio de Ciencia e Innovación; European Commission","keywords":"Detector; Large Hadron Collider; Monte Carlo method; Event reconstruction; Event (particle physics); Atlas (anatomy); Isotropy; Transverse plane","score_opus":0.018363456056775664,"score_gpt":0.20267398686007998,"score_spread":0.1843105308033043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7011243628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97522277,0.00006007851,0.02233511,0.000030868927,0.0000048807324,0.000014633605,0.00060164713,0.000229613,0.0015004067],"genre_scores_gemma":[0.99083054,0.000022173153,0.008021954,0.00000628129,0.0000030321025,0.000008479899,0.00078740873,0.00007574187,0.0002443921],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991817,0.00014534539,0.000050622533,0.00021033404,0.00033022472,0.00008177542],"domain_scores_gemma":[0.99776936,0.0008184047,0.0005314348,0.00047461627,0.00026257048,0.00014352673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011673627,0.00038184682,0.00040398553,0.001057426,0.00042769444,0.001006252,0.0006508947,0.00032578662,0.001026612],"category_scores_gemma":[0.0035129052,0.00033096576,0.00036118698,0.0015928411,0.0006772978,0.0007575077,0.0010949377,0.00042199288,0.00020569847],"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":[0.008760082,0.0005470066,0.31887838,0.00019204873,0.0003547356,0.001564393,0.0011126546,0.20130672,0.34289047,0.020122513,0.0012421327,0.103029005],"study_design_scores_gemma":[0.00013375863,0.0006810278,0.26426637,0.000017248442,0.000090881156,0.0018267386,0.00033616173,0.43489563,0.28770462,0.007123888,0.0027376893,0.00018605326],"about_ca_topic_score_codex":0.0015459977,"about_ca_topic_score_gemma":0.002039609,"teacher_disagreement_score":0.0015459977,"about_ca_system_score_codex":0.0010465782,"about_ca_system_score_gemma":0.00040844863,"threshold_uncertainty_score":0.0075935125},"labels":[],"label_agreement":null},{"id":"W7016050130","doi":"","title":"Vancouver Consumer - Feb. 18, 2023 - Dr. Ron Zokol with BC Perio","year":2023,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Population; Public health","score_opus":0.007756999015564303,"score_gpt":0.19334961448928886,"score_spread":0.18559261547372455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016050130","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042919308,0.0017872347,0.00040963676,0.0028079364,0.0034115843,0.00007636862,0.00412182,0.0011391034,0.98581725],"genre_scores_gemma":[0.00034927856,0.00030282378,0.000065804576,0.00018626652,0.00005727247,0.000004808765,0.00040096094,0.00013735324,0.9984956],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996302,0.000016772603,0.000009027395,0.000066420245,0.00021292965,0.00006453247],"domain_scores_gemma":[0.9986349,0.00007935808,0.000022449949,0.00006507331,0.00079753785,0.0004007034],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00040817694,0.0009325574,0.0007560426,0.0013270456,0.0027849264,0.004294981,0.0008135251,0.0018798636,0.8551282],"category_scores_gemma":[0.0014624664,0.00045503103,0.0004284406,0.0016807609,0.00045000232,0.0012658486,0.0013836451,0.0021264157,0.75315034],"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":[0.00002540996,0.000007233107,0.000068883695,0.00003143714,0.0000013129875,0.000021771219,0.0000092025,0.000020925858,0.000104451225,0.00036599787,0.9775785,0.021764869],"study_design_scores_gemma":[0.0000040149475,0.0000060326647,0.00033875363,0.00003839592,0.0000012265772,0.000018749242,0.00004182961,0.000031546748,0.000067474386,0.00010510319,0.99934345,0.0000034570369],"about_ca_topic_score_codex":0.060568433,"about_ca_topic_score_gemma":0.30407992,"teacher_disagreement_score":0.14487177,"about_ca_system_score_codex":0.0018792241,"about_ca_system_score_gemma":0.0019622496,"threshold_uncertainty_score":0.20664203},"labels":[],"label_agreement":null},{"id":"W70170654","doi":"10.1007/978-0-387-69216-6_9","title":"Google and the Page Rank Algorithm","year":2008,"lang":"en","type":"book-chapter","venue":"Springer undergraduate texts in mathematics and technology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Rank (graph theory); Algorithm; Mathematics; Combinatorics","score_opus":0.01197039423935505,"score_gpt":0.21858932054423078,"score_spread":0.20661892630487572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W70170654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03331637,0.11137218,0.55218154,0.021592753,0.0060607367,0.00016831486,0.0031595207,0.008638486,0.2635101],"genre_scores_gemma":[0.39286754,0.055750784,0.3427149,0.0030303746,0.008042511,0.0002710271,0.005502801,0.003429502,0.1883906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975594,0.0006812141,0.000097731725,0.00034749834,0.0010764714,0.00023760852],"domain_scores_gemma":[0.9970817,0.0013953375,0.00011172919,0.00083816634,0.0004782186,0.000094898416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020471506,0.0012781181,0.0019854296,0.004783753,0.0014257806,0.0057699136,0.0015906777,0.0022917534,0.017622186],"category_scores_gemma":[0.012284605,0.00070887955,0.00096672616,0.010421894,0.0030032275,0.010814051,0.0023961791,0.002797344,0.01245784],"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":[0.00025783596,0.000061245606,0.00068257854,0.00024853132,0.000054125918,0.000087849,0.000112769274,0.015116433,0.00045934602,0.47165373,0.14574586,0.36551964],"study_design_scores_gemma":[0.000053002695,0.000035063495,0.0005935324,0.00010398297,0.000031006726,0.00038040886,0.00009383334,0.060074106,0.0009726609,0.81528115,0.122334525,0.00004670616],"about_ca_topic_score_codex":0.0072402316,"about_ca_topic_score_gemma":0.0064044464,"teacher_disagreement_score":0.017622186,"about_ca_system_score_codex":0.0015635869,"about_ca_system_score_gemma":0.0017795628,"threshold_uncertainty_score":0.058952034},"labels":[],"label_agreement":null},{"id":"W7018028875","doi":"","title":"CHAN's PLANAR CONVEX HULL ALGORITHM: A Brief Survey and Sequential Experimental Comparison","year":2006,"lang":"en","type":"article","venue":"NPARC","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convex hull; Planar; Hull; Convex set; Correctness; Set (abstract data type); Regular polygon","score_opus":0.024965640696305216,"score_gpt":0.27190637220017105,"score_spread":0.24694073150386583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018028875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02278096,0.013620008,0.93377405,0.00062580226,0.0003606911,0.000825379,0.0008730261,0.004810825,0.02232919],"genre_scores_gemma":[0.11352358,0.013818198,0.8603353,0.0003201869,0.00022270472,0.000979422,0.0032493286,0.0012138103,0.0063374764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943539,0.0011818837,0.00051567965,0.0007297155,0.0029732625,0.00024568912],"domain_scores_gemma":[0.99183416,0.0036569366,0.0003187762,0.0015688844,0.0024481856,0.00017307347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041425657,0.0015573262,0.0014783985,0.0045177354,0.0013443321,0.0026225422,0.0029625162,0.001467386,0.011205852],"category_scores_gemma":[0.020047769,0.0008769906,0.0008094469,0.011452018,0.0012897643,0.007047156,0.0022333814,0.00179697,0.0036799756],"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":[0.0006157605,0.0002565022,0.0015244711,0.0006884622,0.00009406322,0.00005904418,0.00016627525,0.017103186,0.004720151,0.018414944,0.01279928,0.9435578],"study_design_scores_gemma":[0.00042545178,0.0023230477,0.010614418,0.00048531857,0.00030645813,0.002413592,0.0009992318,0.62328184,0.07420408,0.076506875,0.2080208,0.00041892572],"about_ca_topic_score_codex":0.0057348073,"about_ca_topic_score_gemma":0.0047518522,"teacher_disagreement_score":0.011205852,"about_ca_system_score_codex":0.0017937218,"about_ca_system_score_gemma":0.0024320404,"threshold_uncertainty_score":0.037487328},"labels":[],"label_agreement":null},{"id":"W7019610485","doi":"","title":"Hardware Architectures for Lossless Compression","year":2022,"lang":"en","type":"other","venue":"eScholarship (California Digital Library)","topic":"Algorithms and Data Compression","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":"","keywords":"Huffman coding; Lossless compression; Lossy compression; Encoder; Data compression; Canonical Huffman code; Throughput; Encoding (memory)","score_opus":0.013958102154227861,"score_gpt":0.2259091941780104,"score_spread":0.21195109202378254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019610485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09623092,0.005078744,0.814429,0.0012432,0.0005695949,0.00032437925,0.0007165583,0.013888833,0.06751875],"genre_scores_gemma":[0.62562406,0.003340034,0.33636707,0.00081227603,0.00019651646,0.00028901728,0.0019123354,0.00036413388,0.031094547],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997787,0.00001608647,0.00001513815,0.00003239837,0.00012758699,0.000030030304],"domain_scores_gemma":[0.9997061,0.00006215756,0.00002421472,0.00006495186,0.00013104144,0.000011527275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020502899,0.00048864156,0.00023429481,0.0007599797,0.00041037917,0.001001418,0.0012479846,0.00037833408,0.008895747],"category_scores_gemma":[0.00072361797,0.00023667744,0.00020895878,0.00067759544,0.00027601523,0.0013830331,0.0005449797,0.0005916982,0.0024989517],"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":[0.0005316227,0.00019326157,0.0014865834,0.0007268146,0.00007625939,0.00036981952,0.0002516787,0.045821052,0.19099328,0.08183491,0.03514548,0.64256924],"study_design_scores_gemma":[0.00017548622,0.0008618558,0.0020908772,0.00018333377,0.00010946065,0.0010359781,0.0001483455,0.54386854,0.2818703,0.03078794,0.13877615,0.00009178598],"about_ca_topic_score_codex":0.0011369225,"about_ca_topic_score_gemma":0.0020016504,"teacher_disagreement_score":0.008895747,"about_ca_system_score_codex":0.0007630137,"about_ca_system_score_gemma":0.0006588789,"threshold_uncertainty_score":0.029759288},"labels":[],"label_agreement":null},{"id":"W7020655610","doi":"","title":"Legislación española sobre discapacidad psíquica","year":2024,"lang":"en","type":"article","venue":"Dialnet (Universidad de la Rioja)","topic":"Algorithms and Data Compression","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":"","keywords":"Legislation; De facto; Mental Health Act; Mental health; Common law; Civil law (Civil law); Mental illness","score_opus":0.008467442954923906,"score_gpt":0.2468319733619699,"score_spread":0.238364530407046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020655610","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04069841,0.0279705,0.034979645,0.070907086,0.008773815,0.00028286144,0.0061356686,0.00096478837,0.80928725],"genre_scores_gemma":[0.44605485,0.026432913,0.02631887,0.0535939,0.0045591122,0.0007728996,0.0065416656,0.0006772371,0.4350486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996852,0.0005932124,0.00015993687,0.0005558275,0.0013874323,0.00045164544],"domain_scores_gemma":[0.9955383,0.0018352366,0.00028538003,0.0004410036,0.0017679181,0.00013207126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051776124,0.000507579,0.0005625,0.0011858823,0.001900022,0.0031958413,0.00085183705,0.0022408126,0.020344352],"category_scores_gemma":[0.009533956,0.00021570083,0.00064074155,0.001661469,0.002164015,0.0013811331,0.0020401166,0.004343945,0.004409885],"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":[0.0002497777,0.00010812276,0.003750963,0.00053424796,0.000045019046,0.00032468257,0.0024525712,0.0010593486,0.0025450746,0.5484462,0.23495106,0.20553292],"study_design_scores_gemma":[0.00003908382,0.00004087645,0.0047883536,0.00044237138,0.00003101317,0.00015527393,0.00051414024,0.00033360257,0.0006484498,0.016153704,0.97682697,0.00002605193],"about_ca_topic_score_codex":0.05989623,"about_ca_topic_score_gemma":0.043439902,"teacher_disagreement_score":0.05989623,"about_ca_system_score_codex":0.005716397,"about_ca_system_score_gemma":0.008545054,"threshold_uncertainty_score":0.119095206},"labels":[],"label_agreement":null},{"id":"W7024254867","doi":"","title":"Queen Victoria's cabin, H.M. yacht Alberta","year":2009,"lang":"en","type":"other","venue":"Open Research Exeter (University of Exeter)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Queen (butterfly); Clothing; Government (linguistics)","score_opus":0.04712443867649635,"score_gpt":0.3132948650064985,"score_spread":0.26617042633000215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024254867","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037723812,0.031108096,0.0023802607,0.018505432,0.007924255,0.0000508519,0.0020574378,0.00078161265,0.93341976],"genre_scores_gemma":[0.0023860042,0.0033138266,0.0003568631,0.00023883398,0.00007201519,0.000003456524,0.00009718559,0.000086944725,0.9934449],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99965,0.000015718264,0.000008474712,0.0001271229,0.00015185527,0.00004691855],"domain_scores_gemma":[0.99938333,0.0000748589,0.000021864023,0.000031867778,0.00028308335,0.00020496744],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033521364,0.00066684757,0.0006259859,0.0008397864,0.0031585237,0.0028628362,0.0008915811,0.0014827225,0.47020617],"category_scores_gemma":[0.0008139155,0.0003747681,0.00032197605,0.0010544563,0.00056001404,0.0009689,0.0011780737,0.0014207778,0.20863904],"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":[0.00012554637,0.000034402037,0.00036688749,0.00019320543,0.0000067892574,0.00034304976,0.00022218561,0.00027908295,0.0015618792,0.008723048,0.845679,0.14246488],"study_design_scores_gemma":[0.0000031493848,0.00000779971,0.00051988324,0.000054469994,0.0000023699506,0.000071118666,0.0001335198,0.00006815266,0.00025850727,0.00042836677,0.9984478,0.000004815414],"about_ca_topic_score_codex":0.09998342,"about_ca_topic_score_gemma":0.31173012,"teacher_disagreement_score":0.47020617,"about_ca_system_score_codex":0.0028869335,"about_ca_system_score_gemma":0.0030784165,"threshold_uncertainty_score":0.7556866},"labels":[],"label_agreement":null},{"id":"W7024406142","doi":"","title":"Sanitation, Modernisation, Identity, and the 1851 Great Exhibition – The emergence and downfall of the St Giles Rookery.","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Exhibition; Exposition (narrative); Paraphernalia; Painting","score_opus":0.021881457577360115,"score_gpt":0.25303803204148195,"score_spread":0.23115657446412183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024406142","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18993944,0.16307646,0.0035599137,0.03639266,0.0017308361,0.00005236783,0.0006811426,0.00010803028,0.6044592],"genre_scores_gemma":[0.7207053,0.061675187,0.0023492046,0.0014995242,0.00083396264,0.000037747934,0.0003797257,0.00010428017,0.21241508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99968016,0.00010978729,0.000012335732,0.00004698552,0.000083810286,0.00006687433],"domain_scores_gemma":[0.9997501,0.000089945876,0.000045182012,0.000031436994,0.00004258547,0.000040797106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040982993,0.00022710225,0.00014658607,0.00065725675,0.0015921572,0.0021189959,0.00036794663,0.0006578261,0.01374731],"category_scores_gemma":[0.00097523566,0.0001728179,0.00017172702,0.0015005084,0.0053798454,0.0017692056,0.0017728852,0.0011693197,0.0010321784],"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":[0.000160037,0.00005563768,0.008791091,0.00083465636,0.00002847098,0.00037769706,0.058987133,0.0014147022,0.000849745,0.45656025,0.15791795,0.3140226],"study_design_scores_gemma":[0.0000030351287,0.000043771117,0.037379798,0.00043861585,0.0000046922232,0.00022104611,0.017606214,0.00017098752,0.00041393176,0.014420733,0.92927635,0.000020807971],"about_ca_topic_score_codex":0.031003278,"about_ca_topic_score_gemma":0.082762495,"teacher_disagreement_score":0.031003278,"about_ca_system_score_codex":0.0038195527,"about_ca_system_score_gemma":0.0015910956,"threshold_uncertainty_score":0.061645627},"labels":[],"label_agreement":null},{"id":"W7024529199","doi":"","title":"Selected Soybean Plant Introductions with Partial Resistance\\nto &lt;i&gt;Sclerotinia sclerotiorum&lt;/i&gt;","year":2002,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"Algorithms and Data Compression","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":"","keywords":"Sclerotinia; Stem rot; Inoculation; Petiole (insect anatomy); Plant disease resistance; Sclerotinia sclerotiorum; Canopy","score_opus":0.012650000479531812,"score_gpt":0.17320647746300843,"score_spread":0.16055647698347664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024529199","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99734735,0.00007278997,0.00043418165,0.000022950077,0.000014456113,0.00019033333,0.00053349463,0.00007844716,0.0013059642],"genre_scores_gemma":[0.98116046,0.00019066416,0.0038197876,0.00021599725,0.000007965704,0.00030466594,0.003815541,0.0000628314,0.010422041],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9997583,0.000029530873,0.00002451111,0.00007765686,0.000059040096,0.000050927883],"domain_scores_gemma":[0.999754,0.000024750503,0.000059402028,0.000016092592,0.000037292644,0.00010843287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022661104,0.00040930146,0.00030695045,0.00038357527,0.0003160965,0.0002025869,0.000288324,0.0002455134,0.0021491598],"category_scores_gemma":[0.00011576966,0.00017606861,0.00023672212,0.00026381947,0.00018736388,0.00010766192,0.0002469921,0.00049488526,0.00039380847],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006344315,0.00039207414,0.012609997,0.000056902678,0.00003017157,0.00028868255,0.00014723779,0.000074530646,0.980719,0.00007592731,0.0003117324,0.004659323],"study_design_scores_gemma":[0.0005473693,0.014019732,0.59598386,0.000037783597,0.000346084,0.0019131365,0.0008822508,0.0019061542,0.3630951,0.000074469914,0.021124242,0.000069837624],"about_ca_topic_score_codex":0.0057011265,"about_ca_topic_score_gemma":0.025121251,"teacher_disagreement_score":0.0057011265,"about_ca_system_score_codex":0.00077299884,"about_ca_system_score_gemma":0.00050481135,"threshold_uncertainty_score":0.011335909},"labels":[],"label_agreement":null},{"id":"W7027033745","doi":"","title":"Canadian Solar Opens $712 Million Storage Hub in Kentucky","year":2024,"lang":"en","type":"other","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Solar energy; Production (economics)","score_opus":0.010443371341681678,"score_gpt":0.23553034262580982,"score_spread":0.22508697128412813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027033745","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019412534,0.0013619963,0.0010586258,0.011818139,0.0010596076,0.00014644697,0.018742915,0.0022059048,0.94419384],"genre_scores_gemma":[0.02127497,0.0005503767,0.0005387626,0.00050557934,0.0000590755,0.000020815758,0.0027409003,0.00027726116,0.97403234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995459,0.000013145717,0.0000078456405,0.0000789345,0.00020102668,0.00015314188],"domain_scores_gemma":[0.9990507,0.000030520674,0.000020834781,0.000057539295,0.00052359456,0.0003168415],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032397255,0.0007170055,0.0004219486,0.0012073059,0.007119018,0.0031287605,0.0011376115,0.0012210051,0.44474757],"category_scores_gemma":[0.0008806499,0.00034232784,0.00044850112,0.0023055496,0.001054468,0.0017538103,0.0023832016,0.0010288899,0.087875865],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001817409,0.000042647247,0.0013661763,0.00005390629,0.000005891225,0.000114997674,0.000058938298,0.00041120162,0.00085742696,0.009798088,0.9406843,0.046424594],"study_design_scores_gemma":[0.0000396049,0.000019847648,0.0046890867,0.00006237348,0.000005715893,0.0000490325,0.00037287574,0.0008733548,0.0008933661,0.0019213376,0.9910528,0.000020595091],"about_ca_topic_score_codex":0.92177004,"about_ca_topic_score_gemma":0.9600166,"teacher_disagreement_score":0.44474757,"about_ca_system_score_codex":0.021916812,"about_ca_system_score_gemma":0.027001532,"threshold_uncertainty_score":0.7920002},"labels":[],"label_agreement":null},{"id":"W7028405950","doi":"","title":"Fake news, opioids, hospital harm is the 3rd leading cause of death in Canada and the U.S., and the impact of Wynne government's health care cuts","year":2017,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Algorithms and Data Compression","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":"","keywords":"Harm; Limiting; Government (linguistics); Health care; Supreme court; Chronic pain; Pain medicine; Public health","score_opus":0.005308625572192095,"score_gpt":0.20548119203062223,"score_spread":0.20017256645843015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028405950","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020640898,0.036959954,0.003362948,0.0917433,0.014203658,0.00014773355,0.014031997,0.0045460435,0.81436354],"genre_scores_gemma":[0.067043416,0.04000797,0.002716143,0.009322555,0.003964079,0.000038316757,0.006526338,0.0014142814,0.86896694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990564,0.00003991869,0.00001946027,0.000045315148,0.0006928676,0.00014604686],"domain_scores_gemma":[0.9970927,0.0004429847,0.00021707545,0.0001721202,0.0015664612,0.0005085654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055105815,0.0006345662,0.00032149968,0.0021210941,0.0032575608,0.0058337324,0.0004712467,0.0010714465,0.15516163],"category_scores_gemma":[0.007420761,0.00029005794,0.0002229852,0.0041137915,0.0012976249,0.002070604,0.0011272271,0.0012031731,0.03456834],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026298629,0.0000073587457,0.00078296475,0.00005768924,0.0000026499697,0.00004679969,0.000107854605,0.000071174436,0.00014757745,0.0010226832,0.92935365,0.06837334],"study_design_scores_gemma":[0.000010586723,0.000012814261,0.007235527,0.0002510003,0.000013096892,0.00020299369,0.0013202684,0.00054755394,0.0006784694,0.0010658466,0.9886324,0.000029402712],"about_ca_topic_score_codex":0.62355137,"about_ca_topic_score_gemma":0.76815784,"teacher_disagreement_score":0.37644863,"about_ca_system_score_codex":0.008019562,"about_ca_system_score_gemma":0.009366883,"threshold_uncertainty_score":0.7573312},"labels":[],"label_agreement":null},{"id":"W7038232172","doi":"","title":"Impact of binge alcohol on\\n\\t\\t\\t\\t mortality among people who inject drugs","year":2017,"lang":"en","type":"article","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Algorithms and Data Compression","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":"","keywords":"Binge drinking; Hazard ratio; Proportional hazards model; Alcohol; Psychological intervention; Cohort study; Cohort; Prospective cohort study","score_opus":0.029611656514341677,"score_gpt":0.29028588116491094,"score_spread":0.2606742246505693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038232172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99386805,0.0011796554,0.00010688464,0.00034124078,0.000019810024,0.000022921917,0.002182364,0.00001023222,0.0022688156],"genre_scores_gemma":[0.9977203,0.00066165347,0.00009648679,0.00006438043,0.000012648976,0.0000068886225,0.00089187664,0.0000036496858,0.0005421446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994337,0.000059732196,0.00002574465,0.000063636035,0.00017153159,0.00024561535],"domain_scores_gemma":[0.9988696,0.00011875405,0.00033687416,0.00006410316,0.00027432194,0.00033633024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511976,0.0002215095,0.00029030003,0.00055222015,0.0010092359,0.0009784064,0.0006326027,0.0002538917,0.0020147888],"category_scores_gemma":[0.002686305,0.00019468686,0.00081999734,0.0010724268,0.0004064415,0.00031433723,0.0009672702,0.00082364347,0.0001617838],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011368986,0.000021202326,0.99342865,0.000025287638,0.00010818813,0.000039858605,0.00013672987,0.00010626114,0.000098778284,0.00005993377,0.00039373792,0.005467558],"study_design_scores_gemma":[0.00000173544,0.000013936975,0.99933773,0.00002214117,0.00003477175,0.000030690615,0.00012390371,0.0001617133,0.000026201227,0.000023250353,0.00022032768,0.000003628621],"about_ca_topic_score_codex":0.9054812,"about_ca_topic_score_gemma":0.9428148,"teacher_disagreement_score":0.9054812,"about_ca_system_score_codex":0.004876144,"about_ca_system_score_gemma":0.0066818977,"threshold_uncertainty_score":0.1901508},"labels":[],"label_agreement":null},{"id":"W7039189700","doi":"","title":"Libro del XIV Congreso Nacional de Ciencia y Tecnología - APANAC 2023","year":2023,"lang":"es","type":"article","venue":"Congresos CLABES Conferencia Latinoamericana sobre el ABandono de la Educación Superior (Universidad Tecnológica de Panamá)","topic":"Algorithms and Data Compression","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":"","keywords":"Quarter (Canadian coin); Backwardness; Social impact","score_opus":0.012132010604871625,"score_gpt":0.2702413287369187,"score_spread":0.25810931813204707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039189700","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011081183,0.02831502,0.0011345827,0.026843455,0.059727296,0.0004564097,0.008457414,0.00070172217,0.8732559],"genre_scores_gemma":[0.004522627,0.011044562,0.0010257995,0.0043733814,0.0034818312,0.00024663485,0.0032778957,0.00034476552,0.9716825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918,0.0001031746,0.000035555335,0.0001193089,0.0004029651,0.00015886848],"domain_scores_gemma":[0.9988794,0.00009490011,0.000078914745,0.000116933705,0.0005308424,0.00029896767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012491007,0.0010485187,0.00056655647,0.0013372042,0.0014854097,0.005836889,0.0010110533,0.0023862293,0.20851383],"category_scores_gemma":[0.0022658664,0.0002955522,0.0004465758,0.0017602636,0.0005224892,0.0018623485,0.0026753475,0.0040404736,0.097267315],"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":[0.000037085352,0.000026442938,0.00021352977,0.0002134709,0.0000050484364,0.00006462029,0.00006418986,0.00009759784,0.00023583668,0.0070051216,0.9556768,0.03636032],"study_design_scores_gemma":[0.0000014993748,0.0000026350808,0.00025874405,0.00005091213,6.8165e-7,0.0000094874995,0.000016725468,0.000008912426,0.000029450679,0.0001690005,0.99945,0.0000020158177],"about_ca_topic_score_codex":0.027541744,"about_ca_topic_score_gemma":0.036554307,"teacher_disagreement_score":0.20851383,"about_ca_system_score_codex":0.0030641274,"about_ca_system_score_gemma":0.0060274974,"threshold_uncertainty_score":0.6975483},"labels":[],"label_agreement":null},{"id":"W7069604203","doi":"","title":"HSI Model","year":2018,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Algorithms and Data Compression","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":"","keywords":"Symbol (formal); Symbolic data analysis; Variety (cybernetics); Fraction (chemistry); The Symbolic; Symbolic computation; Relation (database); Variable (mathematics)","score_opus":0.016943541210308322,"score_gpt":0.2576003156150712,"score_spread":0.24065677440476285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069604203","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052899767,0.0017185762,0.5209004,0.011447951,0.000752043,0.0010637058,0.02192674,0.0024752452,0.3868156],"genre_scores_gemma":[0.7140663,0.0019279852,0.08810587,0.002092899,0.00046657512,0.0016764145,0.012952407,0.0004703085,0.17824122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987865,0.00038524033,0.00006204302,0.00033465188,0.00023879069,0.00019268293],"domain_scores_gemma":[0.9974485,0.0014063533,0.00023662808,0.00040735785,0.00038003727,0.00012115103],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017663277,0.001111809,0.0008340974,0.0019671435,0.0011959438,0.0041141436,0.0032175335,0.0022569667,0.11154148],"category_scores_gemma":[0.007480549,0.0004971815,0.0012107937,0.0027815585,0.001475889,0.0041993856,0.0027503609,0.0028564443,0.020459378],"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":[0.00013199903,0.00017228302,0.008462428,0.00024444194,0.0001159221,0.00055437785,0.0006569492,0.0496605,0.0002496485,0.84758687,0.034244213,0.05792029],"study_design_scores_gemma":[0.000092030416,0.000094106355,0.0024882383,0.00013736733,0.00008360387,0.00047570837,0.0009811172,0.21249948,0.0002352799,0.6796209,0.10323896,0.00005315919],"about_ca_topic_score_codex":0.010243825,"about_ca_topic_score_gemma":0.006018859,"teacher_disagreement_score":0.8884585,"about_ca_system_score_codex":0.0016988759,"about_ca_system_score_gemma":0.0019351754,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W7095483770","doi":"","title":"Euclidean Strings","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Euclidean geometry; Euclidean domain; String (physics); Euclidean distance; Prime (order theory); Embedding; Euclidean algorithm","score_opus":0.0090900059430895,"score_gpt":0.2455221423916911,"score_spread":0.2364321364486016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095483770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07359793,0.0031000231,0.74596983,0.0014742302,0.0014827112,0.00024830658,0.0030480642,0.0019324824,0.16914654],"genre_scores_gemma":[0.36644757,0.002691616,0.49885553,0.0012849147,0.00061955396,0.00039160615,0.0054527614,0.0009820751,0.123274356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830854,0.00033206094,0.00022224354,0.00049288716,0.0004547413,0.00018960667],"domain_scores_gemma":[0.99794906,0.0005594045,0.00025902555,0.0005456106,0.0005607387,0.0001262345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007631137,0.00073798076,0.00070092815,0.002054903,0.0016991858,0.0032088323,0.0011505148,0.0014763133,0.025699686],"category_scores_gemma":[0.0055211186,0.00041284887,0.00077330606,0.00311845,0.0019235874,0.0059127784,0.002121508,0.0013348064,0.009290857],"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":[0.00013191722,0.000026894011,0.00042074008,0.00016640505,0.000015435391,0.00013374248,0.00025076643,0.0015398122,0.0034199092,0.9018704,0.008332855,0.0836911],"study_design_scores_gemma":[0.00003356051,0.00015305285,0.0006015571,0.00017571509,0.000028204728,0.0010730042,0.00031416072,0.00975911,0.008145725,0.7258695,0.25377595,0.00007039602],"about_ca_topic_score_codex":0.00045045168,"about_ca_topic_score_gemma":0.00061599445,"teacher_disagreement_score":0.025699686,"about_ca_system_score_codex":0.0010914719,"about_ca_system_score_gemma":0.0007322755,"threshold_uncertainty_score":0.08597398},"labels":[],"label_agreement":null},{"id":"W7097119529","doi":"","title":"The coding technique of Generalized Interval Transformations","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Data compression; Computation; Interval (graph theory); Coding (social sciences); Entropy encoding; Computational complexity theory; Entropy (arrow of time); Representation (politics); Arithmetic coding","score_opus":0.025606416604872527,"score_gpt":0.25561862857508594,"score_spread":0.2300122119702134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097119529","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006686703,0.00036106404,0.98686093,0.00012119092,0.00012611324,0.000039906063,0.0000871932,0.000506808,0.005210111],"genre_scores_gemma":[0.26987842,0.0010321598,0.7190245,0.00032244416,0.0004213355,0.0003063088,0.00047253468,0.00052092556,0.008021335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999316,0.00015179397,0.000043164102,0.00010864262,0.00030945952,0.000070995426],"domain_scores_gemma":[0.99918336,0.00031714723,0.00006668982,0.00026754374,0.00014205725,0.000023168104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005186867,0.00050363503,0.00036818453,0.001007559,0.00038156682,0.00080592424,0.00082817936,0.00043917992,0.004475636],"category_scores_gemma":[0.0025328768,0.00018454845,0.00050234626,0.0014139203,0.0011802713,0.0017185418,0.0009542238,0.0013730628,0.0010105276],"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":[0.00019811408,0.000024191022,0.00026331947,0.00018978919,0.000023204298,0.00017277311,0.00024005183,0.027240377,0.031966645,0.53753996,0.0037727728,0.39836875],"study_design_scores_gemma":[0.000078490724,0.00023906003,0.0006372944,0.00012236733,0.00005077495,0.0008356386,0.00009142507,0.3925119,0.090021834,0.44537956,0.0699379,0.000093739465],"about_ca_topic_score_codex":0.0006637669,"about_ca_topic_score_gemma":0.00042234297,"teacher_disagreement_score":0.004475636,"about_ca_system_score_codex":0.00039247217,"about_ca_system_score_gemma":0.0004646059,"threshold_uncertainty_score":0.014972448},"labels":[],"label_agreement":null},{"id":"W7097835506","doi":"","title":"PPM with extended alphabet","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Lossless compression; Data compression; Compression (physics); Alphabet; Lossy compression; Basis (linear algebra)","score_opus":0.008065291086439628,"score_gpt":0.2139325548284975,"score_spread":0.20586726374205785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097835506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047823116,0.0014840876,0.9162722,0.0009948718,0.0008480312,0.0001247301,0.0010271488,0.005275475,0.02615024],"genre_scores_gemma":[0.38704887,0.0011059954,0.5737523,0.00088451995,0.00064095465,0.00022066105,0.0026356843,0.0005502274,0.033160772],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912137,0.00015812546,0.00006855978,0.00018859649,0.00038194415,0.00008132843],"domain_scores_gemma":[0.9984962,0.00039601952,0.00008153684,0.0007481664,0.00022169361,0.00005632922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005177704,0.0003478447,0.0006007923,0.0007262629,0.00040846696,0.00081679836,0.00095498457,0.0006453795,0.00953714],"category_scores_gemma":[0.0031847202,0.00018495643,0.0003273642,0.0012674375,0.0005665881,0.0015425868,0.001257779,0.0006868417,0.0046693934],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006559088,0.00008692189,0.0013098099,0.0003686988,0.000046578276,0.0008833156,0.00014080494,0.032409776,0.033487175,0.10221323,0.028895412,0.7995023],"study_design_scores_gemma":[0.00013653548,0.00038706287,0.0018577583,0.000120974575,0.00006173599,0.0037710862,0.00008662467,0.5241976,0.06914773,0.21484616,0.1853262,0.000060577317],"about_ca_topic_score_codex":0.00041180808,"about_ca_topic_score_gemma":0.0003487791,"teacher_disagreement_score":0.00953714,"about_ca_system_score_codex":0.00033860203,"about_ca_system_score_gemma":0.0005516036,"threshold_uncertainty_score":0.031904876},"labels":[],"label_agreement":null},{"id":"W7097891953","doi":"","title":"The PAQ1 Data Compression Program","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Bigram; Data compression; Lossless compression; Context (archaeology); Compression (physics); Word (group theory); Data set; String (physics); Set (abstract data type)","score_opus":0.09180408803109666,"score_gpt":0.30317915745561197,"score_spread":0.2113750694245153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097891953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022294285,0.0010200966,0.8486886,0.00066009274,0.0005016415,0.00071346096,0.008050719,0.09652839,0.021542719],"genre_scores_gemma":[0.12610656,0.0011158211,0.7779825,0.0009845368,0.00027885922,0.0018078603,0.03008901,0.007711393,0.0539234],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994305,0.00004249588,0.000033579938,0.00010465483,0.000335136,0.000053586125],"domain_scores_gemma":[0.9993243,0.00012327936,0.00003322281,0.00017399527,0.00032218118,0.000023034221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005829958,0.00080858124,0.0005131031,0.0011409748,0.0004265434,0.00089675514,0.0014284484,0.0005487671,0.025604837],"category_scores_gemma":[0.002522949,0.00034087052,0.0003687072,0.0013513095,0.00031114696,0.0012199536,0.0011664891,0.0013307844,0.017867824],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008139081,0.0001525063,0.0010819056,0.00028884967,0.000047783324,0.000248107,0.00013746296,0.009938151,0.051564522,0.011808223,0.11989259,0.80402595],"study_design_scores_gemma":[0.00027998752,0.00047756537,0.0030744649,0.00009237861,0.00005879445,0.0014214776,0.00011704499,0.33159652,0.28045535,0.01557976,0.3667199,0.00012675753],"about_ca_topic_score_codex":0.0013117378,"about_ca_topic_score_gemma":0.0010175926,"teacher_disagreement_score":0.025604837,"about_ca_system_score_codex":0.00042993037,"about_ca_system_score_gemma":0.00059908174,"threshold_uncertainty_score":0.08565676},"labels":[],"label_agreement":null},{"id":"W7099075988","doi":"","title":"Environmental and Human Factors Affecting the Population Biology of Nova Scotia Brook Trout","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Trout; Nova scotia; Population; Population biology; Agriculture; Salmonidae","score_opus":0.024102966538345816,"score_gpt":0.25533091316664114,"score_spread":0.23122794662829532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099075988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99891067,0.000056311936,0.000036231067,0.00003800755,0.0000030252493,0.0000033088882,0.00019989081,0.0000010006437,0.00075158087],"genre_scores_gemma":[0.9988782,0.00007312904,0.00006143974,0.00001704551,0.0000019027709,0.0000026888576,0.00016754626,0.00000108167,0.0007969467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99988115,0.000018318742,0.0000074037143,0.00003129119,0.00002555523,0.000036339217],"domain_scores_gemma":[0.9994646,0.000060126917,0.00015556163,0.000022707907,0.00016478241,0.00013222278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022372653,0.00010434937,0.00007883788,0.00038856082,0.00037868824,0.00036128578,0.00014640742,0.0001011499,0.0012099843],"category_scores_gemma":[0.0007540262,0.00009392476,0.0001029361,0.00035287565,0.00042792645,0.000117376,0.0002938868,0.0001429639,0.00015949331],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007481307,0.000013274574,0.99386203,0.000008377249,0.000017969234,0.00010458602,0.00021535515,0.0004792212,0.0017474429,0.000056463527,0.00025906874,0.0031613417],"study_design_scores_gemma":[9.787757e-7,0.000005258323,0.9995542,0.0000017698679,0.000002286344,0.000015975134,0.000156049,0.00012329279,0.000027162494,0.000009085862,0.000102558784,0.0000012811586],"about_ca_topic_score_codex":0.76402336,"about_ca_topic_score_gemma":0.9235475,"teacher_disagreement_score":0.23597664,"about_ca_system_score_codex":0.002604997,"about_ca_system_score_gemma":0.0012288409,"threshold_uncertainty_score":0.4747327},"labels":[],"label_agreement":null},{"id":"W7100839026","doi":"","title":"Post BWT Stages of the . . .","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"Lossless compression; Data compression; Context (archaeology); Entropy encoding; Compression (physics); Image compression; Entropy (arrow of time); Sequence (biology)","score_opus":0.0067751267992245835,"score_gpt":0.22720169151482061,"score_spread":0.22042656471559602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100839026","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12526985,0.0022729125,0.8093006,0.001514913,0.001488119,0.0009670759,0.00467204,0.02074129,0.033773154],"genre_scores_gemma":[0.19626567,0.001450545,0.7294764,0.00057539233,0.00046259345,0.0005346009,0.009106192,0.004997541,0.05713107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994448,0.00005161054,0.00004428842,0.00011247157,0.0002500391,0.00009671828],"domain_scores_gemma":[0.99853504,0.00035417528,0.00008763373,0.00048729466,0.00049349386,0.00004236361],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006437,0.001219698,0.0007405173,0.001564499,0.000825223,0.0017140125,0.00087884255,0.000700846,0.023486443],"category_scores_gemma":[0.0036553128,0.0004479636,0.00069866935,0.00182392,0.0008673845,0.001886822,0.0014547588,0.0014510493,0.017303007],"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":[0.00055115996,0.000092595255,0.00096295186,0.00032708087,0.000029466717,0.00032070364,0.00034331618,0.0036903785,0.14005455,0.0065652984,0.012682745,0.8343798],"study_design_scores_gemma":[0.00009592068,0.0006472581,0.013261565,0.00013323949,0.00014652238,0.0018542055,0.0005707399,0.11238935,0.7119104,0.016877566,0.14198619,0.00012698582],"about_ca_topic_score_codex":0.0043617752,"about_ca_topic_score_gemma":0.0059689824,"teacher_disagreement_score":0.97651356,"about_ca_system_score_codex":0.00048568146,"about_ca_system_score_gemma":0.0011507176,"threshold_uncertainty_score":0.07856995},"labels":[],"label_agreement":null},{"id":"W7101132852","doi":"","title":"AI-Based Syntactic Pattern Recognition of Sequences","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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":"","keywords":"String (physics); Character (mathematics); Spelling; Beam search; Sequence (biology); Pattern matching; Encoding (memory); Character recognition","score_opus":0.03613546770460378,"score_gpt":0.27249214445133546,"score_spread":0.23635667674673166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101132852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00465455,0.0016554175,0.9717709,0.0011068543,0.0005054492,0.00011590268,0.00040916275,0.001923296,0.017858466],"genre_scores_gemma":[0.12501125,0.0035236888,0.84484994,0.00087206735,0.00035469542,0.00022000677,0.0021058563,0.00029000407,0.022772549],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991161,0.00014579951,0.00009165833,0.00020292804,0.00038255402,0.00006084788],"domain_scores_gemma":[0.99908924,0.00036554568,0.000052739248,0.00018461268,0.00028124233,0.000026683909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073922554,0.0005480348,0.0005088909,0.0014592314,0.00046887278,0.0016577352,0.0015851257,0.0009432179,0.009314583],"category_scores_gemma":[0.003289876,0.00024164323,0.00085934886,0.0017546178,0.0013619622,0.0022191934,0.0007468417,0.0011495419,0.0039856],"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":[0.00011713904,0.000048998194,0.00041413552,0.00038202346,0.000050550087,0.0001392858,0.000152691,0.013481703,0.023605973,0.15833008,0.016571315,0.78670603],"study_design_scores_gemma":[0.00004686378,0.00022030601,0.0010456135,0.00019824327,0.00006954392,0.00089777715,0.00014959286,0.55200034,0.045956638,0.24490525,0.15442973,0.00008005433],"about_ca_topic_score_codex":0.0024492026,"about_ca_topic_score_gemma":0.0022079968,"teacher_disagreement_score":0.009314583,"about_ca_system_score_codex":0.0008109728,"about_ca_system_score_gemma":0.001161353,"threshold_uncertainty_score":0.031160414},"labels":[],"label_agreement":null},{"id":"W7110020821","doi":"10.4230/lipics.cpm.2025.19","title":"The Trie Measure, Revisited","year":2025,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Trie; Cardinality (data modeling); Monotone polygon; Encoding (memory); Binary number; Integer (computer science); Sequence (biology); Binary logarithm; Focus (optics)","score_opus":0.00988895079960905,"score_gpt":0.2593516950114112,"score_spread":0.24946274421180215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110020821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12708662,0.006560079,0.80568796,0.003461874,0.0004620747,0.00018354558,0.0007879106,0.0010642643,0.054705583],"genre_scores_gemma":[0.59934294,0.003162441,0.37132296,0.0010346284,0.0006912128,0.00039766077,0.0009990229,0.0009376001,0.022111552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99689543,0.00095841364,0.00018743589,0.0007522948,0.0008473722,0.00035909915],"domain_scores_gemma":[0.99117064,0.005664043,0.0008005166,0.0012680981,0.0006926249,0.00040404266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021784552,0.0011749913,0.0015391199,0.0017208584,0.0014374919,0.0032793419,0.002894907,0.002197575,0.00799174],"category_scores_gemma":[0.017219111,0.00072446704,0.0012858289,0.003551878,0.0034911016,0.010474402,0.0027384132,0.0039574103,0.0013005226],"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":[0.00017545851,0.00010721616,0.0008106785,0.00032655033,0.000061585095,0.00013154237,0.00038603434,0.054762047,0.0042954865,0.8748402,0.0064108456,0.057692472],"study_design_scores_gemma":[0.000053004496,0.000294236,0.00042706204,0.00007919247,0.000066305176,0.00051362603,0.00024986826,0.24817272,0.006202139,0.72516173,0.018717134,0.00006292699],"about_ca_topic_score_codex":0.0013945379,"about_ca_topic_score_gemma":0.0011560621,"teacher_disagreement_score":0.00799174,"about_ca_system_score_codex":0.0025859172,"about_ca_system_score_gemma":0.0014156481,"threshold_uncertainty_score":0.026735008},"labels":[],"label_agreement":null},{"id":"W7110117496","doi":"10.4230/oasics.grossi.10","title":"Faster run-length compressed suffix arrays.","year":2025,"lang":"en","type":"article","venue":"PubMed","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institutes of Health; Agencia Nacional de Investigación y Desarrollo; Centre for Biotechnology and Bioengineering; Ministero della Salute; Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University","keywords":"Search engine indexing; Suffix; Compressed suffix array; Interval (graph theory); Suffix array; Binary logarithm; Suffix tree; Alphabet; Log-log plot","score_opus":0.01550374496687705,"score_gpt":0.21933296344423675,"score_spread":0.20382921847735969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110117496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042797025,0.010002421,0.81131196,0.005836475,0.0029305604,0.0011031572,0.011036761,0.06707026,0.04791145],"genre_scores_gemma":[0.15078324,0.0013409033,0.80318755,0.0016459381,0.00079567824,0.00080280105,0.012696659,0.002392461,0.02635471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662435,0.00067061617,0.00035351494,0.00065510697,0.001429697,0.000266683],"domain_scores_gemma":[0.9912321,0.0029490886,0.0005215498,0.003552195,0.0014353048,0.00030968452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017001275,0.0011539486,0.0011236977,0.0025553568,0.0008312359,0.0032267268,0.002260998,0.0014126941,0.033236943],"category_scores_gemma":[0.014675897,0.0006297547,0.0009826345,0.0061758305,0.00081665243,0.006230763,0.0023552252,0.0018741005,0.0205583],"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":[0.0012243667,0.0003001099,0.0017342041,0.00083653524,0.000118519696,0.00017579352,0.00031888168,0.008988845,0.029910075,0.0560956,0.08267896,0.8176181],"study_design_scores_gemma":[0.0010606609,0.0009873401,0.0020822794,0.00043390132,0.0002598671,0.00219295,0.00063163287,0.33310264,0.11365965,0.23543249,0.30997446,0.00018204858],"about_ca_topic_score_codex":0.0016874743,"about_ca_topic_score_gemma":0.0040755514,"teacher_disagreement_score":0.033236943,"about_ca_system_score_codex":0.0014146253,"about_ca_system_score_gemma":0.0032238737,"threshold_uncertainty_score":0.11118865},"labels":[],"label_agreement":null},{"id":"W7126268783","doi":"10.1109/iscmi67495.2025.11358636","title":"Graph Compression with a Genetic Algorithm: Exploring Fitness, Randomness, and Efficiency","year":2025,"lang":"","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Merge (version control); Graph; Set (abstract data type); Fitness function; Genetic algorithm; Data compression","score_opus":0.01769186209384433,"score_gpt":0.23415947685557192,"score_spread":0.2164676147617276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126268783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5287044,0.0011548718,0.46211928,0.00087864045,0.00006457207,0.00024502544,0.00014428142,0.0011877184,0.005501106],"genre_scores_gemma":[0.5972397,0.00044388176,0.40059915,0.00011216273,0.000032043044,0.0001965439,0.00023965271,0.0001759323,0.00096094125],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991462,0.00034073248,0.000036211044,0.00014481143,0.00025476838,0.00007719123],"domain_scores_gemma":[0.9948095,0.004031526,0.00021630654,0.0004408026,0.00042818915,0.000073571784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022866074,0.0009790928,0.0009841458,0.0023620597,0.00058519596,0.001165405,0.0013904235,0.0011712143,0.0008108631],"category_scores_gemma":[0.009205986,0.00038636185,0.00073217467,0.0018886026,0.0011508727,0.0018269158,0.0007613255,0.00081353134,0.00014429013],"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":[0.00020713783,0.00020996138,0.004984403,0.0001486945,0.00008988055,0.00015458552,0.0002731803,0.8482222,0.0067397277,0.010682384,0.0009637655,0.12732407],"study_design_scores_gemma":[0.00003119251,0.00008348456,0.0005110232,0.000015914888,0.000022530592,0.00004756,0.00006443077,0.9906318,0.0030168265,0.0050651287,0.00049947633,0.000010587071],"about_ca_topic_score_codex":0.0051423376,"about_ca_topic_score_gemma":0.004589607,"teacher_disagreement_score":0.0051423376,"about_ca_system_score_codex":0.0013731348,"about_ca_system_score_gemma":0.0013613851,"threshold_uncertainty_score":0.012092888},"labels":[],"label_agreement":null},{"id":"W7135553930","doi":"","title":"Dictionary methods as second phase of BWT","year":2007,"lang":"sk","type":"dissertation","venue":"Digital Repository (National Repository of Grey Literature)","topic":"Algorithms and Data Compression","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":"","keywords":"Lossless compression; Huffman coding; Data compression; Encoding (memory); Compression (physics); Phase (matter); XML","score_opus":0.015255515335693292,"score_gpt":0.35160050987106184,"score_spread":0.33634499453536854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135553930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010857755,0.00067143573,0.9750649,0.00018711308,0.00019348896,0.00023303306,0.00033292905,0.0031261982,0.00933325],"genre_scores_gemma":[0.08088685,0.00073658815,0.8971993,0.00013783941,0.00011843683,0.000389448,0.001325772,0.0010010364,0.018204719],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982968,0.0002551947,0.00012988171,0.0002487054,0.00095377804,0.00011559765],"domain_scores_gemma":[0.99849534,0.0004494557,0.00009481407,0.00039917493,0.00051172776,0.000049417406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009455087,0.00070045906,0.00058373256,0.002123939,0.0005678329,0.002216684,0.0010172514,0.00080496067,0.013262807],"category_scores_gemma":[0.0037921562,0.00028227805,0.000552446,0.0031044509,0.0006829118,0.0020757408,0.0012183553,0.0011614282,0.008926886],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033369518,0.00010176705,0.00077459286,0.00037543642,0.00003341043,0.00013173642,0.00032847453,0.007909883,0.0634262,0.07908768,0.008663578,0.8388337],"study_design_scores_gemma":[0.00018514686,0.0006780042,0.001976079,0.00017996684,0.00008113103,0.0021370077,0.00048489714,0.31273377,0.39556146,0.07475099,0.21112852,0.00010297822],"about_ca_topic_score_codex":0.0010961697,"about_ca_topic_score_gemma":0.00090201857,"teacher_disagreement_score":0.013262807,"about_ca_system_score_codex":0.0006024687,"about_ca_system_score_gemma":0.001147958,"threshold_uncertainty_score":0.044368505},"labels":[],"label_agreement":null},{"id":"W7145257302","doi":"","title":"Compression by Substring Enumeration Using Sorted Contingency Tables","year":2020,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Algorithms and Data Compression","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":"Japan Society for the Promotion of Science","keywords":"Substring; Lexicographical order; Enumeration; Upper and lower bounds; Contingency table; Encoding (memory); Compression (physics); Table (database)","score_opus":0.03307146768172269,"score_gpt":0.2559402002473943,"score_spread":0.22286873256567158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7145257302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06648261,0.0011069523,0.9273599,0.0002273578,0.00009031498,0.0001397591,0.00042996072,0.0017105576,0.0024526743],"genre_scores_gemma":[0.27061185,0.0006587387,0.7241516,0.00018352781,0.00008203943,0.00014379212,0.0015001677,0.00018483761,0.00248335],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99914324,0.0001278823,0.000113779286,0.00015461266,0.00038840753,0.000072054645],"domain_scores_gemma":[0.9976332,0.0012381577,0.00017244328,0.00048212876,0.00042606267,0.000047879646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065283827,0.00054168026,0.00070360996,0.002238806,0.0003845818,0.00080426596,0.0008957842,0.00040670374,0.0018029175],"category_scores_gemma":[0.004218101,0.00026196317,0.00037479596,0.0025647483,0.00048913085,0.0019899851,0.000699093,0.0007430465,0.00048463652],"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":[0.0005550567,0.00012290952,0.0023575258,0.000219577,0.00004676625,0.00027228132,0.00018085801,0.05537711,0.042348824,0.02815121,0.0034979973,0.86686987],"study_design_scores_gemma":[0.000114606984,0.00035057298,0.002503018,0.00008350679,0.00006542271,0.0010290802,0.0001701431,0.8256054,0.12155513,0.032173432,0.016270239,0.00007943918],"about_ca_topic_score_codex":0.0020519206,"about_ca_topic_score_gemma":0.0027274978,"teacher_disagreement_score":0.002238806,"about_ca_system_score_codex":0.00054991664,"about_ca_system_score_gemma":0.0009955273,"threshold_uncertainty_score":0.006031394},"labels":[],"label_agreement":null},{"id":"W7153241338","doi":"10.47749/t/unicamp.2025.1530178","title":"The gray-sorted distance","year":2025,"lang":"","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":"National Institute of Standards and Technology; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Work (physics); Closure (psychology); Point (geometry); Table (database)","score_opus":0.011036885584843201,"score_gpt":0.267813581765854,"score_spread":0.2567766961810108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7153241338","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047091424,0.005202255,0.9311636,0.0009280498,0.00088998437,0.0001465152,0.0007077496,0.0010554609,0.012814957],"genre_scores_gemma":[0.40229148,0.003754047,0.5745646,0.0006266748,0.0004612931,0.00014129965,0.0011600857,0.00034738172,0.016653154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800533,0.00030278825,0.00014916735,0.0003781435,0.0010315345,0.00013311756],"domain_scores_gemma":[0.9981718,0.000519025,0.0001093509,0.0003659847,0.00073793833,0.00009585865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010669224,0.0005247286,0.000819228,0.0039235614,0.00057406345,0.0031321696,0.001311834,0.00095760316,0.0051022647],"category_scores_gemma":[0.00525735,0.00021015502,0.0007795306,0.0042371787,0.0013981069,0.0033048843,0.001487096,0.00091343455,0.0015013303],"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":[0.0004870897,0.00009674163,0.0024788955,0.00044232345,0.00012715283,0.0001172624,0.00028747096,0.023969572,0.025416873,0.14932053,0.007587902,0.7896682],"study_design_scores_gemma":[0.00010165547,0.0008443886,0.008383054,0.00025240215,0.00017748924,0.0020384581,0.00080500083,0.5661413,0.07041046,0.19544455,0.15517794,0.00022326282],"about_ca_topic_score_codex":0.004228105,"about_ca_topic_score_gemma":0.0025884975,"teacher_disagreement_score":0.0051022647,"about_ca_system_score_codex":0.0014546599,"about_ca_system_score_gemma":0.0016518665,"threshold_uncertainty_score":0.017068803},"labels":[],"label_agreement":null},{"id":"W73714569","doi":"10.1007/978-3-0348-8211-8_16","title":"A Note on Random Suffix Search Trees","year":2002,"lang":"en","type":"book-chapter","venue":"Birkhäuser Basel eBooks","topic":"Algorithms and Data Compression","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":"McGill University","funders":"","keywords":"Combinatorics; Suffix tree; Mathematics; Independent and identically distributed random variables; Random binary tree; Self-balancing binary search tree; Tree (set theory); Binary search tree; Suffix; Optimal binary search tree; Sequence (biology); Binary tree; Binary number; Binary logarithm; Search tree; Discrete mathematics; K-ary tree; Random variable; Search algorithm; Algorithm; Tree structure; Arithmetic; Statistics; Chemistry","score_opus":0.03655109184865478,"score_gpt":0.25138651067222967,"score_spread":0.21483541882357488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73714569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011580398,0.020170126,0.8662139,0.0056000217,0.0018771063,0.00018863582,0.0006717726,0.001522945,0.09217505],"genre_scores_gemma":[0.25106588,0.035351813,0.59757847,0.0057155835,0.0066797375,0.001031544,0.0019396348,0.0025166008,0.0981208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970553,0.0009860384,0.00016692802,0.00042615953,0.0011502632,0.00021535282],"domain_scores_gemma":[0.99109125,0.0063846703,0.00023699294,0.001477442,0.00064656476,0.00016301851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030334033,0.00092818803,0.0014493825,0.0016986665,0.0017085562,0.003065443,0.0019712143,0.0021889105,0.008967566],"category_scores_gemma":[0.01886715,0.0009301229,0.0012186298,0.0048926994,0.003113645,0.010001831,0.0033161542,0.006319797,0.0059342273],"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":[0.00009785243,0.000040339157,0.00033817333,0.00020850454,0.000022355549,0.00022179197,0.00018499099,0.023857241,0.001605275,0.85936326,0.02543971,0.08862046],"study_design_scores_gemma":[0.000035728557,0.000059011298,0.00023818821,0.00012738844,0.000019096196,0.00065511727,0.000038187205,0.0851025,0.0020911398,0.8343026,0.07728741,0.000043732147],"about_ca_topic_score_codex":0.0016664045,"about_ca_topic_score_gemma":0.0013615504,"teacher_disagreement_score":0.008967566,"about_ca_system_score_codex":0.001652727,"about_ca_system_score_gemma":0.0012432194,"threshold_uncertainty_score":0.029999554},"labels":[],"label_agreement":null},{"id":"W77988331","doi":"10.1007/0-306-47015-2_20","title":"Parallel Processing of the Evolving Tree Transformation System","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Algorithms and Data Compression","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":"University of New Brunswick","funders":"","keywords":"Speedup; Computer science; Implementation; Parallel computing; Process (computing); Tree (set theory); Transformation (genetics); Software; Parallelism (grammar); Operating system; Programming language","score_opus":0.01864597990004742,"score_gpt":0.22595139230266068,"score_spread":0.20730541240261324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W77988331","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08837712,0.00016692755,0.89993507,0.00014640046,0.00008994072,0.00005682009,0.00008256581,0.0021677038,0.008977387],"genre_scores_gemma":[0.6210446,0.00025722384,0.36973476,0.000063857275,0.00004821892,0.00010543145,0.00038253466,0.00025916813,0.008104263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975294,0.000055856384,0.000016084598,0.000044047156,0.000107838845,0.000023191904],"domain_scores_gemma":[0.99956137,0.0001695893,0.000025834124,0.0001101334,0.00010962642,0.000023408735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030655653,0.00019465847,0.00029863275,0.00026264967,0.00030260824,0.00062522636,0.00055801676,0.00026648093,0.0032176417],"category_scores_gemma":[0.0013772406,0.00012354269,0.00028538267,0.00052309566,0.0003672284,0.0007514417,0.00051193114,0.0004900897,0.00061366695],"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":[0.00030054792,0.000091558664,0.0014516122,0.00013104697,0.000041585976,0.0004537061,0.00024847224,0.35561413,0.08165582,0.10177255,0.0052925423,0.45294634],"study_design_scores_gemma":[0.000023880291,0.00006473112,0.0003397113,0.000004629079,0.000007983485,0.00015340811,0.00001986846,0.9471142,0.019659469,0.024400266,0.008201668,0.000009997293],"about_ca_topic_score_codex":0.000676642,"about_ca_topic_score_gemma":0.0004933188,"teacher_disagreement_score":0.0032176417,"about_ca_system_score_codex":0.00025667658,"about_ca_system_score_gemma":0.00034488263,"threshold_uncertainty_score":0.010764062},"labels":[],"label_agreement":null},{"id":"W808699425","doi":"10.5120/20786-3434","title":"A Hybrid OpenMP-MPI Parallelization of Structure Software","year":2015,"lang":"en","type":"article","venue":"International Journal of Computer Applications","topic":"Algorithms and Data Compression","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":"Trent University","funders":"","keywords":"Computer science; Parallel computing; Software; Computational science; Operating system","score_opus":0.017621122317937474,"score_gpt":0.2838205532360191,"score_spread":0.2661994309180816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W808699425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12210608,0.0003002797,0.8393555,0.00060119206,0.00016864394,0.00035164962,0.00050530763,0.023839977,0.0127714025],"genre_scores_gemma":[0.2960366,0.00018774382,0.6934385,0.0002224469,0.00007330178,0.0007061728,0.0018778136,0.001778721,0.0056787506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906117,0.00017499937,0.00003774404,0.00015646993,0.00047745195,0.00009216789],"domain_scores_gemma":[0.9988882,0.00027107805,0.000057616577,0.00038339815,0.00032413515,0.00007557957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083608116,0.00065561914,0.00054284476,0.00069092424,0.0008645472,0.0011561298,0.0025546118,0.00075200084,0.0020888268],"category_scores_gemma":[0.0031273703,0.0005008111,0.0008012265,0.0012098813,0.00062309427,0.0010092503,0.001456509,0.0014518644,0.0009545525],"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":[0.0012707257,0.0009903805,0.012985397,0.00042485647,0.00048349387,0.0009358068,0.00101552,0.2879187,0.09845292,0.063316114,0.02654056,0.5056655],"study_design_scores_gemma":[0.00023630662,0.0003016939,0.00309917,0.000022425982,0.00004727254,0.00022794951,0.00007945706,0.92259413,0.036205698,0.018939672,0.01819022,0.000056008386],"about_ca_topic_score_codex":0.0020983927,"about_ca_topic_score_gemma":0.00258332,"teacher_disagreement_score":0.0025546118,"about_ca_system_score_codex":0.0005461005,"about_ca_system_score_gemma":0.0014252885,"threshold_uncertainty_score":0.00698781},"labels":[],"label_agreement":null},{"id":"W816103523","doi":"","title":"Optimal search trees with 2-way comparisons?","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Algorithms and Data Compression","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 Waterloo","funders":"","keywords":"Computer science","score_opus":0.033504911361875056,"score_gpt":0.2552714701103656,"score_spread":0.22176655874849055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W816103523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10223967,0.005226819,0.8417333,0.0028837116,0.00058556104,0.00023747096,0.0008768304,0.0023187455,0.043897953],"genre_scores_gemma":[0.4551338,0.0012704642,0.52405334,0.0010245069,0.00037284312,0.00025877112,0.0010506373,0.0006191366,0.016216537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981786,0.00044963567,0.000090964604,0.00053655636,0.0004011117,0.0003432027],"domain_scores_gemma":[0.99768806,0.0015088563,0.00018436485,0.00036990977,0.00015388093,0.00009496482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013674794,0.0007348431,0.0011718861,0.0006689784,0.00076596206,0.0026200486,0.001119092,0.0013499523,0.016580025],"category_scores_gemma":[0.0067443443,0.0007717612,0.00090684823,0.0018460847,0.0011057984,0.00760325,0.0018209438,0.0019016023,0.0026806633],"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":[0.0019426132,0.00040213377,0.0023881155,0.0011246845,0.00014285413,0.00037243328,0.0005389194,0.096811764,0.01186163,0.49776265,0.037726533,0.34892574],"study_design_scores_gemma":[0.00039981084,0.00024966788,0.00074704154,0.00016791484,0.00007328964,0.00065295,0.00016918985,0.24892946,0.008175587,0.70584553,0.034537353,0.00005215881],"about_ca_topic_score_codex":0.00095032476,"about_ca_topic_score_gemma":0.001437665,"teacher_disagreement_score":0.016580025,"about_ca_system_score_codex":0.0013275108,"about_ca_system_score_gemma":0.0013326394,"threshold_uncertainty_score":0.0554657},"labels":[],"label_agreement":null},{"id":"W892404463","doi":"10.1007/s00500-015-1769-3","title":"The Agile particle swarm optimizer applied to proteomic pattern matching and discovery","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Particle swarm optimization; Local optimum; Computer science; Fitness function; Benchmark (surveying); Swarm behaviour; Mathematical optimization; Local search (optimization); Multi-swarm optimization; Fitness approximation; Convergence (economics); Algorithm; Artificial intelligence; Mathematics; Genetic algorithm","score_opus":0.017599999115322874,"score_gpt":0.24627912457139295,"score_spread":0.22867912545607008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W892404463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028031679,0.00035188458,0.9682976,0.00025930285,0.00011919238,0.00008423423,0.0000592333,0.0009126103,0.0018843082],"genre_scores_gemma":[0.28545332,0.00036136585,0.71011996,0.0002731222,0.00009091999,0.00029296314,0.00015037782,0.0002243822,0.0030335945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959,0.00014671944,0.000027862738,0.00005315772,0.00015030568,0.00003201115],"domain_scores_gemma":[0.9991748,0.00048431128,0.000053260246,0.00010244019,0.00014990306,0.00003524641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016591713,0.0006082968,0.00095133664,0.00079849554,0.0004670043,0.0009768946,0.00092479336,0.00090425846,0.0012466931],"category_scores_gemma":[0.0033702,0.00045892363,0.00053797354,0.00094292406,0.00046993507,0.0006233681,0.00096218,0.0009950271,0.0003740785],"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":[0.00028611126,0.00012565608,0.0020419478,0.00013487616,0.00016971362,0.00012454964,0.00009238087,0.682049,0.007726349,0.012950697,0.0035243793,0.2907743],"study_design_scores_gemma":[0.000012086492,0.000021800754,0.00012450594,0.0000031332083,0.0000060481552,0.000014973182,0.0000049991713,0.99668616,0.0009527961,0.0016780113,0.00049256504,0.0000030214474],"about_ca_topic_score_codex":0.0029363113,"about_ca_topic_score_gemma":0.0025669304,"teacher_disagreement_score":0.0029363113,"about_ca_system_score_codex":0.00044384168,"about_ca_system_score_gemma":0.0009768249,"threshold_uncertainty_score":0.008774638},"labels":[],"label_agreement":null},{"id":"W941738672","doi":"10.1016/j.tcs.2015.06.037","title":"Three overlapping squares: The general case characterized &amp; applications","year":2015,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Combinatorics; Computer science; Algebra over a field; Algorithm; Pure mathematics","score_opus":0.033579848746125164,"score_gpt":0.29099748231754263,"score_spread":0.25741763357141745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W941738672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1872972,0.0006561394,0.74164623,0.0009779311,0.00018074799,0.00008202935,0.00016720856,0.00038350275,0.068609014],"genre_scores_gemma":[0.7925263,0.00030842112,0.18818238,0.00023972284,0.00012638699,0.00005819695,0.0001507362,0.00014289803,0.018264936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988764,0.00026173814,0.00005244917,0.00023660732,0.0003920983,0.00018077137],"domain_scores_gemma":[0.9973205,0.0011912042,0.00030533018,0.00048422642,0.000454283,0.00024452427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009823004,0.0006532385,0.0010076906,0.00065004785,0.0009596015,0.0018053856,0.0018959075,0.002570671,0.008255845],"category_scores_gemma":[0.006115977,0.00050168595,0.00063173246,0.0016236942,0.0019525682,0.0018462507,0.0021709558,0.0014590987,0.0011053655],"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":[0.0009055433,0.00024632394,0.0058067203,0.00047466648,0.00012280302,0.0052963556,0.0008301289,0.1826773,0.02141781,0.61222804,0.007629694,0.16236466],"study_design_scores_gemma":[0.000067246794,0.000100814505,0.0015398532,0.000034311925,0.00004129232,0.00360441,0.00041102947,0.7178217,0.007550118,0.25749737,0.011255396,0.00007652781],"about_ca_topic_score_codex":0.0010389972,"about_ca_topic_score_gemma":0.0010233924,"teacher_disagreement_score":0.008255845,"about_ca_system_score_codex":0.0003918273,"about_ca_system_score_gemma":0.0006436761,"threshold_uncertainty_score":0.027618527},"labels":[],"label_agreement":null},{"id":"W94179444","doi":"10.1002/net.10092","title":"A linear algorithm for compact box‐drawings of trees","year":2003,"lang":"en","type":"article","venue":"Networks","topic":"Algorithms and Data Compression","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":"University of Waterloo","funders":"","keywords":"Tree (set theory); Node (physics); Algorithm; Combinatorics; Computer science; Mathematics; Discrete mathematics; Engineering","score_opus":0.01584166116086022,"score_gpt":0.25901036155948726,"score_spread":0.24316870039862704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W94179444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015956467,0.00046166344,0.97617173,0.0001306177,0.000036940997,0.00015849015,0.00026659685,0.0038763527,0.002941007],"genre_scores_gemma":[0.07641503,0.0002872603,0.91888916,0.00004769361,0.000028112707,0.00026139917,0.0010407992,0.00031818677,0.002712327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991447,0.00017026454,0.000068572226,0.00016935443,0.00033851137,0.00010858962],"domain_scores_gemma":[0.99818736,0.0010146406,0.0001497011,0.00034520862,0.0002343467,0.00006872803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065476994,0.00091051316,0.0010926957,0.0014698207,0.0005373514,0.0011228807,0.0014636891,0.00087888195,0.01199491],"category_scores_gemma":[0.003694441,0.0006356836,0.00066235365,0.002293911,0.0005921168,0.0029995022,0.0019579867,0.0009206377,0.002548795],"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":[0.00043052773,0.00012755439,0.00051309506,0.00034697144,0.00004131145,0.00017138166,0.0003147361,0.0783677,0.012633729,0.04002879,0.018898265,0.8481259],"study_design_scores_gemma":[0.00024950097,0.00018247894,0.00034569175,0.00006968143,0.000033455846,0.00041287343,0.00016741823,0.8937962,0.014391629,0.06791893,0.022394802,0.000037290705],"about_ca_topic_score_codex":0.0017048809,"about_ca_topic_score_gemma":0.002379759,"teacher_disagreement_score":0.01199491,"about_ca_system_score_codex":0.0007207793,"about_ca_system_score_gemma":0.00065836293,"threshold_uncertainty_score":0.04012692},"labels":[],"label_agreement":null},{"id":"W94197046","doi":"10.1007/978-1-4939-2864-4_646","title":"Compressed Representations of Graphs","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.01480105077713292,"score_gpt":0.2518319579986708,"score_spread":0.23703090722153788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W94197046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016754638,0.008173979,0.87897843,0.002081779,0.0016155302,0.00017863513,0.0059354836,0.0055793044,0.08070221],"genre_scores_gemma":[0.24153304,0.016441647,0.58888036,0.0012265168,0.0017178088,0.00048700543,0.030063318,0.0026890403,0.11696134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996094,0.00007726238,0.000019513685,0.000071033945,0.00019239236,0.00003030507],"domain_scores_gemma":[0.99936444,0.00018609235,0.000032266933,0.0002698438,0.00012042086,0.000026916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022317386,0.000942106,0.0006563932,0.001766469,0.0003116799,0.001668756,0.0011601803,0.0008564636,0.026379427],"category_scores_gemma":[0.002221566,0.0003996047,0.00044819913,0.0026638224,0.00056695135,0.002320431,0.0014508546,0.0015730386,0.0076817386],"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":[0.00014999164,0.00006792604,0.00013361311,0.0004396416,0.000041923995,0.0001745684,0.00014964529,0.04670577,0.010653384,0.20157515,0.11214662,0.6277617],"study_design_scores_gemma":[0.000056580546,0.00009383116,0.00048388867,0.000252173,0.000040005652,0.0008483421,0.00016275838,0.3031604,0.017196694,0.48518702,0.19246398,0.000054397362],"about_ca_topic_score_codex":0.0009229023,"about_ca_topic_score_gemma":0.00138142,"teacher_disagreement_score":0.026379427,"about_ca_system_score_codex":0.00049723644,"about_ca_system_score_gemma":0.0004906193,"threshold_uncertainty_score":0.088248014},"labels":[],"label_agreement":null},{"id":"W964042512","doi":"10.1007/978-1-4615-1527-2_2","title":"Issues of Data Management","year":2001,"lang":"en","type":"book-chapter","venue":"˜The œKluwer international series on Asian studies in computer and information science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computation; Computer science; Data management; Business; Operations research; Database; Engineering; Algorithm","score_opus":0.05413809268399474,"score_gpt":0.3325943772451645,"score_spread":0.2784562845611698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W964042512","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031916953,0.11386483,0.09636826,0.20610358,0.020638138,0.00013035162,0.00041661152,0.0006029703,0.5586836],"genre_scores_gemma":[0.18875594,0.09773789,0.04303152,0.04684779,0.06023779,0.00049346115,0.0007869272,0.0012812666,0.5608274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99369353,0.0024775825,0.00043283444,0.0007858123,0.0022853375,0.00032496086],"domain_scores_gemma":[0.9892197,0.0044507408,0.00047354106,0.0032597552,0.001993253,0.0006029463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093359705,0.0008338578,0.0012514318,0.0035089166,0.0050212047,0.019878367,0.0028684349,0.004924195,0.034162346],"category_scores_gemma":[0.022129918,0.00083600427,0.0006313081,0.007945903,0.014475711,0.03469048,0.004675303,0.007045181,0.009918895],"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":[0.000005980012,0.000009759462,0.000048470698,0.00004762035,0.0000034007244,0.000014762779,0.00035574075,0.00006930947,0.000058637856,0.91212535,0.06251953,0.02474132],"study_design_scores_gemma":[0.000004802574,0.0000101407395,0.00008524384,0.00011812428,0.000005094607,0.00010202303,0.00037612257,0.00049458793,0.00012165505,0.44731078,0.5513623,0.000009132373],"about_ca_topic_score_codex":0.002267199,"about_ca_topic_score_gemma":0.0014855292,"teacher_disagreement_score":0.034162346,"about_ca_system_score_codex":0.004801119,"about_ca_system_score_gemma":0.0030724283,"threshold_uncertainty_score":0.114284396},"labels":[],"label_agreement":null},{"id":"W97511675","doi":"10.63317/3373r7z5hu7z","title":"TransSearch: A Free Translation Memory on the World Wide Web","year":2000,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; World Wide Web; The Internet","score_opus":0.04250910367630814,"score_gpt":0.25676944832921805,"score_spread":0.2142603446529099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W97511675","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040139694,0.004551455,0.6810533,0.0039231745,0.0014623792,0.0010355611,0.029594501,0.14981979,0.08842014],"genre_scores_gemma":[0.20045377,0.0039908546,0.5540495,0.0017957981,0.0011214381,0.0015096222,0.08413038,0.023956966,0.12899172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99624014,0.0014147136,0.00042328384,0.00049039454,0.0011952446,0.00023628914],"domain_scores_gemma":[0.9893138,0.0027422395,0.00063392526,0.0050529097,0.0016582451,0.00059890386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044697295,0.0011817298,0.0012373031,0.0047693565,0.0019719256,0.006526409,0.0021657362,0.0019616112,0.039669547],"category_scores_gemma":[0.020302987,0.0009431563,0.0006761486,0.008909,0.0014192234,0.01182217,0.005839717,0.0017806175,0.040352326],"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":[0.0017693206,0.00018581397,0.0017309125,0.00069641747,0.00012884603,0.00050440256,0.0015529728,0.0023202894,0.013673158,0.031840634,0.24787967,0.69771755],"study_design_scores_gemma":[0.0003904591,0.00035886417,0.003157505,0.00039817256,0.00012443183,0.0013907512,0.0013093262,0.030740425,0.05090726,0.05006381,0.86084884,0.00031010938],"about_ca_topic_score_codex":0.0021205836,"about_ca_topic_score_gemma":0.0028226168,"teacher_disagreement_score":0.039669547,"about_ca_system_score_codex":0.0007116077,"about_ca_system_score_gemma":0.001909584,"threshold_uncertainty_score":0.13270783},"labels":[],"label_agreement":null},{"id":"W982892443","doi":"10.1016/j.jda.2015.05.006","title":"On a lemma of Crochemore and Rytter","year":2015,"lang":"de","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Lemma (botany); Generalization; Mathematics; Combinatorics; Position (finance); Upper and lower bounds; Discrete mathematics; Mathematical analysis","score_opus":0.02995527514708905,"score_gpt":0.28109114939238333,"score_spread":0.25113587424529427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W982892443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03411299,0.019117268,0.7238773,0.028776115,0.00719456,0.00020206026,0.0010296591,0.0010670695,0.18462302],"genre_scores_gemma":[0.6580257,0.01962118,0.19208089,0.020780077,0.009498273,0.0007486426,0.0018687063,0.0026840821,0.094692536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959615,0.0012016894,0.00019793668,0.000960071,0.0011194622,0.00055937114],"domain_scores_gemma":[0.9830556,0.011938117,0.00044702835,0.0022738352,0.0018589873,0.00042642644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042441213,0.0017015073,0.0027964038,0.00454227,0.0035086165,0.0051671993,0.0028886828,0.0031483038,0.017173553],"category_scores_gemma":[0.029791474,0.0010377127,0.0026518535,0.00626635,0.008461587,0.016327195,0.011946562,0.00890626,0.0036329788],"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":[0.0002766922,0.000059151054,0.00038247087,0.00021106964,0.000046894813,0.00017394699,0.00042647243,0.0024437932,0.0017601463,0.9392055,0.023295846,0.03171802],"study_design_scores_gemma":[0.000057655747,0.0000616169,0.0004043522,0.00012668059,0.00006697222,0.00040023238,0.00013897853,0.01225962,0.0016143429,0.9502094,0.034603946,0.00005623332],"about_ca_topic_score_codex":0.0029513272,"about_ca_topic_score_gemma":0.0015950022,"teacher_disagreement_score":0.017173553,"about_ca_system_score_codex":0.0023424637,"about_ca_system_score_gemma":0.0014287491,"threshold_uncertainty_score":0.05745125},"labels":[],"label_agreement":null}]}