{"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031594175,0.0023963454,0.98871005,0.0027319586,0.0005355085,0.00042188837,0.00001876919,0.00019935762,0.0018267329],"genre_scores_gemma":[0.45840102,0.00022641479,0.54024124,0.00039138473,0.00015022146,0.000013172309,0.00005470638,0.000010668095,0.0005111825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977548,0.00014880837,0.0004548676,0.000812897,0.00046356214,0.0003650342],"domain_scores_gemma":[0.99858207,0.00023365188,0.00020500035,0.00040148039,0.00026475932,0.00031304345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012290517,0.00026961995,0.00026624085,0.00015833636,0.00056687393,0.00054622587,0.0011043639,0.00014756681,0.00025354352],"category_scores_gemma":[0.00005701731,0.00027538935,0.00004907241,0.0005081659,0.000119604585,0.0012053618,0.0012548771,0.00022970508,0.00021637026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002566791,0.00028715856,0.0020866646,0.00003603509,0.000051341467,0.000031085256,0.0013995678,0.03256936,0.000060010745,0.06989299,0.13834864,0.7552115],"study_design_scores_gemma":[0.0004958015,0.00013230571,0.05643963,0.00007936502,0.000009733934,0.00010890242,0.00003141752,0.7994428,0.0000037477691,0.13675526,0.0061918953,0.00030908862],"about_ca_topic_score_codex":0.00016531642,"about_ca_topic_score_gemma":0.0000033959077,"teacher_disagreement_score":0.7668735,"about_ca_system_score_codex":0.00007136682,"about_ca_system_score_gemma":0.00021393293,"threshold_uncertainty_score":0.99996984},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005398706,0.0016981096,0.9850139,0.00010145239,0.000113698596,0.0003101895,0.000028795406,0.000087007844,0.012641425],"genre_scores_gemma":[0.03508999,0.023992246,0.8823842,0.00077937613,0.0017054385,0.0006939337,0.0012687545,0.00024056771,0.053845495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857163,0.000016295744,0.00034198372,0.0006294499,0.00022349754,0.0002171094],"domain_scores_gemma":[0.99904144,0.00007459484,0.00017994539,0.0005580974,0.00005675741,0.0000891606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083632294,0.00024215857,0.0002788064,0.0002027024,0.00034580784,0.00013655922,0.00053880375,0.00009759175,0.000014141248],"category_scores_gemma":[0.0000056403737,0.0002184351,0.000034131746,0.00010579084,0.0002233506,0.00033188623,0.00029924457,0.00045431487,0.00003590695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004151548,0.00002789598,0.00012116537,0.000015059619,0.000011553915,0.000017165165,0.00016518455,0.0006357795,0.000004659494,0.05244214,0.0013168624,0.9452384],"study_design_scores_gemma":[0.000044072098,0.00007572957,0.00003650346,0.00046659363,0.000022108754,0.000034220502,0.00015456157,0.17221887,0.0003448584,0.036544178,0.7893236,0.00073468563],"about_ca_topic_score_codex":0.00004856819,"about_ca_topic_score_gemma":0.00002643466,"teacher_disagreement_score":0.9445037,"about_ca_system_score_codex":0.000031366362,"about_ca_system_score_gemma":0.000057618487,"threshold_uncertainty_score":0.89075255},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006656204,0.0008687632,0.99595344,0.000227526,0.0013621978,0.0002556399,0.0000140008815,0.00010018515,0.0011516633],"genre_scores_gemma":[0.3635633,0.000034390312,0.6353432,0.0005270344,0.00037099473,0.0000059331323,0.000014898348,0.00002706398,0.00011320752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962488,0.000033522756,0.00057640165,0.0010877668,0.0014946122,0.00055890763],"domain_scores_gemma":[0.996673,0.0005745671,0.00048116644,0.0017119686,0.00037535667,0.00018393421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008282967,0.0004325263,0.00050615007,0.00071812567,0.00018324927,0.00025455075,0.0035454454,0.0003712127,0.0000592782],"category_scores_gemma":[0.00008241145,0.00037679795,0.00011577207,0.0005520873,0.0005896264,0.0010334112,0.0013813572,0.0006746504,0.000033316694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063804905,0.000066830406,0.0005850584,0.00006892641,0.000008073302,0.000023577359,0.00024351485,0.040376224,0.00039576474,0.024031142,0.000037349768,0.93415713],"study_design_scores_gemma":[0.00032033146,0.00014034318,0.0012402566,0.00064695167,0.000010080065,0.000023361525,8.0953555e-8,0.91965276,0.005525989,0.06957184,0.0021743178,0.00069371786],"about_ca_topic_score_codex":0.00004316928,"about_ca_topic_score_gemma":0.000028917902,"teacher_disagreement_score":0.93346345,"about_ca_system_score_codex":0.00014848524,"about_ca_system_score_gemma":0.00082435657,"threshold_uncertainty_score":0.9998684},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104618885,0.000027189839,0.8907748,0.00020639454,0.000095073716,0.0012546354,0.000027380642,0.00014004436,0.0028555866],"genre_scores_gemma":[0.9948693,0.00014545537,0.0033103293,0.000045476303,0.000036669007,0.0000022772194,0.0010163195,0.000007505927,0.0005666898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980075,0.0003305529,0.00037861144,0.00037849243,0.00060097,0.00030391314],"domain_scores_gemma":[0.99774384,0.0001275494,0.00027658386,0.00028527767,0.0014074844,0.00015925571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935714,0.00017933728,0.00021199862,0.0012135716,0.0011114785,0.00030489897,0.00049966876,0.00020681422,0.0000057091943],"category_scores_gemma":[0.000076132084,0.00022460613,0.000058771388,0.0012044841,0.000104189334,0.0073331995,0.0001891493,0.00015955596,0.0000068821328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015765327,0.0010424735,0.0055433353,0.0007718759,0.00024000673,0.00006606932,0.017970843,0.036958195,0.2666793,0.6192978,0.0050201486,0.04483345],"study_design_scores_gemma":[0.0040918635,0.0030621293,0.010320951,0.00018568125,0.00008181135,0.00007023115,0.003255778,0.8346907,0.042424764,0.0019678168,0.09884221,0.0010060774],"about_ca_topic_score_codex":0.00015064026,"about_ca_topic_score_gemma":0.000008392743,"teacher_disagreement_score":0.8902504,"about_ca_system_score_codex":0.00035530404,"about_ca_system_score_gemma":0.0002341329,"threshold_uncertainty_score":0.9159172},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007787489,0.000036809444,0.9898665,0.00049113756,0.00061014964,0.00033005353,0.000013128142,0.00013086162,0.0007338511],"genre_scores_gemma":[0.806307,0.0000013862413,0.19330385,0.00026443248,0.00009903347,0.000008268126,0.0000022516892,0.000007825992,0.00000590971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705774,0.00007252324,0.00040602207,0.00076141674,0.0011098565,0.00059243845],"domain_scores_gemma":[0.9975021,0.00027822517,0.00015624655,0.0011215643,0.00046759725,0.00047430064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016156136,0.00021528383,0.0003273181,0.0001983556,0.00022637294,0.0002880437,0.0035169595,0.0000715066,0.000010050405],"category_scores_gemma":[0.00011407591,0.0001718092,0.0000846303,0.00082630134,0.0015808959,0.0009196678,0.002028946,0.0001380351,0.000010407293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004059156,0.00012873887,0.00014802054,0.000016376722,0.000006720881,0.000004713175,0.00041015356,0.001660671,0.00049672736,0.9593083,0.0005252641,0.03725371],"study_design_scores_gemma":[0.000775897,0.0002798424,0.00041381828,0.000036778918,0.00000407338,0.000010127116,0.0000109295515,0.83136344,0.0074279266,0.15851438,0.00096359185,0.00019920821],"about_ca_topic_score_codex":0.0000115472785,"about_ca_topic_score_gemma":2.8654466e-7,"teacher_disagreement_score":0.82970273,"about_ca_system_score_codex":0.000059934686,"about_ca_system_score_gemma":0.00021684605,"threshold_uncertainty_score":0.7006176},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018555736,0.00009960022,0.9762758,0.0014417237,0.0004979498,0.0002680295,0.0000045819,0.000074458214,0.0027821297],"genre_scores_gemma":[0.8523432,0.00001545708,0.14744438,0.00009867031,0.000052099575,0.00000878684,3.762141e-7,0.000008019193,0.000028999666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751365,0.00013059918,0.000413109,0.00045136502,0.0010515766,0.0004396849],"domain_scores_gemma":[0.99718684,0.0007215251,0.00020052415,0.0015828174,0.00018523789,0.00012307959],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012688126,0.00018871677,0.00019568828,0.00005941898,0.0011895157,0.0005748364,0.0042260345,0.00004323033,0.000033023567],"category_scores_gemma":[0.00024899357,0.0000897381,0.0001331498,0.00080976996,0.0027986625,0.00053931214,0.001880978,0.00019910237,0.00003759225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.746948e-7,0.000057232504,0.000021682372,0.000013134421,0.000004227333,9.857946e-7,0.0018666787,0.00011446059,0.00057043065,0.9760778,0.000119185606,0.021153217],"study_design_scores_gemma":[0.00010912532,0.000054093616,0.0003906705,0.00006119086,0.0000063196553,0.000019193774,0.00005115407,0.88158864,0.002632379,0.11482771,0.00013239328,0.00012714101],"about_ca_topic_score_codex":0.0000027040023,"about_ca_topic_score_gemma":6.7704343e-7,"teacher_disagreement_score":0.8814742,"about_ca_system_score_codex":0.000027538772,"about_ca_system_score_gemma":0.00003743158,"threshold_uncertainty_score":0.9999151},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057690637,0.0006212854,0.99196774,0.00027143088,0.0006235861,0.000259232,0.000010983092,0.00007355086,0.00040310068],"genre_scores_gemma":[0.11168752,0.000055381945,0.88789785,0.00013450734,0.0001431383,0.0000016928246,0.0000051861703,0.000014080351,0.00006065964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704146,0.000036367757,0.00043171772,0.0011666407,0.0008840285,0.00043978138],"domain_scores_gemma":[0.99820924,0.00025589185,0.00020923717,0.0009645766,0.00020538371,0.00015565882],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005785127,0.00036351176,0.0004519365,0.00052919996,0.00027408262,0.00032798643,0.0015565241,0.00023419832,0.000009895155],"category_scores_gemma":[0.000029002516,0.00030734626,0.000077214114,0.00042202917,0.0013313732,0.00027879456,0.0014478848,0.00054021896,0.00000628802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008325417,0.000030223002,0.00003175468,0.000019674068,0.0000040688114,0.000031923228,0.0004161492,0.15668549,0.00034209597,0.0038085803,0.000004841778,0.8386169],"study_design_scores_gemma":[0.00027083862,0.00030375918,0.0009152961,0.00031988745,0.0000046606838,0.00010108691,3.507639e-7,0.99178135,0.0011107291,0.0045809075,0.00027871534,0.0003324032],"about_ca_topic_score_codex":0.00003474125,"about_ca_topic_score_gemma":0.0000064410733,"teacher_disagreement_score":0.8382845,"about_ca_system_score_codex":0.00009178768,"about_ca_system_score_gemma":0.00034764607,"threshold_uncertainty_score":0.9999379},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093875633,0.0031290806,0.9209996,0.003539664,0.015086786,0.0023625465,0.0011912473,0.0006859053,0.052066408],"genre_scores_gemma":[0.0038062055,0.00026515694,0.6868354,0.0035521458,0.010185011,0.00006535592,0.0010457265,0.00028209004,0.2939629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943969,0.000019934736,0.00067751284,0.002257618,0.0015373413,0.0011106955],"domain_scores_gemma":[0.9972394,0.00011063608,0.0003560099,0.0016081105,0.00024056205,0.00044527947],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00077882764,0.000728923,0.00061260886,0.0006917613,0.00035609113,0.0012795572,0.006217861,0.00039673565,0.00012760687],"category_scores_gemma":[0.000045576082,0.0006264485,0.00005856113,0.00014860979,0.00041002053,0.001132027,0.006689306,0.0011570818,0.000008361533],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028861852,0.00005209574,0.00017254263,0.00010891575,0.00012649015,0.0002072246,0.0010190669,0.00043956752,0.00013536352,0.0028304257,0.2277047,0.7671747],"study_design_scores_gemma":[0.00074821716,0.000030189904,0.0006582375,0.0006443462,0.000030521936,0.00013026528,0.000007977974,0.16925707,0.00035646692,0.0040256577,0.8228794,0.0012316474],"about_ca_topic_score_codex":0.01170232,"about_ca_topic_score_gemma":0.09526677,"teacher_disagreement_score":0.7659431,"about_ca_system_score_codex":0.0008366223,"about_ca_system_score_gemma":0.0030549702,"threshold_uncertainty_score":0.99975723},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2717571,0.0004326547,0.6894295,0.00039206987,0.0053979545,0.00042708553,0.000003353235,0.0008642477,0.031296022],"genre_scores_gemma":[0.9530831,0.000007768113,0.046545733,0.00015057327,0.000016516371,0.000005721685,0.0000036011133,0.0000105344425,0.00017644482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988373,0.000018931049,0.00019894834,0.00031464602,0.00028678597,0.00034342054],"domain_scores_gemma":[0.99909365,0.00007592067,0.0000670061,0.00058617495,0.000056936937,0.00012032213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045309184,0.00011718435,0.00011678403,0.00007611376,0.00013800972,0.0001298164,0.00077344564,0.00005708317,0.000012153254],"category_scores_gemma":[0.000018881745,0.000107099295,0.000041677245,0.0003395268,0.00001924632,0.0006199851,0.00047017302,0.00013426627,0.00010918095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045291195,0.00007573763,0.0009873931,0.000009261142,0.0000061700866,0.000040863164,0.00022009735,0.0000088862635,0.0006496778,0.9612885,0.0027425226,0.03396634],"study_design_scores_gemma":[0.0012794669,0.00023283888,0.015061933,0.000089474415,0.0000055080122,0.000040982606,0.00003211277,0.012237134,0.007854097,0.89102924,0.07160628,0.00053095084],"about_ca_topic_score_codex":0.0000527383,"about_ca_topic_score_gemma":0.000003033572,"teacher_disagreement_score":0.68132603,"about_ca_system_score_codex":0.000043929696,"about_ca_system_score_gemma":0.00003324561,"threshold_uncertainty_score":0.43673825},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19782142,0.000113494374,0.79011256,0.00023440062,0.00036357838,0.0003466429,0.000025990228,0.00011941866,0.010862529],"genre_scores_gemma":[0.8892636,0.0000047352473,0.11029081,0.00031854314,0.000025323634,0.000009078586,0.00003922717,0.000004971353,0.000043713473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987848,0.00001992344,0.0005193309,0.0001089872,0.0003565787,0.00021042832],"domain_scores_gemma":[0.9991277,0.000042029948,0.00016354099,0.00044628547,0.00010432364,0.00011611862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002820259,0.0000987984,0.00021337124,0.000108574684,0.000033539436,0.00006134709,0.000655505,0.00004133343,0.000021726572],"category_scores_gemma":[0.00006226837,0.000083948486,0.000021115891,0.00048444927,0.000033464472,0.0012418608,0.00054982875,0.00011841198,0.00009744281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015058019,0.0019334725,0.2155956,0.0004707541,0.00008459502,0.00001796905,0.07510878,0.016715938,0.0004874618,0.07605865,0.1551847,0.45819148],"study_design_scores_gemma":[0.0012167834,0.00021547737,0.0020933703,0.000052196905,0.000002861156,0.0000033487652,0.0012749843,0.90560335,0.0021335988,0.0010387634,0.08615928,0.00020600417],"about_ca_topic_score_codex":0.00013999829,"about_ca_topic_score_gemma":0.0000089958185,"teacher_disagreement_score":0.8888874,"about_ca_system_score_codex":0.00004427382,"about_ca_system_score_gemma":0.00009133909,"threshold_uncertainty_score":0.34233198},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000039194383,0.001233657,0.9899263,0.0012307271,0.003562279,0.00045495704,0.000016507445,0.00020261017,0.0033690773],"genre_scores_gemma":[0.00162339,0.00034329298,0.99243176,0.0015270712,0.0011472566,0.00003054643,0.000013875433,0.00005562025,0.0028271892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533784,0.00004892023,0.0005876523,0.0016692363,0.0014289563,0.000927415],"domain_scores_gemma":[0.99555933,0.00076053373,0.0003480459,0.0027387317,0.0003363519,0.000256994],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010204508,0.0006180476,0.00047448726,0.00038688502,0.0010552757,0.0017807191,0.007591217,0.00032275167,0.000040460407],"category_scores_gemma":[0.000066784414,0.00039765515,0.00015239684,0.0005275745,0.0011363468,0.0010400201,0.0036337948,0.001072981,0.00033795668],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.933921e-7,0.000011701399,0.000003469521,0.0000056579156,0.000006950424,0.000037594717,0.00011969941,0.00094135967,0.000018952298,0.015490065,0.00044713687,0.9829164],"study_design_scores_gemma":[0.00016305414,0.00010189165,0.000061972976,0.00017070178,0.0000043987498,0.00007671955,1.0964412e-7,0.74690133,0.00025255748,0.19956064,0.052163735,0.0005428887],"about_ca_topic_score_codex":0.00007542991,"about_ca_topic_score_gemma":0.00006711125,"teacher_disagreement_score":0.98237354,"about_ca_system_score_codex":0.00020979074,"about_ca_system_score_gemma":0.00045303194,"threshold_uncertainty_score":0.99984753},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017353539,0.00079253747,0.98497635,0.00074651645,0.0024383971,0.00035707973,0.000008723241,0.00023567455,0.010427346],"genre_scores_gemma":[0.010046979,0.00012720985,0.9847518,0.001952232,0.0009524112,0.000022129503,0.000012470897,0.000048127866,0.0020866466],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99610835,0.000029911014,0.00047719822,0.0016164349,0.0010665555,0.0007015577],"domain_scores_gemma":[0.9969098,0.00029685948,0.0002629193,0.0020608292,0.00024112649,0.00022846862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051561504,0.00056711584,0.0005432768,0.0005892623,0.00032049583,0.00097322435,0.0044836914,0.00032914517,0.00015606731],"category_scores_gemma":[0.00005546055,0.00046172726,0.00012801244,0.00042831732,0.0006896952,0.0015007159,0.0018260418,0.000777848,0.0003900403],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028000286,0.000022788292,0.00002669828,0.00002941485,0.000007888472,0.000061640065,0.00048990705,0.0014509016,0.00022497977,0.034078483,0.000422073,0.96318245],"study_design_scores_gemma":[0.00061353255,0.00034211238,0.0003957868,0.0010090214,0.000012570261,0.00018446732,2.8624302e-7,0.4179733,0.0032655161,0.49599805,0.078016564,0.0021887855],"about_ca_topic_score_codex":0.00006684425,"about_ca_topic_score_gemma":0.000030079862,"teacher_disagreement_score":0.96099365,"about_ca_system_score_codex":0.00017647608,"about_ca_system_score_gemma":0.00039046365,"threshold_uncertainty_score":0.99978346},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017653078,0.000004890446,0.97293127,0.0014634895,0.001009543,0.00019582816,0.00003440215,0.00012401762,0.006583483],"genre_scores_gemma":[0.6623942,0.0000029287714,0.3363395,0.0009305143,0.00019747861,0.000015574222,0.00004605322,0.000009783275,0.00006394956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977886,0.00003541204,0.00031706813,0.0007590735,0.00079550367,0.00030433197],"domain_scores_gemma":[0.9987711,0.00007562525,0.00008535864,0.00022024855,0.00066793413,0.00017976978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031491584,0.00022402778,0.00016784965,0.00035494444,0.00033607494,0.0005989961,0.0010527611,0.000054514563,0.000029757686],"category_scores_gemma":[0.000022898144,0.00021921446,0.00007616442,0.00016805182,0.00003185573,0.0008760273,0.00047596032,0.00033003333,0.00034291288],"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":[0.000015043992,0.00008115266,0.0000031748473,0.0000025276522,0.00001600896,0.000019849598,0.00055446225,0.7772565,0.00004696504,0.20158046,0.000018215336,0.020405637],"study_design_scores_gemma":[0.00056751695,0.000092979586,0.000010650412,0.0004300946,0.0000032606258,0.000015722255,0.000041849195,0.9330562,0.00011771549,0.065347135,0.000060408474,0.00025650335],"about_ca_topic_score_codex":0.0001741219,"about_ca_topic_score_gemma":0.0000039798674,"teacher_disagreement_score":0.6447411,"about_ca_system_score_codex":0.0001258914,"about_ca_system_score_gemma":0.00016053945,"threshold_uncertainty_score":0.8939306},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.611389e-7,0.0008308528,0.15580139,0.00004943344,0.0010713359,0.00048185166,0.0001893154,0.0005448279,0.8410304],"genre_scores_gemma":[0.000017965427,0.00029647083,0.0058169854,0.00007449263,0.00025523145,0.0000017534244,0.00006154682,0.00004662382,0.99342895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782443,0.00005869064,0.0002962316,0.0009977585,0.0004796025,0.0003433009],"domain_scores_gemma":[0.9979176,0.00018382489,0.00021519943,0.0012984587,0.00014778264,0.00023715585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028364515,0.0005058118,0.00082915794,0.00030061151,0.00019648533,0.00029167408,0.0019454691,0.0003985912,0.0000058693277],"category_scores_gemma":[0.000008962143,0.00048275155,0.00052908977,0.00001717332,0.00028139722,0.00030426195,0.0024379895,0.0006782147,0.00016040418],"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":[0.00053461385,0.000005026398,5.374948e-9,0.000052782063,0.00016168195,0.0007380932,0.000030288746,0.0000017023661,0.0000030500132,0.94337666,0.048977755,0.0061183386],"study_design_scores_gemma":[0.015210982,0.000022723018,8.323572e-8,0.00029093918,0.00018846674,0.000040553532,0.0000030703684,0.018813092,0.000061779756,0.0006881672,0.96413153,0.0005485885],"about_ca_topic_score_codex":0.00010128067,"about_ca_topic_score_gemma":3.2093214e-7,"teacher_disagreement_score":0.94268847,"about_ca_system_score_codex":0.00014412226,"about_ca_system_score_gemma":0.00013486996,"threshold_uncertainty_score":0.9997624},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043063934,0.00043235664,0.99257255,0.0003406204,0.001824015,0.00027206322,0.000019949226,0.00021987225,0.004275521],"genre_scores_gemma":[0.015690995,0.0007140784,0.97965664,0.0019082304,0.0013183077,0.000020899004,0.00011046388,0.000051927953,0.0005284869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964913,0.00003256046,0.00046644596,0.0014630817,0.0009841849,0.00056241936],"domain_scores_gemma":[0.9978065,0.00019648629,0.00027319606,0.0012919655,0.00024508793,0.00018675854],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041336103,0.00044789954,0.00040103766,0.0006063923,0.00038514377,0.000421806,0.0022766474,0.0003083346,0.00005262032],"category_scores_gemma":[0.00004581428,0.0004059548,0.00011734591,0.00046875718,0.00046041462,0.0012074856,0.0012752175,0.0006823376,0.000281432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029978473,0.000025013784,0.0000057411526,0.000014237878,0.000003845069,0.00010143014,0.00026569655,0.0016592304,0.000049894054,0.0012307493,0.00030965,0.9963315],"study_design_scores_gemma":[0.00052982534,0.0003439158,0.00024474968,0.0010893703,0.000011560568,0.00046539123,1.1616685e-7,0.7140833,0.0024942574,0.25868696,0.020577243,0.0014732889],"about_ca_topic_score_codex":0.00002424181,"about_ca_topic_score_gemma":0.000016589323,"teacher_disagreement_score":0.9948582,"about_ca_system_score_codex":0.00020869086,"about_ca_system_score_gemma":0.00035562436,"threshold_uncertainty_score":0.99983925},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057692123,0.000058465113,0.97678053,0.00091113703,0.00007870957,0.00005899062,9.0522155e-7,0.000246412,0.016095612],"genre_scores_gemma":[0.68868697,0.0000032426833,0.30994204,0.00086737145,0.00006010195,1.4784776e-7,0.0000033637273,0.0000029181267,0.00043382056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916476,0.000014107757,0.00011107348,0.00029479663,0.00020716414,0.00020806988],"domain_scores_gemma":[0.99933213,0.000028422197,0.000045921675,0.000476198,0.000039635124,0.0000777073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008312693,0.00009867649,0.000103478684,0.000028153472,0.00011319016,0.00015994717,0.00059542,0.000023494567,0.00001198786],"category_scores_gemma":[0.0000051802035,0.000065311884,0.000019156349,0.00022771074,0.000016544152,0.00044510452,0.00008652188,0.00008271413,0.000036210586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022521857,0.00022136062,0.0012838094,0.0000072879006,0.000011853038,0.000102264516,0.000492293,0.00095735496,0.0011130334,0.30846053,0.014378595,0.6729491],"study_design_scores_gemma":[0.00071990764,0.0003886578,0.031921383,0.000085705826,0.0000038946387,0.000054322067,0.000032622163,0.93136334,0.0036678482,0.0044478322,0.02684761,0.00046685289],"about_ca_topic_score_codex":0.000012179978,"about_ca_topic_score_gemma":0.0000029840558,"teacher_disagreement_score":0.93040603,"about_ca_system_score_codex":0.000012438343,"about_ca_system_score_gemma":0.00002086102,"threshold_uncertainty_score":0.26633415},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060764137,0.00003748843,0.98875165,0.0014406551,0.000268116,0.00024743294,0.000008049975,0.00023972239,0.0029304568],"genre_scores_gemma":[0.7354812,0.0000050875788,0.26275006,0.0003259075,0.000072385286,0.000017652881,0.000006078782,0.000009804098,0.0013318338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989594,0.00001852607,0.00012857311,0.00037494762,0.0002626108,0.00025593652],"domain_scores_gemma":[0.9992508,0.00012469623,0.000047466026,0.00035144293,0.00009115215,0.00013442377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008150462,0.0001229646,0.00012140044,0.00010937904,0.0004242653,0.00018359021,0.00046703013,0.000037966507,0.000049190712],"category_scores_gemma":[0.000010642334,0.000085972235,0.000030261876,0.00027397092,0.000029773537,0.0003465339,0.00028499824,0.00006757709,0.00004368636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019200543,0.0006058291,0.000689134,0.00007509677,0.00006016207,0.000046214936,0.0046830196,0.047635134,0.009118794,0.5995228,0.15536727,0.18200451],"study_design_scores_gemma":[0.0005407068,0.00018468527,0.00040430482,0.00006626861,0.0000041817975,0.000009472988,0.00012314823,0.9341149,0.0018100428,0.00006868833,0.062495112,0.00017849769],"about_ca_topic_score_codex":0.000024452573,"about_ca_topic_score_gemma":0.0000045448423,"teacher_disagreement_score":0.88647974,"about_ca_system_score_codex":0.000051031384,"about_ca_system_score_gemma":0.000015134208,"threshold_uncertainty_score":0.3505846},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010242586,0.0014989638,0.7521669,0.0018929591,0.00088622904,0.0010638771,0.0000770703,0.0002315275,0.24115822],"genre_scores_gemma":[0.17810537,0.022714792,0.7946951,0.0017982484,0.00013621086,0.00005567643,0.00032168833,0.000027896185,0.002145033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798554,0.000043815806,0.00068006595,0.00036216737,0.00063572347,0.00029265764],"domain_scores_gemma":[0.99696004,0.00014546701,0.00021624201,0.0022932028,0.00027041364,0.00011461824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007635855,0.00022741314,0.0002658073,0.0012765484,0.0004784312,0.000583179,0.004938252,0.00014091602,0.00000907216],"category_scores_gemma":[0.000022083572,0.00021127235,0.000035063316,0.0006345405,0.0009887012,0.008937226,0.004098461,0.0005831108,0.00004134233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024361175,0.000020732181,0.00015171216,0.00002705674,0.0000035830315,0.0000037285783,0.005539506,0.0014356928,0.000009410495,0.2707685,0.0004841642,0.7215535],"study_design_scores_gemma":[0.00036991813,0.000053268457,0.0066796457,0.00029879002,0.00000150201,0.00008526762,0.000034373334,0.9120482,0.000029279845,0.005400648,0.07456655,0.00043256633],"about_ca_topic_score_codex":0.000058892758,"about_ca_topic_score_gemma":0.000030624,"teacher_disagreement_score":0.9106125,"about_ca_system_score_codex":0.00016295069,"about_ca_system_score_gemma":0.00044374084,"threshold_uncertainty_score":0.9176582},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010559606,0.00022862919,0.9925194,0.00213916,0.0023117836,0.0003679698,0.000029522016,0.00020721422,0.0020907396],"genre_scores_gemma":[0.029190633,0.000086027525,0.9643143,0.003926743,0.0011021022,0.000013435306,0.00003228285,0.00006479109,0.0012696745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99473417,0.000043812808,0.0005329592,0.0019353542,0.0018251287,0.0009285572],"domain_scores_gemma":[0.99616736,0.0005741168,0.00021223063,0.0024406628,0.00029362642,0.0003120065],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009647622,0.0006287451,0.0006057112,0.00076223456,0.00041287762,0.0008806678,0.005548148,0.00049191347,0.00010412891],"category_scores_gemma":[0.00007492631,0.00051543565,0.0001363416,0.00062441325,0.0009161532,0.0011065853,0.003097526,0.0019054149,0.0000785455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009099897,0.00006312812,0.000066944674,0.00004935598,0.000015197809,0.00021445466,0.0010254198,0.011708117,0.0012875242,0.015787309,0.0002977373,0.9694757],"study_design_scores_gemma":[0.0004621357,0.00025288123,0.00041597543,0.00044073878,0.000009831146,0.00010632285,2.7942934e-7,0.8502619,0.0041779308,0.11897135,0.023706479,0.0011941387],"about_ca_topic_score_codex":0.00007399783,"about_ca_topic_score_gemma":0.00012772164,"teacher_disagreement_score":0.96828157,"about_ca_system_score_codex":0.00018705975,"about_ca_system_score_gemma":0.0007388163,"threshold_uncertainty_score":0.99983233},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020441597,0.00010694777,0.9737752,0.00075778854,0.0001948904,0.00005725884,0.0000050184913,0.000110618144,0.0045506805],"genre_scores_gemma":[0.71758944,0.000008681729,0.28174907,0.00016613097,0.00012048669,0.0000027156361,0.000004938256,0.0000033659396,0.00035521202],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921167,0.000020478305,0.0001824749,0.00020507128,0.00026105714,0.00011927418],"domain_scores_gemma":[0.99899256,0.00004580552,0.00006050285,0.00079019903,0.000043561184,0.00006737687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079486956,0.0000694447,0.00010451289,0.000044535194,0.000060338738,0.000030303967,0.00094330165,0.00003225081,0.0001153109],"category_scores_gemma":[0.000024364703,0.000048915972,0.0000399391,0.000114445145,0.000037334758,0.0005044921,0.0007227077,0.00005759412,0.000033842625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014925306,0.00040105212,0.00093860383,0.00001743738,0.000009623908,0.0000049059154,0.0003216432,0.0004565042,0.007029253,0.13735202,0.13752599,0.7159281],"study_design_scores_gemma":[0.0011213023,0.00014204663,0.030970443,0.000101458776,0.000006349107,0.000014750687,0.000014144198,0.8047654,0.03323834,0.0071887346,0.122088,0.00034904675],"about_ca_topic_score_codex":0.000045046552,"about_ca_topic_score_gemma":0.000013123501,"teacher_disagreement_score":0.8043089,"about_ca_system_score_codex":0.000012591263,"about_ca_system_score_gemma":0.000018387098,"threshold_uncertainty_score":0.19947354},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009384423,0.00048059723,0.9913078,0.00074468623,0.0014973512,0.0002284432,0.000015288266,0.0000754272,0.0055565382],"genre_scores_gemma":[0.08111144,0.00043983408,0.9120103,0.0022722494,0.0020142498,0.000021398377,0.000019710631,0.000068576745,0.0020422447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973661,0.00003393587,0.00044467562,0.0009937438,0.00077391136,0.00038764995],"domain_scores_gemma":[0.99699926,0.00066582503,0.0003313449,0.0016705394,0.00024676337,0.00008627665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076501723,0.00032048556,0.00034307913,0.00034776618,0.0003092541,0.0002543447,0.002914525,0.0001754177,0.000026947439],"category_scores_gemma":[0.000095338495,0.00022727852,0.00011810677,0.0004928907,0.0005678431,0.0007105769,0.0018284027,0.00067265524,0.000036642603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045210436,0.000022816032,0.000014731647,0.000016715721,0.000010961516,0.00001898131,0.0004318829,0.01856098,0.00021618133,0.019491233,0.000075317825,0.9611357],"study_design_scores_gemma":[0.00034649431,0.00027990603,0.0005620636,0.0010722727,0.000025966661,0.00016051346,7.790082e-7,0.8714132,0.0062568416,0.09225309,0.026698252,0.0009306324],"about_ca_topic_score_codex":0.000034801713,"about_ca_topic_score_gemma":0.00006610439,"teacher_disagreement_score":0.960205,"about_ca_system_score_codex":0.0001497467,"about_ca_system_score_gemma":0.0003331959,"threshold_uncertainty_score":0.9268149},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018088463,0.000101906655,0.99008113,0.0004507896,0.0001953301,0.00023044246,0.000014270653,0.00023004261,0.006887224],"genre_scores_gemma":[0.19095421,0.000048322694,0.80201966,0.0008692757,0.00020154462,0.0000478603,0.000040755407,0.000013550682,0.0058048414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899065,0.000027798975,0.0001831679,0.0003337011,0.00022393704,0.00024075527],"domain_scores_gemma":[0.999155,0.00014894764,0.000051918996,0.0004790282,0.000059727914,0.00010539325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115033334,0.00011748588,0.00012639882,0.000060970615,0.00019415635,0.000107983025,0.00079307414,0.00004799416,0.0005070831],"category_scores_gemma":[0.00003133056,0.00008883355,0.000048662325,0.00014947524,0.000027339127,0.0006917492,0.00057282497,0.00008026859,0.00030494155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022727863,0.00056591665,0.00046428217,0.00003768689,0.000026468033,0.0000110225465,0.00045389932,0.00018919243,0.02991826,0.04515882,0.23096152,0.69219023],"study_design_scores_gemma":[0.00043869627,0.000105895095,0.00015552739,0.00002631289,0.0000017012476,0.0000034087325,0.0000030992283,0.94279695,0.005875425,0.0011336848,0.049308643,0.00015064797],"about_ca_topic_score_codex":0.000020660314,"about_ca_topic_score_gemma":8.985705e-7,"teacher_disagreement_score":0.94260776,"about_ca_system_score_codex":0.000017156603,"about_ca_system_score_gemma":0.000009793699,"threshold_uncertainty_score":0.5552204},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026139866,0.00014569615,0.99426925,0.000018294644,0.00027099164,0.000061125,0.0000018999798,0.000027189832,0.0025915352],"genre_scores_gemma":[0.69915336,0.00014214209,0.3003789,0.000051015155,0.00008379505,0.0000052417254,0.00007102856,0.0000035926637,0.00011092956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994741,0.000016234626,0.00012695878,0.00017117668,0.00012468794,0.00008682425],"domain_scores_gemma":[0.9990579,0.000014394726,0.00003906399,0.00081119814,0.000039012713,0.000038420883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026206003,0.00004063664,0.00006669545,0.000041778214,0.000012391752,0.000023107475,0.0009154438,0.000024674124,0.000005116387],"category_scores_gemma":[0.000010026666,0.0000315673,0.0000043903533,0.00025107322,0.000011181492,0.00073983474,0.0008851075,0.000039435876,0.000003443241],"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":[0.000002141436,0.00002701245,0.0017421375,0.0000021832464,6.436944e-7,5.6322955e-7,0.000037271508,0.88471067,0.0000012254006,0.0001503879,0.001480579,0.11184519],"study_design_scores_gemma":[0.00016251614,0.00003772539,0.0004750748,0.000011450405,4.2089277e-7,0.0000012423463,0.000009998498,0.9973764,0.000025518855,0.000014606042,0.0018423188,0.000042744563],"about_ca_topic_score_codex":0.000049706727,"about_ca_topic_score_gemma":0.0000061901646,"teacher_disagreement_score":0.6965394,"about_ca_system_score_codex":0.000008164722,"about_ca_system_score_gemma":0.000037859787,"threshold_uncertainty_score":0.17011376},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6895012,0.0025963094,0.30530858,0.00032950865,0.00095422193,0.0002771835,0.000009477606,0.00044101925,0.00058245065],"genre_scores_gemma":[0.826713,0.00012302416,0.17275687,0.00021058378,0.000112227164,0.000046076373,0.0000036814333,0.000008402951,0.000026122303],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861455,0.00010342026,0.00019709238,0.00046668993,0.00029475614,0.00032348576],"domain_scores_gemma":[0.99866444,0.00042748975,0.00008896256,0.00043869013,0.000174014,0.00020639144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051783316,0.00013334445,0.00013159802,0.000100013305,0.00012058896,0.00039963776,0.0005327519,0.000057113968,0.00000452318],"category_scores_gemma":[0.003179528,0.00012147029,0.000017435292,0.00034944623,0.000055186683,0.0056720544,0.0009505694,0.0002877029,0.000004765456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040330816,0.0006117244,0.02488426,0.00009253192,0.00002426157,0.0010382449,0.35390812,0.00046327387,0.0009125371,0.0056277234,0.0012688834,0.61076516],"study_design_scores_gemma":[0.00874689,0.0025173773,0.034422945,0.0014087098,0.000044215132,0.00057254796,0.23284948,0.31544232,0.007246715,0.007883257,0.3842905,0.0045750774],"about_ca_topic_score_codex":0.00038433707,"about_ca_topic_score_gemma":0.000009011683,"teacher_disagreement_score":0.6061901,"about_ca_system_score_codex":0.00004305783,"about_ca_system_score_gemma":0.00012131276,"threshold_uncertainty_score":0.49534148},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014999008,0.0003426807,0.9946324,0.00038645416,0.0012938948,0.00031149384,0.000045048757,0.000065198954,0.0014228994],"genre_scores_gemma":[0.4068386,0.00042525015,0.58896613,0.002824884,0.00068524503,0.000005060558,0.000039140465,0.00005094219,0.00016474795],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99721885,0.000044531833,0.00043415645,0.0010368582,0.0008893974,0.00037621576],"domain_scores_gemma":[0.99714535,0.00071765285,0.00039055082,0.0014256543,0.00023705454,0.00008370559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030837388,0.0004009941,0.00039414,0.00042256934,0.0002979118,0.00019136877,0.0033644321,0.00024614154,0.000037542424],"category_scores_gemma":[0.000101451216,0.00025796087,0.00010379196,0.00047739287,0.00068853726,0.00038160992,0.00097072765,0.00076410436,0.000016837046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009151186,0.000026604755,0.0000074757213,0.000024939127,0.000009429227,0.000036410696,0.00066808995,0.008225445,0.00028867982,0.011166054,0.00015057246,0.97938716],"study_design_scores_gemma":[0.00036128733,0.00045718532,0.00021016758,0.0013539959,0.000009358717,0.00012275315,4.1271323e-7,0.39520407,0.013979089,0.5855259,0.0018931873,0.000882646],"about_ca_topic_score_codex":0.000021895012,"about_ca_topic_score_gemma":0.000049804497,"teacher_disagreement_score":0.9785045,"about_ca_system_score_codex":0.000097297925,"about_ca_system_score_gemma":0.00029581427,"threshold_uncertainty_score":0.99998724},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002752784,0.00048349102,0.99504954,0.0004269408,0.0017437967,0.00034118266,0.000053727297,0.00029924556,0.0015745461],"genre_scores_gemma":[0.025612202,0.000100291254,0.9683928,0.0031737725,0.0021279145,0.000014102309,0.000058067708,0.00007846984,0.00044242048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946157,0.000040786505,0.0006940704,0.0021857242,0.0014635288,0.001000198],"domain_scores_gemma":[0.99652064,0.00034868706,0.00037637094,0.0022355963,0.00020499928,0.00031371345],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00073837227,0.0007610255,0.000687272,0.0007743763,0.00046056727,0.0011038021,0.005326581,0.00025575014,0.000083602834],"category_scores_gemma":[0.000028361663,0.0006764947,0.00018933999,0.000418621,0.00041092455,0.0014541697,0.003918968,0.0011655678,0.00016354634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010171924,0.000025981592,0.0000070182878,0.000013883253,0.0000071908785,0.00017831154,0.00026711897,0.009278382,0.000026824804,0.0008803792,0.00009660517,0.9892173],"study_design_scores_gemma":[0.00027383817,0.00010585866,0.000059497015,0.0003425518,0.000006456429,0.00020089891,1.576385e-7,0.89101744,0.000532412,0.093895786,0.012684578,0.0008805107],"about_ca_topic_score_codex":0.00010773598,"about_ca_topic_score_gemma":0.000053326774,"teacher_disagreement_score":0.9883368,"about_ca_system_score_codex":0.0003622345,"about_ca_system_score_gemma":0.00043687812,"threshold_uncertainty_score":0.9999331},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052617792,0.0003075773,0.94245654,0.004111392,0.00031486287,0.00009890966,0.0000037842108,0.000024566487,0.000064591935],"genre_scores_gemma":[0.52992606,0.000004119256,0.469257,0.00038301907,0.000374469,0.0000025467843,0.000007715396,0.0000048276265,0.000040257168],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986958,0.000059347192,0.00056934793,0.00020906134,0.00024729662,0.00021913569],"domain_scores_gemma":[0.9987886,0.000096677584,0.000492767,0.00017264998,0.0003324177,0.000116892596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004715252,0.00013090404,0.00024266733,0.00014441575,0.00010730303,0.00007175099,0.0006932892,0.00007996954,0.00003303612],"category_scores_gemma":[0.000041033967,0.00009921983,0.00011014211,0.00013259106,0.000049589304,0.00055100856,0.00025000394,0.0002644923,0.00002553691],"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":[0.00022840325,0.0007452066,0.0005255258,0.000033671695,0.00023925841,0.000064633125,0.0005966515,0.50506616,0.089752354,0.03087617,0.003204897,0.36866707],"study_design_scores_gemma":[0.00084336195,0.00050203357,0.0010370465,0.000059626083,0.0000066382036,0.00024781915,0.000014678154,0.96391135,0.002147405,0.01945518,0.01161806,0.00015681284],"about_ca_topic_score_codex":0.0000065543954,"about_ca_topic_score_gemma":5.4015646e-7,"teacher_disagreement_score":0.47730827,"about_ca_system_score_codex":0.00008908433,"about_ca_system_score_gemma":0.00016787673,"threshold_uncertainty_score":0.40460673},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038666287,0.00029129614,0.9947329,0.0007478542,0.0016695388,0.0007412821,0.000115077615,0.0003235833,0.0009917676],"genre_scores_gemma":[0.17561653,0.0002132126,0.8172348,0.003137274,0.0018453981,0.00006194992,0.00020884725,0.0001442463,0.0015377074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99354976,0.00006705967,0.0007406089,0.002757892,0.0018186423,0.0010660064],"domain_scores_gemma":[0.99579823,0.00036110805,0.0003191714,0.002950668,0.00025639767,0.0003144082],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005357135,0.0009485727,0.00079196016,0.0007957261,0.0005481897,0.0011577422,0.0058487663,0.00047246768,0.000017708448],"category_scores_gemma":[0.00008312627,0.0007877207,0.00022961071,0.00078292855,0.000963878,0.0023001155,0.0030883003,0.0014140842,0.00012863128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028860284,0.00020121761,0.00006096451,0.00009138199,0.00003380847,0.0016415378,0.0006303893,0.0524003,0.0010084858,0.040212687,0.0006806651,0.9030097],"study_design_scores_gemma":[0.00079457747,0.000807087,0.0004768389,0.0021790667,0.000010118567,0.00043726966,1.3427687e-7,0.90644705,0.005224669,0.0677632,0.013457537,0.0024024344],"about_ca_topic_score_codex":0.000048090496,"about_ca_topic_score_gemma":0.000015294854,"teacher_disagreement_score":0.9006073,"about_ca_system_score_codex":0.0005412683,"about_ca_system_score_gemma":0.0007612012,"threshold_uncertainty_score":0.9998792},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013411676,0.00002080632,0.9852967,0.00065109425,0.00018218497,0.00015733033,0.000047267455,0.00014282214,0.00009010724],"genre_scores_gemma":[0.30106312,0.0000028108827,0.6985809,0.00010579988,0.00007146521,0.000011339814,0.000082875595,0.0000049993273,0.00007670492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991037,0.000010008296,0.00012324184,0.00029072003,0.0002188155,0.00025347032],"domain_scores_gemma":[0.99937767,0.00007568862,0.000020589674,0.00033860648,0.00008842258,0.000099024604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015038443,0.0000834332,0.00008614365,0.000038310012,0.00017664208,0.00007288425,0.00040412284,0.000035092784,0.000013013334],"category_scores_gemma":[0.000021405487,0.00006470619,0.00004437349,0.00015255845,0.000017562672,0.0003758828,0.00031534786,0.00007082267,0.000031355627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022591683,0.00031689616,0.0001728142,0.00001941125,0.000020813819,0.000017661441,0.0002025316,0.021576464,0.014512086,0.9339296,0.0033328293,0.02587628],"study_design_scores_gemma":[0.0045461818,0.00031228564,0.0037190563,0.00008057751,0.0000061654077,0.000033247677,0.00008116456,0.79962754,0.14332455,0.018947326,0.028724698,0.00059720554],"about_ca_topic_score_codex":0.00007615939,"about_ca_topic_score_gemma":0.000004617296,"teacher_disagreement_score":0.9149823,"about_ca_system_score_codex":0.000040737053,"about_ca_system_score_gemma":0.00007812328,"threshold_uncertainty_score":0.2638642},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026584266,0.00036376197,0.9516119,0.00021674772,0.0031806051,0.00034678573,0.000012660238,0.00033422437,0.043906756],"genre_scores_gemma":[0.01004576,0.00024463126,0.9211672,0.0017494092,0.0019937875,0.000028165881,0.000043871216,0.00012445304,0.06460274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994279,0.000052763542,0.0007820227,0.0022211473,0.001777334,0.0008877252],"domain_scores_gemma":[0.99570763,0.00021461806,0.00045173801,0.0029587364,0.00027910603,0.0003881846],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013544314,0.0006774993,0.00075207266,0.0009612518,0.00045101668,0.0008621867,0.007654699,0.00034632988,0.000070872244],"category_scores_gemma":[0.000018314518,0.0005943096,0.00014934334,0.00046292171,0.0008237372,0.0011469453,0.005828435,0.0008663066,0.00047402162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003094527,0.000037719798,0.000008914776,0.00003077754,0.000005220012,0.000105600906,0.0001604632,0.0007038506,0.00003900975,0.20365314,0.0034055903,0.79184663],"study_design_scores_gemma":[0.00049837574,0.00015703063,0.0002686879,0.0009829857,0.0000056103227,0.000090993344,4.3284732e-7,0.816997,0.0001800664,0.04815698,0.13165182,0.0010100397],"about_ca_topic_score_codex":0.00002665741,"about_ca_topic_score_gemma":0.0000067565607,"teacher_disagreement_score":0.8162931,"about_ca_system_score_codex":0.00024759132,"about_ca_system_score_gemma":0.00042119162,"threshold_uncertainty_score":0.99965084},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029464172,0.00035687804,0.9897594,0.00015839245,0.005437133,0.000824597,0.00005529326,0.00016464372,0.003214194],"genre_scores_gemma":[0.33854154,0.00017104397,0.6490919,0.0029634316,0.00466996,0.00016200477,0.00012233973,0.00020664686,0.004071147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962167,0.00003612368,0.0004979215,0.0016951705,0.0009204347,0.0006336463],"domain_scores_gemma":[0.9972226,0.0005200917,0.0003072755,0.0014720281,0.00028065837,0.00019733461],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005464162,0.00053683924,0.0005089051,0.0007432731,0.00043814527,0.0006176191,0.0028322525,0.00032069936,0.000014527107],"category_scores_gemma":[0.00006315808,0.00046005772,0.00015410753,0.00048256756,0.00033078543,0.00066012476,0.0011707289,0.0006196735,0.000050722487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027722708,0.00025798674,0.00001635813,0.00010433846,0.0001018381,0.00029729953,0.0035674411,0.11567701,0.0004721709,0.15363553,0.0024374172,0.7231554],"study_design_scores_gemma":[0.00050253904,0.00095014286,0.000012823935,0.0008321904,0.0000081148055,0.00010482757,0.0000015705541,0.9518719,0.0008979249,0.02893019,0.015162079,0.0007257024],"about_ca_topic_score_codex":0.000045247078,"about_ca_topic_score_gemma":0.000011750777,"teacher_disagreement_score":0.8361949,"about_ca_system_score_codex":0.0004779216,"about_ca_system_score_gemma":0.00029372593,"threshold_uncertainty_score":0.9997851},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014922353,0.0005624333,0.99480605,0.0006518779,0.0011876643,0.0002968397,0.00003470335,0.000052745185,0.0022584691],"genre_scores_gemma":[0.18279448,0.00009002981,0.8157424,0.00042111817,0.00040404417,0.0000069288762,0.000025678355,0.00004230298,0.0004730487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963293,0.000054990433,0.0008297932,0.0009898624,0.0012847934,0.00051127444],"domain_scores_gemma":[0.9959704,0.00069208717,0.0007257478,0.002130375,0.00038108623,0.0001002612],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010544737,0.00041541125,0.0006200276,0.00037768923,0.00031051834,0.00019923659,0.0051844963,0.00021960706,0.000013832639],"category_scores_gemma":[0.00007327929,0.00028846835,0.00017452521,0.0005226496,0.0024665373,0.00042541188,0.002539575,0.0005463803,0.000009242956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025871184,0.000125542,0.00015433905,0.000112400405,0.00003079873,0.00004737402,0.0004847379,0.016919957,0.001153278,0.19837856,0.0009508527,0.7816163],"study_design_scores_gemma":[0.0003914397,0.00022961159,0.0012114303,0.00053526054,0.000010012531,0.000036278958,1.8653283e-7,0.5481162,0.008420788,0.43674,0.0037539979,0.0005547888],"about_ca_topic_score_codex":0.00016440924,"about_ca_topic_score_gemma":0.00008210532,"teacher_disagreement_score":0.78106153,"about_ca_system_score_codex":0.00009941784,"about_ca_system_score_gemma":0.00038094743,"threshold_uncertainty_score":0.9999567},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008520283,0.0009882393,0.99404734,0.0002663476,0.0029110333,0.00068162964,0.00019717032,0.00017320126,0.0006498605],"genre_scores_gemma":[0.04753038,0.00005267368,0.950701,0.00063471135,0.0006255361,0.000013861658,0.00016522498,0.00006290095,0.00021372865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994856,0.000028684826,0.00056871853,0.002564885,0.0011222984,0.0008593921],"domain_scores_gemma":[0.99486077,0.0005382336,0.0004503677,0.003646919,0.00030677408,0.00019695265],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012564525,0.0006411058,0.0006011797,0.0005973104,0.0004916425,0.0006798833,0.008785454,0.00033828645,0.000029548502],"category_scores_gemma":[0.00013526845,0.00053823786,0.00012178771,0.00039333405,0.00056236365,0.00079568574,0.0059770634,0.00070543104,0.000019836998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002499885,0.00004852106,0.00004610615,0.00011478656,0.000024441297,0.00006569579,0.0005346251,0.020586029,0.00009077287,0.071146,0.0001713098,0.9071467],"study_design_scores_gemma":[0.00033958425,0.00009266866,0.00024191894,0.00027179375,0.000013721858,0.00005895527,1.2176055e-7,0.89016926,0.000100611855,0.10277415,0.005280824,0.00065641257],"about_ca_topic_score_codex":0.000035547906,"about_ca_topic_score_gemma":0.00008149117,"teacher_disagreement_score":0.9064903,"about_ca_system_score_codex":0.00018322867,"about_ca_system_score_gemma":0.00062523683,"threshold_uncertainty_score":0.9997069},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11589263,0.000035451973,0.87727225,0.0059939018,0.00016386747,0.00006301468,0.0000031497084,0.00016588748,0.00040987946],"genre_scores_gemma":[0.9509046,0.00002240728,0.04437689,0.0045903637,0.000053926255,0.000010348461,0.000005357744,0.0000044883773,0.00003162282],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992023,0.000012628009,0.00023860107,0.00013863509,0.00022238363,0.00018547091],"domain_scores_gemma":[0.99949783,0.00003570878,0.00015594174,0.00020426816,0.00004340253,0.00006284626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019465153,0.00010089253,0.00008394826,0.00012493045,0.00018092174,0.00041301828,0.0003583692,0.000038678303,0.000006811563],"category_scores_gemma":[0.000031049378,0.000065787804,0.000014420266,0.00016964272,0.00004478484,0.0068965806,0.00017912178,0.000063369,0.00006340445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042041966,0.00000586652,0.0005027805,0.000037029793,0.0000035248363,0.0000016138524,0.0024613168,0.0000072883054,0.003132937,0.001085175,0.0029782017,0.98978007],"study_design_scores_gemma":[0.009842822,0.00033708703,0.046640787,0.0033335253,0.000056783392,0.0006787662,0.0008896582,0.43302733,0.035987567,0.009744603,0.45543838,0.004022692],"about_ca_topic_score_codex":0.0000047230665,"about_ca_topic_score_gemma":1.5814567e-7,"teacher_disagreement_score":0.98575735,"about_ca_system_score_codex":0.00003133507,"about_ca_system_score_gemma":0.000032533342,"threshold_uncertainty_score":0.49998543},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005329952,0.00007446625,0.9897481,0.00026369994,0.0006555874,0.00014750626,0.000006775244,0.00008256148,0.00369134],"genre_scores_gemma":[0.84942126,0.000005543328,0.14675033,0.00038563696,0.00036093628,0.000029771425,0.00001849477,0.000012022895,0.003016025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992559,0.000015785354,0.00015718942,0.000229611,0.0001714949,0.00017001899],"domain_scores_gemma":[0.9990447,0.00012948846,0.00005496816,0.0006566638,0.00007971519,0.000034440385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016451936,0.00008338855,0.00008409807,0.000020794756,0.00019708401,0.00016098074,0.0006368037,0.00003454574,0.000120571945],"category_scores_gemma":[0.0000059370564,0.00004928357,0.000055859036,0.00013848943,0.000040147253,0.0005493295,0.000116717514,0.00004471833,0.000035927605],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047198417,0.00049746525,0.0021225323,0.000018799048,0.000031961077,0.000003173341,0.000061160266,0.0011047003,0.0012207798,0.8268284,0.062579,0.10548482],"study_design_scores_gemma":[0.0007155543,0.00035867104,0.030990006,0.000015341358,0.0000288235,0.000021812319,0.000031708256,0.73080605,0.0011762711,0.06692044,0.16863143,0.00030389632],"about_ca_topic_score_codex":0.00028130197,"about_ca_topic_score_gemma":0.000028032413,"teacher_disagreement_score":0.8440913,"about_ca_system_score_codex":0.000009729674,"about_ca_system_score_gemma":0.000033627013,"threshold_uncertainty_score":0.20097257},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027006597,0.0010218949,0.9931166,0.00012920666,0.001384315,0.00034683556,0.00002020848,0.000071822076,0.0036390184],"genre_scores_gemma":[0.09347024,0.00026827105,0.9046338,0.00045588677,0.0007345062,0.000020538631,0.000036916994,0.00003929569,0.00034050006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949599,0.000090284644,0.0005286032,0.0011766624,0.0028277866,0.00041678647],"domain_scores_gemma":[0.9967347,0.00021587643,0.00037223872,0.0017281183,0.0008062443,0.00014284639],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017197139,0.0003747753,0.00044078857,0.00063856377,0.00024121595,0.00013804255,0.0029812395,0.0002616035,0.000048907463],"category_scores_gemma":[0.00012863465,0.00031360413,0.00011620955,0.00043799853,0.0004896324,0.00071085873,0.001826031,0.00048158437,0.000019268533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023091957,0.00003073294,0.000010059731,0.000012245467,0.000009482285,0.000022268609,0.0006792716,0.06340106,0.00067873707,0.0023892194,0.0003798235,0.9323848],"study_design_scores_gemma":[0.00031106902,0.00008565214,0.00016322896,0.00032834234,0.000015252584,0.000057461384,6.822678e-8,0.9461281,0.003208793,0.047371134,0.0019453428,0.00038557025],"about_ca_topic_score_codex":0.000037166046,"about_ca_topic_score_gemma":0.000013432058,"teacher_disagreement_score":0.9319992,"about_ca_system_score_codex":0.00022298981,"about_ca_system_score_gemma":0.0011450088,"threshold_uncertainty_score":0.99993163},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033396853,0.00089841674,0.9919209,0.0009493895,0.0015067848,0.00031320835,0.000010832842,0.00028110077,0.004085976],"genre_scores_gemma":[0.04504078,0.00019480928,0.9503138,0.0021758212,0.0004019127,0.0000069446805,0.000033279506,0.000051479376,0.0017811671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955353,0.00003333587,0.000552987,0.0019304327,0.0011594496,0.00078848074],"domain_scores_gemma":[0.99673676,0.0002754876,0.00029466607,0.0022615364,0.00020137872,0.0002301744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000579741,0.0006518419,0.00062294945,0.0008509996,0.00034550633,0.000760221,0.005164682,0.00036822248,0.00004101386],"category_scores_gemma":[0.000053361764,0.0005510968,0.00015422501,0.00064966164,0.00041134245,0.0009826274,0.0018737493,0.0008555817,0.000091121125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003776607,0.00002745629,0.000007515434,0.000009273903,0.0000051319103,0.00012004904,0.0001366647,0.007445282,0.00007839647,0.0054381406,0.00005652691,0.9866718],"study_design_scores_gemma":[0.00030516533,0.00022119562,0.0004890535,0.0003467924,0.000006210246,0.00009928109,5.3424014e-8,0.8204366,0.00017501094,0.16970783,0.0074484334,0.00076434703],"about_ca_topic_score_codex":0.000033735887,"about_ca_topic_score_gemma":0.00017684285,"teacher_disagreement_score":0.98590744,"about_ca_system_score_codex":0.0002920341,"about_ca_system_score_gemma":0.00051955204,"threshold_uncertainty_score":0.99969405},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013651539,0.00023486762,0.9977666,0.00023386153,0.0005800303,0.0004682936,0.00003741842,0.00021657224,0.00032583455],"genre_scores_gemma":[0.11831624,0.000021872826,0.8804228,0.0007207937,0.0003878629,0.0000025569852,0.00008905631,0.00002556554,0.000013282093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575526,0.000041080755,0.0005810535,0.0020480196,0.0011158698,0.00045874168],"domain_scores_gemma":[0.9939028,0.00016832347,0.00038640172,0.0050115553,0.00027112197,0.0002598175],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006803445,0.00045346894,0.0005264081,0.0006626025,0.0002418397,0.000378796,0.00996596,0.0002709259,0.0000074406553],"category_scores_gemma":[0.00003934158,0.00038946504,0.000044613465,0.0006627862,0.00017188373,0.0013751681,0.003886203,0.0005104269,0.000013273173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046125147,0.000045007433,0.00002961973,0.000022967723,0.0000044986978,0.000009229819,0.00040889953,0.014596045,0.0027536794,0.007858632,0.00004565145,0.97422117],"study_design_scores_gemma":[0.00017741453,0.0002522462,0.00082198303,0.00026261117,0.000009295775,0.000030181567,1.9881035e-7,0.91926676,0.0047511565,0.06974635,0.0041046436,0.00057718204],"about_ca_topic_score_codex":0.00005489753,"about_ca_topic_score_gemma":0.000029953395,"teacher_disagreement_score":0.97364396,"about_ca_system_score_codex":0.00012431425,"about_ca_system_score_gemma":0.00031399698,"threshold_uncertainty_score":0.9998557},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011657689,0.00013273822,0.9948227,0.00092941924,0.00040796594,0.00084135035,0.000027339058,0.0001630284,0.0025588796],"genre_scores_gemma":[0.06420257,0.000024361056,0.9285941,0.004888379,0.0017834251,0.000051039577,0.00003482415,0.00005693491,0.00036433025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953167,0.000036185862,0.00039190636,0.0019213249,0.0015966379,0.00073725806],"domain_scores_gemma":[0.9970405,0.00032498897,0.0001622633,0.0018661215,0.00026506567,0.00034105804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052831165,0.00057747547,0.00048377202,0.001022004,0.00049629726,0.0007268831,0.0038170982,0.00024053501,0.000026130685],"category_scores_gemma":[0.000019992242,0.00043220518,0.00008433374,0.000982668,0.00030376666,0.0005026939,0.0013009433,0.0010306841,0.00006210973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021568016,0.000028049742,0.000046646834,0.000014665559,0.000006714933,0.000048525046,0.00026816264,0.043967597,0.000032776243,0.034359984,0.000058353373,0.9211469],"study_design_scores_gemma":[0.0023242275,0.004063416,0.013232766,0.0029209957,0.00004110256,0.0005368864,0.0000013925297,0.57847303,0.0033389605,0.31372327,0.07596878,0.005375151],"about_ca_topic_score_codex":0.000028189563,"about_ca_topic_score_gemma":0.00007372905,"teacher_disagreement_score":0.9157718,"about_ca_system_score_codex":0.00023944098,"about_ca_system_score_gemma":0.0005617886,"threshold_uncertainty_score":0.99981296},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038368157,0.00005517455,0.9933656,0.001808479,0.0007743704,0.00010250018,4.941355e-7,0.00003855776,0.00001801972],"genre_scores_gemma":[0.04447594,0.000020864178,0.9552131,0.00013092971,0.00013799322,0.0000017895268,4.791229e-7,0.0000027954668,0.000016056756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989724,0.000007384421,0.00025163795,0.00026341315,0.00029329656,0.00021183783],"domain_scores_gemma":[0.9987915,0.000020902871,0.00022739022,0.00034475396,0.000491439,0.00012401446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080961874,0.00008584068,0.0001550052,0.000537667,0.00022690611,0.00026479695,0.0015081336,0.000078912446,0.000001817731],"category_scores_gemma":[0.0000613536,0.000063250794,0.000026577325,0.00081070396,0.00018304052,0.0012116458,0.00057274516,0.00022307843,0.0000014427812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004042037,0.00005021353,0.00021641448,0.0000049524074,0.000006165648,0.0000042241372,0.00006280894,0.00003186037,0.00625274,0.111800976,0.001693774,0.87987185],"study_design_scores_gemma":[0.001032201,0.0003040736,0.0004945566,0.000015121482,0.0000071191716,0.000496357,0.000008535436,0.94224215,0.008825934,0.017017717,0.029398289,0.00015797821],"about_ca_topic_score_codex":0.0000024089506,"about_ca_topic_score_gemma":0.0000011194714,"teacher_disagreement_score":0.94221026,"about_ca_system_score_codex":0.00001513049,"about_ca_system_score_gemma":0.00027357443,"threshold_uncertainty_score":0.28025126},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013185419,0.0021874828,0.99204236,0.0019335784,0.0018395964,0.0010486066,0.00005632401,0.00017767597,0.0007011611],"genre_scores_gemma":[0.04290446,0.00020315903,0.9528228,0.0023153992,0.0009862098,0.000056118104,0.000024198798,0.00007118829,0.00061645673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567753,0.000038590653,0.0006120271,0.0017768353,0.0010744728,0.0008205136],"domain_scores_gemma":[0.9953924,0.0014650831,0.00040943333,0.002237993,0.00032124354,0.00017387565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006151849,0.0006491417,0.0005540132,0.0003467271,0.00096930604,0.0006974758,0.00488997,0.00029952094,0.000012016311],"category_scores_gemma":[0.0000776369,0.00043205748,0.00021833293,0.0004749879,0.0010917593,0.0003784965,0.0015999293,0.0007667393,0.000011704217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025818263,0.000027190656,0.000009578207,0.00005544372,0.000033021897,0.00006855787,0.0008529748,0.09105266,0.000042055923,0.09250747,0.0016118672,0.8137134],"study_design_scores_gemma":[0.00044678067,0.00015071583,0.00015272376,0.00024532297,0.000014082648,0.0001802441,4.46058e-7,0.6277445,0.000226443,0.33644968,0.03366059,0.00072843215],"about_ca_topic_score_codex":0.00004678161,"about_ca_topic_score_gemma":0.00009589711,"teacher_disagreement_score":0.81298494,"about_ca_system_score_codex":0.0002203648,"about_ca_system_score_gemma":0.00062558375,"threshold_uncertainty_score":0.99981314},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010310152,0.0011419758,0.98752296,0.00057827553,0.0017893028,0.0003139622,0.0000062644717,0.00029907355,0.008337864],"genre_scores_gemma":[0.010072123,0.00013669116,0.9864645,0.0018711716,0.0006943219,0.000004891596,0.000017329197,0.00003762876,0.0007013665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995298,0.00003828472,0.00059653603,0.0019412487,0.0013184531,0.00080747844],"domain_scores_gemma":[0.9966585,0.0002938009,0.00034959507,0.0022086396,0.00021244731,0.00027699463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006720892,0.00065328483,0.0006390232,0.0008209649,0.00044832387,0.00086646463,0.005142064,0.00040219308,0.000034780263],"category_scores_gemma":[0.000042387546,0.0005532021,0.00015567444,0.00053225114,0.00041127307,0.0012358662,0.0027790586,0.0010740602,0.000077960845],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004038604,0.000027691394,0.0000031897678,0.000013336032,0.000003908305,0.00011471763,0.00026263893,0.025724402,0.00019969403,0.0085913865,0.000101893595,0.9649531],"study_design_scores_gemma":[0.00032668805,0.00018986045,0.00006317698,0.0009251575,0.0000061873648,0.00008829078,7.3732686e-8,0.8633338,0.001344491,0.11929137,0.0135665685,0.00086432515],"about_ca_topic_score_codex":0.000017405486,"about_ca_topic_score_gemma":0.000010114604,"teacher_disagreement_score":0.9640888,"about_ca_system_score_codex":0.00024742546,"about_ca_system_score_gemma":0.00038506553,"threshold_uncertainty_score":0.99969196},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000046237483,0.0011552342,0.9948885,0.0009883568,0.0014613762,0.0006212663,0.0000150496435,0.00019634028,0.0006692537],"genre_scores_gemma":[0.00073403574,0.000029673072,0.99556303,0.0011853651,0.0015377587,0.000009102019,0.000045047007,0.000030310262,0.00086567906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964975,0.0000130387325,0.0004632198,0.0015503771,0.0008693945,0.00060648407],"domain_scores_gemma":[0.997406,0.00024890088,0.00026737942,0.0016691342,0.00018418272,0.00022439114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060793274,0.0004941251,0.00047605275,0.0005056977,0.00030439737,0.00072507485,0.0030800954,0.0003340047,0.00001559588],"category_scores_gemma":[0.00006783994,0.00043543146,0.00015216849,0.0003720483,0.00018270724,0.00093262905,0.00081944064,0.00047803155,0.000026441845],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004170068,0.000013522967,0.0000011836155,0.000010897944,0.0000047235417,0.00003226802,0.0002975079,0.0029471137,0.00016688049,0.012419412,0.00031057926,0.98379177],"study_design_scores_gemma":[0.00036247837,0.00022582362,0.000030873514,0.00022312567,0.000007306054,0.000051305004,8.279003e-8,0.68040603,0.0014794258,0.3080358,0.008648378,0.00052936963],"about_ca_topic_score_codex":0.000060722363,"about_ca_topic_score_gemma":0.00008230853,"teacher_disagreement_score":0.98326236,"about_ca_system_score_codex":0.00018835287,"about_ca_system_score_gemma":0.000584448,"threshold_uncertainty_score":0.99980974},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016401507,0.00010949175,0.99133635,0.00048823917,0.00016546223,0.00012231525,0.0000063692432,0.00014364054,0.007464126],"genre_scores_gemma":[0.7113386,0.000016846547,0.2839761,0.0008819436,0.00002585824,0.000018574741,0.0000034758768,0.0000070716865,0.0037315304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934256,0.000011704491,0.00012199439,0.00022551986,0.00010943171,0.00018875924],"domain_scores_gemma":[0.99944884,0.000063131796,0.00003264223,0.0003430843,0.00004060605,0.00007167607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008486819,0.00007221781,0.000090169895,0.000031927055,0.000112392896,0.00012764057,0.00045637743,0.00001991192,0.00005780736],"category_scores_gemma":[0.0000053597064,0.0000571552,0.000033350603,0.00007433565,0.0000116723495,0.00074596435,0.0001640666,0.00004028308,0.000034922465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031903983,0.00007307893,0.000012483808,0.0000072918783,0.000009196472,0.0000044427006,0.00088721426,0.001253473,0.000068960806,0.25049615,0.053694423,0.6934901],"study_design_scores_gemma":[0.00033209188,0.00004788888,0.0000047566045,0.0000076058955,7.6254605e-7,0.0000025202446,0.0000149890275,0.95431095,0.00024997425,0.032649923,0.012288883,0.00008967242],"about_ca_topic_score_codex":0.000028199518,"about_ca_topic_score_gemma":0.00000452726,"teacher_disagreement_score":0.95305747,"about_ca_system_score_codex":0.000008440624,"about_ca_system_score_gemma":0.0000057116945,"threshold_uncertainty_score":0.23307215},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029453287,0.011262819,0.956303,0.0013065732,0.0011241644,0.0001946782,0.000001144311,0.000022499347,0.0003318451],"genre_scores_gemma":[0.99626744,0.0017960262,0.0012547302,0.00017658538,0.00034307563,0.0000025372874,0.000002145218,0.000012856215,0.00014459006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982567,0.00016842652,0.0003582717,0.0001578092,0.00047297345,0.0005858176],"domain_scores_gemma":[0.9987692,0.00010773995,0.000392986,0.00038999514,0.00017713456,0.00016289756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002148721,0.00016253801,0.00025311115,0.000082761064,0.00033503195,0.00043106373,0.0016203027,0.000064907705,0.000006211049],"category_scores_gemma":[0.00004191409,0.00010587352,0.00005733296,0.0003102042,0.000041132378,0.0021974829,0.0006430499,0.00050242775,0.0000031778798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022183947,0.00023041558,0.0004817826,0.0000076228675,0.00011414973,0.000004810774,0.0015943295,0.000052382587,0.00092247943,0.95276964,0.007391543,0.03640868],"study_design_scores_gemma":[0.0072045405,0.002627559,0.0018034588,0.0001669726,0.00021810908,0.002285056,0.0012895382,0.13188665,0.01089312,0.71447176,0.12592238,0.0012308581],"about_ca_topic_score_codex":0.000017318198,"about_ca_topic_score_gemma":0.0000032602688,"teacher_disagreement_score":0.96681416,"about_ca_system_score_codex":0.00019970578,"about_ca_system_score_gemma":0.00025358156,"threshold_uncertainty_score":0.4317397},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019967062,0.000028453152,0.96771824,0.00022936006,0.0003383017,0.0001871121,0.000017398394,0.00013354255,0.011380521],"genre_scores_gemma":[0.9621478,0.00004971291,0.03726471,0.00037889156,0.000019537409,0.0000037144223,0.000050080143,0.0000034693314,0.000082107224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894893,0.000020394276,0.00039136055,0.000112274814,0.0003368133,0.00019019985],"domain_scores_gemma":[0.9991534,0.000038192204,0.00018001387,0.000471287,0.00008175945,0.000075358796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013952471,0.00011934643,0.00016437651,0.00012094181,0.00009339966,0.00011826322,0.00064667955,0.000055429384,0.000024531293],"category_scores_gemma":[0.0000234698,0.0001011676,0.000040479877,0.00034079095,0.000029954099,0.0016932192,0.0001978899,0.00009328814,0.000035590376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014064544,0.00026146663,0.0014158568,0.00007659846,0.000018989651,0.00000302204,0.0038291996,0.00010425555,0.0008650884,0.84929657,0.004511991,0.13960291],"study_design_scores_gemma":[0.004038208,0.0030477005,0.09090699,0.0004376288,0.000041247404,0.000055593322,0.0018174769,0.4874293,0.04541993,0.18632899,0.17878099,0.0016959604],"about_ca_topic_score_codex":0.000013746678,"about_ca_topic_score_gemma":3.1329103e-7,"teacher_disagreement_score":0.9421807,"about_ca_system_score_codex":0.000045715336,"about_ca_system_score_gemma":0.000046742487,"threshold_uncertainty_score":0.4125495},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023449995,0.00021580697,0.99547327,0.000102004415,0.0007088603,0.0005857848,0.00004219614,0.00006292181,0.00046415103],"genre_scores_gemma":[0.5514771,0.000014410491,0.4477177,0.00057301123,0.000105782725,0.000008794851,0.000053711505,0.000030738353,0.000018781511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99424446,0.00014147689,0.0010433899,0.0024328877,0.0014781243,0.0006596452],"domain_scores_gemma":[0.9940935,0.00050341507,0.0005959969,0.004464688,0.00020502498,0.00013741147],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002070272,0.0005604692,0.00076134206,0.0009529817,0.00021640904,0.00033610887,0.0074348566,0.00027276407,0.00002057853],"category_scores_gemma":[0.00022323235,0.0004861896,0.000048423375,0.0009823954,0.00033412728,0.0008222444,0.0042984798,0.0010483844,0.0000033266315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031291005,0.00053655053,0.004580168,0.0001967263,0.00002360179,0.00032229134,0.0015224552,0.07508388,0.00019049695,0.0057222825,0.000053856467,0.9117364],"study_design_scores_gemma":[0.0014035827,0.0005610164,0.0023775175,0.0010669216,0.000014724862,0.00001761139,0.000003759888,0.9648833,0.0004289343,0.02742047,0.00083564187,0.0009864934],"about_ca_topic_score_codex":0.0003241116,"about_ca_topic_score_gemma":0.0005540374,"teacher_disagreement_score":0.9107499,"about_ca_system_score_codex":0.00024210992,"about_ca_system_score_gemma":0.00060247997,"threshold_uncertainty_score":0.99975896},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016647305,0.00032822523,0.9815891,0.00035099126,0.00018605596,0.00029773446,0.000011435387,0.00014638326,0.00044278157],"genre_scores_gemma":[0.15162992,0.00004195601,0.8476004,0.00026803065,0.00018223099,0.000025927182,0.00001621499,0.000031780877,0.00020350738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975274,0.00003984029,0.0004932302,0.0004944437,0.00043859862,0.0010064408],"domain_scores_gemma":[0.99845225,0.0002834596,0.000122361,0.0009107453,0.00005832403,0.00017285626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011034578,0.00026984065,0.0003267872,0.00022463189,0.00012711737,0.00018336847,0.0012181595,0.00009154851,0.000020433727],"category_scores_gemma":[0.000119814504,0.00022502869,0.00007359749,0.0007294083,0.00004425202,0.000340429,0.00056209334,0.00031514515,0.00009323099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020959631,0.0005140295,0.00019713624,0.00012158567,0.000072619434,0.00009873551,0.0064265863,0.0011607225,0.0074109426,0.250176,0.0011237799,0.7326769],"study_design_scores_gemma":[0.00091287855,0.0004706321,0.00049126666,0.00028766302,0.0000188298,0.00010077147,0.00019035352,0.8375095,0.042833816,0.10978879,0.0062951464,0.0011003378],"about_ca_topic_score_codex":0.000054994205,"about_ca_topic_score_gemma":0.00013737906,"teacher_disagreement_score":0.8363488,"about_ca_system_score_codex":0.00018785692,"about_ca_system_score_gemma":0.00010825963,"threshold_uncertainty_score":0.9176404},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027426468,0.0004542181,0.994036,0.0003956445,0.0028148445,0.00047024907,0.000016858443,0.00019000634,0.0015947069],"genre_scores_gemma":[0.006593918,0.00001845659,0.991513,0.0005122177,0.00093810813,0.000016606768,0.000015240139,0.000038162765,0.00035426053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962044,0.000012990179,0.0004742346,0.0017280127,0.0008360765,0.0007443144],"domain_scores_gemma":[0.9966457,0.00065399107,0.00030337213,0.0018421314,0.0003467055,0.00020810924],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008098668,0.0005251173,0.0004992606,0.00061321,0.0005154365,0.0006289229,0.003426416,0.0004534679,0.000026807746],"category_scores_gemma":[0.00018498444,0.0004605598,0.00015818262,0.00034486028,0.0004417885,0.0011084338,0.0022448217,0.0010207966,0.000024725556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034130555,0.00002408648,0.000016011463,0.00004808137,0.00000764214,0.000030270974,0.0002691952,0.0012700836,0.0017499091,0.038474612,0.00005062193,0.9580561],"study_design_scores_gemma":[0.0003323273,0.00014363619,0.000054512624,0.0005231238,0.000008021807,0.000053250835,1.0879172e-7,0.84686613,0.006032786,0.1253137,0.0198764,0.0007960151],"about_ca_topic_score_codex":0.000019803718,"about_ca_topic_score_gemma":0.000044874665,"teacher_disagreement_score":0.9572601,"about_ca_system_score_codex":0.00015854386,"about_ca_system_score_gemma":0.00052199455,"threshold_uncertainty_score":0.9997846},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65346235,0.00044367713,0.2816267,0.05954744,0.000100839236,0.0009775589,0.00009370109,0.000051350107,0.0036963918],"genre_scores_gemma":[0.9975147,0.000085399166,0.0020708193,0.00003634569,0.00004676243,5.276479e-7,0.0000041855506,0.000003553582,0.0002377037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9982028,0.0005802857,0.0001022755,0.00018895091,0.0006144603,0.00031121398],"domain_scores_gemma":[0.9973969,0.0015061498,0.00014268728,0.00074861833,0.00010293475,0.00010270542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00232507,0.000103971215,0.00023752842,0.000068088426,0.0007522492,0.000059760754,0.0015339111,0.00004362954,0.000058822417],"category_scores_gemma":[0.00014313945,0.000052938354,0.00009277493,0.00031955546,0.002180401,0.00043275225,0.0012136821,0.00032530673,0.00001083926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080393616,0.000101313264,0.0059073875,0.000039146067,0.00012189476,0.0000028546003,0.007321138,0.000014520534,0.00014775559,0.96752286,0.010204243,0.007812974],"study_design_scores_gemma":[0.015218954,0.00057612074,0.7114081,0.00020413066,0.00011227467,0.000020438896,0.006999851,0.08542903,0.0016387132,0.16022578,0.017587908,0.0005787159],"about_ca_topic_score_codex":0.0015340355,"about_ca_topic_score_gemma":0.000062949424,"teacher_disagreement_score":0.80729705,"about_ca_system_score_codex":0.000021306605,"about_ca_system_score_gemma":0.000051603525,"threshold_uncertainty_score":0.80337787},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001424965,0.00025140235,0.99615383,0.00039903037,0.002147915,0.0003059938,0.000029402108,0.00020394429,0.0003659923],"genre_scores_gemma":[0.14157455,0.00003767419,0.85566294,0.0018296506,0.0007437986,0.000010343276,0.00006017518,0.00005176042,0.000029134613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964433,0.000037169015,0.00049037527,0.0014491245,0.0010346726,0.0005453864],"domain_scores_gemma":[0.9977345,0.000326965,0.00034126473,0.0011885753,0.0002411506,0.00016754234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047418108,0.00050208054,0.00042923167,0.00081816316,0.00044476698,0.0006390407,0.0020031307,0.00030819472,0.000065652646],"category_scores_gemma":[0.00004260402,0.0004590816,0.00013262,0.00051185046,0.00042894774,0.001199866,0.0008813843,0.0007152634,0.000057113295],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005651841,0.000038589293,0.00003134094,0.000040430972,0.0000066783314,0.00011602018,0.00012861415,0.042802494,0.000065113185,0.00048761387,0.000006149509,0.9562713],"study_design_scores_gemma":[0.00039852466,0.00015005995,0.00009128223,0.0011106444,0.000013203196,0.000092598944,1.0031805e-7,0.8866921,0.00109648,0.10933543,0.00037012823,0.000649429],"about_ca_topic_score_codex":0.000113753755,"about_ca_topic_score_gemma":0.000023777635,"teacher_disagreement_score":0.9556219,"about_ca_system_score_codex":0.0005785117,"about_ca_system_score_gemma":0.0010380972,"threshold_uncertainty_score":0.9997861},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012936607,0.0011714302,0.59652364,0.00010446102,0.00035821533,0.0006359332,0.00015766583,0.000096609474,0.4009391],"genre_scores_gemma":[0.001682344,0.011017123,0.78104144,0.00020597375,0.0013567026,0.00026477265,0.00030444126,0.0001660144,0.20396118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729544,0.000022508708,0.0009004872,0.0007344776,0.0007470772,0.00030001422],"domain_scores_gemma":[0.9973385,0.00020994834,0.00061930995,0.0012563983,0.000370294,0.0002055517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020438488,0.0003955611,0.00064043567,0.0005526438,0.000180649,0.000032857322,0.0015571112,0.00027166685,0.00009762168],"category_scores_gemma":[0.000044558026,0.00039094914,0.00020746852,0.0002625945,0.00011076657,0.0004174089,0.0007844435,0.0003587343,0.00011057541],"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":[0.000009650986,0.00014857271,0.0000503287,0.00019092388,0.0001308911,0.00004588337,0.0028467278,0.0004359039,0.0001262465,0.13810442,0.012412094,0.8454983],"study_design_scores_gemma":[0.0003448518,0.00020748477,0.00032980225,0.00051054254,0.00004838813,0.000056107343,0.000037055695,0.0048683784,0.00030006916,0.009417387,0.9830887,0.0007912391],"about_ca_topic_score_codex":0.00005746617,"about_ca_topic_score_gemma":0.000004698824,"teacher_disagreement_score":0.9706766,"about_ca_system_score_codex":0.000072963856,"about_ca_system_score_gemma":0.00030886597,"threshold_uncertainty_score":0.99985427},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21141987,0.00040216214,0.78132755,0.0008630517,0.00030651616,0.00012526967,0.000009155059,0.0001288901,0.0054175444],"genre_scores_gemma":[0.71434826,0.00030408308,0.2841713,0.000041733827,0.00003891145,9.1191237e-7,0.000003927577,0.0000049003133,0.0010859481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938756,0.00002219833,0.0001557206,0.00021446621,0.00011972919,0.00010033548],"domain_scores_gemma":[0.99959075,0.000023417475,0.000052480034,0.00024120214,0.000031035837,0.00006111075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007250542,0.000067853456,0.00010796942,0.00005436799,0.000067816036,0.000037972608,0.0001954099,0.000040452556,0.00024211702],"category_scores_gemma":[0.0000046708924,0.000051431693,0.000017506722,0.00012677963,0.00003519722,0.00046004687,0.00006843481,0.000046541667,0.000005254306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038534617,0.00003990815,0.0000785648,0.000013531461,0.000004643291,0.0000016425961,0.0001654241,0.000015429305,0.04819272,0.007895537,0.002234091,0.94135463],"study_design_scores_gemma":[0.0008564502,0.0001646186,0.0025390645,0.00011897,0.000008597268,0.00011251982,0.000047486694,0.84041446,0.1402693,0.0064418,0.00877706,0.0002496924],"about_ca_topic_score_codex":0.000096982505,"about_ca_topic_score_gemma":0.000002027686,"teacher_disagreement_score":0.94110495,"about_ca_system_score_codex":0.000005461044,"about_ca_system_score_gemma":0.0000052054925,"threshold_uncertainty_score":0.26510116},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001832975,0.000033241882,0.99493885,0.00053812173,0.00033717533,0.00011277464,0.000011185606,0.00013966062,0.0020560073],"genre_scores_gemma":[0.11378372,0.0000015722408,0.8824936,0.00041175773,0.00040963697,0.000018615348,0.000034283185,0.000012249208,0.0028345298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991584,0.000011064858,0.00015471369,0.0002904538,0.00014080665,0.0002445641],"domain_scores_gemma":[0.9994838,0.000066323475,0.00004457997,0.00032581043,0.00003475671,0.00004467788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000112497146,0.00009524552,0.000091815346,0.000054326283,0.00015852085,0.00027057104,0.00044127816,0.000037395537,0.000030848314],"category_scores_gemma":[0.0000048846773,0.000074417,0.000049773033,0.00008328953,0.000007950921,0.00053254195,0.00019870166,0.000043393346,0.000019310794],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038315957,0.00010629467,0.0023640948,0.000032735217,0.000009151769,0.000015245829,0.00013023468,0.00012888908,0.002414896,0.039616447,0.02642226,0.92875594],"study_design_scores_gemma":[0.00057999365,0.000055612032,0.0058680573,0.00004879623,0.000004100931,0.000017334622,0.00001858382,0.91948324,0.008563822,0.009575128,0.05547269,0.0003126648],"about_ca_topic_score_codex":0.000106301486,"about_ca_topic_score_gemma":0.0000062486224,"teacher_disagreement_score":0.92844325,"about_ca_system_score_codex":0.000016239117,"about_ca_system_score_gemma":0.000014874073,"threshold_uncertainty_score":0.30346373},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046697687,0.00018608832,0.94278836,0.004368829,0.0007903137,0.0001700587,0.0000014515149,0.00011721459,0.004880024],"genre_scores_gemma":[0.31793284,0.000012983094,0.6790772,0.0010455764,0.000232818,0.000014467848,0.0000030850515,0.000010908076,0.0016701063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906385,0.000050548893,0.00018116439,0.0002595574,0.00023700074,0.0002078901],"domain_scores_gemma":[0.9992665,0.00005399132,0.000037667472,0.00047448167,0.000067993795,0.00009934624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042371787,0.0000801141,0.000088755485,0.000066723514,0.00014933069,0.00023215551,0.00064816553,0.000029736535,0.000009063982],"category_scores_gemma":[0.00009041097,0.00005086312,0.000017908344,0.000463841,0.000022913657,0.00071338454,0.00050241227,0.000099710145,0.000036171743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015583527,0.00043272998,0.009123448,0.000026629874,0.00004615878,0.000115007206,0.01972601,0.14726074,0.011909592,0.37141064,0.15086605,0.28892717],"study_design_scores_gemma":[0.00061493454,0.00010610598,0.0031564406,0.00016070997,0.000004397664,0.000058489946,0.0006947831,0.81564826,0.004172817,0.03761449,0.13736525,0.00040329323],"about_ca_topic_score_codex":0.0007077369,"about_ca_topic_score_gemma":0.0000470902,"teacher_disagreement_score":0.66838753,"about_ca_system_score_codex":0.00006106685,"about_ca_system_score_gemma":0.00012327878,"threshold_uncertainty_score":0.22386809},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002137791,0.00034231727,0.9952426,0.0004255868,0.0007314926,0.0003437885,0.000013450374,0.00009311851,0.0006698348],"genre_scores_gemma":[0.3406621,0.00017148205,0.65593326,0.0014458613,0.0011532869,0.000022612787,0.000040005365,0.00007766431,0.0004937438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958651,0.00004477478,0.0007058828,0.0016287579,0.00092366984,0.00083183585],"domain_scores_gemma":[0.9979546,0.00031986507,0.00023861857,0.0012605177,0.00007454548,0.00015186465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010326897,0.00050116546,0.0005656043,0.0017017566,0.00011749917,0.00056178437,0.0034849015,0.00031877137,0.000056912995],"category_scores_gemma":[0.000055856766,0.00046957986,0.000087163935,0.00081828673,0.00016812314,0.001147611,0.0022412539,0.0011597445,0.00007054406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056146378,0.00006856434,0.0015985376,0.000034413813,0.000003942163,0.000441515,0.0008363714,0.063084655,0.00015593434,0.003998667,0.000016170568,0.9297556],"study_design_scores_gemma":[0.00048452933,0.00007906391,0.0019237507,0.0013068636,0.0000017740022,0.000042626816,1.7077383e-7,0.97897774,0.0004366724,0.015060151,0.0010097986,0.00067687687],"about_ca_topic_score_codex":0.00017874564,"about_ca_topic_score_gemma":0.00044772425,"teacher_disagreement_score":0.92907876,"about_ca_system_score_codex":0.00061701814,"about_ca_system_score_gemma":0.00037094994,"threshold_uncertainty_score":0.9997756},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059003414,0.0003365611,0.9936793,0.0004267369,0.0019901379,0.0004549534,0.000026881513,0.00015121134,0.002875254],"genre_scores_gemma":[0.069916494,0.00007044549,0.9252137,0.0030083673,0.0009048206,0.000020278136,0.000043114047,0.000069708636,0.0007530586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99475944,0.00005733023,0.00065608183,0.002030447,0.001607149,0.00088954216],"domain_scores_gemma":[0.9965328,0.00044745032,0.00034660017,0.002202462,0.00014388301,0.00032682208],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008838728,0.0006758035,0.0006539494,0.00058494176,0.00036510982,0.0006153317,0.0042892923,0.00028270012,0.000033893797],"category_scores_gemma":[0.000055885717,0.00059533387,0.00014908904,0.00044821974,0.0004239681,0.00082069536,0.00255117,0.0006713977,0.00011552843],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003382379,0.0000566289,0.0007675457,0.00002598668,0.00002928886,0.00012961947,0.0003448705,0.008262157,0.00015797939,0.00954565,0.0003537047,0.9803232],"study_design_scores_gemma":[0.0021858905,0.0004755518,0.00067476794,0.0011049758,0.00003902373,0.000112482645,2.99385e-7,0.5643203,0.009740054,0.34767875,0.07068756,0.0029803175],"about_ca_topic_score_codex":0.000045307406,"about_ca_topic_score_gemma":0.00001724539,"teacher_disagreement_score":0.97734284,"about_ca_system_score_codex":0.00042481857,"about_ca_system_score_gemma":0.00027989055,"threshold_uncertainty_score":0.9996498},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072051845,0.000037198235,0.9261752,0.0010654493,0.00012037712,0.0003592612,0.000021594722,0.000065485874,0.00010358904],"genre_scores_gemma":[0.77640337,0.000010708135,0.22323294,0.00010376658,0.000041746553,0.000015546062,0.00015780135,0.000005976717,0.000028141023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991645,0.000029564704,0.00027558915,0.00021322118,0.00017369154,0.00014343114],"domain_scores_gemma":[0.99905884,0.000023727045,0.00016999841,0.0005780872,0.00012219082,0.000047181435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018402492,0.00009229784,0.000117881624,0.00008933247,0.00014490943,0.00007055691,0.0004348259,0.000039739236,0.000018557947],"category_scores_gemma":[0.0000058025535,0.00008060199,0.000041530315,0.00020254773,0.00001557654,0.0007382639,0.00017244431,0.0000382948,0.0000055526575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006452078,0.0004881175,0.0015064828,0.00011915056,0.00008242462,0.000002023744,0.0062416266,0.039816517,0.039564837,0.70945334,0.0030404879,0.19962047],"study_design_scores_gemma":[0.007286775,0.00056460185,0.08084192,0.0001278302,0.00004266675,0.0000107635715,0.0007240246,0.63142,0.19548804,0.08159156,0.0011960702,0.00070575613],"about_ca_topic_score_codex":0.0005943318,"about_ca_topic_score_gemma":0.0001155164,"teacher_disagreement_score":0.70435154,"about_ca_system_score_codex":0.00004919848,"about_ca_system_score_gemma":0.00005500796,"threshold_uncertainty_score":0.32868537},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000086439846,0.0007304583,0.9894286,0.00085331255,0.0024623026,0.00027875454,0.000013367125,0.00023745112,0.0059093405],"genre_scores_gemma":[0.046950586,0.000050265975,0.94700223,0.0026510363,0.0020092272,0.000009659136,0.000025645644,0.000056157925,0.001245212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948928,0.000037905746,0.0006260604,0.0020348253,0.0015365073,0.0008718975],"domain_scores_gemma":[0.99697983,0.00055275805,0.00031185834,0.0016256821,0.00022890189,0.0003009474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076422596,0.00065384427,0.0005852708,0.00079595,0.00047855437,0.00067459507,0.0039870376,0.00030296063,0.000102646096],"category_scores_gemma":[0.000061014918,0.00056705443,0.0001751643,0.00054345326,0.0005840834,0.0012613082,0.0034090797,0.0010174274,0.00018034336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005142413,0.000042812026,0.000025837906,0.000018715464,0.000009063797,0.00014800223,0.00024871618,0.0637484,0.00037633136,0.016096473,0.00029583508,0.91898465],"study_design_scores_gemma":[0.00046391756,0.00012113888,0.00006833301,0.0005820341,0.000007802832,0.00019890662,6.553585e-8,0.9037113,0.0015615099,0.08112878,0.011181149,0.00097501575],"about_ca_topic_score_codex":0.000037825008,"about_ca_topic_score_gemma":0.000078019315,"teacher_disagreement_score":0.91800964,"about_ca_system_score_codex":0.0003676482,"about_ca_system_score_gemma":0.0007544028,"threshold_uncertainty_score":0.9996781},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003840705,0.00017769756,0.99728936,0.00016422721,0.0001051493,0.0001254128,0.000065471315,0.00007536402,0.0016132648],"genre_scores_gemma":[0.22423106,0.000022549233,0.7753618,0.000078961966,0.000063812215,0.0000046440537,0.00006162131,0.0000063354914,0.00016926439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999065,0.000017442015,0.00020962348,0.0003540796,0.00019436887,0.00015953174],"domain_scores_gemma":[0.9985446,0.00007310883,0.00005924436,0.0011982452,0.000069720525,0.000055116918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016925475,0.000082474064,0.00012842384,0.000048102796,0.000086821914,0.0000652243,0.0017024064,0.000033464014,0.00011289672],"category_scores_gemma":[0.000014621598,0.000061086655,0.000030259152,0.00010602378,0.000017584536,0.0011526374,0.001254324,0.000049888364,0.0000140278835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004027553,0.0010300815,0.00005138044,0.00020718694,0.000055266057,0.000016643235,0.0005349251,0.014191865,0.06894843,0.051105037,0.26175317,0.60206574],"study_design_scores_gemma":[0.00027786705,0.000038022154,0.0000034541856,0.00002751872,0.0000028159216,0.000002953509,0.000007862137,0.99418324,0.0013473749,0.0011497997,0.0028720815,0.000086988795],"about_ca_topic_score_codex":0.000034856064,"about_ca_topic_score_gemma":9.830289e-7,"teacher_disagreement_score":0.9799914,"about_ca_system_score_codex":0.000004614541,"about_ca_system_score_gemma":0.000007324847,"threshold_uncertainty_score":0.3163523},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011452,0.0009460877,0.99656063,0.0004955564,0.0009254967,0.00041778386,0.000017820685,0.00012437705,0.0003977012],"genre_scores_gemma":[0.008927915,0.00012553204,0.98874843,0.0013927324,0.00066092535,0.000010124459,0.000014730811,0.000017272876,0.00010235966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966585,0.000020682372,0.0004622153,0.0016517995,0.0005590417,0.0006477645],"domain_scores_gemma":[0.9979464,0.0006822135,0.00025739524,0.00076063245,0.00019888725,0.00015450684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009561522,0.0004694373,0.000511181,0.00039488284,0.00042396982,0.00087978377,0.002121012,0.00033527863,0.0000055158403],"category_scores_gemma":[0.00008974319,0.00036080062,0.00009216241,0.00025494304,0.0005456748,0.00075372274,0.0012386485,0.0004905203,0.0000053489302],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032793782,0.000009543554,0.000029019347,0.00001627688,0.0000039189335,0.000014782208,0.00015372623,0.001380454,0.00012299698,0.008219964,0.000006837003,0.9900392],"study_design_scores_gemma":[0.0002717412,0.0003194242,0.00021468446,0.00042154858,0.0000054096845,0.000098492346,2.7772805e-7,0.7180254,0.0003171391,0.27258736,0.0070644096,0.0006741485],"about_ca_topic_score_codex":0.000015065958,"about_ca_topic_score_gemma":0.000009542588,"teacher_disagreement_score":0.98936504,"about_ca_system_score_codex":0.00010150143,"about_ca_system_score_gemma":0.00020588632,"threshold_uncertainty_score":0.99988437},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87569976,0.00013833331,0.1211897,0.0025027038,0.000027691494,0.00011891429,0.000006217047,0.000014757058,0.00030193865],"genre_scores_gemma":[0.9936109,0.0003861901,0.0055598775,0.0000211486,0.000012905179,2.3084236e-7,0.0000070054434,0.0000022579018,0.00039948607],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991925,0.000105682586,0.000054575205,0.00017159007,0.0003624912,0.000113191505],"domain_scores_gemma":[0.9994174,0.00010037611,0.00006904799,0.0002794345,0.00007957275,0.000054129057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002273423,0.000056193094,0.00009626209,0.00010598515,0.00041418738,0.000022111117,0.0003688504,0.000031919462,0.000049702154],"category_scores_gemma":[0.000023011868,0.00004515684,0.000028211927,0.00021502712,0.00023826353,0.00035525963,0.00023875505,0.00008831212,0.000008411662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011394112,0.0012973988,0.028556725,0.0004480413,0.00037409936,0.000382367,0.12011115,0.0020096102,0.32059327,0.14880821,0.1357578,0.2405219],"study_design_scores_gemma":[0.0025058205,0.0014481012,0.10650889,0.00013133434,0.000017686007,0.000057793783,0.0037943218,0.8702884,0.008445916,0.0015797963,0.0048402664,0.00038168638],"about_ca_topic_score_codex":0.00037881394,"about_ca_topic_score_gemma":0.00006132457,"teacher_disagreement_score":0.8682788,"about_ca_system_score_codex":0.000017885663,"about_ca_system_score_gemma":0.000058485257,"threshold_uncertainty_score":0.31856364},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081167644,0.001036883,0.99521583,0.0004384652,0.00093505747,0.0002607208,0.0000043408986,0.00010448069,0.0011925676],"genre_scores_gemma":[0.1822037,0.00021401921,0.81543833,0.0011099342,0.0006549838,0.000008565249,0.000007879692,0.000042506006,0.00032010916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966707,0.000028338301,0.0004992281,0.0014984875,0.00068942143,0.0006137751],"domain_scores_gemma":[0.9981245,0.00037655866,0.0002431361,0.0010020535,0.00008057732,0.00017318326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070329773,0.0004398464,0.00044818275,0.00071578985,0.000200104,0.00047492085,0.0020651112,0.0002601121,0.000013200544],"category_scores_gemma":[0.00007936202,0.00039320963,0.000054849726,0.0004081187,0.00036175988,0.0009273399,0.002177445,0.0007761986,0.000019683117],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028659158,0.000018118422,0.00025421145,0.000019265352,0.000002564041,0.00009441511,0.00057199376,0.011371857,0.00007616454,0.0034893479,0.000016246695,0.98408294],"study_design_scores_gemma":[0.0003718826,0.00007896559,0.0013676607,0.0005690714,0.0000029404719,0.00008023817,1.6662875e-7,0.9715463,0.00036026732,0.022165567,0.0028088873,0.00064804987],"about_ca_topic_score_codex":0.00005928036,"about_ca_topic_score_gemma":0.00018850261,"teacher_disagreement_score":0.9834349,"about_ca_system_score_codex":0.00020156626,"about_ca_system_score_gemma":0.0002501402,"threshold_uncertainty_score":0.999852},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011254933,0.0006360287,0.99733174,0.00024716379,0.0004513961,0.00041205785,0.00009800639,0.00003290479,0.00067818345],"genre_scores_gemma":[0.14844236,0.00007917614,0.8500676,0.0010392044,0.00015207335,0.000007715933,0.00011008636,0.000025964573,0.00007582009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961211,0.00010540726,0.0005977136,0.0015136342,0.0011774446,0.0004846623],"domain_scores_gemma":[0.9941887,0.00075243384,0.000335819,0.0044153687,0.00022930244,0.00007836139],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021924055,0.00040946176,0.00050287606,0.0005348577,0.00013158149,0.0004566899,0.01417005,0.00024253422,0.000015094004],"category_scores_gemma":[0.0001343471,0.00026302363,0.000047187918,0.00074367045,0.0005570783,0.0013609902,0.0054675937,0.00079167093,0.000010907855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005064536,0.00004629496,0.00013601047,0.000041269046,0.000007188891,0.000026581361,0.0009098084,0.08597558,0.000030642677,0.024369871,0.00040564663,0.888046],"study_design_scores_gemma":[0.00012467908,0.000045068842,0.0021717953,0.00013619455,0.0000023004388,0.000014443309,9.937263e-8,0.86555564,0.00003257494,0.13148999,0.00015280845,0.00027441845],"about_ca_topic_score_codex":0.0007945919,"about_ca_topic_score_gemma":0.0006670136,"teacher_disagreement_score":0.8877716,"about_ca_system_score_codex":0.00006130311,"about_ca_system_score_gemma":0.00058918376,"threshold_uncertainty_score":0.9999822},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045416848,0.00016463696,0.98459405,0.0004038721,0.00019960392,0.000070926246,0.000004380059,0.0002948314,0.013813555],"genre_scores_gemma":[0.008523998,0.00003321501,0.9886785,0.00040391806,0.00013759466,0.000008702566,0.00000760772,0.0000075084977,0.002198954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988658,0.00003362053,0.0001584006,0.0004129432,0.00025118847,0.00027804356],"domain_scores_gemma":[0.99890107,0.000025575362,0.000036771322,0.00082520436,0.000035564226,0.00017582625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089238,0.00012796899,0.000119220436,0.00005743842,0.00012203197,0.00021558031,0.0011063042,0.000053242762,0.00063059723],"category_scores_gemma":[0.0000041347084,0.000099376186,0.00004360164,0.00017454856,0.0000269861,0.0012108708,0.00024761024,0.000086479726,0.0004280395],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011602585,0.00014934942,0.00001417932,9.3248923e-7,0.0000041327476,0.00002960019,0.00016084581,0.00010136798,0.000070777656,0.0031153935,0.025929827,0.97042245],"study_design_scores_gemma":[0.00027288214,0.00013801479,0.000430994,0.000003175676,0.0000016034872,0.000025079016,0.000016832239,0.9637939,0.0002402119,0.0002500604,0.03465907,0.00016822288],"about_ca_topic_score_codex":0.000023383383,"about_ca_topic_score_gemma":0.000001996888,"teacher_disagreement_score":0.9702542,"about_ca_system_score_codex":0.00001191832,"about_ca_system_score_gemma":0.000008068702,"threshold_uncertainty_score":0.6904597},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38859215,0.0001591642,0.6105016,0.00013519287,0.00013468695,0.00025746712,0.00000627017,0.000038548427,0.00017491046],"genre_scores_gemma":[0.82396907,3.693131e-7,0.17578684,0.000057815738,0.00014682625,0.000007296497,0.000020863177,0.000004945986,0.000005961228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981866,0.00030053835,0.0003115427,0.00063070277,0.00023866238,0.0003319426],"domain_scores_gemma":[0.9982237,0.00018046917,0.00011568517,0.0013168214,0.000035696732,0.00012762136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001269003,0.00017927065,0.00020627365,0.000073316594,0.00029808815,0.00036967496,0.0016155085,0.000029966222,0.0000020071177],"category_scores_gemma":[0.000014234363,0.00012784744,0.000020660073,0.0002231535,0.00004546988,0.0008696731,0.002821098,0.000307341,0.000007671734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076830065,0.00038496876,0.030605035,0.000004207862,0.000015854106,0.00055981666,0.00448717,0.0008508789,0.0000019077409,0.00030789993,0.0013436724,0.9614309],"study_design_scores_gemma":[0.0034410348,0.0005337969,0.031216377,0.00009538055,0.000029617115,0.0022534316,0.028335862,0.8529076,0.000006780769,0.00018774412,0.08045594,0.0005364429],"about_ca_topic_score_codex":0.00059237255,"about_ca_topic_score_gemma":0.00004777782,"teacher_disagreement_score":0.96089447,"about_ca_system_score_codex":0.000019362817,"about_ca_system_score_gemma":0.00008713721,"threshold_uncertainty_score":0.5213467},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018738852,0.0005252428,0.99247473,0.00052708894,0.0023504188,0.0002819122,0.000010786218,0.00024323708,0.0035678684],"genre_scores_gemma":[0.08035179,0.00013981841,0.9172953,0.0012625187,0.00035593082,0.000008014254,0.000022332466,0.000051421524,0.00051289564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959091,0.000019027237,0.00048345362,0.0017682762,0.0010947972,0.0007253454],"domain_scores_gemma":[0.99736613,0.000206577,0.00026589862,0.0017869073,0.00016885139,0.00020560913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005916078,0.00055222603,0.00049862027,0.0007797207,0.00035075864,0.0007412108,0.0045291386,0.0003329972,0.000046016725],"category_scores_gemma":[0.000041437757,0.00048949703,0.00012686262,0.0005488453,0.00046983457,0.0010177158,0.0027394348,0.00088105834,0.00010969849],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032783823,0.000027813094,0.0000062918734,0.00003970809,0.000007242165,0.00021025556,0.0003678214,0.027948432,0.00021197386,0.06480221,0.000021013997,0.90635395],"study_design_scores_gemma":[0.00025382955,0.00011080298,0.00006348453,0.0007289508,0.0000043254245,0.000079271114,5.411728e-8,0.70016533,0.00037606497,0.29615045,0.001432198,0.000635266],"about_ca_topic_score_codex":0.000032123447,"about_ca_topic_score_gemma":0.000034813493,"teacher_disagreement_score":0.9057187,"about_ca_system_score_codex":0.0005710868,"about_ca_system_score_gemma":0.00069645676,"threshold_uncertainty_score":0.9997557},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053338003,0.0003373069,0.9944032,0.0005908599,0.0019420366,0.0010343274,0.000033160686,0.00021148124,0.001442338],"genre_scores_gemma":[0.0044394415,0.000055539018,0.99276763,0.0006169107,0.0011090549,0.000055773682,0.0000421006,0.000047698744,0.0008658384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955332,0.000026887028,0.00063779537,0.0019393549,0.0010053826,0.00085732917],"domain_scores_gemma":[0.9971484,0.00033661106,0.00040748678,0.0016434735,0.00023712515,0.00022693211],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079638354,0.0006314495,0.0005745649,0.0005930149,0.0003974414,0.0008315899,0.003378451,0.00035600938,0.000036883677],"category_scores_gemma":[0.000057729252,0.000549313,0.00020147725,0.00038228874,0.00033868922,0.0010450769,0.0013259157,0.00062771427,0.000027792277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064375554,0.000062148734,0.0000025127315,0.000049284863,0.0000127630765,0.000019505282,0.00033635506,0.0070175845,0.00033575328,0.015005823,0.00017093605,0.9769809],"study_design_scores_gemma":[0.000448856,0.00029755238,0.000023456683,0.00018689074,0.000008829905,0.000036347858,1.16104154e-7,0.9129539,0.001398324,0.08014229,0.0038657081,0.0006377012],"about_ca_topic_score_codex":0.000016149754,"about_ca_topic_score_gemma":0.0000079630945,"teacher_disagreement_score":0.9763432,"about_ca_system_score_codex":0.00044484623,"about_ca_system_score_gemma":0.00028839285,"threshold_uncertainty_score":0.99969584},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020641996,0.000042769116,0.86884254,0.006524481,0.00024465137,0.00009601531,0.0000016464722,0.00016030534,0.103445604],"genre_scores_gemma":[0.9690922,0.0000021645105,0.024626795,0.00221872,0.00014676241,0.00000551092,0.0000059706244,0.000004310587,0.003897591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993891,0.000024434912,0.00007880739,0.00016815803,0.00022593411,0.00011354254],"domain_scores_gemma":[0.99929506,0.00011208797,0.000022035407,0.0005340023,0.000016510561,0.000020333006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013371765,0.00005971934,0.000044581848,0.00002440336,0.00035732347,0.000084233696,0.0007371507,0.000021882535,0.0001307237],"category_scores_gemma":[0.000008818958,0.000028785475,0.00002433219,0.00012850975,0.000013237267,0.00018124815,0.0015140914,0.000059802504,0.00013776938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016486944,0.000045311994,0.000054237422,4.5248493e-7,8.024035e-7,0.000002874754,0.000036869747,0.000042122578,0.00031753676,0.84792215,0.08547656,0.06609942],"study_design_scores_gemma":[0.00048238144,0.0001337228,0.021040902,0.000028355276,0.0000025027598,0.000005316987,0.000010259892,0.30174246,0.007860647,0.42813563,0.24024007,0.00031774762],"about_ca_topic_score_codex":0.00015908731,"about_ca_topic_score_gemma":0.00001639828,"teacher_disagreement_score":0.9484502,"about_ca_system_score_codex":0.000010929658,"about_ca_system_score_gemma":0.0000104008095,"threshold_uncertainty_score":0.27482793},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12233425,0.00090028584,0.869707,0.0019019231,0.0009991764,0.00082941965,0.00003228732,0.00026202708,0.0030336143],"genre_scores_gemma":[0.38866535,0.000033497574,0.5987856,0.0005993067,0.0005924576,0.00014868795,0.00010299568,0.000026247644,0.011045882],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990543,0.000020687263,0.00018099013,0.00039994856,0.00010712282,0.00023694756],"domain_scores_gemma":[0.9993677,0.000057592413,0.00004089381,0.00045482715,0.00005094246,0.000028057306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022918495,0.00010288802,0.00012303877,0.00007983567,0.00008512646,0.00016148796,0.00041726805,0.0000396084,0.000013155818],"category_scores_gemma":[0.000019952255,0.00007877684,0.000042054922,0.0001870918,0.000017243536,0.0007316982,0.00018248215,0.000063961415,0.000008305217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002917893,0.0014406779,0.00820516,0.00018483432,0.00003584615,0.000042498425,0.0002583026,0.0014722652,0.13929361,0.053928003,0.40729827,0.38754874],"study_design_scores_gemma":[0.0020625987,0.00069435814,0.04017485,0.00008952,0.000007475042,0.000024127188,0.000027646354,0.7756228,0.032603297,0.039965805,0.107867524,0.0008600173],"about_ca_topic_score_codex":0.00039571352,"about_ca_topic_score_gemma":0.00012554393,"teacher_disagreement_score":0.77415055,"about_ca_system_score_codex":0.000028720986,"about_ca_system_score_gemma":0.000060533384,"threshold_uncertainty_score":0.32124263},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4691753,0.0015068961,0.4546387,0.0027542247,0.00087806047,0.0018093657,0.000082282815,0.0008159043,0.068339266],"genre_scores_gemma":[0.96648586,0.00006388088,0.032715484,0.00029920822,0.00009312552,0.000031412423,0.0000634871,0.0000091054335,0.00023846715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998795,0.000028587574,0.00038833288,0.00015451074,0.00029869258,0.00033491515],"domain_scores_gemma":[0.9991832,0.00011282332,0.00010277271,0.00049647747,0.000024950781,0.00007981793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026241297,0.0001438036,0.00013564178,0.00004661697,0.0007175284,0.0008141992,0.0007152876,0.000040332856,0.000009313734],"category_scores_gemma":[0.0000039072934,0.000091115595,0.00003086275,0.0001176707,0.00009497559,0.0014143357,0.0008832684,0.00015000936,0.000042725376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068620415,0.00039438147,0.024196543,0.00023104559,0.00008788493,0.000032255633,0.004744041,0.0014969232,0.0057836287,0.49035537,0.028986514,0.4436228],"study_design_scores_gemma":[0.0014794433,0.0003194015,0.053195372,0.00018141136,0.00001884508,0.00012011813,0.0005702108,0.5100512,0.0008948502,0.017011946,0.41541162,0.0007455581],"about_ca_topic_score_codex":0.00012089423,"about_ca_topic_score_gemma":0.000015975631,"teacher_disagreement_score":0.5085543,"about_ca_system_score_codex":0.00004098706,"about_ca_system_score_gemma":0.000019522593,"threshold_uncertainty_score":0.78513414},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058057806,0.0000071817653,0.9928374,0.00026134268,0.00007007735,0.00015424025,0.0000030731978,0.000091560345,0.0007693427],"genre_scores_gemma":[0.56839055,0.0000016481428,0.43136963,0.00010344145,0.000037699017,0.0000116549145,0.0000020724488,0.0000018481811,0.00008143764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945,0.000011352272,0.0001172198,0.0001974818,0.000069123416,0.00015477657],"domain_scores_gemma":[0.9997235,0.000094682,0.000024115394,0.000096303316,0.000027155878,0.00003425284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013325637,0.000055065993,0.000064625376,0.00005878828,0.00006079298,0.000050930557,0.0002065292,0.000030929546,0.000021038893],"category_scores_gemma":[0.000034355817,0.00004759058,0.000019844865,0.00010487874,0.000013072863,0.00048084478,0.000068397436,0.000046588495,0.000015924716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010964358,0.0001299729,0.0027931663,0.000008166228,0.000004016013,0.000001038188,0.00029773894,0.0026382608,0.011744325,0.029627156,0.0028350437,0.94991016],"study_design_scores_gemma":[0.0005858395,0.000016068758,0.0019876438,0.000008820606,3.8627908e-7,0.0000035535911,0.000009569578,0.986057,0.0061982996,0.00021794073,0.0048436234,0.00007130023],"about_ca_topic_score_codex":0.000055850833,"about_ca_topic_score_gemma":0.0001755972,"teacher_disagreement_score":0.9834187,"about_ca_system_score_codex":0.000033973374,"about_ca_system_score_gemma":0.00002026306,"threshold_uncertainty_score":0.19406876},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005058648,0.0004188643,0.9941244,0.0008398456,0.0028415404,0.00087636453,0.000047795085,0.00022629341,0.0006198371],"genre_scores_gemma":[0.0055211876,0.00005373252,0.9917046,0.0011197306,0.00093574164,0.000025539333,0.000032546977,0.000046070494,0.0005608829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99497336,0.000018353745,0.0006280346,0.002213762,0.0012315104,0.000934966],"domain_scores_gemma":[0.99655944,0.00049620407,0.0003448208,0.0019673829,0.00023171715,0.00040041702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006486956,0.00069560244,0.00061419606,0.0005395931,0.00038883073,0.000713961,0.0048374897,0.0003729558,0.000031583335],"category_scores_gemma":[0.0000898197,0.00061420683,0.00020571574,0.00043804306,0.00035698418,0.0010082644,0.0020534417,0.00055173587,0.000047666046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069196417,0.000027147917,0.0000060211246,0.00003426044,0.000010931199,0.00007046696,0.00034657196,0.019338366,0.00038458366,0.028693426,0.00015042225,0.9509309],"study_design_scores_gemma":[0.0008582515,0.00029301608,0.000019911737,0.00059041934,0.000009518187,0.00008683229,1.2188325e-7,0.60728115,0.0051620044,0.37548605,0.009296233,0.0009165058],"about_ca_topic_score_codex":0.0001346384,"about_ca_topic_score_gemma":0.00003861032,"teacher_disagreement_score":0.95001435,"about_ca_system_score_codex":0.00067729736,"about_ca_system_score_gemma":0.0015876568,"threshold_uncertainty_score":0.9996309},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019232197,0.00026044348,0.9939256,0.00012032763,0.0043518334,0.0007041451,0.00009102561,0.00024492302,0.00028251924],"genre_scores_gemma":[0.006314123,0.00000693498,0.9903045,0.00059721735,0.0025158837,0.000014370906,0.00008553621,0.000045248198,0.00011614548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951153,0.000031182873,0.0007634415,0.002192912,0.0009936248,0.0009035604],"domain_scores_gemma":[0.9960899,0.00047622577,0.00057290436,0.0020149073,0.0005033086,0.00034276856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013210911,0.0007029195,0.00066009414,0.0005476691,0.00063194963,0.0010284303,0.0046216184,0.00047238587,0.0000069758466],"category_scores_gemma":[0.00007791687,0.00060924655,0.00016251946,0.00053557346,0.00064409786,0.0017865441,0.0013766928,0.0009696995,0.0000050356357],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007403603,0.00001879997,0.000013521305,0.000022556256,0.000005604767,0.000028271721,0.00014400811,0.0016402216,0.00013100723,0.005117824,0.000014594988,0.9928562],"study_design_scores_gemma":[0.00038459394,0.00034417727,0.00007543499,0.00015739055,0.000006329162,0.00003360217,1.8795686e-7,0.89747596,0.0007494035,0.09881674,0.0012527277,0.0007034274],"about_ca_topic_score_codex":0.000062495594,"about_ca_topic_score_gemma":0.00025235594,"teacher_disagreement_score":0.99215275,"about_ca_system_score_codex":0.0003083659,"about_ca_system_score_gemma":0.00055654044,"threshold_uncertainty_score":0.9996359},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004759465,0.000728264,0.99692327,0.0002322787,0.00062455,0.0005894475,0.00006147719,0.00021733773,0.00057580427],"genre_scores_gemma":[0.0077005145,0.00007991669,0.99093074,0.0007963446,0.00036186585,0.000009683497,0.00004250156,0.000019768593,0.000058685844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996077,0.000020722591,0.00045802153,0.0021436156,0.00062827923,0.0006723371],"domain_scores_gemma":[0.99653554,0.0006997858,0.00023088786,0.0021616637,0.00019100423,0.0001810912],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020441378,0.00043318098,0.00045066248,0.000536067,0.00037370302,0.00053940533,0.0049130213,0.00038963972,0.0000048227284],"category_scores_gemma":[0.00016174375,0.0003381685,0.000049454862,0.00038166216,0.0008287043,0.0004410655,0.006247173,0.0005703273,0.0000035438734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064157994,0.000020555353,0.000027509031,0.000028674434,0.00000402211,0.000032759268,0.00007730899,0.0014016632,0.0002989066,0.012337503,0.000033402102,0.9857313],"study_design_scores_gemma":[0.00013716661,0.00017274225,0.000031871085,0.00037712711,0.0000037558168,0.0000795932,8.8547445e-8,0.95361483,0.0010736089,0.035835635,0.008181765,0.0004918186],"about_ca_topic_score_codex":0.000023321189,"about_ca_topic_score_gemma":0.000011538312,"teacher_disagreement_score":0.98523945,"about_ca_system_score_codex":0.00013727706,"about_ca_system_score_gemma":0.00028324517,"threshold_uncertainty_score":0.999907},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04111393,0.000037565827,0.9532031,0.0003417902,0.001112352,0.0001552638,0.0000030871213,0.00046845505,0.003564452],"genre_scores_gemma":[0.67046016,0.0000031604334,0.32914847,0.0002589221,0.000090012974,0.0000056640188,0.000002964875,0.000008012797,0.00002265541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667484,0.00013953073,0.0003179729,0.00096990855,0.0011557029,0.00074202],"domain_scores_gemma":[0.9972315,0.00014356029,0.0001026566,0.0014399048,0.00035297842,0.0007294178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016200452,0.0002501345,0.00025312733,0.00028601347,0.00038460814,0.0007768405,0.0039145937,0.0000769871,0.0000208582],"category_scores_gemma":[0.00014697798,0.00019449115,0.00006406356,0.0017360129,0.0017787224,0.0014674524,0.0025535098,0.00028428965,0.0001918754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008965918,0.00007087536,0.00010877055,0.0000033768392,0.000003241734,0.000016572227,0.00046748863,0.00012373483,0.0003878469,0.9391414,0.00050852954,0.059159227],"study_design_scores_gemma":[0.00053979136,0.00026688277,0.0011761282,0.0000565383,0.000005703855,0.00010043481,0.0000065007716,0.5634215,0.0034753794,0.42692167,0.003535789,0.0004937006],"about_ca_topic_score_codex":0.000012198277,"about_ca_topic_score_gemma":0.0000012930961,"teacher_disagreement_score":0.6293462,"about_ca_system_score_codex":0.00008156509,"about_ca_system_score_gemma":0.00025237235,"threshold_uncertainty_score":0.79311186},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014446024,0.0012883889,0.017458241,0.0026604882,0.012736958,0.0014977118,0.0021181288,0.0010647402,0.9610309],"genre_scores_gemma":[0.00044356452,0.0003136803,0.0015636807,0.0012168351,0.0024675264,0.00004238794,0.0007470363,0.00013027014,0.993075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945482,0.00004003963,0.0008916077,0.0016719607,0.0017698348,0.0010783382],"domain_scores_gemma":[0.9972594,0.00010274891,0.00047180956,0.0011833691,0.00036146934,0.0006212404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002685129,0.0010002194,0.0009986546,0.00025415383,0.00044185732,0.000697331,0.0031561148,0.0006285089,0.00043456838],"category_scores_gemma":[0.000007486948,0.00087938906,0.00019830238,0.0002589158,0.000083592815,0.0012887167,0.0012067242,0.001026771,0.00027786885],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001928821,0.000106605694,0.000008963891,0.000076500924,0.00006270325,0.0001622091,0.00054128084,0.00001965385,0.000004572658,0.0046203006,0.98233896,0.012038931],"study_design_scores_gemma":[0.0010519826,0.0001492057,0.00009859675,0.00036387326,0.000051138042,0.00009443624,0.000029225263,0.004350655,0.000030124911,0.008432747,0.9840549,0.0012931129],"about_ca_topic_score_codex":0.431437,"about_ca_topic_score_gemma":0.095700644,"teacher_disagreement_score":0.33573636,"about_ca_system_score_codex":0.0012377773,"about_ca_system_score_gemma":0.0065480075,"threshold_uncertainty_score":0.9993657},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28674594,0.0001756447,0.63371754,0.00035843576,0.00065584626,0.00053975626,0.000023217075,0.0005142406,0.077269405],"genre_scores_gemma":[0.65901995,0.00009482821,0.3387782,0.0015665761,0.000047083035,0.00003326493,0.000023333027,0.000013739556,0.0004230359],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990521,0.0000170534,0.00030756704,0.00017504221,0.0001929462,0.0002552734],"domain_scores_gemma":[0.99909997,0.00003151542,0.00010851957,0.00057648367,0.000032345994,0.00015116156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020022619,0.00013179821,0.000133403,0.000087609704,0.00013219481,0.00017566457,0.0005881523,0.00005179878,0.00010589114],"category_scores_gemma":[0.000011695767,0.000108267086,0.000028098797,0.00014477539,0.000058633887,0.001828538,0.00069470255,0.00010901952,0.00017058762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008987086,0.0004216173,0.014979713,0.0003691515,0.000118469885,0.00011398076,0.051775374,0.000003040607,0.00084045477,0.297991,0.036342926,0.5969544],"study_design_scores_gemma":[0.007036255,0.002344778,0.1497464,0.0008699483,0.00009005928,0.0010940296,0.0041673873,0.20334278,0.04267928,0.12798198,0.45676225,0.003884856],"about_ca_topic_score_codex":0.000035468824,"about_ca_topic_score_gemma":0.0000012752096,"teacher_disagreement_score":0.59306955,"about_ca_system_score_codex":0.00002251261,"about_ca_system_score_gemma":0.000026929634,"threshold_uncertainty_score":0.44150037},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66606015,0.00024004358,0.27091354,0.05568148,0.003329624,0.00033769137,0.00017493834,0.000073895266,0.0031886504],"genre_scores_gemma":[0.80605894,0.009717387,0.16688178,0.015375541,0.0010599715,0.0000066271014,0.000014954469,0.000033526045,0.00085123634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943103,0.00015200058,0.0014923856,0.000056052442,0.0037134476,0.0002757786],"domain_scores_gemma":[0.99332225,0.00058501697,0.0050811428,0.00025956187,0.00041772303,0.00033430083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029511075,0.00013676207,0.00049084553,0.00017129698,0.00010959226,0.0000842642,0.001968624,0.000103946055,0.00007773917],"category_scores_gemma":[0.002830394,0.00008992453,0.00014545144,0.00067218,0.00024484345,0.00090866105,0.000695615,0.00062688,0.000008329408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030716972,0.00061284273,0.045203883,0.00007021614,0.0007236702,0.000022945564,0.007748984,0.00014266302,0.000020074875,0.00336577,0.40082347,0.5412348],"study_design_scores_gemma":[0.0010728502,0.0002876463,0.0086362595,0.00021973794,0.00003928233,0.00016715462,0.0018125642,0.95831496,0.00003928994,0.00054064544,0.028682474,0.00018716871],"about_ca_topic_score_codex":0.00005078423,"about_ca_topic_score_gemma":0.000010664222,"teacher_disagreement_score":0.95817226,"about_ca_system_score_codex":0.00029485588,"about_ca_system_score_gemma":0.0002226853,"threshold_uncertainty_score":0.36670157},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005043559,0.0010540272,0.94267714,0.006350622,0.00057059317,0.00020119539,0.000024914529,0.00034225575,0.043735705],"genre_scores_gemma":[0.9650859,0.00008465503,0.025039738,0.0023731326,0.00023773212,0.000019454872,0.000032995475,0.000016907228,0.007109433],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986671,0.000050094,0.00025185503,0.00038595888,0.00035946415,0.00028549146],"domain_scores_gemma":[0.9989503,0.00015049435,0.00007085845,0.0007077091,0.00002919319,0.000091429065],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010970748,0.00015604579,0.00014057376,0.000017325088,0.00031428304,0.0002281912,0.0012091855,0.00007215769,0.0010715784],"category_scores_gemma":[0.000005433844,0.0000863454,0.00006319262,0.00015608447,0.00003449644,0.0006688469,0.00025424754,0.00018756141,0.00015171015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070931706,0.00019223198,0.00016545677,0.000004267099,0.000026698748,0.000007989043,0.0010288532,0.00014186536,0.008853428,0.01619348,0.5377655,0.43561313],"study_design_scores_gemma":[0.0006817939,0.000033064895,0.00081124436,0.000039100254,0.0000071459413,0.0000021034284,0.000026387463,0.81733215,0.0052585304,0.004564217,0.17094716,0.00029711513],"about_ca_topic_score_codex":0.0003961249,"about_ca_topic_score_gemma":0.0000059467025,"teacher_disagreement_score":0.9600424,"about_ca_system_score_codex":0.000014806772,"about_ca_system_score_gemma":0.0000049894775,"threshold_uncertainty_score":0.9998416},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013844765,0.00015223995,0.99152553,0.00069095194,0.0007429624,0.0012620063,0.00010417466,0.0005484232,0.004835249],"genre_scores_gemma":[0.016646262,0.000023276172,0.9791982,0.0025998005,0.0007910732,0.000057840873,0.00014330774,0.00006305823,0.00047715285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99272466,0.00008150384,0.00075426797,0.0033265578,0.0019665712,0.0011464179],"domain_scores_gemma":[0.9936507,0.00012742396,0.0003433699,0.0048932433,0.00031584303,0.00066946243],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014451086,0.00088766706,0.00072048896,0.0009684264,0.0004705658,0.0013899233,0.009635007,0.00038702457,0.000016511121],"category_scores_gemma":[0.000078930665,0.00078411674,0.000113616436,0.0010282772,0.0005029192,0.0026681775,0.00417625,0.001099153,0.00013276139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010741052,0.00017210243,0.000003855912,0.000066872904,0.000007817927,0.00012171344,0.0006484906,0.03523903,0.004394387,0.017101184,0.00018413775,0.9420497],"study_design_scores_gemma":[0.0003026772,0.00019558736,0.000020129562,0.00062401884,0.0000048673787,0.00008177249,3.582006e-7,0.975912,0.002228708,0.00947235,0.010010928,0.0011466013],"about_ca_topic_score_codex":0.000066200606,"about_ca_topic_score_gemma":0.000030609495,"teacher_disagreement_score":0.94090307,"about_ca_system_score_codex":0.0004011313,"about_ca_system_score_gemma":0.0008346057,"threshold_uncertainty_score":0.9996467},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44504127,0.00053701753,0.53397536,0.001100062,0.0064691147,0.0023323619,0.00090338837,0.001277636,0.008363781],"genre_scores_gemma":[0.95325017,0.00010121244,0.04193873,0.00026325407,0.0011005886,0.000025976604,0.00018348382,0.00009511171,0.0030414523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953609,0.00025280166,0.00063478027,0.0016904166,0.00089819974,0.0011628725],"domain_scores_gemma":[0.99576026,0.000561517,0.00057011965,0.0020045703,0.00029665208,0.0008068952],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010571445,0.0007272124,0.00089921267,0.00060887955,0.0019260572,0.00083678606,0.0023664462,0.0005482566,0.00011930873],"category_scores_gemma":[0.00016733348,0.0007671435,0.00041082822,0.0007238728,0.00023308583,0.004134747,0.0013359085,0.0010852965,0.00017014123],"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":[0.0010241542,0.002430937,0.023128321,0.003990512,0.0014987448,0.0011654737,0.009066385,0.00089010823,0.029226994,0.76527566,0.091510706,0.070792],"study_design_scores_gemma":[0.0070691183,0.0005430529,0.027852643,0.0007949163,0.00030639325,0.0003369073,0.0017046067,0.14398311,0.0009927173,0.00090261135,0.8132081,0.0023058227],"about_ca_topic_score_codex":0.0013654776,"about_ca_topic_score_gemma":0.0002618802,"teacher_disagreement_score":0.76437306,"about_ca_system_score_codex":0.00037693285,"about_ca_system_score_gemma":0.00033758965,"threshold_uncertainty_score":0.999478},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018087105,0.00083394063,0.9870506,0.006814055,0.0027200077,0.00054037786,0.000015593907,0.0001821283,0.0018252295],"genre_scores_gemma":[0.055314805,0.0002929367,0.93027186,0.0107895415,0.002315576,0.000035673223,0.000022775404,0.000067259614,0.00088954344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958123,0.000044306722,0.00044560884,0.0016080609,0.0013477551,0.000741948],"domain_scores_gemma":[0.9968727,0.00019404937,0.0002102234,0.0022580188,0.0002209133,0.00024406491],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00067012996,0.0005501079,0.00046012554,0.0005391978,0.0006747192,0.0005764337,0.005702949,0.0003221986,0.000019838328],"category_scores_gemma":[0.000086125576,0.00036543055,0.00014666173,0.0007795236,0.00041382207,0.00057764037,0.003351536,0.00095683493,0.00015364344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048979805,0.000017033673,0.0000033892609,0.000009739288,0.0000071261534,0.00009062181,0.0011551102,0.017650707,0.000048682,0.0047473777,0.0024511681,0.97381413],"study_design_scores_gemma":[0.00034843793,0.0003813514,0.00029500175,0.0004621398,0.000009958133,0.0004848585,2.3119767e-7,0.78283983,0.00093566737,0.043867946,0.1692011,0.0011734834],"about_ca_topic_score_codex":0.00009198055,"about_ca_topic_score_gemma":0.00010789641,"teacher_disagreement_score":0.9726407,"about_ca_system_score_codex":0.00027502773,"about_ca_system_score_gemma":0.0007657772,"threshold_uncertainty_score":0.9998798},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009780835,0.00041704232,0.991482,0.002125331,0.0028163707,0.00047977726,0.00002503075,0.0001398392,0.0024167674],"genre_scores_gemma":[0.017578948,0.00008098136,0.97076946,0.010682331,0.0007342557,0.000017866,0.000008845248,0.00004200368,0.000085323954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99498326,0.000038203674,0.0006055178,0.0019910235,0.0013046297,0.001077344],"domain_scores_gemma":[0.9962978,0.0007108367,0.00044271883,0.0018766097,0.00033164618,0.00034042264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012819447,0.00057988195,0.0005918429,0.0010383733,0.0003493254,0.0009654122,0.0046478184,0.00042625362,0.000018115794],"category_scores_gemma":[0.0004583079,0.0005218153,0.00009090239,0.0010331965,0.0002601995,0.002207505,0.0034623255,0.0018004583,0.000055312135],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004640422,0.00030199872,0.00040819234,0.00009320978,0.000022143158,0.0011890717,0.0028575694,0.0156075675,0.0005666872,0.0824059,0.00032971735,0.8961715],"study_design_scores_gemma":[0.0014439012,0.0005388461,0.0011853572,0.0036058077,0.00002219838,0.00027657702,0.0000056007084,0.36152634,0.0032725015,0.10215001,0.5228331,0.0031397333],"about_ca_topic_score_codex":0.0001292527,"about_ca_topic_score_gemma":0.0017132402,"teacher_disagreement_score":0.8930318,"about_ca_system_score_codex":0.0002845256,"about_ca_system_score_gemma":0.0005099645,"threshold_uncertainty_score":0.9997233},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031124579,0.000013289772,0.9575746,0.0004213923,0.0001850172,0.000055516906,0.000010782786,0.00010086295,0.010513963],"genre_scores_gemma":[0.81600314,0.000005975009,0.18330592,0.00019478842,0.000020333448,0.000001761186,0.0000051673014,0.0000033425713,0.00045954363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994451,0.000010874501,0.000110308596,0.00015462484,0.00017310325,0.000105984305],"domain_scores_gemma":[0.9995194,0.000019100526,0.000035892834,0.00035375994,0.000031584746,0.00004027999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000062741514,0.00005934994,0.00008826454,0.00003148837,0.00004405021,0.000028978166,0.00039685346,0.000013532955,0.00003181637],"category_scores_gemma":[0.0000062097156,0.000043061107,0.00002504893,0.00012593059,0.000058714388,0.00024305741,0.0001340502,0.000044666507,0.000061419574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011260836,0.00019274234,0.00010417495,0.000009804342,0.0000071453383,0.00000637996,0.00045399525,0.000981848,0.0011058397,0.97726643,0.0023468656,0.017513491],"study_design_scores_gemma":[0.002295651,0.0011990644,0.040481664,0.000119509954,0.000004605768,0.000014925176,0.0000654683,0.024957199,0.252301,0.6535855,0.024363687,0.00061172375],"about_ca_topic_score_codex":0.00015709775,"about_ca_topic_score_gemma":0.000025545327,"teacher_disagreement_score":0.7848786,"about_ca_system_score_codex":0.000014667889,"about_ca_system_score_gemma":0.000033606742,"threshold_uncertainty_score":0.17559808},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019578874,0.0007261899,0.98819697,0.0073935576,0.0016008925,0.0010714971,0.000013266285,0.00017159797,0.0008240623],"genre_scores_gemma":[0.0023351773,0.00015106608,0.99358314,0.002447611,0.0009817012,0.000029913384,0.000017569138,0.000035918638,0.0004178794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956445,0.00004467022,0.00058442884,0.0017599787,0.0011832808,0.0007831261],"domain_scores_gemma":[0.9949058,0.001859861,0.00038110733,0.0022921537,0.0003647457,0.00019629352],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015002162,0.00058039854,0.00055797846,0.00035151714,0.00072812475,0.0009560958,0.0038032169,0.0003719168,0.000009664371],"category_scores_gemma":[0.00012103935,0.0003814543,0.00017803964,0.00043300097,0.0005946601,0.0009776907,0.0018411401,0.001060087,0.00002870205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009844927,0.000045667184,0.00000238185,0.000016502916,0.0000072255207,0.00006114338,0.00012825438,0.00566241,0.000025163074,0.019941654,0.00057762983,0.9735221],"study_design_scores_gemma":[0.00027627,0.0003544027,0.00010217465,0.0003105052,0.000015897896,0.00020615889,1.4014856e-7,0.8381378,0.00022116616,0.13233094,0.027528247,0.00051627966],"about_ca_topic_score_codex":0.000029551924,"about_ca_topic_score_gemma":0.00004528861,"teacher_disagreement_score":0.97300583,"about_ca_system_score_codex":0.00019063611,"about_ca_system_score_gemma":0.0005215124,"threshold_uncertainty_score":0.99986374},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062660393,0.000035045752,0.9552984,0.00012925359,0.0006627993,0.00038687626,0.000014020244,0.0007784965,0.036429044],"genre_scores_gemma":[0.2961221,0.0000094271445,0.7020909,0.0015176226,0.00004818085,0.000045774028,0.00005023573,0.000013294628,0.000102448445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984992,0.00004155832,0.0004317111,0.0002178613,0.0004295523,0.00038007274],"domain_scores_gemma":[0.9985622,0.000053823307,0.0001808813,0.00093900965,0.000059075253,0.00020497883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023247422,0.00019616817,0.00018906409,0.00013239481,0.00024114459,0.00021483067,0.001278912,0.000076169184,0.0002801978],"category_scores_gemma":[0.000012431379,0.00015373691,0.000073509436,0.0002586793,0.000042832253,0.0017882143,0.00058629067,0.00016551735,0.0006550656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002755629,0.0037785566,0.013569129,0.0010985091,0.00030116955,0.0001425446,0.035028055,0.00018518888,0.00088257034,0.2831717,0.09996286,0.56160414],"study_design_scores_gemma":[0.0018895017,0.0003714121,0.0064359386,0.00014309154,0.000018760398,0.000022776921,0.00019254592,0.79388416,0.0073210876,0.0029628577,0.1861156,0.00064228225],"about_ca_topic_score_codex":0.000035563855,"about_ca_topic_score_gemma":0.000001263792,"teacher_disagreement_score":0.79369897,"about_ca_system_score_codex":0.000055937046,"about_ca_system_score_gemma":0.00007597244,"threshold_uncertainty_score":0.8419761},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004824268,0.0003790047,0.99262303,0.0010371293,0.00058680604,0.000039942133,0.0000044365997,0.000013471954,0.0004918864],"genre_scores_gemma":[0.7969211,0.00011513465,0.20246638,0.000056505996,0.00039252522,0.000001047055,0.0000015463871,0.000007455174,0.00003835042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985894,0.000120727076,0.00051625195,0.00011301237,0.00046739122,0.00019321196],"domain_scores_gemma":[0.9984915,0.00020496611,0.0006021792,0.00038347126,0.00021977707,0.000098077384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010244052,0.00009225773,0.00020847823,0.000057163357,0.00025398543,0.0001491271,0.0010215574,0.000030164209,0.000005689036],"category_scores_gemma":[0.00011607764,0.000054467484,0.00012249163,0.0001808171,0.00017392523,0.0006286687,0.00026449846,0.00020240725,0.0000030317392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042950905,0.00012125985,0.00096607086,0.000033960197,0.00013821802,0.000020590582,0.00065778976,0.0013630927,0.0019120851,0.37916923,0.0041118637,0.6114629],"study_design_scores_gemma":[0.0015969373,0.00094636163,0.020797564,0.00038375775,0.00004388668,0.00024186348,0.0002469141,0.75556743,0.011518655,0.16152342,0.046750277,0.00038291252],"about_ca_topic_score_codex":0.000018944513,"about_ca_topic_score_gemma":0.000002923019,"teacher_disagreement_score":0.7920968,"about_ca_system_score_codex":0.000018447745,"about_ca_system_score_gemma":0.000045257773,"threshold_uncertainty_score":0.22211196},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063911045,0.00006348079,0.9973261,0.000047315443,0.00051601854,0.00033079236,0.000040145365,0.00013088685,0.0009061526],"genre_scores_gemma":[0.0018195049,0.00000791866,0.99741656,0.0001848759,0.00006239969,0.00002283339,0.000031113515,0.000012659768,0.0004421346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987287,0.00006247392,0.00023627086,0.00042227123,0.0002582902,0.00029199195],"domain_scores_gemma":[0.9991617,0.00007317142,0.000102233425,0.00043421987,0.00012457614,0.00010407794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022717209,0.0001589574,0.00015058338,0.00009478415,0.0002969179,0.00024387227,0.0004149143,0.000057946123,0.00005060768],"category_scores_gemma":[0.000019027124,0.00012776152,0.0000646299,0.00022659064,0.000026052294,0.00113063,0.00018316504,0.000069726935,0.000021452981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047984645,0.00016759898,0.000032521475,0.000020647944,0.000016157726,0.000006644673,0.00024921,0.00020230768,0.07057803,0.010751427,0.004747418,0.91322327],"study_design_scores_gemma":[0.0007861269,0.000052875086,0.00008400774,0.000031772142,0.000006278632,0.000021535016,0.00007999328,0.9316759,0.060086664,0.0017374792,0.005219656,0.0002176959],"about_ca_topic_score_codex":0.00004402101,"about_ca_topic_score_gemma":0.0000015440919,"teacher_disagreement_score":0.9314736,"about_ca_system_score_codex":0.00004604629,"about_ca_system_score_gemma":0.00005818195,"threshold_uncertainty_score":0.5209964},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044494674,0.00004493361,0.9525392,0.00054688327,0.00037400893,0.0006253374,0.000028686049,0.00016770643,0.001178586],"genre_scores_gemma":[0.5428582,0.0000046696687,0.45576644,0.0011848246,0.000069540394,0.000017293205,0.000042923344,0.0000051487514,0.000050979303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983318,0.000025004616,0.00058149,0.00027399446,0.00030068296,0.00048705383],"domain_scores_gemma":[0.99904156,0.00016736383,0.00016347396,0.00046114475,0.000051864576,0.00011457677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036930334,0.00019664198,0.00024099016,0.0001616616,0.00020258315,0.00036632165,0.0008625237,0.00006730699,0.000013157172],"category_scores_gemma":[0.000051013547,0.00016574313,0.0000716581,0.000248187,0.000038760383,0.0020037026,0.0002801082,0.00014027042,0.00005828126],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027534936,0.00017969377,0.001891144,0.000054351032,0.000012309364,0.000011822465,0.0047008153,0.0008093731,0.00028655925,0.0043193377,0.0014560168,0.98625106],"study_design_scores_gemma":[0.0012953626,0.00022970348,0.007494742,0.00009784119,0.0000025053434,0.00001762364,0.00029598636,0.98156136,0.00059506873,0.001179316,0.006972005,0.0002584802],"about_ca_topic_score_codex":0.000035253863,"about_ca_topic_score_gemma":0.000005910141,"teacher_disagreement_score":0.98599255,"about_ca_system_score_codex":0.00008155261,"about_ca_system_score_gemma":0.000043547447,"threshold_uncertainty_score":0.67588085},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000330464,0.0072491355,0.33127987,0.018890757,0.015685955,0.001893246,0.0052496404,0.0011688019,0.6185495],"genre_scores_gemma":[0.000010780564,0.00040777156,0.1253111,0.0010945986,0.0021566127,0.000010227461,0.0020025794,0.00004980083,0.8689565],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99553674,0.0000149307725,0.00060997444,0.0017723929,0.0012819323,0.00078404875],"domain_scores_gemma":[0.9973897,0.00008877339,0.00032896694,0.0015186251,0.00020984252,0.0004641023],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036257232,0.0006668467,0.0005325475,0.00026475728,0.00026070105,0.0010659603,0.0061183795,0.00040251616,0.0019132887],"category_scores_gemma":[0.000033303026,0.00052713905,0.00005453287,0.00010050723,0.00011320943,0.002044002,0.0060872184,0.0007764066,0.000020250198],"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":[0.0000053831104,0.000015653131,0.000008376464,0.000019514073,0.00007568591,0.00003164935,0.000050474362,0.000011496477,0.0000029715961,0.003011073,0.91624546,0.08052226],"study_design_scores_gemma":[0.00032144433,0.000013639496,0.00011298849,0.00013461536,0.000027864735,0.00011694534,0.000023271503,0.06272195,0.000018987637,0.0011483476,0.93470234,0.0006576225],"about_ca_topic_score_codex":0.027495736,"about_ca_topic_score_gemma":0.16343713,"teacher_disagreement_score":0.25040698,"about_ca_system_score_codex":0.0004590364,"about_ca_system_score_gemma":0.0018231465,"threshold_uncertainty_score":0.99997103},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045660962,0.0000059428244,0.98806995,0.00036214475,0.00020191302,0.00011028553,0.0000016226483,0.0002636464,0.010527862],"genre_scores_gemma":[0.47249386,6.3638885e-7,0.5259946,0.001089153,0.000071991875,0.0000031830502,0.000017135388,0.0000062545596,0.0003231914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882746,0.00003637141,0.00017289362,0.00026808598,0.00044514527,0.00025005115],"domain_scores_gemma":[0.9991506,0.00016044066,0.000027792845,0.0004823023,0.00006445113,0.00011441696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056035613,0.000093560695,0.00008578249,0.00011616521,0.0001146189,0.00011866439,0.00044358373,0.000051219064,0.0002237491],"category_scores_gemma":[0.000009811008,0.00007101169,0.000030130623,0.00025401654,0.000032477717,0.00031818592,0.00008553061,0.00010850811,0.0003080104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018736695,0.00006134553,0.000008866842,0.000003334766,0.0000014345828,0.000019328854,0.00003063794,0.00047705596,0.00009348353,0.0088734655,0.0011568266,0.98927236],"study_design_scores_gemma":[0.00028140185,0.00011582917,0.0018619607,0.000016201782,8.256899e-7,0.0000039415327,0.00001967382,0.98735654,0.008209765,0.0002324407,0.0018006564,0.000100741745],"about_ca_topic_score_codex":0.00005851829,"about_ca_topic_score_gemma":0.000003741088,"teacher_disagreement_score":0.9891716,"about_ca_system_score_codex":0.00005000397,"about_ca_system_score_gemma":0.00006042922,"threshold_uncertainty_score":0.39589533},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10630407,0.00005301819,0.8926013,0.00005942444,0.00006257144,0.00008106421,0.00006422528,0.000023229431,0.0007510859],"genre_scores_gemma":[0.68951184,0.0000075785224,0.31035513,0.00004402448,0.000012692748,9.879637e-7,0.000031323885,0.0000019157146,0.00003454725],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925524,0.00003535922,0.00024807017,0.00017851131,0.00018178247,0.00010104593],"domain_scores_gemma":[0.9994126,0.000035258246,0.00012081073,0.00027927794,0.000114429175,0.000037602276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010031335,0.00007153068,0.00012857765,0.000033040866,0.00006105837,0.000036890164,0.000236159,0.000037827165,0.000049875052],"category_scores_gemma":[0.000014582982,0.000059060152,0.00002514019,0.00017735416,0.000028089393,0.00044805268,0.000069972506,0.00003299675,0.0000018633737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010035107,0.000617965,0.0012487578,0.000034129887,0.000028717133,0.0000040186696,0.0012438294,0.0048590098,0.65710175,0.2945084,0.007431209,0.03291217],"study_design_scores_gemma":[0.00029738134,0.000031586176,0.0004925128,0.000035000237,0.000007692389,0.000007601261,0.000027412818,0.9609395,0.035855226,0.002054594,0.00015161686,0.00009982904],"about_ca_topic_score_codex":0.00015919443,"about_ca_topic_score_gemma":0.000004435076,"teacher_disagreement_score":0.95608056,"about_ca_system_score_codex":0.000012445817,"about_ca_system_score_gemma":0.00006348364,"threshold_uncertainty_score":0.2408403},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028947974,0.00016989151,0.9949707,0.00048281506,0.0013412214,0.00058072177,0.000010388882,0.00027154703,0.001883265],"genre_scores_gemma":[0.043231785,0.0000153605,0.95498914,0.0007374717,0.00059246604,0.000013629157,0.000009991299,0.000047093235,0.00036306237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954063,0.000032254586,0.00051864545,0.002131396,0.001097279,0.00081406604],"domain_scores_gemma":[0.9961977,0.00028828243,0.00038798136,0.0025277766,0.0003327306,0.00026555324],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084744603,0.0006729778,0.0006085041,0.00052311626,0.00044580307,0.0010306295,0.0042269947,0.00043009516,0.000020229729],"category_scores_gemma":[0.00006700556,0.0004987305,0.00010429862,0.00047607362,0.00092526374,0.0012572514,0.0026089398,0.0015877156,0.000020807998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019136827,0.000057111894,0.00007342185,0.000074882955,0.000014280569,0.00016423354,0.00043412475,0.001325863,0.0045947563,0.010133321,0.00001090958,0.983098],"study_design_scores_gemma":[0.00072113064,0.0005870665,0.0003105656,0.0008250072,0.00001749227,0.00032839514,2.1150305e-7,0.9165761,0.018109675,0.05620853,0.0045960075,0.001719814],"about_ca_topic_score_codex":0.000086117914,"about_ca_topic_score_gemma":0.00019468908,"teacher_disagreement_score":0.98137814,"about_ca_system_score_codex":0.00018440887,"about_ca_system_score_gemma":0.0009560122,"threshold_uncertainty_score":0.99974644},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014027202,0.00003271391,0.9950536,0.00038702306,0.0040250616,0.0002227297,0.000008808979,0.000030863015,0.00009890978],"genre_scores_gemma":[0.07654569,0.000042971595,0.92247856,0.00022498544,0.0006353862,0.000011581403,0.000016102238,0.000014606615,0.000030144052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998521,0.000072779505,0.00046426922,0.00019990363,0.00054257584,0.00019951501],"domain_scores_gemma":[0.9983023,0.00030360898,0.00048038765,0.00030082557,0.00047904684,0.00013386461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004891121,0.00014375028,0.00022994286,0.00016722243,0.00015156993,0.00015768658,0.0005823006,0.00007839459,0.000013087776],"category_scores_gemma":[0.0002146006,0.00012073571,0.00011055705,0.00027394653,0.000019244286,0.0005319809,0.000060545808,0.00013025351,0.0000016753759],"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":[0.00015862714,0.0005323441,0.0000703449,0.000007606854,0.00002103187,0.00005367569,0.000059215366,0.93830913,0.00010640324,0.003414142,0.0025376487,0.054729853],"study_design_scores_gemma":[0.002964981,0.00088239746,0.00001561655,0.000074024116,0.000014741114,0.000031755255,0.000004378799,0.9870966,0.00046080112,0.002995417,0.0053231614,0.00013614226],"about_ca_topic_score_codex":0.000004466061,"about_ca_topic_score_gemma":4.9553563e-8,"teacher_disagreement_score":0.07640542,"about_ca_system_score_codex":0.0001283772,"about_ca_system_score_gemma":0.00015153398,"threshold_uncertainty_score":0.49234596},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007824348,0.00012017246,0.98987603,0.0010186128,0.0004456395,0.00023149824,0.000049677667,0.00028344552,0.000150561],"genre_scores_gemma":[0.020083511,0.000028981985,0.9782792,0.0012192603,0.00020474955,0.000074215626,0.00003588237,0.000008915837,0.00006530044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986022,0.000013703567,0.00024128672,0.00055878394,0.00020153448,0.00038249945],"domain_scores_gemma":[0.9992103,0.00003735854,0.00007666599,0.00048101073,0.00007081699,0.00012387741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015815158,0.00018441376,0.0001914109,0.000058820744,0.00017277876,0.00017847453,0.0010415987,0.0000963522,0.000021544363],"category_scores_gemma":[0.0000056331746,0.00012318119,0.00009124522,0.00027275956,0.000053158223,0.0004027298,0.00043059347,0.00005669073,0.000051153598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020068776,0.00024063484,0.00007049622,0.000008912722,0.000022343043,0.000021710173,0.0002063388,0.0001855698,0.02032347,0.010582364,0.0011089691,0.96722716],"study_design_scores_gemma":[0.0042244717,0.0011730645,0.0027497916,0.000075476855,0.000013972442,0.00048983074,0.00024774144,0.82186586,0.0393888,0.06454998,0.0634219,0.001799107],"about_ca_topic_score_codex":0.00021988348,"about_ca_topic_score_gemma":0.0000063980237,"teacher_disagreement_score":0.96542805,"about_ca_system_score_codex":0.00004305923,"about_ca_system_score_gemma":0.00006998124,"threshold_uncertainty_score":0.5023183},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037221433,0.0006451071,0.99578047,0.00026803013,0.0015946637,0.00034159017,0.000010514814,0.00023221665,0.00075519265],"genre_scores_gemma":[0.13271028,0.00003642188,0.86454225,0.0016575572,0.00087041775,0.000006017082,0.000017653805,0.00005604568,0.00010334497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958605,0.000037958358,0.000516823,0.0016903457,0.0011493313,0.0007449984],"domain_scores_gemma":[0.9972627,0.00023278981,0.00027032322,0.001819166,0.00016143595,0.00025355766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005765342,0.000578768,0.00056650524,0.000938831,0.00033044972,0.00065186544,0.0036180087,0.0004239005,0.0000318525],"category_scores_gemma":[0.00005552601,0.0004983069,0.00016920098,0.0008562024,0.00062939577,0.0009574498,0.0022956778,0.0010278935,0.000029709812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014021391,0.00010242138,0.00008681001,0.00008258966,0.00002393282,0.0013974418,0.0017796166,0.0760348,0.0022369935,0.060081933,0.000022713666,0.8581367],"study_design_scores_gemma":[0.00051636016,0.00014134627,0.0002037674,0.0009721621,0.000012108125,0.00032180865,3.0184472e-7,0.8412332,0.0010557413,0.15399292,0.000551361,0.0009989048],"about_ca_topic_score_codex":0.00014043837,"about_ca_topic_score_gemma":0.00004295719,"teacher_disagreement_score":0.8571378,"about_ca_system_score_codex":0.00032938243,"about_ca_system_score_gemma":0.00085955724,"threshold_uncertainty_score":0.99974686},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020623358,0.00015907502,0.9932916,0.00038594002,0.0019406307,0.00056982413,0.000063197374,0.00015645583,0.0034126204],"genre_scores_gemma":[0.054016404,0.000011727623,0.94205314,0.0010246247,0.0011566642,0.00004022873,0.00004818498,0.00005660223,0.0015924497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996494,0.00003222629,0.00045529922,0.0015754903,0.0007427187,0.00070028],"domain_scores_gemma":[0.99749815,0.0006013678,0.00023192966,0.0012483636,0.00026409616,0.0001560689],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063279533,0.0004845885,0.00043824335,0.00080979685,0.00048452677,0.0007137996,0.0029331974,0.00025325437,0.000014884052],"category_scores_gemma":[0.00004306229,0.00042063324,0.00017803123,0.00039695023,0.00043952442,0.00097192934,0.0020089466,0.00077364047,0.000034790504],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015336589,0.000037112513,0.000013616719,0.000036314894,0.00001731965,0.000040235027,0.00094719173,0.04092916,0.00010914011,0.017886955,0.0011868303,0.9387808],"study_design_scores_gemma":[0.00028129722,0.00025404658,0.000054672644,0.00037445326,0.0000066547123,0.00005271241,4.7634325e-7,0.8983258,0.00034042582,0.091387056,0.008366094,0.00055633223],"about_ca_topic_score_codex":0.00009072119,"about_ca_topic_score_gemma":0.00012975589,"teacher_disagreement_score":0.93822443,"about_ca_system_score_codex":0.0002757264,"about_ca_system_score_gemma":0.0003536215,"threshold_uncertainty_score":0.9998245},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091031596,0.0005806258,0.89332664,0.0018820796,0.0008201807,0.001308141,0.00020508777,0.0007199151,0.010125748],"genre_scores_gemma":[0.95806575,0.00006059344,0.039092194,0.00021045672,0.00028068724,0.0000031828406,0.0000620029,0.00001990146,0.002205235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979315,0.00012979704,0.00021384512,0.0007567561,0.0004138904,0.00055425876],"domain_scores_gemma":[0.9983818,0.0001771236,0.00007823512,0.00082233135,0.000200225,0.0003403098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005611267,0.0002526268,0.00035415616,0.00027736527,0.00058077223,0.00029306152,0.0012215391,0.00015173675,0.000008483179],"category_scores_gemma":[0.000024572157,0.00025625734,0.0001218107,0.0004375909,0.000062596264,0.0013508669,0.00047694583,0.00019448978,0.000038951563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043523507,0.00047698375,0.002716007,0.000987086,0.0001533232,0.00065591367,0.0037907828,0.0002641956,0.004541544,0.84164953,0.03663819,0.10769122],"study_design_scores_gemma":[0.01058465,0.0021204378,0.034345992,0.0013023532,0.00017614523,0.0005567485,0.0044153268,0.3347321,0.0065144766,0.0015946913,0.60093504,0.0027220245],"about_ca_topic_score_codex":0.00014217287,"about_ca_topic_score_gemma":0.0000081138205,"teacher_disagreement_score":0.86703414,"about_ca_system_score_codex":0.00021884828,"about_ca_system_score_gemma":0.00012576113,"threshold_uncertainty_score":0.999989},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79092914,0.000088509856,0.20490156,0.00017229236,0.0006834338,0.00039029508,0.00003056904,0.00016454769,0.002639687],"genre_scores_gemma":[0.9969305,0.00014598864,0.0011055489,0.000046848356,0.000034267727,9.3179904e-7,0.000025543835,0.000011831483,0.001698551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827486,0.00017797104,0.00021981914,0.000892291,0.0001555022,0.00027956298],"domain_scores_gemma":[0.9966378,0.00021309641,0.0003646277,0.0024720528,0.00018248662,0.00012994168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017251004,0.0002728164,0.00031157536,0.00015499593,0.00016132089,0.000115852,0.0033382468,0.00021888342,0.00009111433],"category_scores_gemma":[0.00005991651,0.00020465552,0.00021120277,0.00045148222,0.00014695639,0.00046139915,0.0054594367,0.00055089226,0.00009458101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000170996,0.0012318706,0.031255677,0.0004612766,0.0013052605,0.0008815365,0.007288702,0.17285904,0.0005651906,0.721364,0.028989123,0.033627283],"study_design_scores_gemma":[0.00056171516,0.00008624998,0.014571676,0.00024963918,0.00008503514,0.000007647473,0.00037536424,0.8875941,0.00095118635,0.08780047,0.0070034703,0.00071346277],"about_ca_topic_score_codex":0.0017334216,"about_ca_topic_score_gemma":0.00001521745,"teacher_disagreement_score":0.71473503,"about_ca_system_score_codex":0.000059249905,"about_ca_system_score_gemma":0.00014106712,"threshold_uncertainty_score":0.834561},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025303254,0.000052859228,0.64457244,0.000005316514,0.00044663026,0.00014749239,0.0000051238358,0.00038144382,0.35436338],"genre_scores_gemma":[0.0041128327,0.000013286573,0.06369202,0.00024093984,0.00035236333,0.000018788185,0.000006266735,0.0002101101,0.9313534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991361,0.000036913392,0.0001123164,0.00040490698,0.00015753422,0.00015225337],"domain_scores_gemma":[0.99884486,0.000014269102,0.000083128616,0.0009835735,0.000008787633,0.0000653574],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000785792,0.00016808945,0.0001639643,0.00011131515,0.000047669324,0.00010745005,0.0007995584,0.000082987404,0.0024782908],"category_scores_gemma":[0.0000012267692,0.000121707315,0.000031374155,0.00006482056,0.0000075668218,0.000119607714,0.0008597275,0.0001252721,0.00065340236],"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":[1.6493068e-7,0.00014872874,0.00006371727,0.000012001752,0.00002786071,0.010851336,0.0007775629,1.1986643e-7,3.1649793e-7,0.00043753185,0.6669657,0.32071495],"study_design_scores_gemma":[0.00060960854,0.00019473593,0.000040516385,0.00016402913,0.000025868707,0.0047785444,0.00060888485,0.0033057886,0.000005790186,0.00080701546,0.98847646,0.0009827684],"about_ca_topic_score_codex":0.017604113,"about_ca_topic_score_gemma":0.00089972175,"teacher_disagreement_score":0.5808804,"about_ca_system_score_codex":0.000006452051,"about_ca_system_score_gemma":0.000016838532,"threshold_uncertainty_score":0.9984336},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014131663,0.0005905161,0.9907998,0.00022133965,0.0019911544,0.000847581,0.000027821916,0.00015969566,0.0052207657],"genre_scores_gemma":[0.5286228,0.000041129926,0.46747667,0.0011842328,0.00059149385,0.000034450404,0.00004688898,0.00008917443,0.0019131202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940863,0.000059176,0.00082429266,0.0024939482,0.0014673377,0.001068896],"domain_scores_gemma":[0.996783,0.00024823952,0.00032132753,0.0021615787,0.00022851968,0.000257338],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001180494,0.00069578027,0.0008015529,0.0014569646,0.00020255802,0.0009266658,0.0052459864,0.0003153821,0.0000029532898],"category_scores_gemma":[0.000078745834,0.00060623453,0.00011493457,0.0011385223,0.0003745326,0.00078593055,0.0027624108,0.0011428951,0.00004992909],"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":[0.000038589715,0.0001635726,0.00010205706,0.000148378,0.000010536006,0.0004319422,0.0004124326,0.6642567,0.000111093505,0.015053013,0.0007850064,0.31848666],"study_design_scores_gemma":[0.00033751386,0.00010283559,0.00045157704,0.0007560715,0.000002505591,0.0001811258,1.9919369e-7,0.978368,0.000045956756,0.01597204,0.0030243087,0.00075786],"about_ca_topic_score_codex":0.00024794458,"about_ca_topic_score_gemma":0.00004431964,"teacher_disagreement_score":0.52848154,"about_ca_system_score_codex":0.00079565006,"about_ca_system_score_gemma":0.0005244081,"threshold_uncertainty_score":0.9996389},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000930167,0.0006873874,0.99368936,0.00026893063,0.0016251531,0.00069260696,0.000007759093,0.00051417603,0.0024216324],"genre_scores_gemma":[0.02353362,0.00006441783,0.9745207,0.0006880403,0.0008387659,0.0000055332503,0.000029791667,0.000048262955,0.00027086775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99425054,0.00005907418,0.00077938987,0.0022332896,0.0016620309,0.0010156834],"domain_scores_gemma":[0.99641746,0.00019698282,0.00050683605,0.0022023078,0.0003248027,0.00035162125],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007398155,0.0008387938,0.0007881005,0.0008011421,0.00054559315,0.001116524,0.0048842817,0.00053742697,0.000029505349],"category_scores_gemma":[0.000025385136,0.00068950903,0.00018852393,0.000808029,0.00042133871,0.0012950588,0.0023724127,0.0011895075,0.000036595895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062382856,0.00011399321,0.000012552802,0.0000374876,0.000009764903,0.00013364127,0.00025432126,0.012339227,0.00029356673,0.0042124405,0.000017231438,0.9825695],"study_design_scores_gemma":[0.00042081042,0.0003221462,0.00005542755,0.0009367542,0.00001353052,0.00014362158,9.9456045e-8,0.94594556,0.0009807881,0.0433154,0.006973914,0.0008919352],"about_ca_topic_score_codex":0.000025028765,"about_ca_topic_score_gemma":0.000020211393,"teacher_disagreement_score":0.9816776,"about_ca_system_score_codex":0.0003702059,"about_ca_system_score_gemma":0.00065974495,"threshold_uncertainty_score":0.9999204},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57219595,0.0020891395,0.41836622,0.00049669313,0.0041491166,0.0008916506,0.00047419596,0.00014400942,0.0011930201],"genre_scores_gemma":[0.9647361,0.00024222519,0.033399615,0.00016999213,0.00038882435,0.00005880515,0.000113238064,0.00005139769,0.00083976804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729615,0.00023456267,0.00068412133,0.00079810317,0.0006515408,0.0003355218],"domain_scores_gemma":[0.99576074,0.00020870838,0.00076320523,0.002897627,0.000267983,0.000101714744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026155362,0.00038929097,0.000682594,0.000100232806,0.00014051776,0.00004850278,0.0035701874,0.00031770213,0.0000618867],"category_scores_gemma":[0.00007735329,0.00026019203,0.00032796426,0.0003438003,0.00029731123,0.00025845756,0.0055991383,0.00065465784,0.000025475518],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020257689,0.0032925175,0.11124538,0.00082479743,0.0013017931,0.00017571876,0.018531831,0.004397973,0.009803379,0.0041619735,0.034529857,0.8115322],"study_design_scores_gemma":[0.0023688911,0.0002322782,0.33052143,0.0030235925,0.00017950816,0.000085585474,0.0001880777,0.39729866,0.2365811,0.016608136,0.010890598,0.0020221407],"about_ca_topic_score_codex":0.00084005506,"about_ca_topic_score_gemma":0.0000050461726,"teacher_disagreement_score":0.80951005,"about_ca_system_score_codex":0.000050433548,"about_ca_system_score_gemma":0.0003609789,"threshold_uncertainty_score":0.99998504},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0123364385,0.00025483657,0.9840352,0.0017766375,0.0012686971,0.00013375233,0.0000010786938,0.00012430311,0.00006906937],"genre_scores_gemma":[0.6326372,0.000034470504,0.36656213,0.00063477125,0.00012121543,0.000004702133,5.473283e-7,0.0000033821452,0.0000016093226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784786,0.00006480985,0.00025042385,0.0006577129,0.00062542903,0.0005537687],"domain_scores_gemma":[0.9980636,0.0005268429,0.00007934086,0.0010809395,0.000122639,0.00012661621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006343123,0.00016670262,0.00014487626,0.00014411619,0.0010820666,0.00036730518,0.0030857418,0.000053453205,0.0000042432616],"category_scores_gemma":[0.00009080609,0.00010209274,0.000043991597,0.0015297992,0.001037239,0.0006956969,0.0011238551,0.00028535235,0.000028272636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027636997,0.000036351717,0.0007466326,0.0000017722706,0.0000021952985,0.00008236193,0.00068062096,0.0027793562,0.0005566303,0.004075577,0.000103593906,0.99093217],"study_design_scores_gemma":[0.00021099935,0.00006266586,0.004492482,0.000022485538,5.5387045e-7,0.00025646592,4.058117e-7,0.9705986,0.0053181634,0.017163407,0.0016825995,0.00019120656],"about_ca_topic_score_codex":0.00003566128,"about_ca_topic_score_gemma":0.000016276836,"teacher_disagreement_score":0.99074095,"about_ca_system_score_codex":0.000067781184,"about_ca_system_score_gemma":0.00032145635,"threshold_uncertainty_score":0.83224905},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006279471,0.00038503186,0.99732685,0.00013377085,0.0007893601,0.00024290285,0.000013551991,0.00020323967,0.0002773468],"genre_scores_gemma":[0.155161,0.00001418923,0.8437882,0.00032515463,0.0004162925,0.0000041737258,0.000027907296,0.000024420679,0.00023867053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996441,0.000044302116,0.00062439713,0.0014336132,0.00097124104,0.00048544593],"domain_scores_gemma":[0.99705666,0.00022126462,0.0004644169,0.001948518,0.00016574837,0.00014340594],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008419956,0.00041841433,0.00053506036,0.0015345762,0.00028975093,0.00081847317,0.003022259,0.0002376882,0.000067682675],"category_scores_gemma":[0.000057765494,0.0003716098,0.00018975894,0.0014319504,0.00024692112,0.0010778126,0.001413755,0.00047012907,0.00005423478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.198427e-7,0.000025370879,0.000025295787,0.00001683952,0.00004790314,0.00003404442,0.00088892796,0.097519636,0.0007895073,0.002089934,0.000004214467,0.8985576],"study_design_scores_gemma":[0.00012306173,0.000018057306,0.0006272096,0.00013163181,0.00006490544,0.000018132774,1.8822833e-7,0.99104565,0.0006129277,0.006785988,0.00014536224,0.00042686934],"about_ca_topic_score_codex":0.00012381173,"about_ca_topic_score_gemma":0.00006773393,"teacher_disagreement_score":0.8981307,"about_ca_system_score_codex":0.00032556805,"about_ca_system_score_gemma":0.00026443254,"threshold_uncertainty_score":0.9998736},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012438119,0.00013321875,0.9947017,0.00044560715,0.0021478601,0.00042728154,0.00003902338,0.00023885391,0.0017420794],"genre_scores_gemma":[0.039126467,0.0000067085184,0.9583722,0.0018560512,0.00050175557,0.00001779438,0.00004442517,0.000023215902,0.000051398154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947619,0.00004462792,0.0005270281,0.0024701343,0.001369315,0.0008269971],"domain_scores_gemma":[0.9960431,0.00023731145,0.0002608055,0.0026784637,0.00029409988,0.0004862375],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010665822,0.00064478046,0.00054712076,0.0010168822,0.00045470093,0.0010013892,0.0073338496,0.0003666453,0.000026121861],"category_scores_gemma":[0.000077472876,0.0005479941,0.00010498935,0.000921888,0.0005674799,0.0012840163,0.0015207877,0.0011751949,0.000042590855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071010672,0.00011475039,0.00005596465,0.00004626502,0.000004870387,0.000058528447,0.00072867057,0.096966125,0.002002838,0.0068562496,0.000058688034,0.89309996],"study_design_scores_gemma":[0.00016994242,0.00021730746,0.00006358914,0.0002447431,0.0000049250934,0.000041083797,2.0698354e-7,0.97426826,0.0024635002,0.016599905,0.0050463015,0.0008802193],"about_ca_topic_score_codex":0.000064723834,"about_ca_topic_score_gemma":0.000048178026,"teacher_disagreement_score":0.8922197,"about_ca_system_score_codex":0.00012952111,"about_ca_system_score_gemma":0.00072237465,"threshold_uncertainty_score":0.99969715},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29436505,0.008873111,0.36508423,0.0027693508,0.006794699,0.0052887728,0.00029358815,0.0040356913,0.3124955],"genre_scores_gemma":[0.7676712,0.0013711203,0.04955656,0.00005480673,0.0015366817,0.00004457183,0.00013796377,0.00016243155,0.17946465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923873,0.0011134523,0.0004172791,0.0021302546,0.0025766834,0.0013750123],"domain_scores_gemma":[0.99372977,0.00037450655,0.00028270652,0.003639753,0.0013555171,0.00061774004],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007954254,0.00063362095,0.00067046995,0.0018065363,0.0017835365,0.0018271029,0.005892863,0.00059264957,0.000056120967],"category_scores_gemma":[0.00006177692,0.00060611794,0.00024234854,0.0016095197,0.00067558413,0.001499077,0.009846661,0.0030732672,0.000032310185],"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":[0.0013276673,0.0030128474,0.009712276,0.005646626,0.0025751817,0.09441069,0.013516042,0.014600186,0.011434311,0.6160459,0.15952228,0.068196],"study_design_scores_gemma":[0.0039480804,0.0018571517,0.0029475386,0.0050092754,0.00017815143,0.00086522626,0.004433476,0.09124256,0.026936175,0.0057516806,0.8521602,0.004670466],"about_ca_topic_score_codex":0.0028670984,"about_ca_topic_score_gemma":0.00011535528,"teacher_disagreement_score":0.6926379,"about_ca_system_score_codex":0.00097457645,"about_ca_system_score_gemma":0.0009779728,"threshold_uncertainty_score":0.99963903},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003429129,0.0011702422,0.99283236,0.0011461171,0.0013643303,0.00028700454,0.000025225152,0.0002110259,0.0029293941],"genre_scores_gemma":[0.01803179,0.00010459005,0.97704226,0.0024785933,0.00082992396,0.000016224101,0.00005661347,0.000046794416,0.0013931871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996173,0.000034153436,0.00052893744,0.0015540865,0.0010764785,0.0006333438],"domain_scores_gemma":[0.9974622,0.00028923052,0.00028803298,0.0015496465,0.00020431001,0.00020655715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005892234,0.0005006272,0.00042428044,0.0004977263,0.0005056505,0.00090978073,0.003798092,0.00029935053,0.000039895705],"category_scores_gemma":[0.000055525285,0.0004536657,0.00009961015,0.00046261694,0.00036926608,0.0011882049,0.002118342,0.00078788033,0.00006963837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010029598,0.000058962683,0.0000073615624,0.000013282556,0.000006414028,0.000021409865,0.00028322364,0.019480443,0.00030756355,0.021246592,0.0008705557,0.9577032],"study_design_scores_gemma":[0.00029027514,0.00009564328,0.00002093678,0.00024021126,0.00000461596,0.00002615073,5.273639e-8,0.93521756,0.00067055464,0.045929253,0.016878325,0.000626405],"about_ca_topic_score_codex":0.000021899035,"about_ca_topic_score_gemma":0.000029702796,"teacher_disagreement_score":0.9570768,"about_ca_system_score_codex":0.00025955547,"about_ca_system_score_gemma":0.0003713857,"threshold_uncertainty_score":0.9997915},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21260759,0.015329824,0.7705014,0.00053759495,0.00079618994,0.0001080744,0.0000010202741,0.000024043165,0.000094293035],"genre_scores_gemma":[0.9960575,0.00010967165,0.0033139153,0.000083738305,0.00033546178,0.0000033974252,7.912885e-7,0.00000963824,0.000085886786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874586,0.000081809696,0.00025784457,0.000082413644,0.00030163044,0.0005304416],"domain_scores_gemma":[0.99896204,0.00022046594,0.00028807527,0.00029237865,0.00015830397,0.000078757315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015025631,0.00010150915,0.00015414122,0.00006384004,0.00024555967,0.000073750634,0.00088565145,0.000035696597,0.000002357549],"category_scores_gemma":[0.00007075849,0.000061450184,0.00008736261,0.00023344003,0.00001950082,0.00024587446,0.0001697996,0.00028253288,0.0000035773592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017591847,0.00025454164,0.00010513508,0.000011387558,0.000041365834,0.0000027853148,0.0006592278,0.0027089904,0.002985238,0.98147786,0.0025496688,0.009186201],"study_design_scores_gemma":[0.0037492292,0.0028112135,0.0010929841,0.00015650415,0.00015541396,0.0010216344,0.0009552531,0.66307557,0.023270233,0.23020796,0.072643876,0.00086010183],"about_ca_topic_score_codex":0.0000029799185,"about_ca_topic_score_gemma":2.2528474e-7,"teacher_disagreement_score":0.7834499,"about_ca_system_score_codex":0.00012197568,"about_ca_system_score_gemma":0.00017783708,"threshold_uncertainty_score":0.25058657},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016736263,0.011192384,0.9623782,0.005180054,0.0037723295,0.00019244266,0.0000012378538,0.0000403854,0.00050668116],"genre_scores_gemma":[0.9970549,0.0017410368,0.00026252615,0.00032206852,0.00048023777,0.0000038005362,0.0000014943906,0.00001903435,0.00011491665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971681,0.0003923697,0.0006302805,0.00023264141,0.00094567135,0.0006308963],"domain_scores_gemma":[0.99618936,0.00051675685,0.0014065137,0.001371177,0.00044589513,0.00007030139],"candidate_categories":["open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0041930103,0.00026263457,0.00040706317,0.00008861715,0.0003758587,0.00044261862,0.00614367,0.00014896053,0.0000040553127],"category_scores_gemma":[0.00014304604,0.0001300039,0.00025172203,0.00027779397,0.0000780159,0.0002194402,0.002080672,0.0030975014,0.000009346542],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011259213,0.00006572173,0.000037403737,0.000024978941,0.00013520407,0.000009173874,0.0004696553,0.001753311,0.000020334748,0.9824993,0.0076945797,0.0072790678],"study_design_scores_gemma":[0.00030331686,0.00018396918,0.00013331567,0.00011672162,0.00005797229,0.00018236728,0.00003287205,0.038405944,0.00012025705,0.90562403,0.054647513,0.00019169653],"about_ca_topic_score_codex":0.000018763973,"about_ca_topic_score_gemma":0.0000016677046,"teacher_disagreement_score":0.9803186,"about_ca_system_score_codex":0.00028534688,"about_ca_system_score_gemma":0.0010435311,"threshold_uncertainty_score":0.99923354},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010918882,0.0006827164,0.99476457,0.0001860679,0.0026319618,0.0005133815,0.000023091037,0.00019554899,0.0009917425],"genre_scores_gemma":[0.0036224802,0.00006033777,0.9949376,0.0002276251,0.000063100786,0.00011645421,0.000027689324,0.0000064062015,0.00093833264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880177,0.00007896269,0.000432755,0.0001564635,0.00024173722,0.00028833898],"domain_scores_gemma":[0.9989147,0.00007649709,0.00015149215,0.0004954735,0.00025390522,0.00010793698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073840254,0.00011786429,0.00017659117,0.00017385479,0.00018021672,0.00041551003,0.0007121586,0.00007069904,0.000007383395],"category_scores_gemma":[0.000102830934,0.00009714259,0.00006799047,0.0002373811,0.000024305142,0.0029587422,0.00015398413,0.00008956532,0.0001366774],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040924074,0.000010470942,0.000046622186,0.0000758488,0.000016566582,3.3632097e-7,0.0018054093,0.0013656173,0.00000435972,0.008493645,0.22189713,0.7662799],"study_design_scores_gemma":[0.00013780396,0.000022038566,0.000013569734,0.00002340979,0.0000012836223,0.000007070577,0.00025228926,0.53932977,0.000086419466,0.00011239956,0.45993015,0.000083776176],"about_ca_topic_score_codex":0.0000276948,"about_ca_topic_score_gemma":1.06958936e-7,"teacher_disagreement_score":0.76619613,"about_ca_system_score_codex":0.000105286395,"about_ca_system_score_gemma":0.000022341492,"threshold_uncertainty_score":0.4006773},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068996835,0.01705662,0.9762102,0.000047941467,0.0004955385,0.00058528,0.000017449687,0.00026618424,0.0046308157],"genre_scores_gemma":[0.021323543,0.0010608552,0.9751805,0.00025584502,0.00048166802,0.000016533133,0.00007557141,0.00010953034,0.0014959336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972574,0.00002390832,0.00062851224,0.001110104,0.00039245083,0.0005876295],"domain_scores_gemma":[0.99786776,0.000707345,0.0005448752,0.0006656916,0.00009524403,0.00011907687],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004784004,0.00049980904,0.00066908094,0.00022449614,0.00062444975,0.00029984963,0.00092476915,0.00022533388,0.0000037927114],"category_scores_gemma":[0.000050674797,0.0005328229,0.00011796074,0.00009382724,0.00014339533,0.00096901617,0.00080180605,0.0005941798,0.0000042536476],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038429775,0.000033719458,0.00018909106,0.0006231473,0.000024807941,0.00006619941,0.0010139762,0.01028171,0.00006318763,0.027606186,0.00010096344,0.9599586],"study_design_scores_gemma":[0.0017382833,0.00010642039,0.00003495069,0.0032859952,0.000012319845,0.00006784764,0.00002218866,0.8464937,0.00006740695,0.04823705,0.098944165,0.0009896593],"about_ca_topic_score_codex":0.000017459794,"about_ca_topic_score_gemma":0.000013184268,"teacher_disagreement_score":0.95896894,"about_ca_system_score_codex":0.000086490094,"about_ca_system_score_gemma":0.00014545186,"threshold_uncertainty_score":0.99971235},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04395557,0.00015704858,0.89576983,0.000367333,0.0004152202,0.00018999734,0.0000024208186,0.00027793605,0.05886463],"genre_scores_gemma":[0.7361744,0.0000045973334,0.2624372,0.00022000443,0.000039969764,0.000009116347,0.000015593117,0.0000068866652,0.0010922478],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989067,0.00003979864,0.00023427958,0.00032319786,0.00024790317,0.00024814927],"domain_scores_gemma":[0.99945337,0.000034833418,0.000046573336,0.00039015303,0.000028336251,0.000046734724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011638545,0.00011818539,0.00012621978,0.00010494892,0.000066379405,0.00010124471,0.0006898459,0.000050629737,0.000055901684],"category_scores_gemma":[0.0000027040205,0.00009074311,0.000022475,0.00026795792,0.000017470726,0.00048569005,0.00051288307,0.000092866176,0.00015297128],"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":[0.000036635305,0.0014775958,0.09036711,0.000041257063,0.000018469294,0.00021700637,0.0009004639,0.0025195456,0.017763708,0.25771317,0.06760042,0.5613446],"study_design_scores_gemma":[0.0023459685,0.00005546568,0.5238267,0.00017880078,0.0000020967045,0.000027536795,0.000044964996,0.28713378,0.009557675,0.02294131,0.15304412,0.0008415345],"about_ca_topic_score_codex":0.00048444138,"about_ca_topic_score_gemma":0.00007247503,"teacher_disagreement_score":0.6922188,"about_ca_system_score_codex":0.000031833715,"about_ca_system_score_gemma":0.000029939922,"threshold_uncertainty_score":0.37003967},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013455725,0.0007367193,0.9961525,0.00015902234,0.0010894526,0.00070874626,0.00014457566,0.00014289544,0.0008526127],"genre_scores_gemma":[0.0034727643,0.00005979905,0.99432886,0.0005003652,0.00052037026,0.0000073659185,0.00013429848,0.000055020522,0.00092115137],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950669,0.00003309861,0.00067964516,0.0022295793,0.0012578411,0.0007329262],"domain_scores_gemma":[0.99450946,0.0011286103,0.00050728995,0.0033489906,0.00026314263,0.00024249003],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008303965,0.0006434725,0.0008212534,0.0007229036,0.00037030195,0.0003036626,0.007005576,0.0003772869,0.000029140343],"category_scores_gemma":[0.00012702313,0.000543726,0.00013376649,0.0004909959,0.00046636676,0.0012713968,0.0051753456,0.00069815404,0.000029070352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003918727,0.00006141847,0.0000020057498,0.000039022092,0.000015526895,0.000013979227,0.00047125138,0.13112065,0.00023414004,0.0114224665,0.0004800203,0.8561003],"study_design_scores_gemma":[0.0007308032,0.00045754595,0.000008580661,0.0014841137,0.000012533883,0.00001490704,3.1976097e-7,0.8838426,0.0022492362,0.106942765,0.0036795395,0.000577046],"about_ca_topic_score_codex":0.0001898791,"about_ca_topic_score_gemma":0.0000126142495,"teacher_disagreement_score":0.8555233,"about_ca_system_score_codex":0.00022641859,"about_ca_system_score_gemma":0.0011088169,"threshold_uncertainty_score":0.99970144},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034156954,0.0010425773,0.99419105,0.00014772144,0.0032981145,0.0008004003,0.000041190186,0.00018700241,0.00025778147],"genre_scores_gemma":[0.013040535,0.000031842486,0.98406196,0.0012648787,0.001377961,0.000025721392,0.000038840022,0.00005148185,0.00010677808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954518,0.000039350914,0.0006256149,0.0016876411,0.0012353624,0.00096022506],"domain_scores_gemma":[0.99592483,0.0009585619,0.00037112588,0.0020661126,0.00044233646,0.00023704028],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0025976785,0.0005401039,0.00048157573,0.0006105094,0.0009265002,0.0012455706,0.0054443195,0.00031455373,0.0000075226644],"category_scores_gemma":[0.000071409966,0.00039531605,0.00015181422,0.0006140182,0.00058553874,0.0006841243,0.0014895598,0.0008093158,0.000014480773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034447785,0.00002924106,0.0000037083084,0.000013456107,0.0000074373975,0.000038399325,0.00031637715,0.027677426,0.000078673394,0.007846301,0.000020760348,0.96396476],"study_design_scores_gemma":[0.00035473244,0.00012207114,0.00007430294,0.00024741594,0.000009584044,0.000050575905,5.336442e-7,0.97669464,0.0013714564,0.01710445,0.0034438067,0.0005264314],"about_ca_topic_score_codex":0.000036044217,"about_ca_topic_score_gemma":0.000031299773,"teacher_disagreement_score":0.96343833,"about_ca_system_score_codex":0.00031499667,"about_ca_system_score_gemma":0.00042860568,"threshold_uncertainty_score":0.9999367},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012235735,0.00013512635,0.9970824,0.00009354947,0.0012657373,0.0002931453,0.000049697657,0.00009764554,0.0008603154],"genre_scores_gemma":[0.17961319,0.00005990958,0.8189601,0.00030443683,0.00019423368,0.0000077227805,0.00007225934,0.00003808952,0.0007500692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960884,0.00004031898,0.0009424675,0.0012850063,0.0012266972,0.00041714875],"domain_scores_gemma":[0.99701965,0.00026275255,0.00064417574,0.0016100019,0.0003076551,0.00015578237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008353398,0.0003831818,0.00045871997,0.00059755304,0.00017733322,0.0003237545,0.0026830058,0.00023654776,0.0000382732],"category_scores_gemma":[0.000108652326,0.0003345989,0.00006713971,0.0005239903,0.00055780273,0.0007567415,0.0012084582,0.0005194948,0.0000485872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012455394,0.000117191485,0.000074311196,0.00010209165,0.000024614794,0.0001737706,0.0011858235,0.026313648,0.0012307774,0.053140473,0.00012512352,0.9174997],"study_design_scores_gemma":[0.00025020546,0.00014408505,0.00040531324,0.00031619368,0.000009112585,0.000052363164,1.3943915e-7,0.90541863,0.0052776244,0.08751301,0.00019122016,0.0004220864],"about_ca_topic_score_codex":0.000029543686,"about_ca_topic_score_gemma":0.0000084314825,"teacher_disagreement_score":0.91707766,"about_ca_system_score_codex":0.0001732032,"about_ca_system_score_gemma":0.00024444086,"threshold_uncertainty_score":0.9999106},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014983388,0.0011221652,0.99482876,0.0007741356,0.0010276051,0.00030179686,0.000018180037,0.00017009048,0.0016074382],"genre_scores_gemma":[0.043738484,0.00020108456,0.95373654,0.0011338717,0.0008460394,0.000007906731,0.000036720903,0.000030056457,0.00026930164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964585,0.00003931062,0.00048383872,0.0016233881,0.0008805312,0.000514452],"domain_scores_gemma":[0.99751693,0.00018661984,0.0002831986,0.0016197079,0.00016569943,0.00022786857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005281497,0.00048594028,0.00048095622,0.00044985002,0.00042626346,0.0006105141,0.0026145477,0.00028664857,0.000033141554],"category_scores_gemma":[0.000026187448,0.00042474386,0.00007327813,0.00027144016,0.000914881,0.0010009985,0.0023755233,0.00067764695,0.00003918006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066182565,0.000031585627,0.000026127163,0.000019502273,0.0000054998995,0.000031241023,0.00024868874,0.0021489891,0.00044912234,0.03891011,0.000070058406,0.95805246],"study_design_scores_gemma":[0.00038033345,0.00012360449,0.0010848733,0.00028019084,0.00000685343,0.00012476652,8.0827974e-8,0.83598655,0.0016200629,0.14823909,0.011418317,0.00073526514],"about_ca_topic_score_codex":0.000027608285,"about_ca_topic_score_gemma":0.000019820725,"teacher_disagreement_score":0.9573172,"about_ca_system_score_codex":0.00017022739,"about_ca_system_score_gemma":0.0002271598,"threshold_uncertainty_score":0.9998204},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005086513,0.0012290005,0.9960676,0.00028333726,0.0010384269,0.0005170438,0.00008912798,0.000068621135,0.0001982273],"genre_scores_gemma":[0.1592192,0.00028169935,0.8390276,0.00064324745,0.00058141036,0.000011255348,0.00010132316,0.00004464017,0.00008965514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961821,0.000025650956,0.0004610592,0.0020342886,0.00070327497,0.0005936542],"domain_scores_gemma":[0.9968858,0.0005527943,0.00019139217,0.0021223368,0.00009317344,0.00015454192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061440136,0.00046917945,0.0005233526,0.00070011884,0.000262683,0.00038070386,0.004536664,0.0002598371,0.000005716219],"category_scores_gemma":[0.00008696909,0.0003887147,0.000055856573,0.00034554082,0.00054214784,0.00058645976,0.0033913087,0.0005083889,0.0000026754549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020090243,0.000037533282,0.00009594682,0.000042239088,0.000008217927,0.00011443549,0.00088138244,0.034113772,0.000052594904,0.006192732,0.00022227372,0.95821875],"study_design_scores_gemma":[0.0005858397,0.00013714985,0.0016432923,0.00019673716,0.000004911179,0.0001092287,2.303382e-7,0.97384655,0.00015589637,0.018992426,0.00380938,0.0005183554],"about_ca_topic_score_codex":0.00007585324,"about_ca_topic_score_gemma":0.0002332784,"teacher_disagreement_score":0.95770043,"about_ca_system_score_codex":0.000121681325,"about_ca_system_score_gemma":0.00038778945,"threshold_uncertainty_score":0.9998565},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042484455,0.0007422377,0.98788697,0.00029250872,0.0018840511,0.00033065045,0.00002043986,0.00026310727,0.008537554],"genre_scores_gemma":[0.05554153,0.000082461636,0.9384473,0.0017367637,0.0017835434,0.000014497224,0.00009648284,0.00008558967,0.0022118182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953048,0.00003660533,0.00061522995,0.0019143659,0.00132426,0.00080470677],"domain_scores_gemma":[0.9968889,0.00022975277,0.0003392555,0.0021348398,0.0001930092,0.00021425691],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000558972,0.00064555684,0.0006038772,0.0007925823,0.00041109585,0.0007615834,0.0050218673,0.000393534,0.00004100775],"category_scores_gemma":[0.000022108965,0.00054617214,0.0001560825,0.00043144092,0.00056538766,0.0010467672,0.0035911454,0.00093926146,0.0001181376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009033764,0.00008117618,0.000036285805,0.000048611666,0.000010578578,0.00030841844,0.00022981632,0.06781049,0.0012750094,0.019871056,0.0005747174,0.9097448],"study_design_scores_gemma":[0.0004256976,0.00018386087,0.0005282371,0.00045256515,0.00000763328,0.00009438128,3.555637e-8,0.81740916,0.00079863827,0.14914075,0.029820018,0.0011390074],"about_ca_topic_score_codex":0.00006473767,"about_ca_topic_score_gemma":0.00002221385,"teacher_disagreement_score":0.9086058,"about_ca_system_score_codex":0.00027880998,"about_ca_system_score_gemma":0.00036611402,"threshold_uncertainty_score":0.999699},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091170886,0.00017255647,0.99582213,0.00009325438,0.00034703314,0.00032053815,0.000082181374,0.00010888933,0.0021416827],"genre_scores_gemma":[0.29686138,0.000022890212,0.70145184,0.00025763633,0.000105613835,0.00004782568,0.000013816436,0.000016576465,0.001222422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986978,0.000032054595,0.0002532641,0.00038300717,0.00029426202,0.00033959688],"domain_scores_gemma":[0.9990151,0.00014748002,0.00010839563,0.0005121675,0.00012186023,0.00009498275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002715221,0.00013926902,0.00021740282,0.00009629494,0.00015833692,0.00005859114,0.000630939,0.00005688083,0.00009300264],"category_scores_gemma":[0.000019663139,0.00011323126,0.000095710646,0.00022853226,0.000027415348,0.00028994787,0.00040839362,0.00007775504,0.00003249348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070585666,0.0006049369,0.000008329078,0.0000298203,0.000041718115,0.000014868251,0.0013588022,0.00034160566,0.00044636423,0.037207916,0.020555535,0.93938303],"study_design_scores_gemma":[0.00061094796,0.00014505205,0.00006443249,0.000040535087,0.0000059724202,0.000006666932,0.0001145553,0.9899902,0.00598069,0.0002738087,0.0026124355,0.00015471067],"about_ca_topic_score_codex":0.000016976179,"about_ca_topic_score_gemma":0.0000015255159,"teacher_disagreement_score":0.9896486,"about_ca_system_score_codex":0.000027401322,"about_ca_system_score_gemma":0.000016382754,"threshold_uncertainty_score":0.46174368},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008794616,0.0038162344,0.4627506,0.000108966335,0.0013860946,0.00051981036,0.00005844244,0.00026365544,0.53100824],"genre_scores_gemma":[0.002590789,0.02572063,0.42334294,0.00016231462,0.0031179395,0.00005545649,0.00022447458,0.00030473416,0.54448074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99744064,0.000023109997,0.00065140636,0.0008536485,0.00059079163,0.00044039186],"domain_scores_gemma":[0.9978918,0.00017757557,0.00050865824,0.0010360759,0.00013203683,0.00025385566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039187813,0.00048304428,0.00065469556,0.00025821538,0.00013138281,0.00011135835,0.0011130125,0.00034435163,0.000045549667],"category_scores_gemma":[0.000031815805,0.00044770312,0.00012754303,0.00007236425,0.0001250875,0.0003799062,0.0010931016,0.000506439,0.000041629082],"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":[0.0000032995354,0.000023714165,0.00006968101,0.000221134,0.0000642463,0.00003672006,0.0002720694,0.000037899932,0.000014874472,0.18812507,0.0017761877,0.8093551],"study_design_scores_gemma":[0.0006381895,0.0002626323,0.00038104775,0.00096364575,0.00005797481,0.00006465669,0.000005997323,0.012510056,0.00009276464,0.030228721,0.9537672,0.001027108],"about_ca_topic_score_codex":0.000057959816,"about_ca_topic_score_gemma":0.0000063729035,"teacher_disagreement_score":0.951991,"about_ca_system_score_codex":0.00004323041,"about_ca_system_score_gemma":0.00011209285,"threshold_uncertainty_score":0.99979746},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021291577,0.00039545324,0.9941741,0.00013631373,0.0013299355,0.00027858585,0.000007916273,0.00010077355,0.0033639765],"genre_scores_gemma":[0.08793817,0.00012107455,0.9106288,0.00060786254,0.00032517835,0.0000046254468,0.000024331543,0.000035950507,0.0003140185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964111,0.000030324813,0.00063358655,0.0012644358,0.0011780774,0.00048251278],"domain_scores_gemma":[0.9968994,0.00046711485,0.0004401211,0.0017184425,0.0003345555,0.00014031674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008409935,0.00037753908,0.0005288206,0.0010742527,0.00015645991,0.00019775482,0.0029760296,0.0002747205,0.000026882379],"category_scores_gemma":[0.00007868165,0.00032860698,0.00013808416,0.0010282885,0.0004764074,0.00073576265,0.001511991,0.00052794075,0.000017971264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000098676755,0.000037279133,0.00016988245,0.00003358579,0.000010894461,0.00007585581,0.00032430864,0.0039724456,0.00052838074,0.045510076,0.000047925412,0.9492795],"study_design_scores_gemma":[0.0007108724,0.000341067,0.0011471125,0.0007181621,0.000015620186,0.00009173837,2.656378e-7,0.57118124,0.017900823,0.40510368,0.0018041168,0.0009852947],"about_ca_topic_score_codex":0.000081786915,"about_ca_topic_score_gemma":0.000055412584,"teacher_disagreement_score":0.9482942,"about_ca_system_score_codex":0.00010828866,"about_ca_system_score_gemma":0.00027852223,"threshold_uncertainty_score":0.9999166},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95423,0.013050509,0.023803808,0.0048350426,0.001228254,0.00038668307,0.0000025934073,0.000042418465,0.0024207046],"genre_scores_gemma":[0.99625033,0.003114271,0.00009115271,0.0003869438,0.00008303892,0.0000026689133,5.4792116e-7,0.000013339586,0.0000577283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778855,0.00036342227,0.00044901427,0.000263667,0.00054031826,0.00059502677],"domain_scores_gemma":[0.99840236,0.0003555286,0.00038104795,0.00064987503,0.00009278587,0.00011842006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017376347,0.00023391773,0.00030952904,0.00019827748,0.00017316324,0.0001574224,0.0017593852,0.00009192093,0.000003816496],"category_scores_gemma":[0.000060153878,0.000130778,0.00008588302,0.00062697974,0.0001130054,0.0005593018,0.00028293292,0.001051994,0.0000023782725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009070106,0.00027784525,0.00089959125,0.000009870848,0.000049924987,0.00005990467,0.0045371945,0.000006971272,0.0000712046,0.9866158,0.0010527861,0.006328234],"study_design_scores_gemma":[0.0018972608,0.0020359277,0.008326557,0.000116022566,0.00005058287,0.0011765958,0.00037845527,0.001778082,0.0004203663,0.96677893,0.016714012,0.00032723148],"about_ca_topic_score_codex":0.00003787679,"about_ca_topic_score_gemma":0.00001634247,"teacher_disagreement_score":0.04202032,"about_ca_system_score_codex":0.000095468014,"about_ca_system_score_gemma":0.00023822961,"threshold_uncertainty_score":0.53329724},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019124356,0.00025748805,0.9920426,0.00040212908,0.0026476164,0.0006181767,0.00003140474,0.00020294604,0.00188521],"genre_scores_gemma":[0.1501647,0.00022355205,0.84456736,0.0006587089,0.0005004235,0.0003843823,0.00016077283,0.000049552513,0.003290581],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987797,0.000014150679,0.00018769754,0.00062399823,0.0001849161,0.0002095466],"domain_scores_gemma":[0.9986404,0.000090695015,0.000119781886,0.00093620655,0.00010748655,0.000105388164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022900688,0.00019401994,0.00022156606,0.0000646693,0.00011687163,0.00039540688,0.0009837258,0.00028578096,0.000012546788],"category_scores_gemma":[0.000024056706,0.00015313704,0.00005726587,0.00006181933,0.00003062723,0.00022409511,0.0034757657,0.00044418089,0.0000049894084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045100965,0.00020018096,0.0001225326,0.0005508113,0.000036874815,0.0000049286987,0.0005090999,0.00010941213,0.00049486145,0.78265744,0.056965068,0.15834425],"study_design_scores_gemma":[0.00044744476,0.00007549675,0.0005788529,0.00008683169,0.000010041888,0.000008216814,0.000003682335,0.48811096,0.0003140261,0.38431638,0.12562786,0.00042020265],"about_ca_topic_score_codex":0.00007477091,"about_ca_topic_score_gemma":0.000013862155,"teacher_disagreement_score":0.48800153,"about_ca_system_score_codex":0.000014100844,"about_ca_system_score_gemma":0.00006947381,"threshold_uncertainty_score":0.6244747},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003857684,0.00020654392,0.98096687,0.0008609501,0.0021245827,0.00025194229,0.0000076281135,0.00020693995,0.0153359575],"genre_scores_gemma":[0.06815494,0.00010945824,0.918257,0.008121923,0.0020983366,0.000008806405,0.000024564803,0.0000821586,0.0031427902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952835,0.00003809884,0.00043923393,0.0018615467,0.0015538078,0.0008237995],"domain_scores_gemma":[0.9969036,0.00034883386,0.00021137205,0.0021199647,0.00015747739,0.00025877394],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00080646086,0.00058170344,0.00048909703,0.0008691864,0.0004679648,0.001210916,0.004698886,0.00029781664,0.000031396907],"category_scores_gemma":[0.000054944958,0.00048594305,0.00014618233,0.0005178993,0.00044052055,0.0008712703,0.0018753789,0.0013104222,0.00014588573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062866225,0.000037991394,0.0000033815866,0.00000832218,0.0000037416212,0.00016199121,0.00020227341,0.009946528,0.000047096448,0.017597387,0.000103749844,0.9718813],"study_design_scores_gemma":[0.00035228237,0.0007450566,0.0002002243,0.00096806145,0.000004790285,0.00009406233,7.9842955e-8,0.7504653,0.00055353146,0.22159378,0.023946974,0.001075877],"about_ca_topic_score_codex":0.000017796448,"about_ca_topic_score_gemma":0.000015687692,"teacher_disagreement_score":0.97080535,"about_ca_system_score_codex":0.0002894087,"about_ca_system_score_gemma":0.000450847,"threshold_uncertainty_score":0.9998259},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13240884,0.0024126852,0.73081505,0.0034752951,0.0035953927,0.0028317564,0.000076489,0.0014758827,0.122908585],"genre_scores_gemma":[0.9016179,0.00038667757,0.03144005,0.000095246905,0.0016024638,0.000033048007,0.00008697344,0.00007806958,0.06465961],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956909,0.00052350905,0.0003108929,0.0011419131,0.0012215847,0.001111208],"domain_scores_gemma":[0.99639183,0.0005430554,0.00018096852,0.0016432822,0.00090464053,0.0003361992],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088240125,0.0003021898,0.00033666723,0.0008362574,0.001674238,0.0014428376,0.0029309206,0.00021299941,0.000010679052],"category_scores_gemma":[0.000059039343,0.000298404,0.00021859158,0.0012094319,0.00023115706,0.0037934557,0.0012790976,0.0005940563,0.00006193596],"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":[0.00049030106,0.0020581954,0.006420203,0.00038602954,0.0002531703,0.004822082,0.001507292,0.0016123495,0.04382955,0.8265626,0.078305654,0.033752624],"study_design_scores_gemma":[0.003246598,0.00084560626,0.006835271,0.0006310427,0.000040323463,0.00017911282,0.0033520996,0.043937895,0.027683308,0.014175766,0.8976936,0.001379406],"about_ca_topic_score_codex":0.001045362,"about_ca_topic_score_gemma":0.00014429606,"teacher_disagreement_score":0.8193879,"about_ca_system_score_codex":0.00044879699,"about_ca_system_score_gemma":0.0003475079,"threshold_uncertainty_score":0.99994683},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042170985,0.00023949248,0.9903833,0.00046380612,0.0007318969,0.00020786874,0.000012364474,0.000092904374,0.007826166],"genre_scores_gemma":[0.09616729,0.000100407065,0.9012904,0.0005883876,0.00043018867,0.0000025501581,0.000025145071,0.00002816974,0.0013674444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971375,0.000029243289,0.0004529017,0.0011297459,0.00085718103,0.00039345716],"domain_scores_gemma":[0.9973061,0.00030603155,0.00033117054,0.0016899662,0.00023001537,0.00013670069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039140246,0.00033822004,0.00043628525,0.00074923696,0.00017438506,0.00019734853,0.003220935,0.00020542809,0.00002917123],"category_scores_gemma":[0.00004916083,0.00030206697,0.00012405888,0.00060586026,0.0004338431,0.0008331207,0.0012512807,0.0004631201,0.00001692842],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000520207,0.00003773817,0.000047908987,0.000010917566,0.0000073378096,0.00008226403,0.00033976976,0.017271241,0.00017303946,0.036422413,0.000107546955,0.94549465],"study_design_scores_gemma":[0.00055018795,0.00037439674,0.001979607,0.0005260834,0.000015151599,0.00007764259,3.814442e-7,0.75969154,0.002259737,0.22874996,0.0049881493,0.00078714377],"about_ca_topic_score_codex":0.00006572017,"about_ca_topic_score_gemma":0.00008406918,"teacher_disagreement_score":0.94470745,"about_ca_system_score_codex":0.00013820014,"about_ca_system_score_gemma":0.00044592252,"threshold_uncertainty_score":0.99994314},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027211427,0.00006936292,0.9457454,0.000201376,0.00027327426,0.00020978556,0.000011523479,0.00026103467,0.052956093],"genre_scores_gemma":[0.1168695,0.000008214169,0.8793724,0.0010288997,0.00008477556,0.000012353844,0.00007788883,0.00001670283,0.0025292197],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980147,0.00009830159,0.00022791223,0.00089073915,0.0004064327,0.00036193154],"domain_scores_gemma":[0.9968672,0.00006866775,0.000059181435,0.0026808004,0.00005336119,0.0002708117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041911195,0.00018374335,0.00019011078,0.00009237544,0.00023576636,0.0003257842,0.0029556653,0.00006704008,0.000057563484],"category_scores_gemma":[0.000078396944,0.00013703427,0.000029939856,0.00042313652,0.000024310759,0.0011830871,0.0023304988,0.00015651456,0.00015868025],"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":[0.000021982803,0.0010739362,0.00039626242,0.000062030136,0.000038257844,0.00001713064,0.0010730546,0.008842852,0.003808858,0.17150566,0.69371766,0.11944235],"study_design_scores_gemma":[0.00030625975,0.000029482339,0.00019770203,0.00002729955,0.0000038726225,0.000030167113,0.000053570468,0.74123776,0.0011198645,0.0002658564,0.25645268,0.0002754905],"about_ca_topic_score_codex":0.00005265076,"about_ca_topic_score_gemma":0.0000013886261,"teacher_disagreement_score":0.73239493,"about_ca_system_score_codex":0.000019988916,"about_ca_system_score_gemma":0.000049614628,"threshold_uncertainty_score":0.5588095},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028596427,0.00033615986,0.99071175,0.00045323267,0.001253772,0.00022147097,0.000017545708,0.000114059876,0.0068634134],"genre_scores_gemma":[0.052879695,0.00012367989,0.9453717,0.0005753277,0.00044677116,0.000004932674,0.000018940724,0.000029206809,0.0005497317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661595,0.0000317182,0.0005785495,0.0012482499,0.0010756342,0.0004498792],"domain_scores_gemma":[0.9971585,0.00020621995,0.00041101966,0.0018500313,0.00023636321,0.00013784987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005732679,0.0003942224,0.00053095416,0.00062614976,0.00017937504,0.00022235655,0.0031720917,0.0002538889,0.00010831657],"category_scores_gemma":[0.000051623396,0.00035125794,0.00012959835,0.00052974885,0.0011252818,0.000686737,0.0018514637,0.0005860697,0.000040196854],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000511745,0.00006495323,0.00003086249,0.00006109763,0.00000878969,0.00006432018,0.0004361019,0.0041481513,0.00014902632,0.12671784,0.000127009,0.8681867],"study_design_scores_gemma":[0.00024233676,0.00017827532,0.00021707377,0.0006284655,0.0000056627096,0.00006130454,6.517307e-8,0.6432409,0.0014030886,0.35002005,0.0034657458,0.0005370088],"about_ca_topic_score_codex":0.000037383965,"about_ca_topic_score_gemma":0.00001759778,"teacher_disagreement_score":0.86764973,"about_ca_system_score_codex":0.0001545051,"about_ca_system_score_gemma":0.00017988593,"threshold_uncertainty_score":0.99989396},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047727305,0.00007661079,0.9496161,0.000057475077,0.0011234091,0.0001524953,0.0000060341763,0.00018567883,0.0010549292],"genre_scores_gemma":[0.45510775,0.0000027508174,0.5446777,0.000032210883,0.00014278147,0.0000010481652,0.000010602375,0.000007076297,0.000018080236],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99803793,0.00027832156,0.0004953546,0.00045181732,0.00034128487,0.00039530866],"domain_scores_gemma":[0.9975129,0.0007281934,0.00030483698,0.0011345217,0.000203587,0.00011595943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004021169,0.00017278432,0.0002676455,0.00016725504,0.00017027755,0.00007842396,0.0014086377,0.00008592534,0.000010660481],"category_scores_gemma":[0.00024644754,0.00016233856,0.000079419246,0.00058294943,0.00010762092,0.0003620288,0.000716699,0.00018947579,0.000022366183],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039277,0.00008947319,0.023059137,0.000018721486,0.000026325559,0.000013971168,0.00021746861,0.00013524301,0.0018749259,0.0041592135,0.0005009336,0.96990067],"study_design_scores_gemma":[0.0030737477,0.0006208621,0.6802517,0.0004185412,0.000031736967,0.000422055,0.00042371085,0.18430468,0.08915428,0.0091842,0.0301852,0.0019292851],"about_ca_topic_score_codex":0.00026283247,"about_ca_topic_score_gemma":0.000013495558,"teacher_disagreement_score":0.9679714,"about_ca_system_score_codex":0.00003499598,"about_ca_system_score_gemma":0.000068554065,"threshold_uncertainty_score":0.66199744},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012254785,0.00085582107,0.9911127,0.00026191038,0.0011403086,0.0002599867,0.000017742965,0.00011131492,0.0061176848],"genre_scores_gemma":[0.05722992,0.00052283786,0.94075316,0.0007382542,0.0003096594,0.000008926115,0.000027842645,0.000037937403,0.00037143906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965838,0.00003164504,0.000598145,0.0013014526,0.0010414975,0.0004434587],"domain_scores_gemma":[0.99684155,0.00040849586,0.00036592985,0.001986978,0.00024199477,0.00015504874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003691211,0.00039161686,0.00050578377,0.000927125,0.00025360828,0.00015430333,0.003447354,0.00023130939,0.00002563295],"category_scores_gemma":[0.000054562417,0.00034410742,0.00017063956,0.0007598497,0.0007644014,0.0008520278,0.0016920578,0.0006130905,0.00001992955],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010924677,0.000113808666,0.00032856976,0.00006771992,0.000029205507,0.00035026023,0.0013916446,0.012884857,0.00031303812,0.06403812,0.000743585,0.9197283],"study_design_scores_gemma":[0.0006201888,0.00033117767,0.0022454564,0.00077314366,0.000015436057,0.00039003429,2.7959774e-7,0.5587902,0.0050074244,0.42531925,0.005265511,0.0012418817],"about_ca_topic_score_codex":0.00007538124,"about_ca_topic_score_gemma":0.00002184864,"teacher_disagreement_score":0.91848636,"about_ca_system_score_codex":0.00007637096,"about_ca_system_score_gemma":0.0005276775,"threshold_uncertainty_score":0.9999011},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012557235,0.000050567734,0.97675097,0.000030997242,0.00016585525,0.00017661614,0.000008332954,0.00017932075,0.010080104],"genre_scores_gemma":[0.16774344,0.0000023233288,0.8320184,0.00008901552,0.00007491842,0.0000036623005,0.000014223533,0.000016868367,0.000037186106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872905,0.000011543008,0.00027343602,0.0002930636,0.00039700588,0.00029590874],"domain_scores_gemma":[0.9988797,0.00007265812,0.00016916517,0.00066022575,0.00005461785,0.0001636424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032382726,0.00016864912,0.00022551625,0.00005450614,0.00013306056,0.00022906368,0.00074209954,0.000057740788,0.0000056992017],"category_scores_gemma":[0.000028413508,0.00013879307,0.00003784846,0.00023271795,0.000039941122,0.00032344513,0.0007425032,0.00010444864,0.000053828946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009962156,0.00019623282,0.000040153096,0.0001543299,0.000054369917,0.000019120458,0.008656441,0.014525188,0.008315985,0.9483388,0.005377187,0.014312201],"study_design_scores_gemma":[0.00039034183,0.000018171388,0.0000065972968,0.000056492892,0.000012273341,0.000017431195,0.0006626741,0.960293,0.0021179228,0.03375378,0.0024203663,0.00025096617],"about_ca_topic_score_codex":0.000020377409,"about_ca_topic_score_gemma":7.574615e-7,"teacher_disagreement_score":0.9457678,"about_ca_system_score_codex":0.000050768296,"about_ca_system_score_gemma":0.000079060126,"threshold_uncertainty_score":0.5659817},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003820585,0.0006796277,0.9962907,0.0009585993,0.0003054648,0.0009231749,0.0000040982036,0.00007021478,0.00072990794],"genre_scores_gemma":[0.010073243,0.0001743963,0.9883118,0.0010829698,0.0001482027,0.000051260227,0.0000072471726,0.000021108799,0.00012972433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759185,0.000013081833,0.00048349297,0.00079903833,0.0006154772,0.00049707264],"domain_scores_gemma":[0.9984317,0.00020356367,0.00019650908,0.0008704943,0.00016221327,0.00013556269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008321255,0.00030785232,0.00025956976,0.00036460772,0.0003833533,0.0006977409,0.0022854784,0.00016399402,0.0000010096106],"category_scores_gemma":[0.00004811882,0.00021871942,0.000024546056,0.0007500808,0.00015605043,0.00074425543,0.0018948208,0.00047995677,0.000024593175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030179003,0.0000142598055,0.000015600614,0.000050635816,0.0000022771483,0.000006816684,0.0008841011,0.09118017,0.00010761735,0.046221573,0.000013644562,0.86150026],"study_design_scores_gemma":[0.00017919976,0.00007946392,0.000035025456,0.0005089123,0.0000016664249,0.000020493595,2.9741366e-7,0.8639758,0.00042989,0.13180378,0.0026384313,0.0003270045],"about_ca_topic_score_codex":0.00003422434,"about_ca_topic_score_gemma":0.00013607439,"teacher_disagreement_score":0.8611733,"about_ca_system_score_codex":0.00022476735,"about_ca_system_score_gemma":0.0003860782,"threshold_uncertainty_score":0.89191186},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000117334035,0.00014143177,0.99815625,0.00013106139,0.00018082833,0.0004808892,0.000027350748,0.00002601421,0.00073885405],"genre_scores_gemma":[0.66024345,0.00001631195,0.33908287,0.00041056142,0.0001239132,0.000033412158,0.000018525825,0.000016351592,0.000054579643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980332,0.000077133096,0.0004115889,0.0006384361,0.0006480772,0.0001915095],"domain_scores_gemma":[0.9960899,0.0023082884,0.00039823705,0.0010143762,0.00014427124,0.000044971213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014862731,0.00023493785,0.00031871308,0.00035537698,0.0001625891,0.00012080846,0.0016771357,0.00014675234,0.000009654586],"category_scores_gemma":[0.00009652781,0.00015765154,0.000055650442,0.00031828004,0.0007110742,0.00023340748,0.00055757834,0.00030609692,0.0000017157591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026441905,0.000035966856,0.000007973391,0.000041139476,0.0000053042745,0.0000025198235,0.00009079735,0.26572508,0.00028475112,0.3512007,0.00001884813,0.38256046],"study_design_scores_gemma":[0.00026745023,0.00006332393,0.000044754088,0.00021695103,0.0000058145315,0.0000047475805,7.244561e-8,0.66504145,0.0023557956,0.33179873,0.00006890348,0.00013200167],"about_ca_topic_score_codex":0.000042934673,"about_ca_topic_score_gemma":0.000005419696,"teacher_disagreement_score":0.66012615,"about_ca_system_score_codex":0.00005723813,"about_ca_system_score_gemma":0.00031733402,"threshold_uncertainty_score":0.64288425},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005437103,0.0014879599,0.99251413,0.0010811576,0.0014351064,0.0003098247,0.00002294673,0.00030245876,0.0027920622],"genre_scores_gemma":[0.10987447,0.0003036881,0.88390696,0.003976188,0.001096121,0.000013488902,0.00005359352,0.00006473515,0.00071073195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99470854,0.00004783397,0.0007027849,0.0021326975,0.0014048435,0.0010033164],"domain_scores_gemma":[0.99707496,0.00044466782,0.00045935533,0.0015072778,0.0002360253,0.00027773704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010295673,0.0007031415,0.00065578753,0.00056521205,0.00054727803,0.001012198,0.0050964635,0.00034068435,0.000021044805],"category_scores_gemma":[0.00010569268,0.000621085,0.00013098454,0.0006800159,0.0006722682,0.0016911823,0.0014971258,0.0010532656,0.00003140984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023346015,0.000017188033,0.0000137574225,0.000016531696,0.0000059655545,0.00013706664,0.0002807279,0.0038299088,0.0012422219,0.010642062,0.00010931118,0.9837029],"study_design_scores_gemma":[0.00028227575,0.00021904278,0.000033299155,0.00088657154,0.000008641036,0.00017439194,3.2172008e-7,0.80964077,0.0019741924,0.17812945,0.0074956296,0.0011554206],"about_ca_topic_score_codex":0.000066866,"about_ca_topic_score_gemma":0.000022031281,"teacher_disagreement_score":0.9825475,"about_ca_system_score_codex":0.00031958797,"about_ca_system_score_gemma":0.00048243642,"threshold_uncertainty_score":0.9996241},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013177352,0.00011145414,0.9957276,0.00047056316,0.0013696847,0.00020225708,0.000011343061,0.000041871357,0.0007475042],"genre_scores_gemma":[0.35410368,0.00007052678,0.6428017,0.0022533613,0.0005629448,0.0000074188983,0.0000078108615,0.00004524504,0.00014730533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976733,0.000017274026,0.00034036348,0.00088683376,0.0007277061,0.00035454967],"domain_scores_gemma":[0.9976277,0.00072658004,0.0002881081,0.0011177537,0.00016099517,0.00007888854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084659696,0.00030710507,0.00032140483,0.00028911227,0.00030783156,0.0004313067,0.0024201681,0.0001949598,0.00001375965],"category_scores_gemma":[0.00010827402,0.00020256662,0.00005862977,0.00022303143,0.00060615374,0.00038201103,0.001868596,0.0008975431,0.00000517481],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008799533,0.000042128067,0.00016239205,0.00006545418,0.000011901193,0.000019787687,0.0008953501,0.00172485,0.0014888059,0.14652517,0.000030303489,0.8490251],"study_design_scores_gemma":[0.0005586363,0.00025207386,0.0008005763,0.0021576653,0.000010864052,0.000102012455,5.808747e-7,0.5913342,0.008302174,0.38711104,0.008300084,0.0010700615],"about_ca_topic_score_codex":0.000020840083,"about_ca_topic_score_gemma":0.000013769664,"teacher_disagreement_score":0.847955,"about_ca_system_score_codex":0.000041299412,"about_ca_system_score_gemma":0.000141221,"threshold_uncertainty_score":0.8260427},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008370088,0.000049102015,0.98947895,0.0038231106,0.0001675566,0.00014532117,0.0000018302264,0.0002944352,0.0052027083],"genre_scores_gemma":[0.23984976,0.00000629809,0.7551653,0.0014252164,0.00045433606,0.000024427762,0.000004342259,0.0000129875425,0.003057336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882096,0.000023545274,0.00018787922,0.00041608923,0.0002443797,0.00030711663],"domain_scores_gemma":[0.9991723,0.000025109151,0.000036821886,0.00055599964,0.000021522597,0.00018830235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002270208,0.00013166571,0.00013613,0.000108803804,0.00015202146,0.00019742594,0.00068794494,0.000043327,0.000044733206],"category_scores_gemma":[0.000013408567,0.00010399176,0.000048977094,0.00022417403,0.000013360276,0.00055756833,0.00076834165,0.00009733951,0.00050665956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028744505,0.00011281158,0.000008574696,0.00000793528,0.0000120127925,0.0000053862414,0.0015353223,0.005782295,0.0009808202,0.040280167,0.023664812,0.927607],"study_design_scores_gemma":[0.00015701925,0.000038420054,0.00013225753,0.000015603935,0.0000015696569,0.000018883664,0.000057537254,0.9345314,0.007381581,0.00065664155,0.05680234,0.000206737],"about_ca_topic_score_codex":0.000036921236,"about_ca_topic_score_gemma":0.0000041358844,"teacher_disagreement_score":0.9287491,"about_ca_system_score_codex":0.000038191993,"about_ca_system_score_gemma":0.000021113698,"threshold_uncertainty_score":0.6512252},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014533564,0.00008486665,0.14328098,0.000046514924,0.0003184913,0.00014917365,0.00006247189,0.00024129731,0.85581475],"genre_scores_gemma":[0.07481374,0.00007503724,0.32409543,0.02514406,0.004745483,0.00006327313,0.0005362534,0.00016492188,0.5703618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985086,0.0000085656775,0.00036801156,0.00030950346,0.0005073594,0.00029800122],"domain_scores_gemma":[0.99873006,0.000014880666,0.0002519765,0.000751672,0.00010303663,0.00014837933],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000106092106,0.00030322833,0.0002578957,0.00008490593,0.00013232106,0.00038642887,0.001043753,0.00032001853,0.000015321468],"category_scores_gemma":[0.000009231734,0.00027908487,0.00011019235,0.000020868561,0.00003206259,0.00071648497,0.0005564836,0.00027469374,0.00048755997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023594646,0.0000016413011,3.4843333e-7,0.00000420594,0.000006634874,0.000010263639,0.00002537708,0.0000043150353,4.844547e-7,0.6774197,0.0047049327,0.31781968],"study_design_scores_gemma":[0.00021657071,0.0000788096,0.000030415422,0.00016544669,0.000009416551,0.00005355386,0.0000026637322,0.0023165103,0.000009748328,0.44505942,0.5516668,0.00039064995],"about_ca_topic_score_codex":0.000030146928,"about_ca_topic_score_gemma":0.000006968853,"teacher_disagreement_score":0.54696184,"about_ca_system_score_codex":0.00016032725,"about_ca_system_score_gemma":0.00018626403,"threshold_uncertainty_score":0.99996614},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6283914,0.0002914041,0.3585245,0.004375578,0.0018824674,0.0006221306,0.00011921774,0.0002496253,0.0055436958],"genre_scores_gemma":[0.9779266,0.000032729862,0.020990536,0.0003513632,0.00024018776,0.000029344677,0.00009544018,0.000023600513,0.00031016307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99743927,0.0002579226,0.00046301828,0.0008135436,0.0006792548,0.0003469907],"domain_scores_gemma":[0.99613005,0.00034469797,0.0005404546,0.0027365664,0.00015544941,0.00009280729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004005522,0.00035904825,0.00048612285,0.00009875282,0.00025711925,0.00012483564,0.0030050112,0.00024256391,0.000060247938],"category_scores_gemma":[0.00005874365,0.00024274712,0.00019149795,0.0002067348,0.00026696123,0.00018001154,0.004915251,0.0008892748,0.000108060914],"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":[0.00016600247,0.0032203028,0.086031236,0.0007838939,0.00034388312,0.00008929093,0.0013144892,0.009981467,0.010797955,0.6234518,0.24402493,0.019794686],"study_design_scores_gemma":[0.0007845412,0.00022046738,0.7239508,0.0019328982,0.000048933212,0.0000064068804,0.000021884578,0.14207047,0.018673044,0.10035137,0.010854758,0.001084399],"about_ca_topic_score_codex":0.0009123074,"about_ca_topic_score_gemma":0.000023280172,"teacher_disagreement_score":0.6379196,"about_ca_system_score_codex":0.000059115195,"about_ca_system_score_gemma":0.00010443072,"threshold_uncertainty_score":0.989894},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003815359,0.00018007336,0.99427795,0.00006146622,0.0002009797,0.0000717029,0.000008054364,0.00008073501,0.0013036915],"genre_scores_gemma":[0.6653601,0.0000201923,0.33405495,0.00015824605,0.000011205395,0.0000037594361,0.000012203256,0.000007027744,0.000372323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909186,0.0000817132,0.00019642954,0.00024177607,0.00022272611,0.00016551327],"domain_scores_gemma":[0.9993523,0.000039038896,0.00008388812,0.00042247822,0.000040218325,0.00006208165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017350851,0.00009280384,0.00011653809,0.000039856885,0.000090433845,0.000041708223,0.0004309388,0.000044098193,0.000055761746],"category_scores_gemma":[0.000010855372,0.00007060762,0.000035618392,0.00011027005,0.000018290984,0.00042595455,0.00018551032,0.00007664605,0.000020858193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015820955,0.0020090605,0.0061873603,0.00015939082,0.00006849129,0.00002245037,0.0032284805,0.008386926,0.22714849,0.07891977,0.092872985,0.5809808],"study_design_scores_gemma":[0.00075743446,0.000052068066,0.0011543877,0.00008126012,0.0000035844419,0.000009156668,0.000059195118,0.9432515,0.038256202,0.0011423733,0.0149973985,0.00023542627],"about_ca_topic_score_codex":0.00022895748,"about_ca_topic_score_gemma":0.00000791557,"teacher_disagreement_score":0.9348646,"about_ca_system_score_codex":0.000012848643,"about_ca_system_score_gemma":0.000014153435,"threshold_uncertainty_score":0.2879295},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073444983,0.0008331811,0.9959163,0.00018492389,0.0014158057,0.00055606704,0.000029654382,0.00008722518,0.00024237233],"genre_scores_gemma":[0.09406872,0.00015988127,0.90496033,0.0004048364,0.00017660494,0.00001978176,0.00002094424,0.000038950962,0.00014992346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644035,0.000028766735,0.0005424911,0.0017454164,0.0005310102,0.0007119493],"domain_scores_gemma":[0.9976775,0.00064486044,0.00025358703,0.0010949513,0.00014331937,0.00018580264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006690188,0.00051669317,0.00057007454,0.00084989646,0.00030204325,0.00038430584,0.0019758241,0.0003218092,0.000008238785],"category_scores_gemma":[0.000065604516,0.00046092633,0.00008054513,0.00037723986,0.00044016013,0.00083083764,0.0020526543,0.00055889663,0.000005219227],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067101723,0.000040858024,0.000042041574,0.000040817828,0.000007187559,0.000067256544,0.000617503,0.0015574138,0.00030954045,0.0106327385,0.000011623042,0.9866663],"study_design_scores_gemma":[0.00044727704,0.00018627087,0.00044752893,0.0007528936,0.000008059021,0.00004832626,3.355817e-7,0.8104583,0.00032930312,0.18627095,0.00044371464,0.0006070294],"about_ca_topic_score_codex":0.00011764344,"about_ca_topic_score_gemma":0.00012307407,"teacher_disagreement_score":0.9860593,"about_ca_system_score_codex":0.00020279814,"about_ca_system_score_gemma":0.00028277305,"threshold_uncertainty_score":0.99978423},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87693894,0.0013853157,0.06887981,0.0012859912,0.0045193546,0.0003913734,0.0000079496585,0.0006489268,0.045942314],"genre_scores_gemma":[0.98384964,0.00058778777,0.015033488,0.00020081787,0.00002103737,0.000007840461,0.000004899512,0.000010392274,0.000284081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99911237,0.000024703642,0.00012528306,0.0003107607,0.00019536336,0.00023152564],"domain_scores_gemma":[0.9992665,0.000046152963,0.000041260613,0.0005055632,0.000032820957,0.0001077008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000127447,0.00011198269,0.00012237564,0.000052335767,0.00013387155,0.00014132493,0.0005101574,0.000047498972,0.000017005761],"category_scores_gemma":[0.000015454889,0.00009788709,0.000025758629,0.00022307689,0.00003232853,0.0005273538,0.00039383996,0.00010407907,0.0000456827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004406341,0.000071556125,0.0031699499,0.0000068406152,0.000008545398,0.000078447345,0.0002699075,7.3224595e-7,0.00026838196,0.92314595,0.00680339,0.066171914],"study_design_scores_gemma":[0.0014428458,0.00023801823,0.02962581,0.00004819487,0.000007989401,0.00012696651,0.000067748115,0.027670505,0.0006146634,0.81462157,0.12507038,0.00046533815],"about_ca_topic_score_codex":0.00006258169,"about_ca_topic_score_gemma":0.0000014937644,"teacher_disagreement_score":0.118266985,"about_ca_system_score_codex":0.000018878904,"about_ca_system_score_gemma":0.000022031156,"threshold_uncertainty_score":0.39917198},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52440995,0.0016063616,0.4714711,0.00043886996,0.00016645258,0.000092943046,0.000010635591,0.000250968,0.0015526843],"genre_scores_gemma":[0.86446977,0.00023465922,0.13428144,0.00029399048,0.000057426656,0.0000080746095,0.0000103971715,0.000005041985,0.00063922734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932885,0.000024703775,0.000103888684,0.0002622605,0.00013398843,0.00014628083],"domain_scores_gemma":[0.99957603,0.00004588415,0.00003039701,0.00026503726,0.000015326454,0.00006729655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048343554,0.00008419684,0.00008977457,0.000023161261,0.00021060265,0.00007355559,0.00028189222,0.000026246413,0.000018967543],"category_scores_gemma":[0.000011275592,0.000060528,0.0000141048195,0.000081062295,0.000031540243,0.0004961358,0.0003056505,0.000045687528,0.000008398901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022480413,0.00047865725,0.032279037,0.00003823789,0.00004796331,0.00015606266,0.0029586356,0.0006465262,0.13383017,0.00852031,0.3978456,0.42317632],"study_design_scores_gemma":[0.00050169055,0.00018004545,0.023307074,0.000041273845,0.0000026997402,0.000054212986,0.00003974107,0.94920826,0.008821675,0.00036463307,0.017093724,0.00038499566],"about_ca_topic_score_codex":0.000051630577,"about_ca_topic_score_gemma":0.000003548681,"teacher_disagreement_score":0.9485617,"about_ca_system_score_codex":0.00000510283,"about_ca_system_score_gemma":0.0000145001895,"threshold_uncertainty_score":0.24682601},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026016334,0.00012921375,0.97159314,0.0011698495,0.000089607354,0.00016992004,0.0000024856397,0.000054416392,0.0007750205],"genre_scores_gemma":[0.7584446,0.00007836158,0.24043413,0.0007289059,0.000099682875,0.000037010548,0.000009810206,0.000008470464,0.0001590166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907166,0.000050607934,0.00016350098,0.00030170762,0.00024085384,0.00017166961],"domain_scores_gemma":[0.9993843,0.00008510147,0.00005208266,0.0004107597,0.0000381502,0.000029615263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478991,0.000086494634,0.000093078146,0.00006636374,0.000167897,0.00008845348,0.00050942536,0.000037631482,0.0000020254913],"category_scores_gemma":[0.000030251866,0.00005855646,0.000020275038,0.00028620163,0.000052947915,0.00063917076,0.00024927384,0.00014879186,0.0000104352885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038384354,0.0007295796,0.009039694,0.00006402421,0.00004823573,0.000743651,0.04285044,0.005440991,0.0036828108,0.12626235,0.031957977,0.77914184],"study_design_scores_gemma":[0.00019296883,0.000016505739,0.0028390114,0.00001338585,0.0000014709979,0.00012866643,0.00006039971,0.9892981,0.00024808783,0.006306023,0.00080392027,0.000091434944],"about_ca_topic_score_codex":0.00012858197,"about_ca_topic_score_gemma":0.000004644118,"teacher_disagreement_score":0.98385715,"about_ca_system_score_codex":0.000013023615,"about_ca_system_score_gemma":0.000033802487,"threshold_uncertainty_score":0.23878631},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09338638,0.011062342,0.8895824,0.0035132673,0.0019427999,0.00029259027,0.0000056202034,0.000062024454,0.00015256368],"genre_scores_gemma":[0.9936128,0.004157962,0.0018626681,0.00015353803,0.00011139702,0.000004461754,0.0000061166575,0.000018873045,0.000072174626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977455,0.0003685055,0.0005449999,0.00028931274,0.0005404838,0.00051116926],"domain_scores_gemma":[0.99701476,0.00092997623,0.00066603324,0.0009077041,0.000327089,0.00015442449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087657134,0.00027655627,0.0004610752,0.00016878125,0.00027938728,0.0002932329,0.0021783758,0.00019745617,0.0000015833842],"category_scores_gemma":[0.0002089528,0.0001840689,0.00016691057,0.00025459926,0.00008739019,0.00022937453,0.0010975052,0.0019673195,0.000003384788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008136236,0.00039792023,0.00006203543,0.000074593736,0.0003487329,0.00010903022,0.0009519779,0.007739943,0.00013597417,0.9264471,0.0040609716,0.059590366],"study_design_scores_gemma":[0.00066959945,0.0007998717,0.00009040669,0.00024564698,0.00013460428,0.00081954605,0.000036262983,0.12933227,0.00017976777,0.8609818,0.00638059,0.00032963618],"about_ca_topic_score_codex":0.000017794244,"about_ca_topic_score_gemma":0.0000031614816,"teacher_disagreement_score":0.9002264,"about_ca_system_score_codex":0.00024136768,"about_ca_system_score_gemma":0.0005831475,"threshold_uncertainty_score":0.8547134},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055189605,0.0011464055,0.9922011,0.00015827653,0.0008632125,0.0004823141,0.000020530804,0.000104172825,0.004472117],"genre_scores_gemma":[0.8037184,0.00009528789,0.19539359,0.00047640692,0.000115128234,0.0000140509965,0.0000079140655,0.000033140892,0.00014612495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99462646,0.00009579894,0.0009185109,0.0019751776,0.0016679461,0.0007161182],"domain_scores_gemma":[0.99610454,0.00049160694,0.00045983755,0.0023753392,0.0003455766,0.000223131],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011487699,0.0006138505,0.0008871127,0.0009806487,0.00014582026,0.00023853038,0.0050435737,0.00045202562,0.00007664829],"category_scores_gemma":[0.000086354856,0.0005351197,0.0001709768,0.0011261705,0.0014412669,0.000828685,0.0023380318,0.0011704579,0.000037911836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020258964,0.00017773198,0.00033786902,0.00009710702,0.000011420552,0.00019296882,0.0007135772,0.016957551,0.0003366246,0.023653368,0.000064356274,0.95743716],"study_design_scores_gemma":[0.0006434584,0.00027629535,0.00059727475,0.0014529696,0.0000065579766,0.000072138006,4.347911e-7,0.8241928,0.0016919138,0.16954455,0.0007425441,0.00077902304],"about_ca_topic_score_codex":0.00016044518,"about_ca_topic_score_gemma":0.0002011511,"teacher_disagreement_score":0.9566581,"about_ca_system_score_codex":0.00023959014,"about_ca_system_score_gemma":0.0006397911,"threshold_uncertainty_score":0.99971},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016198653,0.000019049847,0.95226365,0.0109119825,0.0014562103,0.00013004345,0.000009282316,0.00023867708,0.03335124],"genre_scores_gemma":[0.9660809,0.000047477763,0.031563845,0.0016431772,0.00028317975,0.0000080845875,0.000014172052,0.000006818235,0.00035236162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783766,0.000050359333,0.0005083376,0.0006111516,0.0006614302,0.0003310322],"domain_scores_gemma":[0.9986796,0.00007385182,0.00016768048,0.0005941981,0.00033734585,0.00014732461],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028969272,0.00022871996,0.00019728737,0.0002254799,0.00016487966,0.0006354399,0.001652908,0.00007875648,0.0005370819],"category_scores_gemma":[0.00015745145,0.00020358562,0.00010688524,0.00023037344,0.00006132049,0.0008131107,0.00025012033,0.000280169,0.0011993097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010860568,0.000106935666,0.0000026451219,6.516762e-7,0.0000057635857,0.000032152784,0.00012779616,0.00020583438,0.005243797,0.58527535,0.00045326896,0.40853497],"study_design_scores_gemma":[0.000036002053,0.00023195967,0.00057639525,0.000120039986,0.0000024691205,0.000022978375,0.00006986784,0.56506044,0.057795625,0.3729057,0.00284108,0.00033745778],"about_ca_topic_score_codex":0.000034981604,"about_ca_topic_score_gemma":0.000006726626,"teacher_disagreement_score":0.964461,"about_ca_system_score_codex":0.00007843058,"about_ca_system_score_gemma":0.00009914389,"threshold_uncertainty_score":0.99957836},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008337749,0.000020534331,0.9628948,0.000016654734,0.000086625616,0.00017640197,0.000012977453,0.00009015233,0.028364105],"genre_scores_gemma":[0.40474892,0.000022331684,0.59500885,0.000042591626,0.00002429568,0.000010935945,0.000009104901,0.000016184948,0.00011676249],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989992,0.000016315955,0.00029636026,0.00020950631,0.00026562,0.00021302141],"domain_scores_gemma":[0.998669,0.00016588035,0.0002295208,0.0008284464,0.000048864465,0.000058239155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000392725,0.00012987613,0.0001718516,0.00003137481,0.00018603813,0.00010500607,0.0010339937,0.0000522678,0.000024516816],"category_scores_gemma":[0.000022081544,0.000083682906,0.000037529968,0.0002554946,0.00007047483,0.0002933819,0.0005294694,0.00012130054,0.00000822557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006576716,0.00005030008,0.000008097024,0.00003835904,0.000023746205,0.000001340652,0.0029902107,0.0000088699935,0.0011672837,0.99205315,0.00025077738,0.003401305],"study_design_scores_gemma":[0.0014187777,0.00011248916,0.00079144025,0.00026107449,0.00008179104,0.000010546762,0.002429516,0.49810392,0.03131342,0.4561044,0.008563284,0.0008093589],"about_ca_topic_score_codex":0.00003885858,"about_ca_topic_score_gemma":0.0000012576792,"teacher_disagreement_score":0.53594875,"about_ca_system_score_codex":0.000017027369,"about_ca_system_score_gemma":0.00003652603,"threshold_uncertainty_score":0.341249},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043890197,0.000028176808,0.9922837,0.0000511079,0.0018786202,0.0004674144,0.00010468416,0.00024243777,0.0005548469],"genre_scores_gemma":[0.9683412,0.00010017015,0.030004358,0.00008669201,0.0004001198,0.0000041595745,0.00022857563,0.00002391526,0.0008108139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806243,0.00009886162,0.00019595554,0.0012034148,0.000115898394,0.00032342013],"domain_scores_gemma":[0.99790883,0.00016074262,0.00033420674,0.0011712705,0.00027106065,0.00015387702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021080216,0.00031458045,0.00032407133,0.00019839291,0.00020098817,0.00018939593,0.002019424,0.0002634341,0.000014375617],"category_scores_gemma":[0.00004292117,0.0003318857,0.00019114444,0.00024529113,0.00005071232,0.00055153394,0.0020543593,0.0003149586,0.000036356687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068735564,0.00023555904,0.0005165908,0.00021783034,0.0002191589,0.000090817164,0.0004741131,0.38441816,0.000100789825,0.5822804,0.0042817714,0.027096042],"study_design_scores_gemma":[0.0004923196,0.00006844704,0.00014336855,0.000066630186,0.000027266238,0.0000012462192,0.00000822448,0.8839107,0.00030514447,0.109891444,0.004731644,0.00035354093],"about_ca_topic_score_codex":0.00016520362,"about_ca_topic_score_gemma":0.000006059985,"teacher_disagreement_score":0.9639522,"about_ca_system_score_codex":0.0001629143,"about_ca_system_score_gemma":0.00011111416,"threshold_uncertainty_score":0.99991333},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013185618,0.000034566656,0.9678206,0.00031578157,0.00016178533,0.00003602708,7.029652e-7,0.000142208,0.03016977],"genre_scores_gemma":[0.80501264,0.00003315125,0.19043724,0.000560314,0.000034551285,0.0000040273053,0.0000010997959,0.0000033011759,0.003913694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946755,0.000012706169,0.00008489265,0.00016999636,0.00012952274,0.00013533034],"domain_scores_gemma":[0.99955946,0.000036932368,0.00002206009,0.0003148265,0.000017697686,0.00004901182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004474958,0.0000517999,0.000057136058,0.000027413405,0.00006964326,0.00009423553,0.00039336612,0.0000146814755,0.00049662107],"category_scores_gemma":[0.00000979902,0.00003924958,0.000015797117,0.00011990577,0.000008726554,0.00043388395,0.0001741916,0.000039534025,0.00044848054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.894251e-7,0.00010430003,0.000022896314,0.000012664158,0.000008884573,0.00001914644,0.0011082301,0.000071238355,0.013241683,0.1755408,0.060233247,0.74963593],"study_design_scores_gemma":[0.00018968286,0.00003616106,0.00014636797,0.000014035384,9.744056e-7,0.0000043501013,0.000016059346,0.97091115,0.0148538845,0.0017513607,0.011943275,0.00013272777],"about_ca_topic_score_codex":0.000008417425,"about_ca_topic_score_gemma":8.0242535e-7,"teacher_disagreement_score":0.97083986,"about_ca_system_score_codex":0.000008384753,"about_ca_system_score_gemma":0.000003238923,"threshold_uncertainty_score":0.57644594},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013842327,0.000046286554,0.9816316,0.00020106524,0.00021423808,0.0000893103,0.000010915482,0.00017481878,0.0037894382],"genre_scores_gemma":[0.11828086,0.0000056319236,0.88127154,0.0001081351,0.000070767586,0.000007277211,0.000013685792,0.0000114880795,0.00023062147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990451,0.00003579464,0.00020463238,0.0002033597,0.00028083244,0.00023028142],"domain_scores_gemma":[0.9990183,0.00006219615,0.000110291076,0.0005616291,0.00008353012,0.00016406483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035690056,0.00011134063,0.00014170539,0.000060589136,0.00008130448,0.0001959566,0.0005548088,0.000039834216,0.000008648419],"category_scores_gemma":[0.000107707965,0.0000918395,0.000036691355,0.00025015604,0.000058201447,0.00048716232,0.00028620855,0.00009030911,0.000058866688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000086631235,0.00015037264,0.001025912,0.00012931177,0.000034546396,0.00009396678,0.008544076,0.00040672673,0.0018532957,0.92126775,0.021024415,0.045460977],"study_design_scores_gemma":[0.0003587488,0.00006000584,0.000046303176,0.00006901578,0.000010483779,0.00024512302,0.0005148297,0.69780105,0.002401789,0.28337607,0.014827703,0.0002888847],"about_ca_topic_score_codex":0.00005051894,"about_ca_topic_score_gemma":0.000008866411,"teacher_disagreement_score":0.6973943,"about_ca_system_score_codex":0.00007339138,"about_ca_system_score_gemma":0.00011635686,"threshold_uncertainty_score":0.37451062},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1792098e-7,0.0007148713,0.7927615,0.0002977251,0.0002961702,0.0004408272,0.0005468974,0.00020352923,0.20473827],"genre_scores_gemma":[0.0000259437,0.00021489958,0.7373486,0.00033730752,0.00030615233,0.000014990338,0.0013775781,0.000037751128,0.26033676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698514,0.00005089146,0.00052817335,0.0014714028,0.0005913594,0.00037305098],"domain_scores_gemma":[0.9956074,0.00036385574,0.00035536967,0.003325698,0.00017268429,0.00017501519],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062727724,0.0004643544,0.0005099216,0.0001663679,0.00024861319,0.0002857993,0.003932973,0.00037815573,0.00008157427],"category_scores_gemma":[0.00002626063,0.00036814305,0.00013035492,0.000035836052,0.000046268502,0.0019740134,0.0029908991,0.00031427582,0.000042253847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027075874,0.000029561546,2.4550925e-8,0.000043077413,0.00003786139,0.000014333314,0.0007185541,0.000020000414,0.0002519352,0.34023777,0.13559961,0.5230202],"study_design_scores_gemma":[0.0004473428,0.00010461888,3.6543878e-7,0.00037985985,0.000025045383,0.000009377424,0.00004126224,0.41265476,0.0003321875,0.3970775,0.1882226,0.00070508086],"about_ca_topic_score_codex":0.000012757353,"about_ca_topic_score_gemma":0.0000035842634,"teacher_disagreement_score":0.5223151,"about_ca_system_score_codex":0.00006281979,"about_ca_system_score_gemma":0.00014765078,"threshold_uncertainty_score":0.99987704},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07064436,0.00017590933,0.9276822,0.00036035944,0.0003138555,0.00023050999,0.000027952045,0.00017835436,0.0003864919],"genre_scores_gemma":[0.81912667,0.000009467739,0.18003972,0.00019213109,0.00043315542,0.000010842092,0.00004484503,0.0000069038265,0.0001362918],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885774,0.00002318469,0.00021152437,0.0003496317,0.00016628182,0.00039163974],"domain_scores_gemma":[0.9991377,0.00030176714,0.00007494559,0.0003260147,0.000049450744,0.000110109686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057673967,0.00013400333,0.00018388177,0.00009569863,0.00023120314,0.00013691056,0.0007410677,0.00011567555,0.000009906887],"category_scores_gemma":[0.0000339257,0.0001027264,0.00007217424,0.00020832742,0.000068821566,0.00029214798,0.00034153412,0.00009892401,0.00001608438],"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":[0.00007787458,0.0002572478,0.27751955,0.00016257085,0.00014286928,0.00016251064,0.0015442278,0.0000752312,0.01628596,0.11090093,0.017553777,0.57531726],"study_design_scores_gemma":[0.002250246,0.0009239923,0.7047239,0.00025510057,0.000028100996,0.000051288298,0.00030182465,0.02652706,0.07494798,0.019663977,0.16860159,0.0017249358],"about_ca_topic_score_codex":0.000026061507,"about_ca_topic_score_gemma":0.0000046573305,"teacher_disagreement_score":0.7484823,"about_ca_system_score_codex":0.000034656376,"about_ca_system_score_gemma":0.00002944771,"threshold_uncertainty_score":0.41890612},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049712326,0.008017497,0.93398356,0.005858945,0.00094957993,0.00008771118,3.7876146e-7,0.000054856802,0.001335125],"genre_scores_gemma":[0.99871093,0.00041867158,0.000354957,0.0003053957,0.00012491099,2.6154024e-7,2.402068e-7,0.000004421849,0.0000802275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861956,0.000073132884,0.00030717652,0.000101367805,0.00046961874,0.00042913784],"domain_scores_gemma":[0.99891543,0.00009696269,0.00033908905,0.00038210917,0.00020516611,0.000061260354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010363372,0.00010470307,0.0001641792,0.00008065792,0.00020037095,0.00014591508,0.0016181224,0.00003709589,0.0000031639443],"category_scores_gemma":[0.00004968691,0.00006395208,0.00008057549,0.0004153573,0.000019476718,0.0005584849,0.00008852357,0.00052914803,0.0000071507648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007104604,0.00007107596,0.00003904235,0.0000013861195,0.000013078558,0.000010098409,0.00014154657,0.000052176754,0.00024363073,0.9813357,0.0020412195,0.016043944],"study_design_scores_gemma":[0.0004974971,0.00077628,0.0009576939,0.000031379266,0.000013071277,0.0002623958,0.000027117447,0.0061695413,0.0008033909,0.96778,0.022560706,0.00012091361],"about_ca_topic_score_codex":0.0000034370257,"about_ca_topic_score_gemma":4.4353814e-7,"teacher_disagreement_score":0.9489986,"about_ca_system_score_codex":0.0001259581,"about_ca_system_score_gemma":0.00027649035,"threshold_uncertainty_score":0.3006901},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000960681,0.0004173997,0.98930925,0.00014518251,0.00072248053,0.0003216371,0.000012651341,0.00010569409,0.008869644],"genre_scores_gemma":[0.08659688,0.0002592221,0.9121137,0.00024424575,0.00034992426,0.000008774234,0.000036044476,0.000029636909,0.0003615498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962557,0.00003346721,0.0006086713,0.0013742695,0.0012697318,0.0004581637],"domain_scores_gemma":[0.99713826,0.00019966098,0.00042419796,0.001820021,0.00027722024,0.00014062735],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044355495,0.00043444254,0.00062497053,0.00078489434,0.00020601967,0.00019398282,0.0033987327,0.0002732553,0.000011755917],"category_scores_gemma":[0.00006179666,0.00035659433,0.00016244028,0.0008317138,0.00060900545,0.0009399891,0.0018493553,0.00051661633,0.000009541469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008982674,0.00006196935,0.00006481979,0.00003766066,0.0000121805615,0.000052245206,0.0010319966,0.023204835,0.00009299714,0.005768479,0.00013301783,0.9695308],"study_design_scores_gemma":[0.00039054936,0.00020950791,0.0010220695,0.00025955026,0.000008122151,0.00017857664,3.9647338e-7,0.966243,0.002866347,0.026541349,0.0016835245,0.0005969816],"about_ca_topic_score_codex":0.00013579387,"about_ca_topic_score_gemma":0.000033446096,"teacher_disagreement_score":0.9689338,"about_ca_system_score_codex":0.00015710268,"about_ca_system_score_gemma":0.00056011515,"threshold_uncertainty_score":0.9998886},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005322342,0.0006245543,0.99191314,0.00031088322,0.0011826855,0.00040583097,0.000009404655,0.00016226154,0.0048590135],"genre_scores_gemma":[0.47123677,0.00015301758,0.5246095,0.001660514,0.0010719314,0.00002884459,0.0000616606,0.000102065576,0.0010756617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99561155,0.000039866045,0.00074696564,0.0016898961,0.0011063087,0.0008054007],"domain_scores_gemma":[0.9972686,0.0005069607,0.00032609742,0.0016189597,0.00012098219,0.00015836202],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000983109,0.0005874311,0.00075172586,0.0011422451,0.00020507608,0.0006599508,0.0043245987,0.00037195996,0.000015281747],"category_scores_gemma":[0.000039005383,0.0005291375,0.00013258503,0.000809194,0.00044309645,0.0010109914,0.0023091678,0.0008842919,0.000036146288],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024227207,0.00007991765,0.0007093139,0.000048452104,0.0000066158736,0.00045313535,0.0003707472,0.054018512,0.00011508237,0.01359915,0.00024655377,0.9303283],"study_design_scores_gemma":[0.0020938595,0.00016698074,0.0019573637,0.0011265799,0.0000072932103,0.00009994329,1.21357e-7,0.84944886,0.0016683349,0.1330425,0.009006953,0.0013812195],"about_ca_topic_score_codex":0.0004014858,"about_ca_topic_score_gemma":0.00024496033,"teacher_disagreement_score":0.9289471,"about_ca_system_score_codex":0.00034317293,"about_ca_system_score_gemma":0.0003975129,"threshold_uncertainty_score":0.99971604},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011635473,0.00028838043,0.9954822,0.0009286505,0.0013118285,0.0009587214,0.000049328155,0.00013969331,0.00082952913],"genre_scores_gemma":[0.0011514847,0.000034777244,0.99637526,0.0017047238,0.00020318321,0.000041618277,0.00001758053,0.000040025032,0.0004313326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953411,0.00003336095,0.00042986125,0.0020329147,0.0012824853,0.00088023714],"domain_scores_gemma":[0.9968325,0.00040312248,0.00031976955,0.0018006054,0.00032780698,0.00031618107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074081455,0.00064813485,0.00054949,0.0005900034,0.0005117307,0.00051377394,0.0030173108,0.000268547,0.000013761753],"category_scores_gemma":[0.000036772668,0.0005044122,0.00013300382,0.0006220659,0.0006603038,0.00044292878,0.0012386239,0.000546163,0.000022298365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009561794,0.000085739026,0.000005016993,0.000040277504,0.000022248681,0.00013644887,0.00048511842,0.0648747,0.00013725615,0.02563481,0.0003716069,0.9081972],"study_design_scores_gemma":[0.0005792836,0.0003957233,0.0000040862033,0.00051311404,0.000013754004,0.00012298,4.0609e-7,0.9578329,0.0016400884,0.023737513,0.014387323,0.00077285635],"about_ca_topic_score_codex":0.000025395857,"about_ca_topic_score_gemma":0.000013905468,"teacher_disagreement_score":0.90742433,"about_ca_system_score_codex":0.0005340002,"about_ca_system_score_gemma":0.00074694655,"threshold_uncertainty_score":0.9997407},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053788044,0.0003898899,0.9442469,0.00043698464,0.00030139342,0.00011541973,0.0000023723462,0.000077722114,0.0006412659],"genre_scores_gemma":[0.60886395,0.00017734371,0.39035746,0.00045423655,0.000034571116,0.000034103363,0.0000033968856,0.0000056041895,0.00006930596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991642,0.000043103453,0.00017834082,0.00028049282,0.00017738786,0.00015647084],"domain_scores_gemma":[0.99894214,0.00034574172,0.00013950896,0.00034004266,0.00017093681,0.00006164024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009419401,0.00009239838,0.00010415527,0.000039064384,0.00016612449,0.00016380867,0.00032517157,0.000044505363,0.0001926101],"category_scores_gemma":[0.00049573736,0.00007490659,0.000020752577,0.00021809888,0.00007142655,0.005740998,0.0002712323,0.00009664096,0.00003106697],"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":[0.000053538093,0.0006503753,0.011268327,0.00021364489,0.00009310754,0.000032269745,0.23439342,0.0001342087,0.05028265,0.08455782,0.013349631,0.604971],"study_design_scores_gemma":[0.0025558546,0.0014288692,0.025490006,0.00074361323,0.000089279034,0.0007347002,0.06568194,0.08565506,0.10918626,0.038452175,0.6668377,0.003144526],"about_ca_topic_score_codex":0.00024188537,"about_ca_topic_score_gemma":0.0000022058139,"teacher_disagreement_score":0.6534881,"about_ca_system_score_codex":0.000012990312,"about_ca_system_score_gemma":0.00003482341,"threshold_uncertainty_score":0.41620848},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86250675,0.00017265712,0.11949875,0.0003412521,0.00011166066,0.0004631274,0.000015593743,0.00029715005,0.016593078],"genre_scores_gemma":[0.9594067,0.000008192682,0.04002769,0.00035962,0.000027011085,0.0000207742,0.000026156542,0.000007088051,0.00011680792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999188,0.000017011793,0.00021258934,0.00014486791,0.00022576175,0.00021177111],"domain_scores_gemma":[0.99954164,0.000052404353,0.000076523975,0.00027228176,0.000013739933,0.00004340343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001233742,0.0001195047,0.000119765864,0.00012492755,0.0000866022,0.0001901094,0.00022510368,0.000030728228,0.000014041188],"category_scores_gemma":[0.0000036594379,0.000083792,0.0000110019355,0.00021378302,0.000022792736,0.00086915836,0.00017735786,0.00011183398,0.000040034618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015595488,0.0016187544,0.050099466,0.0010029359,0.0001474669,0.0001754163,0.0454403,0.008351886,0.0011048284,0.7999558,0.008674065,0.08327316],"study_design_scores_gemma":[0.015205381,0.0045459615,0.25115642,0.0038999796,0.000069862326,0.000593983,0.0052828533,0.62433803,0.0037260184,0.03813955,0.049340308,0.0037016913],"about_ca_topic_score_codex":0.00033400528,"about_ca_topic_score_gemma":0.000050229035,"teacher_disagreement_score":0.7618162,"about_ca_system_score_codex":0.00003482049,"about_ca_system_score_gemma":0.000022670207,"threshold_uncertainty_score":0.34169385},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008285223,0.00037669676,0.98993325,0.00006419216,0.0007913525,0.00022494429,0.000025651505,0.00009608454,0.00020259262],"genre_scores_gemma":[0.4964353,0.0000012983302,0.50337857,0.00002140549,0.000076649565,0.000006974063,0.000037740716,0.0000058118126,0.000036229234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815977,0.000029641657,0.0006623243,0.0004127148,0.00041791805,0.000317645],"domain_scores_gemma":[0.9974328,0.0014587296,0.00031698155,0.00024427523,0.00045132494,0.00009586081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005857817,0.0001572223,0.00024843717,0.00019485776,0.00027528967,0.000048707152,0.0007831282,0.00007056534,0.00001826436],"category_scores_gemma":[0.00017648088,0.00015736616,0.0001039005,0.0004463698,0.00009376313,0.00046218117,0.00029335942,0.00014461076,0.000013808559],"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":[0.000046367393,0.0002606798,0.0024581996,0.00004982309,0.000031591113,0.000004792742,0.0015221918,0.70442975,0.00016487228,0.05598568,0.001629918,0.23341615],"study_design_scores_gemma":[0.00008695997,0.0001438308,0.003233389,0.00007145864,0.000005128103,0.00002058327,0.0003410083,0.9785797,0.0060313717,0.010549395,0.0007570047,0.00018019183],"about_ca_topic_score_codex":0.000021826341,"about_ca_topic_score_gemma":0.000002422498,"teacher_disagreement_score":0.4881501,"about_ca_system_score_codex":0.00006889078,"about_ca_system_score_gemma":0.000104961335,"threshold_uncertainty_score":0.64172053},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007078732,0.00017867186,0.9843301,0.000593745,0.002702124,0.0004173995,0.000004540101,0.00017633478,0.011526273],"genre_scores_gemma":[0.047828127,0.00011113757,0.94296265,0.004032807,0.0010633245,0.000026699314,0.000027982178,0.00006712482,0.0038801776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955295,0.000033978722,0.00050069555,0.0017555322,0.0014695942,0.0007107549],"domain_scores_gemma":[0.99697334,0.00039760242,0.00032144153,0.001870696,0.0001837515,0.0002531945],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058069115,0.00056776614,0.00046206138,0.0006634785,0.0004276063,0.0010779457,0.004044546,0.0002669833,0.00016739144],"category_scores_gemma":[0.00006603616,0.0004665818,0.000115546885,0.00039056863,0.00030114484,0.0012223236,0.0029732771,0.0007838742,0.0006206388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005384662,0.000030731855,0.000007928487,0.000019828754,0.000008932389,0.00008249885,0.00023455652,0.0071304855,0.00006624027,0.02508786,0.00050408614,0.9668215],"study_design_scores_gemma":[0.0008493395,0.0006306553,0.00014990651,0.0017221657,0.000011832599,0.000057676207,2.4867373e-7,0.65878195,0.0017823738,0.30574358,0.028679978,0.0015903348],"about_ca_topic_score_codex":0.000068786576,"about_ca_topic_score_gemma":0.0000062957115,"teacher_disagreement_score":0.9652311,"about_ca_system_score_codex":0.00040882465,"about_ca_system_score_gemma":0.00026801563,"threshold_uncertainty_score":0.99995905},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005807681,0.000048583333,0.9877551,0.0008081365,0.0002500092,0.00018426271,0.000079325386,0.00024297168,0.0048239334],"genre_scores_gemma":[0.30877328,0.00005396546,0.68865293,0.0014631102,0.000117573145,0.000019361125,0.0007538148,0.00001510192,0.00015086729],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987682,0.000012302348,0.00027403134,0.00024374119,0.00045008416,0.0002516188],"domain_scores_gemma":[0.9981694,0.000029755434,0.0001206503,0.0015229317,0.000042655956,0.00011459835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013850715,0.00014604339,0.0001410505,0.00007571678,0.0003283489,0.00043459176,0.0017286524,0.000037041442,0.000045188255],"category_scores_gemma":[0.000009882538,0.0000993696,0.00001630313,0.00023559663,0.00008540896,0.0048748567,0.0016369063,0.0001314502,0.00023831139],"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":[0.00021586311,0.0013342196,0.0056221006,0.0004066934,0.00030971773,0.00013011761,0.013853765,0.011912003,0.0008078062,0.44694856,0.09137269,0.42708647],"study_design_scores_gemma":[0.0064007062,0.0009383421,0.014612247,0.000981745,0.00004272589,0.000504744,0.0016070851,0.38618106,0.0037520898,0.0074978066,0.5761257,0.0013557514],"about_ca_topic_score_codex":0.00005427011,"about_ca_topic_score_gemma":0.000005339071,"teacher_disagreement_score":0.484753,"about_ca_system_score_codex":0.00004298165,"about_ca_system_score_gemma":0.00010251565,"threshold_uncertainty_score":0.41907784},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000147686405,0.0006551059,0.9897724,0.00019945322,0.0024112524,0.00024967195,0.000013016197,0.000277783,0.0064065782],"genre_scores_gemma":[0.10084419,0.00019601783,0.8954721,0.0011931898,0.0010831663,0.000016910282,0.000028916156,0.00006937623,0.0010961028],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963645,0.000026110081,0.00049114315,0.0015299126,0.00096547237,0.00062289863],"domain_scores_gemma":[0.99723554,0.00028614263,0.0002800973,0.0017793031,0.00021777491,0.00020117189],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046742157,0.0005182689,0.00048767217,0.0006758034,0.00042728396,0.0006065412,0.004191908,0.00028943788,0.00006752349],"category_scores_gemma":[0.000039995753,0.00045549532,0.00011620477,0.0004088165,0.0006513016,0.0011739245,0.0029673055,0.00080691883,0.000076467564],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067281926,0.000037616814,0.000049627466,0.00002703017,0.000012988408,0.00009758287,0.00055798056,0.006805926,0.00007675556,0.14339523,0.00010905611,0.8488235],"study_design_scores_gemma":[0.00036431555,0.00017605264,0.0004021846,0.0005770869,0.000009918965,0.00009160941,1.17225724e-7,0.48742443,0.0016867293,0.48992327,0.018324198,0.0010200865],"about_ca_topic_score_codex":0.00006164599,"about_ca_topic_score_gemma":0.000024477273,"teacher_disagreement_score":0.8478034,"about_ca_system_score_codex":0.00016705002,"about_ca_system_score_gemma":0.00039132914,"threshold_uncertainty_score":0.99978966},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011245983,0.0013224423,0.9939601,0.00026250322,0.0006324463,0.00032460983,0.0000042952993,0.00016070243,0.0022083267],"genre_scores_gemma":[0.18716002,0.00010336526,0.8113878,0.00066972093,0.00041748644,0.0000038199623,0.00000832004,0.00004745026,0.00020204877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99599814,0.00003427729,0.00042670907,0.0018204985,0.000976617,0.0007437406],"domain_scores_gemma":[0.9976116,0.00030024894,0.00029680552,0.0013576505,0.00018162388,0.00025207596],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005004059,0.0006166442,0.00056200405,0.00059727835,0.0004836996,0.00085155695,0.0025591026,0.0002574806,0.00001057767],"category_scores_gemma":[0.00002626355,0.0004812349,0.00006033073,0.000560166,0.00090492103,0.000559926,0.002208939,0.00068776356,0.000012958009],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008628892,0.0000260224,0.0005078826,0.000033229633,0.000013880995,0.00024290141,0.00037477823,0.022265732,0.00007007787,0.0056314482,0.00001722658,0.9708082],"study_design_scores_gemma":[0.00050639606,0.00038065622,0.0022733037,0.0007852334,0.000013029295,0.00055363594,3.418145e-7,0.9465689,0.00020424266,0.044975113,0.0027557209,0.0009834005],"about_ca_topic_score_codex":0.00005511793,"about_ca_topic_score_gemma":0.00015368595,"teacher_disagreement_score":0.9698248,"about_ca_system_score_codex":0.00014842424,"about_ca_system_score_gemma":0.00039245104,"threshold_uncertainty_score":0.9997639},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034023393,0.00027735773,0.9912761,0.00045264032,0.0015353442,0.00024434557,0.000021513786,0.00010654674,0.006052159],"genre_scores_gemma":[0.13574654,0.000070465714,0.8621599,0.00047487445,0.00050023425,0.000011895818,0.000035741985,0.000036842284,0.0009635121],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99708486,0.000019850686,0.0005154855,0.0011467753,0.00085010007,0.0003829557],"domain_scores_gemma":[0.99718153,0.00028500694,0.00030864862,0.0018132717,0.00027816725,0.00013335877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039444177,0.0003281754,0.00039874393,0.00074265496,0.00024441248,0.00021313084,0.002564015,0.0002007398,0.00007104102],"category_scores_gemma":[0.00006643375,0.00029028064,0.00013089414,0.0006678026,0.00051290507,0.0007540695,0.0015215932,0.00050348724,0.000044814515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006160227,0.00008902403,0.00009704979,0.000052940883,0.00002016245,0.00007630991,0.0006493546,0.1118219,0.00034967507,0.13193654,0.00014475797,0.75475615],"study_design_scores_gemma":[0.0006735881,0.00031711438,0.0011195734,0.00087471085,0.00002118876,0.00010948731,4.487126e-7,0.3702938,0.003159683,0.6197808,0.0027040665,0.000945525],"about_ca_topic_score_codex":0.00011492785,"about_ca_topic_score_gemma":0.00004943153,"teacher_disagreement_score":0.7538106,"about_ca_system_score_codex":0.0001876096,"about_ca_system_score_gemma":0.0007510533,"threshold_uncertainty_score":0.99995494},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009725214,0.0011774801,0.994613,0.00025600573,0.0009908687,0.00030312015,0.000008701141,0.00021383964,0.0023397265],"genre_scores_gemma":[0.04217165,0.0004197386,0.95548254,0.0008081904,0.0006507144,0.000011638591,0.000013232975,0.00004698905,0.00039530915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959195,0.00002728335,0.0004080725,0.0017270048,0.0012048149,0.00071328593],"domain_scores_gemma":[0.99713373,0.00043884292,0.0002501073,0.001733857,0.00021605386,0.0002274301],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036834713,0.00056526135,0.0005085237,0.0007265244,0.0005087147,0.00046662378,0.0037957383,0.00024644873,0.000014810531],"category_scores_gemma":[0.000039306746,0.00042951686,0.00009426775,0.0005711843,0.0007509536,0.0010343883,0.0020215134,0.00075071416,0.000041450887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009622722,0.00002895896,0.00021589462,0.000022498689,0.000010401025,0.00041961682,0.0006372534,0.018183328,0.00017592726,0.0022332494,0.00008782492,0.9779754],"study_design_scores_gemma":[0.00059586926,0.00034225849,0.00028792978,0.0006774713,0.0000068442855,0.0005831992,1.551819e-7,0.9567533,0.0027500214,0.012821769,0.023954842,0.0012263226],"about_ca_topic_score_codex":0.000044284356,"about_ca_topic_score_gemma":0.00005698389,"teacher_disagreement_score":0.9767491,"about_ca_system_score_codex":0.00019017259,"about_ca_system_score_gemma":0.00057028193,"threshold_uncertainty_score":0.99981564},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010052248,0.00072573987,0.99065536,0.0006673649,0.0010829853,0.0003510999,0.00000818776,0.000283146,0.0062160627],"genre_scores_gemma":[0.016159615,0.00011956512,0.97941774,0.0028384684,0.0007836272,0.00000437168,0.000052430212,0.00003763854,0.00058656547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958187,0.000040569077,0.00059588964,0.0017343089,0.001187123,0.00062340824],"domain_scores_gemma":[0.9973586,0.00028727145,0.00035750063,0.0014871088,0.0002977089,0.00021181953],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073486724,0.0005527159,0.00057213684,0.00086831534,0.00031592618,0.0008044738,0.0033478998,0.00032998694,0.000021582855],"category_scores_gemma":[0.00005829536,0.0004921009,0.00013226445,0.00074277754,0.00032412185,0.0010453882,0.001409796,0.00079577375,0.00010613015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002808134,0.000020152731,0.000005356428,0.000015463429,0.0000039189113,0.000078467565,0.00012880452,0.01137211,0.000047275375,0.011053433,0.00016216486,0.97711],"study_design_scores_gemma":[0.00024866348,0.00017406346,0.0001937581,0.0005297078,0.000005951622,0.00007603388,3.2236446e-8,0.76850593,0.00023456193,0.2225571,0.0068339566,0.0006402683],"about_ca_topic_score_codex":0.000012962587,"about_ca_topic_score_gemma":0.00000721977,"teacher_disagreement_score":0.97646976,"about_ca_system_score_codex":0.0002564809,"about_ca_system_score_gemma":0.0003619376,"threshold_uncertainty_score":0.99975306},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002214806,0.00019396901,0.9953751,0.00034034607,0.001539086,0.00025180524,0.000018617939,0.000096429045,0.0019631537],"genre_scores_gemma":[0.119982585,0.000054652715,0.8790746,0.00024248274,0.00019162823,0.000005426302,0.000018243694,0.000027100128,0.00040332339],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968873,0.000019410207,0.000531763,0.0012460947,0.00089615356,0.00041926609],"domain_scores_gemma":[0.9967703,0.0003806867,0.00038522598,0.002055694,0.00026794017,0.00014012463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052957534,0.0003561163,0.00044083793,0.000719594,0.00021181331,0.00025740138,0.0037106676,0.0002979095,0.00003884776],"category_scores_gemma":[0.000085842155,0.00031352628,0.00011934276,0.0005147524,0.0006125438,0.0007262826,0.0021521675,0.0009015543,0.000020991087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042178403,0.000042714844,0.000065300126,0.000039008515,0.000010191221,0.00005392762,0.00045411036,0.0033516432,0.0029134252,0.020796265,0.000018693692,0.9722505],"study_design_scores_gemma":[0.000365405,0.00016535909,0.0012626172,0.00042634562,0.000011205809,0.00008809092,1.8766674e-7,0.7535131,0.0066977874,0.23470448,0.0020407245,0.0007246982],"about_ca_topic_score_codex":0.000074209165,"about_ca_topic_score_gemma":0.00010677212,"teacher_disagreement_score":0.9715258,"about_ca_system_score_codex":0.00009749607,"about_ca_system_score_gemma":0.00043379233,"threshold_uncertainty_score":0.9999317},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004084582,0.0014821659,0.92142653,0.00019348867,0.000024365374,0.0007681947,0.00011701579,0.00003994857,0.07553985],"genre_scores_gemma":[0.3058862,0.016643612,0.5161551,0.00033387396,0.00055542827,0.0015152474,0.0003751728,0.00033437,0.15820095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894446,0.000009850559,0.00038494417,0.0003416566,0.00016863707,0.00015044025],"domain_scores_gemma":[0.99861276,0.00037087794,0.00034497285,0.00049422245,0.00012274459,0.000054436274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016004912,0.0002206542,0.00032478108,0.00013646537,0.00029046365,0.00014890663,0.0003866394,0.00010265182,0.000010807163],"category_scores_gemma":[0.000008604306,0.00015910901,0.000033451437,0.00012264673,0.00013536446,0.00017196321,0.00029356038,0.00022127181,0.0000038432827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.126864e-7,0.000037112462,0.000016446787,0.00010352883,0.000025434267,0.0000015055069,0.0007108937,0.000033419623,0.000012785842,0.97955436,0.000053215397,0.019450383],"study_design_scores_gemma":[0.0002043138,0.000051712577,0.00002828611,0.00053736835,0.00005424645,0.000102562095,0.00027229474,0.81936,0.000012985997,0.16388041,0.015195974,0.00029983505],"about_ca_topic_score_codex":0.000013906051,"about_ca_topic_score_gemma":0.00012385554,"teacher_disagreement_score":0.8193266,"about_ca_system_score_codex":0.000030816413,"about_ca_system_score_gemma":0.000037631056,"threshold_uncertainty_score":0.64882773},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08582632,0.0011782526,0.90868944,0.0004911428,0.00058533996,0.00018194468,0.0000036591657,0.00018079668,0.0028631054],"genre_scores_gemma":[0.9461587,0.00042787715,0.052500088,0.0007928303,0.000042068732,0.000031493844,0.0000049495297,0.000008378006,0.000033598655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986337,0.00008734836,0.00025166516,0.0005475318,0.00024732834,0.0002324526],"domain_scores_gemma":[0.99897045,0.00028506565,0.000214406,0.00026189102,0.000116563424,0.00015159923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020603476,0.00018356803,0.00015983233,0.000077652614,0.00042236812,0.00026942947,0.00034966617,0.000065442655,0.000015922502],"category_scores_gemma":[0.00014561125,0.00016142668,0.000023871466,0.00019396229,0.00013149645,0.0025307904,0.00027000986,0.00021405058,0.000030414334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010874656,0.00031448842,0.000987927,0.000040148938,0.000025688125,0.00017982027,0.047085535,0.00007424238,0.00019633019,0.29429844,0.00087973225,0.6558089],"study_design_scores_gemma":[0.0031388327,0.0019775422,0.030673526,0.00048205542,0.000067545625,0.00095953344,0.012369052,0.862791,0.0008480441,0.043760713,0.041079037,0.0018531169],"about_ca_topic_score_codex":0.0000610665,"about_ca_topic_score_gemma":7.4075194e-7,"teacher_disagreement_score":0.86271673,"about_ca_system_score_codex":0.000011023609,"about_ca_system_score_gemma":0.000041489504,"threshold_uncertainty_score":0.65827894},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011408312,0.00016025137,0.9843849,0.0005473735,0.00028460962,0.00014530173,0.0000028842207,0.000062577215,0.0030037912],"genre_scores_gemma":[0.6275359,0.000022508508,0.3723002,0.00007378537,0.00004854284,0.0000017796826,4.6542362e-7,0.000005477079,0.000011367289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978029,0.000038774702,0.00044513377,0.00043309724,0.00078816223,0.0004919073],"domain_scores_gemma":[0.99735874,0.0010554474,0.00015762378,0.0010267679,0.00018857703,0.00021282103],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0030537178,0.00017142108,0.0002184258,0.00009471894,0.0007179811,0.0005631249,0.0023415058,0.000043037275,0.0000074417817],"category_scores_gemma":[0.00017318179,0.00009656117,0.000054585336,0.00065589667,0.0040104976,0.000524231,0.0020131983,0.00015026258,0.000006321297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000352509,0.00002760233,0.00002016569,0.00001600785,0.0000035302064,0.0000039991455,0.0008345912,0.0000024054118,0.00035083236,0.9787834,0.000040483694,0.019913448],"study_design_scores_gemma":[0.0001436988,0.00013052493,0.00047881398,0.000076665,0.000006268642,0.000045648703,0.00009599343,0.48801324,0.005961356,0.5042251,0.0006290926,0.00019365572],"about_ca_topic_score_codex":0.0000027949188,"about_ca_topic_score_gemma":0.000001292387,"teacher_disagreement_score":0.61612755,"about_ca_system_score_codex":0.00001442354,"about_ca_system_score_gemma":0.000055145174,"threshold_uncertainty_score":0.9987},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000065771937,0.0009070011,0.5542098,0.000085610125,0.0013272468,0.00021001339,0.000038012673,0.00018724821,0.44302845],"genre_scores_gemma":[0.00007572193,0.002511401,0.43036634,0.0001404192,0.0015426241,0.00001838411,0.00015266641,0.00012867214,0.5650638],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967719,0.000048211095,0.000792033,0.0009852049,0.0009937232,0.00040892954],"domain_scores_gemma":[0.99666286,0.00017853556,0.00072428887,0.002028572,0.00017492282,0.00023083527],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041655477,0.0005801569,0.0007922439,0.00028805432,0.00016173377,0.000090958354,0.0021912016,0.0005126885,0.00021443421],"category_scores_gemma":[0.000027172924,0.0005081668,0.0002854786,0.000071238384,0.00010736292,0.00044328143,0.0014576877,0.0005961513,0.000219158],"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":[0.000011484049,0.000053263324,0.0000027577764,0.00019387255,0.00006869607,0.00010191905,0.00055554294,0.00008776753,0.00025591627,0.30913535,0.043855846,0.64567757],"study_design_scores_gemma":[0.00033652852,0.00013060751,0.000015102345,0.0008120504,0.000028954631,0.000028906135,0.0000053623776,0.004709099,0.0004845686,0.09899413,0.89373106,0.0007236095],"about_ca_topic_score_codex":0.00002374792,"about_ca_topic_score_gemma":0.0000011615149,"teacher_disagreement_score":0.8498752,"about_ca_system_score_codex":0.00005145533,"about_ca_system_score_gemma":0.00013123798,"threshold_uncertainty_score":0.99973696},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026898151,0.00003417255,0.9701074,0.00011269548,0.0012253717,0.024766104,0.000008791739,0.00012471084,0.00093098555],"genre_scores_gemma":[0.008734163,0.000016200345,0.9640256,0.0003590554,0.0004357724,0.026346805,0.000015282447,0.000027130907,0.0000399748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985158,0.00003934846,0.0005186416,0.0001864441,0.00037988342,0.00035987582],"domain_scores_gemma":[0.99845797,0.00005539249,0.0002142154,0.0011053,0.00008003764,0.00008706762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005154781,0.00018304675,0.00016428676,0.000110816996,0.00020330763,0.00037638022,0.0017138888,0.00007776708,0.0000193986],"category_scores_gemma":[0.00007255715,0.00011353344,0.000058545498,0.0005011167,0.00008903657,0.0013415285,0.0008307133,0.00055512635,0.000052975898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013976126,0.0003714653,0.0028136591,0.00045881842,0.000012640923,0.0000061857804,0.0025047318,0.0005927552,0.0021551307,0.05532779,0.0049881777,0.93075466],"study_design_scores_gemma":[0.00032300735,0.000025137082,0.00052924897,0.00016806362,0.000001907374,0.000027348766,0.00003153408,0.89806885,0.0007535558,0.0011779774,0.098689474,0.00020390168],"about_ca_topic_score_codex":0.0000067053543,"about_ca_topic_score_gemma":0.000005571057,"teacher_disagreement_score":0.93055075,"about_ca_system_score_codex":0.000030111787,"about_ca_system_score_gemma":0.00013040387,"threshold_uncertainty_score":0.46297592},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009582807,0.0044100387,0.45607585,0.000024159996,0.00018707423,0.00011521715,0.000010120235,0.0001370397,0.5390309],"genre_scores_gemma":[0.0064223493,0.0038323542,0.8721391,0.00068596256,0.0004624153,0.000020331952,0.0024189854,0.00009244737,0.11392608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872005,0.000008506055,0.0005323985,0.0003206729,0.00019198102,0.00022640575],"domain_scores_gemma":[0.998892,0.00006194766,0.00036503878,0.00045823952,0.00014010447,0.00008267477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046153867,0.00022911151,0.00023459956,0.00040449965,0.00020740359,0.00032282417,0.00074770214,0.00017339247,0.000010226283],"category_scores_gemma":[0.0000650301,0.00021971969,0.000016842821,0.00012027418,0.0000399685,0.0072487644,0.0011924559,0.00042792602,0.000054062613],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043772843,0.000003886189,0.0000060457032,0.00013609426,0.0000020352522,0.0000021733142,0.0011568331,0.000025768206,0.0000018338292,0.008312009,0.00012305289,0.9902259],"study_design_scores_gemma":[0.00032335357,0.000019831741,0.000019671616,0.0008914441,0.0000035446,0.00001418896,0.00010896383,0.28303,0.000009420996,0.0010784684,0.7142216,0.00027952297],"about_ca_topic_score_codex":0.0000011075633,"about_ca_topic_score_gemma":0.000013370996,"teacher_disagreement_score":0.98994637,"about_ca_system_score_codex":0.000046436613,"about_ca_system_score_gemma":0.00016013901,"threshold_uncertainty_score":0.8959909},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000149686,0.00045733288,0.20572235,0.000023242403,0.000514226,0.00048457115,0.000116485186,0.00034958363,0.7923307],"genre_scores_gemma":[0.000021586438,0.0010699058,0.011375472,0.00010178469,0.00020476068,0.0000015133992,0.0000678751,0.000038450664,0.98711866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977453,0.00010356966,0.00031708734,0.00091691216,0.00054006313,0.000377069],"domain_scores_gemma":[0.99748635,0.00020739729,0.0003654389,0.0014612005,0.00020697403,0.00027264355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020893391,0.0005187317,0.00094869407,0.00025669084,0.0003588202,0.000116660485,0.0021729034,0.0004262701,0.0000046132177],"category_scores_gemma":[0.000014295991,0.000519868,0.00050539844,0.000014394098,0.0004085502,0.00036242398,0.0018672355,0.0005774768,0.000058135065],"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":[0.0009132691,0.000009485609,2.3930877e-8,0.000018818493,0.00012014916,0.00080318295,0.000047600013,0.000002561322,0.0000024423996,0.8747632,0.11413346,0.009185828],"study_design_scores_gemma":[0.02849985,0.000026358506,5.0184235e-7,0.000120763,0.000082107625,0.00009049783,0.0000019505683,0.0086014345,0.000071416776,0.000037279624,0.9618777,0.00059013756],"about_ca_topic_score_codex":0.00013058091,"about_ca_topic_score_gemma":2.5398498e-7,"teacher_disagreement_score":0.8747259,"about_ca_system_score_codex":0.00013512024,"about_ca_system_score_gemma":0.00017971358,"threshold_uncertainty_score":0.9997253},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8726038,0.0065208636,0.117733315,0.00047478586,0.00037958007,0.00036649508,0.000015198169,0.0000693767,0.0018366142],"genre_scores_gemma":[0.98826945,0.0019462645,0.008886234,0.0007082832,0.00010663677,0.000011201246,0.0000066573193,0.000017691018,0.000047599915],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973674,0.00020703985,0.00067547994,0.0005990281,0.00069701596,0.00045404758],"domain_scores_gemma":[0.99814403,0.00015518928,0.00060525845,0.0007608634,0.000121254496,0.00021340238],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009919478,0.00029580382,0.0005758693,0.0006243049,0.00026218226,0.0029870523,0.0058521517,0.0000752297,0.0005910451],"category_scores_gemma":[0.00003213093,0.00022789156,0.00008096548,0.0009268691,0.00007119385,0.006098068,0.001187363,0.0004189114,0.000013507685],"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":[0.00019690882,0.00075323,0.32556045,0.000091771006,0.00012895218,0.0008548313,0.0018800668,0.0037216386,0.12697154,0.0016354064,0.01007769,0.5281275],"study_design_scores_gemma":[0.0008229713,0.00004558358,0.9303772,0.0009615898,0.000015892776,0.00008758118,0.00006329594,0.0049426206,0.0073263356,0.05218953,0.0024974258,0.00067001244],"about_ca_topic_score_codex":0.001732094,"about_ca_topic_score_gemma":0.00013116395,"teacher_disagreement_score":0.60481673,"about_ca_system_score_codex":0.00011492397,"about_ca_system_score_gemma":0.00019494398,"threshold_uncertainty_score":0.9995267},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017417498,0.0008273408,0.99137,0.0014027626,0.0011449079,0.00042558447,0.0000129407,0.00010745398,0.004691584],"genre_scores_gemma":[0.039735224,0.00012337668,0.95350695,0.0051548746,0.00071834575,0.000031266678,0.000024377407,0.000054980697,0.00065063144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951284,0.0000693277,0.00058813696,0.0016376099,0.0017739722,0.00080258935],"domain_scores_gemma":[0.99632645,0.00064945564,0.00024668514,0.0023604769,0.00022773238,0.00018922017],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0020865733,0.00058003917,0.0005280163,0.00069262553,0.00023788809,0.00078149687,0.007749975,0.00033421422,0.000008742977],"category_scores_gemma":[0.00012867647,0.00039885545,0.00011619338,0.00085259683,0.0006816493,0.0010523184,0.0014316243,0.0013044243,0.000049563976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050941653,0.0000510818,0.000021982783,0.000014814586,0.00000440777,0.00017537686,0.0018837096,0.18363649,0.000020368578,0.016924815,0.0006631678,0.7965987],"study_design_scores_gemma":[0.00021668174,0.00005894977,0.000031422303,0.0001945687,0.000003059948,0.000052863197,3.8427734e-7,0.76197815,0.00006050343,0.23370093,0.0032707804,0.0004317224],"about_ca_topic_score_codex":0.000048191832,"about_ca_topic_score_gemma":0.00007441211,"teacher_disagreement_score":0.79616696,"about_ca_system_score_codex":0.0002855075,"about_ca_system_score_gemma":0.00079398864,"threshold_uncertainty_score":0.99984634},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016672786,0.00044822815,0.9662165,0.0006759786,0.00021472,0.00009210818,0.0000041230705,0.00025490142,0.015420646],"genre_scores_gemma":[0.94771904,0.00009487791,0.050616026,0.00055824866,0.00007061917,0.000003792644,0.0000032232258,0.00000582234,0.0009283533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920017,0.000033585613,0.00010318468,0.00030206158,0.00017149221,0.00018953257],"domain_scores_gemma":[0.9993932,0.000037511076,0.000030180261,0.00041426133,0.000021452246,0.000103342616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009650835,0.00009235065,0.00010212554,0.000050326307,0.00018341544,0.00023847073,0.00044607048,0.000029533521,0.0003992934],"category_scores_gemma":[0.000010397618,0.000071168135,0.00003067502,0.00013495985,0.00006302624,0.00052967365,0.00035290583,0.00008620819,0.00008522843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013386858,0.0001519083,0.003269038,0.000015395695,0.000016684107,0.000029371062,0.00081694877,0.0000048084016,0.0009012139,0.7555223,0.046609133,0.19266187],"study_design_scores_gemma":[0.00092404796,0.00020376568,0.025151495,0.0000310281,0.000008376441,0.00013721327,0.000036827016,0.8397043,0.000688441,0.06765497,0.06491459,0.00054498145],"about_ca_topic_score_codex":0.000083958585,"about_ca_topic_score_gemma":0.0000064443648,"teacher_disagreement_score":0.93104625,"about_ca_system_score_codex":0.000008016534,"about_ca_system_score_gemma":0.000003406014,"threshold_uncertainty_score":0.43719825},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018508557,0.00028673466,0.92709726,0.036638394,0.00032143123,0.0010332683,0.00015653028,0.00022809741,0.015729718],"genre_scores_gemma":[0.8981952,0.000004777996,0.099883676,0.0014671376,0.00016499612,0.00008576165,0.0000054131833,0.000019694384,0.0001733173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986498,0.00007448094,0.00022962,0.00021505315,0.00043926577,0.0003917782],"domain_scores_gemma":[0.9978472,0.0006470766,0.00016343246,0.0011054561,0.000051081923,0.00018574213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034263442,0.0001571484,0.0002596929,0.000039727107,0.00018408181,0.00018182742,0.0014731986,0.000023390876,0.000016578186],"category_scores_gemma":[0.00023830519,0.00007463391,0.000069532114,0.0005786741,0.00023222259,0.0002624645,0.00072137965,0.00013175748,0.00007145781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006935618,0.0013371148,0.002553904,0.00020964214,0.00023215613,0.000020006632,0.03446758,0.00029689,0.0009504444,0.71690524,0.09898363,0.14397407],"study_design_scores_gemma":[0.0011593525,0.0014584031,0.07314856,0.0007679565,0.00015580158,0.00011784219,0.007308772,0.31159487,0.0019375852,0.065033995,0.5355173,0.0017995721],"about_ca_topic_score_codex":0.000098051794,"about_ca_topic_score_gemma":0.000029651961,"teacher_disagreement_score":0.87968665,"about_ca_system_score_codex":0.000016200609,"about_ca_system_score_gemma":0.000018226452,"threshold_uncertainty_score":0.30434823},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021460304,0.0003846052,0.9947651,0.00012438088,0.0008314894,0.00069569435,0.0000234497,0.0001193255,0.0030344664],"genre_scores_gemma":[0.033069856,0.000020668103,0.96579933,0.00037579588,0.00034467323,0.00004875228,0.000029530287,0.00003693052,0.00027443303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621993,0.000025928164,0.0004942306,0.0018343376,0.0006851183,0.0007404817],"domain_scores_gemma":[0.99755085,0.00036060959,0.00027515236,0.0014907115,0.0001583554,0.00016434374],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084196916,0.00052738393,0.0005735634,0.00078617415,0.00020525236,0.00042921034,0.004223601,0.00031950904,0.000009700848],"category_scores_gemma":[0.00008074515,0.00044706924,0.00013554348,0.00048511062,0.0004020336,0.0007565327,0.0020501057,0.0006449029,0.00000943825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017730206,0.00008173447,0.00011839302,0.00009778254,0.00000661436,0.000040795538,0.0006017423,0.003644278,0.000018582974,0.05778606,0.000113715585,0.9374726],"study_design_scores_gemma":[0.00047614236,0.00021625422,0.0003078066,0.00031122743,0.000005096956,0.000032155724,1.7652232e-7,0.86191314,0.00021222251,0.13114671,0.0046651955,0.0007138458],"about_ca_topic_score_codex":0.00009530116,"about_ca_topic_score_gemma":0.000066975546,"teacher_disagreement_score":0.9367587,"about_ca_system_score_codex":0.00020204409,"about_ca_system_score_gemma":0.0003406506,"threshold_uncertainty_score":0.9997981},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60043603,0.00012581478,0.39762086,0.00065193616,0.000076687094,0.0003315761,0.000016574651,0.00007001316,0.0006705067],"genre_scores_gemma":[0.9787078,0.000048030786,0.02107706,0.000018064522,0.0000451994,0.000028849498,0.000024654919,0.000008974695,0.000041380397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695814,0.0007885911,0.00029460608,0.0004190402,0.0009867575,0.0005528397],"domain_scores_gemma":[0.99723554,0.0014674917,0.00006749698,0.00085672847,0.00024365072,0.00012911095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004222885,0.00010816222,0.00020109204,0.00034761667,0.00014534083,0.00014733041,0.0012681547,0.00007997188,0.000013140593],"category_scores_gemma":[0.0010056498,0.00009396571,0.000039743583,0.00094025576,0.00011698249,0.0015172166,0.0009149321,0.00030217826,0.00005546541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020407615,0.0017062154,0.24491066,0.00058143766,0.000020148571,0.000066499524,0.007884931,0.0009411201,0.08396784,0.20132884,0.0025656668,0.45582256],"study_design_scores_gemma":[0.0013334791,0.0004774115,0.12478525,0.0002963798,0.0000014372223,0.000004486242,0.00018796159,0.75063354,0.08692282,0.032298427,0.002734106,0.00032469077],"about_ca_topic_score_codex":0.0007902312,"about_ca_topic_score_gemma":0.001196388,"teacher_disagreement_score":0.74969244,"about_ca_system_score_codex":0.000062370695,"about_ca_system_score_gemma":0.0001499201,"threshold_uncertainty_score":0.38318107},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011076478,0.000012092572,0.98525417,0.001032006,0.00043945567,0.00019035958,0.0000023981925,0.00021300938,0.0017800201],"genre_scores_gemma":[0.5655341,8.517425e-7,0.4339766,0.00031692442,0.00014533527,0.000010637847,9.163564e-7,0.00000625801,0.0000083576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777085,0.00006534742,0.00018023534,0.0007576666,0.00065471296,0.0005712123],"domain_scores_gemma":[0.9981872,0.000315434,0.0000694089,0.00095432525,0.00022666935,0.0002470017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001343437,0.00018862858,0.00022012078,0.00012299903,0.0006253521,0.00067669555,0.0022885299,0.000046003952,0.000004290329],"category_scores_gemma":[0.00007522884,0.00012762196,0.000044590626,0.0006534213,0.0019584156,0.0010473025,0.0010625053,0.00013921665,0.0000083707855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001116115,0.000019821538,0.00006014248,0.0000073425335,0.0000020115492,0.0000014449298,0.0001668765,0.0001965172,0.00011692983,0.8948182,0.00007470358,0.10452488],"study_design_scores_gemma":[0.0003620817,0.0004568212,0.0005739342,0.000058620644,0.000003723129,0.000029341818,0.000012583092,0.8660874,0.0030578629,0.12649135,0.002597908,0.0002684161],"about_ca_topic_score_codex":0.000005267127,"about_ca_topic_score_gemma":9.28049e-7,"teacher_disagreement_score":0.86589086,"about_ca_system_score_codex":0.000032237545,"about_ca_system_score_gemma":0.00012066812,"threshold_uncertainty_score":0.7215864},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012706672,0.00002325369,0.98403823,0.000055333985,0.00016188844,0.00008896536,6.6401657e-7,0.000140259,0.002784748],"genre_scores_gemma":[0.90225035,0.0000068841064,0.097569175,0.0001247919,0.000011986066,0.0000055265223,0.000018443321,0.0000017077147,0.00001110528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994743,0.000027218592,0.00018526713,0.00008430855,0.000136023,0.00009291395],"domain_scores_gemma":[0.99968666,0.0000260788,0.000102749385,0.000060316397,0.000084316795,0.0000398976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001944419,0.000059789563,0.000050415234,0.00008101902,0.0001923338,0.0004115827,0.00007700154,0.000026870779,0.0000026219732],"category_scores_gemma":[0.000049629605,0.000055852826,0.000010711517,0.0001977474,0.0000068881404,0.0028027943,0.000038596572,0.000060356357,0.000015128284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018928691,0.000018647052,0.0012042165,0.0000452079,0.000006021415,3.263847e-7,0.0020683806,0.022737253,0.000065812696,0.2949246,0.0005534595,0.6783742],"study_design_scores_gemma":[0.00025984365,0.000029826582,0.003166568,0.00002235265,0.0000014608207,0.000024292405,0.00006321479,0.96980345,0.00017267719,0.008047234,0.018304346,0.00010473627],"about_ca_topic_score_codex":0.00001663589,"about_ca_topic_score_gemma":0.000001226853,"teacher_disagreement_score":0.9470662,"about_ca_system_score_codex":0.00001954578,"about_ca_system_score_gemma":0.000022760118,"threshold_uncertainty_score":0.39689016},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011084764,0.0005476378,0.98196274,0.000025157125,0.0005691184,0.0006680499,0.015013313,0.000060905968,0.000044578042],"genre_scores_gemma":[0.008668174,0.00004512839,0.979298,0.000114529816,0.00008027116,0.00007087379,0.011681956,0.00003096976,0.000010080329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744546,0.00015263328,0.00066849845,0.0010253467,0.0001835088,0.00052457204],"domain_scores_gemma":[0.99609345,0.0001504393,0.00047445015,0.0028654644,0.00026086613,0.00015532889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008489378,0.00027621863,0.0005499246,0.00017288046,0.00012429,0.000018308534,0.0034650334,0.00023319226,0.000018886027],"category_scores_gemma":[0.00009244171,0.00023773802,0.00013140694,0.0002248623,0.00014528412,0.0006397581,0.0016876495,0.000105181105,0.0000020095017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009039929,0.0007622934,0.00004454578,0.00008333278,0.00014510992,0.000010276958,0.00021906878,0.000002733669,0.06492332,0.021335227,0.0024360234,0.9099477],"study_design_scores_gemma":[0.0026506686,0.0018881388,0.00016732594,0.000071536066,0.00007714093,0.000024764862,0.000047023546,0.7614823,0.17651053,0.018568393,0.038000453,0.0005117165],"about_ca_topic_score_codex":0.0001805842,"about_ca_topic_score_gemma":0.000010477367,"teacher_disagreement_score":0.9094359,"about_ca_system_score_codex":0.00001440164,"about_ca_system_score_gemma":0.00011921055,"threshold_uncertainty_score":0.9694675},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07683435,0.00020587127,0.86895466,0.04223305,0.00084133726,0.00054159295,0.000005933726,0.00003778808,0.010345389],"genre_scores_gemma":[0.73640794,0.0001986664,0.25497216,0.0006233585,0.001666261,0.000049115424,0.0000011614808,0.00004626933,0.006035074],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976211,0.00025110107,0.00040209363,0.00012518393,0.001299218,0.00030128585],"domain_scores_gemma":[0.9967514,0.0017432716,0.00019549594,0.0006340529,0.00052488694,0.00015088671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030338129,0.00009052556,0.00017211853,0.0002447836,0.00033923358,0.0004540585,0.0015830365,0.000060859336,0.00035172646],"category_scores_gemma":[0.00068269495,0.000047127574,0.000106719854,0.0003940673,0.00007998748,0.0005019788,0.0004346219,0.000801638,0.00065473496],"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":[0.000015050538,0.0009151364,0.0000460057,0.0000532491,0.00008299309,0.00003792414,0.002413819,0.00016347336,0.007175015,0.023859194,0.85452944,0.11070868],"study_design_scores_gemma":[0.0017347537,0.0019286498,0.002676985,0.0008452827,0.000031540494,0.00066044426,0.0028148775,0.754461,0.012465051,0.0986453,0.1231674,0.00056873856],"about_ca_topic_score_codex":0.000023027891,"about_ca_topic_score_gemma":0.0000010333662,"teacher_disagreement_score":0.7542975,"about_ca_system_score_codex":0.0000719051,"about_ca_system_score_gemma":0.00014655301,"threshold_uncertainty_score":0.8415512},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15035205,0.00010613904,0.84791124,0.00041659642,0.0010661643,0.000057298643,0.0000122799165,0.000007582127,0.00007066717],"genre_scores_gemma":[0.721284,0.00002225384,0.27850708,0.000028374288,0.0001421278,0.0000011784537,0.0000061262904,0.000002134432,0.0000067571145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99783593,0.00004228171,0.00054671156,0.00016566718,0.0012002337,0.00020916354],"domain_scores_gemma":[0.9974689,0.000111708134,0.0008229267,0.00031286164,0.0011473062,0.00013629317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010058547,0.00010473476,0.00017943062,0.00026477847,0.00011225072,0.00017445216,0.0021506017,0.00002112213,0.000016135242],"category_scores_gemma":[0.00003928787,0.0000773872,0.000070477465,0.00054732116,0.00033393467,0.003292928,0.00040129034,0.00009334416,0.000003950994],"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":[0.00048291936,0.0036948815,0.077870265,0.000069292764,0.0007396796,0.00008025663,0.0051890705,0.1445089,0.034168176,0.36830446,0.0044406494,0.36045143],"study_design_scores_gemma":[0.005425061,0.0026429463,0.5384434,0.0020362413,0.00013919674,0.0020152975,0.0002698444,0.32992667,0.07733704,0.015002862,0.02530452,0.0014569112],"about_ca_topic_score_codex":0.00002750315,"about_ca_topic_score_gemma":7.187442e-7,"teacher_disagreement_score":0.5709319,"about_ca_system_score_codex":0.00015453032,"about_ca_system_score_gemma":0.0004089162,"threshold_uncertainty_score":0.3996389},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832196,0.00010584806,0.008128562,0.00051314867,0.00060987554,0.00020829862,0.000030309473,0.000073360236,0.0071110004],"genre_scores_gemma":[0.3675319,0.00014879162,0.6301528,0.00014171266,0.0011446852,0.00003177289,0.000030373398,0.000056867462,0.0007610839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988241,1.3937644e-8,0.00028114498,0.00024478606,0.00044111212,0.0002088247],"domain_scores_gemma":[0.9993003,0.00002702278,0.00015371702,0.00005898055,0.00039274624,0.00006720831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016200625,0.00015442485,0.00016238732,0.00006044063,0.0000706515,0.000116755946,0.00070249115,0.000091360744,0.00008048606],"category_scores_gemma":[0.000044277265,0.00012677052,0.00020091985,0.00017580399,0.000057447538,0.00042426397,0.00022259551,0.00012786737,0.000008552283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017782297,0.000051290688,0.000032889686,0.00006932163,0.00009580984,1.9003745e-7,0.00004986636,0.0001013816,0.43710965,0.55049914,0.010151956,0.0018207135],"study_design_scores_gemma":[0.0010136797,0.00022052131,0.00052640855,0.00035867697,0.000111561414,0.00007115197,0.00007784068,0.8130411,0.06680409,0.0057452167,0.1114536,0.0005761835],"about_ca_topic_score_codex":0.0000025142288,"about_ca_topic_score_gemma":4.621493e-8,"teacher_disagreement_score":0.8129397,"about_ca_system_score_codex":0.00009303598,"about_ca_system_score_gemma":0.000020235162,"threshold_uncertainty_score":0.5169552},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57533586,0.01736832,0.38384765,0.020898174,0.0012226375,0.00025197602,0.00006251226,0.000020463765,0.0009924029],"genre_scores_gemma":[0.9773354,0.0058547854,0.016657911,0.00009664223,0.000020631867,0.0000012447263,0.0000024443214,0.0000029966948,0.00002793098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991681,0.00008128564,0.00037082215,0.00006551128,0.00023080743,0.000083471255],"domain_scores_gemma":[0.99812174,0.00017038162,0.0005256184,0.0006010603,0.00054475147,0.000036441357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021308688,0.000058708672,0.000121144345,0.000058784968,0.00012883922,0.000022705744,0.0026639234,0.000022755901,0.000008757665],"category_scores_gemma":[0.00007633533,0.000041106105,0.00007227753,0.0001355133,0.0001593073,0.00029956337,0.0006370686,0.00018505607,6.652093e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003996665,0.00036699625,0.0077213505,0.0000064828896,0.00020337089,0.0000046611035,0.000622162,0.00032547093,0.0147313215,0.9647368,0.0016770501,0.009564371],"study_design_scores_gemma":[0.003502169,0.0010170211,0.14158021,0.00055984466,0.000107785774,0.0016631015,0.0001726168,0.57375157,0.05501609,0.08774455,0.13433345,0.0005515774],"about_ca_topic_score_codex":0.000034489105,"about_ca_topic_score_gemma":0.0000075491407,"teacher_disagreement_score":0.8769922,"about_ca_system_score_codex":0.000025552123,"about_ca_system_score_gemma":0.00026996777,"threshold_uncertainty_score":0.4950277},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027874341,0.00053414423,0.9682585,0.0011092175,0.00036739281,0.00030283435,0.000010974235,0.0003321292,0.0012104381],"genre_scores_gemma":[0.04457775,0.000380965,0.94722813,0.0062953904,0.00015770968,0.00011799327,0.000010044899,0.00001937316,0.0012126698],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982154,0.000067572815,0.00023482404,0.0006660324,0.00043483305,0.000381363],"domain_scores_gemma":[0.99864775,0.00017551471,0.00007770425,0.0007023753,0.00010126481,0.00029536735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018895292,0.00019396671,0.00016161083,0.0000587654,0.00038843526,0.00036103182,0.0007514493,0.00006663323,0.0002239274],"category_scores_gemma":[0.00015883124,0.00016402497,0.000029184785,0.00031958145,0.0000502838,0.0032749998,0.00054014777,0.00017083023,0.00024096321],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020251395,0.00008946554,0.000069668014,0.0000041964636,0.0000050169665,0.00002949442,0.0038322618,0.000011146795,0.0006028863,0.00014384503,0.0019606994,0.99323106],"study_design_scores_gemma":[0.00066566817,0.00036621754,0.0013010739,0.00010447935,0.000010616096,0.00013761537,0.0009044345,0.018726349,0.0044831997,0.0006206019,0.9720453,0.0006344693],"about_ca_topic_score_codex":0.00021824068,"about_ca_topic_score_gemma":8.5735724e-7,"teacher_disagreement_score":0.9925966,"about_ca_system_score_codex":0.000023486737,"about_ca_system_score_gemma":0.00003596673,"threshold_uncertainty_score":0.6688744},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15489282,0.0019306537,0.83875257,0.000003978191,0.0016068812,0.00015596686,0.00014236028,0.00004598844,0.002468786],"genre_scores_gemma":[0.9980935,0.00004655065,0.0016978204,0.000007546699,0.000085918095,0.000006290296,0.000049977298,0.0000013477401,0.000011062507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999351,0.000028447119,0.00033181199,0.000063055566,0.00013086926,0.00009480254],"domain_scores_gemma":[0.9992582,0.000049260063,0.00022519408,0.00027338602,0.00013763309,0.000056314093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023802624,0.00006662902,0.00013552951,0.00007612772,0.00006423347,0.00003815247,0.00017253085,0.000033260756,0.0000028359323],"category_scores_gemma":[0.000030500905,0.000052628486,0.000018975841,0.00011726038,0.0000308405,0.005503072,0.00015717912,0.00004258985,0.000034477976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047513222,0.00025551947,0.032974686,0.0014493878,0.00008330744,4.7874875e-7,0.07268022,0.00005446666,0.057009146,0.08382105,0.002933645,0.7486906],"study_design_scores_gemma":[0.00091188593,0.00016164471,0.037796803,0.00064804003,0.000025585068,0.000019599362,0.0018367482,0.42178378,0.060195755,0.00008112916,0.47607198,0.00046707081],"about_ca_topic_score_codex":0.00025176318,"about_ca_topic_score_gemma":0.000004623627,"teacher_disagreement_score":0.8432007,"about_ca_system_score_codex":0.000012887698,"about_ca_system_score_gemma":0.00002388659,"threshold_uncertainty_score":0.39895943},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015523161,0.00004712106,0.985248,0.00015915361,0.00023469536,0.00020473143,0.0000027750498,0.00028870188,0.013659587],"genre_scores_gemma":[0.08142995,0.000009084544,0.9168441,0.0013050213,0.000022616503,0.000054937533,0.000035029752,0.000007534042,0.0002916971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867207,0.000028700026,0.00035499586,0.00019609577,0.0004618576,0.00028628626],"domain_scores_gemma":[0.9992136,0.00001392626,0.00019704502,0.00038379713,0.00011215595,0.0000794831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038703458,0.0001509642,0.00010958817,0.00022235172,0.0003502201,0.0010331195,0.00053399475,0.00004140626,0.000025690413],"category_scores_gemma":[0.000014790316,0.00013788801,0.0000386567,0.00047169745,0.000023911469,0.0046112523,0.00017377792,0.00009905601,0.00015721312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018204172,0.000027662054,0.0000091634165,0.00008637738,0.0000065562504,0.0000044922713,0.00034330314,0.0021595014,0.000002647096,0.015575444,0.0012290061,0.98055404],"study_design_scores_gemma":[0.0005388582,0.000023558638,0.00023016306,0.00008889313,0.0000070233637,0.000005652603,0.00012687613,0.8058408,0.00045664085,0.00047682814,0.19199786,0.0002068834],"about_ca_topic_score_codex":0.000004527163,"about_ca_topic_score_gemma":1.073681e-7,"teacher_disagreement_score":0.98034716,"about_ca_system_score_codex":0.000063502965,"about_ca_system_score_gemma":0.00006659489,"threshold_uncertainty_score":0.99623954},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82509315,0.00004555101,0.16936247,0.00015012111,0.000116195726,0.0002032266,0.000058855974,0.00008473262,0.0048856875],"genre_scores_gemma":[0.8654032,0.000028587836,0.13376072,0.00019242625,0.00011149927,0.00033123887,0.00007159417,0.000059680333,0.000041061492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976259,0.000025890737,0.0006284946,0.00056113856,0.00065246556,0.00050612487],"domain_scores_gemma":[0.99786115,0.00030530358,0.0003949066,0.0012106278,0.000042776745,0.00018526775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004804965,0.0003160785,0.00028605238,0.00006852263,0.0002642086,0.0003891096,0.0011180687,0.00020681707,0.000019243773],"category_scores_gemma":[0.00008154762,0.00026348047,0.00013848412,0.00029831662,0.00017645933,0.00042146473,0.0014160721,0.00031692084,0.0002972971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020984253,0.00015113121,0.000011924805,0.0003224986,0.00004199434,0.0000072891207,0.0022121235,0.00018206835,0.0004470972,0.9935363,0.0005989271,0.0024676882],"study_design_scores_gemma":[0.0004295101,0.000074282674,0.00027858734,0.0001789366,0.000045980556,0.00005036397,0.0010561345,0.9873739,0.0011178114,0.008377027,0.00070856133,0.00030890558],"about_ca_topic_score_codex":0.00029433233,"about_ca_topic_score_gemma":0.000031884076,"teacher_disagreement_score":0.98719186,"about_ca_system_score_codex":0.000011308085,"about_ca_system_score_gemma":0.00007528801,"threshold_uncertainty_score":0.99998176},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28359276,0.0018837258,0.7087188,0.00010056915,0.0026320985,0.000049478145,0.0000019023514,0.0000348233,0.0029858889],"genre_scores_gemma":[0.9908955,0.000038142167,0.008820507,0.000052375057,0.00014199705,4.2828127e-8,0.0000010027445,0.000011120019,0.000039287683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9979926,0.0007988987,0.00048160736,0.00009748042,0.00034995787,0.00027948408],"domain_scores_gemma":[0.99886817,0.0001796426,0.00034953994,0.00027809173,0.0001732072,0.0001513257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044765742,0.00010507721,0.00019708474,0.00018173689,0.000069266425,0.00012563274,0.0009755665,0.000017126913,0.0000025472082],"category_scores_gemma":[0.0001926678,0.000090480404,0.000049698974,0.0004205534,0.000021725995,0.0009707418,0.00043743613,0.00030489473,0.0000120409295],"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":[0.0000688017,0.0016970228,0.4180209,0.00007939035,0.000076725635,0.0010665493,0.0072582318,0.00056532637,0.00028866704,0.4414792,0.019287512,0.11011165],"study_design_scores_gemma":[0.0014803746,0.00028308417,0.976354,0.00022471166,0.000005068311,0.0002830673,0.00010334124,0.0037827077,0.0002191611,0.0031908776,0.01377695,0.00029664853],"about_ca_topic_score_codex":0.0000066311827,"about_ca_topic_score_gemma":3.6023619e-7,"teacher_disagreement_score":0.70730275,"about_ca_system_score_codex":0.00005056332,"about_ca_system_score_gemma":0.000040405164,"threshold_uncertainty_score":0.3689684},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59507334,0.00010523138,0.40437794,0.0001872531,0.0000875937,0.00013193786,0.000016610007,0.000005276769,0.000014828081],"genre_scores_gemma":[0.88942194,0.00009936594,0.110315226,0.000059528797,0.00007226569,0.0000017307664,0.000019963352,0.000003644093,0.0000063436523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987049,0.00007969889,0.00059678947,0.00016414643,0.00025480348,0.00019967389],"domain_scores_gemma":[0.9983015,0.00040687522,0.0003791535,0.00055828446,0.00029017625,0.000063979416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011955353,0.000117331205,0.0003701653,0.00019656094,0.00032446405,0.00012989895,0.0015858435,0.00002166515,0.00001759824],"category_scores_gemma":[0.00001907889,0.00007437687,0.00004988764,0.00047319275,0.000062480474,0.0020371045,0.0011118901,0.00013978317,0.0000014884711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024698258,0.0005014239,0.052504208,0.00044294898,0.0043753544,0.000004000535,0.043285362,0.28519,0.019137219,0.0024754219,0.008641234,0.58319587],"study_design_scores_gemma":[0.0004357237,0.00017526766,0.05720627,0.000062780055,0.00018730789,0.000029163784,0.00063209207,0.9402232,0.00068513985,0.0000318087,0.00024312093,0.00008811924],"about_ca_topic_score_codex":0.00013817409,"about_ca_topic_score_gemma":0.000011676056,"teacher_disagreement_score":0.65503323,"about_ca_system_score_codex":0.000018401663,"about_ca_system_score_gemma":0.00004785993,"threshold_uncertainty_score":0.30330008},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00985623,0.00028241432,0.9776972,0.006302881,0.0001811005,0.00033523518,0.0001572837,0.00030657792,0.004881106],"genre_scores_gemma":[0.7836423,0.00037574302,0.21210319,0.00061276875,0.0005945004,0.00017749789,0.00034666978,0.00007190985,0.0020754295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808186,0.00005911068,0.0002356122,0.00071657385,0.0004944511,0.0004124082],"domain_scores_gemma":[0.99876463,0.000058411206,0.00007020712,0.0008416095,0.000114186754,0.00015096582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014494229,0.0002513077,0.00019355158,0.00015015794,0.000550797,0.00048137832,0.00060429715,0.00007097473,0.000016788583],"category_scores_gemma":[0.000002175865,0.00018374117,0.00004391236,0.00030949237,0.000175047,0.00080566044,0.00034367404,0.00020423163,0.00007591466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110225876,0.00049607654,0.0017708432,0.000051603824,0.00011500166,0.00006687103,0.0009129713,0.010707068,0.010952212,0.88734776,0.007409977,0.08005938],"study_design_scores_gemma":[0.002477215,0.001107288,0.050017945,0.00014993035,0.00006210169,0.0003112735,0.0003031932,0.854056,0.008321501,0.013265647,0.06822626,0.0017016671],"about_ca_topic_score_codex":0.00031481936,"about_ca_topic_score_gemma":0.000014611991,"teacher_disagreement_score":0.87408215,"about_ca_system_score_codex":0.000041685,"about_ca_system_score_gemma":0.000059508755,"threshold_uncertainty_score":0.74927473},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05481348,0.0011820667,0.93950576,0.00023491228,0.00050337706,0.00015071443,0.0000024865355,0.00041194103,0.003195288],"genre_scores_gemma":[0.49955082,0.00023380977,0.49931985,0.00073825434,0.00004545762,0.0000270949,0.0000018696687,0.0000080100135,0.000074842515],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987667,0.000074177115,0.00017290936,0.00046606798,0.00026769575,0.0002524224],"domain_scores_gemma":[0.99886256,0.00017457573,0.00012983449,0.00058177556,0.00009665135,0.00015460802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017138798,0.00014700256,0.00013516934,0.00004572657,0.00030417703,0.00016922492,0.0006497341,0.00006027653,0.000050130573],"category_scores_gemma":[0.0003124904,0.000115889816,0.00002405853,0.00016670974,0.00009716869,0.0038610448,0.0006702886,0.00015368838,0.000051886476],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019288156,0.0005922225,0.014132027,0.000047473302,0.000033153483,0.00021328004,0.1008982,0.0000050972394,0.0024780412,0.018423928,0.0032186646,0.85976505],"study_design_scores_gemma":[0.0040135556,0.0018993085,0.056629907,0.000939251,0.000121796584,0.002640169,0.02722101,0.048967574,0.04874219,0.03564085,0.7687597,0.0044246814],"about_ca_topic_score_codex":0.00019371259,"about_ca_topic_score_gemma":0.0000018027217,"teacher_disagreement_score":0.85534036,"about_ca_system_score_codex":0.000009027314,"about_ca_system_score_gemma":0.000033765602,"threshold_uncertainty_score":0.47258496},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019312441,0.000012171773,0.9369527,0.002198917,0.00012650911,0.000034458626,0.0000010322154,0.00009637073,0.041265395],"genre_scores_gemma":[0.9615519,0.0000010489736,0.034884237,0.0015485925,0.00008286446,0.0000034649308,0.000003203151,0.0000029410521,0.0019217313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99962455,0.000015416854,0.000050489904,0.000108074084,0.000117381314,0.000084116],"domain_scores_gemma":[0.9995381,0.00008669266,0.000013809668,0.0003422424,0.0000075248786,0.000011616124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009390674,0.000037879447,0.000027520377,0.000012090041,0.000106921994,0.000115098315,0.00046344477,0.000010486178,0.000060608894],"category_scores_gemma":[0.0000027516828,0.000018406066,0.000014585776,0.0000697924,0.0000069262674,0.00014577576,0.00014216406,0.000045373727,0.00017554691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6730137e-7,0.000010373331,0.000012830639,2.2869902e-7,3.829006e-7,0.000001784822,0.000013276006,0.00007983371,0.00010511617,0.94773954,0.04789888,0.0041374806],"study_design_scores_gemma":[0.0001520768,0.000037360904,0.006532829,0.000016419468,9.617175e-7,0.000009516722,0.000016871581,0.15814674,0.0032507996,0.7851252,0.04653554,0.00017570319],"about_ca_topic_score_codex":0.0001904014,"about_ca_topic_score_gemma":0.00000811873,"teacher_disagreement_score":0.94223946,"about_ca_system_score_codex":0.000004423212,"about_ca_system_score_gemma":0.000005159677,"threshold_uncertainty_score":0.2256359},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01903833,0.000017940574,0.97853506,0.00039347477,0.0001345519,0.00010184188,4.5722842e-7,0.00005399322,0.0017243737],"genre_scores_gemma":[0.4536893,0.0000038585003,0.5459118,0.00013996914,0.00001819586,0.000006583224,9.617273e-7,0.000002102447,0.00022720793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994565,0.000014689752,0.00014092826,0.00015163513,0.00013708623,0.00009914294],"domain_scores_gemma":[0.9995147,0.000054379187,0.0000386541,0.00026053886,0.00007449864,0.00005720312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010215312,0.000045402176,0.00007050481,0.0000733268,0.00003939948,0.000066365574,0.0003183061,0.000018188399,0.00006229043],"category_scores_gemma":[0.000031195974,0.00003562407,0.000016740169,0.00020989176,0.0000058029964,0.00047008804,0.00018695855,0.000031586056,0.00014089375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012004982,0.000038226925,0.00022435606,0.000011323845,0.0000047514927,0.0000010411653,0.00061175285,0.0017404372,0.012105557,0.040058114,0.0027888862,0.94241434],"study_design_scores_gemma":[0.00008970611,0.000050230305,0.0026659435,0.000034359276,0.0000010772874,0.0000017405042,0.00007182391,0.98651457,0.0062852995,0.002202952,0.002001044,0.00008123432],"about_ca_topic_score_codex":0.00046823788,"about_ca_topic_score_gemma":0.0000051718844,"teacher_disagreement_score":0.9847742,"about_ca_system_score_codex":0.000007759741,"about_ca_system_score_gemma":0.000011894365,"threshold_uncertainty_score":0.18109511},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008593925,0.005780282,0.8507362,0.13779055,0.0005584867,0.0011320797,0.0013054843,0.00010607234,0.0017314453],"genre_scores_gemma":[0.54136163,0.0029307974,0.44599405,0.0042576906,0.00036321572,0.00009930902,0.0021058249,0.000041512307,0.0028459851],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980019,0.00028485537,0.0005718021,0.0004944854,0.00026709022,0.0003798703],"domain_scores_gemma":[0.99267805,0.0005151259,0.00041688266,0.005746619,0.00051920756,0.00012414511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007913697,0.00020954787,0.00030521647,0.00014092258,0.00053322606,0.00015252955,0.004768517,0.00015170114,0.00003854907],"category_scores_gemma":[0.00040902948,0.00021567849,0.00011341839,0.00046115628,0.00013761493,0.0012708114,0.0009963101,0.00033708924,0.000042052616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007726555,0.0020671203,0.0000026270327,0.00006549783,0.00006445528,7.9142006e-7,0.0004830649,0.003025045,0.0006880585,0.22887808,0.14042763,0.6242204],"study_design_scores_gemma":[0.0004384079,0.0009175576,0.0012127678,0.00033814536,0.000024445328,0.00000431411,0.00003263645,0.6704535,0.0021310193,0.030384302,0.29380292,0.00026000236],"about_ca_topic_score_codex":0.0003274668,"about_ca_topic_score_gemma":0.000050927592,"teacher_disagreement_score":0.66742843,"about_ca_system_score_codex":0.000015964064,"about_ca_system_score_gemma":0.00015987715,"threshold_uncertainty_score":0.88611704},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112514734,0.000031285916,0.8832625,0.0010243992,0.0026849497,0.000063568536,0.0000030281014,0.000015482834,0.00040003288],"genre_scores_gemma":[0.59533596,0.000015942924,0.40402183,0.00015980877,0.00045038227,4.341942e-7,0.0000036971041,0.0000036814863,0.00000828047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709755,0.00005760751,0.00091533136,0.0002821381,0.0013833822,0.00026398964],"domain_scores_gemma":[0.9966513,0.0004109125,0.0008567189,0.000360146,0.0015885588,0.00013234891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028599205,0.00011664294,0.0001890674,0.0010736068,0.00012576375,0.00044779514,0.0032005063,0.000038105554,0.000009237876],"category_scores_gemma":[0.00037309792,0.000108005836,0.00008769823,0.00083199836,0.00023596219,0.005255622,0.0007332998,0.00021434543,0.000013425705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018846676,0.0009805824,0.0006588613,0.0000062509757,0.0000993355,0.0003381194,0.0019498536,0.018846404,0.06553912,0.018631175,0.0026509946,0.89011085],"study_design_scores_gemma":[0.0035897703,0.00069698336,0.019515024,0.00048128242,0.000026399091,0.0012263488,0.0001287938,0.8899685,0.037515778,0.0047974084,0.04138098,0.000672689],"about_ca_topic_score_codex":0.00006360294,"about_ca_topic_score_gemma":0.0000048499082,"teacher_disagreement_score":0.88943815,"about_ca_system_score_codex":0.00021947216,"about_ca_system_score_gemma":0.0005657742,"threshold_uncertainty_score":0.594739},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008075523,0.00036861503,0.9850438,0.0006820436,0.0011581866,0.00020440508,0.000024547238,0.00036679962,0.004076037],"genre_scores_gemma":[0.6952435,0.000008352711,0.3035261,0.0003579762,0.0004409746,0.000045388595,0.000026766866,0.000016060036,0.0003349261],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822104,0.000086194865,0.00026817952,0.0004225496,0.00043043465,0.000571613],"domain_scores_gemma":[0.9982771,0.00014990235,0.000101143094,0.001093574,0.00009196372,0.000286275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002740744,0.00017652668,0.00016698557,0.00010285344,0.00027651747,0.00014481675,0.0010611762,0.0000679394,0.00008029395],"category_scores_gemma":[0.000051861076,0.00015412325,0.00007746761,0.00045703916,0.00006765857,0.00055194227,0.0006095032,0.00017658227,0.0004504621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002380693,0.0019189132,0.0019354759,0.00005530307,0.00013955822,0.00009803516,0.004524322,0.007493769,0.027470123,0.28078333,0.045233738,0.63032365],"study_design_scores_gemma":[0.00048027624,0.000044557535,0.0059343977,0.000029426788,0.000014169637,0.000094523566,0.000058398473,0.9443334,0.009760491,0.0016536816,0.0371241,0.00047259513],"about_ca_topic_score_codex":0.0000735282,"about_ca_topic_score_gemma":4.4081196e-7,"teacher_disagreement_score":0.93683964,"about_ca_system_score_codex":0.000045817993,"about_ca_system_score_gemma":0.000047386784,"threshold_uncertainty_score":0.62849635},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03654871,0.5120419,0.43068066,0.012602496,0.0016452961,0.0019107653,0.00032097969,0.00035995906,0.0038891877],"genre_scores_gemma":[0.036554452,0.36307427,0.59247255,0.0069726724,0.00043176842,0.000017741108,0.0002554609,0.000039556497,0.00018156199],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868554,0.00007499541,0.0003373525,0.00046851553,0.00022267099,0.00021095423],"domain_scores_gemma":[0.9972909,0.00016342016,0.0001355854,0.002286402,0.000038394104,0.00008527297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034722232,0.0001378363,0.00029249853,0.00007323057,0.000040497765,0.000053359894,0.0022995186,0.000052512973,0.000062872205],"category_scores_gemma":[0.00025811512,0.00010669354,0.000025396468,0.00032409147,0.00003965849,0.001013035,0.0021893997,0.00013401265,0.000007360633],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004047424,0.00003483792,0.0018191922,0.00030513082,0.000006455383,0.000029886938,0.00008713329,0.0000013209199,0.00019573333,0.00043969924,0.037684083,0.9593925],"study_design_scores_gemma":[0.0014908296,0.00021956756,0.03360058,0.0053724824,0.000024686973,0.00023236703,0.00006481441,0.024362898,0.0007386042,0.015840644,0.9172823,0.0007702546],"about_ca_topic_score_codex":0.0005812189,"about_ca_topic_score_gemma":0.000039062936,"teacher_disagreement_score":0.9586222,"about_ca_system_score_codex":0.000010962488,"about_ca_system_score_gemma":0.000048630198,"threshold_uncertainty_score":0.43508363},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039641038,0.00002317098,0.95811224,0.0013385925,0.00030082438,0.00013069686,0.000028004215,0.00026569102,0.00015976887],"genre_scores_gemma":[0.227552,0.000012488427,0.77212393,0.00013073438,0.00007094787,0.000016041646,0.0000028616848,0.0000131074585,0.000077863675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987757,0.000026940448,0.00014622418,0.0004959015,0.00028269042,0.0002725249],"domain_scores_gemma":[0.9984087,0.000269565,0.000056363602,0.0009799044,0.00010853659,0.00017693888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017504174,0.0001868661,0.00015987534,0.000121452846,0.0005242343,0.00030376416,0.00067933643,0.0000811489,0.000036222133],"category_scores_gemma":[0.000060179937,0.00014306157,0.000030074616,0.00043795267,0.00013058668,0.0006543243,0.000040957744,0.00048794303,0.000019264184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015306881,0.00016987008,0.00053457177,0.0000116951705,0.000022882117,0.000023717548,0.00033925212,0.00020635518,0.003296402,0.0011501036,0.00006333245,0.9941665],"study_design_scores_gemma":[0.0038241353,0.0019837725,0.06756431,0.00021269958,0.00009393203,0.0013258327,0.00037082558,0.84083575,0.030900689,0.0065832767,0.044251718,0.0020530778],"about_ca_topic_score_codex":0.00031035094,"about_ca_topic_score_gemma":0.00008371931,"teacher_disagreement_score":0.9921134,"about_ca_system_score_codex":0.000011224534,"about_ca_system_score_gemma":0.00006940203,"threshold_uncertainty_score":0.58338815},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016093338,0.00013545777,0.9958677,0.0008610297,0.00019811706,0.00052608846,0.000063876,0.0003250101,0.00041336264],"genre_scores_gemma":[0.32888067,0.000107978805,0.66938925,0.00068140717,0.00011961067,0.00023656513,0.000023722185,0.000032457723,0.0005283624],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981673,0.000029188499,0.0002834296,0.00068587414,0.00041086902,0.00042337793],"domain_scores_gemma":[0.99811435,0.00027244142,0.000069607624,0.0010558652,0.00010061301,0.0003871014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002934815,0.0002500488,0.00020285488,0.0002942,0.0007601408,0.00020269249,0.000736518,0.00009881325,0.00002200085],"category_scores_gemma":[0.0000135085465,0.0002089819,0.000044920343,0.00077616435,0.00007860581,0.0008448109,0.000063947395,0.00028547837,0.000037660822],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006698267,0.0003366775,0.00033843564,0.00001479561,0.00005210418,0.000018987519,0.00065715855,0.0018309448,0.0008252467,0.0014409065,0.0002761323,0.99414164],"study_design_scores_gemma":[0.010220899,0.0042353226,0.12718481,0.0007662281,0.00030715333,0.0013614596,0.0016554429,0.16723824,0.059439216,0.009770387,0.61270225,0.0051186047],"about_ca_topic_score_codex":0.00024417334,"about_ca_topic_score_gemma":0.00024112282,"teacher_disagreement_score":0.98902303,"about_ca_system_score_codex":0.00007350184,"about_ca_system_score_gemma":0.00007264358,"threshold_uncertainty_score":0.8522035},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08810658,0.00006727284,0.9097724,0.0003617901,0.0005562043,0.00011363183,0.0000010342636,0.00017533904,0.00084577035],"genre_scores_gemma":[0.58623326,0.0000010803964,0.41302034,0.0005379919,0.00018948082,0.0000041152557,6.9652356e-7,0.000004447323,0.000008596128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976952,0.00007896228,0.00020144004,0.0005105595,0.00074149494,0.0007723193],"domain_scores_gemma":[0.99834216,0.00013581512,0.000068805784,0.0008543293,0.00015529168,0.00044357943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009595938,0.00017514592,0.00016930852,0.00009419239,0.00052623847,0.00047340733,0.0018559237,0.00003480888,0.00003262364],"category_scores_gemma":[0.00003818954,0.000112510264,0.000032835724,0.00065766624,0.0011517062,0.0018514307,0.0013127167,0.00016927846,0.00007896845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048325724,0.00007216443,0.00048008983,0.0000029441671,0.000002785722,0.0000063436255,0.0002984771,0.00011571557,0.003333998,0.93429846,0.000105348205,0.061278857],"study_design_scores_gemma":[0.0003564657,0.00026196172,0.004191547,0.00004550683,0.0000044153044,0.00015813866,0.000011420429,0.9787627,0.012064718,0.0031246226,0.0006474094,0.0003711231],"about_ca_topic_score_codex":0.000004507545,"about_ca_topic_score_gemma":2.3042341e-7,"teacher_disagreement_score":0.97864693,"about_ca_system_score_codex":0.000040066265,"about_ca_system_score_gemma":0.00007425308,"threshold_uncertainty_score":0.45880353},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05022053,0.0004913533,0.9474423,0.00009289877,0.00079885643,0.0005591408,0.000036303984,0.00010163095,0.00025699384],"genre_scores_gemma":[0.9060241,0.0000033131269,0.0935621,0.00003485138,0.00025168376,0.000009542418,0.000031396274,0.00001326418,0.0000697413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983643,0.000245875,0.00042633235,0.00044344718,0.00022981515,0.0002901995],"domain_scores_gemma":[0.99748725,0.0006392183,0.00024948482,0.0014565098,0.00010504345,0.000062499625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012053126,0.00015647881,0.00034730806,0.000107846376,0.00009052629,0.00011281882,0.0020628937,0.00007220943,0.0000033638116],"category_scores_gemma":[0.000096736985,0.00012682771,0.000039580704,0.00017170764,0.000050183484,0.0005519494,0.00080272905,0.0001180921,0.000008746792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057018315,0.00014407153,0.001051667,0.0007350829,0.00006983699,0.0000060620587,0.004487226,0.06751255,0.0033722236,0.85370797,0.0097753415,0.05908095],"study_design_scores_gemma":[0.00041956498,0.000036348523,0.0009234732,0.00021193956,0.0000034092718,0.000008597105,0.00014634244,0.97522604,0.00020045904,0.022055153,0.0006109291,0.00015773991],"about_ca_topic_score_codex":0.00055179524,"about_ca_topic_score_gemma":0.000004585577,"teacher_disagreement_score":0.9077135,"about_ca_system_score_codex":0.000021102365,"about_ca_system_score_gemma":0.000050878145,"threshold_uncertainty_score":0.5171884},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1723386,0.0030381626,0.7909803,0.026296133,0.0022672273,0.00041430665,0.000022162309,0.0008840429,0.0037590987],"genre_scores_gemma":[0.5481615,0.0006516399,0.44336373,0.0024661603,0.00069003436,0.00002918897,0.000055180124,0.000040917308,0.0045416397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856716,0.00007373536,0.0002060045,0.00052786624,0.0003099783,0.00031525808],"domain_scores_gemma":[0.9983505,0.00015392948,0.00008894404,0.0012477736,0.00004962731,0.000109200104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002476942,0.00014487431,0.00015418346,0.000053849315,0.00034616108,0.0000712036,0.0013754454,0.000065616696,0.00015194855],"category_scores_gemma":[0.0002465446,0.00012788459,0.000047326837,0.00018782831,0.0000426761,0.00017018443,0.0010463682,0.00018641916,0.00040106347],"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":[0.000007044086,0.000057083667,0.00038164528,0.00000495324,0.0000063573452,0.000063447944,0.0005224087,0.000050177317,0.0029249778,0.00038105712,0.90804064,0.08756018],"study_design_scores_gemma":[0.00030498294,0.00006249337,0.0003863887,0.00004133175,0.0000023717039,0.0000851799,0.000017991415,0.0035600306,0.007364856,0.00026912385,0.98768073,0.00022451619],"about_ca_topic_score_codex":0.00014417604,"about_ca_topic_score_gemma":5.6115414e-7,"teacher_disagreement_score":0.3758229,"about_ca_system_score_codex":0.000035338096,"about_ca_system_score_gemma":0.000028306142,"threshold_uncertainty_score":0.52149826},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008042973,0.38956064,0.60853136,0.000033055683,0.0004242393,0.00032173534,0.000050519688,0.00004678317,0.0010236474],"genre_scores_gemma":[0.0000124149765,0.8195707,0.17968795,0.000007737845,0.00013413398,0.000001975777,0.00006954404,0.00001660707,0.00049890985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795717,0.00021721494,0.00047969635,0.0006296829,0.00042888333,0.00028735705],"domain_scores_gemma":[0.9968958,0.00017100533,0.0014355131,0.0010891345,0.00025383694,0.00015470767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003797966,0.00036048747,0.0017357134,0.0005018602,0.00017682713,0.00008651624,0.0039562243,0.00031399677,0.00010765906],"category_scores_gemma":[0.000025067655,0.00035405828,0.0005361752,0.00077200873,0.00026188252,0.0013952915,0.0012808064,0.0003215756,0.000024904048],"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":[0.0000026480925,0.000055382952,0.000008688434,0.0030191748,0.00009221764,0.000011396803,0.00006404397,0.000003456053,0.0000023450348,0.0012462357,0.0015485693,0.99394584],"study_design_scores_gemma":[0.00033034838,0.000057182482,0.00001770463,0.00411896,0.00023041607,0.000059908594,0.00005703968,0.0017531499,0.000010461152,0.00011999018,0.99288124,0.00036357154],"about_ca_topic_score_codex":0.0005915336,"about_ca_topic_score_gemma":0.000029266374,"teacher_disagreement_score":0.99358225,"about_ca_system_score_codex":0.000068606474,"about_ca_system_score_gemma":0.0003176693,"threshold_uncertainty_score":0.99989116},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52341807,0.0003317952,0.33234814,0.0016653487,0.00050742156,0.0001729757,0.000004466619,0.0011158547,0.14043595],"genre_scores_gemma":[0.68337494,0.00006769018,0.30554157,0.00042255438,0.00012013603,0.0000043923287,0.000005868143,0.00000778909,0.010455066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994433,0.000014617342,0.00008418028,0.00020541895,0.000116630465,0.00013588405],"domain_scores_gemma":[0.99947494,0.000015864998,0.000011638234,0.00043829755,0.000009416828,0.000049821952],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000038093436,0.00006121269,0.000057194484,0.00002974798,0.0000941916,0.00008965887,0.0005280186,0.000022960146,0.000944773],"category_scores_gemma":[0.000002499396,0.0000448783,0.00001921357,0.0001341467,0.000012163493,0.00047265703,0.00014573749,0.00004639585,0.0001815749],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043617,0.000021541648,0.000112751826,0.0000018408593,0.0000031989114,0.000027966998,0.00009446902,0.00031474294,0.0007396842,0.008393467,0.007853122,0.98243284],"study_design_scores_gemma":[0.00077547715,0.00015954969,0.0678292,0.000039030525,0.0000032416976,0.00008105592,0.00002284088,0.6038841,0.004774131,0.015186708,0.3067273,0.0005173885],"about_ca_topic_score_codex":0.00007022454,"about_ca_topic_score_gemma":0.0000051480743,"teacher_disagreement_score":0.9819155,"about_ca_system_score_codex":0.000005873151,"about_ca_system_score_gemma":0.000013356163,"threshold_uncertainty_score":0.99996847},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017695688,0.0002727616,0.99468935,0.001758614,0.0004929065,0.00023374196,0.00020785723,0.00015799196,0.00041719485],"genre_scores_gemma":[0.06822116,0.00006894538,0.9300114,0.0005536076,0.00076208723,0.000027730965,0.00018302308,0.00002473815,0.00014733995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985499,0.0000565526,0.00018277165,0.0006910337,0.00022849378,0.00029124808],"domain_scores_gemma":[0.99790865,0.0003008703,0.00008802805,0.0015239423,0.000058458285,0.00012006515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002636933,0.00019916939,0.00022302472,0.00006547219,0.0002483789,0.00017868684,0.0013663871,0.00008276122,0.000008427835],"category_scores_gemma":[0.00015420787,0.0001550738,0.000032852215,0.00011786225,0.00008415651,0.0006939604,0.000611172,0.00012805797,0.000009840715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032206128,0.000072531446,0.00022259007,0.00004343861,0.00004148911,0.0000065417757,0.00039804747,0.000036348836,0.0009103566,0.23352565,0.018549453,0.74616134],"study_design_scores_gemma":[0.0014335087,0.00061311026,0.004856109,0.000069693204,0.000025889962,0.00002935051,0.000040793544,0.728922,0.0029961546,0.08864537,0.17170995,0.00065806403],"about_ca_topic_score_codex":0.00009233281,"about_ca_topic_score_gemma":0.00002946962,"teacher_disagreement_score":0.7455033,"about_ca_system_score_codex":0.000011130807,"about_ca_system_score_gemma":0.000032011765,"threshold_uncertainty_score":0.63237256},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0513492,0.00017348111,0.9458547,0.0005699067,0.00089534785,0.00007265118,0.00001838411,0.000044367716,0.0010219302],"genre_scores_gemma":[0.91491735,0.000042392563,0.08332622,0.00031348737,0.0011158322,0.0000022782792,0.0000071279796,0.000026148939,0.00024917244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997981,0.0000715776,0.0006130886,0.00026619254,0.0007333579,0.00033479312],"domain_scores_gemma":[0.99859977,0.00009788775,0.00059245137,0.0004313198,0.00013696906,0.00014159786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000425768,0.00021451643,0.00031119402,0.00023536467,0.00015257063,0.00033055755,0.0011872246,0.00007620685,0.000016253465],"category_scores_gemma":[0.000013987843,0.0001565897,0.00018002547,0.00022592735,0.00003329165,0.0012563647,0.0003035369,0.00043425275,0.000023846405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026399397,0.00024735136,0.0006938689,0.000025263884,0.0000510724,0.00084849464,0.00047024887,0.0024600094,0.0017116921,0.0023311945,0.00473163,0.98640275],"study_design_scores_gemma":[0.011637809,0.006871285,0.14042409,0.0034165997,0.00019204448,0.0043479977,0.0007101905,0.62594193,0.04375725,0.098087855,0.060579695,0.0040332526],"about_ca_topic_score_codex":0.000105247374,"about_ca_topic_score_gemma":0.0000031177917,"teacher_disagreement_score":0.98236954,"about_ca_system_score_codex":0.000063370644,"about_ca_system_score_gemma":0.000055252425,"threshold_uncertainty_score":0.6385543},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055953927,0.000053763593,0.94220525,0.0003415271,0.00062637,0.00018589874,0.000002560322,0.00013644545,0.00049426896],"genre_scores_gemma":[0.58222663,0.0000026408757,0.41730988,0.00031295035,0.00013216872,0.0000030202264,6.8558353e-7,0.0000045494517,0.0000074881636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784076,0.00002695037,0.00023437881,0.000724851,0.0004973995,0.0006756825],"domain_scores_gemma":[0.99847806,0.00041218672,0.00005126259,0.00057357317,0.00017367206,0.0003112525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023693503,0.0001681062,0.00017900298,0.00016066847,0.00058389554,0.00062447716,0.0016088652,0.0000597811,0.0000102357835],"category_scores_gemma":[0.00007121933,0.00012906302,0.000045865152,0.00065570156,0.0017539539,0.00087233895,0.0011659589,0.00014401364,0.000009061354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030393188,0.000041433814,0.000045372715,0.0000052052524,0.0000024649369,0.000008041648,0.00016988991,0.000038948863,0.00059566204,0.9013503,0.00014539769,0.09756687],"study_design_scores_gemma":[0.00060599786,0.0006197638,0.0019622939,0.000029545927,0.000004913131,0.00008241127,0.000004050008,0.91044116,0.0063582603,0.07727003,0.0022830027,0.00033855307],"about_ca_topic_score_codex":0.000002326927,"about_ca_topic_score_gemma":4.3765812e-7,"teacher_disagreement_score":0.91040224,"about_ca_system_score_codex":0.00003169372,"about_ca_system_score_gemma":0.00008935645,"threshold_uncertainty_score":0.6462516},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13463968,0.00008187368,0.8647225,0.00017860834,0.00018368963,0.000036128287,0.000007869589,0.000002157351,0.00014749044],"genre_scores_gemma":[0.9032946,0.000039160663,0.096522,0.00007317871,0.000051163275,2.6756516e-7,0.000012504694,0.0000013107132,0.000005785118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918467,0.000028793973,0.00055206165,0.000039710947,0.00013020005,0.00006457884],"domain_scores_gemma":[0.9986913,0.000084497544,0.00086798397,0.00009405576,0.00024292473,0.000019209205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019376268,0.000053640688,0.00015064761,0.00006330055,0.000043268028,0.000017186409,0.0003181719,0.00004008028,0.0000014965422],"category_scores_gemma":[0.000011458261,0.000031752214,0.000050291714,0.0001347227,0.00007806774,0.00023322031,0.00013835609,0.00006507678,1.921313e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009323607,0.0003850738,0.021107977,0.00019356541,0.00014283371,0.0000034948685,0.0009816139,0.075742446,0.017218541,0.55126464,0.0007831182,0.33208343],"study_design_scores_gemma":[0.00029990962,0.00014457093,0.083895765,0.000053814816,0.0000064563537,0.00006618031,0.000011224617,0.8969101,0.00046987407,0.017727977,0.0003631263,0.00005103229],"about_ca_topic_score_codex":0.0000040697014,"about_ca_topic_score_gemma":5.83978e-7,"teacher_disagreement_score":0.82116765,"about_ca_system_score_codex":0.000005420426,"about_ca_system_score_gemma":0.000050061506,"threshold_uncertainty_score":0.12948178},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064251445,0.000025919933,0.93220204,0.00028977226,0.00032139444,0.00008279265,0.0000013516388,0.00012540785,0.0026999011],"genre_scores_gemma":[0.71987194,0.00000814847,0.27994406,0.000110799876,0.00005215423,0.0000018591376,4.4050415e-7,0.0000033863519,0.0000072227317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805236,0.000044332253,0.00025852202,0.00054612645,0.0006652388,0.00043344888],"domain_scores_gemma":[0.9985137,0.000090469395,0.00007881759,0.00095011166,0.00016309465,0.00020382006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008949214,0.00013394981,0.00019004561,0.00014946006,0.00024719982,0.0002262535,0.002872232,0.00003589827,0.000051229807],"category_scores_gemma":[0.00003774165,0.00010166451,0.000051452374,0.0011193571,0.0017959006,0.00087510847,0.0018024478,0.00012291569,0.000025535355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004394512,0.00004598685,0.0001073828,0.000004194594,0.0000012867802,0.000009336063,0.00017288819,0.000052603737,0.0010223781,0.8886875,0.000027217184,0.10986482],"study_design_scores_gemma":[0.00019792287,0.00014832015,0.002067257,0.000033505326,0.0000020748118,0.00007461429,0.0000050512226,0.90492636,0.007066433,0.084765606,0.00053237786,0.00018049887],"about_ca_topic_score_codex":0.0000060696134,"about_ca_topic_score_gemma":8.728206e-8,"teacher_disagreement_score":0.9048737,"about_ca_system_score_codex":0.000022955688,"about_ca_system_score_gemma":0.00008115748,"threshold_uncertainty_score":0.66170704},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051029125,0.0000255023,0.9980101,0.00084707205,0.00011358925,0.00034915205,0.0000035789028,0.0001071498,0.00049283373],"genre_scores_gemma":[0.003506274,0.0000011439125,0.9955824,0.0002570637,0.000060511567,0.000066176,0.0000034507393,0.0000052494524,0.000517726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993898,0.000015237415,0.00010027486,0.000300579,0.00007244966,0.000121623205],"domain_scores_gemma":[0.99943346,0.00002956085,0.000026721904,0.00033659427,0.00004460456,0.00012903704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015236367,0.00006759475,0.00007095523,0.00006120078,0.000106237,0.00004380023,0.00028485685,0.00002836955,0.00001719777],"category_scores_gemma":[0.000011815103,0.00005804415,0.000020678845,0.00015078303,0.0000030957408,0.00028706135,0.00017304276,0.000026795,0.00001042691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019048663,0.000046751786,0.0000066630164,0.000020906513,0.000008911072,4.7891837e-7,0.000813625,0.0006835651,0.017233366,0.07315915,0.006498889,0.9015086],"study_design_scores_gemma":[0.00017465976,0.000053272168,0.00021457317,0.0000086062555,0.000004349133,0.0000049322994,0.00001457069,0.96212447,0.011227844,0.0022965895,0.023782706,0.000093405346],"about_ca_topic_score_codex":0.00013657758,"about_ca_topic_score_gemma":0.00001810252,"teacher_disagreement_score":0.9614409,"about_ca_system_score_codex":0.000010106918,"about_ca_system_score_gemma":0.000029221375,"threshold_uncertainty_score":0.23669717},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016876575,0.0000649575,0.97219694,0.00085703545,0.00007896913,0.000036745027,2.1298378e-7,0.00013566589,0.009752881],"genre_scores_gemma":[0.82087964,0.0000032887071,0.1783061,0.000535051,0.0000291865,1.8691544e-7,9.866957e-7,0.0000010796565,0.0002445046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994784,0.000012222542,0.00010380764,0.00016092134,0.00010594452,0.00013870088],"domain_scores_gemma":[0.9996825,0.000019716188,0.000018335044,0.00023845705,0.000012812723,0.000028169947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115916366,0.000048657457,0.00006492772,0.000057259458,0.00004117721,0.00009771903,0.00040201924,0.000021142914,0.0000066886732],"category_scores_gemma":[0.000006579654,0.000040656112,0.000013360049,0.0001621128,0.000006747891,0.00039116433,0.00014571763,0.000057621746,0.00000934011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010796605,0.000041592953,0.00037394508,0.0000019219767,6.852952e-7,0.000019931509,0.00026742296,0.00014631561,0.00032511455,0.62871253,0.0020843733,0.36802506],"study_design_scores_gemma":[0.00059991464,0.00012117331,0.10844045,0.00008698235,6.976117e-7,0.000024936076,0.0000822449,0.7919752,0.0031164924,0.08742246,0.007810709,0.00031870606],"about_ca_topic_score_codex":0.000045565786,"about_ca_topic_score_gemma":0.0000029360735,"teacher_disagreement_score":0.80400306,"about_ca_system_score_codex":0.000011678347,"about_ca_system_score_gemma":0.000011754294,"threshold_uncertainty_score":0.16579081},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03761946,0.000024800693,0.9608952,0.000012361463,0.00015691543,0.000712944,0.0001438646,0.00002891566,0.00040553554],"genre_scores_gemma":[0.97814953,8.9782276e-7,0.021443063,0.000027467144,0.000026381183,0.000036010362,0.0003071013,0.0000021554579,0.00000738623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881524,0.000020408026,0.00051211624,0.00009359821,0.0003608697,0.00019778972],"domain_scores_gemma":[0.99934846,0.000047603902,0.0001063214,0.00033775548,0.00011130453,0.00004854455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016292821,0.000066349676,0.0001202761,0.00020099658,0.000054102664,0.0001083002,0.00043506583,0.00006054548,0.0000010179261],"category_scores_gemma":[0.000042732787,0.000058576752,0.000018423101,0.00024230908,0.0000120942,0.0027297265,0.00019619144,0.00007787595,0.0000062485365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030593903,0.000420341,0.031933468,0.0046047056,0.0001043504,0.00001646584,0.013088853,0.0098152235,0.007388942,0.21894039,0.009799596,0.70358175],"study_design_scores_gemma":[0.00095600047,0.00009284994,0.004776335,0.0004839669,0.0000016607494,0.000007505781,0.00057245325,0.8255023,0.017673254,0.00011833199,0.14956433,0.00025103815],"about_ca_topic_score_codex":0.00014564891,"about_ca_topic_score_gemma":0.0000056937965,"teacher_disagreement_score":0.94053006,"about_ca_system_score_codex":0.000059922528,"about_ca_system_score_gemma":0.00006050164,"threshold_uncertainty_score":0.23886906},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045574717,0.0015580552,0.98885787,0.00008613354,0.0025184886,0.00018925466,0.00002027007,0.00037760648,0.0018348465],"genre_scores_gemma":[0.2288722,0.000028998218,0.7703232,0.00013177551,0.00038967907,0.000007748983,0.000037343263,0.000018079976,0.00019095613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982522,0.000084497806,0.00031461043,0.00058811327,0.00035981915,0.00040071804],"domain_scores_gemma":[0.9980586,0.000098926386,0.00021824066,0.0013789732,0.00008116345,0.00016409144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022257774,0.0002931063,0.00033726834,0.00011402197,0.00022530419,0.00064706133,0.001615591,0.0002376377,0.000057959274],"category_scores_gemma":[0.000022506105,0.00024096176,0.00010835522,0.000101061814,0.000051796862,0.00081139395,0.0074330857,0.00046006474,0.000042926793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028828325,0.00086597644,0.0027964925,0.0007856796,0.00026912353,0.00012656064,0.0046648597,0.029031282,0.00776144,0.049867075,0.015412535,0.8883901],"study_design_scores_gemma":[0.00018555693,0.0000048019397,0.0007992443,0.00022878013,0.000015228979,0.000013354461,0.000009891115,0.9867083,0.0016612351,0.0024271756,0.007500115,0.00044630616],"about_ca_topic_score_codex":0.00034181547,"about_ca_topic_score_gemma":0.0000024086687,"teacher_disagreement_score":0.957677,"about_ca_system_score_codex":0.000058604386,"about_ca_system_score_gemma":0.000120851735,"threshold_uncertainty_score":0.98261356},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008583029,0.0035194575,0.9863744,0.0005140796,0.0006291021,0.00014972944,7.171214e-7,0.0000064984083,0.00022303051],"genre_scores_gemma":[0.6371179,0.000029738261,0.3623806,0.00012294107,0.00030668423,0.000004725842,6.469064e-8,0.0000023926098,0.00003496058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909896,0.00015904364,0.00034847212,0.00015620056,0.00013997534,0.00009732732],"domain_scores_gemma":[0.9988998,0.00033847181,0.00039937682,0.00020163141,0.00011126999,0.000049429742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028184114,0.000067276516,0.00017589422,0.000072668954,0.00033314287,0.00011723154,0.0007445473,0.00001841287,5.419593e-7],"category_scores_gemma":[0.000011090307,0.000029375595,0.00004359091,0.00013141987,0.00012398219,0.00027706567,0.00017250712,0.000060621496,1.357677e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019824142,0.0000143234665,0.0003025407,0.000042703712,0.000020004649,5.453614e-7,0.007286598,0.000360456,0.002516866,0.012340052,0.0014455478,0.9756684],"study_design_scores_gemma":[0.00020239221,0.00035788107,0.002120516,0.00012715887,0.000009664215,0.00059821305,0.0006749302,0.96101195,0.0001202912,0.001420763,0.03325244,0.000103802435],"about_ca_topic_score_codex":0.0000058954506,"about_ca_topic_score_gemma":6.730416e-7,"teacher_disagreement_score":0.9755646,"about_ca_system_score_codex":0.00003097048,"about_ca_system_score_gemma":0.000024680148,"threshold_uncertainty_score":0.25622994},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033962764,0.00005241773,0.93922305,0.00008868447,0.0001421526,0.00003858274,7.5929773e-7,0.00005466993,0.026436947],"genre_scores_gemma":[0.74931765,0.000001479764,0.25040755,0.0001043281,0.000009386399,0.0000010496256,5.75996e-7,0.0000013784078,0.00015659594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936193,0.000031855157,0.00015248648,0.0001717991,0.00014737184,0.00013455594],"domain_scores_gemma":[0.9995402,0.000047905225,0.000051415234,0.00029241477,0.00002408657,0.000043957312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001878836,0.000051165684,0.00008438102,0.00002656035,0.00005193669,0.00001962419,0.00032087747,0.000027951659,0.00008445769],"category_scores_gemma":[0.00004964699,0.000034191453,0.000027031789,0.00011802504,0.000024047084,0.000048695296,0.00009373012,0.00004579319,0.00001874718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.6396005e-7,0.0000689198,0.00045590298,0.0000027262863,0.0000022569388,0.000006229037,0.000081950246,0.0003689336,0.0009030344,0.9905621,0.0005884035,0.0069586737],"study_design_scores_gemma":[0.00092668005,0.0003799908,0.0066761165,0.00004961976,0.0000072614052,0.00009210704,0.00034285753,0.87165076,0.04291597,0.04886665,0.027502999,0.0005889833],"about_ca_topic_score_codex":0.000016325745,"about_ca_topic_score_gemma":5.080163e-7,"teacher_disagreement_score":0.94169545,"about_ca_system_score_codex":0.0000056691892,"about_ca_system_score_gemma":0.000018588335,"threshold_uncertainty_score":0.13942869},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02773302,0.000013252006,0.9687911,0.00018953413,0.0009812304,0.00011292593,0.0000018373648,0.000112554015,0.002064543],"genre_scores_gemma":[0.8512925,6.727915e-7,0.14846732,0.00015774545,0.00006468554,0.000002488791,6.365259e-7,0.000004561239,0.0000094123925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763995,0.000076067394,0.0002634376,0.00060210243,0.0010036238,0.00041481323],"domain_scores_gemma":[0.9983327,0.00010603954,0.00009048063,0.0009037331,0.00024225155,0.00032482215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016014725,0.00014530966,0.00019889006,0.00017423366,0.00017425562,0.00025154292,0.00248202,0.00004135567,0.000007989565],"category_scores_gemma":[0.00010969477,0.00010943911,0.00003969905,0.000872408,0.0010203535,0.0008893655,0.0016958027,0.00017895384,0.00002800976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007271007,0.00005590876,0.000029748111,0.00000563763,0.0000016158324,0.0000051675665,0.00042428946,0.0036029853,0.00011375227,0.977191,0.000113547285,0.018449128],"study_design_scores_gemma":[0.0002848996,0.0002790083,0.00026898345,0.000079548394,0.0000012472867,0.000014554779,0.0000047470235,0.7795235,0.0025114228,0.2167784,0.00010841666,0.00014527564],"about_ca_topic_score_codex":0.000007003111,"about_ca_topic_score_gemma":1.3312787e-7,"teacher_disagreement_score":0.82355946,"about_ca_system_score_codex":0.000054681233,"about_ca_system_score_gemma":0.0001855438,"threshold_uncertainty_score":0.4612252},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15471286,0.00005685835,0.84435296,0.00018047272,0.00028472376,0.000026394244,0.0000041970357,0.000008690327,0.00037285336],"genre_scores_gemma":[0.95120186,0.00001697106,0.048513174,0.00009088365,0.00013016838,0.0000012244986,0.0000018305124,0.0000041073527,0.000039761828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991122,0.000015360845,0.0002542394,0.00007950384,0.00046893218,0.000069766495],"domain_scores_gemma":[0.9989012,0.000026390948,0.0003285655,0.00014524095,0.0005581507,0.000040439714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008357493,0.00006120469,0.000101134654,0.00008642999,0.000017434957,0.0000693884,0.00078592147,0.000022047663,0.0000070481633],"category_scores_gemma":[0.000013141618,0.00004958643,0.000088767054,0.00006964314,0.000016598447,0.001190905,0.00015398629,0.000107693486,0.000005922794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022387358,0.0003076677,0.00035375994,0.0000073129822,0.00015042775,0.000010173706,0.0026755289,0.062391553,0.2929811,0.04894515,0.0017958323,0.59035915],"study_design_scores_gemma":[0.0002227832,0.00002868634,0.00021183361,0.000028094848,0.0000027367112,0.00001505656,0.000009822908,0.76933783,0.012896066,0.21718463,0.000018112722,0.000044359163],"about_ca_topic_score_codex":0.00002970397,"about_ca_topic_score_gemma":5.561361e-7,"teacher_disagreement_score":0.796489,"about_ca_system_score_codex":0.000022684397,"about_ca_system_score_gemma":0.00005117952,"threshold_uncertainty_score":0.2022076},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062883333,0.00008210555,0.9913859,0.00013496524,0.0011919722,0.00010572845,0.000007079998,0.00007409442,0.0007298333],"genre_scores_gemma":[0.93935573,0.0000035759633,0.05996719,0.00020854264,0.00013574435,0.000019565443,0.000009047353,0.000004233371,0.00029635907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946886,0.000012718252,0.0000923895,0.00012760278,0.0001243878,0.00017406735],"domain_scores_gemma":[0.9995318,0.000059393027,0.000047971716,0.0002509665,0.000044238237,0.000065621636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020444741,0.0000557998,0.0000560663,0.00003343905,0.000068212925,0.000083671504,0.0003911303,0.000031450218,0.000010105358],"category_scores_gemma":[0.000043608896,0.000047259342,0.00003462646,0.000092244525,0.000017590246,0.002400498,0.0001274309,0.000054064923,0.00007881061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033233864,0.00022133529,0.011488096,0.000055920973,0.000039361432,0.0000057715856,0.00413059,0.00039148895,0.0074373945,0.50609434,0.044582233,0.4255202],"study_design_scores_gemma":[0.0006886549,0.0001341478,0.009499601,0.00009897467,0.000015017107,0.000037993017,0.00015419918,0.857872,0.004393985,0.020479769,0.10613691,0.0004887575],"about_ca_topic_score_codex":0.00004449588,"about_ca_topic_score_gemma":0.0000022269987,"teacher_disagreement_score":0.9330674,"about_ca_system_score_codex":0.00003568495,"about_ca_system_score_gemma":0.000019688041,"threshold_uncertainty_score":0.192718},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0968061,0.00016344221,0.9004974,0.0012199165,0.0001427162,0.00016649344,0.000035899888,0.00025673848,0.0007113377],"genre_scores_gemma":[0.8995852,0.000011910886,0.099674016,0.00020799306,0.00015091726,0.000025928386,0.00008591326,0.000009760072,0.00024836257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988332,0.00003428783,0.0001432836,0.00026524678,0.00050813693,0.00021585506],"domain_scores_gemma":[0.99909985,0.000028696591,0.00005696433,0.00054622686,0.000073527975,0.00019472263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016867368,0.00009526553,0.00014423318,0.000029378347,0.000064835316,0.000115798364,0.0005910253,0.000039070277,0.000009016331],"category_scores_gemma":[0.000057315163,0.000080058504,0.0000208374,0.00017985968,0.000017250271,0.000418495,0.00060888135,0.00008737917,0.00009829257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000372459,0.049931154,0.17203738,0.00067367643,0.0026263464,0.0010272661,0.021622181,0.001605354,0.14863265,0.21464045,0.15032871,0.23650238],"study_design_scores_gemma":[0.0036242832,0.0006221337,0.019055706,0.0006819721,0.000102980106,0.000011200182,0.00023245336,0.820945,0.11770361,0.021997208,0.013658153,0.0013652825],"about_ca_topic_score_codex":0.000041971874,"about_ca_topic_score_gemma":0.0000020705172,"teacher_disagreement_score":0.8193397,"about_ca_system_score_codex":0.000064575426,"about_ca_system_score_gemma":0.00004237395,"threshold_uncertainty_score":0.3264691},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013020135,0.0063896375,0.9769832,0.0017456186,0.0009346958,0.00029668058,0.0000022019644,0.000029898834,0.00059794914],"genre_scores_gemma":[0.79489756,0.00021475034,0.20444588,0.000058454814,0.00023927781,0.0000071216205,1.2595943e-7,0.00000438416,0.00013245159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874556,0.00006277658,0.0004269774,0.00021731097,0.00035559759,0.00019175015],"domain_scores_gemma":[0.9990142,0.00026621748,0.00034593834,0.00015092664,0.00013008417,0.00009265587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013847331,0.00010449479,0.0002058251,0.0000950003,0.000589972,0.00088944065,0.0008087544,0.000037246613,0.0000018118486],"category_scores_gemma":[0.00000667225,0.00005279009,0.000053670406,0.00023485575,0.00016648843,0.0010055427,0.00022460733,0.00009802489,8.060415e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003188392,0.0003115401,0.0024117203,0.0008569917,0.00031559242,0.000065565924,0.017602539,0.03450052,0.00029321705,0.16905567,0.03927964,0.7352751],"study_design_scores_gemma":[0.0004179859,0.0005637092,0.0005754994,0.0002185315,0.000012034697,0.0012421648,0.000114200404,0.9912538,0.000009933506,0.0007830718,0.004718457,0.00009060106],"about_ca_topic_score_codex":0.0000038366406,"about_ca_topic_score_gemma":3.8099193e-7,"teacher_disagreement_score":0.9567533,"about_ca_system_score_codex":0.000011326382,"about_ca_system_score_gemma":0.000028313703,"threshold_uncertainty_score":0.8576897},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03895312,0.000027345368,0.940929,0.0012877971,0.00051767105,0.00014101135,0.000004256189,0.0003424258,0.017797355],"genre_scores_gemma":[0.7856544,0.000016804763,0.21269692,0.001269635,0.0002264694,0.0000061376886,0.0000014046668,0.00000817574,0.00012004222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968191,0.000097762284,0.00029970866,0.0010808307,0.0009589336,0.0007436585],"domain_scores_gemma":[0.99788743,0.000196609,0.0000513104,0.0013181892,0.0001625266,0.00038393744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010389695,0.00022658959,0.00022459324,0.00013338179,0.00071398204,0.00071952475,0.0033877713,0.00005888409,0.00046443005],"category_scores_gemma":[0.000050956478,0.00017906488,0.00007611563,0.0008905736,0.0017633818,0.0014117683,0.0012221959,0.0002673426,0.00042135792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008717109,0.000037854952,0.0000132195355,0.0000021624314,0.0000018034514,0.000033217122,0.00023719657,0.00007909463,0.00043017179,0.73037875,0.00009066175,0.26868713],"study_design_scores_gemma":[0.0003002156,0.00023848511,0.0018418159,0.00006720807,0.000004350073,0.000120485,0.000008631369,0.93556726,0.009512144,0.046644833,0.005251909,0.00044266006],"about_ca_topic_score_codex":0.000023640681,"about_ca_topic_score_gemma":3.6032623e-7,"teacher_disagreement_score":0.93548816,"about_ca_system_score_codex":0.00006503431,"about_ca_system_score_gemma":0.00013138082,"threshold_uncertainty_score":0.7302054},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04388424,0.00006189023,0.9527986,0.00042059855,0.00038702652,0.000077860816,0.000004802572,0.00006666213,0.0022983255],"genre_scores_gemma":[0.8245356,0.0000039264087,0.17530113,0.000070679795,0.0000696407,0.000003796123,0.0000015547388,0.0000024384115,0.000011242929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988148,0.000054444,0.0001843191,0.00029339065,0.00035227707,0.00030075986],"domain_scores_gemma":[0.99878263,0.00023806612,0.00005239497,0.00055935374,0.00013425646,0.00023330146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062964426,0.00008350419,0.00010749937,0.00014448476,0.00039327974,0.00012110165,0.00069033896,0.000022986802,0.00003417033],"category_scores_gemma":[0.00007409774,0.00006590018,0.000027705297,0.00075043924,0.0013343494,0.0013778269,0.00084776763,0.00008337823,0.000021952834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010659683,0.000052672956,0.001052436,0.0000027463977,0.0000018778157,4.0594097e-7,0.0004899489,0.000035397738,0.0005103929,0.97854066,0.00008188478,0.019230496],"study_design_scores_gemma":[0.00032796996,0.00017430571,0.10370169,0.00003074059,0.000015647667,0.00012037786,0.00007434073,0.7947665,0.0038060294,0.096100256,0.0005857552,0.00029642106],"about_ca_topic_score_codex":0.000007367773,"about_ca_topic_score_gemma":2.0665368e-7,"teacher_disagreement_score":0.88244045,"about_ca_system_score_codex":0.000013413256,"about_ca_system_score_gemma":0.00004857384,"threshold_uncertainty_score":0.49164662},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037338674,0.0041146604,0.95541215,0.00079186447,0.0013959365,0.0000918004,0.000011180168,0.00004912343,0.0007945927],"genre_scores_gemma":[0.7668761,0.0004961177,0.2315412,0.0002569427,0.0006488113,0.00000216684,0.000003609598,0.000024267281,0.00015077501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985286,0.000062712745,0.0004041457,0.00020018299,0.0005683602,0.0002359981],"domain_scores_gemma":[0.998666,0.000056477966,0.00031985846,0.00031016264,0.00024528455,0.00040225632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006681577,0.0001417007,0.00025490345,0.00018399139,0.00008352467,0.00024568988,0.00073793234,0.00005777718,0.0000038158],"category_scores_gemma":[0.00007524848,0.00010438581,0.00007786781,0.00028803997,0.0000478474,0.0015525465,0.00034443458,0.0002549007,0.0000049887503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023985518,0.00013773295,0.0024385655,0.000028883336,0.0001409974,0.0005493365,0.0019433035,0.00021484775,0.0008569925,0.028710676,0.014155734,0.9507989],"study_design_scores_gemma":[0.017240766,0.006318871,0.045049578,0.0013879465,0.00028655835,0.011480493,0.0026943078,0.46513125,0.008949172,0.288794,0.14941987,0.0032471674],"about_ca_topic_score_codex":0.000018216027,"about_ca_topic_score_gemma":8.6601665e-7,"teacher_disagreement_score":0.9475518,"about_ca_system_score_codex":0.00003250143,"about_ca_system_score_gemma":0.00012399761,"threshold_uncertainty_score":0.42567295},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009928042,0.000088193665,0.9887587,0.00005838356,0.00015734573,0.00053660205,0.00005996018,0.00016729865,0.0002454828],"genre_scores_gemma":[0.3310532,0.000098452954,0.6676923,0.00032389702,0.00012845059,0.00037298034,0.000099670404,0.000025719331,0.00020533495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981309,0.00003925532,0.0003760039,0.000695691,0.00036684473,0.000391304],"domain_scores_gemma":[0.99871,0.00019417507,0.00011031535,0.0008025307,0.00007087307,0.00011212106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031244644,0.00022681616,0.00025054836,0.00017606467,0.00031512315,0.00007980805,0.0009401157,0.00006956,0.000034733894],"category_scores_gemma":[0.000044394805,0.00021121927,0.00006247285,0.0005046126,0.00015004349,0.0005695148,0.0003348428,0.00016937332,0.00009527078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014017723,0.00038651528,0.0001609959,0.000026763573,0.000008310876,0.000049801347,0.00053562847,0.00096624513,0.009508663,0.0026112748,0.000864106,0.9847415],"study_design_scores_gemma":[0.00032579264,0.00021540347,0.0014477659,0.000043443782,0.0000051703387,0.000025867419,0.0000521347,0.73291004,0.2556092,0.0007707374,0.008202065,0.00039238416],"about_ca_topic_score_codex":0.00014080737,"about_ca_topic_score_gemma":0.00006791129,"teacher_disagreement_score":0.98434913,"about_ca_system_score_codex":0.00007547077,"about_ca_system_score_gemma":0.00010543621,"threshold_uncertainty_score":0.86132723},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021341557,0.00052198244,0.97704244,0.00032454522,0.00018648902,0.0002535693,0.00004158577,0.00011931267,0.00016855042],"genre_scores_gemma":[0.55293757,0.000017863762,0.44658998,0.00011681509,0.00015378013,0.000024841293,0.00006314452,0.000015872669,0.000080100486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990517,0.00002738812,0.00014116205,0.0002874569,0.00015381307,0.00033850104],"domain_scores_gemma":[0.99917996,0.00012717005,0.00008964795,0.0003745415,0.00006230963,0.00016639038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017632262,0.00015066574,0.00015800909,0.00004815562,0.00019727145,0.00012674811,0.0003275767,0.000044157154,0.0000020468478],"category_scores_gemma":[0.000009077291,0.000110263936,0.000031639946,0.00019054076,0.00006413211,0.00083308003,0.00008697539,0.00007981615,0.000004697477],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007023597,0.00028524638,0.00670481,0.00007752318,0.000062379324,0.000007278549,0.0010146368,0.000019864452,0.00062083063,0.14710158,0.0032408661,0.84079474],"study_design_scores_gemma":[0.0061200103,0.0016011441,0.11828188,0.0006240682,0.00014619494,0.0004166477,0.0003335436,0.4703594,0.016977377,0.063454114,0.31911334,0.0025722482],"about_ca_topic_score_codex":0.000043774275,"about_ca_topic_score_gemma":0.0000052392966,"teacher_disagreement_score":0.8382225,"about_ca_system_score_codex":0.000018900704,"about_ca_system_score_gemma":0.000020475156,"threshold_uncertainty_score":0.44964328},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03609077,0.004243105,0.9117581,0.031171612,0.00094054366,0.0009755457,0.00012900877,0.0002551003,0.014436186],"genre_scores_gemma":[0.60901695,0.000025289157,0.39085835,0.000065227934,0.0000013988713,0.000005901084,0.0000049087594,0.0000031491174,0.000018791616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990739,0.0002981041,0.00025866847,0.000118619035,0.00016216526,0.000088548666],"domain_scores_gemma":[0.96764714,0.00038406008,0.00023060536,0.031581983,0.00012783725,0.000028356653],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00026650948,0.000069698646,0.00012770093,0.000049945487,0.00015535642,0.000017680488,0.031143973,0.000036064343,0.0000074409077],"category_scores_gemma":[0.0023116914,0.000047526017,0.00007667007,0.0003214072,0.00018771642,0.00014485186,0.013975288,0.0001286857,0.0000032362539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061007588,0.0026508586,0.016409101,0.00018826657,0.0001445914,7.680661e-7,0.0025409749,0.0030374283,0.13450396,0.6711439,0.10728234,0.06203682],"study_design_scores_gemma":[0.0015331765,0.00014976693,0.011214036,0.00092303735,0.00004389619,0.000008450505,0.00011793532,0.39055803,0.26184776,0.2391415,0.09404222,0.00042016976],"about_ca_topic_score_codex":0.000032978194,"about_ca_topic_score_gemma":0.0000074473296,"teacher_disagreement_score":0.5729262,"about_ca_system_score_codex":0.000012880419,"about_ca_system_score_gemma":0.000066172215,"threshold_uncertainty_score":0.9939995},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013333092,0.000016437269,0.9271003,0.00042739778,0.000056760593,0.0002807309,0.0000043138134,0.00017968946,0.058601253],"genre_scores_gemma":[0.19616911,0.000032421656,0.8022224,0.00029381504,0.000043066084,0.00008637932,0.000037982434,0.000020016356,0.0010948284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990804,0.000009896401,0.00019325047,0.00026825676,0.00024030713,0.00020788015],"domain_scores_gemma":[0.9991945,0.000048222424,0.00007410816,0.00060123147,0.000018355453,0.00006357644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000121118974,0.00013237646,0.00016074655,0.000035036457,0.00010914525,0.00008402167,0.00049582927,0.000049052524,0.00025781797],"category_scores_gemma":[0.0000026362934,0.00009426399,0.000022985523,0.0001448977,0.0000379629,0.00017635286,0.00010651037,0.00007300356,0.00018662063],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001250728,0.00017981946,0.000004991323,0.000038410224,0.00002390545,0.000008486187,0.0017693341,0.00013637984,0.00077982096,0.86787975,0.0017912538,0.12737532],"study_design_scores_gemma":[0.004071833,0.000691934,0.0005379581,0.00021506428,0.00008022325,0.0001565551,0.0010413014,0.36828506,0.023441691,0.5367916,0.06296294,0.0017238198],"about_ca_topic_score_codex":0.0000054794637,"about_ca_topic_score_gemma":0.0000014788825,"teacher_disagreement_score":0.36814868,"about_ca_system_score_codex":0.000023263883,"about_ca_system_score_gemma":0.000017461192,"threshold_uncertainty_score":0.3843974},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036763009,0.000028174603,0.9724654,0.0007381693,0.00023103789,0.00007274926,0.0000064584847,0.000042516636,0.022739207],"genre_scores_gemma":[0.86659586,0.0000018293796,0.13307919,0.00019066308,0.000010493919,0.0000044877975,0.0000026990383,0.0000020108232,0.00011275768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993886,0.00008179662,0.00011906744,0.00015536955,0.00016764305,0.00008754383],"domain_scores_gemma":[0.99929714,0.00011908426,0.00005864603,0.000456614,0.000043307256,0.000025195892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001382762,0.0000573584,0.000066439155,0.000026958296,0.000117783406,0.000018862185,0.0003041926,0.000019850355,0.00014688763],"category_scores_gemma":[0.000038388727,0.000033521224,0.000034989767,0.00016485697,0.00015366386,0.0001499071,0.000033498534,0.000056709116,0.0000137862025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003977785,0.000037512043,0.00016727773,0.0000017680018,0.0000017972313,3.1122863e-7,0.0000075282005,0.000052114432,0.00007378915,0.9830134,0.0029019641,0.013738576],"study_design_scores_gemma":[0.00051505293,0.00015144433,0.011378539,0.000059239963,0.0000032338792,0.000015627098,0.000038623584,0.47873834,0.008903319,0.4881959,0.011810664,0.00019004926],"about_ca_topic_score_codex":0.000017979628,"about_ca_topic_score_gemma":0.0000076299975,"teacher_disagreement_score":0.86291957,"about_ca_system_score_codex":0.000021247713,"about_ca_system_score_gemma":0.000044011857,"threshold_uncertainty_score":0.16083165},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020241205,0.00007833478,0.9739573,0.000285452,0.00014418032,0.00025547307,0.0000058179644,0.000041134947,0.004991107],"genre_scores_gemma":[0.785416,0.000008028117,0.21410763,0.00025157022,0.000018779074,0.000021090469,0.0000013827046,0.000012153269,0.00016335088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873936,0.00007847103,0.00027714562,0.00023726783,0.00047098452,0.00019675732],"domain_scores_gemma":[0.9981395,0.00056543964,0.00012911731,0.0010165729,0.0000664603,0.00008288803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005721918,0.00012654458,0.00020278171,0.00022762209,0.000094396324,0.000070084505,0.00068180007,0.000035120043,0.00003349819],"category_scores_gemma":[0.0010447433,0.00006987217,0.00007908181,0.0015255157,0.000022115213,0.0001157765,0.00021849596,0.00008485951,0.000079261124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004035054,0.00016870815,0.000007921985,0.000026426123,0.000016348167,0.000005392486,0.0010030845,0.00018439854,0.0005119967,0.98519355,0.003162917,0.009715225],"study_design_scores_gemma":[0.0010450332,0.0011162837,0.0008121682,0.00044767282,0.00008654243,0.000046989564,0.00077119627,0.6797803,0.06644808,0.23642072,0.012152058,0.00087296334],"about_ca_topic_score_codex":0.000005715267,"about_ca_topic_score_gemma":6.1317536e-7,"teacher_disagreement_score":0.7651748,"about_ca_system_score_codex":0.000015820922,"about_ca_system_score_gemma":0.000024073039,"threshold_uncertainty_score":0.28493044},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068868264,0.00006502137,0.92551833,0.0005726854,0.0004086534,0.0001290455,0.0000010412211,0.00013901573,0.06627939],"genre_scores_gemma":[0.94820124,0.000046166184,0.04963724,0.0006660351,0.00035527654,0.00002475996,0.0000011515086,0.0000141308265,0.0010540123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893695,0.00006237373,0.00019049589,0.00015624224,0.0003196257,0.00033429053],"domain_scores_gemma":[0.9986748,0.0004366225,0.000048672307,0.0007049837,0.000022302374,0.000112593545],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00057139207,0.000113855414,0.00011545181,0.00002642399,0.00014594498,0.000096850206,0.0009463874,0.000041957537,0.00039241888],"category_scores_gemma":[0.000070137234,0.00005920323,0.000057167716,0.00016356577,0.000068769164,0.0003190726,0.00035372828,0.0001627788,0.0021468988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033123708,0.00009465993,0.000019839094,0.0000076185224,0.0000076103,0.0000011875121,0.0022477137,0.000006624778,0.000049099137,0.912463,0.002602696,0.08249662],"study_design_scores_gemma":[0.0001384404,0.00018908041,0.00087378896,0.00028011305,0.000029579625,0.00009908979,0.00067111704,0.15278094,0.019545062,0.79965806,0.0250407,0.0006940608],"about_ca_topic_score_codex":0.000014134531,"about_ca_topic_score_gemma":3.7476335e-7,"teacher_disagreement_score":0.9413144,"about_ca_system_score_codex":0.000025797744,"about_ca_system_score_gemma":0.000009358334,"threshold_uncertainty_score":0.99863005},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014856386,0.000018099077,0.9799412,0.004256273,0.00027237576,0.0002673355,0.000014305766,0.0000670434,0.00030700647],"genre_scores_gemma":[0.57744235,0.00002180266,0.41210777,0.0012442531,0.0005767072,0.00014307235,0.00001545278,0.000012866466,0.00843572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924767,0.00003397645,0.00018000316,0.00020268283,0.00018825491,0.00014743987],"domain_scores_gemma":[0.99937266,0.00007459975,0.00003683463,0.00039704007,0.000060754996,0.000058099664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013498188,0.000065000546,0.00006881618,0.000035630885,0.00014534776,0.00005761176,0.00030737772,0.000038559494,0.000038866554],"category_scores_gemma":[0.000019550276,0.00003876143,0.000033648274,0.00012834619,0.000037945447,0.00050044176,0.00011595357,0.000065178036,0.000020843285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010066687,0.00016234178,0.000045183104,0.0000088437155,0.000026092379,0.000001433453,0.00025517002,0.0047987727,0.12434131,0.1678772,0.013835719,0.68854725],"study_design_scores_gemma":[0.00063593197,0.0004023135,0.0031584052,0.000014249102,0.000004968679,0.000013825936,0.00001624224,0.35694388,0.045878615,0.0013624774,0.5914228,0.0001463023],"about_ca_topic_score_codex":0.00005328761,"about_ca_topic_score_gemma":0.000048556558,"teacher_disagreement_score":0.688401,"about_ca_system_score_codex":0.000017352637,"about_ca_system_score_gemma":0.000034041528,"threshold_uncertainty_score":0.15806453},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025077271,0.00012238816,0.9948557,0.00009817696,0.0009586022,0.00020542779,0.000015092856,0.000032422067,0.0012044464],"genre_scores_gemma":[0.74778676,0.000015141824,0.2510954,0.00043456073,0.000547933,0.000019579235,0.000064506174,0.000007837377,0.000028266828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779576,0.00007213256,0.0010934895,0.00010133993,0.00073981803,0.00019745991],"domain_scores_gemma":[0.9986063,0.000052605614,0.00032529846,0.0003617198,0.00048237378,0.00017167164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006061047,0.00012409054,0.00020087176,0.00033547962,0.000083681705,0.00044589667,0.0006132777,0.00005481276,0.0000058107253],"category_scores_gemma":[0.000047390215,0.00009386202,0.00008137735,0.0003441101,0.000013665344,0.0023460365,0.00010088045,0.00013773056,0.00015047955],"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":[0.00013091599,0.00082323246,0.00090199587,0.00035614954,0.00006424846,0.000035436693,0.0011082947,0.7698402,0.0007849252,0.062317904,0.10127036,0.062366363],"study_design_scores_gemma":[0.00026862984,0.00013114474,0.0005691779,0.00011771469,0.000007651909,0.00016705824,0.00010699727,0.9255016,0.001755826,0.00006246291,0.071172565,0.00013919233],"about_ca_topic_score_codex":0.0000662389,"about_ca_topic_score_gemma":2.4069513e-7,"teacher_disagreement_score":0.745279,"about_ca_system_score_codex":0.00010204067,"about_ca_system_score_gemma":0.00009737431,"threshold_uncertainty_score":0.42997918},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01039603,0.000039623,0.9679377,0.0001319316,0.00009344242,0.000042876833,4.892993e-7,0.00017171062,0.021186162],"genre_scores_gemma":[0.2628989,0.0000064099886,0.735483,0.0002982936,0.00006750739,0.0000013189735,0.0000021818194,0.000004578778,0.0012378405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936146,0.0000073177343,0.00009348592,0.00020173268,0.00016325545,0.0001727637],"domain_scores_gemma":[0.9994607,0.000056770208,0.00002868898,0.0003563702,0.000032270116,0.00006521291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002497782,0.000060454386,0.000061764746,0.000041981264,0.00007925866,0.00008262522,0.00038881425,0.000023398348,0.000021220707],"category_scores_gemma":[0.000006129867,0.00003725214,0.0000118392945,0.00017445568,0.000015230565,0.00039611218,0.00016744657,0.00005756674,0.000040106414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041493724,0.0001534018,0.0064684935,0.00001563128,0.000024343537,0.0001161258,0.00053620007,0.00018085225,0.00337257,0.15414846,0.008042,0.8269004],"study_design_scores_gemma":[0.0025389376,0.0010162048,0.06625515,0.00032924055,0.000019104835,0.00028702617,0.00030101466,0.39104283,0.13258821,0.0138255,0.39010692,0.0016898803],"about_ca_topic_score_codex":0.000051963187,"about_ca_topic_score_gemma":0.000029706216,"teacher_disagreement_score":0.8252106,"about_ca_system_score_codex":0.000008783409,"about_ca_system_score_gemma":0.0000156699,"threshold_uncertainty_score":0.15190981},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36962193,0.00012321456,0.60580057,0.0015424432,0.0017816606,0.00023128063,0.000010465995,0.0005129884,0.020375434],"genre_scores_gemma":[0.66828114,0.000020163874,0.3304849,0.00048228513,0.00005303272,0.0000067793953,0.00000707368,0.000005238502,0.0006593982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994361,0.000012449323,0.000081438186,0.00022632406,0.00012030622,0.00012339625],"domain_scores_gemma":[0.99943143,0.00004229468,0.00002522668,0.00038012958,0.000025868461,0.00009505529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009338843,0.00006789413,0.00006997193,0.00004179064,0.00012460098,0.00012578949,0.0003963572,0.00004581751,0.000046664474],"category_scores_gemma":[0.000008402421,0.000046440724,0.000015131338,0.00009357182,0.000038581482,0.0004072179,0.00048237696,0.00012382312,0.00002871426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005566558,0.000077248784,0.001911983,0.000008108109,0.000004936092,0.000013384575,0.00013599626,0.0000018652576,0.06934051,0.7071215,0.03786076,0.18351814],"study_design_scores_gemma":[0.0013719387,0.0001995633,0.05085558,0.000038767546,0.0000065825443,0.00014603796,0.000035543937,0.3721925,0.024784174,0.10359157,0.4461117,0.0006660402],"about_ca_topic_score_codex":0.000035802255,"about_ca_topic_score_gemma":0.000012800522,"teacher_disagreement_score":0.60352993,"about_ca_system_score_codex":0.000001308562,"about_ca_system_score_gemma":0.000010006631,"threshold_uncertainty_score":0.18937977},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011828195,0.000058190937,0.9836357,0.0014374913,0.00029080475,0.00010556438,0.0000014212874,0.00013372142,0.0025089053],"genre_scores_gemma":[0.82972586,0.000018831746,0.16977108,0.0004322058,0.000042332747,0.0000019045239,7.1748826e-7,0.000002380684,0.0000047057542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981795,0.000050572173,0.00022600734,0.00064573024,0.00046940747,0.00042878778],"domain_scores_gemma":[0.99888474,0.000111993744,0.000041731237,0.00064597453,0.0000864089,0.00022914895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086632004,0.00013565719,0.00016078791,0.00022410638,0.0002859123,0.0004204896,0.0013957233,0.000044014672,0.0000070672822],"category_scores_gemma":[0.00005171238,0.00011368378,0.000022647891,0.0011973608,0.00081841863,0.0009890556,0.00077902334,0.0002058589,0.000011338394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012772367,0.00006289992,0.00003749668,0.0000012398177,3.360969e-7,0.000018925351,0.0001257164,0.000017245417,0.00008566567,0.9303799,0.000024690937,0.06924457],"study_design_scores_gemma":[0.0002128969,0.0001784288,0.0069330162,0.000030097865,8.0215364e-7,0.00003851132,0.000003301336,0.46219212,0.0003327886,0.5298033,0.0001364373,0.000138334],"about_ca_topic_score_codex":0.0000042863644,"about_ca_topic_score_gemma":2.3199193e-7,"teacher_disagreement_score":0.8178976,"about_ca_system_score_codex":0.000045486388,"about_ca_system_score_gemma":0.00006303862,"threshold_uncertainty_score":0.463589},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11846384,0.000005669696,0.87582356,0.0011963262,0.00027277478,0.000101432226,8.1818206e-7,0.000040010826,0.004095584],"genre_scores_gemma":[0.8898282,0.0000012448097,0.1095706,0.0005409981,0.000050408944,0.0000018405779,1.5457199e-7,0.0000031092966,0.000003452647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980998,0.00007393485,0.00024496968,0.0004367205,0.00070512877,0.00043941702],"domain_scores_gemma":[0.9979625,0.0008770614,0.00006489535,0.0008933151,0.00008712468,0.00011515155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028459022,0.00011794523,0.0001449755,0.00013075296,0.00016311202,0.0001294193,0.0026387533,0.000036567828,0.00003481689],"category_scores_gemma":[0.00011414504,0.000068684894,0.000041382085,0.0013578396,0.0015263864,0.00033556717,0.0010715941,0.00020955944,0.000057148714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011510462,0.00005594972,0.00017666143,0.0000018117798,5.093451e-7,0.000011141087,0.00033111885,0.000036618287,0.00021819521,0.92423517,0.00003608316,0.074885204],"study_design_scores_gemma":[0.00032009237,0.00016404637,0.020183131,0.00014383628,0.0000014980117,0.00003304359,0.000017048424,0.6448026,0.014794322,0.31891897,0.0003737405,0.00024769807],"about_ca_topic_score_codex":0.0000101738515,"about_ca_topic_score_gemma":0.0000016948858,"teacher_disagreement_score":0.77136433,"about_ca_system_score_codex":0.000034642464,"about_ca_system_score_gemma":0.000064961525,"threshold_uncertainty_score":0.56240344},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025841175,0.0027057438,0.95691794,0.004142503,0.004969464,0.00019682526,0.00007732669,0.000111425354,0.005037618],"genre_scores_gemma":[0.72485495,0.0002443364,0.27031207,0.00089027156,0.0033014854,0.0000032459404,0.000013088271,0.0000323325,0.0003482164],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99791896,0.00008339576,0.00059756875,0.00019653427,0.0007775828,0.0004259683],"domain_scores_gemma":[0.99827003,0.00016609284,0.00055010116,0.0005447209,0.0001502238,0.00031882687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082283345,0.00018734619,0.00028540223,0.00019947179,0.00014553925,0.00015999406,0.000999161,0.00007571873,0.000011173999],"category_scores_gemma":[0.00013854205,0.00012927684,0.00017571702,0.00028072135,0.00003960772,0.0020092274,0.0002747498,0.00036106136,0.00003351983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054021983,0.0011885947,0.0014468302,0.000068851,0.00037607425,0.0006776981,0.010359277,0.0018090815,0.0034505748,0.020966986,0.123871796,0.835244],"study_design_scores_gemma":[0.012209674,0.0052720658,0.104843676,0.0023093512,0.00017841005,0.0037035309,0.0022527322,0.25662923,0.014560318,0.006816317,0.588365,0.002859666],"about_ca_topic_score_codex":0.000013993321,"about_ca_topic_score_gemma":2.2062815e-7,"teacher_disagreement_score":0.83238435,"about_ca_system_score_codex":0.0000688947,"about_ca_system_score_gemma":0.00006074857,"threshold_uncertainty_score":0.52717566},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026788623,0.0001135911,0.98578244,0.002146403,0.00021303979,0.00097126036,0.000046350397,0.00011432518,0.007933753],"genre_scores_gemma":[0.12443225,0.00006761228,0.8729595,0.0010466606,0.000346891,0.00049237366,0.00008743123,0.00004644654,0.0005208583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977355,0.00023989692,0.0006130521,0.000766589,0.0002922695,0.00035267262],"domain_scores_gemma":[0.9966675,0.0009738488,0.000360778,0.0017911934,0.000112650385,0.00009399799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063759036,0.0003387439,0.0006190909,0.000066620836,0.00007654549,0.00007355598,0.002414991,0.0004510533,0.00026153852],"category_scores_gemma":[0.00036331924,0.00018673521,0.0001835901,0.0000695683,0.00028434987,0.000024710165,0.003725282,0.00072049844,0.00029736204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012099016,0.00040450622,8.539598e-7,0.00037593397,0.00003631264,0.0000014816709,0.0002339199,0.0024244443,0.000026921176,0.98450875,0.007607638,0.004367159],"study_design_scores_gemma":[0.00014483508,0.000105602274,0.000008943979,0.000167645,0.000013590203,0.000006661525,0.000004534148,0.4940297,0.000047857917,0.50076926,0.004517468,0.00018387697],"about_ca_topic_score_codex":0.000056410056,"about_ca_topic_score_gemma":9.189748e-8,"teacher_disagreement_score":0.49160525,"about_ca_system_score_codex":0.00002915548,"about_ca_system_score_gemma":0.00006887163,"threshold_uncertainty_score":0.7614841},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015227291,0.00031520272,0.9941586,0.0021593606,0.00094427477,0.0013103494,0.000021595428,0.00027330447,0.0006649862],"genre_scores_gemma":[0.031582393,0.000065901426,0.9647849,0.0009986102,0.0009866573,0.0007340085,0.000035084122,0.00004529284,0.00076715025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740595,0.00023623325,0.00052418286,0.0007006355,0.00043477243,0.00069825846],"domain_scores_gemma":[0.99428016,0.0038901777,0.00022966211,0.0012574642,0.00016748862,0.0001750655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020967263,0.00031058324,0.00054796465,0.00009545073,0.00053325796,0.0004633566,0.0019377157,0.000117651485,0.000018899114],"category_scores_gemma":[0.00044217135,0.000189272,0.00031626195,0.0003030053,0.00016783336,0.00059827947,0.000602454,0.00025631586,0.000060728737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057355204,0.00007751929,0.0000043834616,0.000022074319,0.00010610316,0.0000024116846,0.00020868747,0.00018655299,0.000064488566,0.069618784,0.0059959097,0.9231395],"study_design_scores_gemma":[0.030315172,0.00008781445,0.000023816281,0.00003311776,0.000046105582,0.000019099465,0.00001135561,0.8506009,0.0011250731,0.026956378,0.090472326,0.00030883608],"about_ca_topic_score_codex":0.000095252384,"about_ca_topic_score_gemma":0.0000028786612,"teacher_disagreement_score":0.9228307,"about_ca_system_score_codex":0.000038146427,"about_ca_system_score_gemma":0.000064624895,"threshold_uncertainty_score":0.77182883},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022919537,0.00033289805,0.9746537,0.000034469915,0.0006013167,0.00030276738,0.000021007141,0.00011251418,0.0010217876],"genre_scores_gemma":[0.8655738,0.0000051248267,0.13359155,0.000023352635,0.00028030403,0.000009242574,0.000015510906,0.00001789994,0.00048319742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984594,0.00019689693,0.0005346631,0.0002874968,0.00024178611,0.00027977664],"domain_scores_gemma":[0.99839705,0.0004608965,0.00043216278,0.00051143946,0.00013195019,0.00006650134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014137987,0.00014255378,0.00038782356,0.000121210316,0.00013904074,0.000059269023,0.00069913745,0.000062943036,0.0000092568835],"category_scores_gemma":[0.000042223994,0.00013059459,0.00010707364,0.00023168302,0.00008096457,0.00021762827,0.00021883947,0.00006474085,0.000009719426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010782108,0.00038782574,0.00023430277,0.00042539858,0.00024999958,0.000019264326,0.00510811,0.0154172145,0.012833751,0.074158825,0.01422433,0.87683314],"study_design_scores_gemma":[0.0006137718,0.00016016509,0.000251516,0.0004038638,0.000013518804,0.000044803095,0.0001555818,0.99256,0.0018222483,0.0013509421,0.002441616,0.00018195072],"about_ca_topic_score_codex":0.00006963706,"about_ca_topic_score_gemma":2.1638877e-7,"teacher_disagreement_score":0.9771428,"about_ca_system_score_codex":0.000020932406,"about_ca_system_score_gemma":0.000050370876,"threshold_uncertainty_score":0.53254926},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07684191,0.000035340694,0.91647834,0.00038939415,0.0004572033,0.00014979577,0.0000012261222,0.00013157871,0.0055152145],"genre_scores_gemma":[0.7250334,0.0000041994267,0.27467525,0.00023593257,0.000039142236,0.0000044885696,4.969041e-7,0.000003654443,0.000003429583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978988,0.0000661534,0.00030736128,0.0005783647,0.00067983055,0.00046946062],"domain_scores_gemma":[0.998255,0.00020738007,0.00008809391,0.0009835592,0.00020851666,0.0002574504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007408035,0.00015263792,0.00020856297,0.00021722907,0.00025876876,0.00030748697,0.0030596335,0.000041896994,0.00013030671],"category_scores_gemma":[0.00004217246,0.00011220889,0.000069159476,0.0011284045,0.001689989,0.0016528411,0.001673912,0.00016222332,0.00010065922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010925718,0.00003956489,0.000120399585,0.000005449347,0.0000017917519,0.000003326956,0.00012644196,0.00001530394,0.0027185432,0.94888836,0.00012375032,0.04795598],"study_design_scores_gemma":[0.00013194069,0.00013577742,0.0042839115,0.000037924354,0.0000017738507,0.000023366405,0.0000042001825,0.55277836,0.013243462,0.42913505,0.000053656757,0.00017053912],"about_ca_topic_score_codex":0.000022306867,"about_ca_topic_score_gemma":1.06798005e-7,"teacher_disagreement_score":0.6481915,"about_ca_system_score_codex":0.00001830965,"about_ca_system_score_gemma":0.00008902558,"threshold_uncertainty_score":0.6226835},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09117196,0.004205095,0.901754,0.000371552,0.0006670937,0.00090595824,0.00022942928,0.00018894984,0.0005059673],"genre_scores_gemma":[0.8291175,0.000131662,0.1703094,0.00007021063,0.00020336692,0.000028559165,0.000019308807,0.000012366424,0.000107664324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844843,0.0000694909,0.0004025041,0.00042735063,0.00037496228,0.00027726672],"domain_scores_gemma":[0.99885976,0.00022833895,0.00017793347,0.0004918687,0.000110919456,0.00013120392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021264624,0.00022197209,0.0004326769,0.0001768778,0.00017579045,0.00014254796,0.00060386315,0.000089706424,0.000023955448],"category_scores_gemma":[0.00006976848,0.00016192194,0.00008802397,0.0003662011,0.0001350947,0.00045216168,0.00032208045,0.00015231085,0.000002265005],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087549,0.00011218076,0.00019334316,0.00005230126,0.000031513828,0.000010206325,0.00026783362,0.00034224422,0.0007289118,0.016503138,0.0006554567,0.9810153],"study_design_scores_gemma":[0.026066486,0.0007709337,0.09511364,0.00014885757,0.00020713151,0.00033861445,0.00010486337,0.7996349,0.024076708,0.025486859,0.026490068,0.0015609501],"about_ca_topic_score_codex":0.000073643416,"about_ca_topic_score_gemma":0.0000048832358,"teacher_disagreement_score":0.9794544,"about_ca_system_score_codex":0.000015903328,"about_ca_system_score_gemma":0.000043200926,"threshold_uncertainty_score":0.66029847},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00885549,0.00009512026,0.9896277,0.000068143076,0.00074493844,0.00023717017,0.0001272055,0.0001291744,0.00011506328],"genre_scores_gemma":[0.8386069,0.000005119525,0.16124564,0.0000145030235,0.00005704597,0.000018311865,0.0000121938965,0.0000079230995,0.00003234365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987236,0.0000849596,0.00031563142,0.00030008826,0.00033620765,0.00023946105],"domain_scores_gemma":[0.99776936,0.00042186852,0.00014559332,0.0015387947,0.00006458361,0.00005981061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011084728,0.00012711054,0.00016199276,0.00010105733,0.00037248788,0.000093272436,0.000979523,0.000037439535,0.0000043208006],"category_scores_gemma":[0.000056157387,0.000087908054,0.000047921178,0.00045050195,0.00005093674,0.0006701408,0.00005683245,0.00020773684,0.0000070320825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016116122,0.001163655,0.00067495304,0.0011055368,0.00031226958,0.00007373625,0.0036174944,0.11682294,0.033196736,0.05399875,0.0009992147,0.78787357],"study_design_scores_gemma":[0.0004520912,0.00012411799,0.0005994808,0.00043990664,0.000026277788,0.00010765125,0.00039189146,0.95498556,0.03957935,0.0003621578,0.0026030594,0.0003284636],"about_ca_topic_score_codex":0.0006743145,"about_ca_topic_score_gemma":0.00004156485,"teacher_disagreement_score":0.8381626,"about_ca_system_score_codex":0.00003277867,"about_ca_system_score_gemma":0.000041864834,"threshold_uncertainty_score":0.35847867},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13742556,0.0000061172827,0.86002463,0.00034924198,0.0007952162,0.000081615304,0.000001966964,0.00009569415,0.0012199553],"genre_scores_gemma":[0.71336377,0.0000017868914,0.28652653,0.000055682027,0.000041519943,0.0000017124714,0.000001115983,0.000002966709,0.0000049279074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823153,0.000048610513,0.00025046003,0.0005503005,0.00061298325,0.00030614075],"domain_scores_gemma":[0.9982067,0.00019710684,0.00008927973,0.0011623309,0.00018039983,0.00016423267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007263936,0.00011449926,0.00016851051,0.0001635689,0.00021097291,0.00019037304,0.0024647466,0.000044112992,0.000051130723],"category_scores_gemma":[0.00009464307,0.00008687363,0.000052789837,0.0010215981,0.0017098013,0.00090025994,0.0011999758,0.00019932161,0.00002687758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032044775,0.00004131546,0.00008845768,0.0000021278254,0.0000012300142,0.0000033152328,0.00012218016,0.000022315977,0.024219029,0.83254814,0.000022843522,0.14292586],"study_design_scores_gemma":[0.0001532627,0.00009900613,0.012942147,0.000011498055,0.000002127883,0.000027446044,0.000002811262,0.85624236,0.021523768,0.10881461,0.000057730053,0.00012325676],"about_ca_topic_score_codex":0.000010302633,"about_ca_topic_score_gemma":0.0000034941752,"teacher_disagreement_score":0.85622,"about_ca_system_score_codex":0.000012269015,"about_ca_system_score_gemma":0.00008250663,"threshold_uncertainty_score":0.6299834},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02992259,0.000009220972,0.9495593,0.00004611325,0.00015933372,0.000041636238,0.0000011702609,0.00012915755,0.020131486],"genre_scores_gemma":[0.92647475,0.0000013224425,0.07269544,0.00012275632,0.000016075403,6.7933485e-7,8.3836244e-7,0.000001698765,0.00068641815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940544,0.000017507688,0.00004965754,0.0001884761,0.00019333069,0.00014558178],"domain_scores_gemma":[0.99949884,0.000011648971,0.000009702653,0.00036963326,0.00003726276,0.00007290567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010218938,0.00004660597,0.00004455008,0.00004018897,0.00023622827,0.000028653596,0.0007692998,0.000019587816,0.0002617377],"category_scores_gemma":[0.0000018449526,0.00003447533,0.000021563936,0.00012765752,0.000019334124,0.00010407567,0.002674719,0.000052212265,0.00035475395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036328005,0.0015210402,0.039688982,0.00004128418,0.000045140463,0.00037234722,0.024241952,0.00093789236,0.00037700767,0.4728274,0.03412555,0.42578506],"study_design_scores_gemma":[0.00031242872,0.000089392975,0.041255444,0.0000102498825,0.0000022464496,0.000008744037,0.00013398557,0.953394,0.0022530442,0.0010623498,0.0012698227,0.00020831032],"about_ca_topic_score_codex":0.00024134941,"about_ca_topic_score_gemma":0.0000017537668,"teacher_disagreement_score":0.9524561,"about_ca_system_score_codex":0.000009249571,"about_ca_system_score_gemma":0.000013117807,"threshold_uncertainty_score":0.45597625},"labels":[],"label_agreement":null},{"id":"W1997102766","doi":"10.1145/1882471.1882478","title":"A brief survey on sequence classification","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":552,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Sequence (biology); Feature selection; Artificial intelligence; Feature vector; Task (project management); Feature (linguistics); Machine learning; Pattern recognition (psychology); One-class classification; Support vector machine; Data mining","score_opus":0.11534281954831148,"score_gpt":0.3164656778829131,"score_spread":0.20112285833460158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997102766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09228618,0.000009077189,0.86820585,0.035357915,0.0017942815,0.00037158906,0.000073632145,0.0004644681,0.0014370043],"genre_scores_gemma":[0.89421445,0.000008327051,0.09627791,0.008443297,0.0003719966,0.000099804434,0.00033248923,0.00001980526,0.0002319422],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984847,0.00012749773,0.00026091756,0.00053945044,0.00033203777,0.0002554012],"domain_scores_gemma":[0.9969554,0.0003475122,0.0001081661,0.0023647044,0.00011342994,0.000110779125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030919202,0.00016700443,0.00012488144,0.00013110765,0.00030147232,0.00039059843,0.0016223188,0.00010184111,0.000057383582],"category_scores_gemma":[0.0004714458,0.00014592611,0.00004387678,0.00047825347,0.00006592059,0.0015791984,0.00035742283,0.00038643295,0.0006626029],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021661474,0.00034224798,0.004535983,0.000006223268,0.000022720196,0.000026290252,0.00095429557,0.000110008754,0.45190167,0.08969273,0.3611196,0.09126659],"study_design_scores_gemma":[0.0016388189,0.00041790953,0.42252123,0.00007307317,0.000019956839,0.00004848029,0.000059683123,0.15496136,0.052407287,0.020922303,0.34502938,0.0019005279],"about_ca_topic_score_codex":0.00015286567,"about_ca_topic_score_gemma":0.00014430235,"teacher_disagreement_score":0.8019282,"about_ca_system_score_codex":0.000017287273,"about_ca_system_score_gemma":0.000071117036,"threshold_uncertainty_score":0.85166407},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01907952,0.00014576981,0.97267616,0.0004237489,0.00013059711,0.00006823318,0.000002065158,0.00013805738,0.007335879],"genre_scores_gemma":[0.94728184,0.000005350279,0.05180341,0.00014487938,0.00008896168,0.000003020392,0.00001529733,0.0000037350248,0.00065349956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993459,0.000028519034,0.0001084044,0.00026077608,0.00014226118,0.00011414705],"domain_scores_gemma":[0.9995321,0.000047524944,0.000037551876,0.00032171473,0.000026201382,0.00003491877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006732138,0.0000691549,0.00007512312,0.000037856506,0.00012719055,0.00021067026,0.0002636559,0.000031603966,0.000011751984],"category_scores_gemma":[0.0000047709927,0.00005347449,0.000015122803,0.00011318976,0.000019041601,0.00058900286,0.00025311587,0.00006411987,0.000009624209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015967007,0.00025026998,0.016232872,0.000045419183,0.000020239513,0.000115751856,0.0005130119,0.0055069732,0.022428306,0.53968596,0.07508477,0.34010047],"study_design_scores_gemma":[0.0005261524,0.000022372991,0.06585709,0.000021302349,0.0000037983477,0.000048983584,0.000027767164,0.90353096,0.0044924105,0.014559792,0.0106786275,0.00023074802],"about_ca_topic_score_codex":0.0007376746,"about_ca_topic_score_gemma":0.000022482582,"teacher_disagreement_score":0.92820233,"about_ca_system_score_codex":0.000006161435,"about_ca_system_score_gemma":0.0000074273644,"threshold_uncertainty_score":0.21806264},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64661443,0.0042451024,0.33541805,0.00815216,0.004795734,0.00013048713,0.0001272983,0.00003296931,0.00048380348],"genre_scores_gemma":[0.96350986,0.0019630243,0.032278698,0.0008493313,0.0013279524,5.990029e-7,0.000026336715,0.00000766641,0.000036552203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987963,0.000039682705,0.00031437734,0.00016570752,0.000571968,0.000112002206],"domain_scores_gemma":[0.999042,0.00006791211,0.0002519943,0.00032468032,0.00024281116,0.000070624366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025503122,0.0000991668,0.00013292374,0.000078925004,0.00018922232,0.00018105305,0.002760507,0.00003482796,0.000015784173],"category_scores_gemma":[0.0000040569967,0.000057122237,0.000041729592,0.00007283086,0.000051271592,0.0017807984,0.0006059783,0.00017248254,0.000002135902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025181312,0.0034534042,0.08814034,0.00056570413,0.0036261235,0.006403939,0.0390306,0.036759324,0.05616504,0.02704416,0.07821497,0.65807825],"study_design_scores_gemma":[0.0014955845,0.00007522624,0.009308089,0.00033098558,0.000023463048,0.0029737253,0.00023799817,0.88667107,0.0005005301,0.0014193284,0.09674972,0.00021428826],"about_ca_topic_score_codex":0.00007902455,"about_ca_topic_score_gemma":0.000018172941,"teacher_disagreement_score":0.84991175,"about_ca_system_score_codex":0.00001334941,"about_ca_system_score_gemma":0.00007201443,"threshold_uncertainty_score":0.51297545},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040651496,0.00003389234,0.9552883,0.0021986864,0.00056947384,0.00013542741,0.0000035483397,0.0002741125,0.00084507023],"genre_scores_gemma":[0.8145532,0.000008432021,0.18474935,0.00048187296,0.00015582953,0.0000045633483,0.0000010469697,0.0000063923408,0.000039290422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972736,0.00007275192,0.00019908023,0.0008440233,0.00089244015,0.00071808934],"domain_scores_gemma":[0.99804085,0.00013983864,0.00006870264,0.0011611212,0.00017341995,0.00041604985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000577727,0.00020911328,0.00022675283,0.00017450652,0.0009345006,0.0007020592,0.003420549,0.000050564042,0.000013790193],"category_scores_gemma":[0.00005931318,0.00016278081,0.0000550656,0.00095852744,0.0022470162,0.001189923,0.00214406,0.00023940958,0.000028656803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027731649,0.000035699228,0.00008978258,0.0000024527594,0.0000021512974,0.000089318615,0.00032796632,0.00002664569,0.00051870383,0.97526044,0.00013508191,0.023509009],"study_design_scores_gemma":[0.00048112386,0.000349204,0.0039704386,0.000043532746,0.000003616896,0.00037636462,0.000014739023,0.90846694,0.0059828786,0.07830171,0.0015152274,0.00049422105],"about_ca_topic_score_codex":0.0000137807865,"about_ca_topic_score_gemma":7.9368846e-7,"teacher_disagreement_score":0.9084403,"about_ca_system_score_codex":0.000070476475,"about_ca_system_score_gemma":0.00019302205,"threshold_uncertainty_score":0.82792246},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75049114,0.00041363985,0.21741936,0.0029527121,0.0022463708,0.00052687293,0.000017452558,0.0008968862,0.025035586],"genre_scores_gemma":[0.849886,0.00007664124,0.14649121,0.00077308004,0.00016447052,0.000010203401,0.00003617976,0.000018453384,0.0025437775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998957,0.000018885301,0.00020997161,0.00034374325,0.00025449987,0.00021590469],"domain_scores_gemma":[0.99927825,0.0000659917,0.00009373906,0.00037099485,0.000091573886,0.00009948276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004737044,0.00011266898,0.00011575872,0.000065145505,0.00023649403,0.000185895,0.00041351083,0.00009120492,0.00018688988],"category_scores_gemma":[0.00005101921,0.00008670802,0.00002494252,0.00020555999,0.000057844198,0.00078079227,0.0005307901,0.00029638523,0.000056834317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021028733,0.0005042873,0.17722917,0.00019715328,0.00010673466,0.00010877578,0.002143491,0.0000858731,0.062625125,0.42936996,0.089601904,0.2380065],"study_design_scores_gemma":[0.0013311417,0.00006320547,0.022486243,0.00007658489,0.000011556168,0.00017189932,0.00003269906,0.8066378,0.0005152598,0.0057536573,0.16244978,0.00047016577],"about_ca_topic_score_codex":0.000094960946,"about_ca_topic_score_gemma":0.000046785928,"teacher_disagreement_score":0.80655193,"about_ca_system_score_codex":0.000005386607,"about_ca_system_score_gemma":0.000043204276,"threshold_uncertainty_score":0.35358506},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004394346,0.0000113322885,0.97496414,0.00011365003,0.00037797992,0.00013160647,0.0000040343193,0.000094260875,0.019908646],"genre_scores_gemma":[0.49923754,0.000008712896,0.4999016,0.0006701577,0.00003737672,0.000046636615,0.000004854968,0.000001727192,0.000091392096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993373,0.0000072743296,0.00018441117,0.000102874474,0.00021149486,0.00015662416],"domain_scores_gemma":[0.99956506,0.000036511785,0.0000986681,0.00017605802,0.00008285284,0.000040830502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043668994,0.00005248494,0.000054167154,0.00010722493,0.00032202213,0.00028655276,0.0007927094,0.00002458485,0.000024416813],"category_scores_gemma":[0.000046737572,0.000040952622,0.000022068616,0.0002890949,0.000069275775,0.0057289186,0.00018691456,0.000029141915,0.0000533052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011311686,0.00004121372,0.0022067323,0.000031143292,0.000007708078,5.3723045e-7,0.014684474,0.0002910098,0.00009196767,0.31791055,0.010193366,0.65453],"study_design_scores_gemma":[0.00057103625,0.00033844038,0.017133838,0.000044374698,0.0000028307727,0.00001522605,0.00078062195,0.6744623,0.003815178,0.02825216,0.27416414,0.00041984013],"about_ca_topic_score_codex":0.000059234764,"about_ca_topic_score_gemma":0.000007233091,"teacher_disagreement_score":0.6741713,"about_ca_system_score_codex":0.000007341996,"about_ca_system_score_gemma":0.00005986308,"threshold_uncertainty_score":0.41533276},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006631662,0.000016934488,0.99247515,0.00019873833,0.0012099432,0.0005693772,0.000043665925,0.00037677924,0.0044462266],"genre_scores_gemma":[0.51319385,0.0000017453244,0.4851532,0.0009149197,0.0001414705,0.0003082197,0.00010759586,0.000013739391,0.00016524651],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980195,0.00010740572,0.00057124405,0.00026644598,0.0007458626,0.00028954705],"domain_scores_gemma":[0.99799806,0.0000699281,0.00017665476,0.0011093827,0.00030797633,0.0003379888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047459127,0.00021031986,0.00022026403,0.0003615103,0.00034919247,0.0007785773,0.001137029,0.00010951166,0.000003337096],"category_scores_gemma":[0.000035020563,0.00017618896,0.00006644811,0.0006230705,0.000015423186,0.0032520478,0.00004700272,0.00020645827,0.000277585],"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":[0.000031141273,0.00016351661,0.000011071004,0.000052882155,0.000017883553,7.6335783e-7,0.0022851587,0.87520474,0.00008669882,0.00266345,0.007039732,0.112442955],"study_design_scores_gemma":[0.0007620878,0.00014076773,0.000033606215,0.000065371445,0.0000041890694,0.000015527718,0.00035188548,0.94955826,0.00067890255,0.000046820598,0.048103753,0.0002388087],"about_ca_topic_score_codex":0.000217704,"about_ca_topic_score_gemma":8.806089e-7,"teacher_disagreement_score":0.5125307,"about_ca_system_score_codex":0.00012898297,"about_ca_system_score_gemma":0.0001362859,"threshold_uncertainty_score":0.75078386},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47277895,0.00042052747,0.52584815,0.000087357424,0.0002652678,0.0004425494,0.00012362929,0.000024996836,0.000008612287],"genre_scores_gemma":[0.56303465,0.0000110970705,0.43678293,0.00003541403,0.000075917036,0.000005844739,0.000044669727,0.000008845444,6.235019e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781966,0.000052889296,0.000875548,0.00046960879,0.00051692873,0.0002653463],"domain_scores_gemma":[0.99652016,0.00008823869,0.0006580572,0.0025190369,0.00012992688,0.00008459971],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0014291614,0.00018706569,0.00036036255,0.00021041944,0.00011159548,0.00008612265,0.0058915755,0.00005824001,0.0000018900018],"category_scores_gemma":[0.00010958211,0.00015833278,0.00003951974,0.0002845821,0.000044026034,0.0024810517,0.0037411044,0.00022553092,3.2783493e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006762268,0.0142408805,0.0099616805,0.00024386594,0.00017210406,0.00025979712,0.004535853,0.0018118859,0.080621675,0.0003309119,0.00051777577,0.8866273],"study_design_scores_gemma":[0.00866645,0.00553907,0.0015897005,0.0005232912,0.000046807683,0.00010037743,0.003485164,0.82537395,0.15335907,0.00023997715,0.0005037258,0.00057241315],"about_ca_topic_score_codex":0.0002475737,"about_ca_topic_score_gemma":0.000014082502,"teacher_disagreement_score":0.88605493,"about_ca_system_score_codex":0.00015640716,"about_ca_system_score_gemma":0.00024277363,"threshold_uncertainty_score":0.99948704},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1063875,0.000050949424,0.81794983,0.0015945322,0.00014968972,0.0003757466,0.00006561795,0.0006207116,0.07280545],"genre_scores_gemma":[0.7161655,0.000080981416,0.28206024,0.0013443597,0.00003487543,0.000017079594,0.00005576751,0.000008225936,0.00023299895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914354,0.000013271308,0.00019694766,0.00014178548,0.00026430277,0.00024012584],"domain_scores_gemma":[0.99913335,0.00005212207,0.000044406814,0.00064981455,0.00002370922,0.000096599266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010566365,0.00011238813,0.000107469044,0.000044085697,0.00014882114,0.00015956981,0.00070585887,0.000019573272,0.00030679005],"category_scores_gemma":[0.000007832563,0.00007755527,0.000020782187,0.00021828213,0.000044985994,0.0039917193,0.000074856674,0.000105570725,0.00018927963],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033686614,0.000061105835,0.00010594975,0.000079422825,0.000029729654,0.000037407408,0.004251197,0.00036890537,0.00040022066,0.012346693,0.0068206284,0.97546506],"study_design_scores_gemma":[0.00091374526,0.0002268535,0.000976856,0.00032415122,0.000016482021,0.00029569928,0.0002166365,0.43876135,0.0027084323,0.00034923368,0.55449915,0.0007114382],"about_ca_topic_score_codex":0.00006135127,"about_ca_topic_score_gemma":0.0000036210972,"teacher_disagreement_score":0.9747536,"about_ca_system_score_codex":0.000016679007,"about_ca_system_score_gemma":0.00006792666,"threshold_uncertainty_score":0.3359136},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022229224,0.000027682061,0.9762019,0.00032495783,0.00064532144,0.00022603848,0.00021494506,0.00006491287,0.00006500863],"genre_scores_gemma":[0.38960618,8.8638933e-7,0.60861313,0.0006524267,0.00035518518,0.000008677799,0.0007088789,0.000007145303,0.000047476668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895227,0.000055839184,0.00020907668,0.0002943574,0.00023730456,0.0002511505],"domain_scores_gemma":[0.9987771,0.00013865126,0.00008247131,0.0008736422,0.00004230597,0.00008584284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007429424,0.00008952624,0.000109513894,0.000046781683,0.00016329184,0.00006959714,0.0006181069,0.00002970099,0.00009312492],"category_scores_gemma":[0.000029624887,0.00006845688,0.000022754759,0.00010758674,0.000008808535,0.0015116987,0.0006371655,0.000041737487,0.00001992199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009109333,0.0007579811,0.0014251607,0.000035163128,0.000069925634,0.000001931382,0.00041768048,0.0005007523,0.0051499996,0.29696858,0.09592957,0.5986522],"study_design_scores_gemma":[0.0026741705,0.00022150476,0.007976729,0.000025595746,0.000028951281,0.000007723771,0.00007094727,0.944184,0.013821279,0.004538112,0.026007246,0.00044371522],"about_ca_topic_score_codex":0.00032094403,"about_ca_topic_score_gemma":0.000014476452,"teacher_disagreement_score":0.94368327,"about_ca_system_score_codex":0.000033211112,"about_ca_system_score_gemma":0.000042243595,"threshold_uncertainty_score":0.27915907},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56004703,0.000008797663,0.4389954,0.00006986329,0.000077667944,0.0006360969,0.0000047375047,0.000021972537,0.0001384619],"genre_scores_gemma":[0.94773287,0.0000058470796,0.052018784,0.00003470545,0.000023836856,0.000119910954,0.00001032515,0.0000023419814,0.000051375457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905,0.0000591159,0.00036183378,0.00026615974,0.0001497902,0.00011305005],"domain_scores_gemma":[0.9991864,0.000095371004,0.0001621707,0.00033982864,0.00017142596,0.000044780383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021094964,0.00008610234,0.00016710722,0.000047428883,0.00007318817,0.00006010207,0.0002847962,0.000048584203,0.000084153726],"category_scores_gemma":[0.000015838043,0.00005611044,0.000035008263,0.000116122574,0.000023378068,0.00058453344,0.0001003599,0.000030066194,0.000003539258],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008758819,0.005339383,0.006985448,0.00014010617,0.00014415375,0.00007687846,0.017517993,0.0013994988,0.19860758,0.01011544,0.009213306,0.75037265],"study_design_scores_gemma":[0.003727423,0.009009687,0.0077931196,0.00007665459,0.00003183041,0.00026324464,0.012167041,0.7155478,0.24287099,0.007220466,0.00065840327,0.0006333727],"about_ca_topic_score_codex":0.0013498345,"about_ca_topic_score_gemma":0.000091759444,"teacher_disagreement_score":0.7497392,"about_ca_system_score_codex":0.0000150529695,"about_ca_system_score_gemma":0.000026344722,"threshold_uncertainty_score":0.22881173},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039095156,0.000044213237,0.9572037,0.00077077595,0.0023356215,0.000051976538,0.000005812283,0.00002083924,0.00047189774],"genre_scores_gemma":[0.83074605,0.0000063875177,0.16870391,0.000097399105,0.0004194471,6.1105e-7,0.0000034116947,0.0000034963725,0.000019275074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970569,0.00003278736,0.0007023101,0.00025625684,0.0017460735,0.00020566539],"domain_scores_gemma":[0.9967092,0.00011176769,0.0007069386,0.00040859627,0.0019646361,0.0000988417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082558574,0.000115631956,0.00017942883,0.0006785233,0.00015813339,0.000552425,0.004117552,0.000030447958,0.000027330272],"category_scores_gemma":[0.000048673344,0.00009843816,0.00011646755,0.0005938465,0.00024507867,0.003054596,0.00075337116,0.00014125727,0.0000114626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057044526,0.0013591812,0.017152848,0.000013305922,0.00014893699,0.000190841,0.00047233602,0.056994807,0.01678605,0.35029328,0.008470036,0.5480613],"study_design_scores_gemma":[0.0013485291,0.000290278,0.11489531,0.0000992821,0.000010953978,0.00057410105,0.000014964874,0.7939208,0.010205282,0.06148019,0.016855847,0.000304436],"about_ca_topic_score_codex":0.00009076729,"about_ca_topic_score_gemma":0.000008424704,"teacher_disagreement_score":0.7916509,"about_ca_system_score_codex":0.00012429254,"about_ca_system_score_gemma":0.0004616664,"threshold_uncertainty_score":0.7651505},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011644248,0.0006502615,0.98443586,0.0023753997,0.00023138736,0.00038237893,0.000010149921,0.000037743936,0.00023256992],"genre_scores_gemma":[0.17717431,0.0006488367,0.8206807,0.00026422454,0.0010318415,0.000031731615,0.000007337961,0.00003222323,0.00012880148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985329,0.0000737056,0.00043665638,0.00024429648,0.00044256603,0.00026989623],"domain_scores_gemma":[0.9984129,0.00021211243,0.000303407,0.0005872693,0.000218008,0.0002662703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012358841,0.00013562856,0.00020628008,0.000117679025,0.00056815223,0.0005801985,0.0010011329,0.00004957709,0.0000016711424],"category_scores_gemma":[0.00005079885,0.000081440696,0.00006082,0.00032401047,0.000059094647,0.0006969646,0.0006579051,0.0006002205,0.000004398568],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001717551,0.0000419343,0.00022301589,0.000022300337,0.000024208748,0.000022754142,0.00029185606,0.000088715555,0.007897594,0.017487133,0.0007635112,0.9731198],"study_design_scores_gemma":[0.0026149251,0.0014082924,0.027806794,0.0010870453,0.00011634722,0.002961294,0.0006132737,0.59061146,0.00755692,0.080799334,0.28298274,0.0014415728],"about_ca_topic_score_codex":0.000013879483,"about_ca_topic_score_gemma":0.00000629291,"teacher_disagreement_score":0.97167826,"about_ca_system_score_codex":0.00001646167,"about_ca_system_score_gemma":0.000044263023,"threshold_uncertainty_score":0.55948675},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29056367,0.000018647797,0.7077126,0.00035774865,0.0012421589,0.0000612688,0.0000044138096,0.0000040324576,0.000035464935],"genre_scores_gemma":[0.76827455,0.00001784958,0.23151653,0.000044582022,0.00013688252,0.000001467297,8.6519907e-7,0.0000024296683,0.000004867499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982067,0.000023955223,0.0005693358,0.00017546372,0.00087752944,0.00014704201],"domain_scores_gemma":[0.9974739,0.00029428685,0.0004989747,0.000345438,0.0013267662,0.000060612434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008497873,0.00007998155,0.0001516336,0.00032609748,0.00015948823,0.00016965615,0.0033055868,0.000020884827,0.000011147364],"category_scores_gemma":[0.00008335526,0.000058271853,0.00008774636,0.0004706735,0.00037881688,0.0024506012,0.00029822206,0.00010670949,0.0000015095095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033356418,0.003227313,0.041741535,0.0000359115,0.000280249,0.00014089592,0.006785622,0.100570805,0.017745428,0.35931963,0.0010272259,0.4687918],"study_design_scores_gemma":[0.0012599654,0.00041220908,0.13275579,0.00016902343,0.000009202214,0.00078058476,0.00003397172,0.8490372,0.0032306514,0.010871367,0.0012716283,0.00016840843],"about_ca_topic_score_codex":0.00003902504,"about_ca_topic_score_gemma":0.000005983216,"teacher_disagreement_score":0.7484664,"about_ca_system_score_codex":0.00006944196,"about_ca_system_score_gemma":0.00054161006,"threshold_uncertainty_score":0.61426574},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00833196,0.000034230816,0.9208147,0.00041629537,0.000044223154,0.000053567706,0.0000012386198,0.00011762143,0.07018615],"genre_scores_gemma":[0.5935641,0.00009834887,0.40416124,0.00005845872,0.000014657976,0.0000032474907,0.000008667828,0.0000036823944,0.0020876098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995092,0.00006601076,0.00011276682,0.00010784467,0.00013779268,0.00006635248],"domain_scores_gemma":[0.99895483,0.00008414443,0.00005711728,0.0008349634,0.000040981166,0.000027959912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026097737,0.000040731666,0.000074066214,0.000026043814,0.00004411565,0.000029242876,0.0007697971,0.00002124609,0.000052470958],"category_scores_gemma":[0.000013637687,0.00003073923,0.000016375066,0.000063016814,0.000016556132,0.00026136966,0.00044479923,0.000030099496,0.00005546607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005831242,0.0001834672,0.0004800608,0.000019772397,0.000016653838,8.211127e-7,0.00050667184,0.0001578762,0.045749858,0.57246035,0.021283899,0.35913473],"study_design_scores_gemma":[0.00063273835,0.0001479466,0.0145046795,0.000067635025,0.000007510816,0.0000079933325,0.000027924225,0.87536806,0.07144735,0.024674796,0.01281716,0.000296216],"about_ca_topic_score_codex":0.00017433686,"about_ca_topic_score_gemma":0.000004194102,"teacher_disagreement_score":0.87521017,"about_ca_system_score_codex":0.000005036409,"about_ca_system_score_gemma":0.00000838249,"threshold_uncertainty_score":0.14304873},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088212015,0.00021679854,0.9888552,0.0003702443,0.0005283543,0.00008982311,0.00007241187,0.000041832467,0.0010041659],"genre_scores_gemma":[0.64870954,0.00018381963,0.3500753,0.00017296722,0.0005856368,0.0000044421927,0.00003489484,0.000025570867,0.00020785024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983815,0.000076659984,0.00038712722,0.00025463256,0.0006110966,0.00028897953],"domain_scores_gemma":[0.99843526,0.000066681576,0.00046246784,0.0004062301,0.00038823398,0.00024115319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029533307,0.00019521578,0.00028464172,0.00009887566,0.0001666296,0.00009397388,0.00063618494,0.00006726443,0.000026296158],"category_scores_gemma":[0.000027908556,0.00012904857,0.00013087124,0.0003539327,0.000097494034,0.0016027831,0.00021548294,0.00031808316,0.000017402019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003939326,0.0058294553,0.01426888,0.00027791358,0.0034687226,0.019521601,0.030561056,0.0015958827,0.004378112,0.19754575,0.119849056,0.59876424],"study_design_scores_gemma":[0.014363255,0.0147449365,0.46122298,0.0033176574,0.0005335716,0.020248557,0.003856645,0.3534727,0.052321285,0.026297146,0.045498054,0.0041232095],"about_ca_topic_score_codex":0.000056628687,"about_ca_topic_score_gemma":0.0000024183312,"teacher_disagreement_score":0.6398883,"about_ca_system_score_codex":0.00007319547,"about_ca_system_score_gemma":0.0001553972,"threshold_uncertainty_score":0.5262448},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015343056,0.0007570312,0.9464622,0.0004218634,0.0010442742,0.0007339976,0.00009261792,0.000366548,0.034778412],"genre_scores_gemma":[0.8155912,0.00020675152,0.18306258,0.0006253322,0.00011624942,0.000075214746,0.00003146653,0.000026420435,0.00026473618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978624,0.00010907289,0.00028732902,0.000898022,0.0004608386,0.00038236153],"domain_scores_gemma":[0.99668026,0.00011158426,0.00010296331,0.003005846,0.000012901672,0.00008641602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005155409,0.00022899163,0.00020339907,0.0003335852,0.00010806773,0.00017646072,0.0044398615,0.0000605691,0.00021936998],"category_scores_gemma":[0.00005391684,0.00018454253,0.00003850969,0.00029852573,0.00003738494,0.0008289977,0.0030636762,0.00018456577,0.00017017874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107560794,0.00037307086,0.00028548256,0.00005308424,0.00006395715,0.000364838,0.00031694694,0.00012966333,0.00012895241,0.021100018,0.008240119,0.9688363],"study_design_scores_gemma":[0.005045965,0.0012909673,0.5199672,0.0038594236,0.00032082832,0.00016739448,0.000704931,0.16332598,0.07337515,0.07386115,0.15191428,0.0061667343],"about_ca_topic_score_codex":0.00017261329,"about_ca_topic_score_gemma":0.000071988965,"teacher_disagreement_score":0.96266955,"about_ca_system_score_codex":0.000045473313,"about_ca_system_score_gemma":0.000015260493,"threshold_uncertainty_score":0.82504416},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22828527,0.00015952298,0.76906586,0.0001654907,0.000300049,0.00006950681,0.000014486582,0.00011579867,0.0018240241],"genre_scores_gemma":[0.19693314,0.0000052058326,0.80243427,0.00015535178,0.00015559285,0.000001088813,0.000033047203,0.0000060322363,0.00027629276],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910986,0.000038485057,0.00013824219,0.00025016064,0.00018421904,0.00027902774],"domain_scores_gemma":[0.99890137,0.000033619872,0.000036459198,0.000934214,0.000013536058,0.00008081184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040440322,0.00008436983,0.00010927114,0.00005327619,0.000101037724,0.00016261067,0.0012677518,0.0000342286,0.00010108487],"category_scores_gemma":[0.000029498626,0.00006843526,0.000010596949,0.00019354309,0.00002754797,0.0036271873,0.0019110771,0.000067520086,0.00006119488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078046396,0.0017617446,0.57858074,0.000116810275,0.000073282485,0.00013085887,0.02201201,0.0007224549,0.045311738,0.031866014,0.055078067,0.26426822],"study_design_scores_gemma":[0.00025476396,0.000026696518,0.01924663,0.000051900144,0.000003687025,0.00005685929,0.00015093795,0.9602496,0.0013650183,0.0001211375,0.018149009,0.00032375957],"about_ca_topic_score_codex":0.00014879626,"about_ca_topic_score_gemma":0.00000966937,"teacher_disagreement_score":0.95952713,"about_ca_system_score_codex":0.000018858038,"about_ca_system_score_gemma":0.000033983615,"threshold_uncertainty_score":0.2790709},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009854037,0.00006644435,0.98723537,0.00044094707,0.00064895075,0.00028910543,0.0000063700786,0.00021832109,0.0012404636],"genre_scores_gemma":[0.62140197,0.0000013335537,0.3779709,0.00037382756,0.00021990063,0.000016855716,0.0000017195905,0.000007102764,0.0000063722036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975339,0.000055722325,0.00020806053,0.00059157994,0.0007315633,0.0008791747],"domain_scores_gemma":[0.99797684,0.00030642812,0.0000727201,0.0009948194,0.00020477509,0.00044440763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011440688,0.0002108105,0.0002276184,0.000137057,0.0005581422,0.00044900944,0.002529459,0.00005134037,0.000018850564],"category_scores_gemma":[0.000037669033,0.00013970437,0.000053829495,0.0007482215,0.0016919554,0.0018809971,0.0011519783,0.00014829608,0.000033730466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016874821,0.00009108229,0.00029049302,0.000007289939,0.000004368313,0.0000012832046,0.0002904381,0.000078248486,0.0002914149,0.9523507,0.0002938984,0.046283912],"study_design_scores_gemma":[0.00093658257,0.00063456164,0.0067555737,0.0000779036,0.000013196435,0.000092159746,0.000010074696,0.92548895,0.00975608,0.049903154,0.0057056095,0.0006261624],"about_ca_topic_score_codex":0.0000031150141,"about_ca_topic_score_gemma":1.669605e-7,"teacher_disagreement_score":0.9254107,"about_ca_system_score_codex":0.000038292168,"about_ca_system_score_gemma":0.00010380615,"threshold_uncertainty_score":0.623408},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007732187,0.00018878312,0.997654,0.00007160551,0.00050565344,0.000108442495,0.000015846324,0.00020114807,0.00048127535],"genre_scores_gemma":[0.11288262,0.0000071962127,0.8865759,0.000027684533,0.00036519868,0.0000127464045,0.000015027576,0.000015321419,0.000098303055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990609,0.0000060980387,0.00012804475,0.00020619518,0.00017325571,0.0004254623],"domain_scores_gemma":[0.99927145,0.00015369587,0.000022282957,0.0002933658,0.000038733895,0.00022045044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013889134,0.00013512156,0.00013893301,0.000058053523,0.00008236015,0.000085964355,0.0004412148,0.0000660941,0.000009191567],"category_scores_gemma":[0.000029139412,0.000117540076,0.00005437944,0.00011913989,0.000019586681,0.00085004483,0.0003420766,0.00012208527,0.000022842887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000616254,0.00018713211,0.000037940295,0.00004256407,0.000027380425,0.000012069901,0.0001385396,0.0038849318,0.009340502,0.15199298,0.0025248625,0.83180493],"study_design_scores_gemma":[0.00032801417,0.00003448746,0.0003966992,0.00003405555,0.000005810147,0.000014427813,0.000013540357,0.9686204,0.0070551136,0.000035655285,0.023262361,0.00019943688],"about_ca_topic_score_codex":0.000003529857,"about_ca_topic_score_gemma":2.7024088e-8,"teacher_disagreement_score":0.96473545,"about_ca_system_score_codex":0.000032329157,"about_ca_system_score_gemma":0.000012518484,"threshold_uncertainty_score":0.4793145},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013195614,0.00082982966,0.9824403,0.0002472735,0.0014325433,0.00009780414,0.0000016566534,0.000034888537,0.0017201244],"genre_scores_gemma":[0.8134448,0.000031149473,0.1860708,0.00018325103,0.0002176875,0.0000013432768,2.1382176e-7,0.0000042478396,0.000046530953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981098,0.00024993875,0.0004793132,0.0002743892,0.00060070836,0.00028582578],"domain_scores_gemma":[0.99894476,0.00018269576,0.00038231866,0.000212889,0.00012488101,0.00015243777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002373143,0.00015016794,0.00030441766,0.00020636732,0.00051555963,0.0005480775,0.00084359886,0.000039910017,0.0000030790973],"category_scores_gemma":[0.000022189226,0.000091162256,0.00008175758,0.00031180133,0.00006677273,0.0008771485,0.00015349766,0.0001678139,0.0000047375784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003402946,0.0005290747,0.008456799,0.00035154584,0.00010714,0.00032915754,0.005152564,0.019040681,0.0003640444,0.8509945,0.014849598,0.099790834],"study_design_scores_gemma":[0.0009251205,0.0008742666,0.0014468854,0.00056847645,0.0000073368547,0.0010997922,0.00018833131,0.98365504,0.000041831994,0.0020620904,0.008894972,0.00023588761],"about_ca_topic_score_codex":0.0000060077,"about_ca_topic_score_gemma":0.0000014163213,"teacher_disagreement_score":0.96461433,"about_ca_system_score_codex":0.000020192792,"about_ca_system_score_gemma":0.000089526584,"threshold_uncertainty_score":0.5285124},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009986449,0.00026046854,0.99236774,0.001180019,0.00037043932,0.00008972895,0.0000026082043,0.00037664516,0.004353682],"genre_scores_gemma":[0.112511046,0.0000142687495,0.8823009,0.00038278304,0.0009726766,0.00002154126,0.000044620236,0.000019300074,0.003732875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898946,0.000031346237,0.00012756314,0.0003545639,0.00022654259,0.00027053742],"domain_scores_gemma":[0.99946994,0.000030577852,0.000057585512,0.00033137054,0.000057355246,0.000053151503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009651726,0.00012452474,0.00011058971,0.00006869331,0.00019833508,0.00017099502,0.00050621864,0.000078755394,0.000013995833],"category_scores_gemma":[0.000006279959,0.00010807777,0.000050508716,0.00033503363,0.000017459648,0.00055245473,0.00018747734,0.00015647587,0.00008111611],"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":[0.000008025413,0.00021135938,0.0006287524,0.0000146410075,0.000025062725,0.00006132489,0.00009280373,0.0006061239,0.006572344,0.18195897,0.23963457,0.570186],"study_design_scores_gemma":[0.0005032567,0.00007914811,0.0074399784,0.000025573978,0.000007701435,0.00012794031,0.0000070206966,0.5341353,0.008882313,0.02075573,0.42760193,0.0004341514],"about_ca_topic_score_codex":0.00012869119,"about_ca_topic_score_gemma":0.00000825447,"teacher_disagreement_score":0.56975186,"about_ca_system_score_codex":0.000033332188,"about_ca_system_score_gemma":0.000030246834,"threshold_uncertainty_score":0.44072837},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072334185,0.000021827089,0.9260376,0.0001874709,0.0006174016,0.00013090529,0.000005378036,0.00014731375,0.00051791826],"genre_scores_gemma":[0.75756586,0.0000023532727,0.24194993,0.00018864569,0.00010703692,0.0000035250919,0.000036842164,0.000007806763,0.00013800246],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907756,0.000023088147,0.00016389524,0.00031696144,0.00023606169,0.00018245667],"domain_scores_gemma":[0.9992956,0.000027083972,0.0000535262,0.00042019034,0.000080810714,0.00012278595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012451709,0.00010235507,0.000084741674,0.000077123994,0.0002468915,0.0002756178,0.00043250094,0.00006358102,0.00005699431],"category_scores_gemma":[0.000024596722,0.00008685315,0.000017149707,0.00028702265,0.000009721655,0.0009786639,0.0003223583,0.00012345801,0.000051619056],"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":[0.000002697475,0.000049484406,0.0008090841,0.00000516746,0.0000027842507,0.0000018988809,0.00013893528,0.0011868608,0.8978526,0.0055789133,0.007238613,0.08713298],"study_design_scores_gemma":[0.00016203285,0.0000220691,0.00046517598,0.000024581066,0.0000018588046,0.000008370763,0.0000055797927,0.8867617,0.0984944,0.00013181094,0.013751947,0.00017043925],"about_ca_topic_score_codex":0.00010657708,"about_ca_topic_score_gemma":0.000017291733,"teacher_disagreement_score":0.8855749,"about_ca_system_score_codex":0.000022127288,"about_ca_system_score_gemma":0.000030520016,"threshold_uncertainty_score":0.35417685},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21876065,0.00006631918,0.78024334,0.00012708471,0.00039530118,0.0002013335,0.0000041953226,0.00008800293,0.00011374846],"genre_scores_gemma":[0.60461134,0.0000020519703,0.39497402,0.00030522508,0.00007839792,0.0000016711781,0.00001711314,0.000005393185,0.0000047741064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794704,0.00015013253,0.00058288797,0.0005480282,0.00027789234,0.00049400725],"domain_scores_gemma":[0.9985819,0.00041623652,0.00016822989,0.0005381969,0.00009484438,0.00020057721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010045533,0.0001907393,0.00030469007,0.00028291694,0.00015586324,0.0001276498,0.0011428035,0.00006545431,0.000005228207],"category_scores_gemma":[0.000036443766,0.00016468189,0.000057896683,0.0007331612,0.00007250403,0.0005406827,0.0006830362,0.00021515127,0.000011052827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005378092,0.00039526273,0.051985715,0.000033680044,0.000021790946,0.00015804704,0.0062844306,0.15229057,0.00036618166,0.0010310224,0.0005280189,0.7868515],"study_design_scores_gemma":[0.0004387737,0.00012622934,0.11247237,0.00016708755,0.0000020519713,0.000022188528,0.0004365084,0.88551825,0.00012955659,0.00029799,0.00014033973,0.0002486757],"about_ca_topic_score_codex":0.0001578083,"about_ca_topic_score_gemma":0.00010399794,"teacher_disagreement_score":0.78660285,"about_ca_system_score_codex":0.000069733374,"about_ca_system_score_gemma":0.000045444573,"threshold_uncertainty_score":0.6715532},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027351256,0.00006142397,0.9713699,0.00009752508,0.0003460865,0.00010130367,0.000004212481,0.00026360794,0.00040466659],"genre_scores_gemma":[0.9483111,0.0000052768614,0.05112509,0.00017315926,0.00012570524,0.000015441776,0.000072140545,0.000010195173,0.00016189596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987661,0.000064291125,0.00022736232,0.0004313845,0.00026780757,0.00024303343],"domain_scores_gemma":[0.9990496,0.00007309209,0.00010304168,0.00060111086,0.00005664952,0.00011650642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002282236,0.00014407527,0.00014338165,0.000057587924,0.0002989869,0.0002580444,0.0006454716,0.000060361144,0.000032095675],"category_scores_gemma":[0.000018376226,0.00011624508,0.000034235585,0.00015589448,0.000010495315,0.0011933976,0.0003871699,0.00010187302,0.000039196508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061222163,0.00012439313,0.000190731,0.000011515481,0.0000030591061,0.0000013729984,0.00008929514,0.00008682947,0.30487114,0.0036065178,0.003193996,0.687815],"study_design_scores_gemma":[0.0006932009,0.00006460716,0.00005606191,0.00001887926,0.000002088482,0.0000040598547,0.000006497431,0.87276924,0.11719682,0.00029876057,0.008717602,0.00017220929],"about_ca_topic_score_codex":0.00026885275,"about_ca_topic_score_gemma":0.0000041648864,"teacher_disagreement_score":0.92095983,"about_ca_system_score_codex":0.000021909449,"about_ca_system_score_gemma":0.000018122555,"threshold_uncertainty_score":0.47403365},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017975175,0.00003243814,0.9956896,0.0007632833,0.00008400495,0.00015013243,0.0000028296938,0.0002497656,0.0012304424],"genre_scores_gemma":[0.24303146,7.7851917e-7,0.7561727,0.00061098486,0.00004391114,0.000005466914,0.000002756594,0.0000059872536,0.0001259196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982535,0.00019140384,0.00024204483,0.00047594702,0.00044568797,0.00039141416],"domain_scores_gemma":[0.9987626,0.000242204,0.000055387136,0.0007058847,0.00008493066,0.00014898232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012245206,0.0001304596,0.0001447455,0.00010458074,0.00020934873,0.00020511645,0.00087819877,0.00004398155,0.00010675355],"category_scores_gemma":[0.00004272308,0.00010084963,0.00004607925,0.00042285066,0.000029553705,0.00066152384,0.00050642574,0.00018178266,0.0000824905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037269456,0.00013342348,0.0000836939,0.000028743047,0.0000036315087,0.000005882964,0.00018772452,0.011709071,0.008508906,0.0043226704,0.00025267477,0.9747599],"study_design_scores_gemma":[0.00029925435,0.000053431522,0.00014696897,0.0000139377635,0.0000023470366,0.0000051499173,0.000022030736,0.9893715,0.008072803,0.00012213537,0.0017423109,0.00014813615],"about_ca_topic_score_codex":0.00029110265,"about_ca_topic_score_gemma":0.0000149351545,"teacher_disagreement_score":0.97766244,"about_ca_system_score_codex":0.00006320742,"about_ca_system_score_gemma":0.00020869204,"threshold_uncertainty_score":0.41125286},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001553692,0.000017079581,0.9938372,0.00027421064,0.0030881478,0.00043640425,0.000046858666,0.00054417434,0.0002022462],"genre_scores_gemma":[0.5754748,0.0000136362905,0.42364025,0.00043211086,0.00025936036,0.0000685587,0.000008989996,0.00003370325,0.00006858129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786705,0.00009405587,0.00038972823,0.0006680293,0.00043854563,0.00054258935],"domain_scores_gemma":[0.99846673,0.0002916168,0.00009196887,0.0007947293,0.000118580705,0.00023637392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041999502,0.00031541512,0.00032751187,0.00019689034,0.0006650862,0.00025895846,0.0010905231,0.00010103272,0.000010061981],"category_scores_gemma":[0.0000031689133,0.00030960984,0.0002446684,0.00031037212,0.00007841433,0.00089077646,0.000012304927,0.0003104095,0.00003416993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031744097,0.0002013798,0.0000010795607,0.000060810922,0.000048411006,0.0000033159545,0.00031322747,0.11216999,0.00043360508,0.001763092,0.00037731038,0.88459605],"study_design_scores_gemma":[0.0012541214,0.00024282839,0.00005364411,0.00013258432,0.000015534637,0.000024281462,0.00001790023,0.9747879,0.020433336,0.0006184488,0.0020251565,0.0003942838],"about_ca_topic_score_codex":0.000047307072,"about_ca_topic_score_gemma":0.000017622016,"teacher_disagreement_score":0.88420177,"about_ca_system_score_codex":0.00009069068,"about_ca_system_score_gemma":0.000051989242,"threshold_uncertainty_score":0.9999356},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05790662,0.0000037435225,0.93554175,0.00021995284,0.0004627391,0.000040582025,0.000001559266,0.00015965888,0.0056633693],"genre_scores_gemma":[0.87964815,0.0000015428254,0.11955544,0.0003249773,0.00006057238,0.0000041922854,0.000003183535,0.000003013768,0.0003989185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994752,0.000010927713,0.0000834611,0.00019123353,0.0001085099,0.00013067246],"domain_scores_gemma":[0.9993481,0.000025994688,0.000021990523,0.0005183522,0.000019880974,0.00006568753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007542305,0.00005909909,0.00005982617,0.000022366054,0.000047399568,0.00016982129,0.00059781875,0.000034646757,0.00025836102],"category_scores_gemma":[0.0000063525363,0.00004160391,0.000021950018,0.00006922897,0.000014080802,0.00038257215,0.00022383849,0.000115915376,0.00018542596],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.157965e-7,0.000036088422,0.00027900562,0.0000016456722,0.0000028566305,0.000011479136,0.00002913498,0.0000026743678,0.024412205,0.02091795,0.0026582258,0.95164794],"study_design_scores_gemma":[0.000992427,0.00017778695,0.023814581,0.000009210186,0.0000034943528,0.000075023185,0.000016564769,0.8484057,0.0233897,0.018589884,0.08394278,0.0005828281],"about_ca_topic_score_codex":0.0000729641,"about_ca_topic_score_gemma":0.000015477675,"teacher_disagreement_score":0.95106506,"about_ca_system_score_codex":0.0000014868192,"about_ca_system_score_gemma":0.000016317446,"threshold_uncertainty_score":0.2828872},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012601695,0.000023743027,0.97815526,0.003334118,0.002616892,0.00010909626,0.000001102981,0.00020305034,0.0029550293],"genre_scores_gemma":[0.8291588,0.000004221753,0.17001309,0.00052193954,0.00027581435,0.0000042741576,3.9067024e-7,0.000004538018,0.000016940296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795306,0.00005285862,0.00018532651,0.0005719789,0.00068136887,0.000555393],"domain_scores_gemma":[0.99759626,0.00041873485,0.000052069692,0.0015327599,0.0001372692,0.00026292301],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0014759321,0.00014530639,0.00011114766,0.000059576098,0.0014518496,0.0012084083,0.0051782043,0.000054572465,0.000033786466],"category_scores_gemma":[0.00011221234,0.00007864205,0.000048537695,0.0007159789,0.0035646642,0.000654105,0.0020297407,0.00047035777,0.0001183802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014694617,0.000012194038,0.000010562276,5.5299853e-7,9.0173694e-7,0.0000045360957,0.00006501805,0.0000072272824,0.0012646716,0.87240005,0.00029133554,0.12594146],"study_design_scores_gemma":[0.00013596316,0.00008790772,0.00096244004,0.00000614567,0.0000014975095,0.0000842579,0.0000021489243,0.6298554,0.004550613,0.34876063,0.015366402,0.0001865701],"about_ca_topic_score_codex":0.0000028353497,"about_ca_topic_score_gemma":0.0000019297747,"teacher_disagreement_score":0.8165571,"about_ca_system_score_codex":0.000011967548,"about_ca_system_score_gemma":0.00013475439,"threshold_uncertainty_score":0.9998481},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011446514,0.00077601866,0.99486464,0.00023820915,0.00030581665,0.00021571667,0.000020369884,0.00027072988,0.0021638344],"genre_scores_gemma":[0.23512629,0.000008849863,0.76172394,0.0004803465,0.00041066215,0.000032968408,0.000034640358,0.000018212724,0.0021641003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876815,0.000024065374,0.00021724956,0.000405815,0.0002503317,0.00033438773],"domain_scores_gemma":[0.9992653,0.0000698091,0.00006566798,0.0004650899,0.000073127434,0.00006098456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021875069,0.0001395958,0.00016962305,0.00006148115,0.00019329383,0.00030786998,0.0005475807,0.000057210338,0.000024534344],"category_scores_gemma":[0.000009705407,0.00011431083,0.000089172434,0.00011009556,0.000020646654,0.0005487542,0.00022077805,0.00007647138,0.000031240663],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014360534,0.0000545917,0.000018191888,0.0000053206463,0.0000076013916,0.000016939946,0.000049261947,0.000045498666,0.0004201808,0.007975801,0.0036567277,0.98774844],"study_design_scores_gemma":[0.0015456246,0.0001624509,0.0014200123,0.000075465854,0.000018683168,0.00008489527,0.00027246674,0.9054752,0.018465063,0.0074685006,0.06440003,0.00061162974],"about_ca_topic_score_codex":0.0013691685,"about_ca_topic_score_gemma":0.000057096535,"teacher_disagreement_score":0.98713684,"about_ca_system_score_codex":0.000033509623,"about_ca_system_score_gemma":0.000028795333,"threshold_uncertainty_score":0.46614605},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54486203,0.00017796365,0.45465514,0.00006412315,0.00008642961,0.00002966734,0.00011080462,0.0000021225283,0.00001173892],"genre_scores_gemma":[0.98317873,0.000115824805,0.0166709,0.000016122654,0.000011392126,3.2682797e-7,0.000002486741,0.0000012841209,0.0000029515327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988324,0.00015339849,0.00048880704,0.000103998005,0.00030499298,0.000116402145],"domain_scores_gemma":[0.9983233,0.0006283064,0.00060041423,0.00019305765,0.00020045812,0.00005447069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034014584,0.00008301772,0.00025043255,0.000021385353,0.0001123352,0.000014602076,0.00063847966,0.00003443629,0.0000023548143],"category_scores_gemma":[0.00044677148,0.00003908414,0.000042473494,0.00015973704,0.00065383676,0.00020729928,0.0002286146,0.00024423975,1.4511632e-7],"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":[0.00010598614,0.0003450935,0.90048957,0.00009542026,0.000052447725,0.00007929264,0.001897386,0.0042533446,0.0128302565,0.05542235,0.0004097499,0.024019113],"study_design_scores_gemma":[0.00034289024,0.0003269438,0.9529943,0.00039063834,0.000009219124,0.00016026259,0.00003922633,0.033973284,0.0054252385,0.006225857,0.00003553577,0.0000765895],"about_ca_topic_score_codex":0.00010815331,"about_ca_topic_score_gemma":0.0000025910665,"teacher_disagreement_score":0.4383167,"about_ca_system_score_codex":0.000011695407,"about_ca_system_score_gemma":0.00010684078,"threshold_uncertainty_score":0.24090888},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020000678,0.000979689,0.9769934,0.0009741589,0.0006885107,0.00015064572,0.0000041261887,0.00009985234,0.00010897122],"genre_scores_gemma":[0.3527358,0.0030500516,0.63976055,0.0013903943,0.002237295,0.00017255898,0.00011654185,0.000039001687,0.0004978229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991498,0.00001855905,0.0002111654,0.00030823157,0.00006002766,0.00025219523],"domain_scores_gemma":[0.9994644,0.00018543293,0.000039354094,0.00020493242,0.0000319522,0.00007394508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002743586,0.00013859713,0.00024193173,0.0001663781,0.000043280546,0.000012702871,0.00029967944,0.000086237735,0.00000663521],"category_scores_gemma":[0.000045048906,0.00009507135,0.000018233646,0.0002223009,0.00006063917,0.00015637574,0.00007936682,0.00011935927,0.0000031870673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023298517,0.00008699087,0.0024101709,0.00007663673,0.000030014906,0.000094868585,0.0004252522,0.00085200695,0.0836068,0.0045725354,0.0119878305,0.8958336],"study_design_scores_gemma":[0.0013470213,0.00042606148,0.0029066394,0.0001818775,0.000004971056,0.00009515448,0.000008480581,0.9160757,0.00045865503,0.0009460784,0.07736477,0.00018456756],"about_ca_topic_score_codex":0.000021750324,"about_ca_topic_score_gemma":0.0000030022065,"teacher_disagreement_score":0.9152237,"about_ca_system_score_codex":0.000011897581,"about_ca_system_score_gemma":0.000010994454,"threshold_uncertainty_score":0.3876897},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0193979,0.0000069129587,0.97653073,0.00141613,0.0005182059,0.00010653636,0.000016596732,0.00018310943,0.0018238632],"genre_scores_gemma":[0.6363735,0.0000035420564,0.36101347,0.0008281477,0.00010188882,0.0000055705164,0.00001520383,0.00000969367,0.0016489364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986571,0.0000306888,0.00014990836,0.0004235414,0.00039924346,0.00033948998],"domain_scores_gemma":[0.9986872,0.00011953663,0.000028786619,0.0009052731,0.00008418114,0.0001749956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018982089,0.00014368468,0.00011815254,0.00008569552,0.00013802724,0.00022778145,0.0011250401,0.00007793222,0.00052822294],"category_scores_gemma":[0.000035264944,0.000103830345,0.000056611327,0.00022460902,0.000033799108,0.00064238143,0.0004059123,0.00035299567,0.00029768588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012420116,0.00032245344,0.0072082644,0.00002667875,0.000019776782,0.00006802865,0.00031389637,0.0009861195,0.051946346,0.012835978,0.036727104,0.8895329],"study_design_scores_gemma":[0.00041079475,0.000047174402,0.028043365,0.000010342244,0.0000016536698,0.000012794541,0.000023885263,0.92557156,0.024606435,0.00031732884,0.020666976,0.000287717],"about_ca_topic_score_codex":0.0005320157,"about_ca_topic_score_gemma":0.000076142365,"teacher_disagreement_score":0.9245854,"about_ca_system_score_codex":0.000011198618,"about_ca_system_score_gemma":0.00012987909,"threshold_uncertainty_score":0.5783671},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016132734,0.000020611042,0.99023616,0.0001562961,0.0008995244,0.00013644662,7.944194e-7,0.00013703371,0.0067998488],"genre_scores_gemma":[0.07317839,0.000006357121,0.92631495,0.00018105618,0.0001322639,0.000006990132,0.0000068861273,0.0000068224635,0.00016626129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992329,0.000029404351,0.00013457294,0.00023279342,0.00020474313,0.00016556929],"domain_scores_gemma":[0.99936295,0.000022273984,0.00004448503,0.00039843709,0.00009628934,0.00007553952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007281968,0.00008427141,0.00008509475,0.000046551788,0.000112723515,0.00029150734,0.0005060929,0.00004877011,0.00019480225],"category_scores_gemma":[0.0000044721533,0.0000677688,0.00002409035,0.00015445755,0.0000122172605,0.0021850471,0.00040980132,0.000045820423,0.000035546127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000089826535,0.0002742508,0.00011101606,0.000018139608,0.000033117492,0.0000095717605,0.0003796897,0.35081494,0.0011229521,0.4229239,0.03497532,0.18932812],"study_design_scores_gemma":[0.00020796731,0.000014315514,0.0000162052,0.000006669748,0.0000016956251,0.0000034170912,0.0000063440857,0.9771023,0.00014459653,0.02225634,0.00013877865,0.00010139055],"about_ca_topic_score_codex":0.00036784596,"about_ca_topic_score_gemma":3.6573502e-7,"teacher_disagreement_score":0.62628734,"about_ca_system_score_codex":0.00002513643,"about_ca_system_score_gemma":0.000034055953,"threshold_uncertainty_score":0.28110123},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021032822,0.0008140361,0.99472505,0.0002580297,0.0010358061,0.00022940063,0.000010645667,0.00016622001,0.0025505023],"genre_scores_gemma":[0.06667232,0.00012396771,0.93130225,0.00097563176,0.00061951234,0.0000028676614,0.0000121871235,0.000033741337,0.00025751928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644053,0.000022131198,0.0004517618,0.0015183584,0.0009123547,0.0006548607],"domain_scores_gemma":[0.9976934,0.0003874654,0.00022162696,0.0013055142,0.00014704166,0.00024495143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008947858,0.00048212815,0.00048816763,0.0007159045,0.0003600869,0.0006618197,0.002627468,0.00027127957,0.000019167293],"category_scores_gemma":[0.000044685392,0.0004200535,0.00007532642,0.00042045332,0.0009557696,0.0008058288,0.002973107,0.0007647756,0.000018600216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004011956,0.000018726923,0.00008319807,0.000019977408,0.000005459427,0.000093732495,0.00026405463,0.0011311063,0.000045864403,0.08787189,0.000021691074,0.91044027],"study_design_scores_gemma":[0.0004276138,0.00020900178,0.0019299588,0.0005333535,0.000007659384,0.00016739295,2.4209945e-7,0.6916273,0.00068086025,0.29694477,0.006459644,0.0010121489],"about_ca_topic_score_codex":0.00006957588,"about_ca_topic_score_gemma":0.00019787288,"teacher_disagreement_score":0.9094281,"about_ca_system_score_codex":0.00015136732,"about_ca_system_score_gemma":0.0002212381,"threshold_uncertainty_score":0.9998251},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003920864,0.00003241906,0.98716444,0.0029477263,0.0012871879,0.00012871981,0.00014641686,0.000041265394,0.0043309773],"genre_scores_gemma":[0.8948642,0.000009056806,0.10290629,0.0015094313,0.0003537242,0.000010292802,0.000026872058,0.000014865634,0.000305256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998674,0.00003895342,0.00030142348,0.00018582183,0.00065342063,0.00014642798],"domain_scores_gemma":[0.99858546,0.0006827439,0.0002678015,0.00023501634,0.0001570003,0.000071976916],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00011751551,0.00012862151,0.00013109182,0.00014612213,0.0001597595,0.0015188783,0.0014549698,0.00003344387,0.00004319664],"category_scores_gemma":[0.00012384084,0.0000768583,0.0001216357,0.000088245135,0.00004296291,0.0023806475,0.00023112501,0.0001580674,0.000012766091],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023793157,0.00063614955,0.0013939742,0.000007973117,0.00009509313,0.000033417142,0.0004329003,0.0047624162,0.000076407334,0.16233167,0.012167068,0.817825],"study_design_scores_gemma":[0.0014623402,0.0005478435,0.0016447348,0.00028176792,0.000004970177,0.00003229581,0.000018741483,0.7738176,0.0021029315,0.01012544,0.20978464,0.00017668103],"about_ca_topic_score_codex":0.0000012753785,"about_ca_topic_score_gemma":7.640048e-8,"teacher_disagreement_score":0.89094335,"about_ca_system_score_codex":0.000048806363,"about_ca_system_score_gemma":0.000032755273,"threshold_uncertainty_score":0.9995176},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09182915,0.00030267492,0.9056934,0.0001704539,0.00066525635,0.000032575095,4.2678806e-7,0.000012938415,0.0012930841],"genre_scores_gemma":[0.85758054,0.000011454696,0.14217724,0.000043148055,0.00017855964,1.5375957e-7,5.4308842e-8,0.0000011044053,0.000007761422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988537,0.000039295726,0.00042156212,0.00015218441,0.00036021884,0.0001730754],"domain_scores_gemma":[0.99939376,0.00011076068,0.00021128134,0.00011421581,0.00007689312,0.000093113675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002237599,0.000064712985,0.00015962987,0.0002964285,0.00013221623,0.0002329155,0.000603253,0.00002557483,0.000001005099],"category_scores_gemma":[0.000006155652,0.00004407211,0.00003617447,0.00038797618,0.00006419349,0.00089168904,0.00017503357,0.000099734614,0.0000014144803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031190873,0.00019633373,0.024768112,0.000114220566,0.000021179769,0.0010471792,0.0025161707,0.0010418479,0.0005094236,0.6696647,0.0019835788,0.2981061],"study_design_scores_gemma":[0.0025686554,0.0023519022,0.3650681,0.002383351,0.00001497769,0.011237204,0.0019794158,0.5901868,0.0008158465,0.009500876,0.0131259635,0.0007668895],"about_ca_topic_score_codex":0.0000144843025,"about_ca_topic_score_gemma":0.0000037312675,"teacher_disagreement_score":0.76575136,"about_ca_system_score_codex":0.000024813064,"about_ca_system_score_gemma":0.00005685409,"threshold_uncertainty_score":0.22460096},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033427174,0.000049860708,0.9953879,0.0006351386,0.00024529983,0.00018384849,0.0000065634094,0.00011113353,0.000037536898],"genre_scores_gemma":[0.015468028,0.000009877189,0.9838041,0.0005447183,0.00012251487,0.000005515372,0.000033044384,0.0000078345965,0.00000436928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894744,0.00003161823,0.00030081315,0.0003183604,0.00018476648,0.00021698081],"domain_scores_gemma":[0.99921626,0.00005310514,0.00024227127,0.00034481767,0.000079419864,0.000064107866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023380523,0.000114741786,0.00013905881,0.00013848067,0.00016643478,0.00014179706,0.0005250122,0.000038469298,0.0000046176933],"category_scores_gemma":[0.000013433175,0.00010632515,0.00004999296,0.0002743997,0.000012890177,0.0004979385,0.000059718004,0.000056837012,7.8263366e-7],"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":[0.0000020887535,0.000046837547,0.000013334089,0.0000057871894,0.0000036606298,0.0000013480529,0.00014591463,0.81208634,0.0013107475,0.0010851647,0.000090569,0.18520822],"study_design_scores_gemma":[0.00029703637,0.000062037456,0.000069521746,0.000034865436,0.0000063578127,0.0000017307319,0.000011341815,0.9965792,0.0025855699,0.000051764502,0.0001694091,0.00013117096],"about_ca_topic_score_codex":0.000007452914,"about_ca_topic_score_gemma":1.14367324e-7,"teacher_disagreement_score":0.18507704,"about_ca_system_score_codex":0.00002444888,"about_ca_system_score_gemma":0.00001724544,"threshold_uncertainty_score":0.43358135},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016375242,0.000038704486,0.97125566,0.00022629762,0.00014051353,0.00005138877,0.0000028106335,0.000078143785,0.011831211],"genre_scores_gemma":[0.8848825,0.0000059394747,0.11409234,0.00006261303,0.000062905674,0.0000024721626,0.000019154435,0.000003005256,0.00086906867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993918,0.000020188723,0.00015767923,0.00017590757,0.0001608348,0.0000935922],"domain_scores_gemma":[0.9994074,0.00006234309,0.000059581278,0.00040584736,0.000042988573,0.000021852813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006966606,0.000049885966,0.00007609044,0.000055492317,0.00003888555,0.00003804047,0.0003292404,0.000022394917,0.00004220804],"category_scores_gemma":[0.0000098158425,0.000038737206,0.000028962186,0.00026489756,0.000013284169,0.00042768978,0.00016073271,0.00002950623,0.000029844394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016295517,0.00039846817,0.02825743,0.000032471708,0.000018022221,0.000033177854,0.00028267803,0.0031524613,0.015864154,0.67696005,0.060446214,0.21453857],"study_design_scores_gemma":[0.00094561686,0.00013616556,0.18223429,0.000036340476,0.0000068240024,0.000011671031,0.000033498316,0.68794906,0.062417787,0.053768653,0.01213273,0.00032735954],"about_ca_topic_score_codex":0.0008336872,"about_ca_topic_score_gemma":0.00002411279,"teacher_disagreement_score":0.86850727,"about_ca_system_score_codex":0.000005514332,"about_ca_system_score_gemma":0.000010617924,"threshold_uncertainty_score":0.15796573},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039718235,0.00022923342,0.99246466,0.0017155436,0.00021420875,0.00010010602,0.00000861134,0.00015986037,0.0011359231],"genre_scores_gemma":[0.80529135,0.000047272653,0.19288275,0.0006447914,0.00023912908,0.00000579724,0.000019766992,0.000009204329,0.00085993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987989,0.000048101938,0.00015916012,0.00042282365,0.00029473187,0.00027627868],"domain_scores_gemma":[0.99911493,0.00006700794,0.000021108155,0.000541868,0.00007963548,0.0001754627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018770045,0.00012224152,0.00012515772,0.000095760566,0.00024224089,0.00016265918,0.00051383296,0.00006764744,0.000023752033],"category_scores_gemma":[0.000013661813,0.000101692895,0.000032635253,0.00030974566,0.0000645563,0.0005736659,0.00030712484,0.00017991045,0.000092487964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043426126,0.000051810883,0.000015650572,0.0000011735776,0.0000041890085,0.000013113313,0.000083648636,0.00011175159,0.00015218132,0.0077880565,0.0037273343,0.98804677],"study_design_scores_gemma":[0.0005717757,0.0004111518,0.013780042,0.000028261335,0.000007085171,0.00012850105,0.000060962928,0.9284581,0.0010469097,0.011138765,0.044051416,0.00031706333],"about_ca_topic_score_codex":0.000043471107,"about_ca_topic_score_gemma":0.0000015475837,"teacher_disagreement_score":0.98772967,"about_ca_system_score_codex":0.000023484838,"about_ca_system_score_gemma":0.000051528878,"threshold_uncertainty_score":0.41469157},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013061019,0.0024003116,0.99136484,0.0024035412,0.0015084612,0.0003127824,0.00019526371,0.000111792266,0.00039689284],"genre_scores_gemma":[0.00381443,0.00022107933,0.9910243,0.00065966946,0.0036483663,0.000018685094,0.000024729026,0.000055900957,0.00053280743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960587,0.00012722975,0.0012782359,0.0005992906,0.0010621372,0.00087437953],"domain_scores_gemma":[0.9961445,0.00036150057,0.0010559597,0.0012328613,0.00054456526,0.0006606479],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015293132,0.00044959772,0.0007029092,0.00037637915,0.00046722378,0.0005037686,0.0032703676,0.00015292183,0.000047821173],"category_scores_gemma":[0.0003447177,0.0003535338,0.0005087175,0.000557401,0.000114691815,0.0028225908,0.0009752303,0.0006295614,0.000021208043],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032729025,0.00017452688,0.000027191947,0.000019641377,0.000103220525,0.00011242021,0.00037213572,0.0003180068,0.0002842608,0.0012348264,0.01590019,0.9814209],"study_design_scores_gemma":[0.0046193465,0.0007549371,0.00019934405,0.00035565786,0.00009636963,0.0008272882,0.00013558878,0.90955704,0.0018065714,0.011994303,0.06894996,0.00070356723],"about_ca_topic_score_codex":0.000032999877,"about_ca_topic_score_gemma":0.000015640584,"teacher_disagreement_score":0.9807173,"about_ca_system_score_codex":0.00018112925,"about_ca_system_score_gemma":0.0003332343,"threshold_uncertainty_score":0.99989164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08489986,0.00012784601,0.9125184,0.00087762193,0.00008880616,0.00009016107,0.000018281333,0.00010407206,0.0012749553],"genre_scores_gemma":[0.42162734,0.0000350474,0.57773626,0.0002083956,0.00009890372,9.773781e-7,0.000025279738,0.000005621964,0.00026213969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987902,0.00004980324,0.00016637817,0.00045216733,0.00027088204,0.00027058896],"domain_scores_gemma":[0.9984165,0.000054032487,0.000023014198,0.0014136052,0.000023592185,0.00006928325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004034231,0.00008761931,0.00010117911,0.00008697463,0.000067746216,0.00018214356,0.002094039,0.000035632547,0.000091162794],"category_scores_gemma":[0.000012987392,0.00006979741,0.000011485166,0.00032686972,0.00002549492,0.0021707795,0.0019005106,0.00012271813,0.0000618083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011993575,0.00037644315,0.009171513,0.000023942675,0.000012745992,0.0001495968,0.0010708142,0.010526207,0.021664701,0.017492568,0.007882283,0.9316172],"study_design_scores_gemma":[0.00013657189,0.000010309902,0.001987538,0.000021728003,6.274732e-7,0.000019307146,0.00001972918,0.99029964,0.0010826719,0.00009623716,0.0062178676,0.000107765256],"about_ca_topic_score_codex":0.0013125628,"about_ca_topic_score_gemma":0.0002784076,"teacher_disagreement_score":0.97977346,"about_ca_system_score_codex":0.000048247344,"about_ca_system_score_gemma":0.00008883857,"threshold_uncertainty_score":0.38912803},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034971096,0.000023856295,0.95974755,0.0019740541,0.0005115233,0.00023033837,0.0000032329556,0.00012403839,0.0024142996],"genre_scores_gemma":[0.8037187,0.0000010728177,0.19482164,0.0009958722,0.00016316619,0.000009121837,0.0000028653646,0.000009662408,0.0002778944],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985741,0.000102251266,0.00017882015,0.0004075509,0.0003869589,0.00035035313],"domain_scores_gemma":[0.9986774,0.000115566225,0.00006954339,0.0009366582,0.00007096812,0.00012989741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003343436,0.00014686031,0.00014103358,0.00007123329,0.0003685899,0.00028671464,0.00093796593,0.00004599501,0.00003168247],"category_scores_gemma":[0.00004166436,0.00009132852,0.000055923065,0.00034257403,0.00003580086,0.00020437363,0.0005712001,0.00011567489,0.00012201057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071598566,0.0007679517,0.00037994212,0.00004425216,0.000053039395,0.000010841463,0.0041079205,0.1892783,0.47331458,0.19598575,0.034152154,0.10183368],"study_design_scores_gemma":[0.0002177186,0.00005842155,0.0017671302,0.00002700938,0.0000039206056,0.000009153388,0.000030831474,0.96763664,0.0043247966,0.00072115276,0.02503895,0.00016429891],"about_ca_topic_score_codex":0.00032590146,"about_ca_topic_score_gemma":0.000011203074,"teacher_disagreement_score":0.77835834,"about_ca_system_score_codex":0.000043695425,"about_ca_system_score_gemma":0.000039751012,"threshold_uncertainty_score":0.3724269},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06986175,0.000018062348,0.9245461,0.0042226673,0.00041831913,0.00015452063,0.000019152607,0.00028551862,0.00047390955],"genre_scores_gemma":[0.891925,0.000025423551,0.061781477,0.044843823,0.0008910919,0.00006765916,0.00036239202,0.00005529175,0.00004784337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819285,0.00020856949,0.00031257686,0.000559724,0.00035625574,0.00037002843],"domain_scores_gemma":[0.99878967,0.00014614308,0.0001616053,0.000690226,0.00009350492,0.000118876254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003764555,0.00020840511,0.00019355069,0.00014288387,0.00019764196,0.00037792735,0.00082096603,0.00005944052,0.00024922125],"category_scores_gemma":[0.00004476034,0.00019345015,0.00006947955,0.00025939403,0.000020564867,0.0010263588,0.00047753868,0.00022664435,0.0006729166],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018177325,0.000032361902,0.0020790158,0.000056184897,0.000015402327,0.000014206976,0.00027518,0.00004052631,0.0029873902,0.000012150784,0.007081089,0.98740464],"study_design_scores_gemma":[0.003994954,0.00024561968,0.055216853,0.0022942652,0.000084022664,0.00021770592,0.000097276185,0.8599555,0.007361224,0.008414976,0.058837287,0.003280321],"about_ca_topic_score_codex":0.00016660834,"about_ca_topic_score_gemma":0.000006935895,"teacher_disagreement_score":0.98412436,"about_ca_system_score_codex":0.000027000848,"about_ca_system_score_gemma":0.000007780979,"threshold_uncertainty_score":0.8649206},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03171324,0.00024533324,0.967188,0.000032388634,0.00018250686,0.00046168288,0.000023232436,0.000024400742,0.00012918447],"genre_scores_gemma":[0.03949535,0.00034705945,0.95999694,0.000037792623,0.000022912089,0.00006475348,0.000023920391,0.000003818845,0.0000074601617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918854,0.000014666849,0.00037439293,0.00012449369,0.000117488686,0.00018041396],"domain_scores_gemma":[0.99945515,0.000119219345,0.00013581286,0.00019907265,0.00005391139,0.000036828173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017431627,0.000094370815,0.00015266653,0.00012640975,0.000037283462,0.000037873717,0.00023981702,0.000033105527,0.0000027833935],"category_scores_gemma":[0.00004537785,0.00007803891,0.000014293971,0.00025398604,0.00004057675,0.0012884453,0.00017719854,0.000065323315,0.0000023368175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050185947,0.00031966675,0.004002777,0.00064188533,0.000008731551,0.0000019175718,0.0026806123,0.10767003,0.0003325583,0.046230067,0.00032018975,0.8377414],"study_design_scores_gemma":[0.00054410193,0.00007962128,0.0010045883,0.00007405803,0.0000010026667,0.0000063128664,0.000103719925,0.9948739,0.00055231183,0.0010978621,0.0015568865,0.00010567738],"about_ca_topic_score_codex":0.0000898208,"about_ca_topic_score_gemma":0.000050680417,"teacher_disagreement_score":0.8872038,"about_ca_system_score_codex":0.000021702153,"about_ca_system_score_gemma":0.000030984163,"threshold_uncertainty_score":0.31823343},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30026466,0.00008407863,0.678818,0.0014317053,0.00008038891,0.00020689458,0.0000010449738,0.00018572771,0.018927522],"genre_scores_gemma":[0.8403693,0.000014322885,0.15505089,0.0014435345,0.00003451633,0.000020448726,0.000003979213,0.000006369835,0.0030566417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995296,0.000011484398,0.00005933862,0.0001879573,0.000100939185,0.00011068187],"domain_scores_gemma":[0.99962723,0.000018069239,0.000022089409,0.00023673712,0.000025409816,0.000070471266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002713646,0.00006584637,0.00006158087,0.000035947487,0.000051320254,0.00020368664,0.00023801698,0.000022858481,0.0001571463],"category_scores_gemma":[0.0000014086319,0.000036180627,0.000005967588,0.00008545208,0.000024999616,0.0008716258,0.00022152046,0.00003990368,0.00010170574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008113402,0.00011012813,0.022564555,0.00001857326,0.00004186859,0.000016949836,0.0015228397,0.0000061046303,0.0009423877,0.015065957,0.041945934,0.9177566],"study_design_scores_gemma":[0.0019529191,0.00053444476,0.32635957,0.00007530003,0.000009580002,0.000091098205,0.00027093163,0.62289435,0.0021708717,0.004176988,0.040748898,0.0007150666],"about_ca_topic_score_codex":0.0003057884,"about_ca_topic_score_gemma":0.000025852642,"teacher_disagreement_score":0.91704154,"about_ca_system_score_codex":0.000002458784,"about_ca_system_score_gemma":0.000009277633,"threshold_uncertainty_score":0.1964155},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015326553,0.010102008,0.8919877,0.0654693,0.008601577,0.0007533466,0.00018321407,0.000110102905,0.0074662147],"genre_scores_gemma":[0.91251516,0.0024405876,0.07026702,0.0089350175,0.0038650853,0.0000042565043,0.000013232586,0.000058472055,0.0019011493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520046,0.00040448338,0.0012543871,0.0005408797,0.0018338904,0.00076592545],"domain_scores_gemma":[0.9956122,0.0006555471,0.0014199613,0.0013387512,0.00050977734,0.00046373883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018204071,0.00052582624,0.00067788345,0.00025998856,0.000562083,0.0009067985,0.0036381185,0.00021395208,0.0002225335],"category_scores_gemma":[0.0003437356,0.00030156056,0.0005423505,0.00080736773,0.00020342233,0.0016053508,0.00035632422,0.001467477,0.00016233682],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019239592,0.00065968814,0.000034539207,0.00002026372,0.0002302263,0.0013309631,0.0019631397,0.0010029365,0.0018800654,0.08427198,0.09437799,0.81403583],"study_design_scores_gemma":[0.0043407576,0.014012229,0.0071809334,0.0038019528,0.0003992274,0.0035587419,0.00048322862,0.5932087,0.006549164,0.2790938,0.0849793,0.0023919614],"about_ca_topic_score_codex":0.00001903207,"about_ca_topic_score_gemma":0.0000012193941,"teacher_disagreement_score":0.8971886,"about_ca_system_score_codex":0.00015935162,"about_ca_system_score_gemma":0.00043590297,"threshold_uncertainty_score":0.9999437},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004381551,0.00017088193,0.9886375,0.00091010024,0.0019059816,0.0007028535,0.000019688181,0.00019974625,0.007409434],"genre_scores_gemma":[0.065419436,0.00007256127,0.9285024,0.0028461432,0.0013425674,0.000042638956,0.000016332437,0.00008342882,0.0016745182],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995043,0.000048057194,0.000604138,0.0023118183,0.0011698629,0.00082314666],"domain_scores_gemma":[0.99626976,0.00035279265,0.00031195045,0.002326411,0.0003341824,0.00040492372],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006952221,0.00068790297,0.000644541,0.000881635,0.00024842855,0.0006110881,0.006040474,0.0002852985,0.00005908801],"category_scores_gemma":[0.00017032225,0.00057234295,0.00014295829,0.00069428835,0.0009082168,0.0008525088,0.0039490964,0.0007719024,0.00024201139],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019567768,0.00008574064,0.000020697025,0.000042013686,0.00001893562,0.00021640878,0.0032249242,0.025287997,0.000063365515,0.076703206,0.00046152304,0.89385563],"study_design_scores_gemma":[0.00030463212,0.000538042,0.00024608138,0.00089301623,0.000010893535,0.000058875463,2.1176233e-7,0.46475783,0.0008143085,0.52093506,0.010303178,0.0011378799],"about_ca_topic_score_codex":0.00012879363,"about_ca_topic_score_gemma":0.00018234806,"teacher_disagreement_score":0.8927177,"about_ca_system_score_codex":0.0003031483,"about_ca_system_score_gemma":0.00046302922,"threshold_uncertainty_score":0.99967283},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45429483,0.000033138887,0.5419776,0.0025320833,0.0007958674,0.000031608986,0.0000060357415,0.0000056507756,0.00032319906],"genre_scores_gemma":[0.94346535,0.0000024124672,0.05608209,0.00032725846,0.00011260953,4.86652e-7,0.0000022496174,0.0000020398884,0.0000055235996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999255,0.000080750004,0.00031913217,0.000087122186,0.00016980404,0.000088191104],"domain_scores_gemma":[0.99853134,0.00069249055,0.00034924317,0.00014903868,0.00023789144,0.000039975355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042051185,0.000064555046,0.00014487527,0.000121272846,0.00004793978,0.000021751928,0.0007548782,0.000046082372,0.000038279744],"category_scores_gemma":[0.00010224299,0.000035160378,0.000100517,0.00012757744,0.00010073184,0.00012775711,0.000121703546,0.00027496374,0.0000064520286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007736803,0.00016174956,0.00087453856,0.0000030609842,0.000051536714,0.000011432342,0.00016305025,0.0011195494,0.0065458226,0.9233398,0.0038458193,0.063806295],"study_design_scores_gemma":[0.00082034944,0.0013491561,0.04775512,0.00003758421,0.000008942099,0.00044368848,0.000019221567,0.08447762,0.0018716147,0.85757816,0.0055059143,0.00013262381],"about_ca_topic_score_codex":0.0000032190837,"about_ca_topic_score_gemma":0.0000018860757,"teacher_disagreement_score":0.4891705,"about_ca_system_score_codex":0.000004884574,"about_ca_system_score_gemma":0.00007771493,"threshold_uncertainty_score":0.14337985},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13929921,0.000038667833,0.85825634,0.0010047413,0.0011589596,0.000033517168,0.0000036057588,0.000010527357,0.000194419],"genre_scores_gemma":[0.6862101,0.0000101584,0.31341955,0.00007556449,0.00027496804,3.0891516e-7,7.930567e-7,0.0000022427525,0.000006354978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975466,0.00002769154,0.00081974204,0.00019378102,0.001255657,0.00015648828],"domain_scores_gemma":[0.9964133,0.00014100765,0.0011029036,0.00032148615,0.0019348637,0.000086437416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093868683,0.000093674615,0.00018556457,0.0006045595,0.00009423726,0.00023291993,0.0035508338,0.000018536924,0.00002005619],"category_scores_gemma":[0.00009156951,0.0000805847,0.00010280405,0.0004669926,0.00025835182,0.0031965359,0.00070928334,0.00012383924,0.000005202894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007457304,0.00025104408,0.0030673814,0.000005953437,0.000046459856,0.000007978039,0.0007967012,0.016767675,0.009609021,0.032482386,0.00021811736,0.9367398],"study_design_scores_gemma":[0.0013006942,0.0003013479,0.017331725,0.0003436417,0.000013112197,0.00033929368,0.000027925156,0.91499937,0.055870198,0.006375491,0.0028583882,0.00023883613],"about_ca_topic_score_codex":0.000032021253,"about_ca_topic_score_gemma":0.0000042885185,"teacher_disagreement_score":0.93650097,"about_ca_system_score_codex":0.00007538328,"about_ca_system_score_gemma":0.00037445285,"threshold_uncertainty_score":0.6598392},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09686499,0.0004770801,0.90150535,0.0005128332,0.00024012342,0.000026601894,0.00001096087,0.000016739521,0.00034530458],"genre_scores_gemma":[0.7190417,0.0000027820863,0.2804661,0.000044418073,0.0004151789,4.8205766e-7,0.00001739437,0.0000023667837,0.000009576146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989878,0.00007713501,0.0004891494,0.00012425851,0.00018442245,0.00013722277],"domain_scores_gemma":[0.99880254,0.0003660349,0.0004889303,0.0000952545,0.00020793577,0.00003929764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003070595,0.00008452703,0.00020908986,0.00011195391,0.000098145785,0.000060598602,0.00052714493,0.00004437326,0.000005209485],"category_scores_gemma":[0.000029419713,0.000061948354,0.00007326629,0.00015100342,0.00006128626,0.00032022296,0.00011410722,0.000116642834,0.0000054917123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041210842,0.000257684,0.11206536,0.0000373988,0.00016235675,0.00006063074,0.00029319743,0.04945323,0.002745362,0.53444785,0.007321823,0.2931139],"study_design_scores_gemma":[0.0006756993,0.00029099826,0.12532501,0.000036195917,0.000012106794,0.00014796497,0.000018734672,0.05142065,0.00052644056,0.8105293,0.010809687,0.00020718551],"about_ca_topic_score_codex":0.000009597935,"about_ca_topic_score_gemma":0.0000010976332,"teacher_disagreement_score":0.6221767,"about_ca_system_score_codex":0.00002033079,"about_ca_system_score_gemma":0.00006673235,"threshold_uncertainty_score":0.25261807},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039338055,0.00010304507,0.99126244,0.0005450396,0.003923461,0.00011335046,0.000024564833,0.000044209843,0.00005010684],"genre_scores_gemma":[0.4449399,0.000019922265,0.5531676,0.000097202894,0.0017013773,0.000013462178,0.000012072455,0.000017626413,0.000030856212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900264,0.000017933915,0.00041251455,0.00014973075,0.0002877435,0.0001294477],"domain_scores_gemma":[0.99890363,0.0002081477,0.00023787565,0.000111630296,0.00045428792,0.00008444511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028127438,0.000111844434,0.0001463718,0.00033064332,0.00007263106,0.0001709025,0.00058371696,0.00007065002,0.000008288334],"category_scores_gemma":[0.0002077812,0.00010252938,0.0000835766,0.00014065501,0.000017004284,0.0007897531,0.00015286112,0.00020277848,0.0000017119423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017771724,0.00032681093,0.000566423,0.000015178077,0.0005761171,0.000102435566,0.0017511033,0.09144341,0.00047418353,0.028489554,0.013491706,0.86258537],"study_design_scores_gemma":[0.0022482295,0.00028445444,0.001111247,0.00031471762,0.00003419296,0.0003896935,0.0000564696,0.9682441,0.00047993165,0.0023893258,0.024197448,0.000250201],"about_ca_topic_score_codex":0.000009193669,"about_ca_topic_score_gemma":4.7258965e-7,"teacher_disagreement_score":0.87680066,"about_ca_system_score_codex":0.000060483693,"about_ca_system_score_gemma":0.00006577402,"threshold_uncertainty_score":0.41810268},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003007696,0.00034683003,0.9837414,0.008802851,0.0004903717,0.000139568,0.000030816424,0.00026558602,0.003174872],"genre_scores_gemma":[0.47235632,0.000058515114,0.52448785,0.0029499999,0.000052756164,0.000029510556,0.00002911073,0.00000684386,0.000029088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889874,0.00018504295,0.00021733278,0.0001829158,0.00018032377,0.00033565395],"domain_scores_gemma":[0.9962327,0.00031631938,0.00009834453,0.0031641347,0.000054956454,0.00013356228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040789117,0.00012607485,0.00012741366,0.00007750344,0.00038462415,0.00013004326,0.0031420954,0.000044715864,0.000018058749],"category_scores_gemma":[0.000036466765,0.000118299475,0.000037956605,0.00034494748,0.00022184436,0.001207472,0.00066213805,0.00022748874,0.000121896905],"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":[0.0000044877215,0.00044929993,0.0019602322,0.000021572456,0.00008090431,0.000004140019,0.0019697524,0.00027226686,0.17989062,0.7111655,0.0499529,0.054228358],"study_design_scores_gemma":[0.0013310547,0.00006744505,0.0038378055,0.00022691123,0.000061270664,0.00026665366,0.00019319926,0.3030779,0.00826499,0.00480131,0.6762887,0.0015827224],"about_ca_topic_score_codex":0.00008638021,"about_ca_topic_score_gemma":0.0000026943355,"teacher_disagreement_score":0.70636415,"about_ca_system_score_codex":0.000050397077,"about_ca_system_score_gemma":0.000046345434,"threshold_uncertainty_score":0.5838848},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026445382,0.0007257582,0.99347186,0.0005251134,0.00007568721,0.00018056895,0.000008137242,0.0002376068,0.0045107934],"genre_scores_gemma":[0.047836144,0.00055476616,0.94855964,0.0006342067,0.00016537319,0.00009509718,0.000009610067,0.000011943291,0.0021332435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910766,0.000024592822,0.00013482687,0.00037237132,0.00016994667,0.00019060912],"domain_scores_gemma":[0.9991578,0.000043851815,0.000038240847,0.00058440765,0.000044878845,0.00013081459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010100944,0.0001047673,0.000102789505,0.00007121294,0.00020119222,0.00016405167,0.0004764911,0.000051458574,0.000059871938],"category_scores_gemma":[0.0000047109957,0.00008518699,0.000027355169,0.00030882345,0.000045433415,0.00048021926,0.00035892086,0.00010357988,0.00008441601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5348444e-7,0.00008445813,0.00014898957,0.000004107675,0.0000050887456,0.00000402496,0.000125083,0.0000017753149,0.000051640684,0.02600531,0.0053186873,0.9682507],"study_design_scores_gemma":[0.0005078424,0.00008074192,0.004054802,0.000012199747,0.0000094416355,0.00010502725,0.000031612082,0.7788239,0.0004177915,0.01820521,0.1972885,0.00046292448],"about_ca_topic_score_codex":0.00013631617,"about_ca_topic_score_gemma":0.000009714193,"teacher_disagreement_score":0.96778774,"about_ca_system_score_codex":0.0000109935645,"about_ca_system_score_gemma":0.000008097446,"threshold_uncertainty_score":0.34738246},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06630898,0.00019344364,0.9313734,0.0004393826,0.00038262535,0.000096512405,0.0000029363505,0.00009064035,0.0011120577],"genre_scores_gemma":[0.813935,0.000009616299,0.1858658,0.000116300136,0.00006106533,0.0000016793167,4.9905793e-7,0.0000034404611,0.0000066415396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981678,0.000084726336,0.0002605122,0.00048949965,0.00067259656,0.0003248651],"domain_scores_gemma":[0.9984912,0.0002059706,0.000085243504,0.00065881334,0.0002461156,0.00031263396],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011775548,0.00013977752,0.0002358664,0.00015779004,0.00019757205,0.00026332051,0.0015752695,0.00004173014,0.0000059705085],"category_scores_gemma":[0.00011538708,0.000096439275,0.00003049367,0.00082155946,0.0027218512,0.0008922646,0.0015164379,0.00009981179,0.0000096078675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012739675,0.000036455494,0.00008594975,0.00000468177,0.0000017800043,0.0000051815,0.00067415007,0.000015217297,0.000110331486,0.9509099,0.00011626377,0.048027325],"study_design_scores_gemma":[0.0006518624,0.00049926207,0.0013559551,0.00003650915,0.0000054414822,0.000039593073,0.00002581199,0.49772373,0.008649216,0.48987558,0.0008905655,0.00024647816],"about_ca_topic_score_codex":0.000009779466,"about_ca_topic_score_gemma":3.0682588e-7,"teacher_disagreement_score":0.747626,"about_ca_system_score_codex":0.000019288906,"about_ca_system_score_gemma":0.0001652975,"threshold_uncertainty_score":0.9999922},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18957043,0.0015113034,0.8044892,0.00015414658,0.0019383723,0.000460521,0.000002710381,0.00028276176,0.0015905405],"genre_scores_gemma":[0.9885444,0.000013883515,0.011207061,0.000065339744,0.00012155343,0.000010984729,0.0000067784094,0.000013201554,0.00001678967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974043,0.0002607422,0.00052866014,0.0005961685,0.0004373943,0.0007727584],"domain_scores_gemma":[0.99794906,0.000421371,0.00018324694,0.0010875165,0.00012423868,0.00023455282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001995773,0.00024603997,0.000362218,0.00009390985,0.00023354903,0.00015887806,0.0012379744,0.00010768151,0.00000477495],"category_scores_gemma":[0.00031814017,0.00023436693,0.00007902589,0.00083843846,0.000062824416,0.0010684285,0.0010551912,0.00039386612,0.00003387831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010647,0.0014595251,0.28570572,0.00017017822,0.000010515865,0.000019073137,0.002380974,0.0004222839,0.000061342274,0.61038077,0.00043642664,0.098942555],"study_design_scores_gemma":[0.0062021394,0.00019151613,0.31942952,0.00046779818,0.00001396612,0.000060619564,0.00007685283,0.42750892,0.00056214805,0.2319001,0.011912679,0.0016737531],"about_ca_topic_score_codex":0.00003346726,"about_ca_topic_score_gemma":0.0000022842376,"teacher_disagreement_score":0.798974,"about_ca_system_score_codex":0.00027245132,"about_ca_system_score_gemma":0.00009365328,"threshold_uncertainty_score":0.9557206},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018653405,0.000053577023,0.99450296,0.00013641795,0.00030581668,0.0001634299,0.000038398688,0.00014957294,0.0027845108],"genre_scores_gemma":[0.2688384,0.000011891594,0.73031634,0.00014659256,0.00014712328,0.000036366306,0.000039232153,0.000014300225,0.00044973232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992329,0.00001682802,0.00012346663,0.00029375023,0.00011848097,0.00021459615],"domain_scores_gemma":[0.9993453,0.00005759951,0.000043061784,0.00038509624,0.00007766714,0.00009126571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007858857,0.00009908142,0.00009848002,0.00007074731,0.0001887953,0.000055229673,0.00060928974,0.000045726458,0.00003692563],"category_scores_gemma":[0.0000131327915,0.00008871965,0.000059324586,0.00014208336,0.00003982614,0.00055776484,0.00018393237,0.000057326622,0.000035439793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023646438,0.00026664266,0.00025725728,0.000015645044,0.000066830034,0.000042288022,0.0034260196,0.00001799669,0.0005447181,0.39533302,0.009546082,0.5904599],"study_design_scores_gemma":[0.0019873453,0.000596815,0.011917924,0.000052295673,0.000060755126,0.00008659436,0.000487371,0.7543445,0.015951937,0.11942361,0.09404319,0.0010476147],"about_ca_topic_score_codex":0.00005498476,"about_ca_topic_score_gemma":0.0000046273553,"teacher_disagreement_score":0.7543265,"about_ca_system_score_codex":0.00001667017,"about_ca_system_score_gemma":0.000048417256,"threshold_uncertainty_score":0.36178824},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018904919,0.00012768852,0.97178996,0.0017546647,0.00019423675,0.00009246511,0.0000010644555,0.00020194345,0.006933066],"genre_scores_gemma":[0.5889581,0.000007879802,0.40964952,0.0009837184,0.00008465234,0.0000056875147,0.000005258925,0.000005255425,0.00029997702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990702,0.000041268966,0.00019294102,0.00029428236,0.00019656772,0.00020471001],"domain_scores_gemma":[0.99933684,0.000075917495,0.000040869465,0.00045440413,0.000022580405,0.00006941175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019046238,0.00008945837,0.00010387199,0.000118464624,0.00006741143,0.000083811705,0.00059644645,0.000047793925,0.000067206376],"category_scores_gemma":[0.000014688628,0.00006864015,0.000026506988,0.000261564,0.000011592979,0.0005837515,0.00024566578,0.00011479657,0.000113815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013223728,0.0003046934,0.0028428663,0.000011417268,0.0000024350943,0.000022710852,0.00017794891,0.014634264,0.005677371,0.011659928,0.010080979,0.95457214],"study_design_scores_gemma":[0.00044525668,0.000018248364,0.0033323595,0.000061143495,4.3438453e-7,0.0000017521803,0.0000035126795,0.9439777,0.008928381,0.00031443313,0.042793874,0.00012290936],"about_ca_topic_score_codex":0.000059893508,"about_ca_topic_score_gemma":0.00003394599,"teacher_disagreement_score":0.95444924,"about_ca_system_score_codex":0.000028863506,"about_ca_system_score_gemma":0.00003253288,"threshold_uncertainty_score":0.27990642},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16611964,0.00005487274,0.8313465,0.00020846799,0.0009662613,0.00014594305,0.0000068352156,0.00014549891,0.0010059956],"genre_scores_gemma":[0.8390181,2.524448e-7,0.16013227,0.00020365686,0.00013520887,0.000004265183,0.000008135302,0.0000044785497,0.0004935948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999262,0.000011245076,0.000085178086,0.00024529482,0.0001824027,0.00021392103],"domain_scores_gemma":[0.99935836,0.0000976373,0.000026777856,0.000415289,0.00003760298,0.00006432476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014190027,0.00007878472,0.00007058034,0.00005921863,0.00015499818,0.0002184527,0.00075579924,0.000039220784,0.000037912025],"category_scores_gemma":[0.000047238012,0.000053064614,0.000037935566,0.00010193879,0.000022927656,0.00030556723,0.00034853688,0.00022369719,0.000011434234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011777037,0.000037505542,0.00028156317,0.000016190937,0.000009294837,0.000007848781,0.0011575203,0.00009683039,0.06752697,0.14742503,0.0059106606,0.7775188],"study_design_scores_gemma":[0.00043333764,0.00003412361,0.0074390206,0.000005500318,0.0000014336971,0.000015138327,0.00007584834,0.9647626,0.012127161,0.0031815206,0.011732856,0.00019144731],"about_ca_topic_score_codex":0.0000716603,"about_ca_topic_score_gemma":0.00003863257,"teacher_disagreement_score":0.9646658,"about_ca_system_score_codex":0.0000048050447,"about_ca_system_score_gemma":0.000026768574,"threshold_uncertainty_score":0.21639122},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01943836,0.00006581896,0.974715,0.0017460118,0.00023942855,0.00017279555,0.000010349348,0.00010984782,0.0035023824],"genre_scores_gemma":[0.4611336,0.00012757137,0.53294235,0.0006387211,0.00013745205,0.00008130235,0.000021013999,0.000028931492,0.004889061],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991568,0.0000241304,0.00019207377,0.00016680926,0.0002621286,0.0001980726],"domain_scores_gemma":[0.9988908,0.0001291352,0.000060331768,0.0007491843,0.00007470522,0.00009579915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016805842,0.00009790683,0.000099894176,0.000030514571,0.00070500426,0.00016956053,0.00091299764,0.000023991699,0.0000051343477],"category_scores_gemma":[0.000060657807,0.000059213264,0.000037960064,0.00023576536,0.000048192847,0.00019374059,0.000414909,0.000071679155,0.00022733168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013158447,0.00013158872,0.000034843564,0.000012791609,0.000016003713,0.000020040578,0.0037622675,0.000219034,0.0003133226,0.9496685,0.036221616,0.009598661],"study_design_scores_gemma":[0.00049187726,0.00011920945,0.0016005798,0.000068693735,0.000010207562,0.000121157434,0.00032547524,0.87528545,0.0025491389,0.04686179,0.07208475,0.00048170204],"about_ca_topic_score_codex":0.000006692685,"about_ca_topic_score_gemma":0.0000037973023,"teacher_disagreement_score":0.9028067,"about_ca_system_score_codex":0.000015037752,"about_ca_system_score_gemma":0.000022641016,"threshold_uncertainty_score":0.5422394},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005889579,0.00010669947,0.9912464,0.0005363072,0.00018433439,0.00029024645,0.000027061571,0.00031076136,0.0014086183],"genre_scores_gemma":[0.14922796,0.000023436958,0.8489352,0.0009907094,0.000074094765,0.000053975167,0.000028096172,0.0000126953155,0.00065387646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986597,0.000029116994,0.00021857723,0.00047604914,0.00028044364,0.00033614945],"domain_scores_gemma":[0.99881095,0.00013609727,0.00005013885,0.00073955796,0.00013580131,0.00012747743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001836743,0.00015688458,0.0001691322,0.00007330198,0.0003141344,0.00009133792,0.0010141868,0.00006964912,0.000030992676],"category_scores_gemma":[0.000020424539,0.00012857035,0.000080583035,0.0002242376,0.00003864628,0.0009196117,0.00024318152,0.00008723241,0.000022683746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018036959,0.0009603902,0.0012250262,0.00033882933,0.00010582825,0.0003778703,0.0024795444,0.036654428,0.052037343,0.11284285,0.09296617,0.69983137],"study_design_scores_gemma":[0.0005505965,0.000052621566,0.000025285908,0.000025789454,0.000002658501,0.000012420877,0.0000063702846,0.98886913,0.004811491,0.0038659335,0.0015743567,0.00020337455],"about_ca_topic_score_codex":0.00008023582,"about_ca_topic_score_gemma":0.0000028956433,"teacher_disagreement_score":0.95221466,"about_ca_system_score_codex":0.000032880413,"about_ca_system_score_gemma":0.00015862724,"threshold_uncertainty_score":0.5242946},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016377933,0.0000076279853,0.9511277,0.00071262766,0.0009679936,0.000032803942,7.890241e-7,0.00021345029,0.030559048],"genre_scores_gemma":[0.42334515,0.0000018125642,0.57336205,0.00071782287,0.00017583351,0.0000033183178,0.0000017548296,0.0000033996864,0.002388841],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996292,0.000004159322,0.00004947595,0.00013489761,0.000091556154,0.00009072377],"domain_scores_gemma":[0.9994687,0.000015762473,0.000011956262,0.00042549198,0.000018014476,0.000060072838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000061034698,0.000036771642,0.000034025412,0.000017899889,0.000049047747,0.00008055008,0.00052840955,0.000023888353,0.00017836424],"category_scores_gemma":[0.000009839872,0.00002533766,0.000014615509,0.00006987075,0.0000102496215,0.0003392482,0.0002486688,0.00008236877,0.00031487396],"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":[5.711912e-7,0.000039534483,0.0003380938,0.0000015007741,0.0000022152196,0.0000082377355,0.0000640076,8.28278e-7,0.03898056,0.6765317,0.04667758,0.2373552],"study_design_scores_gemma":[0.0002872561,0.000039887804,0.010051382,0.00000402431,0.0000012171878,0.00003612934,0.000007000573,0.1784625,0.033007916,0.017088745,0.7607459,0.00026808368],"about_ca_topic_score_codex":0.00002120946,"about_ca_topic_score_gemma":0.0000061014916,"teacher_disagreement_score":0.7140683,"about_ca_system_score_codex":0.000001337907,"about_ca_system_score_gemma":0.000014518057,"threshold_uncertainty_score":0.4047173},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032207228,0.00002553577,0.9936452,0.0009853056,0.00027353223,0.0007285518,0.000008699511,0.00018069775,0.0009317907],"genre_scores_gemma":[0.014748485,0.000002814413,0.98231995,0.000969366,0.00022282725,0.0001500699,0.000030342935,0.000016201659,0.0015399456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862903,0.00004211563,0.00031118028,0.0004137214,0.00017601567,0.00042795093],"domain_scores_gemma":[0.99869925,0.00015530243,0.00014453297,0.00071624777,0.00018492481,0.00009976511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037922378,0.00017234811,0.00019105525,0.000041350493,0.000528147,0.00046258103,0.001201479,0.000056908626,0.00011958862],"category_scores_gemma":[0.000022680388,0.00010310928,0.00009341838,0.00019701723,0.0000635564,0.0008229249,0.000691374,0.00011410925,0.00015129968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021087626,0.000060836246,0.000014783073,0.000009069857,0.00002789676,0.0000012219497,0.0002460534,0.00001545597,0.04497497,0.0053429,0.020637235,0.9286675],"study_design_scores_gemma":[0.00040613534,0.000045765468,0.00042700913,0.000008795778,0.000004119675,0.0000060320504,0.000027907936,0.9858857,0.005151295,0.0057017338,0.0021570735,0.00017842506],"about_ca_topic_score_codex":0.00076818373,"about_ca_topic_score_gemma":0.0000056143467,"teacher_disagreement_score":0.98587024,"about_ca_system_score_codex":0.000026113774,"about_ca_system_score_gemma":0.00003725972,"threshold_uncertainty_score":0.44606793},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001516425,0.00008389886,0.9863225,0.00034223232,0.00052871095,0.00008723282,5.1241045e-7,0.00015051123,0.010967958],"genre_scores_gemma":[0.9038825,0.000013646388,0.0950287,0.00018043509,0.00028155468,0.000008863882,0.000006455719,0.0000061061533,0.00059174455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929106,0.000020055048,0.000099560515,0.00015919811,0.00020981638,0.0002202781],"domain_scores_gemma":[0.99947417,0.000037497095,0.000040947263,0.0003069604,0.000037697864,0.00010271692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018042243,0.00008396019,0.0000869232,0.000041353756,0.00010264692,0.00013249526,0.00029123496,0.000026277921,0.00005696267],"category_scores_gemma":[0.00000918412,0.00005228865,0.000018165436,0.00016353483,0.000010022406,0.003458811,0.00016011839,0.00005985799,0.00010183713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012312307,0.00027292312,0.0069843754,0.000018912124,0.00004422634,0.000008953229,0.005337072,0.00014188967,0.0028622046,0.45877898,0.02747557,0.49795178],"study_design_scores_gemma":[0.011080444,0.0005210337,0.009988505,0.00015960057,0.000040461855,0.00014682376,0.0009818476,0.83176786,0.033180963,0.0118832365,0.098708235,0.0015410181],"about_ca_topic_score_codex":0.000014397616,"about_ca_topic_score_gemma":0.0000013600356,"teacher_disagreement_score":0.90236604,"about_ca_system_score_codex":0.000012168152,"about_ca_system_score_gemma":0.000014381452,"threshold_uncertainty_score":0.25075546},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014028506,0.000014411388,0.9826008,0.000007768325,0.00013786378,0.00008706574,0.0000037859945,0.0001513379,0.015594087],"genre_scores_gemma":[0.016332727,0.000005286556,0.9834489,0.00010026369,0.000020555324,0.0000035555415,0.000004475998,0.000004762774,0.00007944498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992645,0.000007728101,0.00019064065,0.00009877607,0.00019884502,0.000239543],"domain_scores_gemma":[0.99920404,0.000019409195,0.00009827679,0.0005317047,0.000037824553,0.000108736036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012591963,0.00009964133,0.000090854664,0.0000612226,0.00009527632,0.00009665549,0.00063311704,0.000036352343,0.000014922137],"category_scores_gemma":[0.000011052288,0.00006775292,0.000022868733,0.00017506427,0.000031809563,0.0011446901,0.00025591053,0.000079939586,0.00012493155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009712604,0.00043556248,0.035725694,0.00050265045,0.00009824935,0.000054895685,0.03256641,0.00090257335,0.000020233825,0.3255682,0.010589418,0.593439],"study_design_scores_gemma":[0.000491448,0.00018167577,0.006977727,0.000060524915,0.0000072066464,0.00004015373,0.0004340518,0.98433703,0.00045158505,0.0007393149,0.0059930803,0.00028617927],"about_ca_topic_score_codex":0.000018815465,"about_ca_topic_score_gemma":0.000006784814,"teacher_disagreement_score":0.9834345,"about_ca_system_score_codex":0.000016278249,"about_ca_system_score_gemma":0.00007177823,"threshold_uncertainty_score":0.2762884},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019476737,0.0003161019,0.9952342,0.0029774175,0.00024756035,0.00043498282,0.000029481582,0.000296692,0.0002687844],"genre_scores_gemma":[0.051676873,0.00012281354,0.94745874,0.00024168976,0.0001473503,0.00012059256,0.00018888063,0.000015648327,0.000027432063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863034,0.00009327734,0.00031616178,0.0004115059,0.00022916995,0.00031955767],"domain_scores_gemma":[0.9959348,0.00022821137,0.00010081415,0.0033412806,0.00025970783,0.0001351963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003092286,0.00016031417,0.00016705993,0.00014891071,0.00070191675,0.00035875596,0.0038381272,0.00007542814,0.0000026972527],"category_scores_gemma":[0.000010839038,0.00015883175,0.0000944278,0.00043709343,0.00010113267,0.00072756415,0.0019712762,0.00023419283,0.000056911165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.267475e-7,0.00016737728,0.000017006992,0.0000060876905,0.000015180405,6.43637e-7,0.0005710773,0.00068094267,0.00009846495,0.14274482,0.0003308007,0.85536665],"study_design_scores_gemma":[0.0006484894,0.000074453026,0.0015027964,0.000043544893,0.0000062288946,0.000014172429,0.000049822607,0.9759995,0.0001887032,0.008466316,0.012803552,0.00020246039],"about_ca_topic_score_codex":0.00003690194,"about_ca_topic_score_gemma":0.000014244494,"teacher_disagreement_score":0.9753185,"about_ca_system_score_codex":0.000117436335,"about_ca_system_score_gemma":0.00012313269,"threshold_uncertainty_score":0.7132259},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065730873,0.000028711222,0.9974688,0.0003270545,0.0005113252,0.0003388777,0.00005671497,0.00035980906,0.0002513518],"genre_scores_gemma":[0.3480637,0.0000025589834,0.6513606,0.0002521587,0.0001042187,0.00010651118,0.000010142401,0.000024343812,0.00007578197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806225,0.00016687404,0.0003437954,0.00072950596,0.00031510813,0.0003824902],"domain_scores_gemma":[0.9983493,0.00024618936,0.00018745702,0.0006279576,0.0004491508,0.00013996495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005457075,0.00027294783,0.00028668987,0.00021889163,0.0008709456,0.0006495035,0.0008782537,0.00009976244,0.000011961567],"category_scores_gemma":[0.000016876294,0.00022441855,0.000075830365,0.0006383937,0.00009230333,0.0028573552,0.0000102887525,0.00028780507,0.000011558263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007148563,0.00029092326,0.0000017545159,0.00010077941,0.000012378746,0.0000021251742,0.0007177689,0.0033791799,0.09828239,0.00030031533,0.00024363701,0.89659727],"study_design_scores_gemma":[0.0006041487,0.00022488978,0.000045683646,0.00012990784,0.000013012308,0.000009188002,0.000053695538,0.73688775,0.2598851,0.0009491582,0.00092211715,0.00027535026],"about_ca_topic_score_codex":0.000023133543,"about_ca_topic_score_gemma":0.0000030117558,"teacher_disagreement_score":0.8963219,"about_ca_system_score_codex":0.000043241085,"about_ca_system_score_gemma":0.00008677982,"threshold_uncertainty_score":0.91515225},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62520313,0.000038464812,0.37326035,0.00003353803,0.000018202243,0.00020173301,4.4507448e-7,0.00009494427,0.0011491835],"genre_scores_gemma":[0.91824377,0.000002510316,0.08139793,0.00006432554,0.000017027769,0.000016688935,7.6555096e-7,0.000005126479,0.00025188006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904495,0.00003134294,0.00014883536,0.00035651628,0.00021963338,0.00019869572],"domain_scores_gemma":[0.9994242,0.000024233912,0.000041844884,0.0004030007,0.000037101367,0.00006958036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008973681,0.00011192891,0.00012462644,0.00008142308,0.00016617749,0.000089138615,0.00035639232,0.000022887045,0.000009525649],"category_scores_gemma":[0.0000033991573,0.00007103189,0.000011194061,0.00041423846,0.000027497581,0.00072913704,0.00023202198,0.000098163604,0.000014076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055999248,0.0035418542,0.15401949,0.000024671306,0.0000238375,0.083010994,0.018288162,0.003941877,0.000036156343,0.0005671561,0.0020251002,0.7344647],"study_design_scores_gemma":[0.0027710968,0.001052837,0.011957498,0.00006113345,0.000005411246,0.013506106,0.0034586384,0.96586233,0.00005713369,0.00012299947,0.000636509,0.00050830573],"about_ca_topic_score_codex":0.0014941624,"about_ca_topic_score_gemma":0.0007155688,"teacher_disagreement_score":0.96192044,"about_ca_system_score_codex":0.000016746715,"about_ca_system_score_gemma":0.0000875791,"threshold_uncertainty_score":0.28965965},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016354093,0.00034517556,0.9803412,0.0001281276,0.0006180322,0.00012846584,6.856878e-7,0.000023369827,0.0020608413],"genre_scores_gemma":[0.6275097,0.000004692965,0.37218106,0.00004851298,0.0002483469,0.0000015881969,3.6792443e-8,0.0000020155946,0.0000040179034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854857,0.00006415003,0.0003966759,0.00023838058,0.0004992161,0.00025302405],"domain_scores_gemma":[0.99916035,0.00005965126,0.00026584583,0.00024018507,0.00010902038,0.00016495983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019040725,0.000109550536,0.00020650224,0.0001516767,0.00039070036,0.00047637286,0.001689489,0.000025684953,5.748275e-7],"category_scores_gemma":[0.000004843435,0.000055895343,0.00005643938,0.00042967364,0.000064082575,0.0008420844,0.00052460004,0.00012787637,0.0000030904064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030704854,0.00026568532,0.008858192,0.00021340176,0.00008660031,0.000086096385,0.014367275,0.0044714003,0.000100847436,0.46696773,0.005343566,0.49920848],"study_design_scores_gemma":[0.0006968273,0.001388211,0.02915178,0.00096517685,0.000025692205,0.0032595722,0.001249461,0.9539164,0.0002476362,0.0035201018,0.005098691,0.00048046236],"about_ca_topic_score_codex":0.000043140095,"about_ca_topic_score_gemma":0.000002859286,"teacher_disagreement_score":0.949445,"about_ca_system_score_codex":0.000020067122,"about_ca_system_score_gemma":0.00008298285,"threshold_uncertainty_score":0.45936745},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06375924,0.00068071246,0.934212,0.0011193473,0.000067243345,0.00010930053,0.0000012602246,0.00001624972,0.000034643243],"genre_scores_gemma":[0.55897987,0.0005768413,0.44034734,0.00005353341,0.000035611913,0.0000016989019,9.123447e-7,0.000001978963,0.0000022305933],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927294,0.000020099866,0.00044073738,0.000043764278,0.00010091052,0.00012151951],"domain_scores_gemma":[0.9989922,0.00016548502,0.00057821744,0.0000993773,0.00014643384,0.000018291475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007163904,0.000051339248,0.000103127604,0.0001764875,0.00022520732,0.000108779015,0.00022664882,0.00003251993,0.0000016175013],"category_scores_gemma":[0.000018531911,0.00003444731,0.000019480041,0.00013622617,0.000037778642,0.00084280106,0.00014428503,0.00007395271,3.1932706e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038074197,0.0000041299045,0.00014610593,0.000011863421,0.00001073356,2.8563807e-7,0.0011186465,0.000024870189,0.00018777742,0.06782124,0.0015417789,0.92912877],"study_design_scores_gemma":[0.004548514,0.0017616135,0.005001483,0.00018909742,0.00002404062,0.00075890194,0.01800058,0.29614127,0.014240173,0.025008293,0.63397384,0.000352224],"about_ca_topic_score_codex":0.0000011707713,"about_ca_topic_score_gemma":1.9285986e-7,"teacher_disagreement_score":0.9287765,"about_ca_system_score_codex":0.000008630387,"about_ca_system_score_gemma":0.000009285263,"threshold_uncertainty_score":0.17321353},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07584103,0.000028322345,0.8836715,0.03821202,0.00014751976,0.0005555182,0.0000062984004,0.00008902285,0.0014487173],"genre_scores_gemma":[0.7071477,0.000016630282,0.27872276,0.0092258165,0.00036171434,0.00086449424,0.000031897616,0.000025442223,0.0036035571],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979918,0.00039915228,0.00015160743,0.0004055073,0.00059230434,0.0004596183],"domain_scores_gemma":[0.99839765,0.00013605547,0.0000046889113,0.0009714404,0.00025179674,0.00023839115],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00094271486,0.00008762092,0.000082719074,0.00028540537,0.00046299558,0.001084158,0.0012582914,0.0000317588,0.00025438413],"category_scores_gemma":[0.00019601038,0.00006924534,0.000028525235,0.00069819635,0.00007698259,0.0012694562,0.0008097259,0.00028314174,0.0033112022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010152697,0.00016807826,0.000051767136,0.000012065436,0.000026317164,0.00004643614,0.004613219,0.018263372,0.15753497,0.23300444,0.40884274,0.17742644],"study_design_scores_gemma":[0.0006642265,0.00032034316,0.0051615504,0.00011898056,0.0000026304301,0.000029178984,0.00049647834,0.7254197,0.011475674,0.005841671,0.24976774,0.0007018075],"about_ca_topic_score_codex":0.00073524256,"about_ca_topic_score_gemma":0.000042568507,"teacher_disagreement_score":0.70715636,"about_ca_system_score_codex":0.00006182735,"about_ca_system_score_gemma":0.00007741674,"threshold_uncertainty_score":0.9999528},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005060575,0.000028450235,0.9729152,0.00086176983,0.0002551082,0.000029083261,3.5117057e-7,0.00018708165,0.02521694],"genre_scores_gemma":[0.69302297,0.000014183281,0.30319417,0.0009477035,0.00021090156,0.000009322882,0.0000042011748,0.0000067198007,0.002589843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941957,0.000027113521,0.0000816776,0.00019327278,0.00013904342,0.000139315],"domain_scores_gemma":[0.9994337,0.000043829874,0.000017798613,0.0004156656,0.000023890567,0.00006512212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010883221,0.00006172057,0.00007519533,0.00002509844,0.00007424353,0.00010204913,0.0004954681,0.000027503213,0.00006871195],"category_scores_gemma":[0.000019511086,0.000042676136,0.000022969369,0.00010039864,0.000018737494,0.00038762615,0.00029662723,0.000048288657,0.00024299628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016023349,0.00002905408,0.00031533217,0.0000027104718,0.0000016836345,0.0000039032902,0.00006282555,0.0000024331307,0.000063839754,0.8303775,0.016561743,0.15257733],"study_design_scores_gemma":[0.00035069213,0.000121191275,0.0058374107,0.0000041379794,0.0000018774823,0.00002918238,0.000009471747,0.28214657,0.0006424368,0.047724307,0.66288364,0.00024908918],"about_ca_topic_score_codex":0.00007766902,"about_ca_topic_score_gemma":0.0000036832648,"teacher_disagreement_score":0.7826532,"about_ca_system_score_codex":0.00000716827,"about_ca_system_score_gemma":0.00001011438,"threshold_uncertainty_score":0.31233066},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018325777,0.00014995174,0.9777534,0.0015728392,0.000513373,0.00035775994,0.00006449077,0.00049050985,0.017265106],"genre_scores_gemma":[0.8635343,0.00007940918,0.12864348,0.00076391833,0.0010560104,0.00022373023,0.0008955357,0.00008734554,0.004716273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975722,0.00007487318,0.0003367503,0.0008207485,0.00067886413,0.0005165826],"domain_scores_gemma":[0.9982786,0.0001028009,0.00017171702,0.001140595,0.00015163187,0.00015463996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019949411,0.00032054223,0.00025708345,0.00030450572,0.00040783052,0.00036984822,0.00083701755,0.000103035156,0.000023426092],"category_scores_gemma":[0.000010961977,0.00024214508,0.00008829184,0.0012856,0.00007017443,0.0009218325,0.00022738219,0.00022102009,0.00021930085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039848703,0.0029109565,0.006383965,0.00016192628,0.00039875295,0.00034130475,0.0005523019,0.06426985,0.023769716,0.18741316,0.2557336,0.45766598],"study_design_scores_gemma":[0.0037180732,0.002015228,0.028324818,0.00014623714,0.00007555727,0.00010919437,0.00007188054,0.78265893,0.012140311,0.0058780448,0.16304965,0.001812047],"about_ca_topic_score_codex":0.00039328507,"about_ca_topic_score_gemma":0.00002934847,"teacher_disagreement_score":0.8617017,"about_ca_system_score_codex":0.00009959088,"about_ca_system_score_gemma":0.00008509133,"threshold_uncertainty_score":0.987439},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33498695,0.0003193225,0.65311176,0.0023181217,0.00010376404,0.00009945495,0.0000016646596,0.000017058452,0.009041877],"genre_scores_gemma":[0.42386773,0.0010709873,0.5742401,0.00039316734,0.00008188974,0.0000020052817,2.5893652e-7,0.0000032612866,0.00034064532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902254,0.00003879299,0.00029461845,0.00013013983,0.00039922906,0.00011470574],"domain_scores_gemma":[0.9994482,0.000060293045,0.00019434048,0.0001852686,0.00002789871,0.000084028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005330656,0.00006692703,0.00018171608,0.000093359624,0.00009071198,0.000083051214,0.00073826726,0.0000074265645,0.000078347766],"category_scores_gemma":[0.000018115315,0.00004147892,0.000039762584,0.00030463992,0.000364851,0.0005278222,0.00016389875,0.000039439663,0.0000044652347],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005741296,0.00011817702,0.000053345688,0.0000232787,0.000022042243,0.000013961988,0.00023290986,0.00016288397,0.00016247801,0.10283302,0.0021274395,0.89424473],"study_design_scores_gemma":[0.0022712671,0.006500243,0.009102059,0.0009573822,0.0001913071,0.0006151615,0.0021672745,0.53931,0.0028665264,0.41688043,0.018155966,0.0009823991],"about_ca_topic_score_codex":0.000004465398,"about_ca_topic_score_gemma":4.731801e-7,"teacher_disagreement_score":0.8932623,"about_ca_system_score_codex":0.0000037339807,"about_ca_system_score_gemma":0.000014217455,"threshold_uncertainty_score":0.16914612},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13632408,0.000059020214,0.8605396,0.0005057146,0.0024695157,0.000032148175,0.0000074351015,0.000005555289,0.000056945195],"genre_scores_gemma":[0.79083455,0.000017383323,0.20894246,0.000035003115,0.00016341328,4.2449376e-8,5.5170096e-7,0.0000016765507,0.000004957279],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997879,0.00002154812,0.0006044656,0.00012867345,0.0012272922,0.00013901714],"domain_scores_gemma":[0.9962382,0.00035008672,0.00080053735,0.00032711017,0.0022134231,0.00007069799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079006515,0.00007176904,0.000118178126,0.0003431598,0.00016822788,0.00024816138,0.0039866925,0.000021218833,0.000008402202],"category_scores_gemma":[0.00013753262,0.000045711353,0.00007394431,0.00048060983,0.00040675842,0.0015881615,0.000503912,0.00011530609,0.0000011071909],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031527077,0.000112387315,0.0015443832,0.0000041093654,0.00006304162,0.000011047883,0.00075810595,0.0012971598,0.049261134,0.11918448,0.00031072964,0.8274219],"study_design_scores_gemma":[0.0018372865,0.0009044193,0.3025775,0.00041908203,0.000021951744,0.00090972055,0.00015617187,0.20816581,0.38206834,0.073587626,0.028830767,0.0005213387],"about_ca_topic_score_codex":0.0000105240815,"about_ca_topic_score_gemma":0.0000065563754,"teacher_disagreement_score":0.82690054,"about_ca_system_score_codex":0.00005158924,"about_ca_system_score_gemma":0.00034551785,"threshold_uncertainty_score":0.74083334},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013002754,0.00006021274,0.9836421,0.00012722964,0.00040767787,0.00019252986,0.000015082214,0.00021807947,0.0023343393],"genre_scores_gemma":[0.9920301,0.000097326636,0.007531668,0.00011683371,0.00003437559,0.000013734998,0.000009933687,0.0000040376362,0.00016198803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990626,0.000029932677,0.0003299717,0.00013166663,0.00029437328,0.00015148705],"domain_scores_gemma":[0.9991835,0.00007796292,0.00006443737,0.00054764457,0.00005208332,0.00007438549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022744467,0.00010287245,0.00011158032,0.00014333999,0.00030998487,0.0004435837,0.00040549645,0.00006245962,0.000043636253],"category_scores_gemma":[0.000008642032,0.00009163724,0.000030430127,0.0002940403,0.000016043248,0.0035181344,0.000009782622,0.00013411762,0.00017339402],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043253345,0.000025216608,0.00003579896,0.00003661267,0.000021279813,0.000001843004,0.001730597,0.016313493,0.00003932846,0.0016224592,0.0001940818,0.97993606],"study_design_scores_gemma":[0.0019754178,0.00023771152,0.003681121,0.0003806465,0.000024776495,0.00031432242,0.0005997243,0.77433115,0.0015361984,0.00048286526,0.21570343,0.0007326474],"about_ca_topic_score_codex":0.00004718519,"about_ca_topic_score_gemma":6.068114e-7,"teacher_disagreement_score":0.9792034,"about_ca_system_score_codex":0.000030275138,"about_ca_system_score_gemma":0.000020941407,"threshold_uncertainty_score":0.4277488},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1280967,0.00022050411,0.870279,0.00012751498,0.0010245674,0.00009063702,0.0000011172194,0.00002312791,0.00013683732],"genre_scores_gemma":[0.5260027,0.0000031259835,0.47362262,0.000032556713,0.00032445352,4.291334e-7,1.1293066e-7,0.0000025186025,0.000011462371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855685,0.000036988924,0.00047403207,0.00021647243,0.00043023535,0.00028542083],"domain_scores_gemma":[0.9990218,0.000195188,0.00036782128,0.00014091448,0.0001345765,0.00013969516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002842361,0.00011615749,0.00025572747,0.00022683151,0.0003212625,0.000588172,0.0007786054,0.000037142225,4.3608804e-7],"category_scores_gemma":[0.00000442192,0.00007630422,0.00007844191,0.00022267821,0.000056213416,0.0011878113,0.00026090193,0.00009490303,6.717566e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023147737,0.00027978036,0.0047572944,0.0011406383,0.00021229961,0.00038068226,0.015024509,0.041160103,0.0059819804,0.30443513,0.004017284,0.6223788],"study_design_scores_gemma":[0.0009312855,0.0007379218,0.002264638,0.00057246635,0.000012980317,0.0014551977,0.001209683,0.9892783,0.0009487065,0.0007464544,0.001574217,0.00026814244],"about_ca_topic_score_codex":0.0000042792935,"about_ca_topic_score_gemma":5.553368e-7,"teacher_disagreement_score":0.9481182,"about_ca_system_score_codex":0.000025021965,"about_ca_system_score_gemma":0.000055585224,"threshold_uncertainty_score":0.5671756},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6474295,0.0009997489,0.3469496,0.0010807079,0.0014157905,0.00034135574,0.0000072413272,0.00016476904,0.0016112583],"genre_scores_gemma":[0.9884163,0.00012312109,0.011098705,0.00019578305,0.00003755519,0.0000061693677,0.0000042825236,0.000012079269,0.00010601726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875194,0.000047299636,0.00029442774,0.00026792337,0.00032488635,0.000313512],"domain_scores_gemma":[0.9984302,0.0001176688,0.00018468675,0.00070636783,0.00041650797,0.00014456832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017682306,0.00014395516,0.0002231109,0.00012649733,0.00017807444,0.00012206125,0.0009015128,0.00008129809,0.00001978893],"category_scores_gemma":[0.00006465039,0.00012865334,0.00008278473,0.00052726996,0.000037820482,0.00082797685,0.00048454455,0.00011342077,0.000032648433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026362492,0.0029098594,0.01033389,0.00022265832,0.00023837996,0.00017272295,0.0034667607,0.0033303571,0.052488137,0.47268224,0.13894449,0.31518415],"study_design_scores_gemma":[0.00065122027,0.00044611786,0.016306791,0.00028606423,0.00001659598,0.00005192243,0.00009408804,0.7788288,0.038139697,0.15746938,0.0069970815,0.0007122586],"about_ca_topic_score_codex":0.00023189733,"about_ca_topic_score_gemma":0.0000012489791,"teacher_disagreement_score":0.77549845,"about_ca_system_score_codex":0.000012116407,"about_ca_system_score_gemma":0.0000697985,"threshold_uncertainty_score":0.52463305},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93331677,0.0006595729,0.0636157,0.0010712491,0.0006950746,0.00027428387,0.000007185147,0.000015811433,0.00034434185],"genre_scores_gemma":[0.98760134,0.00003204457,0.012146372,0.00017610949,0.000034836263,0.0000022384495,1.6710854e-7,0.000003273857,0.000003638755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975501,0.0006387925,0.0006069323,0.0002758775,0.0006932274,0.00023509096],"domain_scores_gemma":[0.99804544,0.00068804173,0.00056122785,0.00045879633,0.00013629803,0.00011019566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023893076,0.00017483193,0.00042016708,0.000084785854,0.0005583684,0.00046751392,0.0015797702,0.000044979734,0.0000019657566],"category_scores_gemma":[0.000036585265,0.000081216764,0.000084515166,0.00042913246,0.0010732646,0.0005990492,0.00030314416,0.00023076321,5.71121e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039433296,0.0002885869,0.0511069,0.0002519882,0.00008545555,0.000067985486,0.0032644062,0.0028129683,0.0048775175,0.92253757,0.0010942381,0.013572974],"study_design_scores_gemma":[0.0024082614,0.0043463963,0.15466848,0.004789976,0.000087485896,0.006721364,0.0014675324,0.76623845,0.0073670186,0.049544413,0.001302289,0.0010583145],"about_ca_topic_score_codex":0.0000614888,"about_ca_topic_score_gemma":0.000012419088,"teacher_disagreement_score":0.8729931,"about_ca_system_score_codex":0.000025080972,"about_ca_system_score_gemma":0.00010200548,"threshold_uncertainty_score":0.45082477},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004210732,0.000047537298,0.9949234,0.0003308533,0.00015365933,0.00017716512,0.000024159115,0.00010336683,0.000029118823],"genre_scores_gemma":[0.9793191,0.00014216156,0.019996597,0.00030121233,0.000013407543,0.000043858417,0.000008621713,0.0000069256307,0.00016809229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986936,0.00007602169,0.00029600228,0.00049042876,0.00023970041,0.00020426727],"domain_scores_gemma":[0.9990509,0.00007235454,0.00009019429,0.0005535998,0.000095922915,0.00013699109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015483542,0.0001835492,0.00022131625,0.00032971113,0.0002566723,0.00024983718,0.00044557053,0.000058708636,0.000301853],"category_scores_gemma":[0.000003617657,0.00014376473,0.00014236168,0.00073769875,0.000043341843,0.0006268311,0.00001071062,0.00021728963,0.00017142452],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021115015,0.00021879723,0.00032498626,0.000008245541,0.00014524994,0.0000044722433,0.0001726639,0.0056312364,0.00088652066,0.000034364188,0.000024177809,0.99254715],"study_design_scores_gemma":[0.00008415773,0.00007753142,0.0058988333,0.000013675679,0.00011006068,0.000006135095,0.000021686821,0.92398024,0.069364965,0.00014361972,0.00007850431,0.00022059039],"about_ca_topic_score_codex":0.0026652238,"about_ca_topic_score_gemma":0.0004883815,"teacher_disagreement_score":0.99232656,"about_ca_system_score_codex":0.00001978763,"about_ca_system_score_gemma":0.000012993667,"threshold_uncertainty_score":0.58625555},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14873473,0.00008591694,0.84960055,0.00042498476,0.00037399435,0.00027302274,0.000009152912,0.00010121851,0.0003964101],"genre_scores_gemma":[0.7699088,0.0000057944,0.22969788,0.00027855116,0.00008485714,0.000010213295,0.0000015345574,0.0000050541958,0.000007320192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978343,0.000100408215,0.0002818612,0.00060332665,0.00044038182,0.0007396901],"domain_scores_gemma":[0.9984227,0.00045668188,0.00007486154,0.0005974925,0.00009314488,0.0003551607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021595357,0.00018649091,0.0002850751,0.0001594549,0.00031603896,0.0003359932,0.001221785,0.00005761472,0.00001803009],"category_scores_gemma":[0.0001119624,0.00014073876,0.000041739124,0.00062182866,0.0016964732,0.0011795447,0.0013580889,0.0001463056,0.000022063183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003477988,0.00010627114,0.0010205376,0.000010402735,0.0000022038305,0.000006469925,0.0006602316,0.000013248068,0.0017168534,0.9628594,0.00019908446,0.033370536],"study_design_scores_gemma":[0.00067845464,0.00015142138,0.003827511,0.0000544968,0.000004446381,0.000055048225,0.000008261227,0.9371369,0.0027814112,0.054682974,0.0003498531,0.00026924297],"about_ca_topic_score_codex":0.000006447243,"about_ca_topic_score_gemma":0.0000019261709,"teacher_disagreement_score":0.93712366,"about_ca_system_score_codex":0.00004414668,"about_ca_system_score_gemma":0.00007606014,"threshold_uncertainty_score":0.62507266},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019079885,0.0000072712733,0.9603202,0.012262864,0.00043203385,0.00048591994,0.000013408097,0.00037620496,0.0070222416],"genre_scores_gemma":[0.16359353,0.0000053552694,0.8210383,0.0053437287,0.00041099885,0.00021651873,0.000007894676,0.000019142652,0.009364509],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990151,0.0000078082685,0.00014375009,0.00039297168,0.00018872811,0.00025164714],"domain_scores_gemma":[0.9987022,0.00006778277,0.000038905357,0.0009715993,0.000041402396,0.00017808605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012263925,0.00011781541,0.000103375205,0.000045923352,0.00014987998,0.00018473885,0.0010299319,0.000052789634,0.000272076],"category_scores_gemma":[0.000008922315,0.00009372353,0.00003281979,0.00025116486,0.000023884773,0.00061504106,0.00040047485,0.00016865933,0.0018568755],"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":[0.000007415365,0.00018482305,0.00020805404,0.00002398805,0.000012030592,0.000002693465,0.0003577391,0.000027871918,0.4619678,0.02482357,0.087437205,0.4249468],"study_design_scores_gemma":[0.00038787955,0.00014272521,0.0069728033,0.000014095792,0.0000055123714,0.000027351958,0.000014800034,0.14529085,0.053731777,0.00093409145,0.79195493,0.0005231807],"about_ca_topic_score_codex":0.000026275882,"about_ca_topic_score_gemma":0.0000036065203,"teacher_disagreement_score":0.7045177,"about_ca_system_score_codex":0.000010331791,"about_ca_system_score_gemma":0.000031769196,"threshold_uncertainty_score":0.9989203},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019721715,0.000030485377,0.9774711,0.0006910944,0.00016491253,0.0002450984,0.0000059236368,0.000089042864,0.0015806169],"genre_scores_gemma":[0.68920106,9.0697256e-7,0.3101358,0.0002066952,0.000102163394,0.000017997645,0.000011979103,0.000005286885,0.0003181043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991659,0.000023968176,0.00008394976,0.00019746897,0.00023548384,0.00029322138],"domain_scores_gemma":[0.9993413,0.00007802589,0.000025294381,0.0003624808,0.00007525423,0.0001176441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002819741,0.00008195196,0.00007627662,0.000038737177,0.00016145248,0.00008885265,0.00027412554,0.000035019864,0.00003737326],"category_scores_gemma":[0.00001118153,0.000052692914,0.000024517418,0.00015976433,0.000021459698,0.00032516097,0.00012402495,0.00006206915,0.00002102136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023410578,0.0018907271,0.015035092,0.00012902806,0.00008638104,0.0000058486066,0.004977276,0.030151138,0.008626774,0.74866,0.048670065,0.14153355],"study_design_scores_gemma":[0.00040934476,0.00012592228,0.008101571,0.00000898322,0.0000040017067,0.0000050320696,0.000045250672,0.9773778,0.0072655333,0.00009917723,0.0064014997,0.00015592702],"about_ca_topic_score_codex":0.000042711235,"about_ca_topic_score_gemma":0.00000524512,"teacher_disagreement_score":0.94722664,"about_ca_system_score_codex":0.000018952094,"about_ca_system_score_gemma":0.0000356602,"threshold_uncertainty_score":0.21487547},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02884775,0.000007499826,0.9646576,0.00086033193,0.00036047667,0.00022900682,0.0000043022583,0.000082589686,0.0049504433],"genre_scores_gemma":[0.8750889,0.0000018918156,0.12390033,0.0009423305,0.000052841653,0.0000026324349,0.0000011092216,0.0000034776845,0.0000065372265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775857,0.000084202606,0.00030919275,0.0007112937,0.00070399715,0.000432732],"domain_scores_gemma":[0.9982037,0.00013743108,0.00010339872,0.001196952,0.000140397,0.00021810093],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011197653,0.00016612369,0.00024871112,0.00013885481,0.0002190114,0.00057427026,0.006683903,0.000029517252,0.000047823974],"category_scores_gemma":[0.000036370326,0.00011964688,0.000054826865,0.00063785625,0.0006652156,0.0010631969,0.002475122,0.00016604802,0.000039322076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008430364,0.00013636597,0.0000185631,0.000003033652,0.0000012537531,0.000005980891,0.00014714232,0.0002459589,0.00043095896,0.88232476,0.000080896156,0.11659666],"study_design_scores_gemma":[0.00041536705,0.001042522,0.001940203,0.00016299568,0.0000018007631,0.000018482488,0.0000015582036,0.5774419,0.00578967,0.41293216,0.00006664061,0.00018674896],"about_ca_topic_score_codex":0.000013489004,"about_ca_topic_score_gemma":4.90446e-7,"teacher_disagreement_score":0.8462411,"about_ca_system_score_codex":0.000029328416,"about_ca_system_score_gemma":0.00007537674,"threshold_uncertainty_score":0.9986904},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041937545,0.000072665716,0.9496668,0.0020863437,0.00080378726,0.00012677611,0.000023956884,0.00016150027,0.0051206546],"genre_scores_gemma":[0.8391446,0.00002666975,0.16022055,0.00028253655,0.00019864737,0.0000024365202,0.000009368426,0.000006141834,0.00010908445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934906,0.00002004198,0.00006028756,0.0003372793,0.00010742205,0.00012590589],"domain_scores_gemma":[0.9990446,0.000078599754,0.000029889192,0.00075617584,0.000024992423,0.00006571944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014804765,0.00006585933,0.000064233405,0.000037733917,0.00012739292,0.00015181638,0.00071211276,0.000028628621,0.000020755293],"category_scores_gemma":[0.00008311511,0.00005314954,0.000008501235,0.000063097206,0.000024557394,0.0003691031,0.0007655594,0.00018430228,0.000020189162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004078285,0.000023648978,0.00021346613,0.000001554088,0.0000046778064,0.000014045067,0.00031045135,0.0000018226089,0.0065193293,0.974433,0.0036331424,0.014840781],"study_design_scores_gemma":[0.0007272332,0.00012729382,0.004161372,0.000054694396,0.000007072225,0.000045515346,0.00019156036,0.91158575,0.0068686344,0.024181446,0.051693182,0.00035625813],"about_ca_topic_score_codex":0.000059361893,"about_ca_topic_score_gemma":0.000010506754,"teacher_disagreement_score":0.9502516,"about_ca_system_score_codex":0.00001463157,"about_ca_system_score_gemma":0.000020239333,"threshold_uncertainty_score":0.21673752},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08144954,0.00002456716,0.91647565,0.00009330059,0.00079354714,0.00011374825,0.000002924427,0.00013498683,0.00091172755],"genre_scores_gemma":[0.47975743,0.0000014912964,0.51994497,0.00024378467,0.000043426822,0.0000017792638,0.000001206307,0.0000043016703,0.0000016461878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975246,0.0001616015,0.00025758124,0.0007625065,0.0007553508,0.00053834694],"domain_scores_gemma":[0.9985114,0.00017096377,0.00007137353,0.0007329274,0.00021521162,0.00029814942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013333696,0.00017566569,0.00017166526,0.00017361632,0.00057307485,0.0002936792,0.0011464021,0.000056005087,0.00010629663],"category_scores_gemma":[0.000120985234,0.00014112392,0.000056353696,0.0009956986,0.0011041309,0.0010672628,0.0007395068,0.00018106432,0.00014368306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032402768,0.00007577791,0.000020830319,0.0000028790905,0.0000022749514,0.000023069631,0.00009735961,0.00017677528,0.0025369467,0.9562525,0.000022246799,0.040786058],"study_design_scores_gemma":[0.00027006067,0.00009497579,0.00020385833,0.000039326227,0.0000033150397,0.00021160691,0.000003063915,0.8694243,0.0068195085,0.122396246,0.000288436,0.00024530062],"about_ca_topic_score_codex":0.0000038948792,"about_ca_topic_score_gemma":1.0066222e-7,"teacher_disagreement_score":0.8692475,"about_ca_system_score_codex":0.00005692557,"about_ca_system_score_gemma":0.00017683262,"threshold_uncertainty_score":0.5754866},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96559995,0.0008078182,0.027730517,0.0043691033,0.00035325138,0.00012507374,0.000020202424,0.000024991312,0.00096908025],"genre_scores_gemma":[0.86368835,0.00008588972,0.13450035,0.0011644069,0.00024378236,0.0000014907603,0.0000011171529,0.000006569325,0.00030803183],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993668,0.000058117024,0.00016155186,0.00009421251,0.00021709086,0.00010220104],"domain_scores_gemma":[0.99883944,0.000056225254,0.00016106019,0.0008331672,0.00004532205,0.00006479872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001749147,0.00007093465,0.00011611218,0.000014278169,0.000087588975,0.000100720186,0.001774822,0.000025981515,0.000033448006],"category_scores_gemma":[0.00015232479,0.000035722394,0.00003858434,0.00008473575,0.000041011983,0.0003543908,0.00043667972,0.00010772843,0.000007959896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015049394,0.000048253958,0.0002871803,0.000007182055,0.000025675185,0.00013523769,0.00046086745,0.00004089419,0.00011105732,0.000047951104,0.005995589,0.9926896],"study_design_scores_gemma":[0.041816384,0.0075028506,0.33767626,0.004410013,0.00074456516,0.04578808,0.0029194157,0.09814362,0.005182896,0.4105578,0.04231301,0.0029450993],"about_ca_topic_score_codex":0.000020025198,"about_ca_topic_score_gemma":0.000013254085,"teacher_disagreement_score":0.98974454,"about_ca_system_score_codex":0.000019261532,"about_ca_system_score_gemma":0.000037399717,"threshold_uncertainty_score":0.32980904},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000077238525,0.00001313157,0.9658853,0.0010988099,0.0003294279,0.00021785726,0.00001588585,0.00006757507,0.03229476],"genre_scores_gemma":[0.07438604,0.00001084509,0.92426896,0.0010786379,0.000064112995,0.00002082503,0.000009546287,0.0000012526801,0.00015976619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991961,0.000010824312,0.00023044489,0.00011024501,0.00029647487,0.00015589068],"domain_scores_gemma":[0.99934137,0.0001182717,0.00015234818,0.00027200923,0.000066038236,0.000049945884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076258415,0.000057379337,0.000051142528,0.000056297133,0.000512692,0.00035481335,0.0012906379,0.000018856459,0.000013371065],"category_scores_gemma":[0.00005214629,0.000031876938,0.00002944701,0.00029025556,0.000115955285,0.004860484,0.00020340792,0.000037479007,0.00007779713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024537894,0.000010087955,0.00004647511,0.0000052972728,0.0000049386717,1.0377037e-7,0.0089431945,0.00037244172,0.000009164539,0.4782717,0.08994909,0.42236298],"study_design_scores_gemma":[0.00064897793,0.00016130705,0.006746191,0.000016002088,0.000003192025,0.0000073048964,0.00050614023,0.50243855,0.00078107376,0.06898092,0.41953248,0.00017785895],"about_ca_topic_score_codex":0.0004286213,"about_ca_topic_score_gemma":0.0000132697905,"teacher_disagreement_score":0.50206614,"about_ca_system_score_codex":0.000009391494,"about_ca_system_score_gemma":0.00012726652,"threshold_uncertainty_score":0.3943264},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.57735e-7,0.0018729679,0.8531891,0.13905342,0.002219966,0.00021786425,0.000060346698,0.000362695,0.0030227944],"genre_scores_gemma":[0.000051013016,0.000021026726,0.59554535,0.4016622,0.0012259289,0.00002485919,0.0008372174,0.00004388423,0.00058854243],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937857,0.0023069526,0.00051968615,0.001496965,0.0011439458,0.0007467755],"domain_scores_gemma":[0.9949298,0.0015978122,0.00046295527,0.0025672445,0.00026118662,0.00018103259],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001531577,0.0006992385,0.0008567131,0.00030419492,0.0002669315,0.00040620388,0.003951291,0.0045450986,0.00006387546],"category_scores_gemma":[0.00017614466,0.0005260661,0.00022729974,0.0005004168,0.00011404512,0.00035384757,0.0008828765,0.008884238,0.00007496748],"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":[0.000005001998,0.000020822026,0.000001123739,0.00006243699,0.00001387102,0.000052036743,0.0000060002812,0.000014171159,0.0004174951,0.0002469355,0.8015784,0.19758168],"study_design_scores_gemma":[0.00033789992,0.000083543055,0.00000932406,0.00022978132,0.000024000601,0.000018988756,6.3175963e-7,0.10095761,0.0054384773,0.00096833747,0.891326,0.0006054192],"about_ca_topic_score_codex":0.000058225793,"about_ca_topic_score_gemma":0.0000010296769,"teacher_disagreement_score":0.26260877,"about_ca_system_score_codex":0.00012209475,"about_ca_system_score_gemma":0.0002038594,"threshold_uncertainty_score":0.9997191},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27920583,0.000033591903,0.7157043,0.0036328814,0.00007875704,0.000085554246,0.0000030819508,0.00007934974,0.001176624],"genre_scores_gemma":[0.98679954,8.4900154e-7,0.009826786,0.0033164702,0.000030407542,0.000006535002,0.000013990458,0.0000027037827,0.0000026950454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991213,0.0000368805,0.00027526068,0.00009376144,0.00033516114,0.00013763747],"domain_scores_gemma":[0.9992527,0.00008624861,0.00025208364,0.00030599334,0.00008272299,0.000020300145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036240864,0.00008559517,0.000075479984,0.000091105874,0.00020662822,0.00034081543,0.0005485254,0.000026645494,0.0000044376256],"category_scores_gemma":[0.000060793478,0.000058550035,0.000026993446,0.00030776305,0.00006791278,0.0026191878,0.00008238473,0.000097924436,0.00001764241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094506744,0.00027881755,0.0047507496,0.0009852302,0.000037289206,0.000037854763,0.00915525,0.032040495,0.09135597,0.3484968,0.036870386,0.47589666],"study_design_scores_gemma":[0.0011022914,0.00010626722,0.036285494,0.0013731479,0.000019882786,0.00017883684,0.0002140156,0.8879683,0.03947518,0.013688883,0.018634837,0.0009528772],"about_ca_topic_score_codex":0.00019204924,"about_ca_topic_score_gemma":8.011084e-7,"teacher_disagreement_score":0.8559278,"about_ca_system_score_codex":0.000031418193,"about_ca_system_score_gemma":0.00004238044,"threshold_uncertainty_score":0.3286491},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027658767,0.000055408364,0.977102,0.00612263,0.0008065235,0.00011010828,0.000006160802,0.0003833425,0.012647959],"genre_scores_gemma":[0.063175425,0.000024301718,0.9130201,0.021959616,0.00074320496,0.000018540364,0.000061101484,0.000026943771,0.00097078446],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805367,0.00011410345,0.00030373049,0.00065433595,0.00044547964,0.00042869008],"domain_scores_gemma":[0.99834055,0.000089432506,0.00009994736,0.0012674807,0.000071012466,0.00013159808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024126522,0.00023972781,0.00024134871,0.000058014048,0.00026963657,0.0003625651,0.0014386403,0.000103942584,0.0003241983],"category_scores_gemma":[0.0000130190465,0.00017125277,0.000085314394,0.00021583801,0.00006221507,0.0015353062,0.0011515911,0.00022156759,0.0006341862],"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":[0.0000068246086,0.00015388317,0.00082807906,0.000018376819,0.00002259348,0.000020097383,0.000250277,0.000036750167,0.0019324366,0.04450579,0.28784934,0.66437554],"study_design_scores_gemma":[0.00050599984,0.000059448128,0.0013366286,0.000039568713,0.0000052518294,0.00001669119,0.000004485849,0.29983068,0.006036086,0.017108401,0.6746878,0.0003689799],"about_ca_topic_score_codex":0.00011599262,"about_ca_topic_score_gemma":0.0000040297464,"teacher_disagreement_score":0.6640066,"about_ca_system_score_codex":0.000018364688,"about_ca_system_score_gemma":0.000013903726,"threshold_uncertainty_score":0.81513923},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038772842,0.00014589773,0.98771256,0.0024087862,0.0008979346,0.0009985911,0.00034347855,0.00039871235,0.0032167328],"genre_scores_gemma":[0.6749784,0.00010771321,0.30808017,0.004397094,0.0029941278,0.00124882,0.0012018259,0.00019672212,0.0067951344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707156,0.00009971038,0.00048883737,0.00097394275,0.0005790313,0.0007869253],"domain_scores_gemma":[0.9983193,0.00021991318,0.00010755945,0.0010832063,0.0001405232,0.00012944403],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046214878,0.00039861473,0.00034658643,0.00022761778,0.0007731514,0.0005946356,0.0010889269,0.00015681627,0.000029034563],"category_scores_gemma":[0.000038105183,0.00032888193,0.00020523129,0.00046055403,0.00004312114,0.00090851606,0.00028624645,0.0002693249,0.00012815285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033870095,0.0023176344,0.00031934475,0.00013348827,0.00023741629,0.00010540975,0.001138558,0.036257055,0.03504686,0.713357,0.08281572,0.12793285],"study_design_scores_gemma":[0.0030385486,0.001304524,0.0008025909,0.0001681269,0.000028687946,0.000017569735,0.000029501234,0.9078004,0.01573731,0.0037312629,0.066402555,0.00093895826],"about_ca_topic_score_codex":0.00010575692,"about_ca_topic_score_gemma":0.000022184266,"teacher_disagreement_score":0.8715433,"about_ca_system_score_codex":0.00010789818,"about_ca_system_score_gemma":0.000104687315,"threshold_uncertainty_score":0.9999163},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047583104,0.0000353394,0.9943851,0.0014382713,0.0010870157,0.00015684328,0.000051209805,0.00015455211,0.0022157924],"genre_scores_gemma":[0.9865906,0.00002355631,0.009836692,0.0024254278,0.00008318837,0.00005453131,0.000007275597,0.000006388766,0.00097231544],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913275,0.000074165735,0.00017584869,0.00008717167,0.00028721453,0.00024286585],"domain_scores_gemma":[0.999073,0.00012896342,0.000092336784,0.0005548321,0.00006565654,0.00008515912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005042564,0.00011924764,0.000076852164,0.000111277724,0.00042926977,0.00034344324,0.00051008567,0.00006214092,0.000097526565],"category_scores_gemma":[0.0000044886474,0.00007814544,0.00007475473,0.0002383496,0.000049755923,0.006474007,0.000006151158,0.00020236672,0.0004194688],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005941191,0.00013598047,0.0000053388485,0.000019755349,0.000044715678,3.0359877e-7,0.010854342,0.0019890927,0.00009125021,0.13327911,0.0073277056,0.846193],"study_design_scores_gemma":[0.0015509644,0.0003295477,0.00063737045,0.00007947433,0.0000622928,0.00011472782,0.0025355276,0.3348568,0.063160464,0.011472652,0.58420986,0.0009902942],"about_ca_topic_score_codex":0.0000036916338,"about_ca_topic_score_gemma":3.7758846e-7,"teacher_disagreement_score":0.9861148,"about_ca_system_score_codex":0.000031628086,"about_ca_system_score_gemma":0.00002402687,"threshold_uncertainty_score":0.53915626},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019994457,0.0015746331,0.9932528,0.0019345381,0.0010121444,0.00014925427,0.0000155561,0.000018007959,0.000043629083],"genre_scores_gemma":[0.43408874,0.000045112098,0.5643814,0.00020087781,0.0012623331,0.0000010599573,0.0000017008593,0.0000036974466,0.00001506785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880165,0.000029752637,0.00034466689,0.00025338837,0.00040746655,0.00016307087],"domain_scores_gemma":[0.99893034,0.00017603087,0.0002893114,0.0004004922,0.00009815107,0.00010567293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007434051,0.00009776057,0.0001774754,0.00008253348,0.00047564475,0.0005441907,0.002399202,0.00002978422,7.300093e-7],"category_scores_gemma":[0.000006232008,0.000047710153,0.00004536925,0.00024213294,0.000073432966,0.0013873616,0.0005743368,0.000093824005,4.836304e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045490266,0.00009701445,0.00090502587,0.00017286232,0.00017110334,0.000047226844,0.0029966654,0.043984823,0.00049441465,0.23212534,0.050855413,0.6681046],"study_design_scores_gemma":[0.0018201866,0.0012062286,0.008088204,0.0007061023,0.000047013575,0.0045713293,0.00047752884,0.92297786,0.00007365801,0.029297937,0.030427907,0.0003060351],"about_ca_topic_score_codex":0.000041503255,"about_ca_topic_score_gemma":0.0000072393445,"teacher_disagreement_score":0.87899303,"about_ca_system_score_codex":0.000020303814,"about_ca_system_score_gemma":0.00028876448,"threshold_uncertainty_score":0.52476436},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09427853,0.0041336073,0.8904746,0.00066738704,0.005265907,0.00008787493,0.000001483918,0.000058149668,0.0050324346],"genre_scores_gemma":[0.99403733,0.00007387412,0.0051229205,0.00016356506,0.00052171445,6.518887e-8,3.098535e-7,0.000013486636,0.00006670875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983382,0.0004904412,0.00039113208,0.000092391914,0.0004167731,0.00027101705],"domain_scores_gemma":[0.9985727,0.00016988929,0.000460813,0.00043644846,0.00017701679,0.00018312503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001480336,0.00011959632,0.00015578611,0.000060034603,0.00020080128,0.00018050091,0.0016194567,0.000014246041,0.0000072181924],"category_scores_gemma":[0.000099235695,0.00007101669,0.000089121844,0.00025272323,0.00003110099,0.00075320737,0.00053184904,0.0003625115,0.0000587874],"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":[0.000027096055,0.0012898486,0.03047445,0.000059771286,0.00018033657,0.00061581534,0.01132284,0.00025347323,0.00050336635,0.24158166,0.05730138,0.65638995],"study_design_scores_gemma":[0.0023063892,0.0010972681,0.3385589,0.00031681856,0.000057460365,0.0021769418,0.00019797326,0.009522621,0.00091414334,0.0030465706,0.64101005,0.0007948343],"about_ca_topic_score_codex":4.966239e-7,"about_ca_topic_score_gemma":1.75401e-8,"teacher_disagreement_score":0.8997588,"about_ca_system_score_codex":0.000032438715,"about_ca_system_score_gemma":0.000032033367,"threshold_uncertainty_score":0.30093804},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02058434,0.000020758793,0.9775633,0.00037485606,0.0001723175,0.00003185819,0.000009327798,0.00021543534,0.001027771],"genre_scores_gemma":[0.93637156,0.000014300405,0.06265159,0.000495089,0.00006425207,0.0000026167238,0.00002790763,0.000004180293,0.0003685096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993716,0.000015207217,0.000099286604,0.0001993268,0.0001602819,0.0001543232],"domain_scores_gemma":[0.9994617,0.000024206152,0.000025853009,0.0004036914,0.0000207009,0.00006381916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004820105,0.00006742835,0.00006936585,0.000022590262,0.00016181893,0.000053597014,0.00052888703,0.0000234484,0.00005628729],"category_scores_gemma":[0.0000040968202,0.00005051963,0.00002634824,0.00011325932,0.000014144232,0.0004601002,0.0003771155,0.00006541702,0.00017260802],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008900852,0.00035638886,0.011073937,0.000023816154,0.00003974985,0.0008640469,0.0022135794,0.0006995619,0.0024989531,0.032760423,0.144608,0.8048526],"study_design_scores_gemma":[0.0013470547,0.00012787162,0.11978252,0.00005853858,0.0000048521524,0.00058416784,0.000045185527,0.7427259,0.005966125,0.015567876,0.11281978,0.00097013294],"about_ca_topic_score_codex":0.00016329392,"about_ca_topic_score_gemma":0.0000024983829,"teacher_disagreement_score":0.9157872,"about_ca_system_score_codex":0.000010388288,"about_ca_system_score_gemma":0.000016249991,"threshold_uncertainty_score":0.22185844},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008103375,0.000030041792,0.9872432,0.0021275538,0.00018786138,0.000057836896,0.0000024896071,0.00027115986,0.0019765263],"genre_scores_gemma":[0.8603806,0.0000020162788,0.13520657,0.004212755,0.00004836611,0.000011199243,0.00008632608,0.0000050869194,0.00004707539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921936,0.000009216489,0.00024743698,0.00010500593,0.00024165574,0.00017733137],"domain_scores_gemma":[0.999565,0.000011565901,0.00015026682,0.00019357914,0.000052457515,0.000027125534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001246315,0.000087780514,0.000067300854,0.0001326824,0.00021455326,0.00063203834,0.00040460855,0.000030025767,0.0000046045843],"category_scores_gemma":[0.0000069680896,0.00007856886,0.000021498783,0.00025185294,0.000020363965,0.0064746113,0.00010898094,0.000080258316,0.00009366757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007164421,0.000036512458,0.00027111795,0.00017779275,0.00000526749,0.0000086117025,0.0015047567,0.0069103274,0.009920458,0.011633432,0.029642973,0.93988156],"study_design_scores_gemma":[0.00025400243,0.000008149384,0.0024408961,0.00007262871,0.0000019371475,0.000020275267,0.000020705971,0.9613966,0.0007852469,0.0007052917,0.03409701,0.00019728769],"about_ca_topic_score_codex":0.000023174545,"about_ca_topic_score_gemma":7.123127e-7,"teacher_disagreement_score":0.95448625,"about_ca_system_score_codex":0.00004524972,"about_ca_system_score_gemma":0.000027197031,"threshold_uncertainty_score":0.60947603},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015867752,0.00013391186,0.99659634,0.00019044084,0.00019785766,0.00012852983,0.0000034181367,0.00011620741,0.0010465423],"genre_scores_gemma":[0.0062669204,0.000012971037,0.99198693,0.00034892527,0.00016869909,0.0000037080242,0.0000026195758,0.00000784326,0.0012013622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991136,0.000026630725,0.00014276001,0.00032497867,0.00017033359,0.0002216983],"domain_scores_gemma":[0.999239,0.00016728125,0.000049450344,0.00040762284,0.00003235774,0.000104277344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001426673,0.000108695465,0.0001386019,0.00008437284,0.0002463015,0.00007648892,0.0005250117,0.000033621433,0.00002834019],"category_scores_gemma":[0.000017598777,0.00008200289,0.00006333747,0.00017626233,0.000010094862,0.00040595746,0.00023298101,0.000059356258,0.000010631594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031761527,0.00012058748,0.0007169556,0.000012485717,0.000042939337,0.000039644885,0.0018581795,0.004516288,0.0031280955,0.09465054,0.01909538,0.87578714],"study_design_scores_gemma":[0.00044220794,0.000100060664,0.00050006906,0.000016026679,0.0000036228064,0.000048342954,0.000022166609,0.96241206,0.0032524616,0.003890331,0.029122569,0.00019009483],"about_ca_topic_score_codex":0.0002514534,"about_ca_topic_score_gemma":0.000010802904,"teacher_disagreement_score":0.95789576,"about_ca_system_score_codex":0.00002512041,"about_ca_system_score_gemma":0.00010970257,"threshold_uncertainty_score":0.33439806},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95466065,0.0012101803,0.01802999,0.02440606,0.0008676545,0.00011373911,9.613982e-7,0.00001600886,0.0006947476],"genre_scores_gemma":[0.99479336,0.000097330034,0.004653426,0.00024851042,0.00011237491,3.4005012e-7,1.244884e-8,0.0000026853438,0.00009197501],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99944407,0.000039518687,0.00013565537,0.00006282618,0.00021652385,0.00010139965],"domain_scores_gemma":[0.9988925,0.0001835498,0.00016528771,0.00069204107,0.00002903083,0.000037584225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033627555,0.000048019545,0.000063036554,0.00002447455,0.00015680546,0.00013156547,0.0020298276,0.000014988772,0.000010136174],"category_scores_gemma":[0.00028740463,0.000020258185,0.000038010232,0.00010084793,0.00001782529,0.00025832246,0.00081725005,0.00020265853,0.000004395015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003772558,0.00054590986,0.013673783,0.00006278468,0.00020136304,0.00014209229,0.0062699225,0.006943602,0.011183478,0.11550132,0.20713733,0.63830066],"study_design_scores_gemma":[0.0036426343,0.0012967996,0.14150292,0.0027533772,0.00008861007,0.0028519952,0.0003020833,0.30285588,0.02184817,0.41325542,0.108654544,0.00094756065],"about_ca_topic_score_codex":0.0000032785485,"about_ca_topic_score_gemma":5.497822e-7,"teacher_disagreement_score":0.6373531,"about_ca_system_score_codex":0.00001385439,"about_ca_system_score_gemma":0.0000068276586,"threshold_uncertainty_score":0.37719584},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043663297,0.000025901187,0.9515655,0.00001396716,0.0004282723,0.0035856913,0.00015748422,0.00010532118,0.00045453612],"genre_scores_gemma":[0.985818,0.000006557846,0.010167596,0.0000056048766,0.00018676149,0.0037329455,0.000022971568,0.00003070971,0.000028834882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980056,0.000028231168,0.00085739605,0.0005122357,0.00032775154,0.00026876503],"domain_scores_gemma":[0.9986314,0.00021056212,0.00029649845,0.00056631153,0.00020705142,0.00008812954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050422235,0.00025319232,0.00032141744,0.0003253497,0.000049946528,0.00016794955,0.0011020917,0.00012611675,0.000022211516],"category_scores_gemma":[0.000052356736,0.00024519017,0.00005859871,0.0002900313,0.000026759462,0.0002269383,0.00020149826,0.00022119161,0.0000066300718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013298923,0.0047484245,0.029962998,0.00039265573,0.00072248146,0.00016739008,0.019313002,0.03197292,0.0043531223,0.8054586,0.00019108497,0.102584355],"study_design_scores_gemma":[0.002791218,0.0005644525,0.00072308525,0.0008505839,0.000080435864,0.00026576233,0.011970062,0.9582603,0.010276362,0.0010928825,0.011813811,0.0013110694],"about_ca_topic_score_codex":0.0010426799,"about_ca_topic_score_gemma":0.000049891463,"teacher_disagreement_score":0.9421547,"about_ca_system_score_codex":0.000099500176,"about_ca_system_score_gemma":0.00009784887,"threshold_uncertainty_score":0.99985653},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096644636,0.000059526476,0.99826884,0.00017956902,0.00000783965,0.000284815,0.000090400616,0.00007368875,0.00006885765],"genre_scores_gemma":[0.7591498,0.00000789971,0.2399257,0.00009361569,0.0000816887,0.00030743284,0.00038308086,0.00000854148,0.00004224807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990889,0.000010986949,0.00023638445,0.000384019,0.00012275735,0.00015698717],"domain_scores_gemma":[0.9993103,0.000059230068,0.00012999488,0.00038522817,0.000065515764,0.000049692717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013669883,0.000108911176,0.00016409661,0.00016556536,0.00026945243,0.00029754112,0.00027064868,0.000036209716,0.000007070279],"category_scores_gemma":[0.000001408954,0.0000979971,0.000087897235,0.0005752218,0.00001632923,0.00020691605,0.00006827917,0.00004572707,0.0000014931687],"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":[0.0000023682371,0.0001923257,0.0012669571,0.0000306982,0.00007387656,2.4813136e-7,0.000019027755,0.86123115,0.0012645071,0.015762169,0.000042753334,0.1201139],"study_design_scores_gemma":[0.00030500724,0.000009517796,0.0016903357,0.0000060680977,0.00010818823,6.0532784e-7,0.000012207481,0.9957336,0.00043334498,0.0012071751,0.00036912042,0.0001248157],"about_ca_topic_score_codex":0.00045278916,"about_ca_topic_score_gemma":0.0000641115,"teacher_disagreement_score":0.75834316,"about_ca_system_score_codex":0.000014089534,"about_ca_system_score_gemma":0.000018440289,"threshold_uncertainty_score":0.3996206},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023683328,0.00012059126,0.99671745,0.00034762526,0.00019617016,0.00010305675,0.00005474806,0.000012362657,0.00007963022],"genre_scores_gemma":[0.08047592,0.000026739679,0.9191872,0.00016057013,0.00013185616,0.000001051361,0.000011408234,0.000001994482,0.0000032816008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990099,0.000014994441,0.00061009754,0.00007572453,0.00016763707,0.00012161252],"domain_scores_gemma":[0.9987065,0.00012412686,0.0005903861,0.00009208439,0.00042636783,0.000060530758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004484473,0.00009092274,0.00025056629,0.00015300118,0.00006899266,0.000053210875,0.0003119219,0.0000723488,7.5264666e-7],"category_scores_gemma":[0.00004326434,0.000066372944,0.00007360879,0.00007847211,0.000040114443,0.00044581058,0.00008825625,0.000087156426,1.1451492e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007508008,0.000030484565,0.000010399724,0.000026577107,0.000016489596,7.345265e-7,0.00021929626,0.0005900439,0.00039484332,0.027230976,0.0005484744,0.9708566],"study_design_scores_gemma":[0.0005368925,0.0011166139,0.00007056718,0.000024081932,0.000008089396,0.00005401771,0.00001748524,0.9022201,0.00042526316,0.09496266,0.0004862898,0.00007799616],"about_ca_topic_score_codex":0.0000012937254,"about_ca_topic_score_gemma":7.422689e-8,"teacher_disagreement_score":0.9707786,"about_ca_system_score_codex":0.000019758576,"about_ca_system_score_gemma":0.00017266034,"threshold_uncertainty_score":0.27066103},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017679982,0.0041406644,0.98994887,0.00071724417,0.0011036302,0.000112610855,0.000008846927,0.000043829652,0.0021563077],"genre_scores_gemma":[0.21809874,0.0025480029,0.77619493,0.0005788903,0.002037788,0.000010490294,0.000006339054,0.000059503196,0.00046529644],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998231,0.00009419708,0.00058558676,0.00019453483,0.0005830481,0.00031165604],"domain_scores_gemma":[0.9981412,0.00014208235,0.0005486322,0.00070191856,0.00029049034,0.00017562491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008652004,0.00016317614,0.00024207639,0.00009714058,0.00033585023,0.00026024022,0.0021271657,0.000058381807,0.000029234192],"category_scores_gemma":[0.0000856403,0.00008698254,0.00019411312,0.00030948696,0.000086350155,0.0011491895,0.00042212685,0.00032552093,0.000026151885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009737072,0.00013925612,0.001181812,0.000017286238,0.00020172512,0.000375906,0.0012692327,0.000014806956,0.00032862497,0.03774372,0.030125402,0.9285049],"study_design_scores_gemma":[0.004526878,0.0041056653,0.09617017,0.00092542666,0.00021918338,0.0027376977,0.0007476814,0.23628983,0.007631612,0.21295053,0.43187997,0.0018153572],"about_ca_topic_score_codex":0.000034506018,"about_ca_topic_score_gemma":0.0000057132975,"teacher_disagreement_score":0.9266895,"about_ca_system_score_codex":0.000027428725,"about_ca_system_score_gemma":0.00007948762,"threshold_uncertainty_score":0.39528385},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005632772,0.00004848624,0.98998606,0.0016990632,0.00012692894,0.000048989437,0.0000015159532,0.00016987999,0.0022863287],"genre_scores_gemma":[0.79775596,0.0000047613116,0.19191688,0.0101952,0.000030153278,0.00001300324,0.00003521869,0.000005585204,0.000043247335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908406,0.000030391166,0.0002651256,0.00013183417,0.00029958694,0.00018902628],"domain_scores_gemma":[0.9993524,0.00001698016,0.0001752218,0.00032529145,0.00007103628,0.000059078113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026196227,0.00010095289,0.00010870498,0.00029297647,0.00018852112,0.0007612088,0.0004226921,0.000035532903,0.000027017726],"category_scores_gemma":[0.000037017406,0.000085585765,0.000057481964,0.0009997587,0.000022057995,0.0062259454,0.0000594862,0.00009473004,0.00010458913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012262348,0.00009973594,0.009207245,0.00015587114,0.00029040434,0.000012217665,0.022296531,0.027905703,0.0016391702,0.024072262,0.025139283,0.88916934],"study_design_scores_gemma":[0.0006290104,0.000020396772,0.005888114,0.000046766178,0.000080578306,0.00002209924,0.0002228993,0.66526574,0.0020311272,0.0006936958,0.3245089,0.00059069344],"about_ca_topic_score_codex":0.000008520559,"about_ca_topic_score_gemma":5.0132763e-7,"teacher_disagreement_score":0.8885786,"about_ca_system_score_codex":0.000029139894,"about_ca_system_score_gemma":0.00004111243,"threshold_uncertainty_score":0.73403543},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00759615,0.0000659057,0.987943,0.0010331773,0.0031280823,0.00008804799,0.0000098717555,0.000021528009,0.000114224065],"genre_scores_gemma":[0.38220137,0.00001988291,0.61735475,0.00007668826,0.00032582926,0.0000019962188,0.000001311259,0.0000037470559,0.000014421936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979995,0.000020554995,0.00057334214,0.00023337986,0.0009799224,0.00019329367],"domain_scores_gemma":[0.9972534,0.000188292,0.0006026107,0.00030994054,0.0015450859,0.0001006826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007718863,0.000103946666,0.00017220371,0.0005185831,0.00019003122,0.0005208173,0.0033273848,0.000024019446,0.000017284194],"category_scores_gemma":[0.00008498149,0.00008962546,0.00011605447,0.00042293128,0.00015594227,0.003031478,0.00048258828,0.0001101934,0.000004669474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015955997,0.0003997002,0.00011924166,0.000017941198,0.0000962799,0.000019440988,0.0015682279,0.010554235,0.007332327,0.18042,0.0011595731,0.79829705],"study_design_scores_gemma":[0.0006309115,0.000176644,0.00082971127,0.00011655302,0.0000062913678,0.00019298584,0.000014404965,0.97807556,0.0038231227,0.0129409395,0.003055441,0.00013740874],"about_ca_topic_score_codex":0.000006960326,"about_ca_topic_score_gemma":4.2629003e-7,"teacher_disagreement_score":0.96752137,"about_ca_system_score_codex":0.0000901706,"about_ca_system_score_gemma":0.00013013242,"threshold_uncertainty_score":0.6183164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007820779,0.0000105110175,0.9707067,0.0005510045,0.0016821153,0.00008999529,0.0000083091545,0.00034306108,0.018787513],"genre_scores_gemma":[0.1904155,0.000009284868,0.80683696,0.000551664,0.00041303475,0.000013648476,0.000020970687,0.000014360608,0.0017245956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989262,0.000018109069,0.00014149556,0.00039862315,0.00027727516,0.00023825407],"domain_scores_gemma":[0.9989697,0.00004212379,0.00004786575,0.00076146075,0.00006467059,0.000114179995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012215343,0.00012601874,0.000108898275,0.00007654432,0.00016965333,0.00017736873,0.0006629828,0.00008359259,0.00011930658],"category_scores_gemma":[0.000018333956,0.00009578179,0.000046494933,0.00014346975,0.00004751042,0.00057106744,0.00027352996,0.000256515,0.00019247184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032750918,0.000052422292,0.00010527571,0.0000018670755,0.0000044119147,0.000008056596,0.00006930709,0.000021081756,0.0027391084,0.10015973,0.003913326,0.89292216],"study_design_scores_gemma":[0.0005480122,0.000132645,0.002307118,0.000013999375,0.0000034861605,0.0000879163,0.000021217687,0.9245105,0.012074819,0.018834984,0.041130748,0.00033457254],"about_ca_topic_score_codex":0.00004427899,"about_ca_topic_score_gemma":0.00002697291,"teacher_disagreement_score":0.9244894,"about_ca_system_score_codex":0.000010496605,"about_ca_system_score_gemma":0.000036794165,"threshold_uncertainty_score":0.39058682},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075668894,0.000046845482,0.9226489,0.00015355827,0.00017299056,0.00009738591,0.0000038256403,0.000082821454,0.0011247932],"genre_scores_gemma":[0.75624424,0.0000038402904,0.24361129,0.000069794274,0.00005942609,0.0000017248425,0.0000012826398,0.0000033375088,0.0000050388567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804,0.00003853994,0.00028798849,0.00054304657,0.00061908097,0.00047130484],"domain_scores_gemma":[0.9987479,0.00015297609,0.000091091024,0.0007070189,0.00013863668,0.0001623987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082647253,0.00014403537,0.00018735071,0.00012554269,0.00027072118,0.00022832419,0.0017933684,0.00003947982,0.000016035954],"category_scores_gemma":[0.000026659742,0.00011160635,0.000038156468,0.00065106386,0.0022851431,0.0010787994,0.002085469,0.000111466725,0.000008580975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037892312,0.00003926839,0.00024780614,0.0000071921895,8.3161507e-7,0.000004526963,0.00005939514,0.000033358734,0.0016462164,0.9381379,0.000046267913,0.059773482],"study_design_scores_gemma":[0.0002001615,0.00018841731,0.006160177,0.00002251169,0.0000026171504,0.000038782764,0.0000019155807,0.5847942,0.013234554,0.3950151,0.00016609223,0.00017542462],"about_ca_topic_score_codex":0.00003805594,"about_ca_topic_score_gemma":8.897317e-7,"teacher_disagreement_score":0.6805754,"about_ca_system_score_codex":0.000019862151,"about_ca_system_score_gemma":0.00007524554,"threshold_uncertainty_score":0.8419705},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015037361,0.0012445924,0.9804648,0.0019752465,0.000453592,0.00019011335,0.000007981249,0.000018088875,0.00060821674],"genre_scores_gemma":[0.098596975,0.00021961753,0.8995648,0.0010305126,0.00036659627,0.000006876827,0.00001143902,0.000016026746,0.00018717241],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987248,0.00010362707,0.0005041934,0.00020174235,0.0002524884,0.00021310907],"domain_scores_gemma":[0.9992894,0.000058086644,0.00021190313,0.0002274268,0.00010782123,0.00010537299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005532388,0.00011084747,0.00025978638,0.00017287271,0.000051542484,0.00018892708,0.0017162672,0.000062474704,0.00008444833],"category_scores_gemma":[0.000013366697,0.000087189015,0.00006396955,0.00029204707,0.000034786306,0.001387078,0.00030418608,0.00024033371,0.000029535227],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000287898,0.00057962467,0.00056416274,0.000012549264,0.000062666484,0.00041617773,0.0005066198,0.08219881,0.0009348077,0.04785981,0.0020539796,0.864782],"study_design_scores_gemma":[0.0027831916,0.00066386955,0.0044525163,0.00016181546,0.0000072810503,0.00062638026,0.00001532756,0.4505066,0.00031594487,0.52040035,0.019730357,0.00033637107],"about_ca_topic_score_codex":0.000044062053,"about_ca_topic_score_gemma":9.188489e-7,"teacher_disagreement_score":0.8644456,"about_ca_system_score_codex":0.00004373719,"about_ca_system_score_gemma":0.00014273869,"threshold_uncertainty_score":0.35554647},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014518031,0.000023656472,0.9820906,0.00026716397,0.0012701418,0.00007674114,0.000010526098,0.00019596101,0.0015471805],"genre_scores_gemma":[0.7611684,0.0000059084605,0.23814838,0.000110506335,0.0002138388,0.0000027507806,0.0001763954,0.0000061950445,0.0001676174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989738,0.000022963028,0.0001580267,0.00043367586,0.00024208527,0.00016947383],"domain_scores_gemma":[0.9978739,0.00004876216,0.000055593373,0.0018874697,0.00004615315,0.00008813656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022716526,0.00009460706,0.000087753055,0.000045659814,0.0001887018,0.0002549807,0.002025488,0.00006024623,0.00009578186],"category_scores_gemma":[0.000017350043,0.00007239639,0.000014545521,0.00014060667,0.000020975549,0.0018696708,0.0017017223,0.00020842731,0.00010806503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054543916,0.00013649515,0.0017831174,0.000010730402,0.000008364794,0.000016462393,0.00012210745,0.00005418082,0.21467607,0.03364139,0.01666872,0.7328769],"study_design_scores_gemma":[0.00021273154,0.000011687723,0.0029235347,0.000011034526,0.0000020950326,0.000020561467,0.0000041363787,0.94182956,0.016435344,0.0011166894,0.0372684,0.00016423021],"about_ca_topic_score_codex":0.00008969635,"about_ca_topic_score_gemma":0.000044554297,"teacher_disagreement_score":0.9417754,"about_ca_system_score_codex":0.0000045514726,"about_ca_system_score_gemma":0.000024420084,"threshold_uncertainty_score":0.37638947},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92776495,0.0016108573,0.057018597,0.0012041151,0.0039755553,0.00158726,0.00009051635,0.00017508377,0.006573069],"genre_scores_gemma":[0.9797289,0.00044588684,0.018843926,0.0002256111,0.0002033818,0.000041054143,0.000038328915,0.000032535485,0.00044037885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972723,0.00014406072,0.0007297431,0.0007835939,0.00047165493,0.00059863407],"domain_scores_gemma":[0.9979394,0.00031789416,0.00020367792,0.0011645122,0.00011424362,0.00026023487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001217058,0.00037991238,0.00059698895,0.000211165,0.00023436244,0.0005463225,0.0009775251,0.0002585571,0.00018795124],"category_scores_gemma":[0.00014194618,0.00031717046,0.00007835227,0.00040373846,0.00016943486,0.001348336,0.00096564484,0.0006697106,0.00020255461],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009642067,0.0024861768,0.08422075,0.0052864375,0.00041799797,0.0039346535,0.039022703,0.00022748548,0.0183309,0.19943248,0.028150778,0.61752546],"study_design_scores_gemma":[0.0131074535,0.00079711905,0.30803454,0.0062625404,0.00020062223,0.0011905831,0.0018041756,0.5818183,0.007717801,0.05185537,0.023080649,0.004130854],"about_ca_topic_score_codex":0.00021635085,"about_ca_topic_score_gemma":0.00032769502,"teacher_disagreement_score":0.61339456,"about_ca_system_score_codex":0.000034255972,"about_ca_system_score_gemma":0.00010331161,"threshold_uncertainty_score":0.99992806},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020581128,0.00031445688,0.9745464,0.00066441216,0.0006986069,0.00022671514,0.000038043887,0.0001727292,0.0027575577],"genre_scores_gemma":[0.66534936,0.00003329524,0.33373308,0.0004025417,0.00023899962,0.00002169835,0.0000114456125,0.000015297961,0.00019428994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847615,0.00004183144,0.00031490563,0.00030769606,0.00035584834,0.00050356786],"domain_scores_gemma":[0.9985918,0.00011314621,0.00010258253,0.0008594177,0.000054097443,0.0002789855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024933476,0.00018807295,0.00026944964,0.00017112521,0.000109918576,0.000056389108,0.0010654496,0.00007427423,0.000023712293],"category_scores_gemma":[0.000029278652,0.00015458507,0.00007561668,0.0004856727,0.000042790445,0.0008377074,0.00060862215,0.000115588504,0.00012981627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028823795,0.00067607296,0.0038547774,0.00003676081,0.000087227454,0.000022672391,0.0058194855,0.00015154271,0.0028865084,0.12709856,0.012272523,0.84706503],"study_design_scores_gemma":[0.0021229135,0.0012596174,0.096348606,0.00023291628,0.00008138841,0.0002038856,0.00048688118,0.19029118,0.059483714,0.018115483,0.629258,0.0021154638],"about_ca_topic_score_codex":0.00042764333,"about_ca_topic_score_gemma":0.00003330113,"teacher_disagreement_score":0.8449496,"about_ca_system_score_codex":0.00003818246,"about_ca_system_score_gemma":0.00005776579,"threshold_uncertainty_score":0.6303796},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7087312,0.0000947939,0.27936375,0.000009257968,0.0005854965,0.00016451081,0.000003249713,0.00028788752,0.01075987],"genre_scores_gemma":[0.99457026,0.0000028188358,0.0049088285,0.0000662012,0.00020883082,0.0000017271165,0.0000030259857,0.00001619369,0.00022213171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981143,0.0004006562,0.00038545142,0.0004467733,0.00034789668,0.00030495602],"domain_scores_gemma":[0.9983616,0.00049243344,0.00018061866,0.0008217104,0.00004585474,0.00009781841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013791346,0.00017960322,0.00028612686,0.00013540343,0.00023000778,0.00015544838,0.00091218983,0.000058937,0.000018146064],"category_scores_gemma":[0.000030761315,0.00015621731,0.00005500992,0.00021371256,0.000031068095,0.00028167435,0.00012876767,0.00018221172,0.0000699222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007095475,0.00016034493,0.000031342133,0.000060812694,0.000022525042,0.000022254924,0.0016843317,0.06218693,0.0005961428,0.3792171,0.00008221248,0.55586505],"study_design_scores_gemma":[0.0007736492,0.00083955354,0.0007137855,0.0019298241,0.000008001699,0.000060412523,0.00017627614,0.9803766,0.0019046004,0.012022042,0.0007301478,0.00046510136],"about_ca_topic_score_codex":0.000041306033,"about_ca_topic_score_gemma":4.0178952e-7,"teacher_disagreement_score":0.91818964,"about_ca_system_score_codex":0.000036335594,"about_ca_system_score_gemma":0.000022888737,"threshold_uncertainty_score":0.6370357},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3244315,0.00008121301,0.67278814,0.0002602214,0.00058994506,0.00017355062,0.000011324801,0.0000974509,0.0015666428],"genre_scores_gemma":[0.9313752,0.000019110852,0.06831564,0.00008201462,0.000030511283,0.0000052958026,0.000015377002,0.000003821588,0.00015302027],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992931,0.000021919197,0.00016173042,0.00023516218,0.00017311498,0.00011499365],"domain_scores_gemma":[0.99934804,0.0000412349,0.00008125318,0.00038980832,0.0000659873,0.00007368197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013397819,0.00008428161,0.00012005675,0.00006215269,0.00009437581,0.00006148869,0.00033491856,0.000063241,0.000035960886],"category_scores_gemma":[0.000005775843,0.00006209265,0.00002162102,0.00012276202,0.000058375324,0.0005124459,0.00030161726,0.00010408002,0.000009478786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027020282,0.00023307603,0.003303857,0.000049642807,0.0000144249,0.0000071386194,0.00046965425,0.000018000655,0.51809037,0.30653986,0.012082941,0.159164],"study_design_scores_gemma":[0.0012594322,0.00025772196,0.03436566,0.000064887194,0.000011039138,0.000060706858,0.00002964375,0.7301146,0.17563027,0.028231183,0.029502196,0.00047270206],"about_ca_topic_score_codex":0.00006187623,"about_ca_topic_score_gemma":0.000018041119,"teacher_disagreement_score":0.7300966,"about_ca_system_score_codex":0.0000021275348,"about_ca_system_score_gemma":0.000014269364,"threshold_uncertainty_score":0.25320646},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06609552,0.000011337025,0.9312893,0.0006750014,0.0017177757,0.000056692654,0.000010816638,0.000024595885,0.00011895366],"genre_scores_gemma":[0.6796204,0.0000074593913,0.31978372,0.00032886773,0.00025143754,4.1053593e-7,0.0000021989874,0.0000027949457,0.0000027004164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973045,0.000054215903,0.000600274,0.0003260962,0.0015035002,0.00021140062],"domain_scores_gemma":[0.9971134,0.000112023925,0.00071786204,0.00046067397,0.0014304987,0.00016553362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008407883,0.00014747448,0.00020163572,0.00077723095,0.00018282536,0.0006104696,0.004345744,0.00002470986,0.000008316587],"category_scores_gemma":[0.000032270666,0.00012604728,0.00009704135,0.00038509848,0.00016122675,0.0046032215,0.00029022977,0.00022916483,0.000006847742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001155339,0.00022987256,0.00002786442,6.33225e-7,0.0000141692435,0.000053200376,0.00031420536,0.0041323598,0.0010456636,0.006365125,0.00006154732,0.9877438],"study_design_scores_gemma":[0.00070067175,0.0019814488,0.014706286,0.00024374003,0.0000066746757,0.00047978628,0.000022304483,0.9451463,0.010620386,0.025433354,0.000414612,0.00024442872],"about_ca_topic_score_codex":0.000017283226,"about_ca_topic_score_gemma":5.0671196e-7,"teacher_disagreement_score":0.98749936,"about_ca_system_score_codex":0.00013605153,"about_ca_system_score_gemma":0.00031900764,"threshold_uncertainty_score":0.8075546},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08121181,0.0003134829,0.91683924,0.00042352753,0.0009917375,0.00015867145,0.0000052891537,0.000020021953,0.000036209643],"genre_scores_gemma":[0.9939473,0.00002559586,0.005705002,0.00005068424,0.000252269,0.000006623706,0.0000016260773,0.0000017863554,0.000009056949],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990529,0.00010283184,0.00035109787,0.00012538505,0.0002683859,0.000099413424],"domain_scores_gemma":[0.99928695,0.00008703412,0.00031251504,0.00005668668,0.00021742636,0.000039379785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004256528,0.000074814445,0.00014492356,0.00016277665,0.000049382703,0.00012467119,0.0006184073,0.000048948066,0.0000013442461],"category_scores_gemma":[0.0000837046,0.000051619187,0.00006771945,0.00009099745,0.000015486412,0.00052322855,0.000050070237,0.00021031535,5.999472e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009198776,0.0004172418,0.010043221,0.00001660681,0.000101059835,0.0007684355,0.0008425707,0.038863502,0.4909405,0.009917941,0.00017247838,0.44699654],"study_design_scores_gemma":[0.00081072946,0.0020995275,0.010717093,0.00021448811,0.0000028688833,0.0019381164,0.00007997941,0.9687289,0.0097223325,0.0024925012,0.0030082113,0.0001852369],"about_ca_topic_score_codex":0.00007901478,"about_ca_topic_score_gemma":0.0000044625895,"teacher_disagreement_score":0.9298654,"about_ca_system_score_codex":0.000088047746,"about_ca_system_score_gemma":0.000022146245,"threshold_uncertainty_score":0.21049693},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122127056,0.00026331536,0.85695064,0.00087348215,0.00022175546,0.0000968513,0.000011993801,0.00025896454,0.019195955],"genre_scores_gemma":[0.9584692,0.0001608324,0.03838206,0.0002717337,0.000032723536,0.00000469303,0.0000029857201,0.0000021316127,0.0026736162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956155,0.000026461845,0.00006657272,0.00018270823,0.00007445558,0.00008826686],"domain_scores_gemma":[0.99970216,0.00003148523,0.000011343557,0.00019208954,0.000011757018,0.00005119492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000043320364,0.000056331235,0.00005663768,0.00003012838,0.000108803484,0.00008423069,0.00022725727,0.000020206078,0.00031947528],"category_scores_gemma":[0.0000021651176,0.000039352723,0.000011279698,0.0000950117,0.000027373359,0.00039592833,0.000121134086,0.00005138983,0.000046959172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007764317,0.00004490583,0.0013550691,0.0000028509187,0.000012711893,0.0000064337773,0.00071420433,0.000005998962,0.000032921485,0.060733784,0.013446374,0.923637],"study_design_scores_gemma":[0.00075266673,0.00053010695,0.111342974,0.00009298691,0.0000095639525,0.00013533885,0.0010160476,0.7857427,0.00041759262,0.027850457,0.071473375,0.000636199],"about_ca_topic_score_codex":0.00019106214,"about_ca_topic_score_gemma":0.000016758526,"teacher_disagreement_score":0.9230008,"about_ca_system_score_codex":0.0000051958223,"about_ca_system_score_gemma":0.000008858026,"threshold_uncertainty_score":0.34980303},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1077813,0.0004761278,0.8902125,0.0004946456,0.00038542182,0.00041071838,0.00005617043,0.00010651346,0.000076628836],"genre_scores_gemma":[0.03463753,0.000011452518,0.96450907,0.00017828481,0.00006375832,0.000035928606,0.00033432996,0.000008012032,0.00022161407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827373,0.000044795834,0.00024332822,0.0008646199,0.0003046268,0.00026892548],"domain_scores_gemma":[0.998032,0.00025933186,0.000092175585,0.0013404835,0.00017603263,0.00010000479],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051191286,0.00013197795,0.00015042334,0.00006465851,0.0004949056,0.001389923,0.0016089915,0.0000498345,0.00004610639],"category_scores_gemma":[0.00008832656,0.000098368015,0.000016221544,0.00019194443,0.000063434585,0.002165276,0.003099455,0.00006630145,0.000060377854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010583276,0.000068666144,0.00096209004,0.00006961173,0.000029879928,0.0000020711757,0.00058358035,0.000010338614,0.09992102,0.017947443,0.020311808,0.8600829],"study_design_scores_gemma":[0.00038963903,0.000018378123,0.002053843,0.00013048096,0.0000032737223,0.000002124625,0.00003664439,0.97207206,0.0040574656,0.010813339,0.010236903,0.0001858326],"about_ca_topic_score_codex":0.0002198299,"about_ca_topic_score_gemma":0.000010678754,"teacher_disagreement_score":0.97206175,"about_ca_system_score_codex":0.000016122201,"about_ca_system_score_gemma":0.00009640748,"threshold_uncertainty_score":0.9996467},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0752771,0.0023461282,0.9178856,0.0014233042,0.0012951002,0.00007380483,9.20997e-7,0.000028487679,0.0016695821],"genre_scores_gemma":[0.923916,0.00011115679,0.075671546,0.000086531116,0.00018752209,5.440299e-7,4.0511686e-8,0.0000017112519,0.000024992898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986388,0.00010601281,0.000424402,0.00020425783,0.00042911284,0.00019742161],"domain_scores_gemma":[0.99929655,0.00012977993,0.00026786153,0.00014889408,0.00005914202,0.00009775546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010054398,0.00009388738,0.00022938184,0.0003071947,0.00022205745,0.00039105353,0.0009454823,0.000033369608,0.0000034681973],"category_scores_gemma":[0.000007749937,0.00006176317,0.00004955903,0.0004754137,0.000097242475,0.001297873,0.00019294766,0.00012045419,0.0000036740391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016465414,0.000426395,0.03478491,0.00037592047,0.00007929279,0.0025539324,0.01795238,0.014244643,0.0007225266,0.49833655,0.034746483,0.3957605],"study_design_scores_gemma":[0.0003020554,0.000286341,0.0033115554,0.00054156675,0.0000032252053,0.0014508867,0.0003683663,0.9904628,0.000041995172,0.0011142392,0.0019742753,0.00014269193],"about_ca_topic_score_codex":0.000012063125,"about_ca_topic_score_gemma":0.0000018706629,"teacher_disagreement_score":0.97621816,"about_ca_system_score_codex":0.000027201524,"about_ca_system_score_gemma":0.000030445113,"threshold_uncertainty_score":0.37709382},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043514032,0.00015191412,0.9553083,0.00016127348,0.000062974745,0.0002029369,0.000022040547,0.000024772195,0.0005517485],"genre_scores_gemma":[0.93370295,0.000009700336,0.066176444,0.00003064718,0.00002750434,0.0000054682837,0.000006369824,0.000003216159,0.00003767967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992536,0.000011069881,0.00022550361,0.00017035178,0.00018618446,0.00015333244],"domain_scores_gemma":[0.99884653,0.00040144374,0.00011376375,0.00054354855,0.00005883747,0.00003590329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006312057,0.00007245853,0.00012752587,0.000031631134,0.00005665067,0.000021356138,0.00088789547,0.000032920376,0.000003360599],"category_scores_gemma":[0.000020476622,0.000042467982,0.00004517445,0.00017688966,0.000077827026,0.00021384725,0.00025366113,0.000053964934,5.914425e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051546456,0.0002403428,0.01597189,0.000090679874,0.00004380515,0.0000067821798,0.0015184736,0.0009353622,0.004011932,0.34100565,0.0016885264,0.634435],"study_design_scores_gemma":[0.00066575734,0.0005198495,0.0846838,0.00010691374,0.000025733118,0.00002534852,0.0006747307,0.7972185,0.10651925,0.005746018,0.0034740025,0.00034009773],"about_ca_topic_score_codex":0.00024376933,"about_ca_topic_score_gemma":0.000044340795,"teacher_disagreement_score":0.89018893,"about_ca_system_score_codex":0.0000074674876,"about_ca_system_score_gemma":0.000025378129,"threshold_uncertainty_score":0.1731794},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025853666,0.00009166122,0.9833998,0.0003983604,0.0004315205,0.000028408378,0.0000049002433,0.00014526366,0.015241533],"genre_scores_gemma":[0.03415829,0.00002065861,0.9625943,0.0006419269,0.0002562932,0.0000029285852,0.000064797234,0.000006611776,0.0022541957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994547,0.000013702964,0.00005994586,0.000228886,0.00014256492,0.000100201105],"domain_scores_gemma":[0.99859196,0.000013939552,0.00001657172,0.0012650586,0.000023580154,0.00008889689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023656434,0.000040646995,0.00004570211,0.000021035466,0.000028108225,0.0001015871,0.0014905147,0.00001528178,0.00002044549],"category_scores_gemma":[0.000032560092,0.000030736686,0.0000053647454,0.000097265685,0.000004914648,0.0011801362,0.0022154956,0.000034319986,0.00015787836],"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":[0.0000034349953,0.00004090623,0.00019133904,0.0000038730686,0.0000061131227,0.000021359561,0.00027853568,0.000024281915,0.00024512177,0.014395068,0.42680863,0.5579813],"study_design_scores_gemma":[0.0001755024,0.000022329139,0.00016808826,0.0000059942467,7.153924e-7,0.000009315904,0.00001873298,0.6331531,0.00023090417,0.0021423823,0.36398178,0.00009120551],"about_ca_topic_score_codex":0.00008096543,"about_ca_topic_score_gemma":0.000009041754,"teacher_disagreement_score":0.63312876,"about_ca_system_score_codex":0.000009010979,"about_ca_system_score_gemma":0.000029847122,"threshold_uncertainty_score":0.27697718},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21613123,0.00091091904,0.7769271,0.002337173,0.0023196284,0.00038428776,0.00004779973,0.00024515728,0.0006966719],"genre_scores_gemma":[0.5001808,0.0001477727,0.49812582,0.0011447434,0.00011962001,0.000027920452,0.0000042817924,0.000013138055,0.00023590687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986623,0.00008520546,0.00021884106,0.00038716168,0.00042023964,0.00022628043],"domain_scores_gemma":[0.9980761,0.00043942258,0.00023133989,0.0009076656,0.00024132385,0.00010414057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024272763,0.00014489204,0.00014382415,0.000037150447,0.00035655563,0.00016434565,0.0010524252,0.00008349655,0.00003807311],"category_scores_gemma":[0.0007586297,0.00009212826,0.00004311958,0.00022909864,0.00021712274,0.002245588,0.0010823403,0.00036650876,0.000008535264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030187117,0.00028656036,0.00419657,0.000032461663,0.000016596556,0.000024443405,0.013723419,0.000006675757,0.06107365,0.0047750976,0.0011138639,0.9147205],"study_design_scores_gemma":[0.0019240251,0.00062929303,0.051391963,0.0004414375,0.00006868825,0.00096395926,0.008142491,0.027400615,0.17219573,0.0036550318,0.7314673,0.001719481],"about_ca_topic_score_codex":0.00022927213,"about_ca_topic_score_gemma":0.0000062099034,"teacher_disagreement_score":0.913001,"about_ca_system_score_codex":0.0000058874534,"about_ca_system_score_gemma":0.00006845867,"threshold_uncertainty_score":0.37568814},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062466403,0.00006668633,0.99214107,0.00084368204,0.000013536778,0.00030670784,0.00017684704,0.00007223095,0.00013257403],"genre_scores_gemma":[0.98993194,0.000023478222,0.0086551495,0.00018030661,0.000116904055,0.00044802998,0.0006136992,0.00000768337,0.000022814676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989454,0.000028382108,0.00022754533,0.00043680237,0.00016950394,0.0001923747],"domain_scores_gemma":[0.9991153,0.00015650672,0.00009233112,0.00045976913,0.000111737354,0.00006437319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001608286,0.00012051838,0.00017770534,0.00020566478,0.0003442424,0.00043497066,0.00030515486,0.00004459034,0.000027026474],"category_scores_gemma":[0.0000018491191,0.0001067724,0.00011615652,0.00061890885,0.00003112468,0.00029648136,0.00006608079,0.0000641689,0.00002164333],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003770628,0.0002821013,0.013750054,0.0000687064,0.00013923999,0.0000013693862,0.00005755384,0.001014238,0.00028074346,0.0017448142,0.00045401597,0.98220336],"study_design_scores_gemma":[0.0006569474,0.000058098187,0.04629894,0.000026330501,0.00043992375,0.000003012147,0.000103190854,0.93721414,0.0013888218,0.007179364,0.006237799,0.00039344135],"about_ca_topic_score_codex":0.0016433345,"about_ca_topic_score_gemma":0.000711787,"teacher_disagreement_score":0.9836853,"about_ca_system_score_codex":0.00001857851,"about_ca_system_score_gemma":0.00003236026,"threshold_uncertainty_score":0.43540522},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07615018,0.0014018338,0.920642,0.0008162177,0.0001152336,0.0004064137,0.000069365095,0.000037267604,0.00036146134],"genre_scores_gemma":[0.77751815,0.00082272757,0.22142345,0.0001531561,0.0000050814106,0.000037665464,0.000002948623,0.000005286617,0.000031536518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985925,0.00013107047,0.00040690487,0.00034504556,0.00025573076,0.0002687641],"domain_scores_gemma":[0.9978619,0.00026482504,0.00028666158,0.0014191207,0.0001063615,0.00006113802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005095561,0.00015099655,0.00021443827,0.00008169996,0.0009618742,0.00012486678,0.0026515487,0.000050827945,0.00001054779],"category_scores_gemma":[0.0000032645244,0.00011412752,0.00012533866,0.00043245914,0.0008250573,0.0004914166,0.00020388565,0.00017124595,7.7079716e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020870326,0.006258046,0.0019148152,0.00022517158,0.00057707605,7.1512034e-7,0.019598918,0.010034394,0.005772056,0.32696164,0.00052853907,0.6279199],"study_design_scores_gemma":[0.00071728055,0.0017467969,0.0027600245,0.00014108191,0.000053897682,0.000017335075,0.00012842439,0.95321006,0.01915731,0.008133351,0.0135932965,0.00034115967],"about_ca_topic_score_codex":0.00020751149,"about_ca_topic_score_gemma":0.00012664446,"teacher_disagreement_score":0.9431757,"about_ca_system_score_codex":0.000027027723,"about_ca_system_score_gemma":0.00015982352,"threshold_uncertainty_score":0.7398056},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028488273,0.00012612733,0.9952474,0.00017655596,0.00013051221,0.00017169755,0.000021020358,0.00011782058,0.001159999],"genre_scores_gemma":[0.1180094,0.000027260643,0.88100433,0.000099982375,0.00006899526,0.000038136994,0.00001623098,0.000013370725,0.0007222598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992433,0.000007325555,0.00018959306,0.00020062269,0.00016439008,0.00019477682],"domain_scores_gemma":[0.9991691,0.00015215811,0.000085925734,0.0004860847,0.000048151127,0.000058578567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010487539,0.00010398294,0.00014872334,0.000024611618,0.00022989121,0.00006901391,0.0005378472,0.000029357658,0.000005788996],"category_scores_gemma":[0.00006341874,0.000080130696,0.000057769663,0.0000909762,0.00004583829,0.0003350161,0.00016728751,0.00004491081,0.000024293297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068854883,0.00014124594,0.00017121792,0.00024961645,0.000029462464,0.000030215231,0.006766978,0.00006714007,0.00088859536,0.96903175,0.012980109,0.009636775],"study_design_scores_gemma":[0.0005143672,0.00007872116,0.00012349917,0.00012674349,0.000008862395,0.00006510978,0.00017728118,0.87686735,0.004437847,0.071112946,0.04610326,0.00038403986],"about_ca_topic_score_codex":0.0000025309662,"about_ca_topic_score_gemma":8.313203e-7,"teacher_disagreement_score":0.8979188,"about_ca_system_score_codex":0.000011133471,"about_ca_system_score_gemma":0.000020689777,"threshold_uncertainty_score":0.3267635},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016905269,0.0000205521,0.9805768,0.00026267633,0.0005469847,0.00027920245,0.00004310091,0.00018646501,0.0011789544],"genre_scores_gemma":[0.9693955,0.000030123669,0.027936874,0.001981889,0.000095389194,0.000015331869,0.00014539211,0.0000061963347,0.00039329976],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901175,0.000013299918,0.00032211744,0.00012586554,0.00030378948,0.00022319671],"domain_scores_gemma":[0.99903566,0.000054068434,0.00016662855,0.00036881556,0.00028711028,0.00008769828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017823734,0.000103068414,0.00012495235,0.000107662934,0.0002164107,0.000121224984,0.0005385965,0.000049557293,0.000010564285],"category_scores_gemma":[0.00018281826,0.00008869423,0.0000540481,0.00020740001,0.000043674925,0.003224666,0.00015522982,0.000093303905,0.000105427476],"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":[0.000638112,0.000150992,0.0015871824,0.00015007785,0.00006786099,0.00005423145,0.0038724719,0.0008092258,0.0003005463,0.058894787,0.5312862,0.40218836],"study_design_scores_gemma":[0.00137802,0.00011531303,0.005220438,0.00002183824,0.0000018141853,0.00013069196,0.000013164071,0.7236498,0.0018727195,0.0012821179,0.2661092,0.00020486813],"about_ca_topic_score_codex":0.00002036115,"about_ca_topic_score_gemma":3.3296706e-7,"teacher_disagreement_score":0.95263994,"about_ca_system_score_codex":0.000043097476,"about_ca_system_score_gemma":0.00010659689,"threshold_uncertainty_score":0.36168456},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02370693,0.000054274406,0.96811,0.000521011,0.000708901,0.00011771687,0.0000018140439,0.00037398218,0.0064053214],"genre_scores_gemma":[0.70415914,0.000012266885,0.2952057,0.0004855605,0.00011589203,0.000004047339,0.0000010143178,0.0000046999453,0.000011688732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971377,0.00009321212,0.00027259806,0.00085366727,0.0010018873,0.0006409179],"domain_scores_gemma":[0.99798477,0.00019506674,0.00007113922,0.0011835478,0.00019243849,0.00037306093],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00068045367,0.00020296189,0.00022355422,0.0001687629,0.0010088531,0.00032515023,0.0042613563,0.000050083618,0.000054586064],"category_scores_gemma":[0.000047531466,0.00015196807,0.00006332338,0.0011653849,0.0039402316,0.0014780795,0.0019188139,0.00020909615,0.00023328178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035351284,0.000055706852,0.00015340444,0.0000026711807,0.0000021878523,0.00007255806,0.0002860794,0.00017595821,0.0007607918,0.97342676,0.00036402518,0.024696346],"study_design_scores_gemma":[0.00025642692,0.00017520554,0.0048451447,0.000024877809,0.0000019784695,0.00035177558,0.000003093463,0.9144894,0.007595686,0.07092318,0.0010069405,0.00032630345],"about_ca_topic_score_codex":0.000009493807,"about_ca_topic_score_gemma":3.7055304e-7,"teacher_disagreement_score":0.91431344,"about_ca_system_score_codex":0.000040652376,"about_ca_system_score_gemma":0.00020457075,"threshold_uncertainty_score":0.9987705},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004323701,0.0000671655,0.99874294,0.000069141606,0.000059134967,0.000050850897,0.000014266743,0.000040966886,0.00052316405],"genre_scores_gemma":[0.41533422,0.000003207619,0.58448035,0.000060908864,0.000050725303,0.0000020882849,0.000017046026,0.000001998365,0.000049466737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992564,0.000013926655,0.00025289258,0.00018658083,0.00012894359,0.00016126697],"domain_scores_gemma":[0.99913085,0.00034884593,0.000087680484,0.00028895875,0.000091706264,0.000051983036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020887672,0.000057785255,0.00016491569,0.00008553242,0.000065547116,0.00005446678,0.00031722043,0.000027515056,0.00005104072],"category_scores_gemma":[0.00009929814,0.00004670805,0.000057773545,0.0003501717,0.000015605357,0.00019678779,0.00016916727,0.000040884694,0.000001448864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007227346,0.00011839314,0.0050530513,0.00001515787,0.00028047996,0.000002175342,0.0001449711,0.16257413,0.0000816857,0.33136106,0.012051479,0.4883102],"study_design_scores_gemma":[0.000076752825,0.000019570136,0.0053248187,0.0000038476087,0.00007064273,2.9089796e-7,0.000005099919,0.99291915,0.00004898192,0.00052563666,0.000943957,0.000061264596],"about_ca_topic_score_codex":0.000020566233,"about_ca_topic_score_gemma":0.000015292066,"teacher_disagreement_score":0.830345,"about_ca_system_score_codex":0.000011517994,"about_ca_system_score_gemma":0.000014992777,"threshold_uncertainty_score":0.1904699},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23596068,0.00027955475,0.7606151,0.0026623798,0.00016954946,0.00010597243,0.0000015335532,0.00006946064,0.00013575004],"genre_scores_gemma":[0.7918019,0.000090115725,0.2064359,0.0015224884,0.00007585823,0.000020852754,0.000013533686,0.000009840356,0.000029493387],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926233,0.00002627254,0.0001367197,0.00018529083,0.0001595351,0.00022985012],"domain_scores_gemma":[0.9994656,0.00002582178,0.000080407386,0.000352648,0.00003993064,0.000035632223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006946025,0.00007576169,0.00010811168,0.00004661143,0.00004975328,0.000051167666,0.00041399893,0.00002790342,0.000029108982],"category_scores_gemma":[0.0000073312326,0.000066998764,0.000031896936,0.00015286048,0.000042680225,0.0004352854,0.00009112989,0.00010338017,0.00003209839],"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":[0.0000051688085,0.000049862334,0.001291052,0.000020303263,0.000043470278,0.0000035076328,0.00014958624,0.0003052396,0.75448394,0.10999459,0.025797224,0.10785608],"study_design_scores_gemma":[0.0018945851,0.0004561139,0.009532871,0.00010191252,0.000024480618,0.00008659934,0.00005360454,0.38710636,0.4975041,0.034104172,0.0680731,0.0010621247],"about_ca_topic_score_codex":0.000041185318,"about_ca_topic_score_gemma":0.0000013232145,"teacher_disagreement_score":0.5558412,"about_ca_system_score_codex":0.000030828218,"about_ca_system_score_gemma":0.000031324296,"threshold_uncertainty_score":0.27321303},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07873421,0.00056529924,0.9102139,0.00007665797,0.0011316168,0.00044263247,0.000038238213,0.000098890916,0.008698554],"genre_scores_gemma":[0.9947914,0.000039691862,0.0046922117,0.00006679822,0.0001866948,0.00005084909,0.00007793503,0.000003876956,0.000090575646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991431,0.000064109496,0.00035753785,0.00013943893,0.00011463309,0.00018114514],"domain_scores_gemma":[0.9993484,0.00016856115,0.000082736544,0.00023352835,0.000097800046,0.000068951515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005512421,0.00009459407,0.00015912765,0.00021789972,0.000127939,0.00036094766,0.00029381274,0.00007724724,0.0000020487075],"category_scores_gemma":[0.00003234287,0.000078893274,0.000028904444,0.0001793207,0.000014344385,0.0030581318,0.0001605556,0.0000765844,0.000045163306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006570692,0.000074465,0.008459819,0.00037697915,0.000029784856,8.488189e-7,0.024069915,0.0002474949,0.0002496733,0.19411725,0.031102,0.74120605],"study_design_scores_gemma":[0.0007350158,0.00007483082,0.0029860216,0.00012948434,0.0000018134483,0.0000034976604,0.0001686699,0.6777065,0.00029908563,0.00030142497,0.31743604,0.00015763807],"about_ca_topic_score_codex":0.00023915432,"about_ca_topic_score_gemma":0.000015377234,"teacher_disagreement_score":0.91605717,"about_ca_system_score_codex":0.000026598213,"about_ca_system_score_gemma":0.00003431658,"threshold_uncertainty_score":0.34806266},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05123765,0.000034503137,0.9436024,0.0008094556,0.003293236,0.0000328117,0.0000028839124,0.000017029177,0.00097002025],"genre_scores_gemma":[0.5254032,0.000004517166,0.4741986,0.000039828632,0.00033995544,3.283346e-7,0.0000010367138,0.0000018743855,0.000010654683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979684,0.000028154682,0.00062667544,0.0001983068,0.0010248758,0.00015358739],"domain_scores_gemma":[0.99695635,0.00013007398,0.00072667364,0.00029830716,0.0018231521,0.0000654635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007991678,0.00008661222,0.00014590801,0.0005930062,0.00014260726,0.00045078786,0.0031067466,0.000021355074,0.000015331076],"category_scores_gemma":[0.00007495401,0.000074131065,0.000089579844,0.00056667975,0.00028212482,0.0029536826,0.00033844114,0.000119080476,0.0000065322515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002367518,0.0004985578,0.008741543,0.000009059233,0.00007822462,0.00005783187,0.00059995335,0.010593657,0.046433978,0.35042775,0.0020363522,0.5804994],"study_design_scores_gemma":[0.0025177354,0.00061506155,0.044719346,0.00060700986,0.000025243602,0.0038454705,0.000072038674,0.7017835,0.08808294,0.13103163,0.02595063,0.0007493932],"about_ca_topic_score_codex":0.000038278286,"about_ca_topic_score_gemma":0.0000019591228,"teacher_disagreement_score":0.6911898,"about_ca_system_score_codex":0.000082161525,"about_ca_system_score_gemma":0.00044695177,"threshold_uncertainty_score":0.577316},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026214123,0.00012544314,0.9719428,0.00020978972,0.0005360648,0.00008537449,0.000026644599,0.00007140768,0.00078834785],"genre_scores_gemma":[0.19722098,0.000015738864,0.8021817,0.000099001634,0.00040825646,0.0000016521068,0.000021959273,0.000007523606,0.00004315561],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978426,0.000045086737,0.00030275513,0.0005530382,0.0007848041,0.00047171777],"domain_scores_gemma":[0.99804604,0.000027199932,0.0002136016,0.0014413592,0.00010667498,0.00016513119],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002588516,0.00012597062,0.00012648721,0.00032223813,0.001201362,0.0012995879,0.0065340432,0.0000371168,0.0000120277755],"category_scores_gemma":[0.00004912259,0.00009739359,0.000027223357,0.0012216761,0.00022853567,0.012268809,0.0030689905,0.0003168499,0.000015349415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014029309,0.0003265747,0.0020891477,0.000012475818,0.0000092214505,0.00088669773,0.00024618962,0.003949196,0.8668347,0.010814416,0.038745258,0.07607212],"study_design_scores_gemma":[0.00018254948,0.00004637907,0.0024471649,0.000081314676,0.0000045815827,0.0027517572,0.000023674827,0.97550553,0.005683639,0.0032903808,0.009747108,0.00023591158],"about_ca_topic_score_codex":0.00012230611,"about_ca_topic_score_gemma":0.0000056785852,"teacher_disagreement_score":0.97155637,"about_ca_system_score_codex":0.00009391203,"about_ca_system_score_gemma":0.00053580245,"threshold_uncertainty_score":0.99973714},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27298352,0.002985867,0.7225316,0.00025707702,0.00088530476,0.00009533354,0.0000033799242,0.00005470368,0.00020323526],"genre_scores_gemma":[0.36001387,0.00004684381,0.63910055,0.000117020376,0.00068558234,8.526449e-7,0.0000017930181,0.000017448601,0.000016053413],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772096,0.00008072593,0.000806548,0.000298146,0.0006846678,0.00040892587],"domain_scores_gemma":[0.9979846,0.000106005915,0.0007203639,0.0007127649,0.00024888647,0.00022741774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042038978,0.00024154045,0.0003400065,0.00019981373,0.0003444538,0.0002906618,0.0023739936,0.00008682986,0.000039328308],"category_scores_gemma":[0.00010104276,0.0002068479,0.0001341235,0.00034167283,0.000043471915,0.0026804714,0.0022062121,0.00039569614,0.000007456236],"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":[0.000064541586,0.0008071191,0.0008738877,0.000020085949,0.00012128741,0.00023440675,0.0030160036,0.024890896,0.612106,0.0017936315,0.0014711574,0.35460097],"study_design_scores_gemma":[0.0011172454,0.00019376745,0.00014764612,0.00028310975,0.000012403994,0.00067406363,0.0007342875,0.78144366,0.21253505,0.0005101109,0.002002136,0.00034650048],"about_ca_topic_score_codex":0.000037050686,"about_ca_topic_score_gemma":7.8837684e-7,"teacher_disagreement_score":0.75655276,"about_ca_system_score_codex":0.00019444808,"about_ca_system_score_gemma":0.000108944114,"threshold_uncertainty_score":0.84350127},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002046172,0.000045471003,0.9809983,0.0072250864,0.00020126981,0.0010137169,0.000053777676,0.00037016324,0.008046043],"genre_scores_gemma":[0.7895667,0.000051029103,0.20513423,0.0020385766,0.00097511377,0.00069703633,0.0001448251,0.000092248934,0.0013002595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971415,0.00008672904,0.000325071,0.0010659018,0.0008143178,0.00056650897],"domain_scores_gemma":[0.99773645,0.00011598562,0.00015996532,0.0014894609,0.00014176601,0.00035634433],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026437512,0.00040335112,0.00027825273,0.00029069642,0.00042786254,0.0003647598,0.0011982626,0.000109022985,0.00002460739],"category_scores_gemma":[0.00001165368,0.00029258378,0.00007782297,0.0009775363,0.000077864854,0.00036288952,0.00030548024,0.0002681078,0.0005947323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017635411,0.0009787668,0.000084058236,0.000027781625,0.00006673613,0.000019058978,0.002644607,0.3102696,0.0056849867,0.53906864,0.003037462,0.13794196],"study_design_scores_gemma":[0.0020315323,0.0025139994,0.0010515624,0.00027766536,0.000045535522,0.00004839049,0.00022410332,0.8057501,0.04184639,0.0019104792,0.14251558,0.0017847026],"about_ca_topic_score_codex":0.000040374918,"about_ca_topic_score_gemma":0.00000990576,"teacher_disagreement_score":0.7875205,"about_ca_system_score_codex":0.00016644462,"about_ca_system_score_gemma":0.00009523293,"threshold_uncertainty_score":0.9999526},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08388761,0.000011351964,0.90898305,0.0006208746,0.0003363203,0.0001529152,0.000002789103,0.000079826386,0.005925241],"genre_scores_gemma":[0.9017961,0.0000015322339,0.09781813,0.00035425945,0.000018497112,0.0000035005528,5.026396e-7,0.000004559984,0.0000029317134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977658,0.00019960415,0.00028449716,0.0005228631,0.0007708225,0.00045645636],"domain_scores_gemma":[0.997826,0.0005665171,0.0001182056,0.0012347769,0.00010581771,0.00014872632],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0020973412,0.00016420944,0.00021413535,0.00011194103,0.00057972106,0.00026195415,0.0030175212,0.00003594176,0.000056434117],"category_scores_gemma":[0.00014294487,0.000098845005,0.000062646046,0.0010059209,0.0046547456,0.0004030977,0.0009142865,0.00023475925,0.000029107729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035392675,0.00005778967,0.000031847678,0.000004064445,0.0000017876313,0.0000026654436,0.00016300603,0.00008708331,0.0003233095,0.9951737,0.00006286705,0.004088358],"study_design_scores_gemma":[0.00011543308,0.0001133747,0.00045888362,0.000036335532,0.0000015579959,0.000014799341,0.000005167626,0.38373536,0.020061668,0.5952766,0.00006201465,0.00011880749],"about_ca_topic_score_codex":0.0000043150203,"about_ca_topic_score_gemma":2.103298e-7,"teacher_disagreement_score":0.81790847,"about_ca_system_score_codex":0.000032678905,"about_ca_system_score_gemma":0.00006528501,"threshold_uncertainty_score":0.998054},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017334579,0.0006182146,0.99398786,0.0000802282,0.0012767224,0.00089152297,0.000009399927,0.000103035,0.0012995865],"genre_scores_gemma":[0.7694824,0.0000039015704,0.2292921,0.00011765461,0.0005902268,0.000021135422,0.0000074807044,0.000021107942,0.00046404882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981308,0.00012507424,0.00056963554,0.00034677974,0.00039402832,0.00043370295],"domain_scores_gemma":[0.9974259,0.0011619799,0.00036311545,0.00079977687,0.00017482275,0.000074383664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044414825,0.00018235293,0.00027256084,0.00008884665,0.00029722077,0.00014170345,0.001326722,0.000060776572,0.0000024420754],"category_scores_gemma":[0.000017999997,0.00011633568,0.00010965068,0.00020547675,0.000081994935,0.00017732408,0.00048646453,0.00011098747,0.000012345793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019743047,0.00007396864,0.000075751705,0.00011240265,0.00006900489,0.000004496803,0.0016257056,0.002407191,0.00012396633,0.19193877,0.00091026485,0.8026387],"study_design_scores_gemma":[0.00070688926,0.00021319288,0.0010666625,0.0003220066,0.00001976189,0.000045784444,0.00056081894,0.96766067,0.00029403338,0.015465504,0.01340186,0.00024280294],"about_ca_topic_score_codex":0.000049932336,"about_ca_topic_score_gemma":0.0000031206737,"teacher_disagreement_score":0.9652535,"about_ca_system_score_codex":0.000036521047,"about_ca_system_score_gemma":0.00003637314,"threshold_uncertainty_score":0.47440314},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008180028,0.000013441645,0.9888179,0.0008434803,0.00014862254,0.0002444669,0.0000030496371,0.0001348375,0.0016141966],"genre_scores_gemma":[0.70700455,0.0000060766047,0.29124308,0.00026355052,0.000075418,0.000095753065,0.000011415918,0.000005001468,0.001295192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937046,0.00001013377,0.00011667176,0.00023975785,0.0001108448,0.00015211068],"domain_scores_gemma":[0.9993613,0.00005819277,0.000045282475,0.00040358762,0.000074588934,0.000057059704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009024788,0.000060926588,0.00005913063,0.000028599714,0.00008484344,0.00020097742,0.0005476446,0.00003083197,0.000048627713],"category_scores_gemma":[0.000019226913,0.000047019996,0.000024400442,0.000093668816,0.000011660941,0.0010483105,0.00015024151,0.000035590987,0.00014889636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013614881,0.00003893618,0.0002533667,0.00001346665,0.00000602043,5.701741e-7,0.00012198916,0.000040551553,0.04877361,0.35924208,0.01861987,0.5728882],"study_design_scores_gemma":[0.00017658107,0.000035309826,0.0076676733,0.000014108845,0.0000012879503,0.000002720806,0.000027122109,0.94973814,0.007907046,0.021104096,0.01318728,0.00013862256],"about_ca_topic_score_codex":0.000059683516,"about_ca_topic_score_gemma":0.0000010887384,"teacher_disagreement_score":0.9496976,"about_ca_system_score_codex":0.000021377198,"about_ca_system_score_gemma":0.000023588253,"threshold_uncertainty_score":0.193803},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15638617,0.00001759096,0.8425944,0.00007798303,0.00046586408,0.00013457538,0.0000016435756,0.00011897189,0.00020284377],"genre_scores_gemma":[0.1547206,0.0000069821094,0.8450316,0.00006047343,0.000087799206,0.0000024660965,0.0000018738137,0.000009018385,0.00007913954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997751,0.00003830567,0.00035883905,0.00060359115,0.00080948666,0.0004387602],"domain_scores_gemma":[0.9983629,0.00012778451,0.00016659398,0.0010658884,0.00014619452,0.00013062333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007002475,0.00018918715,0.00024014947,0.00032836047,0.0004277683,0.00031945284,0.002109736,0.000055956327,0.000009958874],"category_scores_gemma":[0.000054862143,0.00016672842,0.000039141487,0.0015523629,0.00026983264,0.0015950812,0.0013345147,0.00015222457,0.00010834851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000196437,0.0046410263,0.013294215,0.0006342758,0.00005936366,0.0006895197,0.09196434,0.16679633,0.12615027,0.2555058,0.006275152,0.33397007],"study_design_scores_gemma":[0.0001575673,0.000020629388,0.00070655014,0.00008538875,0.0000011334258,0.00012264344,0.0000051282695,0.99059105,0.0017631275,0.006072388,0.0002456125,0.0002287712],"about_ca_topic_score_codex":0.000027928392,"about_ca_topic_score_gemma":0.0000023040388,"teacher_disagreement_score":0.8237947,"about_ca_system_score_codex":0.00013166091,"about_ca_system_score_gemma":0.00022151267,"threshold_uncertainty_score":0.6798988},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61674106,0.000060927294,0.38211432,0.00016020011,0.00029444718,0.00029668448,0.0000030910494,0.000041839146,0.00028742134],"genre_scores_gemma":[0.9947046,0.000001737737,0.0051979106,0.00004420395,0.000034984663,0.0000018535806,0.0000026463108,0.0000059489753,0.0000061022693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785,0.00031084262,0.00052341656,0.00042659466,0.00062560197,0.00026356065],"domain_scores_gemma":[0.99566925,0.0014208854,0.0004599088,0.0018206071,0.0005621612,0.00006719939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025266283,0.00017723718,0.00042303483,0.00014495477,0.00037662007,0.00006471984,0.0019086677,0.000062522005,0.0000027704477],"category_scores_gemma":[0.00026054904,0.00008437157,0.00017355931,0.0023606566,0.00026270025,0.00020294626,0.000495074,0.00022483336,4.2624595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013353265,0.0010694253,0.06471114,0.000066195586,0.00031193302,0.0000020574817,0.0026825538,0.0051967558,0.00013963738,0.9080911,0.00006905461,0.017526593],"study_design_scores_gemma":[0.0021568867,0.0008033949,0.2818738,0.00022819541,0.000341393,0.0000030400888,0.00027727836,0.51772994,0.05502639,0.14049919,0.00056784693,0.00049266225],"about_ca_topic_score_codex":0.000048429083,"about_ca_topic_score_gemma":0.000012499243,"teacher_disagreement_score":0.76759195,"about_ca_system_score_codex":0.000058173744,"about_ca_system_score_gemma":0.00008523397,"threshold_uncertainty_score":0.35468113},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025927362,0.00000474412,0.99589556,0.00010198137,0.00047643768,0.00024582376,0.00016429258,0.00013921158,0.00037920423],"genre_scores_gemma":[0.965326,0.0000037910236,0.03427626,0.00023428218,0.000016251824,0.00003650814,0.00003488136,0.0000064356896,0.00006559391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990865,0.00010010459,0.00030775313,0.00012892851,0.0002251761,0.00015152516],"domain_scores_gemma":[0.9987678,0.0003948898,0.0001819135,0.00044966568,0.00013828254,0.00006747643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003888402,0.00012434149,0.00014989197,0.0002622992,0.00023289541,0.0000572944,0.00044365507,0.000076894605,0.000023803612],"category_scores_gemma":[0.0000083296445,0.000106481544,0.00010315936,0.00020353531,0.000069228176,0.0015324465,0.0000045564143,0.000103870116,0.000020948944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073319825,0.0003409655,0.0000041537073,0.00015002747,0.000037264737,3.9874715e-7,0.0011803292,0.23975776,0.0021388805,0.103331275,0.0009450083,0.6513807],"study_design_scores_gemma":[0.001601054,0.00041500223,0.00008796972,0.000095717776,0.000015339585,0.0000017197691,0.00011086004,0.95278347,0.030740125,0.0036054943,0.010370223,0.00017300976],"about_ca_topic_score_codex":0.000008032273,"about_ca_topic_score_gemma":0.0000028542415,"teacher_disagreement_score":0.96273327,"about_ca_system_score_codex":0.00003028876,"about_ca_system_score_gemma":0.000054810334,"threshold_uncertainty_score":0.43421915},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06855462,0.0012547014,0.86181426,0.0150082745,0.0038662152,0.0009914747,0.00008471026,0.0021143667,0.046311386],"genre_scores_gemma":[0.8754609,0.0013611554,0.109339654,0.0016475125,0.00094353023,0.00013195221,0.00023578915,0.00014372455,0.010735741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99676126,0.00014346103,0.00046947668,0.001154334,0.00071610755,0.0007553714],"domain_scores_gemma":[0.9974396,0.000148686,0.00019479395,0.0018566883,0.000087062945,0.0002731265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038530084,0.00039704752,0.00034811793,0.0002646864,0.0004566326,0.00041744005,0.0017786616,0.00013945643,0.00006448552],"category_scores_gemma":[0.00003178145,0.00032875218,0.0001930721,0.00073689566,0.00008209708,0.0012459519,0.000985734,0.00033542453,0.00030399827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004411826,0.002202276,0.008662325,0.00014225571,0.000502488,0.0054615084,0.0032406251,0.013145514,0.10603048,0.041882567,0.04050666,0.77778214],"study_design_scores_gemma":[0.0010134092,0.0005040609,0.008782722,0.00014875589,0.000020210613,0.00018518436,0.000081886785,0.94297695,0.002026732,0.0020337217,0.04139578,0.00083057006],"about_ca_topic_score_codex":0.00014141871,"about_ca_topic_score_gemma":0.000013489338,"teacher_disagreement_score":0.92983145,"about_ca_system_score_codex":0.00008991072,"about_ca_system_score_gemma":0.0000590415,"threshold_uncertainty_score":0.99991643},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006453769,0.0000811095,0.9923509,0.00055034924,0.00007420124,0.00006880282,8.561285e-7,0.000031843418,0.00038818113],"genre_scores_gemma":[0.07095213,0.000004235075,0.92842853,0.00054313656,0.000047491758,0.000003480359,0.00000569392,0.0000036827644,0.000011633715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857837,0.00035837136,0.00033128864,0.00032019874,0.00026217528,0.00014960798],"domain_scores_gemma":[0.996926,0.002602208,0.0000824974,0.00023627163,0.00005208701,0.000100920144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013002912,0.00011687008,0.00038573108,0.00027949864,0.000072547016,0.000022594248,0.00027212483,0.00004701469,0.000033062173],"category_scores_gemma":[0.00063393696,0.000080096506,0.000032966618,0.00061571714,0.00012964159,0.00008933304,0.00015055531,0.00011559606,0.0000034565614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006291793,0.00010518667,0.00014604097,0.000042303047,0.000046263624,0.000009457638,0.00042173432,0.033811726,0.00034070213,0.7709195,0.00008164951,0.19406913],"study_design_scores_gemma":[0.00020138445,0.000053501426,0.0026540982,0.000056368313,0.000022282997,0.00001089661,0.0000070131273,0.6074,0.000013538457,0.38948673,0.000039328046,0.000054881355],"about_ca_topic_score_codex":0.000009477191,"about_ca_topic_score_gemma":0.0000012699169,"teacher_disagreement_score":0.57358825,"about_ca_system_score_codex":0.000015706762,"about_ca_system_score_gemma":0.000014202403,"threshold_uncertainty_score":0.32662407},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84518135,0.0014246767,0.1460858,0.0011732043,0.0025100666,0.0008492241,0.0024457006,0.000035562112,0.00029442337],"genre_scores_gemma":[0.9957378,0.000034566223,0.0030682625,0.00025063351,0.00075538555,0.00001177799,0.00011316602,0.000024497356,0.000003929089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981807,0.00009114833,0.0006198216,0.00032077287,0.00034136893,0.0004461842],"domain_scores_gemma":[0.998193,0.0001750795,0.0005236725,0.00039773388,0.0002649229,0.0004455421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033835656,0.00028155377,0.00046515962,0.00021026579,0.00018055913,0.00017301124,0.00055478653,0.0001185594,0.0000038002186],"category_scores_gemma":[0.0000746103,0.00023969258,0.00013658308,0.00030206377,0.00012960524,0.0008336574,0.000044969416,0.0003105861,0.000008535032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027380462,0.0013364758,0.0025561887,0.0007521942,0.0004601947,0.0010467479,0.005729565,0.03543521,0.042603467,0.74559504,0.033807676,0.13040343],"study_design_scores_gemma":[0.009896328,0.003960493,0.0040412187,0.003901334,0.00011988618,0.0004079255,0.00046702463,0.6923669,0.10573038,0.17348975,0.0036145502,0.0020042048],"about_ca_topic_score_codex":0.0014364636,"about_ca_topic_score_gemma":0.0024737802,"teacher_disagreement_score":0.6569317,"about_ca_system_score_codex":0.0001805741,"about_ca_system_score_gemma":0.00081945054,"threshold_uncertainty_score":0.977438},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011983525,0.0004121298,0.9823497,0.0035103236,0.00070979155,0.00019316433,0.0000138699215,0.00003521894,0.0007922966],"genre_scores_gemma":[0.44823813,0.00074035244,0.5482251,0.00032707248,0.0019152289,0.000011656731,0.000012587396,0.00005558278,0.00047430032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822277,0.00008724495,0.00045558132,0.00027749577,0.0005724353,0.00038449303],"domain_scores_gemma":[0.9979424,0.00044371534,0.00051949435,0.00053535076,0.00032621974,0.00023284521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074783276,0.0002064152,0.0002871028,0.00014637902,0.0004461165,0.00030870337,0.0016404951,0.00007591378,0.00000549805],"category_scores_gemma":[0.000047359616,0.00011248238,0.00019986731,0.0003466961,0.00015492589,0.000691239,0.00026522466,0.00030665126,0.000002793416],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031863896,0.0008214459,0.001789783,0.00012973782,0.0011657141,0.00051819015,0.0017316834,0.0029471226,0.0034060997,0.1969397,0.041715134,0.745649],"study_design_scores_gemma":[0.007407724,0.0070001534,0.009629517,0.00038426215,0.00014370824,0.0005316672,0.00045318808,0.5637683,0.0015141327,0.022321906,0.38589194,0.00095348863],"about_ca_topic_score_codex":0.000010045048,"about_ca_topic_score_gemma":0.000005532242,"teacher_disagreement_score":0.7446955,"about_ca_system_score_codex":0.00003257986,"about_ca_system_score_gemma":0.00011306628,"threshold_uncertainty_score":0.45868984},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06695808,0.0025600332,0.92915916,0.00019663318,0.00033378447,0.00020118213,0.000049603495,0.0000857926,0.00045570938],"genre_scores_gemma":[0.9498578,0.0014669324,0.048058502,0.00015243201,0.00017188751,0.000011673727,0.000050176026,0.000011967958,0.00021867934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985166,0.000088110304,0.000377037,0.0004206823,0.00034072172,0.00025682658],"domain_scores_gemma":[0.9988292,0.0002624954,0.000172799,0.0005289915,0.000084339714,0.00012220911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029674,0.00019863137,0.00066433154,0.00031668154,0.00018089297,0.00014933807,0.00051208807,0.00008017747,0.00007488424],"category_scores_gemma":[0.00004702015,0.00013832832,0.00020895599,0.0009754254,0.000106394524,0.00037736454,0.0002459968,0.000111323774,0.0000010450844],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091418886,0.00009096939,0.0054052165,0.000039847673,0.001719702,0.00008143545,0.0013571632,0.0022410718,0.0007399219,0.017616546,0.00088015787,0.9689138],"study_design_scores_gemma":[0.019321108,0.00016910348,0.047723055,0.000033086704,0.00075976324,0.00008578351,0.000114040435,0.89446425,0.0012718405,0.0149969915,0.020449385,0.00061157125],"about_ca_topic_score_codex":0.00014775555,"about_ca_topic_score_gemma":0.000010222556,"teacher_disagreement_score":0.9683022,"about_ca_system_score_codex":0.000007807139,"about_ca_system_score_gemma":0.000024494231,"threshold_uncertainty_score":0.5640865},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005000011,0.00038885826,0.99351305,0.00020691415,0.00009440834,0.00018468327,0.0000010599483,0.000100213,0.00051083294],"genre_scores_gemma":[0.8764542,0.00005042985,0.122885466,0.00012015169,0.0001032217,0.000016898326,0.000015495842,0.0000064690184,0.00034768242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917215,0.00006924258,0.00014947861,0.00025800202,0.0001391804,0.00021192645],"domain_scores_gemma":[0.9995179,0.00007199134,0.00006568227,0.00017423536,0.000036189394,0.00013396985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026477527,0.00009312177,0.0001017799,0.000087360786,0.00007400352,0.000052340245,0.00016132784,0.00005893626,0.0000048930724],"category_scores_gemma":[0.00001915916,0.00008313729,0.000015772606,0.00020977114,0.000011077312,0.00093844684,0.000116528354,0.000144239,0.000038667855],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021290023,0.000025510388,0.00074722833,0.0000023609118,0.0000022501908,5.8020396e-7,0.00065434474,0.000006942,0.0019057315,0.03186615,0.00017355497,0.9646132],"study_design_scores_gemma":[0.00043865404,0.000036479138,0.07629529,0.000016378397,0.000003189021,0.000017202978,0.00034415128,0.9099017,0.0017442383,0.00051972794,0.010479991,0.00020304906],"about_ca_topic_score_codex":0.00023811581,"about_ca_topic_score_gemma":0.000018907374,"teacher_disagreement_score":0.9644102,"about_ca_system_score_codex":0.00003644197,"about_ca_system_score_gemma":0.000029960522,"threshold_uncertainty_score":0.33902404},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113316186,0.00004096213,0.8826652,0.0026436395,0.001077293,0.000039858387,0.0000033684344,0.00000922616,0.00020426247],"genre_scores_gemma":[0.6172416,0.00002698388,0.3825739,0.00007750017,0.000074808086,5.42625e-7,8.83907e-7,0.0000013586218,0.0000024034402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984451,0.000022768489,0.0004835849,0.00019267938,0.0007283875,0.00012747312],"domain_scores_gemma":[0.99847937,0.00007494478,0.0003392622,0.00025156038,0.0007691528,0.00008569527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068072195,0.000074658674,0.00013740029,0.0006859122,0.00009971902,0.0002844565,0.001846052,0.00001928453,0.0000073608066],"category_scores_gemma":[0.000083104336,0.000066378925,0.000043800952,0.0006351602,0.0004484296,0.002417167,0.00054461975,0.00013204763,0.0000024031438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020678308,0.0004689803,0.0024302162,0.000006460196,0.00002933369,0.00006811994,0.0016238148,0.008560763,0.0017912204,0.76059645,0.00008530145,0.22431867],"study_design_scores_gemma":[0.003808968,0.00050972385,0.34512722,0.0009170689,0.000010948641,0.0016413825,0.000095896474,0.15058723,0.0035190394,0.48920318,0.0041086404,0.0004706695],"about_ca_topic_score_codex":0.00005148278,"about_ca_topic_score_gemma":0.000019878391,"teacher_disagreement_score":0.50392544,"about_ca_system_score_codex":0.00011517978,"about_ca_system_score_gemma":0.0004097366,"threshold_uncertainty_score":0.34304547},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07470743,0.00013176475,0.9242855,0.0003146,0.0003672526,0.000043485627,0.0000062267736,0.000014677486,0.00012910698],"genre_scores_gemma":[0.42272633,0.0000415401,0.5768368,0.000330517,0.000039449314,4.2120809e-7,0.000017087732,0.0000025457132,0.000005269431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895936,0.00002083784,0.00062114303,0.0000813616,0.00018876613,0.00012850674],"domain_scores_gemma":[0.9989744,0.000055123994,0.0005628501,0.00010214218,0.00021100145,0.00009452293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034968893,0.00009417631,0.00017099708,0.00017652381,0.00012298813,0.00012239677,0.00033048095,0.000054192355,0.000002360529],"category_scores_gemma":[0.00002624333,0.00006804676,0.00004520488,0.00015974394,0.000049819613,0.0007840561,0.00018411358,0.00013702612,0.0000073175925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011738755,0.0003911192,0.0017909714,0.0001742941,0.00043494574,0.00017151928,0.010942057,0.16771734,0.0013890883,0.53797513,0.00081560056,0.27808058],"study_design_scores_gemma":[0.0027716907,0.0008101757,0.005106668,0.00019262572,0.000019249941,0.0020036872,0.0003521054,0.59037966,0.00068159256,0.39675802,0.0006301318,0.00029440565],"about_ca_topic_score_codex":0.000005545502,"about_ca_topic_score_gemma":4.9428877e-7,"teacher_disagreement_score":0.42266232,"about_ca_system_score_codex":0.00003210561,"about_ca_system_score_gemma":0.00013651104,"threshold_uncertainty_score":0.27748662},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13880867,0.00021959735,0.8597702,0.00012287198,0.0007703547,0.00005383942,0.000011175516,0.000049580503,0.00019370556],"genre_scores_gemma":[0.70772314,0.00005650348,0.29126415,0.0001284776,0.0007766048,0.0000019871072,0.0000073258066,0.0000192568,0.000022534465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799824,0.0001607431,0.0005984233,0.0003154027,0.00060499355,0.00032218624],"domain_scores_gemma":[0.9982219,0.00012272882,0.0005564206,0.0006583022,0.00012590758,0.00031479142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006636123,0.0002083774,0.00035553038,0.00024154155,0.00015435273,0.00038629284,0.0015597334,0.00009207362,0.000010804837],"category_scores_gemma":[0.00006829447,0.00015888605,0.00015472606,0.00025656063,0.000040100727,0.0028269808,0.0004304974,0.00041101885,0.000007732462],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031398227,0.00014205535,0.002089847,0.000012804672,0.0000933896,0.00012522879,0.0010988653,0.0006465303,0.0033873096,0.0021992999,0.0003101431,0.98986316],"study_design_scores_gemma":[0.003025714,0.0018076339,0.044549864,0.00057784293,0.000082701146,0.00031888112,0.00018673993,0.86521596,0.010484867,0.059616666,0.0131631475,0.0009699589],"about_ca_topic_score_codex":0.00009845124,"about_ca_topic_score_gemma":0.0000060579846,"teacher_disagreement_score":0.98889315,"about_ca_system_score_codex":0.00003470401,"about_ca_system_score_gemma":0.00005948652,"threshold_uncertainty_score":0.64791846},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025372676,0.000024959641,0.99752486,0.00027751326,0.0007356094,0.0005037675,0.000046749316,0.00025431745,0.0003784918],"genre_scores_gemma":[0.29526123,0.000010087243,0.7039942,0.00030791055,0.000043830194,0.00023481646,0.000045061974,0.00000770541,0.00009510431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987373,0.00014077911,0.0004333644,0.00016008085,0.0003066157,0.00022189025],"domain_scores_gemma":[0.9983115,0.00038880296,0.000108199056,0.00085072836,0.0002421964,0.000098535354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007803608,0.0001231237,0.00016140612,0.00027580242,0.0006134291,0.00019523656,0.00073245994,0.000085578715,0.000007285078],"category_scores_gemma":[0.000035299738,0.0001077008,0.000085031854,0.0004133723,0.00003292536,0.0022698243,0.000014371426,0.00015077746,0.00008583968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076728014,0.00015824866,0.000043306387,0.0003765487,0.00006235423,0.0000017608288,0.003292443,0.25980332,0.00045042066,0.009173029,0.0022568083,0.72430503],"study_design_scores_gemma":[0.0005823182,0.00009048778,0.000058864473,0.00004647573,0.000003665603,0.00002187394,0.00013586746,0.8781237,0.0018550297,0.000046990386,0.11889699,0.00013771768],"about_ca_topic_score_codex":0.00005921684,"about_ca_topic_score_gemma":5.1698026e-7,"teacher_disagreement_score":0.7241673,"about_ca_system_score_codex":0.00007026043,"about_ca_system_score_gemma":0.00018607917,"threshold_uncertainty_score":0.4718063},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032682087,0.000009440726,0.96448255,0.0011121335,0.0010635243,0.00044703038,0.0000017069665,0.0000791142,0.00012242397],"genre_scores_gemma":[0.16108534,0.0000017897445,0.83852863,0.00020072638,0.00014943874,0.000018118382,7.6405536e-7,0.000008103817,0.0000071185423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746585,0.000041883442,0.0005258573,0.0007118444,0.00062659924,0.0006279958],"domain_scores_gemma":[0.9972551,0.0010969145,0.00019047716,0.0012222131,0.00012271122,0.00011256991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037846216,0.00018806502,0.00024159356,0.00025881853,0.00028194202,0.00073165435,0.0027243567,0.000068357826,0.0000019435272],"category_scores_gemma":[0.0003134374,0.00013241479,0.00005139864,0.0010459842,0.00026412634,0.0010248796,0.0018843124,0.0005361535,0.000008538096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006213381,0.00088225264,0.00055944,0.000113047114,0.000009744418,0.00010022595,0.01239943,0.007923703,0.0028755239,0.40636545,0.00053538877,0.56822956],"study_design_scores_gemma":[0.00030952046,0.00004500513,0.0008140708,0.00007895079,0.0000015072645,0.00009665834,0.000034356064,0.9757599,0.00054413377,0.021778714,0.00036063656,0.00017652374],"about_ca_topic_score_codex":0.000021864995,"about_ca_topic_score_gemma":0.00003507449,"teacher_disagreement_score":0.9678362,"about_ca_system_score_codex":0.00005759068,"about_ca_system_score_gemma":0.00020336,"threshold_uncertainty_score":0.705536},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009551016,0.00037002514,0.9864548,0.0020743434,0.0006746746,0.0001565094,0.00003583611,0.000103281396,0.0005795301],"genre_scores_gemma":[0.1522565,0.000075576725,0.8407701,0.0007228519,0.001320623,0.00008618008,0.000037847745,0.00003227597,0.0046980167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992194,0.000019312705,0.00011407962,0.0001866789,0.00021825211,0.0002422832],"domain_scores_gemma":[0.9989729,0.000107250846,0.000056165278,0.0006941922,0.00006830854,0.000101184385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026419814,0.000079877944,0.0000816139,0.000017030998,0.00026268594,0.0002609473,0.0014237298,0.000028068845,0.000003926255],"category_scores_gemma":[0.00009583118,0.000047426398,0.000042322958,0.000066537854,0.00003953884,0.00024874666,0.00054678065,0.00006038032,0.000038288235],"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":[0.000053463624,0.00008946738,0.00044812934,0.00000789318,0.000032025677,0.000010995652,0.001128076,0.0023119575,0.0002698886,0.3172272,0.63319314,0.045227785],"study_design_scores_gemma":[0.0005824999,0.0000910915,0.00017826098,0.000005538096,0.0000027308274,0.000004394649,0.00006152588,0.3788518,0.0009775213,0.006197751,0.61295915,0.000087734195],"about_ca_topic_score_codex":0.000014472118,"about_ca_topic_score_gemma":0.0000042854304,"teacher_disagreement_score":0.37653983,"about_ca_system_score_codex":0.000018350263,"about_ca_system_score_gemma":0.0000477579,"threshold_uncertainty_score":0.2645668},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2619006,0.00007788188,0.7310497,0.0008443266,0.0020820473,0.00029713023,0.000026334483,0.0003079614,0.0034139715],"genre_scores_gemma":[0.6989439,0.000011275933,0.30068412,0.00008064046,0.00010096506,0.000010120876,0.000020369145,0.000009239801,0.00013934472],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895304,0.000034774053,0.000234778,0.0003210466,0.00027275353,0.00018358498],"domain_scores_gemma":[0.99872917,0.00009749378,0.000121779034,0.0008502303,0.00012053536,0.00008080726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001587714,0.00010144075,0.00016135686,0.00010810099,0.00007973893,0.00005088803,0.0007897586,0.000069817186,0.000055177006],"category_scores_gemma":[0.000053819804,0.000086856155,0.00006636764,0.00047632007,0.000052275816,0.00050326134,0.00028875706,0.00018337871,0.000034827714],"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":[0.000012198716,0.00023862666,0.0018057832,0.000016536162,0.000040620347,0.000025771691,0.00035876347,0.000010447622,0.15544376,0.16373765,0.0060273744,0.67228246],"study_design_scores_gemma":[0.0021400366,0.0002997062,0.03642646,0.000045984143,0.000031744927,0.00011611267,0.000052506894,0.30601278,0.5374071,0.093275525,0.023410628,0.00078144023],"about_ca_topic_score_codex":0.00014627815,"about_ca_topic_score_gemma":0.000010605997,"teacher_disagreement_score":0.67150104,"about_ca_system_score_codex":0.000004526794,"about_ca_system_score_gemma":0.000037142174,"threshold_uncertainty_score":0.3541891},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02026762,0.000057863042,0.9787997,0.00012504142,0.000090086774,0.000058928923,0.000047335136,0.0000674338,0.00048599762],"genre_scores_gemma":[0.28413355,0.0000051473266,0.71550167,0.000114030576,0.000032288564,0.0000033659835,0.00017322501,0.0000028535937,0.000033882032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990283,0.000052613348,0.0002648998,0.00034241076,0.00016623372,0.00014551368],"domain_scores_gemma":[0.99912524,0.00021891789,0.00010690964,0.0003806203,0.00011118011,0.000057126585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012232525,0.000090238034,0.00024374682,0.00024193744,0.000059929193,0.000046345784,0.0004891659,0.00004695007,0.00013727938],"category_scores_gemma":[0.00002265073,0.00007117892,0.0000871947,0.0011042559,0.000050640796,0.00022038759,0.00027013116,0.000056347013,0.000011262384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001014269,0.00041194144,0.016462501,0.000004834754,0.0009610219,0.000027962911,0.00053477316,0.045065206,0.0003636418,0.07417916,0.0005046153,0.8614742],"study_design_scores_gemma":[0.00014785178,0.00003209072,0.025128895,0.000004782389,0.00006557879,0.0000025167262,0.000008388919,0.93979806,0.000016917762,0.034264743,0.0004451349,0.00008504186],"about_ca_topic_score_codex":0.0010371867,"about_ca_topic_score_gemma":0.000036338548,"teacher_disagreement_score":0.89473283,"about_ca_system_score_codex":0.000017567578,"about_ca_system_score_gemma":0.000039183753,"threshold_uncertainty_score":0.2902592},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023675654,0.000018176332,0.98997307,0.00040765476,0.003592109,0.00028413965,0.00004002959,0.00037819045,0.002939054],"genre_scores_gemma":[0.9606893,0.000019532441,0.03859787,0.00018871712,0.000039857474,0.00007934728,0.000044304423,0.000008025066,0.00033301723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864525,0.000039799783,0.00046245303,0.00018876027,0.00044649933,0.00021723758],"domain_scores_gemma":[0.99806255,0.000104636514,0.00017997045,0.001377168,0.0001446913,0.00013097494],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022271462,0.0001655342,0.00015841628,0.00028726412,0.00043188766,0.00049722946,0.0011812508,0.0001421968,0.000057325116],"category_scores_gemma":[0.000016247262,0.00013105391,0.00006910115,0.00035039015,0.000028018449,0.004170322,0.000034178876,0.0003917186,0.001052057],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048636557,0.00032727682,0.000049035472,0.0001766769,0.00007211687,0.000005701939,0.0033890104,0.012439471,0.0053064153,0.04003722,0.0071390076,0.9310094],"study_design_scores_gemma":[0.0006881784,0.00008888029,0.0006818399,0.00010201062,0.00000767088,0.0000841779,0.0001494084,0.5936887,0.0018893295,0.0003872958,0.4018727,0.00035979733],"about_ca_topic_score_codex":0.000054802946,"about_ca_topic_score_gemma":0.000006554284,"teacher_disagreement_score":0.95832175,"about_ca_system_score_codex":0.00003397757,"about_ca_system_score_gemma":0.000046869394,"threshold_uncertainty_score":0.99972576},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14690353,0.00054360315,0.6985052,0.0027214952,0.004650071,0.0016249166,0.00014411678,0.002149024,0.14275804],"genre_scores_gemma":[0.29869983,0.00048554598,0.65325505,0.0029521002,0.0019084478,0.00049866387,0.0006903398,0.00020751785,0.041302517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945989,0.00018350502,0.0008206175,0.0022647223,0.001208607,0.00092359557],"domain_scores_gemma":[0.99400985,0.00014380433,0.00062921963,0.004154202,0.0004921931,0.00057070935],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005296788,0.000875115,0.0009515317,0.00029268378,0.0003098154,0.0014678257,0.0052744597,0.0008528488,0.0007320012],"category_scores_gemma":[0.00009480226,0.00072501524,0.00031148293,0.0003603964,0.000120344004,0.0011654259,0.010187332,0.0013963351,0.002409263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013318607,0.0014576726,0.0013114555,0.0014391645,0.00086566806,0.0026179256,0.0061963005,0.024784163,0.00890763,0.5563291,0.25865394,0.13730381],"study_design_scores_gemma":[0.0016925636,0.00075585954,0.0024281077,0.0024406074,0.00017011649,0.00082610006,0.00071930204,0.80333567,0.030875094,0.048379008,0.102430634,0.005946916],"about_ca_topic_score_codex":0.003696651,"about_ca_topic_score_gemma":0.0000374669,"teacher_disagreement_score":0.7785515,"about_ca_system_score_codex":0.0003438713,"about_ca_system_score_gemma":0.00092737086,"threshold_uncertainty_score":0.99956876},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06950264,0.000036587822,0.9235629,0.0008869077,0.0001748834,0.00009002746,0.000001407807,0.00006935625,0.0056753103],"genre_scores_gemma":[0.93182194,0.000009776703,0.067785434,0.00006878753,0.000044141416,0.000002570725,0.0000018357077,0.0000032600606,0.00026224248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991029,0.000079192105,0.00017044826,0.00018648044,0.00027502913,0.0001859323],"domain_scores_gemma":[0.9989282,0.00021501642,0.000052246287,0.0006878958,0.000065784414,0.000050871746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005200385,0.00006876009,0.000114021124,0.000032383417,0.00026006062,0.00008962117,0.0010518834,0.000022101798,0.000015775275],"category_scores_gemma":[0.000022443362,0.00003819364,0.00004211618,0.00017749955,0.00014327535,0.00019164746,0.00073691196,0.00008047922,0.000017708764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041113602,0.00020366407,0.0040101507,0.000028805724,0.000034475208,0.0000053487474,0.0007229833,0.00053286506,0.022373552,0.34725958,0.011114477,0.613673],"study_design_scores_gemma":[0.00024482442,0.00007705751,0.035728104,0.000015067177,0.000001287829,0.0000020452462,0.00002504857,0.95182085,0.0047971243,0.0035834948,0.0036322807,0.00007280677],"about_ca_topic_score_codex":0.00023338664,"about_ca_topic_score_gemma":0.00002963498,"teacher_disagreement_score":0.951288,"about_ca_system_score_codex":0.000006682414,"about_ca_system_score_gemma":0.000023954264,"threshold_uncertainty_score":0.20002024},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009201319,0.00001909196,0.98276466,0.0002455945,0.0031796324,0.000438393,0.000073160816,0.00019125568,0.003886893],"genre_scores_gemma":[0.98134273,0.0000021283472,0.017231349,0.0003221008,0.0003428839,0.00012498435,0.00011056898,0.0000059101853,0.000517343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991078,0.000020140496,0.00033314934,0.00010568874,0.0002504816,0.00018278397],"domain_scores_gemma":[0.9990758,0.00006655017,0.00017140609,0.0004868234,0.0001253538,0.00007408697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052270404,0.00009340697,0.00011689236,0.000113329894,0.00014680815,0.00047240828,0.00054999336,0.00008174511,0.0000065776812],"category_scores_gemma":[0.0000426964,0.000072336334,0.00004383855,0.00013342952,0.000013713457,0.0033695265,0.00012577955,0.00009828924,0.0001831046],"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":[0.00005297985,0.00016084615,0.00143991,0.00053883076,0.00007715009,0.000006064519,0.015764544,0.002032454,0.008189701,0.4679263,0.27769643,0.2261148],"study_design_scores_gemma":[0.0005124853,0.00003764013,0.0012211342,0.000030843446,0.0000020920652,0.00003320888,0.00013943177,0.3827564,0.0009959678,0.00018337973,0.61390483,0.00018257191],"about_ca_topic_score_codex":0.00006046483,"about_ca_topic_score_gemma":0.000013832137,"teacher_disagreement_score":0.9721414,"about_ca_system_score_codex":0.000014400066,"about_ca_system_score_gemma":0.000052253767,"threshold_uncertainty_score":0.45554438},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000637801,0.00021906117,0.9962164,0.0014450559,0.00054962136,0.00033911908,0.00011694473,0.00027153073,0.00020442702],"genre_scores_gemma":[0.76459926,0.00006303077,0.23456827,0.0003192017,0.000030481902,0.00025255943,0.000035851237,0.000012895776,0.000118417716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895155,0.00012061155,0.00025006323,0.0002050618,0.0001680309,0.00030465526],"domain_scores_gemma":[0.9965918,0.0011244894,0.00009709288,0.0019512911,0.00010243367,0.00013287968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003235563,0.00014518619,0.0001325906,0.0001722366,0.0010812443,0.00014549436,0.0013849345,0.000076666984,0.000016445361],"category_scores_gemma":[0.000021688827,0.00014252837,0.00012206612,0.00030615536,0.00007561495,0.0009957822,0.00001558388,0.00022376842,0.00005548811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002522726,0.0113064,0.0021390114,0.00020226787,0.00038728394,0.000001241204,0.009546021,0.13807666,0.03411441,0.048114844,0.014454544,0.74140507],"study_design_scores_gemma":[0.00067683466,0.00007477072,0.00032908234,0.000053577576,0.000026318638,0.000002098657,0.00006423671,0.9301357,0.01213304,0.00029059875,0.055981312,0.00023241743],"about_ca_topic_score_codex":0.0000539368,"about_ca_topic_score_gemma":0.000049704413,"teacher_disagreement_score":0.79205906,"about_ca_system_score_codex":0.00006134636,"about_ca_system_score_gemma":0.00004506253,"threshold_uncertainty_score":0.83161664},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053372975,0.000097516255,0.94291526,0.0012561876,0.00031408176,0.00058481377,0.000018979166,0.00035169572,0.001088468],"genre_scores_gemma":[0.97562397,0.000072083465,0.02360072,0.0002962169,0.00018590652,0.00011706418,0.000015947375,0.000018670633,0.00006944366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980589,0.000011521089,0.00026661644,0.0007464411,0.00024062519,0.00067586184],"domain_scores_gemma":[0.9986784,0.00012904684,0.0000802626,0.00022552458,0.0002897599,0.0005970064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016715014,0.0003452137,0.00033553285,0.0003438084,0.00035116164,0.0004019171,0.00078986195,0.00014664966,0.0000059396007],"category_scores_gemma":[0.000070995615,0.0003090476,0.00006172371,0.00041695702,0.00005462473,0.0005986522,0.00010180201,0.0003253561,0.000011600622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027397415,0.000039729057,0.0014943364,0.000109506625,0.000034859622,0.000035711935,0.00046901123,0.000091293856,0.006008156,0.6510623,0.0015288349,0.33909884],"study_design_scores_gemma":[0.00033017024,0.00048478512,0.005823047,0.000086208755,0.0000063867656,0.00011409213,0.0000020712027,0.9886364,0.00061107747,0.0013831983,0.0021227023,0.0003998966],"about_ca_topic_score_codex":0.00088069984,"about_ca_topic_score_gemma":0.000099471275,"teacher_disagreement_score":0.98854506,"about_ca_system_score_codex":0.00012333086,"about_ca_system_score_gemma":0.00035008302,"threshold_uncertainty_score":0.99993616},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022760935,0.000024587189,0.97218007,0.00013877456,0.0005556613,0.000080841906,0.000003013524,0.00012760152,0.0041284873],"genre_scores_gemma":[0.77740955,0.0000017081131,0.222357,0.0001383481,0.00008017141,8.536864e-7,8.228682e-7,0.0000031268548,0.000008380106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786884,0.000033053388,0.00031371613,0.0005279408,0.00073826883,0.0005181854],"domain_scores_gemma":[0.9981397,0.00029180004,0.00008445967,0.0009967602,0.00023258895,0.00025469717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020677028,0.00012234203,0.00015768205,0.00019703063,0.00031594443,0.00012919877,0.0025004214,0.00003822218,0.00005684899],"category_scores_gemma":[0.000076686374,0.000095804695,0.000054151293,0.0013661683,0.0019988907,0.0008283114,0.0016515312,0.00013564598,0.000053971617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045312154,0.00004835361,0.00009419944,0.00000392003,0.000001300762,0.000005716206,0.00009888427,0.000052379244,0.0023511949,0.8902753,0.00010263511,0.106961556],"study_design_scores_gemma":[0.00031546157,0.000446135,0.0090200165,0.000045627326,0.0000055246933,0.000061787214,0.000017954628,0.7198048,0.035016537,0.23351134,0.0014008732,0.00035393864],"about_ca_topic_score_codex":0.00000642389,"about_ca_topic_score_gemma":4.9973545e-7,"teacher_disagreement_score":0.7546486,"about_ca_system_score_codex":0.00003028259,"about_ca_system_score_gemma":0.00009249119,"threshold_uncertainty_score":0.7364996},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00619703,0.0001780582,0.9884154,0.0007942127,0.003744386,0.00005871828,0.000010055693,0.000030354233,0.0005717873],"genre_scores_gemma":[0.37915677,0.000031586304,0.61987484,0.00015995106,0.0007567853,4.7404222e-7,0.0000047473604,0.000004002335,0.000010834683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972554,0.000051297473,0.0007737878,0.00023178464,0.0013904134,0.00029735913],"domain_scores_gemma":[0.9959214,0.00018831067,0.00085497246,0.00048545675,0.0023339377,0.00021592823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015310152,0.00013405496,0.00022080835,0.0007248781,0.0002595344,0.0004383457,0.0034911947,0.00003546491,0.0000297786],"category_scores_gemma":[0.00014965497,0.00011771866,0.00014032517,0.000854994,0.00031475874,0.0046723164,0.0009614854,0.00019878795,0.000018265937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075226276,0.00057141023,0.0016588405,0.000009540127,0.00009149204,0.000020399684,0.0013472632,0.0009979589,0.00326253,0.11947101,0.0021453598,0.8704167],"study_design_scores_gemma":[0.0017183382,0.0004315377,0.05116097,0.0009370505,0.00004796808,0.0029504758,0.00010554542,0.8677851,0.014441512,0.010831842,0.048832767,0.00075687707],"about_ca_topic_score_codex":0.0000101603355,"about_ca_topic_score_gemma":2.1486375e-7,"teacher_disagreement_score":0.8696598,"about_ca_system_score_codex":0.0001294167,"about_ca_system_score_gemma":0.00035734824,"threshold_uncertainty_score":0.6487566},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037973376,0.000019434714,0.99373573,0.00020543076,0.0015898142,0.00040300493,0.00002510631,0.000129542,0.00009461177],"genre_scores_gemma":[0.029580137,0.000021231088,0.9695107,0.00010070152,0.00021387222,0.00008010321,0.00011707068,0.000017967102,0.000358267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899185,0.000018132723,0.00017980617,0.00043554374,0.00015169627,0.00022300129],"domain_scores_gemma":[0.9992567,0.00007300564,0.00008506013,0.00035353468,0.00010489103,0.0001268246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001789593,0.00013524339,0.0001250631,0.000117939744,0.00022992116,0.00029438516,0.00027148623,0.00008648187,0.000017956134],"category_scores_gemma":[0.00010809088,0.00012476713,0.000035329525,0.00023847578,0.000018688374,0.00076588575,0.000196644,0.00013291556,0.0000073183687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002595147,0.000063739404,0.00020182905,0.00002123596,0.00002102769,0.0000021482183,0.0005385537,0.021949766,0.005255904,0.0036752864,0.0038060613,0.9644385],"study_design_scores_gemma":[0.00031956282,0.000081983555,0.00019554916,0.00002377579,0.0000065217023,0.000009952775,0.00001121069,0.9916376,0.005137717,0.00011275106,0.0022890898,0.0001742696],"about_ca_topic_score_codex":0.000017052744,"about_ca_topic_score_gemma":0.0000026913917,"teacher_disagreement_score":0.9696879,"about_ca_system_score_codex":0.0000158799,"about_ca_system_score_gemma":0.000024152276,"threshold_uncertainty_score":0.5087856},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25637257,0.000054618184,0.74136597,0.00066687807,0.00039766647,0.000104881554,6.978919e-7,0.00013226137,0.00090448355],"genre_scores_gemma":[0.73048717,0.0000074826607,0.26915497,0.00025128954,0.000090002664,0.0000034067075,5.6383317e-7,0.0000044096214,7.145033e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734837,0.00011262122,0.0003063611,0.00082316436,0.00072919513,0.0006803194],"domain_scores_gemma":[0.9986191,0.00019203314,0.000054280463,0.00078258035,0.00009006623,0.00026195843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002179623,0.0001869075,0.00021050045,0.0002965841,0.0003913267,0.0006580037,0.0030126756,0.000053460648,0.000011735958],"category_scores_gemma":[0.00012434865,0.00014975053,0.000041433705,0.0016753253,0.001228992,0.0018845004,0.0015455645,0.00025516792,0.000056895937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000508974,0.00005146077,0.00029565586,0.0000033979034,7.5133175e-7,0.000088379005,0.0003609066,0.0017794123,0.0011397307,0.9738805,0.0000020570765,0.022392638],"study_design_scores_gemma":[0.00074075366,0.00022705183,0.013506223,0.0002794607,0.0000024245417,0.00032460972,0.000019162218,0.631959,0.012717753,0.33965278,0.00006193501,0.0005088016],"about_ca_topic_score_codex":0.00010907078,"about_ca_topic_score_gemma":0.000007979629,"teacher_disagreement_score":0.63422775,"about_ca_system_score_codex":0.00015117989,"about_ca_system_score_gemma":0.00022765361,"threshold_uncertainty_score":0.63451445},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000959401,0.0010810277,0.9939951,0.0021679713,0.00066533627,0.0005517362,0.00006629193,0.00020216845,0.00031098528],"genre_scores_gemma":[0.23055032,0.00012909592,0.76607585,0.0010756114,0.0006039176,0.00017781861,0.000038384693,0.000042667394,0.0013063194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835974,0.000049570644,0.00028240727,0.0005222794,0.0003596239,0.00042640237],"domain_scores_gemma":[0.99824065,0.00042797416,0.0001284625,0.0009670269,0.00012890907,0.00010696166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021188134,0.00021617935,0.00020708727,0.00004713958,0.00078824564,0.00014425072,0.0012045458,0.00007289339,0.0000135785685],"category_scores_gemma":[0.000033193435,0.00013659256,0.000118514305,0.00028291545,0.00015597988,0.0002456612,0.0003069397,0.00016470093,0.000018476332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084704974,0.0002251242,0.00028549798,0.00006426311,0.00024247704,0.00020310291,0.002927962,0.005556668,0.00038958056,0.28875563,0.118826374,0.58243865],"study_design_scores_gemma":[0.0016636802,0.000220017,0.0067050694,0.00004051197,0.0000316814,0.0005221618,0.00016389706,0.707464,0.0008247109,0.09620748,0.18546286,0.0006939651],"about_ca_topic_score_codex":0.000118316726,"about_ca_topic_score_gemma":0.0000132898585,"teacher_disagreement_score":0.7019073,"about_ca_system_score_codex":0.000036290734,"about_ca_system_score_gemma":0.00009952589,"threshold_uncertainty_score":0.6062628},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5164453,0.010633068,0.45420435,0.009247213,0.005449508,0.0009968819,0.00016495024,0.000299811,0.0025589038],"genre_scores_gemma":[0.03517928,0.0028292625,0.9484095,0.0027727678,0.0037358068,0.000019649662,0.000017049879,0.000107514854,0.0069291717],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638355,0.0001795058,0.0010806313,0.00069582195,0.0009360369,0.0007244547],"domain_scores_gemma":[0.99742395,0.00012723554,0.0004920425,0.00082639384,0.0003103511,0.0008200455],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011031933,0.0004485161,0.00075893983,0.00043672058,0.0003273809,0.00077393866,0.0015422,0.00018180604,0.000399034],"category_scores_gemma":[0.000052916534,0.0003617124,0.00018594797,0.0008638393,0.00008440263,0.0020513665,0.00045687935,0.0004942092,0.000106526364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100727644,0.00025815246,0.00016151939,0.00001796835,0.00012090276,0.00026238142,0.00080498017,0.001447919,0.003423872,0.00024077554,0.044873502,0.9482873],"study_design_scores_gemma":[0.008751879,0.0032807558,0.013371366,0.000678158,0.00017595159,0.0036596837,0.0002597121,0.37903258,0.016583767,0.0020695901,0.5696835,0.0024530347],"about_ca_topic_score_codex":0.00016611954,"about_ca_topic_score_gemma":0.000005749015,"teacher_disagreement_score":0.9458343,"about_ca_system_score_codex":0.0001216125,"about_ca_system_score_gemma":0.00027951697,"threshold_uncertainty_score":0.9998835},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016639045,0.00043206676,0.97921765,0.0010302957,0.00009185014,0.00003485555,0.0000141105575,0.000008517578,0.002531584],"genre_scores_gemma":[0.8192956,0.00093384174,0.1795832,0.000110512025,0.00004265646,0.0000011409992,0.000002635825,0.000002911822,0.000027479911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900776,0.0000151013855,0.0003710557,0.00016310619,0.00035276375,0.00009018316],"domain_scores_gemma":[0.9992802,0.000087293934,0.00024195782,0.0001488811,0.00018070635,0.000060970608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002079177,0.00008450647,0.00022847716,0.00019295324,0.000032631327,0.00006476986,0.0005011401,0.000051644663,0.000091633745],"category_scores_gemma":[0.000027635373,0.00006400044,0.00006367354,0.00021969463,0.00020697058,0.00024860882,0.00026223948,0.00011768366,6.732675e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032759268,0.000087816974,0.000072882896,0.0000022599522,0.00011340396,0.000009733595,0.0000586418,0.008397128,0.00012173954,0.9547854,0.0005839223,0.035734292],"study_design_scores_gemma":[0.00043829595,0.00004962541,0.0011658502,0.00004366241,0.00008965085,0.00014416978,0.0000052952832,0.8928369,0.00016833513,0.10423469,0.0006923924,0.00013111232],"about_ca_topic_score_codex":0.0000011242067,"about_ca_topic_score_gemma":1.6838908e-7,"teacher_disagreement_score":0.8844398,"about_ca_system_score_codex":0.000011556618,"about_ca_system_score_gemma":0.000008981071,"threshold_uncertainty_score":0.2609862},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7169525,0.0001924461,0.2750594,0.0009153925,0.00015521905,0.00024332917,0.000007293307,0.000044041357,0.0064303726],"genre_scores_gemma":[0.99485666,0.000009357915,0.0049846196,0.00010496516,0.0000065291615,0.000009158576,0.00000292171,8.733026e-7,0.000024894774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922556,0.00014595517,0.00011592056,0.0001517944,0.00028539682,0.00007537674],"domain_scores_gemma":[0.99926776,0.0002515256,0.000034741406,0.0003927485,0.00004051329,0.000012729312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066433864,0.00004395068,0.000055912624,0.000033527045,0.000038182698,0.000014659024,0.00030474295,0.000014502276,0.0003010327],"category_scores_gemma":[0.00014856194,0.000021004595,0.00001379847,0.00017302574,0.00003533063,0.00007896897,0.00017835609,0.00004743967,0.000028570194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009053949,0.00049900974,0.0007567464,0.0000028868856,0.000004341205,0.0000026171863,0.0005143185,0.0062978836,0.0012974783,0.88253295,0.00803529,0.1000474],"study_design_scores_gemma":[0.00014613723,0.00004930098,0.0060405415,0.000016152546,8.8211993e-7,8.0212925e-7,0.00002775119,0.9902726,0.0014111289,0.0014920672,0.0005025256,0.0000401034],"about_ca_topic_score_codex":0.000036225792,"about_ca_topic_score_gemma":0.0000055522446,"teacher_disagreement_score":0.9839747,"about_ca_system_score_codex":0.000012862574,"about_ca_system_score_gemma":0.000007693207,"threshold_uncertainty_score":0.32960972},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023151172,0.0050819814,0.59965456,0.3552765,0.0009808387,0.0014680921,0.00007231807,0.0013510517,0.012963522],"genre_scores_gemma":[0.56353205,0.0002963795,0.41802993,0.00652147,0.0017661027,0.00008963335,0.000052139858,0.00006454965,0.0096477205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874693,0.00007543184,0.00018200869,0.0003696007,0.0002959099,0.00033014282],"domain_scores_gemma":[0.9979037,0.0003495194,0.00009158814,0.001486538,0.000063499756,0.00010516957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026458633,0.00014705089,0.000127636,0.000031278392,0.0004388003,0.00037411076,0.0020254368,0.000048428217,0.0001224786],"category_scores_gemma":[0.0001720028,0.000085625405,0.000041615982,0.00018683844,0.000070143375,0.00015969334,0.0008994905,0.00018377841,0.0007531443],"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":[0.000048009515,0.000046060126,0.00016567172,0.0000036654485,0.000015850062,0.000021724421,0.00016270175,0.00007078662,0.00017158504,0.0018276024,0.7806859,0.21678042],"study_design_scores_gemma":[0.0003831502,0.0000968999,0.0013624056,0.00003458518,0.0000040418386,0.000026519538,0.000008823417,0.003931982,0.0002663604,0.000070967304,0.99366254,0.00015173136],"about_ca_topic_score_codex":0.000074523574,"about_ca_topic_score_gemma":0.000009948907,"teacher_disagreement_score":0.5403809,"about_ca_system_score_codex":0.000027987895,"about_ca_system_score_gemma":0.00004385545,"threshold_uncertainty_score":0.9680398},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038861807,0.00013409693,0.9934101,0.00077354925,0.0007670857,0.0002667226,0.000057772362,0.00026631195,0.00043819787],"genre_scores_gemma":[0.21290249,0.000010105056,0.7846211,0.0011588574,0.0008367043,0.000079852514,0.00004907391,0.00003185424,0.00030994046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802095,0.00007895869,0.00027983112,0.0006454837,0.00035403122,0.0006207469],"domain_scores_gemma":[0.99807054,0.000534984,0.00012454801,0.0009754798,0.00010551353,0.00018895065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048101612,0.00024380485,0.00030710056,0.000099929035,0.0003119111,0.00022181125,0.0011970795,0.00015851932,0.000096339056],"category_scores_gemma":[0.00018703434,0.00020430831,0.00013498764,0.0003119298,0.000031028423,0.00055259734,0.000505962,0.00021051789,0.00008242335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025964737,0.0002376495,0.0003232043,0.000018422668,0.000047362337,0.000008777636,0.00014486718,0.0000070081824,0.0003253693,0.43685663,0.017952157,0.5440526],"study_design_scores_gemma":[0.0018769017,0.000412898,0.004142373,0.00009937202,0.000024733137,0.0000170763,0.000020357857,0.6563802,0.0019471298,0.07687513,0.25762373,0.00058015314],"about_ca_topic_score_codex":0.00004869412,"about_ca_topic_score_gemma":0.000016193504,"teacher_disagreement_score":0.65637314,"about_ca_system_score_codex":0.000046042125,"about_ca_system_score_gemma":0.00004695937,"threshold_uncertainty_score":0.83314514},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00751294,0.0021934886,0.98040044,0.008155109,0.0010287421,0.00039181337,0.000037566286,0.00005730396,0.00022256692],"genre_scores_gemma":[0.28902102,0.0010215638,0.70848435,0.00039248154,0.00081609254,0.000038205042,0.000015989166,0.00003561731,0.00017469873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978348,0.00008332203,0.0007248719,0.00027193717,0.0006337118,0.0004513774],"domain_scores_gemma":[0.9978342,0.00029196122,0.00072330347,0.0005232181,0.000426203,0.00020108384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010670079,0.0002138786,0.00031803094,0.00009543237,0.00054866774,0.0005264895,0.0021609562,0.000073080606,0.0000021514504],"category_scores_gemma":[0.00007744222,0.00012224576,0.00020359411,0.00038074132,0.0001869253,0.001435632,0.00023034059,0.0003410928,0.0000067120377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033781125,0.0005157024,0.00066650915,0.00013404625,0.00051247637,0.0008145456,0.0031475658,0.015789714,0.009202225,0.13570698,0.00788026,0.82529217],"study_design_scores_gemma":[0.008935285,0.0065917326,0.0060635693,0.0015531123,0.0001983326,0.0041781645,0.00097232295,0.1396494,0.03522214,0.6885039,0.10613709,0.0019948937],"about_ca_topic_score_codex":0.000087646324,"about_ca_topic_score_gemma":0.000027571255,"teacher_disagreement_score":0.82329726,"about_ca_system_score_codex":0.000109473665,"about_ca_system_score_gemma":0.00031211227,"threshold_uncertainty_score":0.5076951},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061719696,0.0000637216,0.9926643,0.004024165,0.00021764582,0.000079005724,0.0000023189937,0.00031429314,0.0020173963],"genre_scores_gemma":[0.0308682,0.000002333034,0.96174675,0.0068360236,0.00027924412,0.000008446194,0.00009457061,0.000007181941,0.00015725379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889094,0.000013263848,0.0003189225,0.00013920102,0.0004248788,0.00021281108],"domain_scores_gemma":[0.9994095,0.000014000291,0.0001868454,0.00026312578,0.000061659724,0.000064844695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014462593,0.00012192427,0.00009248759,0.00017081632,0.00046630576,0.00055728917,0.0006173943,0.000046151643,0.0000095834675],"category_scores_gemma":[0.000007692087,0.00010526349,0.000032577933,0.00037427054,0.000016378643,0.007184886,0.0006932776,0.000102405545,0.00009830816],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012603186,0.0000065115087,0.000014466135,0.000010266503,9.0394235e-7,0.000001763234,0.0005413729,0.000222994,0.00049118843,0.0006527344,0.026183115,0.9718734],"study_design_scores_gemma":[0.000801486,0.000024722121,0.0018290449,0.00009534577,0.00000449749,0.000038269467,0.000019853345,0.71575415,0.0027613894,0.0042458978,0.2740574,0.00036794977],"about_ca_topic_score_codex":0.00016906162,"about_ca_topic_score_gemma":0.0000017756086,"teacher_disagreement_score":0.97150546,"about_ca_system_score_codex":0.000051478706,"about_ca_system_score_gemma":0.00008882197,"threshold_uncertainty_score":0.53739524},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032714073,0.00032664253,0.965462,0.00014817838,0.00042073513,0.00033566428,0.00015386217,0.00008805867,0.00035075826],"genre_scores_gemma":[0.5628452,0.000015918555,0.43684185,0.0000908529,0.00009492972,0.000012988409,0.000059602058,0.000011059262,0.000027615719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988506,0.000027691585,0.00017967378,0.00054371834,0.00014048982,0.0002578721],"domain_scores_gemma":[0.9988682,0.00008362602,0.00004954983,0.00089168566,0.000024660923,0.00008227985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021685049,0.0001279658,0.00015342166,0.00009560353,0.00008248197,0.000066097855,0.0012080069,0.000055714016,0.000013045989],"category_scores_gemma":[0.000028492079,0.00010356986,0.000020144973,0.00014089319,0.00004565093,0.0003423904,0.00078960095,0.00008517755,0.000003400948],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060208193,0.00022629094,0.0008321816,0.000028406994,0.000032174306,0.000050605646,0.0023792824,0.000048900536,0.00033971635,0.043426633,0.003291598,0.949284],"study_design_scores_gemma":[0.0011535676,0.00015119697,0.049995113,0.000021444377,0.000010134396,0.000029596813,0.00007657802,0.9329101,0.0014663684,0.008599479,0.0052939225,0.00029254242],"about_ca_topic_score_codex":0.0002505233,"about_ca_topic_score_gemma":0.000044230594,"teacher_disagreement_score":0.9489915,"about_ca_system_score_codex":0.000012427441,"about_ca_system_score_gemma":0.000035047753,"threshold_uncertainty_score":0.42234564},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34223112,0.000068498586,0.65592986,0.00016790374,0.001143543,0.00006876726,0.000043348842,0.00013945629,0.00020749339],"genre_scores_gemma":[0.5567214,0.000014254551,0.4416719,0.0006404144,0.00082589866,0.000050804192,0.000032335578,0.000034499564,0.000008498381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626637,0.00008926579,0.0005222687,0.0009102781,0.0010237467,0.001188091],"domain_scores_gemma":[0.9973158,0.00049558823,0.00026445815,0.0012000898,0.00018623123,0.00053781236],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0016051279,0.00033068308,0.00023727724,0.00012307266,0.0014095709,0.00087746035,0.0019081504,0.00016839332,0.00002877911],"category_scores_gemma":[0.00021121763,0.0003281863,0.00023285775,0.00065532455,0.0014752942,0.0018186383,0.0022003418,0.00037430707,0.00024655898],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024395975,0.0001559983,0.0000045439574,0.000029671099,0.00002263862,0.00003080219,0.00030008357,0.00090419245,0.00025862214,0.9827981,0.0002011155,0.015269818],"study_design_scores_gemma":[0.00044047448,0.00030427033,0.000032833934,0.00015920094,0.000042103526,0.0002766438,0.000020042064,0.9854792,0.0051183132,0.0066598053,0.0010899965,0.00037711885],"about_ca_topic_score_codex":0.000049465398,"about_ca_topic_score_gemma":0.0000017214027,"teacher_disagreement_score":0.98457503,"about_ca_system_score_codex":0.000026258025,"about_ca_system_score_gemma":0.00032894177,"threshold_uncertainty_score":0.99991703},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03900392,0.00001375378,0.9594073,0.0011623636,0.00006442349,0.00005764152,0.0000060352913,0.00004378427,0.00024074333],"genre_scores_gemma":[0.9699268,0.0000027731044,0.029982112,0.0000196431,0.00004996,0.0000068185846,1.2481512e-7,0.0000031637508,0.000008605955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916285,0.000023310868,0.00017684686,0.00019429736,0.00029507015,0.0001476049],"domain_scores_gemma":[0.99937147,0.00023995066,0.000050508985,0.00024371158,0.000030742405,0.00006362419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025796602,0.00008951371,0.00017967007,0.000016834792,0.00022521116,0.000025377643,0.00041834352,0.00004215931,0.0000039654424],"category_scores_gemma":[0.00004097781,0.000055742534,0.00019977175,0.00032493146,0.00027413166,0.00016172527,0.00007000418,0.0001540164,0.0000012614576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042351844,0.00094553357,0.000010440413,0.00043615454,0.000051389197,9.287468e-8,0.0020319403,0.046802737,0.0177841,0.9265618,0.000011070334,0.0053605535],"study_design_scores_gemma":[0.00007746929,0.00006840606,0.00018420283,0.000052116324,0.000012353166,0.000001422924,0.000016340835,0.82113767,0.0033060624,0.17505053,0.00003343083,0.000059985636],"about_ca_topic_score_codex":0.0000033646902,"about_ca_topic_score_gemma":1.5448221e-7,"teacher_disagreement_score":0.93092287,"about_ca_system_score_codex":0.0000060192797,"about_ca_system_score_gemma":0.000008473445,"threshold_uncertainty_score":0.22731145},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007070872,0.0000073110355,0.9904364,0.00002970688,0.00027436746,0.00013095165,0.000010308775,0.00022977506,0.0018103068],"genre_scores_gemma":[0.9892278,0.0000061351893,0.010293096,0.00031596154,0.0000126725945,0.00001315231,0.0000035059268,0.0000044053186,0.00012329478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992712,0.000081326645,0.00024896878,0.000124203,0.00013386818,0.00014043163],"domain_scores_gemma":[0.99930453,0.00019461542,0.000106679145,0.0002600852,0.000060315364,0.00007379747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040952032,0.000114248694,0.000089539106,0.00019800519,0.00032874342,0.00014042552,0.00020280619,0.000062934065,0.000097259435],"category_scores_gemma":[0.000009219249,0.00010070204,0.000036966427,0.00016386334,0.00006380727,0.0030002748,0.000004729043,0.00012793341,0.000091266025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103803744,0.000060806615,0.000009848339,0.000025555995,0.000030005365,8.164807e-7,0.0132427225,0.06344897,0.00011860325,0.04326682,0.000039743434,0.8796523],"study_design_scores_gemma":[0.0006465371,0.00012860108,0.00028583358,0.00004065208,0.000013979572,0.000013323829,0.00067119184,0.9785454,0.0094917035,0.007348174,0.0025638763,0.00025071835],"about_ca_topic_score_codex":0.000011000357,"about_ca_topic_score_gemma":5.5444747e-7,"teacher_disagreement_score":0.98215693,"about_ca_system_score_codex":0.000016447852,"about_ca_system_score_gemma":0.000021922795,"threshold_uncertainty_score":0.410651},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02157056,0.0006678724,0.9756049,0.0017283526,0.00011361961,0.00008841992,0.000002866676,0.0000089861,0.00021441755],"genre_scores_gemma":[0.108118586,0.00012839067,0.8906492,0.00010693256,0.00014686158,0.0000102925,0.000005202806,0.0000070389433,0.0008275186],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989014,0.000028581328,0.0002204339,0.00012249239,0.00048760968,0.00023944133],"domain_scores_gemma":[0.9990636,0.000096488766,0.00006314413,0.00013677788,0.000462922,0.00017704534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010024637,0.000058436606,0.00009485834,0.00021026343,0.00023095365,0.00015903686,0.00037036996,0.000029377474,0.0000046252135],"category_scores_gemma":[0.000046362973,0.000042803254,0.000023526496,0.00015108018,0.0000351894,0.00037273837,0.00023039703,0.00017878712,0.000011377614],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056386525,0.00016996184,0.00021308464,0.000026758205,0.00004560865,0.00005271862,0.00054354605,0.00014347504,0.00038213117,0.022025451,0.012181521,0.96415937],"study_design_scores_gemma":[0.0013731708,0.0006157214,0.0019994243,0.0001444762,0.0000033504105,0.0003514572,0.0002751802,0.10365573,0.003365585,0.0048304405,0.88317144,0.00021402248],"about_ca_topic_score_codex":0.0000017414943,"about_ca_topic_score_gemma":0.0000042501065,"teacher_disagreement_score":0.9639453,"about_ca_system_score_codex":0.0001301076,"about_ca_system_score_gemma":0.0005113232,"threshold_uncertainty_score":0.17763321},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06690363,0.00033162136,0.93092644,0.0005861706,0.00053667097,0.00033472475,0.00018451858,0.00011398234,0.00008222083],"genre_scores_gemma":[0.5712059,0.0000019161482,0.42766538,0.00025206505,0.000115898336,0.000019489175,0.00066852383,0.000011010693,0.000059797374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983439,0.000028139675,0.00025113137,0.0005931872,0.00048680778,0.00029686722],"domain_scores_gemma":[0.9983157,0.00047610834,0.0001357419,0.000704014,0.00026758338,0.00010086264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028300742,0.0001579293,0.00016159577,0.00018459573,0.00027189052,0.00035677623,0.0015170813,0.000055742614,0.00007550536],"category_scores_gemma":[0.00011600363,0.00013821789,0.00004752417,0.00043515387,0.00004619528,0.0006421472,0.0010675093,0.00011536926,0.00008636568],"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":[0.000023283052,0.00027906237,0.0029429842,0.0001738871,0.000121181176,0.000011125543,0.00024764,0.52487975,0.00034530112,0.17512965,0.048165955,0.2476802],"study_design_scores_gemma":[0.00037089284,0.000021159496,0.051198523,0.000014432119,0.000004582414,0.000014848,0.0000134595575,0.92676085,0.000006996238,0.018843101,0.002579883,0.00017129416],"about_ca_topic_score_codex":0.000021335583,"about_ca_topic_score_gemma":0.0000011849266,"teacher_disagreement_score":0.50430226,"about_ca_system_score_codex":0.000035130026,"about_ca_system_score_gemma":0.00009918288,"threshold_uncertainty_score":0.5636362},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057875994,0.000112828515,0.98800683,0.0002924287,0.00012106687,0.000050980918,0.000003386849,0.00014594711,0.005478956],"genre_scores_gemma":[0.6564337,0.000011094653,0.34196997,0.00010495548,0.00016035637,0.000007871773,0.000008906214,0.000004468624,0.0012986779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999449,0.000006663011,0.00009744671,0.00020115543,0.00012147715,0.00012427113],"domain_scores_gemma":[0.99964803,0.000031002626,0.00003030569,0.00023273443,0.000022647608,0.000035246954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000061793595,0.000059784503,0.000057520785,0.000033604556,0.00012968405,0.00020418031,0.00024048537,0.000019877327,0.000008235358],"category_scores_gemma":[0.0000055235205,0.000048214984,0.000011590072,0.00013581186,0.000019059282,0.00061928167,0.0002188163,0.000044450157,0.000009472723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.812997e-7,0.00004709611,0.0006597214,0.00000951439,0.0000023967593,0.0000053083872,0.00011955167,0.000109088214,0.00033388266,0.93829614,0.021246161,0.03917036],"study_design_scores_gemma":[0.00035502866,0.000029723613,0.00868415,0.00003466156,0.0000035353617,0.000024230332,0.000030950763,0.8635562,0.0010114036,0.050512068,0.075460546,0.00029749935],"about_ca_topic_score_codex":0.00008813603,"about_ca_topic_score_gemma":0.000010212276,"teacher_disagreement_score":0.88778406,"about_ca_system_score_codex":0.000009637737,"about_ca_system_score_gemma":0.000008680031,"threshold_uncertainty_score":0.19689155},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033993854,0.0000034686623,0.9930692,0.00027775468,0.0010010764,0.00008261174,0.0000013105401,0.00016098726,0.0020042507],"genre_scores_gemma":[0.9042224,7.5415096e-7,0.0945636,0.00029586264,0.00030999316,0.000019742232,0.000008159601,0.0000047487565,0.0005747019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994668,0.000020701313,0.00009558308,0.00020670393,0.00008214301,0.00012808472],"domain_scores_gemma":[0.9995617,0.000061434315,0.000030282392,0.00026324726,0.000033380304,0.000049926985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015257276,0.000058614703,0.00006457181,0.000036515354,0.00009400894,0.00010727224,0.00030417857,0.000027844462,0.000026825619],"category_scores_gemma":[0.000036578782,0.000043999542,0.000039099024,0.000080653605,0.0000110696055,0.00032264975,0.00013317302,0.000033024204,0.000026406236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022794069,0.00009398369,0.00031230933,0.000015987405,0.000012424491,6.239883e-7,0.00027861816,0.000065390086,0.0049318825,0.5624705,0.05443536,0.3773601],"study_design_scores_gemma":[0.00027129843,0.00013618302,0.00035509994,0.0000067529572,0.0000018228533,0.000002218304,0.0000065216304,0.80486155,0.00915486,0.0032512473,0.18185334,0.000099129335],"about_ca_topic_score_codex":0.00007506505,"about_ca_topic_score_gemma":0.000016819216,"teacher_disagreement_score":0.90082306,"about_ca_system_score_codex":0.000012027973,"about_ca_system_score_gemma":0.000009131951,"threshold_uncertainty_score":0.17942493},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0117805265,0.001087425,0.9859559,0.000022405868,0.0003090411,0.000060296647,0.0000023283108,0.00042926107,0.00035282734],"genre_scores_gemma":[0.39326835,0.0003505923,0.60592145,0.00015552777,0.00008940001,0.000025688367,0.0000067566943,0.000021006439,0.0001612289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992273,0.000006869816,0.0001447175,0.00025619345,0.00013998276,0.00022497066],"domain_scores_gemma":[0.9994547,0.0001344733,0.000021084285,0.0003370076,0.000009335488,0.000043433003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006641456,0.000106911895,0.00009876796,0.00006602522,0.00003898307,0.000035045643,0.0004305736,0.000031228272,0.000033870092],"category_scores_gemma":[0.00008598427,0.00009947721,0.000023059485,0.0002165005,0.000006724846,0.00079168763,0.000061146304,0.0001383235,0.000054831115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018148178,0.000017474078,0.000271141,0.0000133089325,8.6449114e-7,0.000017709695,0.00006903071,0.4631168,0.000013198832,0.002229721,0.000026476026,0.5342225],"study_design_scores_gemma":[0.0005039088,0.00007618176,0.003033679,0.00037556892,0.0000011102344,0.000011790656,0.00000442379,0.9373483,0.0004709047,0.0038140134,0.053930797,0.000429306],"about_ca_topic_score_codex":0.0000050261883,"about_ca_topic_score_gemma":0.0000013468106,"teacher_disagreement_score":0.53379315,"about_ca_system_score_codex":0.000026965483,"about_ca_system_score_gemma":0.0000066071834,"threshold_uncertainty_score":0.4056563},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21113163,0.00048175076,0.7839696,0.0007859645,0.0015235706,0.00019334917,0.00007360035,0.00003242753,0.0018081077],"genre_scores_gemma":[0.9007943,0.0000366973,0.09878752,0.00015188658,0.00018419509,3.2150902e-7,0.0000010809935,0.000010057394,0.000033906286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99849415,0.000074381656,0.00047288853,0.00016276522,0.00058934826,0.00020648919],"domain_scores_gemma":[0.99842584,0.00013171528,0.0006161821,0.00051852694,0.00019871393,0.000109035915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031694904,0.0001506275,0.0002544974,0.000116981995,0.00009850535,0.000059106995,0.0015840265,0.00006346333,0.00012595039],"category_scores_gemma":[0.00006844503,0.00007916504,0.00015544923,0.00024402369,0.00007622793,0.0006202717,0.0002811434,0.00037076615,0.0000046678138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006105165,0.000915949,0.0015218712,0.00010212962,0.0008294666,0.00059275085,0.013671701,0.0004830263,0.036012087,0.46365094,0.028220952,0.4533886],"study_design_scores_gemma":[0.005514879,0.009398552,0.059365954,0.0014021745,0.0002503538,0.0015997192,0.0013904917,0.12239124,0.38490427,0.4004799,0.011480065,0.001822394],"about_ca_topic_score_codex":0.00002871731,"about_ca_topic_score_gemma":9.3864037e-7,"teacher_disagreement_score":0.6896627,"about_ca_system_score_codex":0.000020156996,"about_ca_system_score_gemma":0.000073890405,"threshold_uncertainty_score":0.32282564},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.291038,0.0035350034,0.7008393,0.0012550905,0.0010934199,0.0004571293,0.000009218993,0.000090024,0.0016828153],"genre_scores_gemma":[0.42258593,0.00023884857,0.575327,0.0013616486,0.0004133609,0.000013466544,0.0000056097037,0.000024216391,0.000029931742],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767846,0.000066306144,0.0006261578,0.00035586805,0.0008179328,0.00045528455],"domain_scores_gemma":[0.9982752,0.00006989576,0.0003503752,0.0008921089,0.00012288669,0.00028952962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005261036,0.00027060692,0.00031744197,0.00018759858,0.000371685,0.00021398207,0.003387294,0.000074137686,0.0000028902182],"category_scores_gemma":[0.000017923347,0.0001798309,0.0002017599,0.0003975285,0.00006300141,0.0011148129,0.001430006,0.00047917373,0.000012773679],"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":[0.0006811259,0.010880689,0.0023237467,0.000120296165,0.002487837,0.0039861333,0.18188365,0.07783013,0.33618876,0.060280684,0.13204646,0.19129048],"study_design_scores_gemma":[0.014758482,0.0056464123,0.0051227235,0.0012014372,0.00022414658,0.03634652,0.015193433,0.4029352,0.35161206,0.03232943,0.1281274,0.006502755],"about_ca_topic_score_codex":0.000029865598,"about_ca_topic_score_gemma":4.7739536e-7,"teacher_disagreement_score":0.32510507,"about_ca_system_score_codex":0.000111167516,"about_ca_system_score_gemma":0.00008256482,"threshold_uncertainty_score":0.7333291},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033720132,0.00008197719,0.9358148,0.0005215125,0.00006730043,0.00034293567,0.000020304415,0.00020085758,0.029230198],"genre_scores_gemma":[0.81986827,0.000029561656,0.17988713,0.00013486383,0.000022665203,0.000009477844,0.000009131013,0.000008524303,0.000030358184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873066,0.000009416095,0.00028385117,0.00027887843,0.00044983855,0.00024738014],"domain_scores_gemma":[0.9987208,0.00019887464,0.00014899304,0.0008118657,0.000032201264,0.000087221175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020982312,0.00016466425,0.00024276857,0.000114632065,0.00011248778,0.000086449814,0.00088031957,0.00005725083,0.000022769971],"category_scores_gemma":[0.000020550331,0.00012332661,0.00007292293,0.00031823097,0.00006542337,0.00018709083,0.00017683467,0.0001188206,0.00003061034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008738044,0.00022677776,0.0000049842515,0.000080692495,0.000014525974,0.0000029750147,0.0012527963,0.00008884737,0.0018249819,0.9697892,0.0004998108,0.026205692],"study_design_scores_gemma":[0.0010076178,0.0005809488,0.0018896767,0.0004075129,0.000038975813,0.000013020035,0.000384419,0.16455992,0.036159236,0.7927166,0.0015447498,0.0006972972],"about_ca_topic_score_codex":0.0000061396063,"about_ca_topic_score_gemma":0.0000021777196,"teacher_disagreement_score":0.78614813,"about_ca_system_score_codex":0.000010236266,"about_ca_system_score_gemma":0.000020441492,"threshold_uncertainty_score":0.5029113},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07549964,0.00044123194,0.9213738,0.0003280406,0.00023232054,0.00006994044,0.0000035688633,0.00013174093,0.0019197107],"genre_scores_gemma":[0.9626423,0.000015244719,0.037051618,0.000065432985,0.000041695333,7.022889e-7,0.000008362369,0.000005963895,0.00016869859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990502,0.0000799035,0.00025477694,0.00021830465,0.00022620184,0.00017059552],"domain_scores_gemma":[0.9993237,0.000056120698,0.00017335388,0.0003496883,0.000048676724,0.000048454578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028779235,0.00010293286,0.00020160596,0.00009956268,0.00009007094,0.000040281335,0.00059063284,0.000035103538,0.000024173449],"category_scores_gemma":[0.00006904569,0.000088329834,0.000056459518,0.00021828765,0.00001942016,0.00029623354,0.00031194466,0.00016959712,0.000004779636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000361148,0.00014760121,0.0223073,0.000098794226,0.000021441387,0.000029451849,0.0021731497,0.027893921,0.020911243,0.007085649,0.00046909836,0.9188262],"study_design_scores_gemma":[0.0004402649,0.00032407782,0.021916,0.00013106334,0.000006084716,0.000017406228,0.00003018395,0.9600604,0.0049012117,0.00077782205,0.011189399,0.00020608492],"about_ca_topic_score_codex":0.0001433479,"about_ca_topic_score_gemma":0.0000060459315,"teacher_disagreement_score":0.93216646,"about_ca_system_score_codex":0.000008426187,"about_ca_system_score_gemma":0.00001472367,"threshold_uncertainty_score":0.3601986},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044116557,0.000006240537,0.9552548,0.000063371575,0.00012277784,0.000101215766,0.0000017797602,0.0000666949,0.00026658326],"genre_scores_gemma":[0.27223346,0.0000033984434,0.72759664,0.00008580953,0.000035579513,5.7276674e-7,0.0000055439496,0.0000030536132,0.000035982244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995195,0.000006124965,0.00013314982,0.00012012214,0.00009200513,0.00012908549],"domain_scores_gemma":[0.9996523,0.000034638724,0.00006408886,0.00014878182,0.000052931926,0.000047223835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000249886,0.000060995942,0.00006408539,0.00005664948,0.00023525223,0.0002680087,0.00017928306,0.000052197243,0.000003158599],"category_scores_gemma":[0.00004274266,0.000053192773,0.000017838385,0.00006828226,0.000012234486,0.0015680575,0.00020407997,0.00012965004,0.000001108575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013764753,0.000055612432,0.0012597903,0.00015494453,0.00003391379,0.0000024302233,0.012579303,0.0948221,0.16107403,0.18599364,0.0005376885,0.5433489],"study_design_scores_gemma":[0.00018548052,0.000014057782,0.0000222168,0.000005166991,0.0000020562657,0.0000060102893,0.0000243736,0.993981,0.0010603695,0.00212043,0.0024977385,0.000081122205],"about_ca_topic_score_codex":0.000012923443,"about_ca_topic_score_gemma":0.0000037743346,"teacher_disagreement_score":0.8991589,"about_ca_system_score_codex":0.000011177263,"about_ca_system_score_gemma":0.00004316973,"threshold_uncertainty_score":0.25844142},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011184264,0.000051892166,0.987286,0.00059065095,0.000049727732,0.00007707406,6.930813e-7,0.00006690408,0.000692844],"genre_scores_gemma":[0.27568212,0.00006629832,0.72388554,0.00017452429,0.000073613905,0.000009410222,0.0000033610172,0.00000730016,0.0000978145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913913,0.000044814475,0.00020788128,0.0002825612,0.000135576,0.00019002393],"domain_scores_gemma":[0.99957025,0.00010431423,0.00003159567,0.0001987414,0.000017892,0.00007723124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001943555,0.00010110956,0.00014382224,0.00007862163,0.000082694845,0.00016760382,0.00023333015,0.000043155083,0.000047548616],"category_scores_gemma":[0.0000027517638,0.00007789544,0.000022640495,0.00014207026,0.000017799312,0.00044083115,0.00034536436,0.00012984271,0.000045018656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028050956,0.00029596954,0.000046998364,0.00008594759,0.000005474505,0.000018489394,0.002371301,0.012343555,0.000020315401,0.11551072,0.00042732686,0.8688711],"study_design_scores_gemma":[0.00016662198,0.000026511323,0.000016434817,0.00009790055,8.933614e-7,0.000017364542,0.000008984406,0.9583546,0.000026912829,0.04082777,0.00035781332,0.00009818046],"about_ca_topic_score_codex":0.000004776177,"about_ca_topic_score_gemma":2.579556e-7,"teacher_disagreement_score":0.94601107,"about_ca_system_score_codex":0.000012367551,"about_ca_system_score_gemma":0.0000030272413,"threshold_uncertainty_score":0.31764838},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33068168,0.000005684448,0.6633066,0.003164125,0.00051592477,0.00018916123,0.0000049602504,0.00021232896,0.0019195427],"genre_scores_gemma":[0.63364,6.7250016e-7,0.36510694,0.0006778819,0.00026855146,0.000019985675,0.000004936425,0.0000149037605,0.0002661679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888456,0.000018375933,0.00022228192,0.0003320151,0.0002556292,0.00028713915],"domain_scores_gemma":[0.9985893,0.00027769138,0.00004281218,0.00083989877,0.000041853094,0.00020849588],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002565173,0.0001331128,0.00017745419,0.00006265753,0.00010696059,0.0002713615,0.00078438834,0.00006703853,0.00019500639],"category_scores_gemma":[0.00026932455,0.00009729407,0.000048221897,0.00014935779,0.000031920274,0.00040812002,0.00058715034,0.00021426429,0.0013574843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011159464,0.00056743086,0.00041006083,0.00015511518,0.000024005942,0.00007139023,0.0038828799,0.000011123512,0.23736651,0.39999896,0.0049028844,0.3525985],"study_design_scores_gemma":[0.0012327633,0.00046362355,0.026132496,0.0008614061,0.0000423244,0.00044833118,0.000051604955,0.4297129,0.21979304,0.24935512,0.06947656,0.0024298336],"about_ca_topic_score_codex":0.000009715415,"about_ca_topic_score_gemma":0.0000022516904,"teacher_disagreement_score":0.42970178,"about_ca_system_score_codex":0.0000066579305,"about_ca_system_score_gemma":0.000016205144,"threshold_uncertainty_score":0.99942005},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057346295,0.00057363324,0.9913851,0.00030133623,0.0013536727,0.000109422705,0.000042013773,0.00007178519,0.00042838833],"genre_scores_gemma":[0.27846706,0.00016586922,0.71824056,0.0007390261,0.0021662568,0.0000025142128,0.000025093206,0.00005500812,0.00013860273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966784,0.00008810817,0.0010762924,0.00038929173,0.0010919188,0.0006760012],"domain_scores_gemma":[0.99749273,0.00021766326,0.0008198958,0.00067653373,0.00033192793,0.0004612364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017243609,0.00031692872,0.0004982648,0.000357647,0.00024984305,0.00036277922,0.0018316074,0.0000847529,0.00004553381],"category_scores_gemma":[0.00004680539,0.00024376022,0.0003127223,0.00040482706,0.000061754035,0.0020416682,0.000610411,0.0006056072,0.0000352059],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010175697,0.000093592076,0.00013221717,0.000010217657,0.00006251476,0.0009017245,0.00038908227,0.000095132484,0.0004915562,0.00018018148,0.0025326188,0.995101],"study_design_scores_gemma":[0.0074461377,0.0028604367,0.021558726,0.0008616904,0.0001949926,0.010405956,0.00175908,0.7493245,0.02862445,0.048816927,0.12515871,0.002988388],"about_ca_topic_score_codex":0.000098244134,"about_ca_topic_score_gemma":0.0000054329294,"teacher_disagreement_score":0.9921126,"about_ca_system_score_codex":0.00011389213,"about_ca_system_score_gemma":0.00011927479,"threshold_uncertainty_score":0.99402535},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051919032,0.000014114808,0.9432586,0.0003121002,0.00058680575,0.00014624027,5.221302e-7,0.0002562588,0.0035063322],"genre_scores_gemma":[0.74531674,0.0000024693327,0.2542702,0.00029549352,0.00009340104,0.000008196008,3.5458157e-7,0.0000042132506,0.0000089681735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978816,0.0000406017,0.00021568473,0.000664612,0.0006218188,0.00057567854],"domain_scores_gemma":[0.99842864,0.00013175597,0.000051408708,0.0009299122,0.00016371899,0.00029454657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050602836,0.0001530554,0.00015241525,0.00012278989,0.00041340612,0.0009453848,0.002849313,0.00003566325,0.00013994038],"category_scores_gemma":[0.00004531116,0.00011885725,0.00004122238,0.00078841153,0.0009150196,0.0021638335,0.002283728,0.00016392197,0.00046370795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.686862e-7,0.000018199125,0.0000066257535,0.0000022618308,0.000001058831,0.0000022023567,0.00010662789,0.0001190833,0.0065419325,0.849957,0.00005885007,0.14318551],"study_design_scores_gemma":[0.00014845746,0.000086691616,0.0013224027,0.000030329038,9.843642e-7,0.000014109972,0.0000038771273,0.8407864,0.033736728,0.123529404,0.00012080053,0.00021982723],"about_ca_topic_score_codex":0.000012039507,"about_ca_topic_score_gemma":9.671892e-8,"teacher_disagreement_score":0.8406673,"about_ca_system_score_codex":0.00004471294,"about_ca_system_score_gemma":0.00006885116,"threshold_uncertainty_score":0.9116367},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021735974,0.000009420571,0.97148544,0.00014594814,0.000047439928,0.00014545242,0.0000022455783,0.00008561227,0.006342485],"genre_scores_gemma":[0.18388477,0.0000034690477,0.81583303,0.00020700747,0.000015894791,0.000031984113,0.0000035030325,0.000008198354,0.000012150275],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992553,0.0000059237505,0.00023260343,0.00019145744,0.00017850068,0.00013622378],"domain_scores_gemma":[0.99884385,0.000042370015,0.00016415912,0.0008807493,0.000021378857,0.000047476915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012522152,0.00009001015,0.00013173002,0.000057443634,0.000053277978,0.000016383301,0.0007115908,0.00003365113,0.000021115748],"category_scores_gemma":[0.0000056711847,0.000073436386,0.000034619272,0.00013580639,0.000038699778,0.00015229508,0.0002701994,0.00005630163,0.000035228022],"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":[0.0000013772913,0.00010488572,0.0000037935217,0.00003569002,0.000008807426,0.0000010961454,0.0018985266,0.000003538693,0.5748741,0.41414353,0.0036046088,0.005320043],"study_design_scores_gemma":[0.0004958424,0.000034557957,0.0009432499,0.000114084716,0.000024319352,0.0000162522,0.00019078895,0.008929045,0.84837586,0.13833275,0.0021201684,0.00042307298],"about_ca_topic_score_codex":0.0000049525265,"about_ca_topic_score_gemma":8.0134015e-8,"teacher_disagreement_score":0.27581075,"about_ca_system_score_codex":0.000007883392,"about_ca_system_score_gemma":0.0000074766062,"threshold_uncertainty_score":0.29946488},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044356165,0.000008866194,0.9930083,0.00017310037,0.00086149725,0.00009739959,0.000100444995,0.0000786808,0.0012360583],"genre_scores_gemma":[0.040597647,0.0000022444956,0.95912737,0.00010363466,0.00007046385,0.000001400029,0.000080578495,0.0000050552712,0.00001157905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988597,0.000095330266,0.00020334517,0.0004224306,0.0002970925,0.00012210033],"domain_scores_gemma":[0.9980459,0.00023891844,0.00014581425,0.0014160959,0.00008871012,0.00006452077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035076137,0.00010245636,0.00014394062,0.00011938139,0.00014109659,0.00004470722,0.0009902421,0.000073895106,0.000069101145],"category_scores_gemma":[0.000054016342,0.000078250945,0.000028337528,0.00018944593,0.00006531497,0.00070209015,0.000592363,0.00019666858,0.0000039427787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001401949,0.0006380313,0.0017235271,0.00005418262,0.00003986715,0.000016988975,0.00013837821,0.0066973446,0.2540056,0.16624217,0.0073209307,0.56298274],"study_design_scores_gemma":[0.00023906291,0.000047581914,0.0006473851,0.000052759744,0.0000061494407,0.000023491662,0.000015619862,0.9775726,0.015648128,0.0025764243,0.003076064,0.000094740506],"about_ca_topic_score_codex":0.00010224901,"about_ca_topic_score_gemma":0.0000054520924,"teacher_disagreement_score":0.97087526,"about_ca_system_score_codex":0.000009108737,"about_ca_system_score_gemma":0.00007904694,"threshold_uncertainty_score":0.31909811},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5635848,0.00012213804,0.43586817,0.0002445228,0.0000767498,0.000062548024,0.000024517663,0.000002310524,0.000014251274],"genre_scores_gemma":[0.8304872,0.00005869737,0.16940048,0.000022521668,0.000023213375,0.0000011459927,0.0000022228894,0.0000020849473,0.0000024683914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99913013,0.000028922417,0.00034120135,0.000120461424,0.00030169927,0.00007756789],"domain_scores_gemma":[0.9988163,0.00017790125,0.00028648254,0.000083255334,0.0005890174,0.0000470473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032829825,0.00006483689,0.0001407694,0.000077340665,0.000026366759,0.0001538884,0.0002238351,0.000022087237,0.0000077113145],"category_scores_gemma":[0.00011081567,0.00004865008,0.000011031636,0.00006299976,0.00006483825,0.000619771,0.00013068745,0.000110247034,1.9392178e-7],"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":[0.00019855927,0.0006402389,0.6335405,0.0002945705,0.00022414315,0.00021046023,0.0031324767,0.0013638552,0.0057816077,0.084442,0.00030579974,0.26986575],"study_design_scores_gemma":[0.001136084,0.00040343593,0.75481963,0.00039390055,0.000009105242,0.00014657834,0.00007492447,0.16701335,0.00009792532,0.075461596,0.00028919682,0.0001542831],"about_ca_topic_score_codex":0.00030911062,"about_ca_topic_score_gemma":0.000018485522,"teacher_disagreement_score":0.26971146,"about_ca_system_score_codex":0.000019708617,"about_ca_system_score_gemma":0.0000689109,"threshold_uncertainty_score":0.19838926},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4877282,0.0008274399,0.51007044,0.00019576077,0.0008624661,0.000228811,0.00001811646,0.000036832247,0.00003188791],"genre_scores_gemma":[0.63409436,0.000013922135,0.36540318,0.00014132398,0.00030997721,0.0000042559295,0.000017083028,0.00001117765,0.0000047322214],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99797785,0.000110382854,0.0007407944,0.000319912,0.0005577921,0.0002932422],"domain_scores_gemma":[0.9981913,0.00009728653,0.00061381736,0.00059000385,0.00025815528,0.00024942026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005934482,0.0002289705,0.0003490046,0.00028327818,0.00018096974,0.0001596583,0.0014978262,0.000095602045,0.000009229614],"category_scores_gemma":[0.000047180118,0.00020396705,0.00018403113,0.00025548454,0.00008171205,0.0024378262,0.00022923606,0.00023683644,0.0000015352512],"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":[0.00013297627,0.000499768,0.00007853331,0.0000072404614,0.00003895554,0.000018126666,0.0060401927,0.00018644324,0.9254264,0.0019879767,0.0007378199,0.06484553],"study_design_scores_gemma":[0.0014198808,0.004399514,0.00051291,0.00009515913,0.000010240523,0.00026831232,0.002258458,0.11903226,0.8681633,0.0034111037,0.00017800255,0.00025089906],"about_ca_topic_score_codex":0.00002264675,"about_ca_topic_score_gemma":2.8474398e-7,"teacher_disagreement_score":0.14636612,"about_ca_system_score_codex":0.00017770166,"about_ca_system_score_gemma":0.000111695925,"threshold_uncertainty_score":0.8317535},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016424589,0.000010247376,0.97980917,0.0006146884,0.0006807879,0.00016261247,0.0000022124013,0.000057036927,0.0022386669],"genre_scores_gemma":[0.73537713,8.111083e-7,0.26428056,0.00025940867,0.000071841416,0.0000016960826,1.3935501e-7,0.0000046153887,0.000003800113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784213,0.00014884533,0.00026883648,0.0005499992,0.0007630324,0.00042715186],"domain_scores_gemma":[0.9982161,0.00019236829,0.000092951166,0.0010972666,0.00025819457,0.00014311392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013364374,0.00015816318,0.00020321074,0.0001035016,0.0004503262,0.0001851684,0.0031741783,0.000048273323,0.000031318676],"category_scores_gemma":[0.000086035616,0.000092521754,0.000078043784,0.0014837135,0.0020802887,0.0006510273,0.0013102088,0.00018681129,0.000010758523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003762995,0.00004328721,0.000015270123,0.0000048207885,0.000002720757,0.0000010970632,0.00037642106,0.00058924576,0.0019869583,0.96126616,0.000009188893,0.035701096],"study_design_scores_gemma":[0.00017706108,0.000093660376,0.00059847604,0.000043801014,0.000004857424,0.000037112797,0.0000032586502,0.8445209,0.009965989,0.14427659,0.00014844153,0.00012983874],"about_ca_topic_score_codex":0.000019522884,"about_ca_topic_score_gemma":6.4510266e-7,"teacher_disagreement_score":0.8439317,"about_ca_system_score_codex":0.00003800793,"about_ca_system_score_gemma":0.00016454548,"threshold_uncertainty_score":0.766491},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000048205948,0.45146164,0.5466365,0.000006681171,0.001298145,0.00032173452,0.000046962734,0.00018231105,0.00004117692],"genre_scores_gemma":[0.023174874,0.6395063,0.3316446,0.00007348825,0.0019957707,0.00004975908,0.003122958,0.0003112643,0.00012104912],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99323076,0.0024060162,0.0016471834,0.001035395,0.0009291387,0.00075152534],"domain_scores_gemma":[0.99251133,0.0021449958,0.0018220615,0.0029737598,0.00030701043,0.0002408274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036192224,0.0007610736,0.0025498047,0.00048517445,0.0002727708,0.00024343016,0.004456833,0.000544225,0.000021913827],"category_scores_gemma":[0.00036911832,0.00064613356,0.00049227045,0.0014223116,0.000092565184,0.00047783947,0.0023915218,0.000770253,0.00007566053],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.8850145e-7,0.00019804538,0.0021427483,0.0022727645,0.00006148833,0.000002596952,0.000107091146,0.00014121298,4.4457417e-7,0.00017124566,0.00025583577,0.99464595],"study_design_scores_gemma":[0.00051161397,0.00016291732,0.0034357018,0.007827299,0.0002451342,0.000015626336,0.000008615757,0.15478076,0.000026462983,0.00013295563,0.83140093,0.0014519867],"about_ca_topic_score_codex":0.00020384524,"about_ca_topic_score_gemma":0.0000072525204,"teacher_disagreement_score":0.9931939,"about_ca_system_score_codex":0.00014379938,"about_ca_system_score_gemma":0.00048745752,"threshold_uncertainty_score":0.999599},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047338256,0.000038734597,0.99483776,0.00005057878,0.00014316027,0.00006765805,0.000012907518,0.000010896496,0.000104462575],"genre_scores_gemma":[0.5022528,0.000016481457,0.49762112,0.000022892063,0.0000710808,7.626977e-7,0.000007906346,0.00000438612,0.000002554298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988304,0.00008194537,0.0004127027,0.00007387049,0.00040601025,0.0001951145],"domain_scores_gemma":[0.99888724,0.000041012387,0.0006107027,0.00016701123,0.00020746786,0.000086564316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040336518,0.00012707518,0.0002398685,0.0000908058,0.000095094656,0.00007966417,0.0003525864,0.00003089826,0.000010648611],"category_scores_gemma":[0.000008884196,0.00009911108,0.00008953202,0.00019633744,0.000043357355,0.002206516,0.00005475944,0.0002069822,7.413123e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000420062,0.00024391415,0.000799458,0.000087404405,0.000052083844,0.0000017730531,0.006811629,0.023919119,0.0023290133,0.013450266,0.00002700689,0.95223635],"study_design_scores_gemma":[0.00056863134,0.00033217343,0.00037937888,0.00006790477,0.000022078691,0.000021282049,0.0010196018,0.9796461,0.017025178,0.0006048211,0.00018062883,0.00013224274],"about_ca_topic_score_codex":0.000024767309,"about_ca_topic_score_gemma":4.0263558e-7,"teacher_disagreement_score":0.955727,"about_ca_system_score_codex":0.00002915748,"about_ca_system_score_gemma":0.00017808523,"threshold_uncertainty_score":0.40416327},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000495653,0.00010013793,0.9872516,0.0023821762,0.00021585157,0.0000851547,0.000002376939,0.00029617324,0.009170921],"genre_scores_gemma":[0.21413921,0.00005337627,0.7793395,0.0041816593,0.00013782165,0.000006720833,0.000008829855,0.0000049857904,0.002127903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989795,0.000023335115,0.00014276562,0.00033417862,0.00028405094,0.00023617053],"domain_scores_gemma":[0.9991579,0.000018983312,0.00003487471,0.00063635356,0.000032541477,0.00011933219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014658831,0.00010503734,0.00009280207,0.000039979106,0.00009543359,0.00013256325,0.0008036023,0.000034051132,0.00005675998],"category_scores_gemma":[0.0000068255094,0.000078599594,0.000037251957,0.00018021894,0.0000146655075,0.00063399185,0.00017986134,0.000063325715,0.00016186351],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012791029,0.00008491164,0.000018851584,0.0000013556233,0.0000029912624,0.00004598604,0.00010255834,0.00005890852,0.0016369709,0.095940985,0.014823939,0.88728124],"study_design_scores_gemma":[0.000548957,0.00039871605,0.002743831,0.00003916225,0.000004119925,0.000073276635,0.00002487411,0.8283575,0.013833299,0.044746295,0.10868233,0.0005476564],"about_ca_topic_score_codex":0.000024797379,"about_ca_topic_score_gemma":5.0985426e-7,"teacher_disagreement_score":0.8867336,"about_ca_system_score_codex":0.000030536256,"about_ca_system_score_gemma":0.000029628449,"threshold_uncertainty_score":0.32051983},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002520998,0.00023096276,0.995105,0.00018062578,0.00031890508,0.000141038,0.00014621478,0.0002308561,0.0011253579],"genre_scores_gemma":[0.68768555,0.000014609157,0.3119097,0.000053154767,0.00007475713,0.000009530287,0.00003645047,0.00002258484,0.0001936721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980427,0.00006338453,0.0004369275,0.0006671682,0.0004751654,0.00031466407],"domain_scores_gemma":[0.99806273,0.000071078684,0.00021554493,0.0013807489,0.00019026028,0.000079663805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002363976,0.00022543575,0.0002610997,0.00018662061,0.00040297615,0.00034730288,0.0017262076,0.00008204225,0.000033793563],"category_scores_gemma":[0.0000045723664,0.00019677568,0.00006313147,0.00048099886,0.0001505227,0.0031911433,0.000043743392,0.00028129554,0.000033827935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007043613,0.0014057676,0.0000197153,0.00040109383,0.000025079882,0.000059704584,0.00039681996,0.0038630269,0.2481484,0.00016483385,0.0038024047,0.7416427],"study_design_scores_gemma":[0.0007431384,0.00005473877,0.00019912007,0.0003986608,0.000029823306,0.000033545664,0.00004449459,0.7443849,0.25204274,0.00067463267,0.0010383506,0.00035590172],"about_ca_topic_score_codex":0.0001655775,"about_ca_topic_score_gemma":0.000012322199,"teacher_disagreement_score":0.7412868,"about_ca_system_score_codex":0.000029313363,"about_ca_system_score_gemma":0.000110339504,"threshold_uncertainty_score":0.80242795},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041416497,0.00024546852,0.9946473,0.00016690939,0.00020876185,0.00027461082,0.0000244656,0.00019689724,0.000093909315],"genre_scores_gemma":[0.8291619,0.000005692985,0.17041095,0.00019347864,0.0000586962,0.000046631554,0.0000015939322,0.000020800853,0.000100268444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835676,0.000025700314,0.00027881408,0.0006071028,0.00034654222,0.00038509973],"domain_scores_gemma":[0.9992383,0.000117945485,0.00011502093,0.00022967748,0.000138304,0.00016073257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023951239,0.00023816865,0.0002149803,0.00017499056,0.001005958,0.00040532617,0.0003561498,0.000099060955,0.000004458989],"category_scores_gemma":[0.0000024968065,0.00021519486,0.00008564706,0.000344589,0.00011383947,0.00046337748,0.0000089284285,0.0002421957,0.000007538505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009097062,0.0002979949,5.169418e-7,0.00006637411,0.000027377646,0.00001231141,0.00175655,0.32691386,0.0035364882,0.0005391014,0.000035252666,0.6667232],"study_design_scores_gemma":[0.0011137433,0.0003438825,0.000005856682,0.00026160112,0.00002625668,0.00006756638,0.00012682483,0.97703075,0.01877024,0.0014643904,0.00048009056,0.00030879438],"about_ca_topic_score_codex":0.000023112236,"about_ca_topic_score_gemma":0.0000022973254,"teacher_disagreement_score":0.82502025,"about_ca_system_score_codex":0.00010298549,"about_ca_system_score_gemma":0.0001606323,"threshold_uncertainty_score":0.87753916},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008775956,0.000019061856,0.9963005,0.00005334553,0.0011922739,0.00046378095,0.00015469463,0.00020282579,0.0007359074],"genre_scores_gemma":[0.9674857,0.000010735567,0.031391036,0.0007469798,0.000019693161,0.0001433254,0.000017546958,0.000012069206,0.00017289016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986845,0.0001234445,0.0004138448,0.0002074974,0.0003161128,0.0002545814],"domain_scores_gemma":[0.9987551,0.00028775766,0.00015745503,0.000554927,0.00014321749,0.00010156975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005762391,0.00018767537,0.00017038701,0.00018532039,0.00048600422,0.00027941438,0.00043520625,0.00008967674,0.0000979134],"category_scores_gemma":[0.000010756524,0.0001617246,0.00012964939,0.00009997924,0.00003650249,0.0033749407,0.000005724444,0.00020618508,0.00019198588],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053331354,0.00012833657,6.588046e-7,0.0000543214,0.000034287837,9.4225635e-7,0.00216199,0.008488762,0.00041478866,0.025533121,0.00029658424,0.96283287],"study_design_scores_gemma":[0.008218647,0.00049402704,0.000115981195,0.0004499265,0.00007568449,0.00009738469,0.0027781792,0.6644448,0.22012393,0.062200263,0.03947076,0.0015304204],"about_ca_topic_score_codex":0.000019312904,"about_ca_topic_score_gemma":0.0000020330988,"teacher_disagreement_score":0.9666081,"about_ca_system_score_codex":0.000058704256,"about_ca_system_score_gemma":0.000046440877,"threshold_uncertainty_score":0.6594938},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051815016,0.000592053,0.994603,0.00013504442,0.0020017612,0.00048314175,0.000009708015,0.00017718441,0.0014799893],"genre_scores_gemma":[0.035084616,0.00003540135,0.9611168,0.0014782114,0.0015147801,0.00001613998,0.000016848386,0.00006692772,0.00067030964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99558866,0.000053447915,0.00063520775,0.0018385268,0.0011047992,0.0007793759],"domain_scores_gemma":[0.99675846,0.00024557236,0.00036527775,0.002087917,0.00026344534,0.00027932084],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000691133,0.00064924365,0.00070671155,0.00074448885,0.00056447485,0.0012192971,0.004191456,0.00037632647,0.00012340685],"category_scores_gemma":[0.00004344325,0.0005388106,0.00016691719,0.0004767185,0.00053776556,0.0012247949,0.002484961,0.00081763987,0.00010283999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010837055,0.00007239312,0.000031340176,0.000061094106,0.000030379153,0.00023719661,0.0007383925,0.038674485,0.0070999335,0.030129319,0.00044394776,0.9224707],"study_design_scores_gemma":[0.0007184934,0.000106257714,0.000027329019,0.00037756737,0.000009188688,0.00008787314,6.481479e-8,0.9303397,0.002209442,0.061383367,0.003929821,0.00081088394],"about_ca_topic_score_codex":0.000102630154,"about_ca_topic_score_gemma":0.000023204755,"teacher_disagreement_score":0.9216598,"about_ca_system_score_codex":0.00027104572,"about_ca_system_score_gemma":0.0004706586,"threshold_uncertainty_score":0.99981755},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040617038,0.00010785738,0.9545274,0.0007071448,0.0017960784,0.00067067635,0.0004664855,0.0001501319,0.0009571853],"genre_scores_gemma":[0.84654385,0.000004053579,0.15213042,0.00015425643,0.0005445436,0.000034834648,0.00014426094,0.000017592945,0.00042618558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828464,0.00009652114,0.000493121,0.00027630007,0.0005761903,0.0002732062],"domain_scores_gemma":[0.9942311,0.0030169555,0.00066725374,0.00019247952,0.0018451163,0.00004707024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009835619,0.00012590896,0.00019480758,0.000076912685,0.00094086805,0.0000880641,0.0006080313,0.00007112412,5.762763e-7],"category_scores_gemma":[0.0072204345,0.00011573298,0.00014881353,0.00022658404,0.000029502,0.00010224795,0.0002062924,0.00013016071,0.0000015039209],"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":[0.000098345736,0.0009309679,0.1645883,0.000487604,0.00063127215,0.0000034948177,0.0051474725,0.3884861,0.008253797,0.2907028,0.13093075,0.009739125],"study_design_scores_gemma":[0.001000111,0.000064618296,0.004994031,0.00013946502,0.000024043886,0.0000038004282,0.00003610508,0.96765447,0.002917867,0.010485737,0.012443712,0.00023602639],"about_ca_topic_score_codex":0.000029551922,"about_ca_topic_score_gemma":0.000003477346,"teacher_disagreement_score":0.8059268,"about_ca_system_score_codex":0.00020980033,"about_ca_system_score_gemma":0.0002481011,"threshold_uncertainty_score":0.8644056},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2539874,0.00013030747,0.7284817,0.0044867536,0.0040776404,0.0016145424,0.00019648245,0.00023554443,0.006789604],"genre_scores_gemma":[0.97021276,0.000042860505,0.02856342,0.00021022563,0.00028122586,0.00008457353,0.0000042152637,0.000022347414,0.00057839067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997519,0.000015767258,0.0006994135,0.0007116159,0.0006163347,0.00043783872],"domain_scores_gemma":[0.9973318,0.00020433064,0.0004977974,0.00033928588,0.0014930225,0.00013376611],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003599596,0.00032139747,0.0003079582,0.00017923926,0.00031961655,0.0007056263,0.0030379258,0.00013647231,0.00012687429],"category_scores_gemma":[0.00048049793,0.00024554235,0.00023189155,0.0004092737,0.0001956747,0.0018790563,0.00043099746,0.00027567422,0.000071221846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021420782,0.0010143641,0.0000822479,0.00013093952,0.00010229821,0.0000031687327,0.0019400823,0.001958988,0.07814811,0.76542795,0.002112828,0.14886482],"study_design_scores_gemma":[0.00012814387,0.00016191484,0.00006309808,0.0003329474,0.000015944694,0.0000125100005,0.00024521587,0.8359123,0.12944353,0.032074973,0.0012959383,0.00031352715],"about_ca_topic_score_codex":0.000054093514,"about_ca_topic_score_gemma":0.000013975966,"teacher_disagreement_score":0.83395326,"about_ca_system_score_codex":0.00012211943,"about_ca_system_score_gemma":0.00008472337,"threshold_uncertainty_score":0.9999997},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038903568,0.0004997822,0.9521003,0.00021416343,0.00023084432,0.0001638044,0.000002942815,0.00011222306,0.0077723977],"genre_scores_gemma":[0.9165286,0.000083205,0.08290437,0.0001386199,0.000011064514,0.0000052264404,0.00000420234,0.0000040874766,0.00032064674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915,0.00008798424,0.00018984261,0.00017277223,0.00023907355,0.00016037378],"domain_scores_gemma":[0.9989306,0.00017409859,0.00008885995,0.00067435857,0.00008606897,0.000046013276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035259567,0.00008044854,0.00010356598,0.0000289704,0.0002503434,0.00007273834,0.0006620544,0.00002819156,0.000021011505],"category_scores_gemma":[0.000037294005,0.000042767482,0.000035265886,0.00023171659,0.00005267486,0.00023137442,0.00011389398,0.00007079512,0.0000125075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007873102,0.00034402727,0.01384671,0.00014029186,0.00003051873,0.0000066254574,0.00014686337,0.0018277421,0.01329269,0.55205476,0.031200385,0.38703066],"study_design_scores_gemma":[0.00045821338,0.00013951588,0.004082293,0.00010340571,0.0000034587908,0.0000044003864,0.000011194865,0.81656027,0.06932427,0.0008088331,0.108340584,0.0001635544],"about_ca_topic_score_codex":0.000009816395,"about_ca_topic_score_gemma":8.882283e-7,"teacher_disagreement_score":0.877625,"about_ca_system_score_codex":0.0000074800337,"about_ca_system_score_gemma":0.000038932423,"threshold_uncertainty_score":0.19254643},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013021905,0.000009102841,0.9720953,0.00016159478,0.00020908512,0.00038677876,0.0000057854722,0.0001633946,0.025666747],"genre_scores_gemma":[0.10369549,5.2256263e-7,0.89547646,0.00032774545,0.00013602285,0.0000055024125,0.0000060000475,0.000006820099,0.0003454452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986358,0.0000116186075,0.00024453795,0.00046828695,0.00020806884,0.00043168376],"domain_scores_gemma":[0.999089,0.00011881002,0.000053809243,0.0003969144,0.0000511865,0.00029026292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040095422,0.00013641435,0.00016275031,0.00009907029,0.000117786614,0.00014604114,0.0005839491,0.000058580743,0.000060543436],"category_scores_gemma":[0.000040505896,0.00011652834,0.000058516798,0.00022338453,0.000039667786,0.00035285603,0.00020804038,0.00008895892,0.000017878057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021293197,0.000029029634,0.00019868926,0.000010539957,0.000017536271,0.000006178458,0.00063193653,0.0007631274,0.0019797976,0.2816769,0.006383545,0.70828146],"study_design_scores_gemma":[0.0017195485,0.00013945201,0.00033992733,0.00002878149,0.000009678792,0.00014715527,0.0008194647,0.9696553,0.011562815,0.012890268,0.0020994034,0.00058821903],"about_ca_topic_score_codex":0.00009681003,"about_ca_topic_score_gemma":0.000014806915,"teacher_disagreement_score":0.96889216,"about_ca_system_score_codex":0.000036876154,"about_ca_system_score_gemma":0.00012351945,"threshold_uncertainty_score":0.4751888},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07284003,0.00007153221,0.9250421,0.00051685184,0.0013159433,0.000042159587,0.000005736238,0.000010382769,0.00015529897],"genre_scores_gemma":[0.5303222,0.000016698423,0.46941537,0.000039847735,0.00019766047,2.848714e-7,0.0000013601322,0.0000018631857,0.000004695138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975078,0.000028556044,0.00077883963,0.0001850722,0.0013241062,0.00017562663],"domain_scores_gemma":[0.9967365,0.00009237971,0.0008519719,0.0003363503,0.0018874303,0.00009531672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008165857,0.00009885316,0.0001941535,0.0005884157,0.00012530915,0.00017672032,0.003383328,0.000028265611,0.000012494627],"category_scores_gemma":[0.00002798468,0.00008194171,0.00011185952,0.00035820715,0.00024546508,0.005098827,0.000787651,0.00012825287,0.000003859533],"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":[0.000038804505,0.00037179978,0.00023317094,0.0000068361473,0.000048759208,0.00000772394,0.00074686995,0.50322837,0.018828044,0.058675174,0.0002575267,0.41755694],"study_design_scores_gemma":[0.00044519038,0.0001287008,0.0009006835,0.00009990671,0.0000044540493,0.00012107484,0.0000047871044,0.95976067,0.034054924,0.0030131121,0.0013828696,0.000083611536],"about_ca_topic_score_codex":0.000012890266,"about_ca_topic_score_gemma":4.8840127e-7,"teacher_disagreement_score":0.4574822,"about_ca_system_score_codex":0.00007298845,"about_ca_system_score_gemma":0.00034822748,"threshold_uncertainty_score":0.6287122},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3089545,0.00015579764,0.688742,0.0004367693,0.0015376639,0.000043139782,0.0000012127905,0.00004790749,0.00008101915],"genre_scores_gemma":[0.6833747,0.000029606534,0.31458962,0.0006412853,0.0013235387,0.000002321985,0.000003853365,0.000013862038,0.00002122372],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833345,0.00018673943,0.00046711267,0.00035569145,0.00022037451,0.00043660105],"domain_scores_gemma":[0.999133,0.0000976894,0.0001963831,0.00040207178,0.00007540082,0.00009543988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037582542,0.00017054967,0.00027833504,0.00050826056,0.00029535723,0.00030543326,0.0007994023,0.00013002763,0.000017306433],"category_scores_gemma":[0.000004376998,0.00014849652,0.000110303234,0.00055029383,0.00006273464,0.0007864605,0.00044004092,0.00046341907,0.00002703139],"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":[0.00008178043,0.002781051,0.13902773,0.000044015134,0.00018285356,0.0036693572,0.0005388709,0.48510337,0.05226767,0.040506314,0.061555192,0.21424179],"study_design_scores_gemma":[0.00077872945,0.00016867196,0.1189631,0.000032710977,0.0000081148,0.001961785,0.0000033999863,0.8567983,0.00006342004,0.012059852,0.008915866,0.0002460531],"about_ca_topic_score_codex":0.00011501593,"about_ca_topic_score_gemma":0.000031405314,"teacher_disagreement_score":0.37442017,"about_ca_system_score_codex":0.00004872786,"about_ca_system_score_gemma":0.000065739565,"threshold_uncertainty_score":0.6055512},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005135303,0.00004807975,0.8546856,0.000117941025,0.00012534305,0.000043366603,9.945423e-7,0.00015456307,0.1443106],"genre_scores_gemma":[0.259055,0.0000104963365,0.73804724,0.00054653065,0.00003622854,0.000004771236,0.000004168706,0.000006164605,0.002289425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999275,0.000046221547,0.0001038339,0.00023633693,0.0001713801,0.00016718727],"domain_scores_gemma":[0.9993306,0.00003619637,0.00002622829,0.0004937401,0.000032931384,0.000080323305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011663501,0.00007635441,0.00007321888,0.000034479162,0.00010839073,0.00012398166,0.00047739697,0.000028967965,0.000246441],"category_scores_gemma":[0.000021515121,0.00005384017,0.000026667878,0.00013421332,0.000019559635,0.0006019646,0.00020641054,0.00006700399,0.0003167726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014396002,0.00009366046,0.00012263145,0.0000035946084,0.000003495794,0.000019359866,0.000055500976,0.000010185815,0.00968257,0.8744553,0.06467171,0.05088055],"study_design_scores_gemma":[0.0010807714,0.00012437049,0.0023683012,0.000039414394,0.00000372173,0.000096215634,0.00012976569,0.14858676,0.07421888,0.016123705,0.75662124,0.0006068554],"about_ca_topic_score_codex":0.000011787211,"about_ca_topic_score_gemma":6.647992e-7,"teacher_disagreement_score":0.8583316,"about_ca_system_score_codex":0.000007806418,"about_ca_system_score_gemma":0.00002214581,"threshold_uncertainty_score":0.40715766},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051097825,0.00074215874,0.94266,0.0002480039,0.00045628852,0.00024811478,0.000017742668,0.00016836087,0.004361533],"genre_scores_gemma":[0.9575731,0.000014145882,0.04167021,0.00037760186,0.000014699834,0.000011156773,0.000007308289,0.0000083262175,0.00032346332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826336,0.0000972291,0.0004348988,0.00039024552,0.00050974207,0.0003045497],"domain_scores_gemma":[0.998093,0.00014643684,0.00017225959,0.001307357,0.00015555632,0.0001253652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038866376,0.00018538555,0.00038581245,0.00008415666,0.00014342225,0.00009385414,0.0013556528,0.00007429969,0.00012244028],"category_scores_gemma":[0.000077398996,0.00014568098,0.0000902527,0.00021442556,0.000088950466,0.00047405122,0.0002739542,0.0001527035,0.000042664644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001260163,0.00113781,0.042160176,0.00015061285,0.00008278402,0.000012018246,0.0006620352,0.0018204459,0.0013002505,0.27900785,0.031589445,0.64195055],"study_design_scores_gemma":[0.0035576453,0.0007745963,0.0034053358,0.00011822479,0.00002024301,0.000011753257,0.00029165886,0.71606046,0.18932013,0.0011926723,0.08466999,0.00057727366],"about_ca_topic_score_codex":0.00019808442,"about_ca_topic_score_gemma":0.00007076538,"teacher_disagreement_score":0.90647525,"about_ca_system_score_codex":0.00003068899,"about_ca_system_score_gemma":0.00011006285,"threshold_uncertainty_score":0.5940698},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06833169,0.0003036635,0.9204852,0.0014460827,0.0009132058,0.000088876404,0.0000044084195,0.00035864935,0.008068214],"genre_scores_gemma":[0.59116215,0.00030268496,0.40283048,0.0026424401,0.0005269026,0.00001344179,0.000024914143,0.00002077167,0.0024762098],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929386,0.000018884555,0.00011155036,0.00022764565,0.00017584953,0.00017218276],"domain_scores_gemma":[0.9993685,0.000035654448,0.000035026842,0.00046927054,0.00002422899,0.0000673096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090461144,0.00006846992,0.00008170811,0.000036121644,0.00013467079,0.000046180845,0.0005580036,0.000034964596,0.000029271107],"category_scores_gemma":[0.0000142851,0.000056765744,0.00003055414,0.00013907219,0.000018336325,0.00037103327,0.00028968917,0.000083737425,0.0003050482],"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":[0.000022345106,0.00045062735,0.008003072,0.000040286224,0.00007249583,0.0009972223,0.0060839513,0.0005268724,0.009359077,0.041428152,0.45280463,0.4802113],"study_design_scores_gemma":[0.00052622985,0.00006825871,0.010425117,0.000051084164,0.0000043788827,0.00019359725,0.000018671664,0.17884655,0.005289182,0.0042316704,0.7999151,0.0004301751],"about_ca_topic_score_codex":0.000065943335,"about_ca_topic_score_gemma":0.0000012734483,"teacher_disagreement_score":0.5228305,"about_ca_system_score_codex":0.000011151768,"about_ca_system_score_gemma":0.000023094843,"threshold_uncertainty_score":0.39208788},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6062579,0.0045706653,0.0060191886,0.0007722786,0.0029893767,0.0005320185,0.0007963147,0.00006574225,0.3779965],"genre_scores_gemma":[0.98841214,0.00027622373,0.008465641,0.00008593396,0.0000828856,0.000009518859,0.0000826292,0.000010229036,0.0025747966],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99833673,0.00009081695,0.00032292344,0.0002948071,0.00079055177,0.00016415262],"domain_scores_gemma":[0.99884117,0.00034151526,0.00040758465,0.00031668952,0.0000012389402,0.0000917942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000015127349,0.00017882675,0.00024935786,0.000018544963,0.00017770356,0.000027797803,0.00074679893,0.00005872005,0.000023809873],"category_scores_gemma":[0.0000041612698,0.0001205369,0.00003263255,0.000072950344,0.000046220615,0.0004621879,0.0001898106,0.00018867025,3.2029521e-9],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034985438,0.0001524425,0.005127408,0.00043179552,0.00028470252,0.000077454235,0.0024343282,0.00004794462,0.124916516,0.29818442,0.0017644041,0.56622875],"study_design_scores_gemma":[0.0004418051,0.00024038313,0.32478675,0.0012263039,0.00006172789,0.000011053614,0.006857317,0.084233575,0.5389766,0.026543913,0.015686354,0.00093421654],"about_ca_topic_score_codex":0.011791558,"about_ca_topic_score_gemma":0.020574413,"teacher_disagreement_score":0.5652945,"about_ca_system_score_codex":0.000003704015,"about_ca_system_score_gemma":0.0011899571,"threshold_uncertainty_score":0.9972975},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095363037,0.00023810765,0.9861854,0.0047591324,0.0003207405,0.00018589583,0.000020175963,0.0003609863,0.00697595],"genre_scores_gemma":[0.89355433,0.0006578708,0.1046372,0.00021680225,0.000027412325,0.00007214242,0.0000115714265,0.000010773566,0.0008119034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989164,0.00013306447,0.00022869225,0.00030744565,0.00020341872,0.00021100859],"domain_scores_gemma":[0.99588317,0.00016316774,0.000066376895,0.003681252,0.00010939797,0.000096657524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001824664,0.000133248,0.00013127606,0.00011193889,0.00076045666,0.00015393297,0.0021827882,0.000048249374,0.000039782564],"category_scores_gemma":[0.00000769034,0.00012742727,0.00007574198,0.0005551966,0.00011414273,0.0006385387,0.00002764259,0.00032537105,0.0001659521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033761935,0.004803995,0.00008509872,0.000014212349,0.00009025519,0.0000073736483,0.0011017149,0.0023045796,0.009377117,0.015208821,0.005193464,0.9617796],"study_design_scores_gemma":[0.001286086,0.0005380831,0.002216283,0.00017039642,0.00007660017,0.0002019675,0.00014423915,0.3626121,0.061770666,0.010042315,0.55973655,0.0012047013],"about_ca_topic_score_codex":0.00010620979,"about_ca_topic_score_gemma":0.000249491,"teacher_disagreement_score":0.9605749,"about_ca_system_score_codex":0.00005835419,"about_ca_system_score_gemma":0.000053775704,"threshold_uncertainty_score":0.5848895},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09443151,0.00007231161,0.9044084,0.00039427765,0.00029633843,0.00015480787,0.00015295231,0.00005846944,0.000030941814],"genre_scores_gemma":[0.72531843,0.00009572232,0.2740848,0.0003773755,0.000025453794,0.000008612946,0.00008131302,0.000003551091,0.0000047354615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988827,0.00009782694,0.00039961527,0.0002405141,0.00014328478,0.00023602833],"domain_scores_gemma":[0.9985428,0.0008972956,0.0001209572,0.00031074762,0.00006333882,0.00006487407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018531864,0.00016861348,0.0001792567,0.00016638314,0.0008873542,0.000057327867,0.00049339136,0.00008267792,0.0000058957016],"category_scores_gemma":[0.00002224015,0.00011333284,0.000046771605,0.000445734,0.0003346352,0.00049346074,0.000043562697,0.0002751852,0.000010212813],"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":[0.000074821204,0.00048038128,0.010682844,0.00004886927,0.00007860349,0.000035132263,0.0028368242,0.8115003,0.00007866803,0.033333622,0.00020627504,0.14064363],"study_design_scores_gemma":[0.00039038376,0.000077841934,0.009024882,0.00003774005,0.000004442564,0.00014606754,0.000148936,0.98589593,0.000036783513,0.0035983482,0.00046174077,0.00017689155],"about_ca_topic_score_codex":0.000057851747,"about_ca_topic_score_gemma":0.000022972565,"teacher_disagreement_score":0.6308869,"about_ca_system_score_codex":0.000036779446,"about_ca_system_score_gemma":0.00009493585,"threshold_uncertainty_score":0.68249005},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037238857,0.00084156706,0.9151082,0.0011497405,0.00039776493,0.0008843709,0.00007747307,0.000118271215,0.08105024],"genre_scores_gemma":[0.08953829,0.012770905,0.89393514,0.0018787789,0.00012192706,0.00014447338,0.00040709495,0.000022781323,0.001180621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817914,0.000033222088,0.0006637373,0.00034786592,0.00044112813,0.00033488573],"domain_scores_gemma":[0.99732643,0.0002770823,0.00021313864,0.0018276405,0.00025897022,0.000096733354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013723774,0.00019726886,0.00025176027,0.0010265452,0.0006594647,0.00050040026,0.0037029837,0.00011188246,0.0000031341249],"category_scores_gemma":[0.00005394797,0.00018844123,0.000046067667,0.0003790985,0.0005108856,0.0094443625,0.003210634,0.00041248454,0.000015315642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042664783,0.000031619722,0.00010441215,0.0000402667,0.0000031825562,0.0000020424286,0.004811949,0.00023254726,0.0000063343164,0.6294575,0.00045590498,0.36485],"study_design_scores_gemma":[0.00042765785,0.000053855598,0.0014856901,0.00026083467,0.0000013034618,0.00004296478,0.00002108102,0.776513,0.000011591881,0.006527276,0.21436429,0.0002904863],"about_ca_topic_score_codex":0.00002621489,"about_ca_topic_score_gemma":0.000026563368,"teacher_disagreement_score":0.7762804,"about_ca_system_score_codex":0.00013267327,"about_ca_system_score_gemma":0.00038533838,"threshold_uncertainty_score":0.768441},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052560256,0.000055755605,0.9927358,0.00053952035,0.00022996981,0.0004152992,0.00004963629,0.0002006836,0.00051732204],"genre_scores_gemma":[0.15403609,0.00001784042,0.84515655,0.000646399,0.000023801345,0.00007289942,0.000022509656,0.000014774936,0.000009108327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874276,0.00007521483,0.0003297124,0.00033850258,0.00016331591,0.00035049816],"domain_scores_gemma":[0.9971832,0.00037058556,0.00022787077,0.0019585988,0.00014959867,0.000110115536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004528592,0.00017684224,0.00019022496,0.00013717105,0.00045943575,0.00014944113,0.002243694,0.000045260473,0.0000047695376],"category_scores_gemma":[0.000014756129,0.00015446813,0.00005735888,0.00022496415,0.00030241563,0.0006011026,0.00041804803,0.00021940628,0.000004674989],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025936935,0.00016905022,0.0004889613,0.00001930403,0.00014057104,0.000012258202,0.0025807335,0.000021677684,0.034895957,0.006770304,0.0005294746,0.95434576],"study_design_scores_gemma":[0.0030564056,0.00028095313,0.00041659892,0.00018642365,0.000058080626,0.0002383497,0.0011141176,0.92924076,0.059083678,0.0013622596,0.003908971,0.0010533965],"about_ca_topic_score_codex":0.0001330357,"about_ca_topic_score_gemma":0.000060966777,"teacher_disagreement_score":0.95329237,"about_ca_system_score_codex":0.000053421296,"about_ca_system_score_gemma":0.000076438315,"threshold_uncertainty_score":0.6299027},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08437502,0.00008644245,0.9139402,0.00019772055,0.0002698005,0.000049653197,7.3618264e-7,0.00021022583,0.0008701944],"genre_scores_gemma":[0.14154948,0.000022973383,0.8570952,0.00043777065,0.00013134614,0.0000016368214,0.0000022182496,0.00000911818,0.00075026473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909276,0.000019577548,0.00016460587,0.00030408378,0.00018526727,0.00023369941],"domain_scores_gemma":[0.99932605,0.00004126989,0.000060679384,0.00046224202,0.00003214153,0.00007761706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013169533,0.00009645061,0.000104526116,0.000059121623,0.00020657615,0.00009559065,0.0005441591,0.00004308686,0.000023651202],"category_scores_gemma":[0.000016629392,0.00007690541,0.000037928603,0.00015207086,0.000014276329,0.00082394615,0.00051609374,0.00008863277,0.000044426444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020021267,0.00035338502,0.005302148,0.00008501727,0.00007484854,0.0006263298,0.0040058084,0.0028317363,0.25657526,0.01316355,0.013954765,0.7030071],"study_design_scores_gemma":[0.00016047702,0.000020592084,0.00033433476,0.000019466008,0.0000026619127,0.00013090833,0.000019267734,0.9829337,0.0107710995,0.0005740291,0.0048340126,0.0001994276],"about_ca_topic_score_codex":0.00080563204,"about_ca_topic_score_gemma":0.0000055631112,"teacher_disagreement_score":0.980102,"about_ca_system_score_codex":0.000046476824,"about_ca_system_score_gemma":0.000044219258,"threshold_uncertainty_score":0.31361115},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987073,0.00049553294,0.00827936,0.0007319494,0.00040673913,0.00030626124,0.0000035040996,0.00008972422,0.0026139135],"genre_scores_gemma":[0.98783183,0.000013801646,0.011938995,0.00010412638,0.00005436618,0.000011066503,2.1849753e-7,0.0000062982117,0.0000393116],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989588,0.000006712473,0.00019444406,0.00020507441,0.00034693978,0.00028797722],"domain_scores_gemma":[0.99948496,0.000048816328,0.00015202301,0.00014607408,0.000069331094,0.00009878416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003400101,0.00011773375,0.00013070596,0.000057429672,0.00015029183,0.00010083412,0.0004941204,0.000034547615,0.0000051209076],"category_scores_gemma":[0.00006570981,0.000073797484,0.00004081841,0.00021362912,0.000046707188,0.00038318208,0.00094863435,0.00011121304,0.0000022630954],"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":[0.000089112684,0.001229774,0.11621678,0.0003142767,0.00017539937,0.0000020905447,0.010959079,0.00033321115,0.42795873,0.35409015,0.004356822,0.08427459],"study_design_scores_gemma":[0.0023182814,0.00027803538,0.34775618,0.0009819949,0.00010344481,0.00014722273,0.00075397594,0.3043641,0.32575136,0.0043623806,0.012142879,0.0010401718],"about_ca_topic_score_codex":0.00003662682,"about_ca_topic_score_gemma":3.1551076e-7,"teacher_disagreement_score":0.34972778,"about_ca_system_score_codex":0.00003859493,"about_ca_system_score_gemma":0.000011828395,"threshold_uncertainty_score":0.3009374},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013733127,0.00006439947,0.9972906,0.00038031704,0.00020446835,0.0001753696,0.000018149905,0.0001709779,0.00032238913],"genre_scores_gemma":[0.0038973426,0.0000063285383,0.9942667,0.00051681226,0.00046689482,0.000039615657,0.00009338936,0.0000051072743,0.00070779474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992727,0.000019152072,0.00012498748,0.0002668213,0.00015361552,0.0001627041],"domain_scores_gemma":[0.99949,0.000019230985,0.000031757947,0.00032084767,0.00005993959,0.000078200625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009161919,0.00007621655,0.00006277147,0.00004572394,0.000146594,0.000088566776,0.00039738417,0.000033062424,0.000045163426],"category_scores_gemma":[0.0000019530814,0.00006378151,0.000030916526,0.00008393183,0.000010390689,0.0014360981,0.000081359794,0.000031523145,0.000037369657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011726414,0.00007215918,0.000020277768,0.0000011481254,0.0000032612218,4.847365e-7,0.00006168157,0.00030002388,0.0015477724,0.010785599,0.010156822,0.9770496],"study_design_scores_gemma":[0.0002837672,0.00007837409,0.00080726756,0.000002031145,0.0000018466645,0.000007282493,0.000014886795,0.9797914,0.0030241024,0.0013175132,0.014567126,0.00010440333],"about_ca_topic_score_codex":0.000020550035,"about_ca_topic_score_gemma":0.0000018336643,"teacher_disagreement_score":0.97949135,"about_ca_system_score_codex":0.000038946368,"about_ca_system_score_gemma":0.000031039777,"threshold_uncertainty_score":0.26009345},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045089265,0.00005805335,0.9822165,0.0004351722,0.0004306553,0.000081718645,0.000008602288,0.00011635785,0.012144066],"genre_scores_gemma":[0.97148126,0.0000619985,0.027139863,0.00045323482,0.00011453155,0.0000047629323,0.00001046247,0.000011370805,0.00072248705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985283,0.000042208307,0.0002600253,0.00044473124,0.0004740709,0.00025067572],"domain_scores_gemma":[0.9991435,0.00007765065,0.00014500649,0.00017406538,0.00032902492,0.00013074854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026256542,0.0001927182,0.00016964327,0.00014166044,0.00027907226,0.0007049694,0.00057633483,0.000078365614,0.00010697213],"category_scores_gemma":[0.000086288426,0.00017227531,0.000033798042,0.00010607915,0.00008000085,0.00057064835,0.00016131492,0.00023717385,0.000023163731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009790401,0.00040320234,0.00030443043,0.00009915785,0.000065166976,0.00013942533,0.0013737777,0.0015382923,0.029356737,0.40669343,0.0017764018,0.5581521],"study_design_scores_gemma":[0.0005534146,0.00012211516,0.00015407948,0.00022217727,0.0000075687094,0.00004209354,0.00023853377,0.9605438,0.002536878,0.03417832,0.0011075516,0.00029345605],"about_ca_topic_score_codex":0.000012337263,"about_ca_topic_score_gemma":7.0949807e-7,"teacher_disagreement_score":0.96697235,"about_ca_system_score_codex":0.00003894726,"about_ca_system_score_gemma":0.00011962278,"threshold_uncertainty_score":0.70251834},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019124118,0.0006827133,0.992301,0.0002341651,0.0005314783,0.00031665424,0.000006956744,0.00012736942,0.0038872391],"genre_scores_gemma":[0.8863235,0.0000864881,0.11025847,0.00016575411,0.00015492406,0.00003263077,0.000010714988,0.000014584031,0.0029529484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988737,0.000038123377,0.00024526747,0.00035734937,0.00023250218,0.00025304986],"domain_scores_gemma":[0.9992014,0.000102162565,0.00005670109,0.00050823943,0.00005300439,0.00007846906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019563037,0.00010834333,0.00016394511,0.00009403551,0.00009165881,0.00015579603,0.0006689906,0.000072759845,0.000031177202],"category_scores_gemma":[0.000012408654,0.00008088522,0.00003958766,0.00022789538,0.000013158947,0.00084536546,0.00027643284,0.00008323834,0.00004142384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014905966,0.00092630275,0.000119618744,0.00022924754,0.00002682679,0.00005599316,0.0017206176,0.1166641,0.008922304,0.534947,0.20836042,0.12787853],"study_design_scores_gemma":[0.0005019945,0.00006411778,0.000023892722,0.00005672205,9.1615885e-7,0.000009426754,0.000016504207,0.99022233,0.00020092838,0.0018713947,0.006905937,0.00012584946],"about_ca_topic_score_codex":0.00004651285,"about_ca_topic_score_gemma":0.0000027545213,"teacher_disagreement_score":0.8844111,"about_ca_system_score_codex":0.000028200817,"about_ca_system_score_gemma":0.000008529328,"threshold_uncertainty_score":0.32984033},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062919535,0.00013015303,0.9351443,0.00084018917,0.0001158401,0.000104989624,0.0001062435,0.000012581784,0.0006261399],"genre_scores_gemma":[0.9518407,0.00009569753,0.047483847,0.000071749346,0.0004009587,0.000012826917,0.000056014185,0.000004617178,0.00003356752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983444,0.000025033969,0.00045420296,0.00010225264,0.00090146804,0.00017261661],"domain_scores_gemma":[0.9985965,0.00021562439,0.00022572676,0.00021052461,0.0006462338,0.00010542568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038589138,0.000074438605,0.00010055858,0.00030602037,0.00016641924,0.00045879182,0.0010882248,0.000034581364,0.000012651654],"category_scores_gemma":[0.000011858155,0.000059641847,0.000040605337,0.00016371672,0.000056758046,0.00031863718,0.00042839936,0.00023954485,0.000026029538],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032388507,0.0007922091,0.0137757845,0.000035297035,0.0001513508,0.000060382583,0.00093818805,0.004123325,0.003269222,0.04368735,0.005503944,0.92763054],"study_design_scores_gemma":[0.0010724077,0.0001270295,0.037410893,0.00020763696,0.00000662511,0.00015374632,0.00026180618,0.9096002,0.0027500642,0.020663323,0.02751689,0.00022937395],"about_ca_topic_score_codex":0.0001917405,"about_ca_topic_score_gemma":0.0000070995334,"teacher_disagreement_score":0.9274012,"about_ca_system_score_codex":0.000058442383,"about_ca_system_score_gemma":0.000054025582,"threshold_uncertainty_score":0.44241402},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001443051,0.000493898,0.9956399,0.0006563409,0.00092461397,0.00022541436,0.000011975201,0.00013142744,0.0017720907],"genre_scores_gemma":[0.04842379,0.00049188465,0.9474212,0.0018736845,0.0012685613,0.00000350368,0.000031768188,0.000028674554,0.0004569282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746406,0.000018430837,0.00038502255,0.00074206555,0.0009404954,0.00044994248],"domain_scores_gemma":[0.998331,0.0002210015,0.0001365781,0.00092868676,0.0002149145,0.00016782996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000714988,0.00033991825,0.00030550227,0.00075274595,0.00023258796,0.00084555044,0.001904396,0.00024568557,0.0000174248],"category_scores_gemma":[0.000055279696,0.00028902257,0.000048909213,0.00042793693,0.00035762857,0.0024761667,0.0019716267,0.0006356716,0.000053208423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050404783,0.0000069681673,0.000015374228,0.000025271805,0.0000032678124,0.0000125026845,0.00039057646,0.0059311986,0.00007104122,0.010191232,0.000043811568,0.9833037],"study_design_scores_gemma":[0.00023912586,0.00009583475,0.00012394364,0.00019922243,0.0000028116492,0.00007671352,1.1667269e-7,0.9679631,0.0006988926,0.010973821,0.019210815,0.0004155762],"about_ca_topic_score_codex":0.000010043802,"about_ca_topic_score_gemma":0.000006948427,"teacher_disagreement_score":0.98288816,"about_ca_system_score_codex":0.00013011698,"about_ca_system_score_gemma":0.00039916346,"threshold_uncertainty_score":0.9999562},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101529375,0.00034185324,0.8959538,0.00013663471,0.0007761622,0.00043198743,0.00009424802,0.00016271455,0.0005732309],"genre_scores_gemma":[0.99385625,0.00014788182,0.0054006535,0.0001356586,0.00014058972,0.000039876595,0.000019029761,0.000044032597,0.0002160237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727947,0.00025722387,0.00057362695,0.0007979551,0.0005831322,0.0005086119],"domain_scores_gemma":[0.99848896,0.00036492533,0.00016897102,0.00060942536,0.00015717166,0.00021051618],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00031695384,0.00041934373,0.00040384888,0.00030814458,0.00050705136,0.0012459024,0.0003169985,0.0001950506,0.00002128026],"category_scores_gemma":[0.000004769784,0.00040067255,0.00008177227,0.00026385044,0.00018409043,0.00045126435,0.000015419675,0.00044288806,0.000036029127],"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":[0.0004785277,0.0027059247,0.00039470464,0.0015456465,0.00035942212,0.00041783004,0.0021686668,0.7012502,0.0038493704,0.01322253,0.002394499,0.2712127],"study_design_scores_gemma":[0.0014954538,0.00069097744,0.00033107167,0.00088868773,0.00010667811,0.00012043905,0.00034044893,0.9880526,0.0050039412,0.0011750859,0.0009964773,0.0007981237],"about_ca_topic_score_codex":0.0012861922,"about_ca_topic_score_gemma":0.00009086126,"teacher_disagreement_score":0.8923269,"about_ca_system_score_codex":0.00007897533,"about_ca_system_score_gemma":0.00009593366,"threshold_uncertainty_score":0.9998445},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28700274,0.0000658835,0.71181715,0.00033621027,0.00006044284,0.000055582317,0.000032048465,0.00004646214,0.0005834928],"genre_scores_gemma":[0.95793307,0.000044965003,0.041708652,0.0002148124,0.000028820949,0.000004739717,0.00004209661,0.0000028646882,0.000019969726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944127,0.000025630363,0.00014558189,0.0001658795,0.00013625472,0.00008538519],"domain_scores_gemma":[0.9997398,0.000033444507,0.00004935628,0.00010173353,0.00003235707,0.000043311822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006691091,0.00006132416,0.00008525386,0.000051835323,0.000056545083,0.000029272302,0.00011307588,0.000030583335,0.00019737602],"category_scores_gemma":[0.0000025559204,0.000054057167,0.000024501931,0.00007164095,0.000021037644,0.0004946256,0.000016099308,0.00004413568,0.0000052930045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012098242,0.00015438221,0.0007698574,0.000026206917,0.00001840586,0.000010102931,0.0011331564,0.00003124951,0.006353021,0.0052981204,0.00076910126,0.9854243],"study_design_scores_gemma":[0.0022085677,0.000491369,0.021113165,0.00013171905,0.000016823426,0.00006905897,0.00007051787,0.9508842,0.01562842,0.008677566,0.00037530373,0.00033324969],"about_ca_topic_score_codex":0.000059492875,"about_ca_topic_score_gemma":0.0000030655506,"teacher_disagreement_score":0.98509103,"about_ca_system_score_codex":0.0000066893876,"about_ca_system_score_gemma":0.0000031256031,"threshold_uncertainty_score":0.22043873},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24254571,0.00014186141,0.755816,0.00011249726,0.000089622205,0.00026573392,0.000006510483,0.00007801721,0.0009440675],"genre_scores_gemma":[0.946048,0.0000050135336,0.05370557,0.00013005234,0.00002262422,0.000015511758,0.000027388625,0.000002301752,0.000043514927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990796,0.0001606704,0.00014192385,0.00034766857,0.00017948732,0.00009066145],"domain_scores_gemma":[0.9994224,0.000070098824,0.000059018388,0.0002967936,0.000097797114,0.000053938435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001567592,0.00009591559,0.000111403635,0.00003591967,0.00019872496,0.00024609265,0.00020263913,0.000043804168,0.000055302724],"category_scores_gemma":[0.000012403961,0.00007741718,0.000012273104,0.00017052605,0.000015471125,0.00083188876,0.000067275505,0.00009187449,0.000017340017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019982948,0.007973566,0.015535537,0.00003288174,0.0005108887,0.00007522849,0.08627734,0.0027997876,0.18088894,0.50057393,0.054557085,0.150575],"study_design_scores_gemma":[0.002658154,0.00078245654,0.20859212,0.000037822494,0.00003990089,0.0000091691645,0.0033841045,0.6954896,0.05609697,0.026973382,0.0050506038,0.0008857094],"about_ca_topic_score_codex":0.00007673827,"about_ca_topic_score_gemma":0.000015935539,"teacher_disagreement_score":0.7035023,"about_ca_system_score_codex":0.000018393159,"about_ca_system_score_gemma":0.000026637726,"threshold_uncertainty_score":0.3156981},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009388801,0.00034553665,0.99627095,0.00066544977,0.00070636603,0.00018444067,0.00017485295,0.00019016273,0.0005233317],"genre_scores_gemma":[0.03304926,0.0002352113,0.96285945,0.001044233,0.00055555365,0.000030463574,0.0012433322,0.000023979223,0.0009585057],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987343,0.000027540857,0.00018703891,0.0005485554,0.00024339689,0.00025915346],"domain_scores_gemma":[0.9978346,0.00007453086,0.00007573946,0.0018439313,0.00006264932,0.000108532986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018072012,0.00012464655,0.00015071576,0.00004816999,0.0003642355,0.00009158457,0.0024195448,0.000053214866,0.000025042586],"category_scores_gemma":[0.000029752076,0.00010022888,0.00003570477,0.00015129274,0.0000466912,0.0010572003,0.0016848688,0.00009157885,0.00007455314],"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":[0.000020179888,0.00019717647,0.00029645636,0.00002278211,0.000019761399,0.000063068546,0.000225502,0.000028969944,0.0010203773,0.00884255,0.6870183,0.30224487],"study_design_scores_gemma":[0.00035145113,0.000028696391,0.00047737703,0.000016567912,0.000002521641,0.000034497523,0.0000024889189,0.50091076,0.00054134283,0.0007520164,0.49674642,0.00013585435],"about_ca_topic_score_codex":0.00005848381,"about_ca_topic_score_gemma":0.000002549711,"teacher_disagreement_score":0.5008818,"about_ca_system_score_codex":0.000011637845,"about_ca_system_score_gemma":0.00004826866,"threshold_uncertainty_score":0.44961566},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91408575,0.00027857334,0.079080805,0.0058491775,0.00033155104,0.000108723885,3.2540808e-7,0.0000576432,0.00020747256],"genre_scores_gemma":[0.97674173,0.00014807908,0.022826824,0.00016912926,0.000068596,0.0000030307187,6.565903e-8,0.0000023206653,0.00004023511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873716,0.0000110341125,0.00026575872,0.00020484913,0.0005607896,0.00022041275],"domain_scores_gemma":[0.99879956,0.000022204156,0.00019737432,0.00026127684,0.0006245401,0.00009503756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059719005,0.000077884375,0.00015027783,0.0005570668,0.00024814537,0.00017910895,0.0012837222,0.00006310711,0.000013784017],"category_scores_gemma":[0.00007264937,0.000053546064,0.00002075226,0.0010163672,0.00039561227,0.0015770667,0.0006380285,0.00022352807,0.000024438123],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079587,0.0005742174,0.08506422,0.00001783728,0.000055610904,0.00012797858,0.0016461303,0.0002599191,0.041858174,0.06502313,0.008577697,0.79678714],"study_design_scores_gemma":[0.004497042,0.0054152794,0.21381295,0.0003441434,0.000060366936,0.0053251605,0.006382779,0.5647993,0.035518806,0.09189458,0.07067512,0.0012744883],"about_ca_topic_score_codex":0.000008621678,"about_ca_topic_score_gemma":2.7321283e-7,"teacher_disagreement_score":0.7955126,"about_ca_system_score_codex":0.000038037633,"about_ca_system_score_gemma":0.00012119372,"threshold_uncertainty_score":0.23854968},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018818034,0.000024985236,0.97960705,0.00027465273,0.00051775324,0.0002930339,0.00013984037,0.000210362,0.00011429794],"genre_scores_gemma":[0.63255185,0.00002507526,0.36719415,0.000047448084,0.000030878655,0.000027708144,0.000017838514,0.000013856165,0.00009120631],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985167,0.00005167955,0.00032359114,0.00039006418,0.00045951552,0.00025847394],"domain_scores_gemma":[0.99894685,0.00005995626,0.00012273836,0.0005766211,0.00016016225,0.00013367293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001442576,0.00017723492,0.00021352668,0.00013980667,0.00015732377,0.000059828744,0.0006232479,0.0001237193,0.000052804593],"category_scores_gemma":[0.000011375341,0.00016253183,0.00009430265,0.0005529066,0.00007699702,0.0005526276,0.0000075797357,0.00020030951,0.00008271399],"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":[0.00008376309,0.00089440914,0.000019226785,0.0000319022,0.00006981103,0.000016619197,0.00087167666,0.69040954,0.022489902,0.00031804707,0.00019897881,0.28459612],"study_design_scores_gemma":[0.0021296905,0.000320901,0.0006980697,0.00016281671,0.000029247105,0.000014420412,0.00005026856,0.7999492,0.19554454,0.0004434894,0.00032866388,0.0003286367],"about_ca_topic_score_codex":0.00028007862,"about_ca_topic_score_gemma":0.000063833824,"teacher_disagreement_score":0.6137338,"about_ca_system_score_codex":0.000085658685,"about_ca_system_score_gemma":0.00013905659,"threshold_uncertainty_score":0.6627856},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029433495,0.000062957726,0.9862963,0.0035543472,0.0002421113,0.00020592113,0.0000033080785,0.0002477689,0.006443954],"genre_scores_gemma":[0.021129549,0.000013537388,0.97516125,0.0018868918,0.00008886283,0.000008340972,0.000006856846,0.0000066238654,0.0016980763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884266,0.000022819164,0.0001927194,0.0004177718,0.00022764425,0.000296414],"domain_scores_gemma":[0.9991518,0.00003018153,0.000027035454,0.000593714,0.000036936974,0.00016027808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016926565,0.00012425431,0.00014421063,0.00018571077,0.000073608884,0.00009273934,0.00085069594,0.00005154357,0.000043021766],"category_scores_gemma":[0.000017446884,0.0001024565,0.000038665454,0.0007191575,0.000009779849,0.00045963036,0.00023767752,0.00010364156,0.00053045095],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047192875,0.00014600136,0.000040710947,0.0000012403065,0.0000022061697,0.000046257057,0.00022732651,0.000093936615,0.0004936638,0.0051355856,0.020187255,0.9736211],"study_design_scores_gemma":[0.0009163618,0.000523429,0.026799886,0.00010496165,0.0000030078288,0.000049033166,0.000017438593,0.88958824,0.003989642,0.013053176,0.064302325,0.0006525319],"about_ca_topic_score_codex":0.000097001524,"about_ca_topic_score_gemma":0.00001870318,"teacher_disagreement_score":0.9729686,"about_ca_system_score_codex":0.000024586237,"about_ca_system_score_gemma":0.000029040288,"threshold_uncertainty_score":0.6818051},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003802733,0.000055826724,0.9801223,0.000042842934,0.0007725625,0.000058015947,5.317666e-7,0.00012299111,0.015022188],"genre_scores_gemma":[0.493635,0.000019639674,0.5052794,0.0002292705,0.00008013109,0.0000014501848,0.0000036041572,0.000010283897,0.0007411917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990759,0.000042935,0.00017136721,0.00026337284,0.0002288446,0.00021759789],"domain_scores_gemma":[0.9994471,0.000035167115,0.00006340267,0.0003230329,0.000059340513,0.000071965784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029550545,0.00009341414,0.000090199654,0.00009813605,0.00021426783,0.00023798882,0.00032955362,0.000041243657,0.00014893193],"category_scores_gemma":[0.00005836831,0.0000827061,0.000028258186,0.0003812695,0.00001460125,0.0010129864,0.00017005863,0.000068510424,0.000025577672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003734766,0.000079079226,0.003180511,0.000038616414,0.000020966418,0.000037435184,0.0008978747,0.0031022932,0.013040878,0.9359334,0.00585276,0.03781241],"study_design_scores_gemma":[0.00022312248,0.000019755245,0.00022865589,0.000038414495,0.000004710755,0.000046881763,0.0000644455,0.97830325,0.011961895,0.0020346413,0.006888903,0.00018531145],"about_ca_topic_score_codex":0.000055222285,"about_ca_topic_score_gemma":0.0000026047912,"teacher_disagreement_score":0.97520095,"about_ca_system_score_codex":0.00003301439,"about_ca_system_score_gemma":0.00003347107,"threshold_uncertainty_score":0.3372657},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009518271,0.0000049744167,0.9878426,0.0002868171,0.0009363381,0.00013426438,0.000002471452,0.0002122328,0.001062037],"genre_scores_gemma":[0.08078596,7.056083e-7,0.9182768,0.0005764259,0.00025376226,0.00001991734,0.0000074594464,0.0000060023485,0.0000730024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918693,0.00002320911,0.00012266006,0.00033510456,0.00013015933,0.00020192788],"domain_scores_gemma":[0.9991049,0.000079215606,0.00003994047,0.0006282714,0.000044804914,0.00010285476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003559888,0.0000927711,0.00008795601,0.00003371263,0.00016218696,0.00019998242,0.00069725927,0.00005949205,0.000051177252],"category_scores_gemma":[0.000024076598,0.00007362241,0.000041122727,0.00010278583,0.00001615708,0.0011345865,0.000114541486,0.00010961816,0.000014234649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008228443,0.00007288691,0.00010432048,0.000007676213,0.0000077949335,0.0000039297747,0.00013284573,0.00040778992,0.24411547,0.17877547,0.0039302283,0.57243335],"study_design_scores_gemma":[0.00027708654,0.00006024066,0.00079672236,0.000004910365,0.0000030860554,0.000010341575,0.000007933705,0.8643796,0.024664005,0.0029077153,0.10671242,0.00017592253],"about_ca_topic_score_codex":0.00006689233,"about_ca_topic_score_gemma":0.00003799575,"teacher_disagreement_score":0.8639718,"about_ca_system_score_codex":0.00000986803,"about_ca_system_score_gemma":0.000026412285,"threshold_uncertainty_score":0.30022347},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0988916,0.00013965301,0.8993094,0.00039989964,0.0009484863,0.000056834597,0.000006339876,0.000040161303,0.00020765197],"genre_scores_gemma":[0.28174096,0.000026187588,0.7175151,0.00008112905,0.00058472663,0.0000010890498,0.0000020515174,0.000015753907,0.000032995187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836713,0.00003263325,0.0004441971,0.00023166284,0.0006118079,0.00031253893],"domain_scores_gemma":[0.9985212,0.00011035365,0.00046817044,0.00047273532,0.00019956352,0.00022798593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059373333,0.00017890972,0.0002805139,0.00016724455,0.00018791111,0.00036670314,0.0011997746,0.00006838963,0.000020858019],"category_scores_gemma":[0.00003096367,0.000117184136,0.00010290979,0.0002638229,0.000043677413,0.0017945304,0.00029021036,0.00074562867,0.000007053751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001254693,0.0003292649,0.002643749,0.00007193616,0.000365284,0.0008571276,0.002698148,0.0032483628,0.06131335,0.042358216,0.0016792683,0.8843098],"study_design_scores_gemma":[0.018497996,0.006734442,0.075140454,0.0033851385,0.00049040595,0.0209378,0.0025527372,0.5005807,0.06991534,0.12644607,0.16917223,0.0061466573],"about_ca_topic_score_codex":0.000026748527,"about_ca_topic_score_gemma":0.0000069282455,"teacher_disagreement_score":0.87816316,"about_ca_system_score_codex":0.000020372743,"about_ca_system_score_gemma":0.000116044495,"threshold_uncertainty_score":0.47786304},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19163105,0.000005078819,0.8080632,0.000007208061,0.000026013005,0.00007137679,4.3254775e-7,0.000022626886,0.00017300472],"genre_scores_gemma":[0.53815967,0.000004714423,0.4617891,0.00002735802,0.0000049221817,0.000002242088,0.0000032566336,0.0000010948067,0.0000076258516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996858,0.000016288455,0.00008793629,0.000100869394,0.000060198665,0.000048897586],"domain_scores_gemma":[0.9997486,0.000008112125,0.00004003182,0.00014755588,0.000029545492,0.000026148067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010769387,0.000032362346,0.000036304154,0.000026484344,0.000032661945,0.000024881127,0.00013302943,0.000013014846,0.00005598502],"category_scores_gemma":[8.974601e-7,0.000025091043,0.000003982203,0.000048398455,0.000007696857,0.00090091565,0.000078178964,0.000013972063,0.0000017431504],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011938574,0.000047444515,0.0019598126,0.0000075736543,0.0000068100658,0.000002509352,0.004518891,0.00002617883,0.027861811,0.06107212,0.00029140894,0.9041935],"study_design_scores_gemma":[0.00067945314,0.0005988611,0.14309806,0.000008008935,0.000005452944,0.000009524815,0.00023154491,0.53549695,0.3063198,0.013231966,0.00014440597,0.00017599123],"about_ca_topic_score_codex":0.00016224106,"about_ca_topic_score_gemma":0.000009587117,"teacher_disagreement_score":0.9040175,"about_ca_system_score_codex":0.0000023129683,"about_ca_system_score_gemma":0.000012271027,"threshold_uncertainty_score":0.1023183},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09128201,0.000038833015,0.90658456,0.000041566364,0.00005020774,0.00019026102,0.000010027595,0.00003227033,0.0017702379],"genre_scores_gemma":[0.61947167,0.0000023309308,0.38047752,0.000015679041,0.000009672652,0.000006247681,0.0000045768693,0.0000064823553,0.0000058555047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990345,0.000011143628,0.0002940546,0.00019327161,0.0003450233,0.00012197598],"domain_scores_gemma":[0.9991904,0.00006905808,0.00022238199,0.00036393688,0.00006648989,0.00008771795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002435149,0.00011445502,0.00023526182,0.00007696534,0.000033522974,0.000033535878,0.00027826894,0.000042178228,0.0000010926144],"category_scores_gemma":[0.000023392216,0.00008850248,0.000028336024,0.00018532206,0.00006637797,0.000052246065,0.00024590976,0.00006033454,0.0000065699282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012272732,0.00086677173,0.000015835258,0.00086224393,0.00005242539,0.000006759576,0.038076624,0.021359574,0.026951538,0.80846155,0.0004842586,0.102739684],"study_design_scores_gemma":[0.00070886774,0.00018582215,0.00010999298,0.0001792956,0.00001349832,0.0000066917855,0.00043721835,0.9744234,0.0036441018,0.019995876,0.00013137057,0.00016383956],"about_ca_topic_score_codex":0.00000599631,"about_ca_topic_score_gemma":7.052352e-7,"teacher_disagreement_score":0.95306385,"about_ca_system_score_codex":0.000013294111,"about_ca_system_score_gemma":0.000035467456,"threshold_uncertainty_score":0.36090264},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027155443,0.000011194584,0.9731091,0.00014030977,0.00009606295,0.0004941036,0.000019124682,0.00012396598,0.023290578],"genre_scores_gemma":[0.13021497,0.0000049658715,0.86908066,0.00026168633,0.00003454103,0.000089351466,0.000018777771,0.000024043264,0.000270968],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99879456,0.00001482261,0.0002021884,0.00033413953,0.00032845914,0.0003258111],"domain_scores_gemma":[0.99865174,0.00029619882,0.00006777184,0.0008318623,0.000044716053,0.00010773764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041485028,0.00016796605,0.00020667621,0.000059591155,0.00018704815,0.00014405671,0.00058079005,0.00007469211,0.000020789923],"category_scores_gemma":[0.000060107643,0.00013240987,0.0000660783,0.00018423724,0.000031604253,0.00012214841,0.00015975769,0.0001318075,0.00006442283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004450343,0.00008366148,9.684965e-7,0.00006145417,0.000009314784,0.0000010286868,0.00049761316,0.0001146072,0.0010136305,0.9949217,0.0017317956,0.0015597809],"study_design_scores_gemma":[0.0013089803,0.00017845983,0.0000260395,0.00006890174,0.000020261798,0.000008302149,0.00040887762,0.29068953,0.03560638,0.6592716,0.011823055,0.0005895906],"about_ca_topic_score_codex":0.0000013656067,"about_ca_topic_score_gemma":6.010126e-7,"teacher_disagreement_score":0.3356501,"about_ca_system_score_codex":0.000025401734,"about_ca_system_score_gemma":0.000041793526,"threshold_uncertainty_score":0.5399518},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107615024,0.00006152751,0.89087164,0.00007455155,0.0004258105,0.000103230166,0.0000057135294,0.00016964761,0.00067284046],"genre_scores_gemma":[0.7250475,5.250533e-7,0.274458,0.00014754417,0.00022300906,0.0000056395616,0.00000947642,0.0000065494028,0.000101733945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990677,0.00003162162,0.00012913543,0.00020756293,0.00027818212,0.00028574537],"domain_scores_gemma":[0.9994321,0.000020804635,0.00005198012,0.00032060096,0.000044386954,0.00013013688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001844335,0.00010054123,0.00009448603,0.000034318335,0.0001478642,0.00008805856,0.00020985358,0.000029720222,0.000054139502],"category_scores_gemma":[0.0000028221116,0.000066181194,0.000019284125,0.00011959517,0.000026955726,0.0014956639,0.00023130012,0.000069398244,0.000033833938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005586076,0.0033421598,0.13023849,0.00014273095,0.00036266574,0.00011101694,0.0044629117,0.051565696,0.07986415,0.4402472,0.038036782,0.25106758],"study_design_scores_gemma":[0.00057572336,0.00005151488,0.0019149969,0.000027482201,0.0000075581156,0.00011071759,0.000008422701,0.9891817,0.0059068617,0.00026150816,0.0018056754,0.0001478504],"about_ca_topic_score_codex":0.000074224234,"about_ca_topic_score_gemma":0.0000013085269,"teacher_disagreement_score":0.937616,"about_ca_system_score_codex":0.000021174208,"about_ca_system_score_gemma":0.000029427,"threshold_uncertainty_score":0.26987907},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98269963,0.0002134983,0.0053470954,0.00014254653,0.00037408312,0.00046028776,0.00008763031,0.00069456385,0.009980649],"genre_scores_gemma":[0.8663029,0.000029151337,0.13300072,0.00040168955,0.00004641709,0.000028211862,0.000013944434,0.00004737884,0.0001296122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99722147,0.00012239438,0.00039828333,0.0010319352,0.00053886784,0.00068707037],"domain_scores_gemma":[0.9983409,0.000096195705,0.00022473966,0.00084171403,0.00014470165,0.00035172974],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0008133467,0.00040709076,0.0003576673,0.0001852378,0.0014345547,0.0003397846,0.0008966123,0.00012855341,0.0000089893],"category_scores_gemma":[0.00009013955,0.00034031973,0.000065585904,0.00058327307,0.000083592204,0.0031022104,0.0009415285,0.00070081855,0.00006824537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077584344,0.00021275664,0.00015680504,0.000087216446,0.000102179576,0.0004673751,0.000106382555,0.008463317,0.04129684,0.6270052,0.0000017070763,0.32202265],"study_design_scores_gemma":[0.028068148,0.0036362563,0.003512713,0.0055402913,0.0002695267,0.0035815712,0.00074869755,0.15160461,0.45168793,0.2048418,0.13724,0.009268471],"about_ca_topic_score_codex":0.0002270588,"about_ca_topic_score_gemma":0.00007043579,"teacher_disagreement_score":0.4221634,"about_ca_system_score_codex":0.00020793814,"about_ca_system_score_gemma":0.000048514536,"threshold_uncertainty_score":0.9999049},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015206163,0.00016784693,0.98048806,0.0010209704,0.00021217555,0.000106943065,0.0000111982745,0.00014109176,0.0026455726],"genre_scores_gemma":[0.5559952,0.000027232649,0.44082412,0.0017274832,0.00020595994,0.000009071863,0.000017754064,0.000004233915,0.0011889103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99935997,0.000010148825,0.000101581536,0.00022897925,0.00009342883,0.00020588964],"domain_scores_gemma":[0.9995493,0.000033265187,0.000028159984,0.00031414285,0.00002484452,0.000050261337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012651521,0.000071111965,0.00008310041,0.000035374793,0.000116238836,0.00011703425,0.00058620644,0.000028481456,0.000024356104],"category_scores_gemma":[0.0000056047916,0.000051772804,0.00004166959,0.00008006349,0.000008159045,0.00046944208,0.000097338154,0.000031903906,0.00003504544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016607557,0.00022830808,0.00031479538,0.0000074892105,0.000012882951,0.0000138152445,0.000568027,0.000086014166,0.014305581,0.6833731,0.057425853,0.24364756],"study_design_scores_gemma":[0.0014252611,0.00078137126,0.025235258,0.000030469308,0.0000066988273,0.000023714965,0.000114111775,0.34499598,0.006339306,0.13705075,0.48335302,0.00064407254],"about_ca_topic_score_codex":0.000011551998,"about_ca_topic_score_gemma":0.000010354059,"teacher_disagreement_score":0.5463223,"about_ca_system_score_codex":0.000012883307,"about_ca_system_score_gemma":0.000031635554,"threshold_uncertainty_score":0.21112336},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018231978,0.000056952387,0.9963066,0.00023026676,0.000014536985,0.000046520436,0.000001875602,0.000024877834,0.0014951553],"genre_scores_gemma":[0.7111525,0.0001305566,0.2833417,0.00064031366,0.000017919054,0.000006601474,0.0000017533017,0.0000051937473,0.004703441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994592,0.00009724633,0.00009264816,0.00016161628,0.00010340515,0.000085871936],"domain_scores_gemma":[0.9990383,0.0004704355,0.000042779822,0.00039711813,0.000023026125,0.000028363133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029703462,0.000055654502,0.000102239006,0.00006009457,0.00008511396,0.00006993143,0.00033171877,0.000018855391,0.00021118853],"category_scores_gemma":[0.000024567064,0.000029495084,0.000023113475,0.000396323,0.000022520388,0.00012664562,0.00011655792,0.000037919555,0.000011401442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002958292,0.00056508405,0.000953585,0.000020394195,0.0008123402,0.000009286726,0.0029728021,0.17368355,0.0070838537,0.5603628,0.06432382,0.1891829],"study_design_scores_gemma":[0.000059035905,0.000034297776,0.00025063902,0.0000039201727,0.00002380045,5.2822963e-7,0.000008764559,0.99448395,0.0013892483,0.0030075756,0.00069268583,0.000045554596],"about_ca_topic_score_codex":0.00015645557,"about_ca_topic_score_gemma":0.0000020533935,"teacher_disagreement_score":0.82080036,"about_ca_system_score_codex":0.0000029790785,"about_ca_system_score_gemma":0.000003165199,"threshold_uncertainty_score":0.23123664},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064648147,0.0012263549,0.9941287,0.0010440788,0.0016733058,0.0004630539,0.000090928406,0.00021420374,0.0005128845],"genre_scores_gemma":[0.02175312,0.000039617342,0.9757945,0.0013826994,0.00059196213,0.0001819108,0.00015801382,0.000033631048,0.00006453508],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746764,0.00017330938,0.0003727595,0.00068470865,0.00022597921,0.0010756004],"domain_scores_gemma":[0.99820346,0.0001606503,0.00015714049,0.00093604985,0.00017263858,0.00037007921],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006494165,0.00033044716,0.0003761206,0.00014934098,0.00020128289,0.000085061816,0.0009356121,0.00030823963,0.000025580017],"category_scores_gemma":[0.00017797381,0.00027991433,0.00022329461,0.0003304516,0.00012893236,0.0005873966,0.00076842,0.00024433617,0.000103934995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012319513,0.00033734596,0.000088929635,0.000011667579,0.00011192863,0.000030669093,0.00013159518,0.0000035526211,0.014012302,0.20783965,0.0021342721,0.7752858],"study_design_scores_gemma":[0.0032409586,0.0016952178,0.0014160972,0.00003315489,0.0001341092,0.0010995992,0.00007866615,0.26774636,0.0779603,0.08859631,0.5559506,0.002048647],"about_ca_topic_score_codex":0.000057199988,"about_ca_topic_score_gemma":6.134592e-7,"teacher_disagreement_score":0.7732371,"about_ca_system_score_codex":0.0000537744,"about_ca_system_score_gemma":0.00013790284,"threshold_uncertainty_score":0.9999653},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23770677,0.00018629296,0.751794,0.0013914908,0.0002752349,0.00013735869,0.000008758633,0.00020090649,0.008299218],"genre_scores_gemma":[0.8880209,0.0000032561286,0.111707896,0.00013916922,0.000023707593,3.0133026e-7,0.000004461811,9.557766e-7,0.00009937876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944633,0.000023741311,0.00013174038,0.0001478598,0.00014603703,0.000104310384],"domain_scores_gemma":[0.99950784,0.0000247685,0.00004376793,0.0003524305,0.00003016278,0.00004101721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006444901,0.00006244124,0.00012320628,0.00003561711,0.000054640124,0.000029817875,0.000514036,0.000019679448,0.00006064728],"category_scores_gemma":[0.00000612295,0.000041782954,0.000038677263,0.00012066232,0.000044248653,0.00035572477,0.00013106436,0.00003964624,0.000006067495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010273303,0.00012929876,0.000682411,0.000009080378,0.000014833256,0.000019778674,0.0004290072,0.00035531042,0.015331199,0.5604856,0.011198517,0.41124222],"study_design_scores_gemma":[0.0018074275,0.0002953087,0.18229553,0.000017792601,0.000003143341,0.00001601217,0.000015526068,0.7355028,0.0064316904,0.07247577,0.0009468571,0.00019218396],"about_ca_topic_score_codex":0.000044610955,"about_ca_topic_score_gemma":0.0000034090206,"teacher_disagreement_score":0.7351475,"about_ca_system_score_codex":0.000004512731,"about_ca_system_score_gemma":0.000012510184,"threshold_uncertainty_score":0.17038594},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067167077,0.00030342597,0.9895922,0.000043884524,0.000981133,0.00018497939,0.000013698077,0.00022552675,0.0019384457],"genre_scores_gemma":[0.19242942,0.000028016524,0.80694634,0.0003533696,0.00018263455,0.0000039682022,0.000016683094,0.0000107988935,0.000028774812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808526,0.000045116554,0.0005603871,0.00017747509,0.00052049826,0.0006112811],"domain_scores_gemma":[0.9985444,0.00011874906,0.0002989297,0.0006333629,0.000114833834,0.00028970282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005529899,0.0002186725,0.00022466414,0.00011473981,0.00043137383,0.00028001398,0.0007810478,0.00010307531,0.0000126897785],"category_scores_gemma":[0.000075468,0.00017786253,0.00007204158,0.00030757123,0.00007516307,0.0029733675,0.0009538991,0.0001980353,0.00008781949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017956114,0.00053252716,0.007545118,0.000794589,0.000111427384,0.00005260268,0.012898469,0.005487966,0.030120352,0.03243376,0.006466916,0.90353835],"study_design_scores_gemma":[0.00023209541,0.000026467664,0.0004018914,0.00026992348,0.000009116056,0.00014154849,0.00017635433,0.991502,0.002525733,0.00008464232,0.0043505477,0.00027966758],"about_ca_topic_score_codex":0.000025908057,"about_ca_topic_score_gemma":2.3619415e-7,"teacher_disagreement_score":0.98601407,"about_ca_system_score_codex":0.00010916622,"about_ca_system_score_gemma":0.00009455502,"threshold_uncertainty_score":0.7253024},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005284835,0.000077841694,0.8868323,0.00031344566,0.00027235152,0.000099578836,0.000009297428,0.00022326679,0.112119064],"genre_scores_gemma":[0.022563402,0.000013901963,0.96650356,0.0013741918,0.00010360209,0.00001464437,0.0000028685677,0.00000805119,0.009415768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886817,0.000037260856,0.00014991396,0.00040303823,0.00024236653,0.00029925804],"domain_scores_gemma":[0.99896634,0.000093941126,0.000033000804,0.00066853635,0.00007443988,0.00016374291],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016709839,0.0001228708,0.00013851323,0.00006700985,0.00015473028,0.00017650837,0.00087796163,0.000050007362,0.0010214612],"category_scores_gemma":[0.000030885578,0.00009644212,0.000021465446,0.00048593245,0.000014759953,0.000691121,0.0005745574,0.0000986738,0.00077697384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004151131,0.00013956198,0.00002897651,0.0000040194705,0.000017235705,0.000010180199,0.0002541941,0.0011992687,0.0005236174,0.7948332,0.15441847,0.048567146],"study_design_scores_gemma":[0.00019838162,0.00010754149,0.00007092291,0.000021016873,0.0000028542572,0.000010314975,0.000018424793,0.8205,0.00038414137,0.0055702883,0.17291512,0.00020095284],"about_ca_topic_score_codex":0.00016245415,"about_ca_topic_score_gemma":0.0000022703052,"teacher_disagreement_score":0.8193008,"about_ca_system_score_codex":0.00002512642,"about_ca_system_score_gemma":0.000020357364,"threshold_uncertainty_score":0.99989176},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025894502,0.00003082143,0.99212474,0.000054356602,0.0005878769,0.00024002706,0.000054920576,0.0004120241,0.0039058104],"genre_scores_gemma":[0.9333674,0.00006882978,0.065587886,0.00071753276,0.000022099377,0.00006327808,0.00002326264,0.000012868677,0.00013687511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863416,0.00016614413,0.00039140575,0.00019717713,0.0003190454,0.0002920654],"domain_scores_gemma":[0.99890447,0.00017419129,0.000148093,0.0005679132,0.00009178592,0.000113524446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005193718,0.00019226811,0.00015506758,0.00025710659,0.00046136824,0.00026177353,0.00038511102,0.0000850044,0.00009640669],"category_scores_gemma":[0.00000818712,0.00017774732,0.00008640444,0.00023823617,0.000038656017,0.0036220017,0.0000072467815,0.0002649942,0.0002782281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017217829,0.0007615454,0.000028102846,0.00027121752,0.00039127166,0.000018128341,0.018962111,0.17654534,0.0011671534,0.40906504,0.0021743386,0.39044356],"study_design_scores_gemma":[0.00237969,0.0005151812,0.00021736383,0.00023820289,0.00007126607,0.00015359276,0.00085048244,0.82400817,0.022437807,0.011854627,0.1361982,0.0010753945],"about_ca_topic_score_codex":0.000019723355,"about_ca_topic_score_gemma":0.000002669349,"teacher_disagreement_score":0.9307779,"about_ca_system_score_codex":0.000112011614,"about_ca_system_score_gemma":0.0000814182,"threshold_uncertainty_score":0.72483253},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030333807,0.000029587154,0.9929786,0.00007946735,0.00009315802,0.00037810774,0.00000499022,0.00030863882,0.0030940853],"genre_scores_gemma":[0.42893568,0.00000103543,0.57050365,0.00007712237,0.00006729,0.00017536587,0.000011332116,0.000008812326,0.00021972896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911076,0.000015166064,0.00020121648,0.00029459046,0.00012436497,0.00025392394],"domain_scores_gemma":[0.9993062,0.00006633595,0.00007700557,0.00047119652,0.00003596649,0.00004329224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019755297,0.000113857255,0.00014754379,0.000072982344,0.00014853572,0.00015096167,0.0006470805,0.000054773594,0.0000031749605],"category_scores_gemma":[0.0000056867757,0.00009147761,0.00005047703,0.0001509981,0.00001756001,0.0004043209,0.00016068397,0.00006262826,0.000006641392],"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":[0.000029724259,0.0003986881,0.0028944004,0.00032944258,0.000022926797,0.000050975566,0.0003289116,0.00026073924,0.39538273,0.4410879,0.017329233,0.14188431],"study_design_scores_gemma":[0.0008003024,0.00017497558,0.001334653,0.00016563525,0.000009395421,0.00016076698,0.000020117053,0.3116389,0.6294163,0.031452324,0.024163896,0.000662775],"about_ca_topic_score_codex":0.00014053326,"about_ca_topic_score_gemma":0.000010729206,"teacher_disagreement_score":0.4259023,"about_ca_system_score_codex":0.000021822278,"about_ca_system_score_gemma":0.000018376346,"threshold_uncertainty_score":0.37303486},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006172488,0.0017943678,0.9929781,0.0013517835,0.0011091235,0.00035802243,0.000025479145,0.00020270623,0.0021186713],"genre_scores_gemma":[0.019701563,0.0005888104,0.9761098,0.0018181377,0.0011720369,0.000020403484,0.000017247838,0.000053683347,0.00051831134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996261,0.000032966553,0.00045486217,0.0016171047,0.00095412857,0.00067995104],"domain_scores_gemma":[0.9976316,0.00027471696,0.00022808988,0.0014500502,0.00014142487,0.0002741347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059478014,0.00057444186,0.0005844688,0.0005982049,0.00033727946,0.0007215359,0.0027144747,0.00033072112,0.000026476708],"category_scores_gemma":[0.000045466513,0.00047983188,0.00008716176,0.00033755534,0.00086014345,0.0013164472,0.0023376977,0.00069584546,0.00002645868],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007247043,0.000019524949,0.000053922417,0.000044164583,0.0000070495194,0.00007760124,0.0010666858,0.0017708893,0.00003714996,0.016532142,0.00007214615,0.98031145],"study_design_scores_gemma":[0.00043903693,0.00010037131,0.0001398579,0.0003717732,0.000008100615,0.00012086247,2.2778087e-7,0.8887021,0.00024417814,0.10070543,0.008372816,0.0007952343],"about_ca_topic_score_codex":0.00006500171,"about_ca_topic_score_gemma":0.0001593435,"teacher_disagreement_score":0.97951627,"about_ca_system_score_codex":0.00014003013,"about_ca_system_score_gemma":0.00026399727,"threshold_uncertainty_score":0.99976534},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044568586,0.00004992885,0.9898965,0.0033482127,0.0003951812,0.00036587266,0.000002955703,0.0003054345,0.0011790713],"genre_scores_gemma":[0.59285766,0.0000032913752,0.4049694,0.002012145,0.00013987422,0.000007246984,0.0000026946257,0.000004887236,0.0000027965812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734503,0.00005130247,0.00031670358,0.00086737185,0.0006254802,0.0007941258],"domain_scores_gemma":[0.99814624,0.00025656863,0.00006273997,0.0010167244,0.00018003558,0.0003377096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011638033,0.00022346077,0.00025877758,0.00016723099,0.00066691515,0.0010260824,0.0034226119,0.00007101248,0.0000115327875],"category_scores_gemma":[0.000036016394,0.00017667733,0.00008618936,0.0009946314,0.00090083684,0.0015867013,0.0008793991,0.00021844015,0.0000134033635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008986049,0.00006610977,0.00001914076,0.0000028015484,0.0000014731767,0.0000056050685,0.00013269774,0.00021220649,0.0004578625,0.7650108,0.0005327228,0.23354961],"study_design_scores_gemma":[0.0003016742,0.00044660206,0.0005226458,0.000089079076,0.000003886041,0.000030071777,0.0000038626736,0.78280777,0.0015907581,0.21307349,0.0008669226,0.00026327203],"about_ca_topic_score_codex":0.0000052214286,"about_ca_topic_score_gemma":7.9065575e-7,"teacher_disagreement_score":0.7825955,"about_ca_system_score_codex":0.000055738656,"about_ca_system_score_gemma":0.00007726881,"threshold_uncertainty_score":0.9894536},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031038113,0.000023003151,0.9936143,0.0013749087,0.00057491026,0.0007183829,0.000060862963,0.00026426633,0.0002655646],"genre_scores_gemma":[0.010955561,0.000017835931,0.98538506,0.0013911959,0.0005807347,0.0001824378,0.0013689074,0.000019301115,0.00009897198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984009,0.000114717484,0.00021213214,0.000581207,0.000418906,0.00027213508],"domain_scores_gemma":[0.9989296,0.00006236591,0.00011727158,0.0003909397,0.00038220428,0.00011761848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009173653,0.0001763269,0.00017138815,0.00013001374,0.00032359152,0.00032038675,0.0003603089,0.00014254815,0.000048674567],"category_scores_gemma":[0.00003455844,0.00014543385,0.000077242046,0.00025793022,0.0000122488045,0.0015014551,0.000052249,0.0001669414,0.000044141114],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003581212,0.0001950109,0.0000040211708,0.0000040394184,0.000013917216,0.0000016085278,0.00010388664,0.0008376438,0.0016302208,0.0005788857,0.0016137665,0.99498117],"study_design_scores_gemma":[0.0032033708,0.00055787596,0.00072444306,0.00005331157,0.000022721022,0.00002614779,0.000016795408,0.9756023,0.012808522,0.005297032,0.0013949868,0.00029245424],"about_ca_topic_score_codex":0.000028836886,"about_ca_topic_score_gemma":0.000008110759,"teacher_disagreement_score":0.99468875,"about_ca_system_score_codex":0.00015208058,"about_ca_system_score_gemma":0.00008396258,"threshold_uncertainty_score":0.59306204},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033812975,0.000015329751,0.98865783,0.004122102,0.0009333145,0.00027730118,0.0000028455129,0.00021857739,0.0023913884],"genre_scores_gemma":[0.41514713,0.000002628316,0.58324367,0.0009787601,0.00051478454,0.000004164083,0.000002120515,0.000008770226,0.00009800615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969891,0.0001008798,0.00028082271,0.001002861,0.0009420881,0.0006842876],"domain_scores_gemma":[0.99764246,0.00057835854,0.00008755025,0.0010895513,0.00011245862,0.00048965245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001795282,0.00023569091,0.00026073345,0.00015761165,0.00049470074,0.0007778833,0.0031783017,0.00006736085,0.00007109394],"category_scores_gemma":[0.0001500031,0.00017242579,0.000093182025,0.0007321505,0.0008562891,0.0008334652,0.0008296736,0.00017028631,0.00017548563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000228098,0.000023325832,0.0000023215282,0.0000039288043,0.0000020843981,0.0000017668821,0.000117232106,0.00013770096,0.0008260895,0.90946203,0.0010503287,0.08835041],"study_design_scores_gemma":[0.00037742476,0.00091875164,0.00010285178,0.000049340837,0.000003726549,0.000014149693,0.0000012920278,0.61018986,0.015569494,0.36782256,0.0046934346,0.00025712454],"about_ca_topic_score_codex":0.000005713047,"about_ca_topic_score_gemma":1.207711e-7,"teacher_disagreement_score":0.61005217,"about_ca_system_score_codex":0.00006610249,"about_ca_system_score_gemma":0.00018268128,"threshold_uncertainty_score":0.7501146},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.1641435e-7,0.0013100026,0.99042106,0.0015997214,0.003943378,0.0007259141,0.00001254353,0.0001681086,0.0018186835],"genre_scores_gemma":[0.000514956,0.0000765534,0.9935132,0.001858883,0.0018616628,0.000010830796,0.000009424435,0.000040043247,0.002114445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602455,0.000015443402,0.0004850247,0.001499116,0.0011324448,0.0008434443],"domain_scores_gemma":[0.9957283,0.0013609837,0.0002858677,0.002107409,0.00025352725,0.0002639267],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013348768,0.00055609894,0.0004626374,0.0005436346,0.00054261816,0.0008262185,0.0056546866,0.00034898144,0.000027594786],"category_scores_gemma":[0.00008106658,0.0003761214,0.00019797627,0.00062147964,0.0004033557,0.0006470863,0.0020838177,0.00076508103,0.00003770554],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058510395,0.000008389033,0.0000026494408,0.000010734326,0.000010135173,0.00002337192,0.00024341593,0.004717106,0.000022274566,0.01908928,0.0004871859,0.9753796],"study_design_scores_gemma":[0.00040247227,0.00016889384,0.00005241374,0.00020089075,0.0000127381345,0.000085934225,1.8567205e-7,0.8273931,0.00062798697,0.10806943,0.062381364,0.00060459855],"about_ca_topic_score_codex":0.00008853794,"about_ca_topic_score_gemma":0.000065764056,"teacher_disagreement_score":0.974775,"about_ca_system_score_codex":0.00019851138,"about_ca_system_score_gemma":0.00076361094,"threshold_uncertainty_score":0.99986905},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012136295,0.00024600537,0.98581904,0.000165567,0.0004623673,0.00013264932,0.000024558627,0.00019246753,0.0008210201],"genre_scores_gemma":[0.22938973,0.000011817387,0.7696816,0.00054388517,0.00017967762,9.184095e-7,0.00009132247,0.00001536761,0.00008571831],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998136,0.000044750464,0.00028763173,0.00073656644,0.0004060205,0.00038903198],"domain_scores_gemma":[0.9977103,0.00014870448,0.00010020512,0.0017577377,0.00006604089,0.00021700696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074808946,0.00018793021,0.00019167579,0.00013037205,0.00030763756,0.0002766566,0.0016871664,0.00008718284,0.000035839246],"category_scores_gemma":[0.000019154997,0.00014669362,0.000022909288,0.0002836001,0.00007865906,0.0012455776,0.0022340065,0.00015763094,0.000012266753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003968564,0.00037671774,0.001886612,0.000065895154,0.000026904401,0.0002169754,0.00019507075,0.00049600436,0.008511778,0.008835486,0.008829452,0.9705194],"study_design_scores_gemma":[0.00052587484,0.00003357404,0.0020269607,0.00006611717,0.000006431275,0.00002931477,0.000024038265,0.9801169,0.006246072,0.00043973187,0.010233922,0.0002510747],"about_ca_topic_score_codex":0.00025996278,"about_ca_topic_score_gemma":0.00002126067,"teacher_disagreement_score":0.9796209,"about_ca_system_score_codex":0.000024302853,"about_ca_system_score_gemma":0.00005729024,"threshold_uncertainty_score":0.5981992},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.756903,0.0012361578,0.07264776,0.037616394,0.0033356042,0.003812237,0.000012334755,0.0007929674,0.12364358],"genre_scores_gemma":[0.9512584,0.00002533878,0.047072764,0.00031585892,0.00006228636,0.00006029577,2.4874737e-7,0.0000062641175,0.0011985076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923503,0.000002520733,0.00014511478,0.00018280245,0.00027492642,0.00015957846],"domain_scores_gemma":[0.99949676,0.000014730991,0.00012041873,0.00019577092,0.00012462166,0.000047709553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110680885,0.00007911429,0.000091655194,0.000028741755,0.00008349166,0.000108447435,0.0012610446,0.000021734044,0.00003482133],"category_scores_gemma":[0.000024700155,0.000045504526,0.000049599636,0.00017799786,0.000028574528,0.0006187936,0.0009413285,0.0000696464,0.000058705802],"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":[0.000007013956,0.0003389601,0.005326307,0.00011429047,0.00005377529,4.6436472e-7,0.001745618,0.000021212387,0.2585592,0.32022998,0.23790045,0.17570272],"study_design_scores_gemma":[0.0011427408,0.00020901575,0.033985104,0.0002630177,0.000020197005,0.000038306574,0.00027853475,0.049332887,0.74552506,0.0898834,0.07878714,0.0005346172],"about_ca_topic_score_codex":0.000070750015,"about_ca_topic_score_gemma":1.4311335e-7,"teacher_disagreement_score":0.48696584,"about_ca_system_score_codex":0.000020190078,"about_ca_system_score_gemma":0.000010738056,"threshold_uncertainty_score":0.23433557},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012393787,0.00010667845,0.9850484,0.00015706588,0.00015209828,0.00005827508,0.0000026669559,0.0002399112,0.0018411325],"genre_scores_gemma":[0.78560907,0.00013532354,0.2130142,0.00035485692,0.00005032847,0.000006284279,0.000004679201,0.0000049124055,0.00082035747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993062,0.000020778169,0.0001001239,0.00027479662,0.00013850753,0.00015960903],"domain_scores_gemma":[0.99930507,0.000043422817,0.000022237331,0.00047484165,0.00003425428,0.00012019897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006195614,0.000085845444,0.000081026636,0.000066224784,0.00009051171,0.000108179986,0.00038449428,0.00003116458,0.00023244575],"category_scores_gemma":[0.000017763796,0.000056574925,0.0000129636555,0.00027234238,0.00002290053,0.0008147948,0.00018781722,0.00006505235,0.00003484095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008726492,0.00034832905,0.0012958546,0.000013004208,0.0000121576395,0.00007155423,0.001185301,0.00006478178,0.0010289439,0.09603109,0.0076099113,0.89233035],"study_design_scores_gemma":[0.00032662932,0.0002618788,0.003109462,0.000013720896,0.000001937349,0.000027826009,0.000022976415,0.98101455,0.0007352739,0.0009363362,0.013354676,0.00019475532],"about_ca_topic_score_codex":0.000045001052,"about_ca_topic_score_gemma":0.000009745651,"teacher_disagreement_score":0.98094976,"about_ca_system_score_codex":0.000004156277,"about_ca_system_score_gemma":0.000006558739,"threshold_uncertainty_score":0.25451177},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018322412,0.00014243001,0.935679,0.0005763733,0.00085871224,0.00033619528,0.0000068438267,0.0004892977,0.043588728],"genre_scores_gemma":[0.9188123,0.0000728739,0.079745024,0.00021013693,0.000071414506,0.00003797869,0.0000011811986,0.000017745546,0.001031386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978279,0.000020542815,0.0002612207,0.0008085739,0.00048728226,0.00059447635],"domain_scores_gemma":[0.99862075,0.000061054816,0.0002049294,0.00036224723,0.0004977246,0.00025328578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003631201,0.0003122784,0.00029245927,0.00010207417,0.0003420184,0.00063572504,0.0012170628,0.00012166599,0.00006210546],"category_scores_gemma":[0.0001361141,0.00028397134,0.00006874162,0.000536537,0.00010395088,0.0018569017,0.00026559105,0.00032207437,0.00015915859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001412224,0.00009797959,0.0015906435,0.000037416547,0.000025159925,0.000013680091,0.0018427542,0.000009505169,0.028941017,0.9442399,0.0124144545,0.010773373],"study_design_scores_gemma":[0.0039661643,0.001505755,0.005812238,0.0011955022,0.000084400366,0.00043076163,0.0024810624,0.338587,0.48795915,0.068623476,0.08487515,0.004479347],"about_ca_topic_score_codex":0.000038141476,"about_ca_topic_score_gemma":0.000005028959,"teacher_disagreement_score":0.90048987,"about_ca_system_score_codex":0.000067697845,"about_ca_system_score_gemma":0.00014606697,"threshold_uncertainty_score":0.99996126},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06856574,0.000038007274,0.9308205,0.00007838298,0.000069010224,0.00009812196,0.0000028405696,0.00010556722,0.00022180575],"genre_scores_gemma":[0.5862424,0.0000014697215,0.41362146,0.00010041368,0.000018143279,0.0000014041409,0.0000056548474,0.0000032464816,0.0000058189735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998944,0.000061434126,0.0002084662,0.00027556307,0.0003622518,0.00014827636],"domain_scores_gemma":[0.9992629,0.00002889489,0.00011072363,0.00032183068,0.00019748163,0.0000781663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017404227,0.00010014543,0.0001468475,0.00006834291,0.00017210306,0.00003698893,0.00043638985,0.000046360594,0.000005876938],"category_scores_gemma":[0.000020057843,0.00008075154,0.000034866112,0.0002258925,0.0000526982,0.00073730573,0.00005986578,0.00006694072,0.0000023330088],"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":[0.00018094332,0.0038930927,0.013543818,0.00032248336,0.00007402959,0.000086469285,0.00391929,0.77744275,0.0708158,0.00725661,0.0024473448,0.12001734],"study_design_scores_gemma":[0.00036375574,0.00007974578,0.003514258,0.000021963497,0.0000030310705,0.0000098967885,0.000010476651,0.9713836,0.023284104,0.0010747552,0.00012177813,0.00013267275],"about_ca_topic_score_codex":0.00014947563,"about_ca_topic_score_gemma":0.0000106673915,"teacher_disagreement_score":0.51767665,"about_ca_system_score_codex":0.000015762032,"about_ca_system_score_gemma":0.00015046138,"threshold_uncertainty_score":0.32929522},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031974826,0.00088760053,0.96251905,0.00192448,0.0014487619,0.00005676291,0.0000022475137,0.0000435877,0.0011426647],"genre_scores_gemma":[0.33072522,0.00068372494,0.6649441,0.00042823632,0.0019172174,0.0000023288692,0.0000022217314,0.000029893154,0.0012670193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841523,0.000058219135,0.000423128,0.00019441318,0.000627315,0.00028166498],"domain_scores_gemma":[0.9986703,0.000088821726,0.00036086622,0.0004215573,0.0002480759,0.0002104284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532933,0.00014315093,0.0002518429,0.00020477582,0.00011548665,0.00017640102,0.0010939704,0.000057945195,0.000041914845],"category_scores_gemma":[0.000050103572,0.000102865,0.00014624115,0.0004328592,0.000036161047,0.00053914497,0.0002498618,0.00025509074,0.00004409507],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010549518,0.0014319723,0.0013720036,0.000017899554,0.00016292355,0.003005179,0.002184517,0.016552538,0.0044152737,0.014283508,0.0406463,0.9158224],"study_design_scores_gemma":[0.0022025288,0.0010051011,0.011549741,0.0001920001,0.000033072312,0.0041371975,0.00021211393,0.7194228,0.0034392069,0.0024064046,0.25485712,0.00054273155],"about_ca_topic_score_codex":0.000015066794,"about_ca_topic_score_gemma":0.0000013314365,"teacher_disagreement_score":0.9152797,"about_ca_system_score_codex":0.000054003514,"about_ca_system_score_gemma":0.000094984636,"threshold_uncertainty_score":0.4194713},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016514633,0.000023302691,0.99187785,0.00045232588,0.0003651815,0.000071483344,0.0000064948,0.00012517272,0.0054267175],"genre_scores_gemma":[0.050903667,0.000016074462,0.9460119,0.0028021524,0.00009243632,0.0000032184914,0.00007290354,0.000009196804,0.00008843834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989609,0.000020864725,0.00034737063,0.00019596839,0.00022563881,0.0002492557],"domain_scores_gemma":[0.9983191,0.00014560927,0.00014138,0.0013063952,0.000029504987,0.000058033995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006869928,0.00010332005,0.00013461434,0.00008914358,0.000101722595,0.00021432954,0.0018795483,0.00005148675,0.000004900161],"category_scores_gemma":[0.00033557418,0.00009184154,0.000015044556,0.00028588143,0.000031650558,0.0018128816,0.0017660909,0.00014648525,0.00007453742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011941856,0.000023881988,0.00022633842,0.000034419943,0.0000021883618,0.000002098033,0.0011291533,0.00007090769,0.000005369827,0.0074678943,0.0152119,0.97582465],"study_design_scores_gemma":[0.00019013474,0.000018036168,0.0005526897,0.00006072214,0.0000010930582,0.000045134228,0.00004494898,0.92085254,0.00007178483,0.0006724481,0.07735855,0.00013189614],"about_ca_topic_score_codex":0.00014214749,"about_ca_topic_score_gemma":0.000011497549,"teacher_disagreement_score":0.97569275,"about_ca_system_score_codex":0.000018414508,"about_ca_system_score_gemma":0.000030996653,"threshold_uncertainty_score":0.37451893},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6162519,0.00010234551,0.37325093,0.002089561,0.00010845953,0.00044752948,0.000014473955,0.00024173161,0.007493105],"genre_scores_gemma":[0.6910719,0.000007842008,0.30810696,0.00011030814,0.00010176948,0.000010320879,0.0000017944394,0.00001409388,0.00057498907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988816,0.0000036419642,0.00020665556,0.00023706742,0.00044872626,0.00022232732],"domain_scores_gemma":[0.9994037,0.00007053419,0.00015616308,0.00019304134,0.00013002336,0.000046535086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020273525,0.00013310931,0.00019220797,0.00001318461,0.00016653682,0.00009812182,0.0010011467,0.00006337849,0.000020453519],"category_scores_gemma":[0.000017928707,0.000075311866,0.00015201676,0.0002626855,0.00017295052,0.0005152405,0.0005658376,0.00014358565,0.000008201624],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003438255,0.00057396916,0.001612896,0.00043350944,0.000081412014,0.0000025118227,0.0014571917,0.000049392864,0.028792515,0.9205103,0.045063533,0.001388402],"study_design_scores_gemma":[0.0028100784,0.00037401286,0.006547341,0.00085702504,0.00015318116,0.00011106901,0.0011350211,0.25345233,0.12880157,0.60033756,0.004426252,0.0009945581],"about_ca_topic_score_codex":0.00002156458,"about_ca_topic_score_gemma":3.6433053e-7,"teacher_disagreement_score":0.32017273,"about_ca_system_score_codex":0.00002609993,"about_ca_system_score_gemma":0.000024367664,"threshold_uncertainty_score":0.30711287},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073869905,0.00010235922,0.07209414,0.00016935416,0.0006192833,0.00019935521,0.0000100057005,0.000066586836,0.92600024],"genre_scores_gemma":[0.013860918,0.00010656603,0.028692875,0.0006217896,0.00015490617,0.0000010113876,0.0001165983,0.000047012425,0.9563983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998616,0.00012498259,0.00018049697,0.0004033688,0.00044960988,0.00022558605],"domain_scores_gemma":[0.9982034,0.00051695836,0.00037502858,0.0006589377,0.00018009452,0.00006559258],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024432878,0.00021094349,0.00020449508,0.00016497463,0.00018713124,0.00009122328,0.0015338884,0.00018490702,0.0055138106],"category_scores_gemma":[0.00007329609,0.00016710274,0.00010544561,0.00060442684,0.000030447889,0.000602482,0.00026631847,0.0004105394,0.00007223014],"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":[0.00021051831,0.00012296755,0.000010275077,0.00006424948,0.00008688205,0.0001649027,0.0013071529,0.000076965116,0.00019487858,0.18321908,0.0036210455,0.8109211],"study_design_scores_gemma":[0.00038914374,0.00015776602,0.00019116708,0.00038855808,0.000062295876,0.0000060146344,0.00330313,0.0026360122,0.0018638048,0.0005732824,0.99008846,0.0003403555],"about_ca_topic_score_codex":0.00014906019,"about_ca_topic_score_gemma":0.00005660862,"teacher_disagreement_score":0.9864674,"about_ca_system_score_codex":0.00006263152,"about_ca_system_score_gemma":0.00008799107,"threshold_uncertainty_score":0.9953953},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033428532,0.000034108238,0.99060404,0.00017451742,0.00020603137,0.00008280159,0.0000053788135,0.000100851445,0.005449444],"genre_scores_gemma":[0.26424783,0.000006300518,0.73346794,0.00037525,0.000058092897,0.0000061513224,0.0000084738385,0.0000060490966,0.0018238977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993518,0.000025247322,0.00008180339,0.00021827077,0.00014635397,0.00017650217],"domain_scores_gemma":[0.9995811,0.00007611962,0.000033323828,0.00021790327,0.00003277576,0.00005875687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019693357,0.00006724536,0.00006752769,0.000041598865,0.00016272992,0.00014780177,0.00050933176,0.00003184496,0.00003495494],"category_scores_gemma":[0.000019654835,0.000053295124,0.000029667484,0.0001260142,0.000024965704,0.00050553126,0.00012520947,0.00004325501,0.000015153534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021548751,0.000028009452,0.00031766892,0.0000068925297,0.000012428416,0.0000047454682,0.0005847428,0.000102644604,0.00038912168,0.95798707,0.008633895,0.031930618],"study_design_scores_gemma":[0.0012366994,0.00024113404,0.00038275062,0.00003877668,0.000010982171,0.00005223278,0.0009678279,0.100134,0.011628412,0.041948684,0.8427899,0.0005686236],"about_ca_topic_score_codex":0.000017189652,"about_ca_topic_score_gemma":0.0000025328638,"teacher_disagreement_score":0.9160384,"about_ca_system_score_codex":0.000012966611,"about_ca_system_score_gemma":0.000053385782,"threshold_uncertainty_score":0.21733122},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053095655,0.00026330934,0.99484724,0.0010048941,0.00037142367,0.00015221753,0.000007697402,0.000248074,0.0025741819],"genre_scores_gemma":[0.23460035,0.000058365145,0.7611203,0.0015730541,0.00079075526,0.000048076,0.00007425083,0.000012317122,0.0017224966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991904,0.00001829794,0.0001550527,0.00027917325,0.00014332315,0.00021377316],"domain_scores_gemma":[0.9993086,0.00008929027,0.00004421353,0.0004163086,0.00005201729,0.00008957224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012347617,0.00009404888,0.000090665366,0.000037002806,0.00020964202,0.000083130806,0.00050809927,0.000059075424,0.00006513584],"category_scores_gemma":[0.0000052216938,0.0000711182,0.00004993009,0.0001057314,0.000014311525,0.0006969416,0.0002934799,0.00007247073,0.00003848785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021829539,0.00011650182,0.00010523118,0.0000032445896,0.000011518336,0.0000016565939,0.000048586673,0.016816484,0.00015693429,0.037559867,0.39686835,0.5482898],"study_design_scores_gemma":[0.0002317159,0.000045681132,0.00035133382,0.0000073430097,0.0000016149799,0.0000069521984,0.000003251306,0.7730096,0.00023925606,0.00081099855,0.22520527,0.00008698998],"about_ca_topic_score_codex":0.000013655263,"about_ca_topic_score_gemma":0.000005230119,"teacher_disagreement_score":0.7561931,"about_ca_system_score_codex":0.0000195919,"about_ca_system_score_gemma":0.0000168055,"threshold_uncertainty_score":0.2900116},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036811218,0.000063617794,0.9588457,0.0006202518,0.0006234163,0.0002662285,0.0003687411,0.0003184321,0.0020824228],"genre_scores_gemma":[0.08991993,0.000007640304,0.90827954,0.00082169485,0.00009261989,0.000016883108,0.00006769147,0.000016286016,0.00077773683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786735,0.00015591357,0.0002849841,0.0008859454,0.00033246516,0.00047335154],"domain_scores_gemma":[0.9982696,0.00009802432,0.000083910636,0.0010509453,0.000087546825,0.00040998135],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002019307,0.00024120766,0.00025896932,0.00010688763,0.00023524545,0.00022659182,0.0011490647,0.000091407856,0.0011790497],"category_scores_gemma":[0.00006586291,0.00020675504,0.000052440388,0.00045485806,0.000033911714,0.0009967561,0.00038080502,0.00013344214,0.0005219537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087490196,0.0008523958,0.0030647183,0.000027654502,0.0002326589,0.00095243845,0.004453716,0.00061538635,0.25627708,0.13721387,0.053498346,0.54272425],"study_design_scores_gemma":[0.0013737804,0.0005116411,0.004690836,0.0000747061,0.000011422685,0.00025978129,0.0001169161,0.60068864,0.29957438,0.027847027,0.063516326,0.0013345551],"about_ca_topic_score_codex":0.00036014008,"about_ca_topic_score_gemma":0.00008664591,"teacher_disagreement_score":0.6000732,"about_ca_system_score_codex":0.0001135359,"about_ca_system_score_gemma":0.00013161282,"threshold_uncertainty_score":0.999734},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013122451,0.0010466662,0.99495286,0.0005454665,0.00045164578,0.0004762967,0.000009919913,0.00005111498,0.001153792],"genre_scores_gemma":[0.8531061,0.00010999069,0.1455445,0.0002329611,0.00016417069,0.00013951697,0.000010777783,0.000011118269,0.0006808886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988036,0.00006581896,0.00019577987,0.00022282115,0.0005699323,0.0001420258],"domain_scores_gemma":[0.9986304,0.00027915268,0.000110832596,0.00062417286,0.00031844148,0.000036970858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068662065,0.000083318606,0.00010815704,0.000037777543,0.00016466225,0.00006152405,0.00077496324,0.000037617683,0.0001266991],"category_scores_gemma":[0.000046949408,0.000046694233,0.000056635392,0.0001701579,0.000038299157,0.00031531695,0.00022869291,0.00005083454,0.000013626889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034716722,0.00009342821,0.000036159,0.000007843476,0.000012101392,2.508832e-7,0.00021184198,0.00091175083,0.000716382,0.008575198,0.012491256,0.97694033],"study_design_scores_gemma":[0.0006043383,0.00004794286,0.0008071303,0.000018803456,0.00001643736,0.0000038522994,0.000018264607,0.9846759,0.0033073274,0.002171629,0.00825726,0.000071124115],"about_ca_topic_score_codex":0.000036910908,"about_ca_topic_score_gemma":0.0000027094925,"teacher_disagreement_score":0.9837641,"about_ca_system_score_codex":0.000017079137,"about_ca_system_score_gemma":0.000017525144,"threshold_uncertainty_score":0.19041355},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025829585,0.000027786149,0.95750916,0.0066779694,0.000069912916,0.00009074454,4.892454e-7,0.00012837903,0.009665949],"genre_scores_gemma":[0.9779862,0.0000080738,0.019392472,0.0021205305,0.000044622888,0.0000035549685,0.0000017099148,0.0000021441804,0.00044067044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938625,0.000016478738,0.00008603573,0.00019295153,0.00019027625,0.00012801717],"domain_scores_gemma":[0.99951786,0.00003107747,0.000019224879,0.00036640235,0.000030501991,0.000034917473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000105747175,0.00006815736,0.000048285314,0.000022785844,0.00014423698,0.00013332443,0.00051688356,0.00002476958,0.000012645176],"category_scores_gemma":[0.000012637104,0.000036152815,0.000019757474,0.00012123739,0.000004986684,0.00030628667,0.000063068,0.000084079096,0.00004072112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025974392,0.0006347404,0.0000122416595,0.000017223818,0.0000056279005,0.000014644457,0.001352483,0.116209045,0.0066936137,0.5814823,0.01273675,0.28081533],"study_design_scores_gemma":[0.00006819062,0.0000724212,0.000044204156,0.000011746435,9.1646314e-7,0.000001241345,0.0000121742,0.98977673,0.0027312993,0.006710364,0.00050758576,0.000063125204],"about_ca_topic_score_codex":0.000009387462,"about_ca_topic_score_gemma":4.6995314e-7,"teacher_disagreement_score":0.95215666,"about_ca_system_score_codex":0.000009769383,"about_ca_system_score_gemma":0.000018041428,"threshold_uncertainty_score":0.14742689},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004109207,0.000111031484,0.99258786,0.00084072095,0.0013467522,0.00028833732,0.00005345677,0.00021258014,0.00045007607],"genre_scores_gemma":[0.49348727,0.000003770395,0.50587094,0.0003240137,0.00027668057,0.0000058369183,0.0000146763505,0.000007942546,0.000008899356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672157,0.000080274964,0.0002683551,0.001208485,0.0010306733,0.0006906668],"domain_scores_gemma":[0.9958361,0.0003703256,0.00008946449,0.0027966318,0.00034354572,0.0005639491],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001981352,0.00022307779,0.0002624399,0.00033472286,0.0003594848,0.0007825394,0.008091088,0.00006851821,0.000009685235],"category_scores_gemma":[0.00042371085,0.00016619236,0.0000467169,0.0017185118,0.0012444356,0.0020998332,0.0055626403,0.00017277486,0.000034741475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016117472,0.0000507285,0.000024425766,0.000009515894,0.0000032751498,0.0000068034296,0.00014057629,0.0005536597,0.00006553141,0.92588735,0.0037018526,0.06954015],"study_design_scores_gemma":[0.00040819688,0.00015947342,0.00019489214,0.000016139833,0.000004175765,0.000025503365,0.000004684697,0.8058892,0.0012973177,0.1904259,0.0013486539,0.00022589664],"about_ca_topic_score_codex":0.00001812637,"about_ca_topic_score_gemma":9.105839e-7,"teacher_disagreement_score":0.8053355,"about_ca_system_score_codex":0.00006453526,"about_ca_system_score_gemma":0.0003195212,"threshold_uncertainty_score":0.9972756},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033082895,0.000550287,0.96426666,0.0008564043,0.00012940432,0.00038962238,0.000012617296,0.000035114754,0.00067697605],"genre_scores_gemma":[0.83535993,0.00007560316,0.16433848,0.00013141328,0.000028090246,0.000032282656,0.000010117215,0.0000033070041,0.000020790168],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992255,0.000057116395,0.0002046259,0.00018055832,0.00017873032,0.00015345984],"domain_scores_gemma":[0.9994052,0.00020571752,0.00008027021,0.0002604765,0.00002959762,0.000018724715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195472,0.0000745434,0.000097016185,0.000079901314,0.00008999903,0.00005349312,0.00054566737,0.000015229428,0.000040168947],"category_scores_gemma":[0.000009653432,0.00004391466,0.000035834164,0.00018897267,0.00002849802,0.0006442228,0.00014469775,0.00005789261,0.0000023866542],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000984639,0.0001228389,0.00052620855,0.0000776828,0.000003660891,0.0000049545683,0.002499065,0.00023403116,0.011885634,0.015022169,0.0021102072,0.9675037],"study_design_scores_gemma":[0.0013494433,0.0003405639,0.011357793,0.00008191125,0.000006797614,0.000022367349,0.00097193645,0.96220344,0.013140001,0.0054342453,0.004884305,0.00020721399],"about_ca_topic_score_codex":0.000043654167,"about_ca_topic_score_gemma":0.000018571018,"teacher_disagreement_score":0.9672965,"about_ca_system_score_codex":0.000008655287,"about_ca_system_score_gemma":0.0000048624875,"threshold_uncertainty_score":0.17907879},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040615015,0.00015496612,0.95691264,0.00004671009,0.0005982094,0.0001615888,0.000010985818,0.00017729524,0.0013225934],"genre_scores_gemma":[0.82193506,0.000007257849,0.17741176,0.00037162454,0.00004276462,0.0000043145033,0.000004328911,0.000015397776,0.00020747256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981609,0.00013643951,0.00031113162,0.000557616,0.0004510056,0.00038293505],"domain_scores_gemma":[0.9987237,0.00008483067,0.00011219232,0.00083612074,0.00008592517,0.00015725745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030489656,0.00021811675,0.00023680001,0.000079994614,0.00030377446,0.0003753612,0.00082045584,0.0000752103,0.00016156325],"category_scores_gemma":[0.00001734615,0.00017028957,0.000082053986,0.00010469147,0.0000334642,0.0011703375,0.0006061402,0.00019722867,0.0001014359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011805233,0.00055448536,0.001368135,0.000080829246,0.00006707405,0.00025947514,0.0018332744,0.001939409,0.073941305,0.022629457,0.0020721024,0.89524263],"study_design_scores_gemma":[0.0014755122,0.00004073355,0.0011357754,0.00020969515,0.000013005649,0.00013864366,0.00031646987,0.94118226,0.045803722,0.0038164128,0.005184365,0.0006833927],"about_ca_topic_score_codex":0.0006323458,"about_ca_topic_score_gemma":0.000012258635,"teacher_disagreement_score":0.93924284,"about_ca_system_score_codex":0.000051036932,"about_ca_system_score_gemma":0.00004710904,"threshold_uncertainty_score":0.6944207},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12256483,0.00035721532,0.8762266,0.00011669425,0.0005990362,0.00003784159,0.0000014432256,0.00004513709,0.000051180104],"genre_scores_gemma":[0.6460477,0.000016845841,0.35369003,0.000021376107,0.00020768613,5.2783105e-7,8.038297e-7,0.000011618488,0.0000033664078],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893814,0.000023713292,0.00032430186,0.00014005868,0.00036597997,0.00020777559],"domain_scores_gemma":[0.9989158,0.00005601093,0.0002064012,0.0003096819,0.00026806953,0.00024405139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003628225,0.00012730199,0.00018900132,0.00045147692,0.00006929984,0.00016422154,0.0007016929,0.000058660215,0.0000014947177],"category_scores_gemma":[0.000050964827,0.00011282303,0.00011096116,0.0005515192,0.000018780893,0.0013465732,0.00018305938,0.00028331563,0.0000013338921],"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":[0.00003510455,0.00023967156,0.0077214413,0.00008544621,0.00029986317,0.00032159366,0.0048299576,0.84728956,0.07822069,0.03461881,0.0008867124,0.025451168],"study_design_scores_gemma":[0.00078569225,0.00007274232,0.0020675035,0.00020448098,0.000025258818,0.00030069673,0.0002566214,0.98782825,0.00053242245,0.00039151232,0.0072926306,0.00024215631],"about_ca_topic_score_codex":0.0000192625,"about_ca_topic_score_gemma":0.0000011671027,"teacher_disagreement_score":0.5234829,"about_ca_system_score_codex":0.00005620189,"about_ca_system_score_gemma":0.00008676997,"threshold_uncertainty_score":0.46007895},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011156835,0.000084360596,0.9964019,0.00037793297,0.00006622707,0.00011109369,0.000004161901,0.00017145787,0.0026712955],"genre_scores_gemma":[0.17758475,0.0000022182412,0.8202953,0.00048020895,0.00021628402,0.000017593577,0.000006964746,0.000006740555,0.0013899668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931043,0.000004196925,0.00011470765,0.00025231772,0.00013071942,0.00018759945],"domain_scores_gemma":[0.99962956,0.000036313057,0.00003283566,0.0001921298,0.000044896937,0.000064295375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000037939528,0.000081333295,0.00008125859,0.000030401672,0.0001166977,0.00051982416,0.00045802776,0.00002683696,0.000049858394],"category_scores_gemma":[0.0000018873567,0.000060131173,0.000040109964,0.00009127613,0.000015205922,0.0011807195,0.0002061418,0.000037975627,0.00006468305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014089353,0.00005562369,0.000020919799,0.000007435058,0.0000023876214,0.0000026126143,0.00011144941,0.000108260094,0.000008271331,0.0038929123,0.020086275,0.97570246],"study_design_scores_gemma":[0.0002570864,0.000064898646,0.000051039424,0.000011551836,7.771993e-7,0.000010423833,0.000002419405,0.95676917,0.000022111159,0.0012268313,0.04148059,0.00010311124],"about_ca_topic_score_codex":0.0000011949928,"about_ca_topic_score_gemma":1.6542921e-7,"teacher_disagreement_score":0.97559935,"about_ca_system_score_codex":0.000007352064,"about_ca_system_score_gemma":0.000007859265,"threshold_uncertainty_score":0.5012676},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015405209,0.000062821135,0.997447,0.00032897355,0.00010484649,0.00019452664,0.000021124413,0.00019847146,0.00010170071],"genre_scores_gemma":[0.07247922,0.000037387286,0.92720747,0.00018247103,0.000008906446,0.000026335889,0.000026811089,0.0000035909625,0.000027809934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990159,0.000017618955,0.00031198293,0.00018499051,0.00028203867,0.000187425],"domain_scores_gemma":[0.9992142,0.000014541406,0.0001507416,0.00047193596,0.00010334519,0.000045251785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009630743,0.00010241044,0.00011285188,0.00023210637,0.00006585502,0.000049950486,0.000541309,0.00005931172,0.00013348619],"category_scores_gemma":[0.000011034754,0.000087405744,0.000032401807,0.00048908876,0.000040274434,0.001211697,0.00027509194,0.000049049893,0.0000829832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.7330884e-7,0.00003186576,0.00014954428,0.0000067915416,0.000009151532,0.000003212309,0.00029362304,0.000010884699,0.004438608,0.006181002,0.00068107166,0.98819387],"study_design_scores_gemma":[0.0013659934,0.0003240222,0.00053201313,0.000034839075,0.000011155425,0.00005529236,0.00047941017,0.75332713,0.22723716,0.0033608626,0.012887825,0.00038429353],"about_ca_topic_score_codex":0.00016120764,"about_ca_topic_score_gemma":0.0000023478256,"teacher_disagreement_score":0.9878096,"about_ca_system_score_codex":0.00004128968,"about_ca_system_score_gemma":0.000016258176,"threshold_uncertainty_score":0.3564303},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62915164,0.00045923181,0.36717388,0.0002686324,0.0005050724,0.00004401263,0.000002735481,0.00010263753,0.0022921436],"genre_scores_gemma":[0.96199185,0.000019654839,0.037226975,0.00008063487,0.000080923724,7.8707205e-7,0.000010260644,0.0000022931604,0.0005866075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994952,0.00001722804,0.000101241385,0.00015913516,0.00013909746,0.00008806238],"domain_scores_gemma":[0.99955136,0.00003555012,0.000042233616,0.0003188968,0.000026764339,0.000025209909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000039987313,0.00005338231,0.00007602148,0.000040609888,0.000031205407,0.000037216334,0.0003256657,0.000028020164,0.00009020674],"category_scores_gemma":[0.000011128027,0.000038324208,0.000022751972,0.00016300431,0.000014233418,0.00047233072,0.00016905511,0.000063795924,0.000038384478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012922553,0.00015564171,0.0036501766,0.000010316335,0.000027485432,0.00004901901,0.0013003751,0.000028940438,0.10068514,0.009348195,0.009354208,0.8753776],"study_design_scores_gemma":[0.0013884216,0.00018385955,0.19580695,0.00015401262,0.000021591648,0.000082820676,0.0012342922,0.6602108,0.10930496,0.0062126955,0.024690658,0.0007089264],"about_ca_topic_score_codex":0.00080241775,"about_ca_topic_score_gemma":0.00003780917,"teacher_disagreement_score":0.87466866,"about_ca_system_score_codex":0.0000069416346,"about_ca_system_score_gemma":0.000012073362,"threshold_uncertainty_score":0.15628158},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002900997,0.00002561266,0.9933759,0.0012275005,0.0010214087,0.00017494848,0.0000055008245,0.00019059467,0.0036884511],"genre_scores_gemma":[0.0020465085,0.0000032715739,0.9929268,0.00047041432,0.00040164127,0.000011028673,0.0000107404385,0.000006620377,0.0041230265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990951,0.000008068624,0.00013923825,0.00033048133,0.00020763946,0.00021950676],"domain_scores_gemma":[0.9990506,0.000071497096,0.000040467276,0.0006201132,0.000054571832,0.00016273632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000171097,0.0001047099,0.00010603261,0.000057865702,0.00031017628,0.0001292231,0.001002691,0.000074225114,0.00013062496],"category_scores_gemma":[0.000020915395,0.00007630659,0.00005782548,0.00014833696,0.000011289381,0.000542344,0.002086406,0.00012170829,0.000045280347],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011456146,0.00001905036,0.0000067274123,0.0000011035017,0.0000017878068,0.0000014369814,0.00009705676,4.378622e-7,0.0029375711,0.017572358,0.02786962,0.9514917],"study_design_scores_gemma":[0.0005740842,0.00008764234,0.00023772535,0.0000056871104,0.0000025346417,0.000012871723,0.000004429395,0.561968,0.009164802,0.023739796,0.40402907,0.0001733351],"about_ca_topic_score_codex":0.00017342505,"about_ca_topic_score_gemma":0.0000617585,"teacher_disagreement_score":0.9513184,"about_ca_system_score_codex":0.000008111321,"about_ca_system_score_gemma":0.0000856536,"threshold_uncertainty_score":0.31116924},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004399247,0.000138776,0.9823339,0.015842441,0.0008044246,0.00012381033,0.000030171359,0.000035334673,0.00025123535],"genre_scores_gemma":[0.17780939,0.00005756514,0.8102451,0.0077799237,0.003795853,0.000012888959,0.000070736525,0.000019175595,0.00020937304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983898,0.00007233827,0.00045932404,0.00028991455,0.0006315574,0.00015706393],"domain_scores_gemma":[0.9977176,0.00028301636,0.0003307561,0.0010044023,0.0004741764,0.00019005273],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00044409605,0.00012671224,0.00015185805,0.00012205598,0.0001551509,0.0006557483,0.0066817272,0.000028227518,0.000014539023],"category_scores_gemma":[0.00002371093,0.00008717042,0.00005620933,0.00021184239,0.000030253368,0.0008641749,0.001645394,0.0002038377,0.00006095439],"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":[0.0000088023035,0.00008655343,0.00005889494,0.0000013397765,0.00007331037,0.0000029196365,0.00012351325,0.002988203,0.0019920273,0.017331911,0.42068967,0.5566429],"study_design_scores_gemma":[0.0002544001,0.000022957249,0.00032621328,0.000025135001,0.000006737443,0.000073079354,0.0000020375726,0.31679553,0.0002481041,0.0019042451,0.6802548,0.00008673864],"about_ca_topic_score_codex":0.000022834662,"about_ca_topic_score_gemma":0.0000034966663,"teacher_disagreement_score":0.5565561,"about_ca_system_score_codex":0.000033760378,"about_ca_system_score_gemma":0.0001386916,"threshold_uncertainty_score":0.9986926},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016472198,0.00009114516,0.9819116,0.0008460985,0.00022760122,0.00012458999,0.0000034949878,0.00006662162,0.00025667943],"genre_scores_gemma":[0.11105308,0.00004636985,0.88860106,0.00004570924,0.000077041135,0.000006878483,0.000051017338,0.000003455502,0.000115395764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993888,0.00001808474,0.0002701418,0.00007550442,0.00012550691,0.00012196146],"domain_scores_gemma":[0.99948174,0.00005136361,0.000100059966,0.0002795306,0.00006064368,0.000026646803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018046328,0.000059473794,0.00006954047,0.00003384839,0.00018164518,0.000083640196,0.00042929317,0.000032011085,0.000009388317],"category_scores_gemma":[0.000014400226,0.000038148795,0.00002561103,0.00017327089,0.00008015891,0.0004208107,0.000097848344,0.00005962945,0.000044062122],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027985222,0.000011426391,0.000027348195,0.000007758294,0.0000052402115,7.556695e-8,0.00057829084,0.00032413987,0.0000084376325,0.011987818,0.00044061246,0.98660606],"study_design_scores_gemma":[0.00012031453,0.00009140178,0.0012700553,0.000005939188,0.0000019392949,0.0000071688783,0.000037297243,0.9163115,0.000028280123,0.0073702447,0.074689545,0.00006629246],"about_ca_topic_score_codex":0.00001579022,"about_ca_topic_score_gemma":0.0000019150264,"teacher_disagreement_score":0.9865398,"about_ca_system_score_codex":0.000016116024,"about_ca_system_score_gemma":0.00002929854,"threshold_uncertainty_score":0.15556628},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008388737,0.00018488645,0.9726242,0.017678166,0.00047859145,0.00027298526,0.000012686624,0.00024888758,0.000110891226],"genre_scores_gemma":[0.758085,0.00012821192,0.22574928,0.015343399,0.00026169597,0.00019946911,0.00011348225,0.000028517363,0.00009094425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989207,0.00009116218,0.00023868207,0.00033564866,0.00013068534,0.00028315492],"domain_scores_gemma":[0.99636394,0.00013203632,0.00012296229,0.0032062216,0.000082832026,0.00009200706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003152654,0.00013708432,0.00012217865,0.0001245192,0.0007440976,0.00032087922,0.0025967876,0.000050589013,0.0000050923427],"category_scores_gemma":[0.000011649395,0.00013742267,0.00006580847,0.00029237475,0.00005439621,0.0015143394,0.00028844713,0.00018554476,0.000020528425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008666874,0.0008504236,0.0005808421,0.000048022153,0.00013459785,0.0000051441743,0.012348608,0.0020724044,0.3706816,0.005313589,0.0696721,0.538206],"study_design_scores_gemma":[0.00046569676,0.000074144984,0.0005395979,0.000033529075,0.000013625066,0.000010681284,0.00010213179,0.93009794,0.0009559789,0.0008878542,0.066552065,0.0002667505],"about_ca_topic_score_codex":0.00013879027,"about_ca_topic_score_gemma":0.000030758274,"teacher_disagreement_score":0.92802554,"about_ca_system_score_codex":0.0000735849,"about_ca_system_score_gemma":0.000042673437,"threshold_uncertainty_score":0.5723072},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033749355,0.00029966183,0.9805121,0.0009449208,0.00029872736,0.00005377997,0.0000060582724,0.00025118716,0.01729608],"genre_scores_gemma":[0.536224,0.00016695364,0.45625275,0.0011893086,0.0002031284,0.000003449351,0.00006269373,0.000012069795,0.0058856113],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913365,0.00002419797,0.000112141555,0.00036888942,0.00020496486,0.00015615931],"domain_scores_gemma":[0.9978277,0.000037598787,0.00002953497,0.0020167457,0.000017796227,0.000070593094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009158678,0.0000723296,0.000077797864,0.000034565324,0.00010693133,0.00013455447,0.0023156079,0.000026671347,0.0004557944],"category_scores_gemma":[0.000012305706,0.00005100652,0.000012700628,0.0001441404,0.000014488903,0.0011263995,0.0022806989,0.00006643653,0.00066393084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.033813e-7,0.00013845392,0.00020457753,0.000008035751,0.0000062030444,0.00002868127,0.000096661264,0.000019448533,0.0006454969,0.018273238,0.55871725,0.42186123],"study_design_scores_gemma":[0.00011333308,0.000011085528,0.00034441188,0.000012575215,0.0000011180697,0.000012602262,0.0000026291632,0.88952196,0.00019035314,0.00044946207,0.10925756,0.000082914834],"about_ca_topic_score_codex":0.000028554492,"about_ca_topic_score_gemma":0.0000018885287,"teacher_disagreement_score":0.8895025,"about_ca_system_score_codex":0.000004291406,"about_ca_system_score_gemma":0.0000036179752,"threshold_uncertainty_score":0.8533709},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016537888,0.0007707072,0.99596184,0.0008070217,0.00036337282,0.00065755297,0.000013428192,0.00015737263,0.0012521736],"genre_scores_gemma":[0.023945663,0.000066823326,0.97393936,0.0014136235,0.00045183353,0.000032402306,0.000009207241,0.000026658738,0.00011445088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967017,0.000020543812,0.0004865536,0.0015293745,0.00068547874,0.000576355],"domain_scores_gemma":[0.997711,0.00026004575,0.00019798508,0.0013320608,0.0001663915,0.00033249834],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004979926,0.0004291652,0.00047350558,0.00055395043,0.00043493463,0.00077764364,0.002108495,0.00018345391,0.0000064563574],"category_scores_gemma":[0.000021374257,0.00039731717,0.00006312971,0.00044667505,0.00041419064,0.0004936881,0.002551191,0.0005509685,0.000028871294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025754953,0.000024798645,0.000025853822,0.000023461544,0.0000057425495,0.000012337532,0.00018202828,0.023908237,0.000053185537,0.033301234,0.000056362445,0.9424042],"study_design_scores_gemma":[0.00026447125,0.00010975049,0.00012152081,0.0005750946,0.000011068698,0.000104471845,4.603364e-7,0.93003595,0.00039118147,0.026718022,0.040877458,0.0007905598],"about_ca_topic_score_codex":0.000018121751,"about_ca_topic_score_gemma":0.00004131056,"teacher_disagreement_score":0.9416136,"about_ca_system_score_codex":0.00019843328,"about_ca_system_score_gemma":0.0002776079,"threshold_uncertainty_score":0.9998479},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012837218,0.00064855453,0.99634826,0.00032759339,0.00036661187,0.00032608546,0.0000038969365,0.000043963482,0.0018066784],"genre_scores_gemma":[0.13523386,0.000250123,0.86289746,0.0011467936,0.00025951516,0.0000071773284,0.000013468923,0.000021400103,0.0001701984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750376,0.00002393132,0.00041101553,0.00094219024,0.00080273283,0.0003163645],"domain_scores_gemma":[0.9983041,0.00019175893,0.00030163096,0.0009762429,0.00012433396,0.000101891615],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000574022,0.0003234472,0.0003928725,0.0005055829,0.00014568349,0.00021965883,0.0014697952,0.00015866634,0.0000057429957],"category_scores_gemma":[0.000032437594,0.00026389913,0.000056036562,0.00030568885,0.0002507439,0.0004794853,0.00088197616,0.00035073064,0.0000063976254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032841135,0.000021560292,0.000012662325,0.000046275254,0.0000029311066,0.000012356875,0.00022143964,0.0039636944,0.00004572813,0.022678923,0.000009430919,0.9729817],"study_design_scores_gemma":[0.00030584043,0.00046930322,0.000823594,0.0016078193,0.0000064026062,0.000031468957,1.06171456e-7,0.7949361,0.0012088092,0.19862165,0.0015375676,0.00045132235],"about_ca_topic_score_codex":0.000012305146,"about_ca_topic_score_gemma":0.000021122973,"teacher_disagreement_score":0.97253036,"about_ca_system_score_codex":0.00009833648,"about_ca_system_score_gemma":0.00014709184,"threshold_uncertainty_score":0.99998134},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017614966,0.0002597597,0.9807473,0.00012055106,0.00005339267,0.00026930755,0.000003172686,0.000046665224,0.00088490074],"genre_scores_gemma":[0.99099034,0.000022364298,0.008797587,0.00005349811,0.000026820342,0.000041577754,0.0000015656665,0.000005188571,0.000061077124],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999039,0.000042370313,0.00024357572,0.00029590525,0.0002184108,0.00016077282],"domain_scores_gemma":[0.9990197,0.00022760019,0.000078634715,0.00059665396,0.000029171582,0.000048241553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000276443,0.000106081694,0.00014341612,0.00003235272,0.00016582933,0.000055177952,0.0006850663,0.000037417656,0.000058216327],"category_scores_gemma":[0.000016623972,0.000066720924,0.000027291708,0.00017638638,0.00020816203,0.00016317923,0.0002583415,0.0001193913,0.000029822862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031644107,0.000047220212,0.0000028255881,0.000023494893,0.000008214029,0.0000014056575,0.0019157605,0.009631211,0.0010201561,0.45525366,0.0000550258,0.53200936],"study_design_scores_gemma":[0.00030251854,0.000039961804,0.00036892702,0.00016874056,0.000015762218,0.000022282857,0.00036179973,0.41732553,0.0014725806,0.57948947,0.00019849476,0.00023396262],"about_ca_topic_score_codex":0.00017588749,"about_ca_topic_score_gemma":0.000003019491,"teacher_disagreement_score":0.9733754,"about_ca_system_score_codex":0.000022181426,"about_ca_system_score_gemma":0.000027424167,"threshold_uncertainty_score":0.27208003},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015140008,0.00013164442,0.9950966,0.0015877666,0.0009674432,0.00042623602,0.00002256804,0.000043526605,0.00021016835],"genre_scores_gemma":[0.48686522,0.000040823536,0.5110385,0.00052292,0.0012784237,0.0001432427,0.00003219221,0.0000112882335,0.000067425965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856573,0.00003541204,0.0005133908,0.00023441401,0.0004902251,0.00016082879],"domain_scores_gemma":[0.9972161,0.00021138114,0.0004670822,0.00031339316,0.0016666821,0.00012536188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018024122,0.00013646334,0.00018251182,0.00020253078,0.00013740984,0.0003335109,0.001788913,0.00006224678,0.000029603976],"category_scores_gemma":[0.000008701359,0.000111880894,0.00013564006,0.00014802456,0.000053767242,0.0012984253,0.00030675274,0.00015822549,0.00006398159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052283947,0.0006514089,0.00027809362,0.000014977152,0.00025033517,0.000009492254,0.00034025635,0.009201328,0.0037951067,0.31259373,0.051363066,0.62144995],"study_design_scores_gemma":[0.0013295314,0.00015579349,0.0041831266,0.00012707138,0.000016976233,0.00022810137,0.000018673738,0.7912929,0.0020092523,0.0396321,0.16073783,0.00026861837],"about_ca_topic_score_codex":0.000013499081,"about_ca_topic_score_gemma":6.63768e-7,"teacher_disagreement_score":0.7820916,"about_ca_system_score_codex":0.00008630192,"about_ca_system_score_gemma":0.00009650522,"threshold_uncertainty_score":0.45623705},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037802085,0.000049203136,0.9478774,0.00012137277,0.00030383596,0.000029485418,6.385158e-7,0.00011494869,0.013701049],"genre_scores_gemma":[0.29742625,0.0000034942905,0.70133716,0.000051264153,0.00012464565,0.0000027124106,0.000002726062,0.0000023504467,0.0010494232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995737,0.000009830904,0.00007889936,0.00015993304,0.00008006748,0.000097588294],"domain_scores_gemma":[0.99969524,0.000008615605,0.000020303985,0.0002359496,0.000018831404,0.000021070526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000038349426,0.000044102413,0.00004010072,0.000029000783,0.000056242774,0.000068688765,0.00023814353,0.000020660824,0.000060825045],"category_scores_gemma":[0.0000013436247,0.000034938537,0.000016820657,0.000093134855,0.000013028953,0.00023088927,0.0001049883,0.000028041934,0.000072177936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023151053,0.000063891806,0.0017833129,0.0000034532875,0.000003994723,0.000010197519,0.000018835357,0.0027956525,0.009849767,0.10277868,0.016772704,0.8659172],"study_design_scores_gemma":[0.00041246068,0.00007650137,0.02758615,0.000012036524,0.0000029084563,0.00021878225,0.000011072459,0.90238476,0.024604345,0.012671458,0.031709243,0.00031028865],"about_ca_topic_score_codex":0.00007029436,"about_ca_topic_score_gemma":0.000002848866,"teacher_disagreement_score":0.8995891,"about_ca_system_score_codex":0.0000071200175,"about_ca_system_score_gemma":0.000010711483,"threshold_uncertainty_score":0.14247522},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043137528,0.000021951493,0.95463055,0.0002404831,0.000059705166,0.00013136941,0.0000021398666,0.00014596537,0.0016303136],"genre_scores_gemma":[0.90375924,0.0000030354297,0.095731646,0.00025223408,0.00002291263,0.0000029640491,0.00000523494,0.0000029485263,0.00021976964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994697,0.000010985156,0.000065976026,0.00021876195,0.00010416042,0.00013040454],"domain_scores_gemma":[0.9996927,0.00004376889,0.000031835363,0.00012434692,0.000054153814,0.000053193045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008353276,0.000067741596,0.000074027565,0.000025942853,0.0004540529,0.000085200634,0.00016688362,0.000034636498,0.000010195406],"category_scores_gemma":[0.0000026962264,0.000051047293,0.000012033453,0.00011473338,0.000018597084,0.00069363764,0.00029183176,0.000057430538,0.000005196614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023293514,0.00037891103,0.020767154,0.00004932327,0.00008841459,0.0000050505914,0.0023864836,0.002348237,0.0011288354,0.58962107,0.01164568,0.3713479],"study_design_scores_gemma":[0.0015054154,0.00035464443,0.0040653935,0.000025296104,0.000009976839,0.000029157889,0.000019749621,0.97523016,0.0014328422,0.0012710758,0.015863193,0.00019309552],"about_ca_topic_score_codex":0.00015876419,"about_ca_topic_score_gemma":0.000109931265,"teacher_disagreement_score":0.9728819,"about_ca_system_score_codex":0.000015861197,"about_ca_system_score_gemma":0.000010439664,"threshold_uncertainty_score":0.34922537},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026327348,0.00003715539,0.99660194,0.00022641654,0.000054515767,0.00011461317,0.000008544648,0.0000760498,0.00024805934],"genre_scores_gemma":[0.23356466,0.0000050443514,0.7661708,0.000090277514,0.000049657297,0.000010435563,0.000008434392,0.0000033336291,0.00009734303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995178,0.000004894665,0.00007679877,0.00016199781,0.000084926614,0.0001535781],"domain_scores_gemma":[0.9997045,0.00006298182,0.000034890745,0.00012316913,0.000035736084,0.00003873027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010055509,0.00006595311,0.00006325246,0.00006044483,0.00014539955,0.0003209386,0.00012531305,0.000016340407,0.0000042063375],"category_scores_gemma":[0.0000057736647,0.000047798116,0.000005277107,0.00007773185,0.00001257323,0.0010116749,0.00007581184,0.000024255212,0.0000024521437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036878519,0.000009652647,0.000007982425,0.000016295333,0.000003872116,0.0000010130987,0.0006686416,0.0050781425,0.000053007512,0.3584306,0.00057411374,0.635153],"study_design_scores_gemma":[0.00019132883,0.00006312624,0.000034751654,0.000019338999,0.0000023438295,0.0000079588035,0.00011891547,0.99180293,0.00041860764,0.006283305,0.00097451574,0.000082865445],"about_ca_topic_score_codex":0.0000072571097,"about_ca_topic_score_gemma":0.000009660379,"teacher_disagreement_score":0.9867248,"about_ca_system_score_codex":0.000009019375,"about_ca_system_score_gemma":0.00002565109,"threshold_uncertainty_score":0.30948183},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023859562,0.00010399556,0.9603679,0.014400224,0.0003491744,0.00054043945,0.00001557479,0.00014020642,0.00022289359],"genre_scores_gemma":[0.9230483,0.00013887494,0.074462205,0.0011692686,0.00009471937,0.00023349104,0.000009564313,0.000021107118,0.00082247244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841,0.000117014686,0.00020586872,0.0004872182,0.000479023,0.00030087034],"domain_scores_gemma":[0.99825585,0.0003034561,0.000040094084,0.0010985171,0.00015140953,0.00015065333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028554015,0.0001847898,0.00012985514,0.00012253468,0.0005714261,0.00037227935,0.00091923674,0.00007608056,0.00014496758],"category_scores_gemma":[0.000025181263,0.00012181123,0.00008615464,0.00039620526,0.000094489245,0.0006403998,0.00005803524,0.00036118977,0.0002045202],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000122358815,0.0002350459,0.000008682644,0.00000963615,0.000043711643,0.000002536109,0.00057785626,0.0034248924,0.00011473371,0.0013898878,0.0006010889,0.9935797],"study_design_scores_gemma":[0.0008227556,0.0006870441,0.010141385,0.00014066738,0.000028607672,0.00006893627,0.0007288464,0.9780358,0.0023920794,0.0035759083,0.002900634,0.00047735553],"about_ca_topic_score_codex":0.00016475495,"about_ca_topic_score_gemma":0.0000095386185,"teacher_disagreement_score":0.9931023,"about_ca_system_score_codex":0.000052454317,"about_ca_system_score_gemma":0.000053623513,"threshold_uncertainty_score":0.4967318},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012040301,0.00003418217,0.997654,0.00012459829,0.0002732144,0.00019271772,0.00001516092,0.00018453547,0.000317522],"genre_scores_gemma":[0.13006529,0.00000832379,0.86914825,0.00041514385,0.000079518635,0.000033148506,0.000016759835,0.000006380642,0.00022715931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988756,0.000021636564,0.00015205963,0.00040889208,0.00027634238,0.0002654645],"domain_scores_gemma":[0.99910074,0.000037060894,0.00003539416,0.0006103197,0.00006451689,0.00015197354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014429068,0.00010865442,0.00010433705,0.000039052713,0.00024100766,0.00005262418,0.0007529256,0.000038529295,0.000018263125],"category_scores_gemma":[0.0000030749743,0.000083041305,0.000042398282,0.000121982055,0.0000628094,0.0003068604,0.00017862036,0.00004389093,0.000037410424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031045604,0.000276805,0.000014751005,0.0000037534203,0.0000064674937,0.00004258615,0.00031580377,0.0074849697,0.00063738803,0.022922002,0.0048735705,0.9634188],"study_design_scores_gemma":[0.00025393552,0.00016484158,0.00009924726,0.0000047279054,0.0000011969172,0.000056142548,0.000019581119,0.9863982,0.0044123316,0.00038192744,0.008068985,0.00013889124],"about_ca_topic_score_codex":0.0000573138,"about_ca_topic_score_gemma":9.008092e-7,"teacher_disagreement_score":0.97891325,"about_ca_system_score_codex":0.000044634256,"about_ca_system_score_gemma":0.0000623707,"threshold_uncertainty_score":0.3386326},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042157546,0.000030280524,0.9938567,0.000152229,0.00003988472,0.00025181143,0.00000592554,0.00012087644,0.0013265198],"genre_scores_gemma":[0.5729114,0.000030220865,0.425796,0.00019150344,0.00003397489,0.00004143832,0.000013912094,0.000005524337,0.00097603677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990983,0.000029532297,0.00014711704,0.0004014477,0.00014872896,0.00017487734],"domain_scores_gemma":[0.99915284,0.000027397477,0.000051211573,0.0006128434,0.00004363333,0.00011207864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014257351,0.00010416009,0.00014356135,0.0001429855,0.00011811974,0.00021241444,0.0005075653,0.000053107622,0.00010925535],"category_scores_gemma":[0.000004395068,0.000076627446,0.000047474467,0.000305278,0.000024989109,0.000939717,0.0002102596,0.00004902035,0.000009528708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008920737,0.002847673,0.060277607,0.0002414245,0.0008573225,0.000056523262,0.0055210637,0.006198444,0.12398141,0.07244716,0.13790026,0.5895819],"study_design_scores_gemma":[0.00022167662,0.000097731245,0.0029627325,0.000009628725,0.000024637635,0.0000023994871,0.000010824579,0.9872012,0.0039282115,0.0017258172,0.003669277,0.00014586853],"about_ca_topic_score_codex":0.000026531745,"about_ca_topic_score_gemma":0.0000037983814,"teacher_disagreement_score":0.98100275,"about_ca_system_score_codex":0.0000092288765,"about_ca_system_score_gemma":0.000002851673,"threshold_uncertainty_score":0.31247765},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50644505,0.00016176228,0.4904322,0.00033011363,0.00011906509,0.00025259954,0.0000043754976,0.00006795464,0.0021868586],"genre_scores_gemma":[0.9507518,0.000014572797,0.048722148,0.000039235354,0.000020893616,0.000020768655,0.000030032355,0.000004893884,0.00039565444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845237,0.00011198903,0.00043476876,0.0004515609,0.00034320063,0.00020611066],"domain_scores_gemma":[0.99878746,0.00009458547,0.0001746569,0.0007354652,0.00012597503,0.000081877115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014328977,0.00012593681,0.00029278104,0.00044006424,0.000054538537,0.000078409386,0.00073345186,0.000067156405,0.00022522832],"category_scores_gemma":[0.00001931205,0.00009885546,0.00009674155,0.0015636,0.000031779513,0.0013097711,0.0004258803,0.00009216564,0.000047591377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112235,0.0019357974,0.10447422,0.00013379796,0.00035010514,0.00009157228,0.0031416474,0.010216853,0.39163622,0.006280272,0.012266114,0.46936116],"study_design_scores_gemma":[0.00032341914,0.000053298325,0.26366904,0.00003015833,0.00001602624,0.0000019557708,0.0000518068,0.7271581,0.008148028,0.00038568908,0.000049453865,0.000112978145],"about_ca_topic_score_codex":0.0010550052,"about_ca_topic_score_gemma":0.000052051044,"teacher_disagreement_score":0.7169413,"about_ca_system_score_codex":0.000020482936,"about_ca_system_score_gemma":0.00002424916,"threshold_uncertainty_score":0.40312088},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03551392,0.00014444928,0.96296465,0.00002006363,0.00032062316,0.00007067138,0.000014135271,0.00007345179,0.0008780563],"genre_scores_gemma":[0.42369524,0.0000053825825,0.57610124,0.00007317483,0.00008340999,5.17707e-7,0.0000015632155,0.00000864524,0.000030798416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874717,0.000061469036,0.0002638951,0.00038954147,0.00019625766,0.00034168898],"domain_scores_gemma":[0.99922866,0.00013529584,0.00012924847,0.0002935113,0.00007350958,0.00013979703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026002852,0.0001562608,0.00017997845,0.000053154843,0.00034298448,0.00017355852,0.0003534566,0.000050658433,0.000013159069],"category_scores_gemma":[0.00004369227,0.00014141799,0.000023992567,0.00013960243,0.000057498157,0.00017123,0.00073422666,0.00016480887,0.0000046063365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007274388,0.00007347823,0.0029042396,0.00003535053,0.000029155497,0.00013860826,0.0027478235,0.00026136532,0.00026266638,0.10117816,0.0012280273,0.89113384],"study_design_scores_gemma":[0.00019136912,0.00004490228,0.0049700993,0.00005840334,0.0000073261076,0.00003084348,0.00007212332,0.9906717,0.000036452828,0.0031701666,0.0005487131,0.00019789061],"about_ca_topic_score_codex":0.00019570549,"about_ca_topic_score_gemma":0.000007275495,"teacher_disagreement_score":0.9904103,"about_ca_system_score_codex":0.000021383437,"about_ca_system_score_gemma":0.000040424213,"threshold_uncertainty_score":0.5766858},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062304097,0.00061782234,0.99125373,0.0003862252,0.00128004,0.000110799665,0.00002387931,0.000030412273,0.000066652596],"genre_scores_gemma":[0.20300356,0.000014739223,0.7957119,0.0001692542,0.0010606215,0.0000046294845,0.0000054281577,0.000013527128,0.000016366894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822426,0.00004681047,0.00056467485,0.00017937568,0.00054453325,0.00044036945],"domain_scores_gemma":[0.9981599,0.00046555584,0.0005679344,0.00025871917,0.00025117685,0.00029672368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007169608,0.00017589203,0.00030240437,0.00016078107,0.00019281634,0.00020037015,0.00086034066,0.00009585232,0.000015157663],"category_scores_gemma":[0.00016309276,0.00013768405,0.00021100375,0.00021512402,0.000039534578,0.0020392183,0.00025629287,0.00030553373,0.000007914488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014476269,0.00052517897,0.004717399,0.00009090997,0.00031611705,0.00007555553,0.0041052443,0.004321357,0.00032841568,0.1302678,0.0064842133,0.84862304],"study_design_scores_gemma":[0.0026495596,0.0013318866,0.017220719,0.0005599849,0.00010016028,0.0011278833,0.00033102746,0.82565945,0.0012562402,0.12017569,0.028709436,0.00087793026],"about_ca_topic_score_codex":0.00000254645,"about_ca_topic_score_gemma":7.54528e-8,"teacher_disagreement_score":0.8477451,"about_ca_system_score_codex":0.000051293282,"about_ca_system_score_gemma":0.00010202752,"threshold_uncertainty_score":0.56145924},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003518673,0.00037928103,0.9927664,0.0027512352,0.00057925994,0.0006342853,0.0012874011,0.0004862925,0.00076398667],"genre_scores_gemma":[0.2874198,0.0000597811,0.70657694,0.001687742,0.00046557497,0.00015649878,0.0032137358,0.00003646765,0.00038346762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673104,0.0001355,0.0005427157,0.001358117,0.00060222804,0.00063040474],"domain_scores_gemma":[0.9941338,0.00050681253,0.00027467607,0.004461652,0.00030487342,0.0003182243],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00050007796,0.0003754707,0.00041773528,0.0001552809,0.00046351267,0.0006484979,0.0071468977,0.00015394979,0.00017147185],"category_scores_gemma":[0.00014982879,0.0003120625,0.000086835156,0.00028004625,0.00010513851,0.0022401933,0.0030459594,0.00029355116,0.00013429727],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012770716,0.0005822412,0.00010563638,0.00011353656,0.000031852214,0.000011375932,0.000121378805,0.0008444897,0.0060052993,0.031877417,0.23832099,0.7218581],"study_design_scores_gemma":[0.0008765638,0.00004872733,0.00012454412,0.000101898804,0.000008085437,0.0000042768415,0.000005198609,0.56439364,0.0020833109,0.0007386665,0.43134594,0.00026911954],"about_ca_topic_score_codex":0.00005553142,"about_ca_topic_score_gemma":0.000027740383,"teacher_disagreement_score":0.72158897,"about_ca_system_score_codex":0.000036010286,"about_ca_system_score_gemma":0.00025679445,"threshold_uncertainty_score":0.9999331},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067212054,0.000010455079,0.993987,0.00011931136,0.0010194087,0.0005672753,0.0004517245,0.00027742886,0.0028952786],"genre_scores_gemma":[0.9728691,0.000009045784,0.02600628,0.000740456,0.000029446335,0.000046883397,0.00018048091,0.00002130278,0.000096998505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99761647,0.00028436622,0.00047277476,0.00044673288,0.00078929355,0.00039038708],"domain_scores_gemma":[0.99772376,0.00020143627,0.00019089156,0.0015096188,0.00016773077,0.00020656482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007547612,0.00033377585,0.00025152997,0.00037823932,0.0006146493,0.0002733529,0.001061294,0.000114430026,0.000105099396],"category_scores_gemma":[0.0000044398703,0.00026327415,0.00008998843,0.00047446965,0.00014071434,0.0028826192,0.000010664988,0.0004082618,0.00009999248],"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":[0.00036983262,0.0002791502,2.2099755e-7,0.000020946865,0.00003250262,0.000006175139,0.0005973238,0.8354628,0.000018808763,0.033896085,0.00021133544,0.12910481],"study_design_scores_gemma":[0.0030944536,0.00032890312,0.000001408187,0.00015417108,0.00003324141,0.000023833087,0.00030176967,0.98644507,0.003205988,0.0009907171,0.005062479,0.00035798814],"about_ca_topic_score_codex":0.000046361918,"about_ca_topic_score_gemma":0.000011246045,"teacher_disagreement_score":0.972197,"about_ca_system_score_codex":0.0001221869,"about_ca_system_score_gemma":0.00023768448,"threshold_uncertainty_score":0.99998194},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013762411,0.00013936534,0.97348094,0.00018194156,0.00017642158,0.00019712072,0.0000015568439,0.00014456437,0.024301875],"genre_scores_gemma":[0.21881711,0.000026777183,0.78059965,0.00009260251,0.00015435049,0.00007672152,0.000004338593,0.000018968276,0.00020947118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990566,0.000008306517,0.00021465775,0.0001387827,0.00023107136,0.00035063346],"domain_scores_gemma":[0.9990187,0.00012147189,0.000097368415,0.00065671914,0.000018104243,0.000087581764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037099063,0.00012016963,0.00011505668,0.0000185663,0.00026959245,0.00021295354,0.00087308965,0.000032940196,0.0000070927417],"category_scores_gemma":[0.00001263799,0.000069591835,0.0000377345,0.00012777514,0.000037812973,0.00031350437,0.000723635,0.000111242734,0.00012709862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012528056,0.000042060998,0.000008524738,0.000031917498,0.0000115854355,3.6062085e-7,0.0021719255,0.0000076351735,0.0007607079,0.9564188,0.0013211371,0.03922405],"study_design_scores_gemma":[0.0010540783,0.00009405633,0.0004555895,0.0002497657,0.000054979857,0.000088454486,0.003433745,0.32068148,0.014277983,0.36664602,0.29148975,0.0014740903],"about_ca_topic_score_codex":0.0000020920108,"about_ca_topic_score_gemma":7.918285e-7,"teacher_disagreement_score":0.5897728,"about_ca_system_score_codex":0.000015084722,"about_ca_system_score_gemma":0.000011359702,"threshold_uncertainty_score":0.28378728},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15535916,0.0014177737,0.78210515,0.0021867026,0.0031092218,0.00033787475,0.00005639029,0.00073677703,0.05469096],"genre_scores_gemma":[0.9782911,0.00017633168,0.00979845,0.00021139234,0.0002578208,4.5395043e-7,0.000018805908,0.000009243607,0.011236398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980978,0.0001431028,0.00018857546,0.00039123854,0.0006884951,0.0004908069],"domain_scores_gemma":[0.99838454,0.00017970573,0.000102868806,0.000697599,0.0000923513,0.0005429208],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00056751794,0.00017281718,0.00021072259,0.00007451197,0.00024079246,0.0000756497,0.0014713628,0.00018710313,0.0025554218],"category_scores_gemma":[0.00012065149,0.0001517618,0.00006879496,0.00043005878,0.000116974945,0.001169322,0.0009346745,0.00029446924,0.0008982558],"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":[0.00041718554,0.0006599082,0.013484522,0.000057624016,0.000070163354,0.0001683086,0.0030086057,0.0000021604938,0.0014276187,0.20134278,0.13416587,0.64519525],"study_design_scores_gemma":[0.0013511026,0.00025025866,0.044729598,0.00014056974,0.000026348367,0.00015014944,0.00012407164,0.035170943,0.002965439,0.0008965302,0.9133415,0.00085345784],"about_ca_topic_score_codex":0.00009658392,"about_ca_topic_score_gemma":0.00002935853,"teacher_disagreement_score":0.82293195,"about_ca_system_score_codex":0.00011405443,"about_ca_system_score_gemma":0.00022009746,"threshold_uncertainty_score":0.99987966},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077048835,0.0006893136,0.35814956,0.00008173221,0.000101750826,0.0001908241,0.00008079049,0.00013795446,0.63979757],"genre_scores_gemma":[0.15068506,0.0025370808,0.11496254,0.00050818775,0.00033155747,0.0000041783665,0.00016806718,0.00013628017,0.73066705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989602,0.000008841581,0.00016482332,0.00040582466,0.0002824295,0.00017789612],"domain_scores_gemma":[0.999215,0.000048133923,0.00013916395,0.00046234616,0.000051270472,0.000084083076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007660755,0.00021464688,0.00029362866,0.000116956966,0.000107335225,0.00009841458,0.00052737206,0.00013149502,0.00019443843],"category_scores_gemma":[8.1994153e-7,0.00015754654,0.00003565985,0.000032975484,0.00010710788,0.00033205486,0.00039997327,0.00015112502,0.000010976159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019963003,0.000019154419,0.000030209805,0.00003607354,0.000051561692,0.000053711447,0.00021153479,0.0000058749674,0.000011007567,0.9712532,0.0006321161,0.027675604],"study_design_scores_gemma":[0.0036730354,0.0008460457,0.00039023938,0.0021832853,0.00014716819,0.00019172243,0.00015444611,0.041123986,0.00081887667,0.065287635,0.8831276,0.0020559316],"about_ca_topic_score_codex":0.00004332394,"about_ca_topic_score_gemma":0.000030507888,"teacher_disagreement_score":0.90596557,"about_ca_system_score_codex":0.00001563385,"about_ca_system_score_gemma":0.00006493297,"threshold_uncertainty_score":0.6424562},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009839628,0.00007365876,0.99851215,0.00026277077,0.00015177186,0.00014885083,0.00005156948,0.00007280165,0.0006280208],"genre_scores_gemma":[0.012111333,0.00001397855,0.98647314,0.00006809531,0.000041855943,0.000015378222,0.000011654633,0.0000045903826,0.00125995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992856,0.000012364601,0.000174089,0.00020997449,0.00017004956,0.00014795289],"domain_scores_gemma":[0.99938625,0.00006341697,0.00007510501,0.00033791456,0.00009085521,0.000046485326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000084079606,0.000080961196,0.00011261623,0.00005769374,0.000065116474,0.000066708504,0.000413285,0.000030233216,0.000083748586],"category_scores_gemma":[0.000022478864,0.00006321165,0.00004771844,0.00012590893,0.000022196287,0.0006292575,0.00015063678,0.000032415537,0.000029956915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.034795e-7,0.000055343422,0.0000049187825,0.000007017984,0.000004379814,7.975468e-7,0.000072135794,0.00011821064,0.00035092383,0.0062128613,0.01037098,0.98280185],"study_design_scores_gemma":[0.00032512,0.000070269336,0.0002425367,0.000011943689,0.0000029133698,0.0000053176777,0.0000071102954,0.98730224,0.008606755,0.0018707771,0.0014723311,0.00008269795],"about_ca_topic_score_codex":0.000023880672,"about_ca_topic_score_gemma":4.1029057e-7,"teacher_disagreement_score":0.987184,"about_ca_system_score_codex":0.00001032,"about_ca_system_score_gemma":0.000007807359,"threshold_uncertainty_score":0.2577696},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068238396,0.000010248169,0.9906643,0.0012488329,0.00006441046,0.00014982384,0.000057001253,0.00025440415,0.00072714634],"genre_scores_gemma":[0.7243425,0.0000014824526,0.2738384,0.0017352217,0.000025236648,0.0000055873584,0.000013116011,0.000004370333,0.0000340355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989615,0.00007429007,0.0001676724,0.00040122814,0.0001796415,0.00021566074],"domain_scores_gemma":[0.9991366,0.00013666351,0.000051296545,0.0004496866,0.00006513148,0.00016059665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022491717,0.00014161564,0.00014763042,0.00007190252,0.00013427726,0.00017823093,0.00044001947,0.00005360012,0.000046382556],"category_scores_gemma":[0.000032320637,0.00010408205,0.000020957623,0.000116879215,0.000076810255,0.00063559605,0.000044779394,0.0001247535,0.000017350303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001656432,0.000577142,0.00106823,0.000019485937,0.000025026382,0.00007609093,0.00052645494,0.038648754,0.072331384,0.061533846,0.002057117,0.8229708],"study_design_scores_gemma":[0.0011808799,0.00013062966,0.00039640386,0.00003033207,0.0000025195432,0.000007624441,0.000022297578,0.9945197,0.0015609496,0.00005597694,0.0019402612,0.00015242196],"about_ca_topic_score_codex":0.000098820245,"about_ca_topic_score_gemma":0.000048442518,"teacher_disagreement_score":0.9558709,"about_ca_system_score_codex":0.00003148557,"about_ca_system_score_gemma":0.00007071777,"threshold_uncertainty_score":0.42443427},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002935968,0.00011500912,0.99377096,0.00015259304,0.0005758943,0.00020950007,0.000013322237,0.00018040118,0.0049529895],"genre_scores_gemma":[0.0015433412,0.0000046476603,0.9966773,0.00019495728,0.00016181571,0.000045126537,0.000010259768,0.000008784915,0.0013537955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890196,0.000026437952,0.00021320414,0.00036865985,0.00020264203,0.00028709148],"domain_scores_gemma":[0.999161,0.00010212228,0.00007296547,0.00048717338,0.000088212975,0.0000884937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035257344,0.00011564159,0.00013248321,0.00003948867,0.00018629855,0.00020942299,0.00053817185,0.000042336138,0.000025285484],"category_scores_gemma":[0.000077225566,0.000090878486,0.000053898202,0.00022516178,0.000019176478,0.0006473481,0.00011823544,0.00007135347,0.000023609293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014487265,0.000085667685,0.000022592976,0.000017221217,0.000008385879,0.000003422145,0.000100982776,0.00002167441,0.00016677454,0.34933272,0.019918792,0.6303203],"study_design_scores_gemma":[0.00025825982,0.000036621863,0.000010260179,0.00001097154,0.0000015998316,0.000007333214,0.000022143166,0.788049,0.0017393494,0.0067002373,0.20302224,0.00014202163],"about_ca_topic_score_codex":0.000008441734,"about_ca_topic_score_gemma":0.0000014610648,"teacher_disagreement_score":0.7880273,"about_ca_system_score_codex":0.000018361277,"about_ca_system_score_gemma":0.00004639633,"threshold_uncertainty_score":0.3705917},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058869743,0.000022497698,0.98462874,0.0004954494,0.00009924984,0.00026703774,0.0000072128623,0.00022945067,0.008363399],"genre_scores_gemma":[0.71580434,0.0000046405457,0.28361276,0.00012444785,0.00009545273,0.00005083615,0.000015695041,0.000020066109,0.00027176403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874455,0.000010367563,0.0002123397,0.00035010447,0.0003480869,0.00033452548],"domain_scores_gemma":[0.9986436,0.00009334607,0.00014786667,0.0009539397,0.00003536523,0.00012587843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002304249,0.00019784382,0.00025992098,0.00006201806,0.0001714244,0.000537795,0.0009386038,0.00006353945,0.000006497398],"category_scores_gemma":[0.000014850178,0.00015573516,0.00005450581,0.00015905968,0.000036675625,0.000245558,0.00051822246,0.00013074493,0.000026528449],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000341406,0.00003195562,0.0000054536113,0.00006596097,0.000010641943,0.0000021767985,0.0008520098,0.000025164878,0.0014427084,0.9872251,0.00043370173,0.009901719],"study_design_scores_gemma":[0.0034887372,0.00017892648,0.00017417516,0.00023136662,0.00005453037,0.00003195667,0.0021279976,0.60080963,0.030645236,0.32782283,0.033070114,0.0013644748],"about_ca_topic_score_codex":0.00001948779,"about_ca_topic_score_gemma":0.000008435472,"teacher_disagreement_score":0.70991737,"about_ca_system_score_codex":0.000025564204,"about_ca_system_score_gemma":0.000021701624,"threshold_uncertainty_score":0.63506955},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7556399,0.0002847959,0.24276817,0.00018095924,0.00015041055,0.00013412476,0.00015601663,0.00017636239,0.0005092587],"genre_scores_gemma":[0.9685631,0.00015864588,0.030785121,0.00012549823,0.000041108462,1.1226942e-7,0.00009119973,0.0000059074655,0.00022931483],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986228,0.000034578126,0.00013692009,0.0006124106,0.00029808428,0.00029522117],"domain_scores_gemma":[0.9985383,0.000026953716,0.00016061304,0.001057814,0.000093363466,0.00012293975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002536553,0.000050981664,0.00020125648,0.00003691085,0.00039421016,0.00031970217,0.0022017672,0.00006786203,0.0000196197],"category_scores_gemma":[0.000024735351,0.0001682695,0.000040564402,0.00030744556,0.00007599026,0.0028680721,0.0012731018,0.00016354733,0.000018758094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014448958,0.00005884003,0.00051191816,0.000019465337,0.0000046672103,0.000040324285,0.000050160488,0.0000016603874,0.0005443658,0.0000036370584,0.0168411,0.9819224],"study_design_scores_gemma":[0.0010752184,0.00019562268,0.8866251,0.00030448948,0.000016524293,0.00010085868,0.00021403586,0.106516086,0.000016395643,0.00024146702,0.0042711473,0.00042305782],"about_ca_topic_score_codex":0.015555179,"about_ca_topic_score_gemma":0.0038808296,"teacher_disagreement_score":0.9814994,"about_ca_system_score_codex":0.00004223825,"about_ca_system_score_gemma":0.00007692446,"threshold_uncertainty_score":0.9910003},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15821621,0.000008657932,0.8412751,0.00012186433,0.00010340406,0.00016113903,0.000072294206,0.00002433164,0.000017003043],"genre_scores_gemma":[0.969032,4.4761222e-7,0.030667301,0.00014482025,0.000053914115,0.0000035288008,0.00006688565,0.0000064043907,0.000024736986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993367,0.000029666411,0.00013504918,0.00029271576,0.00009109164,0.00011476847],"domain_scores_gemma":[0.99879587,0.0004752727,0.00009310402,0.0005156317,0.000058862708,0.000061259765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032280598,0.00007549525,0.000077757744,0.00003903621,0.00024544742,0.000116403055,0.00028178171,0.000026973485,0.000035215315],"category_scores_gemma":[0.0001742825,0.000051584226,0.0000150571705,0.00005119103,0.000027378723,0.0006125405,0.00030602468,0.00011140609,0.000002110111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031566804,0.000040661565,0.000057280587,0.00003053833,0.0000111669615,0.000012060176,0.0016102833,0.028085008,0.00031076916,0.00030402446,0.00021851191,0.9692881],"study_design_scores_gemma":[0.00023697446,0.00004206769,0.000057857575,0.000037734146,0.000016349464,0.000016132844,0.00009414284,0.996076,0.000026152518,0.0032002172,0.00012066223,0.000075717035],"about_ca_topic_score_codex":0.00021486131,"about_ca_topic_score_gemma":0.000029660809,"teacher_disagreement_score":0.9692124,"about_ca_system_score_codex":0.000004040974,"about_ca_system_score_gemma":0.000029550067,"threshold_uncertainty_score":0.21035436},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017387586,0.00006659629,0.97639686,0.000820982,0.00008927735,0.0005000081,0.000022987944,0.00011525699,0.004600457],"genre_scores_gemma":[0.53918874,0.00006626777,0.4601743,0.00017120074,0.00007311649,0.000060316266,0.000021111706,0.000028277009,0.00021665207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986922,0.000012744792,0.00032082913,0.00025579418,0.00045093131,0.0002675046],"domain_scores_gemma":[0.99853414,0.00011710028,0.00013180177,0.0011036227,0.00004612536,0.000067211375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029016225,0.00015737771,0.00022521915,0.000055961573,0.00016204569,0.00007655961,0.0012810072,0.00005749057,0.000031244075],"category_scores_gemma":[0.000014916283,0.00007713902,0.000059008064,0.00037475367,0.00013453503,0.00015620563,0.00071585074,0.00015056114,0.000056934114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026734087,0.00031528165,0.0000034026987,0.00027031015,0.00004852153,0.000016432421,0.009235158,0.0014596389,0.010167007,0.9583825,0.00050603785,0.01956899],"study_design_scores_gemma":[0.0053523704,0.00079038896,0.0007009023,0.00075227756,0.00011771841,0.00014019343,0.011221717,0.32791725,0.105043255,0.5381166,0.008087312,0.001760025],"about_ca_topic_score_codex":0.000020590347,"about_ca_topic_score_gemma":0.0000032676826,"teacher_disagreement_score":0.5218012,"about_ca_system_score_codex":0.000019864,"about_ca_system_score_gemma":0.00009434463,"threshold_uncertainty_score":0.3145638},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025244966,0.00009671309,0.971489,0.00006592966,0.0002989452,0.00022562842,0.000012827919,0.00015194836,0.0024140112],"genre_scores_gemma":[0.43098897,0.00001708306,0.5686697,0.00009387676,0.00002464981,0.000024608122,0.000013779635,0.0000062518507,0.00016112404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877447,0.000047894122,0.0003175085,0.00036271944,0.00021296105,0.00028445025],"domain_scores_gemma":[0.9991958,0.00018225696,0.00012876015,0.00037189003,0.0000504196,0.000070881295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025003086,0.00013262835,0.00020251435,0.000068906505,0.00017751871,0.000092803326,0.0005018364,0.00006138625,0.000025797954],"category_scores_gemma":[0.00008925011,0.00009661874,0.00010610699,0.00025370307,0.00005812959,0.0006923561,0.00024564803,0.00006909296,0.0000029754356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024040131,0.0009884958,0.0151412515,0.000057031673,0.00010909493,0.00001885761,0.0003524772,0.000040658582,0.00790459,0.5807897,0.004127449,0.39044634],"study_design_scores_gemma":[0.004704749,0.0012096049,0.027335146,0.0001681436,0.00005725182,0.00009006464,0.00053778396,0.66481197,0.18992175,0.09557099,0.014054209,0.0015383436],"about_ca_topic_score_codex":0.00009009344,"about_ca_topic_score_gemma":0.000027221455,"teacher_disagreement_score":0.6647713,"about_ca_system_score_codex":0.000019033514,"about_ca_system_score_gemma":0.000028098008,"threshold_uncertainty_score":0.3939998},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34607902,0.0007777838,0.5737181,0.0015207838,0.004425378,0.0060560983,0.0003764941,0.001205758,0.0658406],"genre_scores_gemma":[0.9816943,0.0013439943,0.013767829,0.00012326859,0.0005825869,0.001114208,0.00015934127,0.000059171434,0.0011553185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938962,0.0000475114,0.0014319284,0.0021603566,0.0014748242,0.0009891869],"domain_scores_gemma":[0.99398786,0.000092028626,0.0009797121,0.00047981492,0.0039305524,0.00053005246],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008634367,0.0008703531,0.0009058184,0.0007972335,0.00056453916,0.0024917389,0.0031041899,0.0005374637,0.000026015023],"category_scores_gemma":[0.00014667801,0.0008331711,0.00011928112,0.00054473797,0.00039126433,0.0033502846,0.00037734886,0.0007220523,0.000028498094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021416861,0.0007588687,0.016779685,0.00051757763,0.000079048405,0.000009922134,0.003960038,0.0001310538,0.0075193383,0.9634859,0.0031024443,0.0034419724],"study_design_scores_gemma":[0.0013394759,0.0005735128,0.010115162,0.0007454914,0.0000264553,0.0002574032,0.0047973413,0.9739854,0.00030443756,0.0035114945,0.0032727898,0.0010710721],"about_ca_topic_score_codex":0.0002257597,"about_ca_topic_score_gemma":0.000004535499,"teacher_disagreement_score":0.9738543,"about_ca_system_score_codex":0.00036171745,"about_ca_system_score_gemma":0.00054338766,"threshold_uncertainty_score":0.9994119},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021899897,0.000023171906,0.9596028,0.00055984495,0.00024091086,0.000027834038,1.880642e-7,0.00015546197,0.0371998],"genre_scores_gemma":[0.8906427,0.0000018482348,0.10722584,0.0011756282,0.00009283359,0.0000019256681,0.0000010026462,0.0000031715767,0.0008550173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994359,0.000025039235,0.00008888918,0.00019432075,0.00012548479,0.00013035185],"domain_scores_gemma":[0.99938613,0.00006188561,0.000025425054,0.0004464479,0.000019342517,0.000060789393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015799646,0.000059394908,0.00007153858,0.000027427486,0.00008305369,0.00012207041,0.0005758243,0.000021817685,0.00003481342],"category_scores_gemma":[0.000021081885,0.0000419682,0.000024305147,0.00007250924,0.000005843277,0.00042247196,0.00028623902,0.000055421595,0.00021150742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.640794e-7,0.000010297259,0.00008422377,9.895339e-7,0.000001266862,8.64202e-7,0.000071407405,0.00000303037,0.0003928166,0.19286336,0.004817689,0.8017536],"study_design_scores_gemma":[0.0003452061,0.000058672456,0.003022763,0.000015482845,0.0000013095157,0.000009403732,0.00002011253,0.77051926,0.0022691076,0.014122124,0.20944212,0.00017443315],"about_ca_topic_score_codex":0.00007394361,"about_ca_topic_score_gemma":0.000020330837,"teacher_disagreement_score":0.88845277,"about_ca_system_score_codex":0.000005671869,"about_ca_system_score_gemma":0.000008797004,"threshold_uncertainty_score":0.27185705},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032945024,0.000058099155,0.9718112,0.0004715229,0.000095993346,0.000046447487,0.000015014247,0.00011057737,0.024096644],"genre_scores_gemma":[0.5770499,0.000020596086,0.4137225,0.00070488366,0.00019395494,0.000022552167,0.00007424384,0.0000066455273,0.008204724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996462,0.0000046498003,0.000058959387,0.00013758213,0.000069854155,0.00008277391],"domain_scores_gemma":[0.99974775,0.000009430969,0.000014303064,0.00019156573,0.00001151312,0.00002541676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000029282724,0.00003796271,0.000033287804,0.000021295953,0.00008106362,0.000080656915,0.00015017146,0.0000127883895,0.000082877115],"category_scores_gemma":[0.0000015967581,0.00002894213,0.000008886687,0.00006318041,0.000012065285,0.00033564135,0.00018794961,0.000023351084,0.000025490855],"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":[7.972324e-7,0.00009031794,0.0003858641,0.0000042200013,0.0000045989004,0.000007895543,0.0000245759,0.000011067187,0.0023322345,0.47987366,0.3147738,0.20249097],"study_design_scores_gemma":[0.0014162534,0.00015235868,0.15943378,0.00002345542,0.000006729591,0.00003613059,0.000018558545,0.2294877,0.007645282,0.11993192,0.481328,0.0005198053],"about_ca_topic_score_codex":0.0002344682,"about_ca_topic_score_gemma":0.000010896049,"teacher_disagreement_score":0.5737554,"about_ca_system_score_codex":0.000003947334,"about_ca_system_score_gemma":0.0000062733257,"threshold_uncertainty_score":0.11802258},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00072014413,0.00014104505,0.9939825,0.0033274237,0.0003639835,0.00047667712,0.000025797857,0.0001055358,0.0008569078],"genre_scores_gemma":[0.1424337,0.00008213738,0.85590607,0.0007892408,0.0003540636,0.000039498245,0.00010895502,0.000012495888,0.00027382476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902976,0.00003333821,0.0001695341,0.00041157645,0.00016429262,0.00019150297],"domain_scores_gemma":[0.99869156,0.0001558981,0.00006490633,0.0009909346,0.000035397432,0.000061284736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046266214,0.00010375785,0.00013590619,0.000022503353,0.00032958252,0.0003174665,0.0014489708,0.00003967224,0.0000064668952],"category_scores_gemma":[0.000032695178,0.00005509211,0.000021550619,0.00008665523,0.00007264509,0.00090387056,0.0018966617,0.00007754989,0.0000054344546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019846777,0.00010038272,0.00002824842,0.0000601966,0.000026467605,0.0000053032877,0.00088637497,0.00041595075,0.0017711681,0.74990875,0.021451835,0.22514686],"study_design_scores_gemma":[0.008523411,0.00009897731,0.00017678321,0.00014192128,0.000016249738,0.000030520892,0.000050808856,0.842771,0.0024813043,0.07757905,0.06781615,0.00031383868],"about_ca_topic_score_codex":0.00016183013,"about_ca_topic_score_gemma":0.000015111489,"teacher_disagreement_score":0.842355,"about_ca_system_score_codex":0.000009979989,"about_ca_system_score_gemma":0.00003900544,"threshold_uncertainty_score":0.30613366},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021420813,0.00014776342,0.9967506,0.000074737334,0.00015368272,0.00025899592,0.000004409968,0.0000319188,0.00043578853],"genre_scores_gemma":[0.6110836,0.0000028941133,0.38866627,0.00007858873,0.00009384668,0.00002245583,0.0000383857,0.000003485955,0.00001041003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991206,0.00005908714,0.00034902644,0.00016297205,0.00015766789,0.00015067963],"domain_scores_gemma":[0.999388,0.00013257388,0.0001305341,0.00026653416,0.00006716489,0.000015210594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002618723,0.000069499976,0.00010511303,0.00013048305,0.00010327879,0.00006991818,0.0004034419,0.000035762696,0.0000030232422],"category_scores_gemma":[0.000019221454,0.000048471687,0.000035764748,0.00083385134,0.000014868615,0.0002099156,0.000072503804,0.000044098615,8.5145246e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040293667,0.00033210535,0.026053462,0.00002176542,0.0000066902844,0.00000404562,0.00023465967,0.2743402,0.000023833676,0.41045275,0.008722481,0.27980393],"study_design_scores_gemma":[0.00018628969,0.00002591208,0.06238052,0.00000870019,0.0000030088147,0.0000026234607,0.000019310757,0.9305207,0.000023829212,0.0065277545,0.0002380818,0.00006326386],"about_ca_topic_score_codex":0.00034497704,"about_ca_topic_score_gemma":0.000036850495,"teacher_disagreement_score":0.6561805,"about_ca_system_score_codex":0.000011229774,"about_ca_system_score_gemma":0.000017628456,"threshold_uncertainty_score":0.19766182},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049609817,0.00008927189,0.96178955,0.0059330133,0.00038452476,0.00041188963,0.000020602209,0.00028087548,0.02612932],"genre_scores_gemma":[0.92877686,0.000021110805,0.068079814,0.0025205102,0.00028016587,0.000018975372,0.000042565178,0.000023591305,0.00023642514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981256,0.000007896663,0.00025340967,0.0005972963,0.0006010583,0.00041472184],"domain_scores_gemma":[0.9987065,0.0001497326,0.000099805045,0.0008138381,0.00009853915,0.00013154886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010659767,0.00019376265,0.00015063846,0.00008403982,0.00035233286,0.0002945246,0.003227889,0.00008054141,0.000044039476],"category_scores_gemma":[0.000042386226,0.00011557284,0.00004182365,0.00032246282,0.000063188454,0.0010358708,0.0005737237,0.00029225723,0.000056830762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039017576,0.0009320812,0.0020028031,0.00018453659,0.000043744138,0.00004795776,0.0020703983,0.00018599133,0.0068895444,0.20469943,0.24030204,0.5422513],"study_design_scores_gemma":[0.0006601841,0.00010765875,0.0024143304,0.00017307325,0.000008252056,0.000010024508,0.00008406772,0.8389505,0.0049815117,0.0026422413,0.14964506,0.00032310258],"about_ca_topic_score_codex":0.000019805108,"about_ca_topic_score_gemma":0.0000021656147,"teacher_disagreement_score":0.92381585,"about_ca_system_score_codex":0.000026867481,"about_ca_system_score_gemma":0.000033816144,"threshold_uncertainty_score":0.59982747},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005953467,0.00021804961,0.9713143,0.004922852,0.00021464804,0.0006480877,0.000020834588,0.00021676709,0.016490983],"genre_scores_gemma":[0.65849054,0.00005875489,0.33613375,0.0009944855,0.00039616472,0.000084372274,0.000022005494,0.000025599462,0.0037943253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744356,0.000121375815,0.00022091532,0.0006097627,0.0008541008,0.0007503098],"domain_scores_gemma":[0.99811786,0.00019752,0.000032441785,0.0011086381,0.0003293578,0.00021420147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011078033,0.00014357986,0.00018614192,0.00022745135,0.00038428197,0.0004281487,0.0020120223,0.00012112444,0.00007028774],"category_scores_gemma":[0.00007745412,0.00011882187,0.000088485845,0.0004872659,0.00007096365,0.0012993838,0.0004527671,0.00034079203,0.00016758736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047020803,0.00011087887,0.000020181957,0.000012957524,0.000008834648,0.000016544154,0.00039301024,0.000007785983,0.0014572884,0.05237754,0.089156784,0.8563912],"study_design_scores_gemma":[0.0007446699,0.00048591068,0.0011381974,0.000038842554,0.0000022160032,0.000013631217,0.000045710305,0.8337148,0.0007763565,0.12112268,0.041677795,0.00023920312],"about_ca_topic_score_codex":0.000024345287,"about_ca_topic_score_gemma":0.0000011364557,"teacher_disagreement_score":0.85615194,"about_ca_system_score_codex":0.00007721621,"about_ca_system_score_gemma":0.00012295284,"threshold_uncertainty_score":0.48454154},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014602063,0.00007210833,0.9846515,0.0005117989,0.0006783282,0.00033779605,0.000008232999,0.00017221816,0.012107809],"genre_scores_gemma":[0.52877474,0.00004719851,0.45562643,0.0059653344,0.0015904397,0.00005191449,0.00004436044,0.000040537205,0.007859073],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986456,0.000018027604,0.00027352828,0.00040739254,0.00031875932,0.00033669668],"domain_scores_gemma":[0.9988042,0.00026318742,0.000094037314,0.0005851518,0.00011551511,0.00013789807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004877389,0.00013747238,0.00018027987,0.0001027659,0.00025081093,0.00037009225,0.0015452149,0.00008527813,0.00012218927],"category_scores_gemma":[0.000022731127,0.00010027176,0.0000821737,0.00023167816,0.000023096174,0.0011076573,0.0007941538,0.000091137,0.000028383969],"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":[0.0002865388,0.00027271354,0.0036730147,0.00003566215,0.000032410033,0.000020368127,0.00046251906,0.00008837215,0.0017276936,0.06691426,0.20252487,0.7239616],"study_design_scores_gemma":[0.006482041,0.0001314281,0.015339258,0.00006703009,0.00000801448,0.000012524204,0.000023976829,0.27481374,0.026705734,0.015371941,0.66051,0.0005342901],"about_ca_topic_score_codex":0.000057835583,"about_ca_topic_score_gemma":0.000018650306,"teacher_disagreement_score":0.7234273,"about_ca_system_score_codex":0.000020849753,"about_ca_system_score_gemma":0.000043838405,"threshold_uncertainty_score":0.40889636},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007261759,0.0000467799,0.99013734,0.001662368,0.00021020931,0.00039881098,0.00012310408,0.00010847484,0.000051178045],"genre_scores_gemma":[0.28215784,0.000012869366,0.7172794,0.00034377174,0.000051686267,0.000044912744,0.00005672246,0.000004628466,0.000048185448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902177,0.000043146134,0.00032946758,0.00022651975,0.00011268585,0.00026640831],"domain_scores_gemma":[0.9990232,0.00041464734,0.000075641205,0.00026948174,0.00012739222,0.00008961761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023286142,0.00015335003,0.00016736693,0.00019151621,0.00046748653,0.000070636015,0.00042391528,0.00014651252,0.000009541918],"category_scores_gemma":[0.000017657529,0.00012849801,0.000062586325,0.0001637497,0.000116818475,0.000479474,0.00002691841,0.00019215865,0.000030433357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009513484,0.00026520927,0.000039779465,0.00007683975,0.00008716261,0.0000012945434,0.0013881805,0.22967619,0.000700588,0.01161345,0.00022791898,0.75582826],"study_design_scores_gemma":[0.0008148417,0.00031719517,0.00008983558,0.000020449339,0.0000063057305,0.000037036883,0.00004773337,0.9898069,0.0019113177,0.0042311274,0.0025432573,0.00017402465],"about_ca_topic_score_codex":0.000006788285,"about_ca_topic_score_gemma":0.0000054572192,"teacher_disagreement_score":0.7601307,"about_ca_system_score_codex":0.000029900219,"about_ca_system_score_gemma":0.00007731104,"threshold_uncertainty_score":0.5239997},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37371188,0.000024557952,0.59571725,0.0003405197,0.00044776784,0.00050718145,0.00005427938,0.00009464083,0.029101925],"genre_scores_gemma":[0.96532047,0.0000019379604,0.03429193,0.000298239,0.0000068464133,0.000007051701,0.000016211226,0.0000029806033,0.000054333388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907273,0.000044522738,0.0003904974,0.00008560432,0.0002781354,0.00012851515],"domain_scores_gemma":[0.99891436,0.0000896629,0.0002596651,0.0006219968,0.00007803485,0.000036294008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027712848,0.00008583881,0.00014769309,0.000067422996,0.00007457861,0.000042922526,0.00065620936,0.00003150821,0.00021950631],"category_scores_gemma":[0.000037878453,0.000054456836,0.000043881213,0.00022961221,0.00008800404,0.00056446705,0.00029047622,0.000076375545,0.000034834957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018318245,0.0013854714,0.0007050278,0.000263441,0.00010813086,0.0000033013082,0.023530472,0.000054799453,0.0063972278,0.8711096,0.028444607,0.06781472],"study_design_scores_gemma":[0.0035308911,0.003852556,0.06494534,0.0018977441,0.00005652535,0.00004354273,0.0017869521,0.6224344,0.20147504,0.06741751,0.031442083,0.0011174435],"about_ca_topic_score_codex":0.00004895966,"about_ca_topic_score_gemma":0.0000017841538,"teacher_disagreement_score":0.8036921,"about_ca_system_score_codex":0.000020266232,"about_ca_system_score_gemma":0.000019717836,"threshold_uncertainty_score":0.24034403},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013723244,0.00009056591,0.9711008,0.00021198615,0.00061975425,0.00010892553,0.0000031932584,0.00031561116,0.02617686],"genre_scores_gemma":[0.19282494,0.0000028841698,0.8061996,0.00045238726,0.000044390566,0.0000079125875,0.000008148889,0.000010227347,0.00044953031],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985674,0.0001073962,0.00023646007,0.0004480523,0.0003175263,0.0003231751],"domain_scores_gemma":[0.99882996,0.00015385193,0.00008959581,0.00070621766,0.00007329122,0.00014708367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025587497,0.00016279217,0.00016784764,0.000091055736,0.00022705637,0.0002087974,0.00065559504,0.0000679199,0.00025727256],"category_scores_gemma":[0.000053437503,0.00012542258,0.00005738798,0.00033960692,0.0000538967,0.00052189664,0.00019118428,0.00015568886,0.000111926514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000487418,0.00015434573,0.0020894466,0.000016190941,0.000012113782,0.00004051498,0.00007632637,0.00029953598,0.0013500787,0.2923489,0.007978644,0.69562906],"study_design_scores_gemma":[0.0013056141,0.00006539536,0.0004903737,0.00010045219,0.0000054541247,0.00007494427,0.00015575743,0.87134516,0.045619354,0.0048014205,0.075473025,0.000563056],"about_ca_topic_score_codex":0.000029172606,"about_ca_topic_score_gemma":0.0000027721774,"teacher_disagreement_score":0.8710456,"about_ca_system_score_codex":0.000034616507,"about_ca_system_score_gemma":0.000085960695,"threshold_uncertainty_score":0.51145846},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016474446,0.00013887094,0.94353545,0.00026812204,0.000118701435,0.00008975174,0.0000025933564,0.00022827409,0.053970795],"genre_scores_gemma":[0.96272194,0.000011151239,0.036203105,0.00017294407,0.000112827496,0.0000074500995,0.0000030255192,0.0000068731274,0.00076068606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992042,0.000045307705,0.00006278266,0.00022498169,0.00022298157,0.00023972424],"domain_scores_gemma":[0.99948865,0.0000739993,0.000041326093,0.0002360778,0.00005531116,0.00010461706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014576425,0.00009968545,0.00008696102,0.000054573018,0.0001747617,0.00006633746,0.00026467926,0.000024581092,0.000044012784],"category_scores_gemma":[0.000023895796,0.00006209823,0.000019206745,0.0001594394,0.000021043026,0.0007456287,0.00019803934,0.00018894997,0.00005812726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010693565,0.00033512563,0.016393624,0.0000064224896,0.00006335187,0.000017658125,0.008501253,0.0009562757,0.00025052548,0.9472049,0.0013770344,0.0247869],"study_design_scores_gemma":[0.0011488763,0.0015121904,0.021330023,0.0001129727,0.0000152066605,0.000070360096,0.0017838825,0.9529682,0.0024525435,0.0014483677,0.016630733,0.00052664283],"about_ca_topic_score_codex":0.000122184,"about_ca_topic_score_gemma":0.0000027124643,"teacher_disagreement_score":0.9610745,"about_ca_system_score_codex":0.0000665539,"about_ca_system_score_gemma":0.000016681199,"threshold_uncertainty_score":0.25322923},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050151077,0.0004834905,0.9979559,0.00041733833,0.0003048171,0.00031795548,0.000079589314,0.00008958603,0.0003011512],"genre_scores_gemma":[0.05740815,0.00005957837,0.9416109,0.00022879473,0.000056361114,0.000014899078,0.00005088696,0.000010378888,0.00056009885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988178,0.0000517256,0.00025305492,0.00042495804,0.00024466641,0.00020778905],"domain_scores_gemma":[0.9966926,0.00029933263,0.000112437985,0.0027307738,0.00008910446,0.00007573788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028077074,0.00011387159,0.00018914689,0.00005181805,0.00010099468,0.00007537913,0.0041216845,0.000052538184,0.00007240504],"category_scores_gemma":[0.00007348686,0.00008445774,0.000029655648,0.0001330864,0.000046434776,0.00083914207,0.0021140196,0.000057432728,0.0000147372375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022707678,0.0002367212,0.00004602659,0.00003602308,0.000019237383,0.000004386429,0.00014802415,0.0003455963,0.0015885665,0.029542712,0.47883025,0.48917973],"study_design_scores_gemma":[0.00077577325,0.00008791758,0.000035801615,0.000036783644,0.000004869557,0.000004431348,0.000013137556,0.97613174,0.0016922207,0.003777788,0.017314805,0.00012475735],"about_ca_topic_score_codex":0.000046606572,"about_ca_topic_score_gemma":0.0000027972328,"teacher_disagreement_score":0.9757861,"about_ca_system_score_codex":0.0000075179273,"about_ca_system_score_gemma":0.000013764868,"threshold_uncertainty_score":0.76591843},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556815,0.003289057,0.03499599,0.0006300199,0.0010868488,0.0011478927,0.00032688584,0.00037026466,0.0024715478],"genre_scores_gemma":[0.3714932,0.00037868097,0.3718551,0.00038362617,0.0005754789,0.000011221626,0.0013945079,0.00022770803,0.25368047],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867254,0.000076089425,0.00012484883,0.00046105133,0.0003470403,0.00031839914],"domain_scores_gemma":[0.998889,0.000049689224,0.00033037228,0.00045874884,0.00015422226,0.00011793946],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024187898,0.00025846387,0.00036002745,0.00022272904,0.00025121853,0.00005630306,0.0006975548,0.00026316373,0.00008148734],"category_scores_gemma":[0.0000053287454,0.00026709313,0.00009864752,0.00018225504,0.00007805732,0.00081417,0.00014598233,0.00024029324,0.000031398515],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009527528,0.001277011,0.045261025,0.005047724,0.00092249847,0.0003299789,0.7724693,0.00032741507,0.0155297015,0.022164728,0.012904341,0.12281354],"study_design_scores_gemma":[0.024649493,0.0028264718,0.29369757,0.015189109,0.0021078822,0.00007712541,0.25776997,0.3280734,0.005143104,0.009751069,0.048250485,0.012464318],"about_ca_topic_score_codex":0.041175537,"about_ca_topic_score_gemma":0.016376397,"teacher_disagreement_score":0.5841883,"about_ca_system_score_codex":0.00004969999,"about_ca_system_score_gemma":0.00009832259,"threshold_uncertainty_score":0.9999781},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022146087,0.000036320856,0.99306726,0.001486485,0.00026377663,0.0002200707,0.000007307957,0.00019035231,0.0025137991],"genre_scores_gemma":[0.5085235,0.0000021704016,0.48934573,0.00083468144,0.00031202877,0.000044158176,0.000009102995,0.000008157229,0.00092042267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999193,0.000009783192,0.00013442793,0.00030432193,0.00015103111,0.00020743556],"domain_scores_gemma":[0.9993975,0.00008205552,0.000042385804,0.0003892621,0.00004013156,0.00004864536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012483864,0.00009325128,0.000085759944,0.00006413686,0.00016954314,0.00032122363,0.000450595,0.000034784855,0.00003061053],"category_scores_gemma":[0.000018259796,0.0000695231,0.00006149238,0.00014428626,0.000011086633,0.0014572763,0.00012043994,0.00005294802,0.00001838426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025075542,0.00031205697,0.001333123,0.000032475953,0.000019585872,0.00000248097,0.00014324911,0.0051734606,0.0020201802,0.22815362,0.019642293,0.7431424],"study_design_scores_gemma":[0.00038977634,0.000059062724,0.00083537877,0.000013502129,0.0000023349578,0.000002024289,0.000006421309,0.97323203,0.007875265,0.0011292337,0.016326401,0.00012857428],"about_ca_topic_score_codex":0.000036831003,"about_ca_topic_score_gemma":0.000013181751,"teacher_disagreement_score":0.9680586,"about_ca_system_score_codex":0.000032294924,"about_ca_system_score_gemma":0.00006706026,"threshold_uncertainty_score":0.3097567},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030228887,0.000113061564,0.99444324,0.00006260783,0.00013849483,0.00037740404,0.00041808328,0.00017260473,0.001251634],"genre_scores_gemma":[0.15258065,0.000016438677,0.8467531,0.00012689398,0.00018436006,0.000030540465,0.00021490952,0.000024873842,0.00006822483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985785,0.00000885096,0.00028728912,0.0005241717,0.00031355632,0.00028766497],"domain_scores_gemma":[0.9971618,0.000088619185,0.00013929777,0.002451173,0.000034981073,0.00012412365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015875287,0.00020727815,0.0002356298,0.0000388025,0.00019548988,0.00031015987,0.0023883772,0.00007486316,0.000074574185],"category_scores_gemma":[0.000019997924,0.00015981981,0.00003221767,0.00010698154,0.000053115742,0.00077491807,0.0006862063,0.00011366594,0.000016549438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014991352,0.00047531235,0.000018947068,0.00031199068,0.000060960276,0.00002168631,0.0073443204,0.0003191741,0.03175717,0.7330649,0.01784018,0.20877036],"study_design_scores_gemma":[0.00030860252,0.000054939614,0.000029730596,0.000039755712,0.000020230078,0.00001902912,0.00028038913,0.9445481,0.0019198263,0.049528144,0.0029329194,0.0003183784],"about_ca_topic_score_codex":0.0000037712798,"about_ca_topic_score_gemma":0.000004090859,"teacher_disagreement_score":0.9442289,"about_ca_system_score_codex":0.000011811666,"about_ca_system_score_gemma":0.000014459991,"threshold_uncertainty_score":0.65172625},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9896599,0.00010696723,0.005871165,0.0012561051,0.00042022235,0.00028858075,0.0000016094335,0.000045412104,0.0023500375],"genre_scores_gemma":[0.99581367,0.000018186865,0.003920101,0.00011052737,0.000045611036,0.0000054036295,1.5770617e-7,0.0000022697122,0.00008407359],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992772,0.0000035423705,0.00019048493,0.00014916428,0.00025747836,0.00012218136],"domain_scores_gemma":[0.99942565,0.00001307156,0.00024406948,0.00019179333,0.00010563311,0.000019780882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025434513,0.00007576347,0.0000893066,0.000033290897,0.00011935916,0.000048351416,0.0010428762,0.000019749727,0.0000026095545],"category_scores_gemma":[0.00002340537,0.00003840383,0.000055688088,0.00020758173,0.000039038434,0.00041505916,0.00039129908,0.0000947562,9.9872e-7],"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":[0.00004561078,0.0002133638,0.0025204783,0.00012642538,0.000023315573,1.480345e-7,0.0025236201,0.00008246111,0.64970684,0.03870257,0.0029585336,0.30309665],"study_design_scores_gemma":[0.00029482544,0.00038693903,0.010202835,0.00017579478,0.000012497981,0.000015023254,0.00016391465,0.112933174,0.87336427,0.0012446936,0.0010958471,0.00011018949],"about_ca_topic_score_codex":0.000050286628,"about_ca_topic_score_gemma":4.4382548e-7,"teacher_disagreement_score":0.30298647,"about_ca_system_score_codex":0.000030518004,"about_ca_system_score_gemma":0.000013238782,"threshold_uncertainty_score":0.19379407},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002487749,0.000012379175,0.85864514,0.00086428435,0.00013517927,0.0001237436,0.000001074631,0.000105178886,0.13986422],"genre_scores_gemma":[0.22694898,0.000019527652,0.7592417,0.00951639,0.00015011938,0.0000161648,0.000015396103,0.0000054931625,0.0040862183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993764,0.000017115524,0.00013947226,0.00012702929,0.00020204356,0.00013789619],"domain_scores_gemma":[0.99942654,0.000042271415,0.000026020862,0.00037983648,0.000034090437,0.000091243106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012984815,0.00006349113,0.000074574025,0.00007286813,0.00007415526,0.00019755893,0.00048363046,0.000037710048,0.00012503084],"category_scores_gemma":[0.000056030938,0.00004748682,0.000026400838,0.00026940333,0.000003889691,0.0013151753,0.00024553633,0.000062850675,0.0003508299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005931843,0.000104816914,0.00004554621,0.000016079839,0.000008517951,0.0000019980089,0.0017465026,0.000104832674,0.00007922043,0.028061943,0.45063877,0.51913244],"study_design_scores_gemma":[0.000857848,0.00008532178,0.0002533514,0.0000072374924,0.0000014095314,0.000011936825,0.000026058093,0.8249575,0.00055510656,0.0002763423,0.172812,0.00015589052],"about_ca_topic_score_codex":0.000022022112,"about_ca_topic_score_gemma":3.0777818e-7,"teacher_disagreement_score":0.82485265,"about_ca_system_score_codex":0.000009839748,"about_ca_system_score_gemma":0.000004903498,"threshold_uncertainty_score":0.45093256},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014284425,0.00008004826,0.982982,0.0007916422,0.00011980828,0.00012364546,3.704765e-7,0.0001729395,0.0014451107],"genre_scores_gemma":[0.7424822,0.0000024229228,0.2573736,0.00006253903,0.000033618562,0.000016423617,0.0000010871021,0.0000027565131,0.000025360045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931115,0.000039166713,0.00016241321,0.00018847716,0.00014961562,0.00014919446],"domain_scores_gemma":[0.99952614,0.00003436728,0.000044260963,0.00035508987,0.000015061027,0.000025096253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037090475,0.000067880384,0.00007633354,0.00003539315,0.00010300835,0.0001452968,0.00046114778,0.000027061815,0.0000013728561],"category_scores_gemma":[0.000014111794,0.00004004951,0.000017982413,0.00017910887,0.000010413135,0.00044708434,0.00022457703,0.00008753093,0.0000131965035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027556255,0.000047345406,0.0016149092,0.000046857193,0.000004373709,0.000023041428,0.0010555099,0.02085223,0.00026834357,0.9101631,0.00005646823,0.065865085],"study_design_scores_gemma":[0.0007491432,0.00003837361,0.026204472,0.0004302195,0.0000022413558,0.00003471669,0.0005731984,0.9635386,0.000478878,0.0069771833,0.0007212284,0.00025177366],"about_ca_topic_score_codex":0.00037529663,"about_ca_topic_score_gemma":0.00003008573,"teacher_disagreement_score":0.9426863,"about_ca_system_score_codex":0.000052508767,"about_ca_system_score_gemma":0.000019158259,"threshold_uncertainty_score":0.16331716},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011476215,0.000049984643,0.9892562,0.00811807,0.00014922177,0.00049672805,0.000027347365,0.000225058,0.0005297706],"genre_scores_gemma":[0.052829184,0.0000017445227,0.9382446,0.007598593,0.00044091232,0.0003480082,0.0002668251,0.000027442306,0.00024268148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985953,0.000024245017,0.0004509192,0.00020952291,0.00038033733,0.00033966676],"domain_scores_gemma":[0.99895865,0.00010290463,0.00036281653,0.00036830234,0.00015686279,0.000050488838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030114822,0.00019751163,0.00015628849,0.00013491408,0.0005838637,0.00080517476,0.00068391685,0.000056392226,0.0000046032965],"category_scores_gemma":[0.000008362366,0.00012577437,0.00005502529,0.00034405515,0.00009462768,0.0044431123,0.00008423546,0.00012900779,0.000051696472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032223357,0.000053573607,0.00003814511,0.000087206754,0.00002193061,0.0000027649257,0.002325453,0.001609884,0.00058746076,0.00018362753,0.17091049,0.8241472],"study_design_scores_gemma":[0.0010445998,0.000119137934,0.00033231566,0.000092601214,0.000018791397,0.000051151197,0.00015368413,0.91239804,0.00033671482,0.00012772335,0.08500137,0.00032385078],"about_ca_topic_score_codex":0.00008595125,"about_ca_topic_score_gemma":0.0000045725974,"teacher_disagreement_score":0.9107882,"about_ca_system_score_codex":0.000048966194,"about_ca_system_score_gemma":0.0001499001,"threshold_uncertainty_score":0.77643186},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028283626,0.000014260005,0.9658701,0.00015292373,0.00034008498,0.00016410516,0.00000567878,0.00012888483,0.033041157],"genre_scores_gemma":[0.08140101,0.000015822323,0.8942217,0.00041190616,0.00008337111,0.00014138025,0.0000059951017,0.0000065011327,0.023712283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994809,0.000010781394,0.00009444076,0.00020908735,0.00008237756,0.00012241155],"domain_scores_gemma":[0.99952406,0.00003857736,0.00003065255,0.0002958546,0.00006295808,0.000047905374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008254388,0.00005528493,0.000058812886,0.00005543673,0.00020382517,0.00007654394,0.00031719584,0.000024155983,0.00010259329],"category_scores_gemma":[0.00001209572,0.000041689396,0.000031612,0.00018743527,0.000014479434,0.00040174945,0.00017414917,0.00002960854,0.000021610831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014606581,0.00011536514,0.00014129595,0.000005051428,0.000020462217,0.0000036492454,0.0008256745,0.0000029339574,0.00017523578,0.8909786,0.08332803,0.024389088],"study_design_scores_gemma":[0.0019407425,0.001285521,0.0074279048,0.00006174383,0.000023532664,0.00003809739,0.00019821203,0.027887523,0.10280014,0.343148,0.5143595,0.00082909927],"about_ca_topic_score_codex":0.00017634722,"about_ca_topic_score_gemma":0.00002017803,"teacher_disagreement_score":0.54783064,"about_ca_system_score_codex":0.00001726341,"about_ca_system_score_gemma":0.00003237825,"threshold_uncertainty_score":0.17000443},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5107361,0.0002087228,0.48328096,0.00056316436,0.00006446425,0.0004811745,0.000021866725,0.00011116239,0.004532382],"genre_scores_gemma":[0.96998465,0.00015843622,0.027261814,0.000030040297,0.00007494852,0.00006666726,0.000045198474,0.0000127724525,0.0023654664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980927,0.0002602666,0.00015212291,0.0004932821,0.00061704806,0.00038456384],"domain_scores_gemma":[0.9984814,0.000096662654,0.0000117441095,0.0008896836,0.00029772503,0.00022280913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047263765,0.00012029653,0.00012847256,0.00012757449,0.00081591035,0.0008115542,0.0005164207,0.000054598677,0.00039492175],"category_scores_gemma":[0.000037476468,0.00008583366,0.00001651913,0.00067128707,0.00014772928,0.0014057548,0.00024795526,0.00028572342,0.0001832335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024517885,0.0031539178,0.049949773,0.00007730133,0.0001617148,0.0009673906,0.012648701,0.0032546676,0.008355089,0.09514139,0.02073332,0.80531156],"study_design_scores_gemma":[0.0020092549,0.00034103138,0.0077370545,0.000046093206,0.0000040650057,0.00009574076,0.00024424994,0.9845737,0.0022162702,0.00007524116,0.0024146147,0.0002426771],"about_ca_topic_score_codex":0.0004465804,"about_ca_topic_score_gemma":0.00042190208,"teacher_disagreement_score":0.981319,"about_ca_system_score_codex":0.000031104886,"about_ca_system_score_gemma":0.000044823282,"threshold_uncertainty_score":0.7825836},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013226697,0.00014012035,0.99516165,0.00016769409,0.002077803,0.0004337243,0.000058054364,0.00037025698,0.0002680534],"genre_scores_gemma":[0.9378502,0.0000030406502,0.061443478,0.00026761278,0.00010003966,0.00017668231,0.000050666513,0.0000060221396,0.00010230236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990122,0.000033849712,0.00031394904,0.00010077145,0.00027974937,0.00025951295],"domain_scores_gemma":[0.9988409,0.00017471325,0.00013169936,0.00066119083,0.000096296775,0.0000951454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028565276,0.00012657078,0.00012336596,0.00019987574,0.00027362272,0.00025834882,0.00056159665,0.00007163437,0.000008799624],"category_scores_gemma":[0.00001826845,0.000103231774,0.000076365286,0.00025041235,0.000009674152,0.003988056,0.000010167689,0.00012036559,0.00019274693],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105991996,0.00050104,0.00020539966,0.00060704263,0.00014854717,9.011568e-7,0.018543754,0.02220205,0.00025547916,0.0121897,0.008516783,0.9367233],"study_design_scores_gemma":[0.0016931993,0.00011824174,0.0007294498,0.00013025524,0.00002426454,0.00002796518,0.001219958,0.7470699,0.0032395157,0.000032978725,0.24521342,0.0005008821],"about_ca_topic_score_codex":0.00003905144,"about_ca_topic_score_gemma":0.0000013440897,"teacher_disagreement_score":0.9365275,"about_ca_system_score_codex":0.00006745898,"about_ca_system_score_gemma":0.000040981457,"threshold_uncertainty_score":0.42096695},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35444397,0.00008739028,0.6296407,0.0060846326,0.0011815799,0.0005709988,0.000049160833,0.00011056496,0.007831011],"genre_scores_gemma":[0.95355046,0.000017842194,0.04465963,0.00082929316,0.00005023342,0.000016712747,0.0000017426706,0.000007628005,0.00086648384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986599,0.00014974149,0.00024592874,0.00029757223,0.0004340767,0.00021278278],"domain_scores_gemma":[0.99761355,0.00047142516,0.000085408574,0.0017517166,0.000041369247,0.00003655017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004943117,0.00011495907,0.00014213633,0.00004138733,0.00024697726,0.000031969194,0.0023266051,0.0000521872,0.00006792178],"category_scores_gemma":[0.00020636566,0.00005489411,0.00007058479,0.00046449486,0.00013651347,0.00030197328,0.00096749334,0.00023347132,0.000011977635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004473008,0.0014116813,0.027743071,0.00004681078,0.000049709302,0.00007026361,0.006985169,0.0015062841,0.0009004563,0.58470076,0.16055475,0.2159863],"study_design_scores_gemma":[0.00112057,0.00015899086,0.23356612,0.00014794825,0.0000044930316,0.000044155975,0.000119585406,0.6912671,0.00936499,0.057732034,0.006063923,0.00041013779],"about_ca_topic_score_codex":0.0004549641,"about_ca_topic_score_gemma":0.00007509155,"teacher_disagreement_score":0.68976074,"about_ca_system_score_codex":0.00004200985,"about_ca_system_score_gemma":0.000079650075,"threshold_uncertainty_score":0.43234497},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043060586,0.00010144179,0.9532863,0.0014059835,0.000034718403,0.00019679834,0.000003046342,0.000033430388,0.0018776912],"genre_scores_gemma":[0.74663496,0.000011518151,0.25323522,0.00008519632,0.000009269211,0.0000075727007,0.0000024406424,0.0000015008827,0.00001230958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936664,0.00005586295,0.00016789591,0.0001674528,0.00015433403,0.00008782187],"domain_scores_gemma":[0.9993272,0.00012223679,0.00007022969,0.00043706756,0.000025836052,0.000017442486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026682025,0.000055022767,0.000080382706,0.000057976697,0.00006907484,0.000058036072,0.0004907045,0.000023773793,0.000008812056],"category_scores_gemma":[0.000048114915,0.00003676219,0.000012983218,0.00019863558,0.000044010663,0.0003575759,0.00020500185,0.00005945744,0.000002386108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009094154,0.00068730797,0.0051095793,0.0001635326,0.000012883714,0.0000051167185,0.0162397,0.00021103212,0.008156064,0.50098014,0.003909511,0.46451604],"study_design_scores_gemma":[0.00026415108,0.000016706155,0.020147884,0.000018485474,0.0000013471051,0.0000055718565,0.00013318888,0.9742112,0.0005035224,0.0045198114,0.00012664379,0.00005149935],"about_ca_topic_score_codex":0.0000855182,"about_ca_topic_score_gemma":0.00002187372,"teacher_disagreement_score":0.97400016,"about_ca_system_score_codex":0.000008013565,"about_ca_system_score_gemma":0.000002444468,"threshold_uncertainty_score":0.14991185},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02829029,0.00001151917,0.9624839,0.0001535284,0.000036458674,0.00016979805,0.000004962304,0.00006269826,0.0087868385],"genre_scores_gemma":[0.927526,0.000016109605,0.07233978,0.000068498346,0.000008207204,0.000024496492,0.000007084206,0.000002482157,0.0000073546535],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99950975,0.00002349322,0.00019930457,0.000110648165,0.000101956044,0.000054851305],"domain_scores_gemma":[0.99921685,0.00003467763,0.00014852059,0.0004788289,0.00010378878,0.000017358614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000233624,0.000050189992,0.00007428847,0.000051803836,0.000038704762,0.000014110567,0.00067423726,0.00003004825,0.000038497084],"category_scores_gemma":[0.0000064032374,0.000032381016,0.000018239349,0.00012510868,0.000024016475,0.00029858423,0.00015310418,0.000059916332,0.000009856522],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000777893,0.000069969145,0.00005906381,0.000014271264,0.0000037056043,5.225117e-8,0.0017957145,0.0000013402041,0.0025809768,0.00040791035,0.00023082129,0.9948284],"study_design_scores_gemma":[0.00010004676,0.00014071514,0.0071995077,0.000117284966,0.0000071588956,0.0000032397459,0.0007366482,0.0041134707,0.97874975,0.008222166,0.00048715138,0.00012283077],"about_ca_topic_score_codex":0.00031674805,"about_ca_topic_score_gemma":0.000042904634,"teacher_disagreement_score":0.99470556,"about_ca_system_score_codex":0.000004908936,"about_ca_system_score_gemma":0.000007898441,"threshold_uncertainty_score":0.13204595},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004895344,0.00025069035,0.9935549,0.00043229465,0.0020437196,0.0002735875,0.000009836004,0.000121739926,0.0028236962],"genre_scores_gemma":[0.107002206,0.00007204562,0.8904663,0.0013357728,0.0007187131,0.000011714592,0.000016150574,0.000041459316,0.00033567613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962143,0.000026350826,0.0004936686,0.001648948,0.0009443131,0.0006724741],"domain_scores_gemma":[0.99733555,0.00025330175,0.00021381365,0.0018730619,0.00013127025,0.00019299299],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007437552,0.0004912692,0.0005136665,0.0008252085,0.00023478843,0.00062924484,0.004392389,0.00046829585,0.000052958178],"category_scores_gemma":[0.000068978894,0.00042325657,0.000096311385,0.0005526119,0.0006753373,0.0008616469,0.0025277284,0.00166591,0.00005934353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003263487,0.000038135153,0.00018724467,0.000015480859,0.0000022895827,0.00016334113,0.0004582944,0.00222071,0.00032615892,0.008475335,0.0000122714055,0.9880975],"study_design_scores_gemma":[0.00051192177,0.00018257124,0.0013051188,0.00058464654,0.000003938924,0.000109394416,1.6313929e-7,0.7775092,0.0023084118,0.20718555,0.009156973,0.0011421215],"about_ca_topic_score_codex":0.00013583247,"about_ca_topic_score_gemma":0.00045705243,"teacher_disagreement_score":0.98695534,"about_ca_system_score_codex":0.00019274247,"about_ca_system_score_gemma":0.0005533242,"threshold_uncertainty_score":0.9998219},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28121588,0.00047806115,0.71500194,0.0016043106,0.00029292604,0.00011782898,0.0000012706796,0.00027496536,0.0010128282],"genre_scores_gemma":[0.533895,0.00009398048,0.46415064,0.0016042005,0.000093267285,0.00003737684,0.0000027949914,0.00001062834,0.00011210258],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873215,0.00003951997,0.00013898169,0.00043536795,0.00037640578,0.0002775684],"domain_scores_gemma":[0.99888164,0.00012893541,0.000102386584,0.00053337286,0.00015143647,0.00020222433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023832542,0.00014666382,0.000120568315,0.000053392858,0.00021492923,0.00031791633,0.00049989007,0.000044505585,0.000004760724],"category_scores_gemma":[0.00020882208,0.00010736615,0.000010147395,0.0002735302,0.00008790059,0.0053246003,0.00048348808,0.00017129233,0.000044635555],"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":[0.00024150034,0.00028081067,0.047600836,0.00006622591,0.0000407927,0.00033186152,0.052659724,0.00021182786,0.00037301797,0.0032721967,0.0052387733,0.8896824],"study_design_scores_gemma":[0.002866982,0.0023513106,0.014527878,0.00042642414,0.000051660045,0.0025239848,0.008756831,0.059024908,0.007319412,0.0016489243,0.89836013,0.0021415695],"about_ca_topic_score_codex":0.00008264626,"about_ca_topic_score_gemma":0.0000017967974,"teacher_disagreement_score":0.89312136,"about_ca_system_score_codex":0.000021733913,"about_ca_system_score_gemma":0.00008305573,"threshold_uncertainty_score":0.43782642},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5775063,0.00011604449,0.42122614,0.0001515765,0.00009003781,0.00013356682,0.000033550717,0.000059288286,0.0006834674],"genre_scores_gemma":[0.9108978,0.000031451127,0.08883799,0.000020937936,0.000033074186,0.0000024872922,0.00006716109,0.0000027678602,0.000106314605],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987119,0.00019038351,0.00025571266,0.00030061905,0.00028265335,0.0002587402],"domain_scores_gemma":[0.99897265,0.00036464876,0.000054033157,0.00031518782,0.0002449817,0.00004847001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012970207,0.000077562996,0.00013099976,0.000103482664,0.00022622987,0.0000783182,0.00046646225,0.00004064225,0.000026686344],"category_scores_gemma":[0.000027229347,0.000055984463,0.000011741618,0.00040621587,0.00012185868,0.0002446938,0.00073258986,0.000109288565,0.000009795693],"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":[0.000017694085,0.00043519898,0.49046493,0.000036121182,0.000021658008,0.000007948025,0.00022654791,0.00024278904,0.0018198165,0.11795287,0.020542629,0.3682318],"study_design_scores_gemma":[0.00021963117,0.00012788759,0.84742415,0.0000068481236,5.244889e-7,0.0000031263737,0.000013210428,0.14951654,0.0014012234,0.00071515405,0.00049625087,0.00007547421],"about_ca_topic_score_codex":0.005493028,"about_ca_topic_score_gemma":0.000082199935,"teacher_disagreement_score":0.36815634,"about_ca_system_score_codex":0.000012787149,"about_ca_system_score_gemma":0.000041010928,"threshold_uncertainty_score":0.8303852},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009154583,0.0004240237,0.98258406,0.0041255555,0.0010805673,0.0005621882,0.000013369531,0.00020114121,0.010917552],"genre_scores_gemma":[0.20005403,0.0002711017,0.78078043,0.014605971,0.0021075287,0.000064668646,0.000030961066,0.00012164627,0.0019636643],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99538183,0.00006709416,0.0005480824,0.0017456741,0.0014662424,0.00079105847],"domain_scores_gemma":[0.9953548,0.0010789401,0.00035439857,0.0028368356,0.00017992758,0.00019510981],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001136836,0.0006499626,0.0005031497,0.0004557385,0.0005872334,0.00096073374,0.007325766,0.0003100723,0.00006552604],"category_scores_gemma":[0.000059256145,0.00042488784,0.00013568359,0.00059422414,0.00091715256,0.0008200011,0.002323249,0.0014092652,0.00022456361],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057407233,0.000044589746,0.000015230847,0.000014965014,0.0000069345215,0.00010335654,0.00028088677,0.01813998,0.000046162477,0.26085955,0.00034222685,0.72014034],"study_design_scores_gemma":[0.00022706045,0.00030955582,0.00012872161,0.0008745256,0.000006995175,0.00013285887,1.04006915e-7,0.4872121,0.0009972041,0.4951969,0.013971252,0.00094272936],"about_ca_topic_score_codex":0.000048397756,"about_ca_topic_score_gemma":0.00012344,"teacher_disagreement_score":0.71919763,"about_ca_system_score_codex":0.0003244781,"about_ca_system_score_gemma":0.00042517885,"threshold_uncertainty_score":0.9998203},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006818705,0.0005124644,0.9778014,0.0005195296,0.0014423965,0.00016608191,0.000034834142,0.00016018734,0.012544409],"genre_scores_gemma":[0.1448385,0.0029720764,0.84137523,0.0004233375,0.0015238973,0.000059552953,0.000059798305,0.000040943076,0.008706652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844414,0.0000418997,0.00035307044,0.00041722384,0.00045739196,0.00028626758],"domain_scores_gemma":[0.998776,0.000074422205,0.00007745049,0.0007906602,0.00014246916,0.00013896821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011941488,0.0001745957,0.00022459992,0.00008964821,0.00027453536,0.00003559113,0.000950858,0.00007499109,0.000042834654],"category_scores_gemma":[0.00003338183,0.0001514075,0.0000761864,0.0004141517,0.00011713176,0.000814561,0.00034450297,0.00016257066,0.00007338372],"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":[0.000053431297,0.0035291088,0.0053118123,0.00015230244,0.00033506574,0.00076603174,0.015652156,0.037328236,0.0019652147,0.27453318,0.33801895,0.32235453],"study_design_scores_gemma":[0.0018896535,0.00043453719,0.024205174,0.000116798,0.000028930435,0.00036066014,0.00018643508,0.44897774,0.0022941486,0.005457855,0.51467615,0.0013719326],"about_ca_topic_score_codex":0.0000902455,"about_ca_topic_score_gemma":0.000010216389,"teacher_disagreement_score":0.41164953,"about_ca_system_score_codex":0.00002810027,"about_ca_system_score_gemma":0.00015596561,"threshold_uncertainty_score":0.61742187},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019608224,0.000050524683,0.9968006,0.00015219404,0.000547649,0.00020017594,0.00014396006,0.00006256157,0.00008151099],"genre_scores_gemma":[0.5810316,0.000007741598,0.4179033,0.00055501115,0.000093359085,0.000006704914,0.0003725279,0.000007850068,0.000021861817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989801,0.00003518806,0.00017049281,0.00047905912,0.0001322933,0.00020288235],"domain_scores_gemma":[0.99898756,0.00013543002,0.000068742396,0.00068721664,0.000034758923,0.000086308166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017445657,0.00011695278,0.00012132786,0.000028178825,0.00015806212,0.0001808254,0.0006391026,0.00003453251,0.0000062564204],"category_scores_gemma":[0.00005377214,0.000084322324,0.000017612647,0.00006352677,0.00002632921,0.00037777238,0.0005681363,0.00006752966,0.0000021606722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011869041,0.00013145233,0.0009334487,0.000062141095,0.000047114332,0.000007890699,0.00024593103,0.001659633,0.00027998342,0.2904012,0.066434674,0.6397847],"study_design_scores_gemma":[0.0007245659,0.00008116624,0.001352336,0.000017920893,0.0000040550494,0.000007626489,0.000015632751,0.9710768,0.00041675576,0.0011675919,0.024973283,0.00016230704],"about_ca_topic_score_codex":0.00001216095,"about_ca_topic_score_gemma":0.0000034339855,"teacher_disagreement_score":0.96941715,"about_ca_system_score_codex":0.000010376135,"about_ca_system_score_gemma":0.000019516061,"threshold_uncertainty_score":0.34385648},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006773359,0.000015868985,0.9902973,0.0003317925,0.00063395465,0.00031484078,0.000052284035,0.00013395358,0.0014466232],"genre_scores_gemma":[0.34480268,0.0000012529541,0.6543636,0.00027955053,0.000116680094,0.000059059956,0.00012169202,0.000007996106,0.00024748707],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998977,0.000007781305,0.00014065087,0.0005068137,0.00017520394,0.00019254748],"domain_scores_gemma":[0.9976895,0.000050061597,0.000050338487,0.002064706,0.00006611152,0.00007932589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025911749,0.00008803071,0.00008103764,0.000034642275,0.00012712865,0.00011519949,0.0018035573,0.000051082145,0.000054271946],"category_scores_gemma":[0.000032462554,0.000066642075,0.0000206735,0.00011131125,0.000023482165,0.00025351945,0.0008548798,0.00009480365,0.00010474625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015145619,0.00069726544,0.000077331686,0.00003507363,0.000020040243,0.0000024929523,0.00038887004,0.0007131723,0.43848273,0.29889205,0.090971366,0.16970447],"study_design_scores_gemma":[0.00023174293,0.000017302702,0.00013102987,0.0000028587312,0.0000017860721,0.0000024708127,0.0000049538103,0.92396384,0.012991994,0.0006590385,0.061891157,0.00010180873],"about_ca_topic_score_codex":0.000040665684,"about_ca_topic_score_gemma":0.00001216211,"teacher_disagreement_score":0.9232507,"about_ca_system_score_codex":0.000006093848,"about_ca_system_score_gemma":0.00004482504,"threshold_uncertainty_score":0.3351488},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2567192,0.00023947393,0.7426613,0.0000125512,0.00016198614,0.00009066736,0.0000014534625,0.00004270534,0.00007066738],"genre_scores_gemma":[0.98357964,0.00005217965,0.016307943,0.000019984747,0.000022620072,0.00000418092,0.0000026857804,0.000004583388,0.0000061838728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991966,0.00007464361,0.00016731002,0.0002615154,0.00016097892,0.00013895883],"domain_scores_gemma":[0.9995044,0.00021144956,0.00007707366,0.00014907871,0.000021161326,0.0000368576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015089981,0.000081659964,0.000099664125,0.00020593268,0.00008722319,0.00026994824,0.000121626916,0.00003351975,0.000008058918],"category_scores_gemma":[0.000053269192,0.00006969948,0.000009586698,0.00046612887,0.000007449959,0.00074961124,0.000051968924,0.00007071415,0.000009132848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014772952,0.00032658968,0.024272475,0.00023410126,0.000021310012,0.00008749723,0.0008156091,0.013402929,0.0018349655,0.0071145836,0.00014701842,0.95172817],"study_design_scores_gemma":[0.00015987741,0.00004283578,0.001704345,0.00023121554,0.0000022206127,0.000008752192,0.000040084367,0.99718934,0.0002916969,0.00021156749,0.000009674533,0.0001083993],"about_ca_topic_score_codex":0.00024454403,"about_ca_topic_score_gemma":0.000008160439,"teacher_disagreement_score":0.9837864,"about_ca_system_score_codex":0.000046953108,"about_ca_system_score_gemma":0.0000040519467,"threshold_uncertainty_score":0.28422627},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05796655,0.00003563292,0.9208007,0.017257862,0.0008918822,0.00023016312,0.00007689882,0.00024486435,0.0024954604],"genre_scores_gemma":[0.98037,0.000069508205,0.01881794,0.00032448996,0.000039535855,0.000013567466,0.0000030371443,0.0000073937777,0.0003545297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992465,0.000048384725,0.00011949096,0.0002582855,0.00017417531,0.00015316029],"domain_scores_gemma":[0.9982662,0.00030159834,0.00003739986,0.0012757158,0.000034546196,0.000084494684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015423355,0.00010140158,0.00008252308,0.00009241621,0.0005201815,0.00017415835,0.0008729194,0.000044472818,0.00013305854],"category_scores_gemma":[0.00002172089,0.00006710457,0.000053987478,0.0002990574,0.00009782111,0.000383067,0.000025531463,0.0003479453,0.00006106264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059761984,0.0011041366,0.0010767012,0.000026296007,0.00025057796,0.000030364808,0.0032150198,0.0024508294,0.15108114,0.1172781,0.034659535,0.68876755],"study_design_scores_gemma":[0.0033742075,0.00052540033,0.038575538,0.00013591998,0.00015272741,0.00051353476,0.0011836669,0.65944123,0.037021354,0.1249829,0.13241956,0.0016739629],"about_ca_topic_score_codex":0.000059946404,"about_ca_topic_score_gemma":0.00010450175,"teacher_disagreement_score":0.92240345,"about_ca_system_score_codex":0.000004603372,"about_ca_system_score_gemma":0.000037762627,"threshold_uncertainty_score":0.40008682},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030030664,0.00015769471,0.99247193,0.00046804245,0.00097119133,0.00031457396,0.0000581254,0.00014814064,0.0053802896],"genre_scores_gemma":[0.03522275,0.000085862936,0.96351933,0.0005073563,0.00027486964,0.000009954762,0.00007319238,0.00003118692,0.0002755231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996793,0.000028180653,0.000677236,0.0010713364,0.0009545905,0.000475705],"domain_scores_gemma":[0.99726427,0.00038019443,0.0004142111,0.0014864503,0.0003063277,0.00014853757],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045973322,0.00038170628,0.0004592392,0.00085256837,0.00028804233,0.00030043678,0.003177579,0.0001659374,0.00006328439],"category_scores_gemma":[0.000034136992,0.0003529928,0.00011629797,0.00077397894,0.00049366406,0.00080257526,0.0018836419,0.00042008192,0.000033987955],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019073673,0.00005285006,0.00005463094,0.000027953083,0.000012056415,0.00003644319,0.00050919707,0.0389681,0.00007217874,0.05195224,0.00014978286,0.90816265],"study_design_scores_gemma":[0.00037361428,0.00014875791,0.00037736894,0.00031539387,0.00001001061,0.00007199722,4.469405e-7,0.85761964,0.000393756,0.13632171,0.0038906308,0.00047664018],"about_ca_topic_score_codex":0.000067825014,"about_ca_topic_score_gemma":0.00006808982,"teacher_disagreement_score":0.907686,"about_ca_system_score_codex":0.00014741007,"about_ca_system_score_gemma":0.0005181348,"threshold_uncertainty_score":0.99989223},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6888267,0.0005003804,0.30888307,0.0013184862,0.00022804718,0.00008448188,0.000002882386,0.000062930725,0.00009301303],"genre_scores_gemma":[0.82727724,0.000041474552,0.17196177,0.00035298802,0.00016663587,0.0000018750304,0.0000023107334,0.000007700995,0.00018799887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989618,0.00010443696,0.00017577088,0.0001875331,0.00036210864,0.00020834773],"domain_scores_gemma":[0.99943674,0.00009401051,0.000078939185,0.00022398596,0.000053709904,0.00011263141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005727402,0.00009876985,0.000105323015,0.000052492232,0.00068650284,0.00022856896,0.0003622432,0.00003727535,0.000092281814],"category_scores_gemma":[0.000020280848,0.00006669457,0.000034985573,0.0001544467,0.000047334022,0.00073162495,0.0001546868,0.00032505294,0.00003313093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038134036,0.00016292772,0.0004247605,0.0000035880678,0.000025138808,0.000024945,0.00031944597,0.029564861,0.0029081884,0.00080005685,0.001531055,0.9641969],"study_design_scores_gemma":[0.0005017431,0.00004381552,0.04055607,0.00004270785,0.0000075387893,0.0008143003,0.000002145352,0.9534601,0.0006595825,0.003173517,0.0006227945,0.00011570321],"about_ca_topic_score_codex":0.000022432174,"about_ca_topic_score_gemma":0.0000027304573,"teacher_disagreement_score":0.96408117,"about_ca_system_score_codex":0.00002884546,"about_ca_system_score_gemma":0.000062563166,"threshold_uncertainty_score":0.5280094},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010140772,0.0004212996,0.9797127,0.00024644288,0.00041981947,0.0004226744,0.000030446387,0.00033084862,0.008274978],"genre_scores_gemma":[0.48313513,0.00042030847,0.51483387,0.00092653284,0.00015211075,0.000048831662,0.000026945287,0.000020648245,0.00043559805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989472,0.00003578318,0.00027077828,0.00019856724,0.00028678591,0.00026088412],"domain_scores_gemma":[0.99900657,0.00011126645,0.00013137539,0.0005524023,0.000052283827,0.00014612584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011938968,0.00017081582,0.00017647394,0.000084128435,0.0002248146,0.0002554013,0.0006145733,0.00007364666,0.000025906305],"category_scores_gemma":[0.000025562367,0.00013148492,0.00003371138,0.00019039902,0.00007764463,0.0015738495,0.0006807072,0.00014143523,0.00014710809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036432612,0.00007185995,0.00017765383,0.0001054138,0.000015255469,0.000012167613,0.003080603,0.00009029593,0.000985178,0.0057854885,0.011576383,0.97809607],"study_design_scores_gemma":[0.0003522176,0.00008035877,0.00097505614,0.000097140066,0.000004155529,0.000049434984,0.00005306657,0.98143953,0.0011916959,0.0003502422,0.015200429,0.00020668196],"about_ca_topic_score_codex":0.000007805942,"about_ca_topic_score_gemma":4.2702948e-7,"teacher_disagreement_score":0.98134923,"about_ca_system_score_codex":0.000024095145,"about_ca_system_score_gemma":0.000007257479,"threshold_uncertainty_score":0.5361799},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14956534,0.0000619841,0.84914774,0.00003410509,0.00028140267,0.000066868866,0.0000014541686,0.00027440814,0.00056671404],"genre_scores_gemma":[0.46492255,0.00002137375,0.53461725,0.0001510319,0.00011365287,0.000002415653,0.000011239857,0.000007535503,0.00015296735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988794,0.00004758612,0.00018674153,0.0003725077,0.0002752599,0.00023852021],"domain_scores_gemma":[0.9989199,0.000026558944,0.000053314965,0.0007586482,0.00007227036,0.0001692927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010703824,0.00013128738,0.00013203012,0.00009592314,0.00036930456,0.000093924216,0.00070020615,0.00006114347,0.00012452992],"category_scores_gemma":[0.0000075842427,0.00010030425,0.000040230152,0.0002229893,0.000029270974,0.0014732012,0.0002580257,0.000093287985,0.00004904975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009981378,0.0023976278,0.006160057,0.000053683118,0.00008259887,0.00069885486,0.0059293536,0.05746949,0.39627093,0.04757152,0.033023685,0.45024237],"study_design_scores_gemma":[0.0003183062,0.000050826224,0.0019200322,0.000016147478,0.000001818426,0.00011634587,0.0000118705475,0.98456675,0.010016704,0.000623051,0.002178236,0.00017992263],"about_ca_topic_score_codex":0.000058889844,"about_ca_topic_score_gemma":0.0000020342566,"teacher_disagreement_score":0.92709726,"about_ca_system_score_codex":0.000023259963,"about_ca_system_score_gemma":0.00005394476,"threshold_uncertainty_score":0.40902886},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048116708,0.000025226895,0.98354363,0.00055221055,0.0003022687,0.00012839164,0.000008362413,0.0001566711,0.014802079],"genre_scores_gemma":[0.47397426,0.000005311184,0.4738154,0.0009180824,0.00034979882,0.00009376296,0.000021020838,0.000013878196,0.050808497],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993433,0.000008037691,0.00011939158,0.00023250679,0.00010088532,0.00019592133],"domain_scores_gemma":[0.9995163,0.00005972237,0.000030239584,0.00028270215,0.00007844979,0.000032590342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008312704,0.0000674373,0.00007185999,0.0000616714,0.00031089108,0.00016971225,0.00036182435,0.000017680513,0.000019441088],"category_scores_gemma":[0.00001554268,0.000053698466,0.000037506572,0.00027763206,0.00001414856,0.0006049286,0.00014354437,0.000042377258,0.0000151193435],"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":[0.0000050370472,0.000072172836,0.0001386096,0.0000060556113,0.0000050338126,0.0000057586917,0.0000112485595,0.0006419922,0.00061050674,0.27028367,0.69979054,0.028429402],"study_design_scores_gemma":[0.00043067647,0.00003803936,0.00087879837,0.000013533543,0.0000017536394,0.000025716308,0.000007676896,0.6496998,0.0031859635,0.03644252,0.30912125,0.00015429962],"about_ca_topic_score_codex":0.0002751419,"about_ca_topic_score_gemma":0.000017922943,"teacher_disagreement_score":0.6490578,"about_ca_system_score_codex":0.000025373043,"about_ca_system_score_gemma":0.000037107344,"threshold_uncertainty_score":0.23911542},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075454046,0.000017385124,0.95304257,0.00086578797,0.00013991623,0.000051545514,1.7664614e-7,0.00016663637,0.038170557],"genre_scores_gemma":[0.63847893,0.000005269768,0.35893548,0.0005900319,0.00010909489,0.000020859132,0.0000040966343,0.0000033441297,0.0018529118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995902,0.000010709614,0.00007097677,0.00013038925,0.000091040885,0.00010664885],"domain_scores_gemma":[0.99964684,0.000017848084,0.000018577704,0.0002474582,0.000025876689,0.00004339274],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004381864,0.0000382438,0.00003616823,0.000019552806,0.00006230997,0.00013876015,0.00026802454,0.000015646741,0.00031122955],"category_scores_gemma":[0.0000052476257,0.000026628939,0.000014266934,0.00007759662,0.0000059274694,0.00090077805,0.00015923077,0.000029719502,0.0009895449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.1743557e-7,0.000030340485,0.00038481565,0.0000022919187,0.0000023550215,0.00000203232,0.000078664336,0.000006056198,0.003254631,0.1278059,0.059780523,0.80865216],"study_design_scores_gemma":[0.00019594429,0.000041981755,0.017491138,0.000013958251,0.0000010591623,0.000008042283,0.00001975273,0.90157247,0.008657444,0.036348827,0.035469808,0.00017958874],"about_ca_topic_score_codex":0.00008381115,"about_ca_topic_score_gemma":0.00000266896,"teacher_disagreement_score":0.9015664,"about_ca_system_score_codex":0.000005089245,"about_ca_system_score_gemma":0.0000057198745,"threshold_uncertainty_score":0.9997883},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027278075,0.000042395586,0.95300144,0.003807754,0.000098834906,0.00036160377,0.0000075322364,0.00020389151,0.0151985],"genre_scores_gemma":[0.48948702,0.00006788374,0.47614956,0.0045234556,0.00024372306,0.000020432448,0.00013883437,0.00002418829,0.029344914],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799955,0.00010742881,0.00023938494,0.0006156204,0.0005503674,0.0004876262],"domain_scores_gemma":[0.9988213,0.000047323014,0.000019440628,0.0007110637,0.00005320544,0.00034762005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064906914,0.00015273983,0.0001748154,0.00023888302,0.00007230443,0.00024647018,0.0009407076,0.00009248665,0.00009508222],"category_scores_gemma":[0.000021480084,0.00012794271,0.00003942166,0.00072754093,0.000015982232,0.000853555,0.0004181529,0.00025834152,0.0003155135],"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":[0.00004173081,0.0007421611,0.0018003577,0.000015302092,0.000006212986,0.000038726605,0.0014102571,0.0011795075,0.005909451,0.0226256,0.689996,0.2762347],"study_design_scores_gemma":[0.002653011,0.0009553939,0.04244335,0.00013476578,0.000006055546,0.00011116907,0.00037409642,0.75691056,0.010303019,0.0018129714,0.18286282,0.0014327939],"about_ca_topic_score_codex":0.0008446416,"about_ca_topic_score_gemma":0.000030527528,"teacher_disagreement_score":0.75573105,"about_ca_system_score_codex":0.000073541036,"about_ca_system_score_gemma":0.0003071002,"threshold_uncertainty_score":0.52173525},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07639174,0.0001556747,0.92265475,0.00020615273,0.00009870562,0.00014535255,0.000005572785,0.000111270034,0.0002307712],"genre_scores_gemma":[0.45884368,0.000010047095,0.5397695,0.00007415374,0.000033652203,0.00000517925,0.000008686767,0.0000042782367,0.0012508444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938345,0.000007804398,0.00013456495,0.0002224891,0.00008642544,0.00016523726],"domain_scores_gemma":[0.9994515,0.00017381618,0.000037041333,0.00022869911,0.000038934762,0.000070008835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023413227,0.00007260102,0.000076420496,0.000081238344,0.00018077213,0.00007199232,0.00022735969,0.000045027416,0.000009487474],"category_scores_gemma":[0.000027545759,0.000055750406,0.000019684563,0.00013647665,0.000017866061,0.00048775214,0.00020678961,0.000051930176,0.0000058313426],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057821955,0.0004946013,0.05596939,0.000029550187,0.000047770794,0.000026187485,0.00094404264,0.00014700064,0.011495538,0.23197396,0.015285493,0.68352866],"study_design_scores_gemma":[0.0017654948,0.00020634943,0.31082803,0.000026483774,0.000007673943,0.00001153673,0.00006586456,0.66933894,0.0031867432,0.0016802199,0.0126042925,0.00027836117],"about_ca_topic_score_codex":0.000071423616,"about_ca_topic_score_gemma":0.000101936756,"teacher_disagreement_score":0.6832503,"about_ca_system_score_codex":0.000010944615,"about_ca_system_score_gemma":0.000016905786,"threshold_uncertainty_score":0.22734356},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015791865,0.000029353941,0.9810132,0.00057798694,0.00055712473,0.00024820093,0.0000042355514,0.00019238063,0.0015856634],"genre_scores_gemma":[0.28698453,0.0000021216376,0.71174544,0.0011322701,0.00007165815,0.000013654797,8.30588e-7,0.000008331033,0.000041193176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969185,0.00013433793,0.0002580076,0.0010252809,0.00090696785,0.0007569256],"domain_scores_gemma":[0.9977837,0.00010959559,0.00006242235,0.0011302797,0.0003023688,0.00061162317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090061064,0.0002567056,0.00025368968,0.0001843689,0.00053075154,0.0008429455,0.002373717,0.000041686686,0.00004109053],"category_scores_gemma":[0.00005319622,0.00017013353,0.000043261785,0.0014552826,0.0010690459,0.00087537454,0.00096274784,0.00017367724,0.00013819753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069552516,0.00006674977,0.000035895268,0.0000021913854,0.000004262618,0.000031649815,0.0002534732,0.000392153,0.00092124246,0.8625577,0.00017232283,0.13555539],"study_design_scores_gemma":[0.00068925496,0.0010062458,0.0008825142,0.00007594449,0.000006715179,0.0002052002,0.00002970234,0.94925946,0.027662242,0.017007679,0.0025157826,0.00065928116],"about_ca_topic_score_codex":0.000007745698,"about_ca_topic_score_gemma":8.025379e-7,"teacher_disagreement_score":0.94886726,"about_ca_system_score_codex":0.00005529629,"about_ca_system_score_gemma":0.00018526128,"threshold_uncertainty_score":0.81285423},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30382735,0.00036884527,0.6791034,0.00014387697,0.00038070235,0.00013682063,0.015986798,0.000048022946,0.000004224437],"genre_scores_gemma":[0.37668216,0.00005547049,0.6004529,0.00046981446,0.00040449566,0.0000014525949,0.021906855,0.000018991639,0.000007847085],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982172,0.00008455231,0.00020166526,0.0009747404,0.00027215006,0.00024969075],"domain_scores_gemma":[0.9905367,0.00015616765,0.00012839628,0.009011734,0.00004723906,0.0001197629],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000350014,0.0001742981,0.00021059636,0.00012466767,0.00043648347,0.0004470089,0.0054938816,0.00004765249,0.000040878127],"category_scores_gemma":[0.0000705504,0.00011848686,0.000019883531,0.00056255626,0.00010427614,0.0022767272,0.015608105,0.00039460039,0.0000055380883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055786495,0.00027549604,0.0117299445,0.00014700863,0.0019363136,0.0005341456,0.0017175069,0.0010136634,0.76448464,0.006104971,0.023447985,0.18855251],"study_design_scores_gemma":[0.0001959398,0.0000047894146,0.006589511,0.0000075726466,0.00021549518,0.00005332448,0.00004492521,0.96441543,0.00012789873,0.000047756705,0.02811801,0.00017934036],"about_ca_topic_score_codex":0.0009331732,"about_ca_topic_score_gemma":0.00074670545,"teacher_disagreement_score":0.9634018,"about_ca_system_score_codex":0.0000074239742,"about_ca_system_score_gemma":0.00007479344,"threshold_uncertainty_score":0.9998869},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077636294,0.00019802692,0.9200742,0.000752813,0.00017477058,0.00063055067,0.000024655274,0.00019864268,0.00031002087],"genre_scores_gemma":[0.3833842,0.00003090556,0.61529833,0.00047890865,0.00018027521,0.0003029624,0.000026002712,0.000033495748,0.00026491596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841833,0.000029285951,0.00021858874,0.000601639,0.0002939425,0.00043820703],"domain_scores_gemma":[0.99874663,0.00022121616,0.00009361291,0.00060477963,0.00016115338,0.00017263203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001738327,0.00021971489,0.0002275252,0.000103446466,0.0003150369,0.0005225665,0.0006387259,0.00006428602,0.0000129434575],"category_scores_gemma":[0.000027324022,0.0001628778,0.00004002896,0.0002339062,0.00006541657,0.00066360075,0.0004400061,0.000126586,0.000037967235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003758291,0.00041021293,0.00031725137,0.00011883406,0.00009975019,0.000023526183,0.0029312992,0.0006512575,0.0029224276,0.030715534,0.017434066,0.94433826],"study_design_scores_gemma":[0.0012347755,0.00039052902,0.0021716475,0.00009705439,0.000016508786,0.00004702029,0.0003800493,0.97241056,0.0021782178,0.0013690318,0.019201934,0.00050264696],"about_ca_topic_score_codex":0.000272475,"about_ca_topic_score_gemma":0.000007438633,"teacher_disagreement_score":0.9717593,"about_ca_system_score_codex":0.000025815369,"about_ca_system_score_gemma":0.000049877355,"threshold_uncertainty_score":0.6641964},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015000365,0.000050076324,0.9756778,0.00011946038,0.00011832065,0.00014807151,0.000013005907,0.00011785695,0.008755079],"genre_scores_gemma":[0.33506715,0.000011156893,0.663922,0.000083220846,0.000016434858,0.0000073789415,0.000019983849,0.000007681933,0.00086498633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895,0.00007183605,0.00022066427,0.00026989993,0.0003016988,0.00018592404],"domain_scores_gemma":[0.9991712,0.00002522731,0.00009628954,0.00049125415,0.00014561009,0.00007039853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002177499,0.000098427365,0.00014091667,0.00004506205,0.00006983699,0.000070661314,0.00052992365,0.00005904573,0.00011932885],"category_scores_gemma":[0.000063773165,0.000079064615,0.000035595618,0.0004184113,0.000028810458,0.0004542264,0.00017214383,0.000057681085,0.000029480043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047947753,0.000848867,0.0051565594,0.00009325089,0.0001005637,0.000029710658,0.0005430559,0.027344901,0.025706809,0.75920504,0.026676066,0.15424721],"study_design_scores_gemma":[0.0010413482,0.00025113445,0.00393887,0.000081839426,0.000011606592,0.000022841172,0.00007809123,0.9071989,0.06560545,0.006062867,0.0152972555,0.0004098191],"about_ca_topic_score_codex":0.000085447304,"about_ca_topic_score_gemma":0.000011168104,"teacher_disagreement_score":0.87985396,"about_ca_system_score_codex":0.000020513193,"about_ca_system_score_gemma":0.00008006708,"threshold_uncertainty_score":0.32241613},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005929484,0.0000053344475,0.97313833,0.00026522225,0.00086312054,0.00007352144,0.0000030678436,0.00023177154,0.019490134],"genre_scores_gemma":[0.82003856,8.6470504e-7,0.17780477,0.00021176269,0.0002584515,0.000010805247,0.00008759623,0.0000068893605,0.0015802976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992127,0.0000082478045,0.00013077428,0.00025253225,0.00026422023,0.00013152648],"domain_scores_gemma":[0.999346,0.00003889828,0.00004629849,0.0004276441,0.000060282877,0.00008083287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007836604,0.00008492198,0.00006724483,0.000053559506,0.00013643832,0.00030254075,0.00040938923,0.00005810444,0.000172472],"category_scores_gemma":[0.000014862048,0.00006196582,0.000030829022,0.00013180137,0.000025286407,0.0018020876,0.00037507812,0.00016575953,0.00024234928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061597702,0.00013146899,0.0006334305,0.00000496631,0.000004677794,0.000002658938,0.000043446635,0.00004343828,0.028639084,0.06907746,0.012786351,0.8886269],"study_design_scores_gemma":[0.00033971653,0.000033338114,0.010216381,0.000007749614,0.0000013056047,0.000042749005,0.000005055053,0.90634924,0.0053818943,0.011565935,0.06585079,0.00020582465],"about_ca_topic_score_codex":0.0000056940835,"about_ca_topic_score_gemma":0.0000015761951,"teacher_disagreement_score":0.90630585,"about_ca_system_score_codex":0.000006048234,"about_ca_system_score_gemma":0.000019795676,"threshold_uncertainty_score":0.31149906},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054779418,0.000059410726,0.93831116,0.0009684291,0.0004991201,0.0002136993,0.0000019672366,0.00023342267,0.0049333535],"genre_scores_gemma":[0.17957047,0.0000072850426,0.81863886,0.00058461225,0.00013582036,0.000013397748,0.0000024919627,0.000009135059,0.0010379223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877465,0.000035222118,0.0002195416,0.00043272733,0.0002201984,0.00031767218],"domain_scores_gemma":[0.9989265,0.000049640083,0.00005715859,0.00068631786,0.00010145238,0.00017890532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014583148,0.00012663257,0.0001534871,0.00008696702,0.00018122596,0.00036469926,0.00078464334,0.000048267695,0.00014732253],"category_scores_gemma":[0.000043814347,0.000101154976,0.000035272602,0.0003702569,0.000015889269,0.0009855073,0.0005595603,0.000092695926,0.00038391523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009056295,0.00011717039,0.00042965086,0.000022628776,0.000022540526,0.000014678996,0.0006626638,0.0014711,0.45202044,0.020048449,0.05364549,0.47153613],"study_design_scores_gemma":[0.0003711084,0.000081261525,0.0039658463,0.00018570902,0.000004392134,0.000030616146,0.00007829444,0.91900724,0.05341001,0.0061837225,0.016139675,0.00054215145],"about_ca_topic_score_codex":0.00054019765,"about_ca_topic_score_gemma":0.0000035120033,"teacher_disagreement_score":0.91753614,"about_ca_system_score_codex":0.00003703781,"about_ca_system_score_gemma":0.000043795746,"threshold_uncertainty_score":0.49345815},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062615857,0.0077519254,0.92342,0.002093412,0.008933967,0.00041287634,0.000049455113,0.00036677037,0.05070998],"genre_scores_gemma":[0.7045493,0.0005389582,0.20248434,0.0030417645,0.0044231843,0.000023534752,0.000083460305,0.00006850236,0.084786944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730605,0.000120685065,0.00037673765,0.000544548,0.0005872928,0.0010646826],"domain_scores_gemma":[0.9976038,0.00014400273,0.00013501087,0.00142875,0.00008186656,0.000606604],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00054885074,0.00033218358,0.0002937031,0.00010749726,0.0003161441,0.0003713228,0.0013558782,0.00019389253,0.0039026563],"category_scores_gemma":[0.00003873508,0.00026158246,0.0001277902,0.00034362136,0.00008769246,0.0036805135,0.0017441115,0.00029812282,0.0104987025],"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":[0.000017420716,0.00073920697,0.0044661216,0.000049430917,0.000053722975,0.000025660542,0.0016420585,0.000010511689,0.0007541916,0.083323896,0.4706896,0.4382282],"study_design_scores_gemma":[0.00076440535,0.00015499505,0.032341022,0.00016754074,0.00003747643,0.00009167703,0.00011528936,0.047462605,0.002674422,0.0012195192,0.91400194,0.0009690834],"about_ca_topic_score_codex":0.00016909634,"about_ca_topic_score_gemma":0.0000073295064,"teacher_disagreement_score":0.7209357,"about_ca_system_score_codex":0.000053500233,"about_ca_system_score_gemma":0.00007410378,"threshold_uncertainty_score":0.99998367},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026595704,0.00008510456,0.9693763,0.0024140633,0.0010068029,0.00007328037,0.00000127746,0.00006775995,0.00037970248],"genre_scores_gemma":[0.6443118,0.000039313483,0.35139424,0.0015819584,0.0022041055,0.0000023613497,0.0000017315489,0.000019979605,0.00044455004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884915,0.00009195549,0.00020535509,0.00019832679,0.00033442248,0.00032078451],"domain_scores_gemma":[0.9990627,0.00007144281,0.00013611978,0.00048359443,0.00009652217,0.00014961293],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002755958,0.00013053884,0.00011997929,0.000073685114,0.0005619188,0.0013397023,0.0019617812,0.000033475393,0.00011441785],"category_scores_gemma":[0.0000027343488,0.00008122753,0.00007682139,0.00015625657,0.000035817568,0.0017250221,0.000962384,0.00045341204,0.00015933279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037104662,0.000056469686,0.00036043528,0.0000041720464,0.0000652422,0.000059867565,0.0028797388,0.003416795,0.0002822665,0.016928291,0.10121197,0.87473106],"study_design_scores_gemma":[0.00045645598,0.00008785933,0.003889243,0.000054849286,0.0000060926936,0.00051635125,0.000106088584,0.97706324,0.00014573523,0.0063830074,0.011094316,0.00019677125],"about_ca_topic_score_codex":0.00002820163,"about_ca_topic_score_gemma":3.7980803e-7,"teacher_disagreement_score":0.97364646,"about_ca_system_score_codex":0.000045169916,"about_ca_system_score_gemma":0.00005397454,"threshold_uncertainty_score":0.999697},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3880187,0.00054727553,0.6105721,0.0002851704,0.00012428849,0.00021422702,0.00000700348,0.00019506604,0.0000362028],"genre_scores_gemma":[0.96066904,0.000036202382,0.03910104,0.000027990063,0.000043386866,0.000041654832,0.000008364254,0.000012588471,0.000059710324],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99847704,0.000049382295,0.00036910072,0.00055049674,0.00021772552,0.00033625215],"domain_scores_gemma":[0.99866086,0.00018256177,0.0002761446,0.0006141459,0.00021793504,0.000048323775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028047574,0.00021618062,0.00042477009,0.00031498118,0.00026482824,0.00010536738,0.0009854996,0.00026375745,0.0000025587085],"category_scores_gemma":[0.000041185198,0.0001835818,0.00006222096,0.00034988712,0.0003441445,0.00033866664,0.00041340932,0.0002158671,0.0000018125821],"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":[0.00013073611,0.00029253348,0.0071156863,0.00034705506,0.000087000626,0.00004742535,0.0004871395,0.0034625952,0.66106284,0.10169751,0.00083558133,0.22443393],"study_design_scores_gemma":[0.0029270472,0.0001356312,0.00057031354,0.00044047995,0.00002980784,0.000059633683,0.00013186113,0.48057285,0.4965861,0.014899292,0.003229165,0.000417816],"about_ca_topic_score_codex":0.00007564258,"about_ca_topic_score_gemma":0.0000070339943,"teacher_disagreement_score":0.5726504,"about_ca_system_score_codex":0.000013186558,"about_ca_system_score_gemma":0.000048817896,"threshold_uncertainty_score":0.7486248},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023542382,0.000019004434,0.992996,0.0034347351,0.0003351794,0.00019928117,0.000029284278,0.00015074013,0.00048158772],"genre_scores_gemma":[0.20459586,0.000004592792,0.7931608,0.0016346249,0.000078694,0.000023982413,0.000031070136,0.000004592981,0.00046580302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988648,0.000017883192,0.00019499799,0.00044862967,0.00022281476,0.00025081538],"domain_scores_gemma":[0.9990717,0.00011122096,0.00009584145,0.0005663943,0.00007103323,0.000083781124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018920877,0.0001173869,0.00011016045,0.000052602096,0.00016946226,0.0001761828,0.00069956464,0.000051145467,0.000021364362],"category_scores_gemma":[0.000036282847,0.0000983956,0.00006178467,0.00020279145,0.000024450766,0.0007583617,0.00004607375,0.00006983164,0.000019317082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114922295,0.00038590116,0.00072978914,0.000061217215,0.000023465758,0.000011408983,0.0006230456,0.0043385504,0.037718803,0.1964432,0.33939978,0.42014992],"study_design_scores_gemma":[0.0002452075,0.00011318555,0.0013442232,0.00002152347,0.0000030133958,0.000001461825,0.000008922637,0.9654626,0.006415367,0.0014958703,0.024717916,0.00017066304],"about_ca_topic_score_codex":0.0000062180193,"about_ca_topic_score_gemma":4.4553147e-7,"teacher_disagreement_score":0.9611241,"about_ca_system_score_codex":0.000050486768,"about_ca_system_score_gemma":0.000048963702,"threshold_uncertainty_score":0.40124562},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026697405,0.00004158102,0.99193585,0.0007538701,0.0004579014,0.00024524765,0.000012173655,0.00030546772,0.0035781916],"genre_scores_gemma":[0.25152808,0.0003608963,0.7101305,0.00077071006,0.00030272975,0.000110159286,0.000045837867,0.000048814374,0.03670223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890083,0.000030174024,0.00018885246,0.00040521644,0.00014638873,0.0003285427],"domain_scores_gemma":[0.9991015,0.00014241503,0.000062407766,0.0005325119,0.000059434216,0.000101718746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022198519,0.00013531811,0.00016252842,0.000094309806,0.0001784167,0.00023648086,0.0006682775,0.000053827258,0.00023071123],"category_scores_gemma":[0.000025382293,0.000108424014,0.00006184766,0.00022681025,0.000021731392,0.0005476561,0.00025913602,0.00005956162,0.00037695604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027143082,0.00080334087,0.000028871083,0.00022637277,0.00010343587,0.00010609247,0.0014369071,0.0023624199,0.09739481,0.1113186,0.1234828,0.6627092],"study_design_scores_gemma":[0.0002868183,0.00006962614,0.00005051333,0.000031398074,0.0000030593812,0.0000080916,0.000004099655,0.9935465,0.0013551946,0.00213561,0.002338551,0.00017056162],"about_ca_topic_score_codex":0.000026115718,"about_ca_topic_score_gemma":0.0000012626323,"teacher_disagreement_score":0.99118406,"about_ca_system_score_codex":0.00002949195,"about_ca_system_score_gemma":0.000010027994,"threshold_uncertainty_score":0.4845133},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012742788,0.00011383435,0.9850532,0.0001452509,0.0001367679,0.0003186395,0.00003461481,0.0006233988,0.0008315054],"genre_scores_gemma":[0.13866666,0.0000891435,0.8609804,0.000091451446,0.000045768826,0.000027826925,0.000039402155,0.000011027555,0.000048349128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871796,0.0000059681333,0.00036766322,0.00021757376,0.00028958227,0.00040125026],"domain_scores_gemma":[0.99890584,0.00007339064,0.00013145895,0.00071964273,0.00011103868,0.000058621554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015425218,0.00019450561,0.00022029648,0.000118928074,0.00039002293,0.00012819425,0.0009159894,0.00010769839,0.0000026823325],"category_scores_gemma":[0.00004594865,0.0001407215,0.00004812184,0.0002824495,0.0001113402,0.0014095622,0.00023608099,0.00014115752,0.000018593983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003483387,0.0005641309,0.0011822775,0.0017725031,0.0006188939,0.00054541946,0.049404737,0.13294877,0.014814703,0.12307893,0.015557774,0.65916353],"study_design_scores_gemma":[0.00084308663,0.00066257763,0.0002789371,0.00015626903,0.000022361093,0.00045712205,0.002101063,0.9631181,0.014277406,0.00074705464,0.016526569,0.00080946763],"about_ca_topic_score_codex":0.000017300668,"about_ca_topic_score_gemma":0.0000022228649,"teacher_disagreement_score":0.8301693,"about_ca_system_score_codex":0.00008012754,"about_ca_system_score_gemma":0.00013971174,"threshold_uncertainty_score":0.5738456},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014722853,0.00009948814,0.9776215,0.00012892557,0.0002934854,0.00017046623,0.000020283596,0.0002238413,0.019969726],"genre_scores_gemma":[0.21302067,0.000009161514,0.7852555,0.000624214,0.000068012,0.00002275285,0.000024197352,0.00001049157,0.0009650348],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982723,0.00008003907,0.00028965445,0.00069450337,0.00029454636,0.00036897877],"domain_scores_gemma":[0.9983594,0.00014307877,0.00009560623,0.00097399775,0.00013218935,0.00029574393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039592088,0.00020059495,0.00030447613,0.0002537509,0.00023270103,0.00018837902,0.0008621768,0.00009393697,0.00053289917],"category_scores_gemma":[0.000065083696,0.00016659705,0.00005640051,0.0012594849,0.000055671,0.0006901014,0.00063764496,0.00012732274,0.00003439829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038020138,0.0012781542,0.0112015335,0.00014600421,0.00096874154,0.0001450801,0.0049443757,0.0039884895,0.0033797836,0.8569908,0.07275391,0.043822933],"study_design_scores_gemma":[0.00080899853,0.0006069425,0.011340277,0.00006900278,0.00021271684,0.000010340675,0.000069954025,0.9612753,0.0024424063,0.0032592528,0.019339519,0.0005653374],"about_ca_topic_score_codex":0.0005142533,"about_ca_topic_score_gemma":0.000004676284,"teacher_disagreement_score":0.9572868,"about_ca_system_score_codex":0.00002435629,"about_ca_system_score_gemma":0.0001184252,"threshold_uncertainty_score":0.6793631},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12859759,0.000051319934,0.8672216,0.0006859798,0.00019349217,0.00017735525,5.212413e-7,0.00024196427,0.002830172],"genre_scores_gemma":[0.9556821,0.000014777033,0.04369137,0.00041528748,0.00016281662,0.000013966583,0.0000011473883,0.000010524756,0.00000799265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962009,0.000044018874,0.00031653274,0.0011143455,0.000899336,0.0014248188],"domain_scores_gemma":[0.9988138,0.00016060131,0.00006430493,0.0005204647,0.0001891139,0.00025173204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027128523,0.00023452308,0.0002652857,0.00035309943,0.00039519268,0.0005964268,0.003931891,0.000074799864,0.000019368757],"category_scores_gemma":[0.00013084181,0.0001918762,0.000052023945,0.0021054808,0.0011268609,0.0015025462,0.0019380068,0.00052695564,0.000040924402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008832041,0.00006146005,0.0004090373,0.0000065266927,0.0000014240076,0.0000021155893,0.00019084576,0.00008044494,0.0033446148,0.9599571,0.000084879546,0.03585267],"study_design_scores_gemma":[0.000295468,0.00042993645,0.00311137,0.000029433051,0.00000103205,0.000021925343,0.0000055151677,0.7829113,0.004240319,0.20811643,0.00061274326,0.00022455759],"about_ca_topic_score_codex":0.0000067779383,"about_ca_topic_score_gemma":0.0000011780027,"teacher_disagreement_score":0.82708454,"about_ca_system_score_codex":0.00020804102,"about_ca_system_score_gemma":0.00022404034,"threshold_uncertainty_score":0.7824484},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013038361,0.00005662837,0.9943241,0.0009601559,0.0012849844,0.00015989543,0.000040008214,0.0003409041,0.0015295036],"genre_scores_gemma":[0.70825565,0.000021738802,0.2902845,0.0006900793,0.00025935285,0.00005223608,0.000012741629,0.00002984609,0.0003938616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809945,0.00008396158,0.00025389594,0.00046843308,0.0005344643,0.0005597893],"domain_scores_gemma":[0.9977894,0.00029056583,0.000071899536,0.0015192494,0.000046854595,0.00028202488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002797802,0.00028183378,0.00022534064,0.00026160706,0.00041668268,0.0001481427,0.0011711227,0.00010762912,0.00021596957],"category_scores_gemma":[0.000024383035,0.00024099991,0.00015787732,0.00049774325,0.000039959472,0.0010440326,0.000034046458,0.00034673713,0.00028722244],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038943486,0.00068340736,0.00013336574,0.000007505318,0.000025098572,0.000012676524,0.00013967926,0.005466309,0.00024245717,0.0005062113,0.00058483286,0.9921595],"study_design_scores_gemma":[0.0025016274,0.0010387714,0.023809107,0.00015866564,0.0000538799,0.00006312293,0.00007151723,0.9041783,0.015696548,0.00066792,0.05070281,0.0010577168],"about_ca_topic_score_codex":0.00009499177,"about_ca_topic_score_gemma":0.0000146841,"teacher_disagreement_score":0.9911018,"about_ca_system_score_codex":0.00010231925,"about_ca_system_score_gemma":0.000054123248,"threshold_uncertainty_score":0.98276913},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030039249,0.000022154689,0.9934957,0.0003697396,0.00020230433,0.0005620244,0.00011904601,0.00017573527,0.002049366],"genre_scores_gemma":[0.008902159,0.0000014578864,0.98870534,0.0015043089,0.00021362542,0.00013997221,0.00015456871,0.000018167868,0.0003604103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825066,0.000027753442,0.00046220716,0.0002766233,0.00046317134,0.0005195759],"domain_scores_gemma":[0.9986615,0.00015004615,0.00019423327,0.0007950633,0.000093581046,0.00010558483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026981704,0.00025254663,0.00024366372,0.00011338207,0.00028636918,0.0006706013,0.0011071279,0.00006900134,0.000029781288],"category_scores_gemma":[0.000010193308,0.00018680561,0.000061980885,0.00018267447,0.00007574542,0.0024546587,0.00056281197,0.00013573522,0.00006824345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013881037,0.00043232887,0.0007259273,0.00021878682,0.00016842356,0.000037207148,0.0023518242,0.0039361613,0.00063173566,0.023447564,0.30620846,0.66170275],"study_design_scores_gemma":[0.0028613387,0.00062129437,0.0004124246,0.00016285396,0.000025182859,0.00003969649,0.00018305841,0.9051784,0.004300634,0.0004557791,0.08518252,0.00057680777],"about_ca_topic_score_codex":0.0000573399,"about_ca_topic_score_gemma":0.0000066105636,"teacher_disagreement_score":0.90124226,"about_ca_system_score_codex":0.00009902658,"about_ca_system_score_gemma":0.000057469384,"threshold_uncertainty_score":0.7617712},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02390391,0.0038502682,0.96781117,0.00029308247,0.0009243204,0.00043708054,0.000028480956,0.0002040939,0.0025475952],"genre_scores_gemma":[0.7788144,0.0009380354,0.2187045,0.00037263782,0.00038430037,0.000029115867,0.000025485966,0.000034588476,0.0006969874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980012,0.0002302305,0.00029052375,0.00059305754,0.00042553095,0.0004594134],"domain_scores_gemma":[0.9987739,0.0002724402,0.000069094065,0.00057968043,0.00007234032,0.00023258908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005171915,0.0002669899,0.00040994323,0.00011713911,0.0003977704,0.00040223796,0.0005497471,0.000105063984,0.00008764339],"category_scores_gemma":[0.00007373699,0.00018784766,0.0001069933,0.000270687,0.00010458643,0.00047119515,0.00022246475,0.00023984072,0.000009861188],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004046761,0.00013546884,0.00080147356,0.00006820592,0.00017372017,0.00017388299,0.0017671094,0.0009085277,0.0021524155,0.19492659,0.0048560454,0.7936319],"study_design_scores_gemma":[0.09941838,0.00077356375,0.016239889,0.00016991203,0.00011507653,0.0014145835,0.0005581139,0.45085824,0.024407936,0.13573855,0.26726368,0.0030420683],"about_ca_topic_score_codex":0.000074601834,"about_ca_topic_score_gemma":0.000005339326,"teacher_disagreement_score":0.7905898,"about_ca_system_score_codex":0.00001468096,"about_ca_system_score_gemma":0.000058796395,"threshold_uncertainty_score":0.76602054},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021596083,0.00033383258,0.9940969,0.0002469051,0.0025367197,0.0006122494,0.000047356523,0.00014707234,0.0017630572],"genre_scores_gemma":[0.04725106,0.000049950293,0.94901824,0.0016693873,0.0012961134,0.00006894389,0.00023674662,0.0000841562,0.00032538708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588853,0.000036894424,0.0006744577,0.0017428674,0.0008587719,0.0007984982],"domain_scores_gemma":[0.9969018,0.0009864757,0.00034314475,0.001438334,0.00019357268,0.00013666408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074457854,0.00057338295,0.0006142653,0.00082094077,0.0002542869,0.00046331747,0.0034452076,0.0003482358,0.000012155272],"category_scores_gemma":[0.00008908231,0.00053146115,0.00013440264,0.00051994674,0.00032151322,0.00085192523,0.0017164552,0.000717643,0.000012083575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034478406,0.000073736905,0.00013636013,0.00016571642,0.000010335969,0.0000852598,0.00049029855,0.057575636,0.00016577201,0.0021105614,0.00046043837,0.9386914],"study_design_scores_gemma":[0.0012245787,0.00023143181,0.0005861967,0.000886361,0.000007164083,0.00001697501,4.3872805e-7,0.9770101,0.00078698486,0.017011818,0.0013753234,0.0008626295],"about_ca_topic_score_codex":0.00021429165,"about_ca_topic_score_gemma":0.00032554005,"teacher_disagreement_score":0.9378288,"about_ca_system_score_codex":0.00047729406,"about_ca_system_score_gemma":0.0005807054,"threshold_uncertainty_score":0.9997137},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066080294,0.00015153992,0.98515767,0.0013858739,0.00027094857,0.00019275823,0.0000047809604,0.00026675215,0.011908852],"genre_scores_gemma":[0.39211756,0.000032181146,0.5970088,0.0017463114,0.00021168831,0.00004844461,0.000005221115,0.000016069776,0.0088137],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991501,0.0000100824245,0.00014215327,0.00028765548,0.00015465256,0.0002553587],"domain_scores_gemma":[0.99920845,0.00016212073,0.000034411933,0.0004779178,0.000027718243,0.00008937002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000855428,0.00009884855,0.00010577986,0.00003083433,0.00012598123,0.00012054035,0.00068350334,0.000043651555,0.00022562912],"category_scores_gemma":[0.000031767442,0.00007370454,0.00006858104,0.00013545634,0.000013172748,0.0006333623,0.00015790976,0.000050855175,0.00013283019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034686884,0.00014501571,0.0000486218,0.000015471367,0.000012858701,0.0000054718907,0.00032425806,0.000012254898,0.00062394503,0.17802015,0.19379675,0.62699175],"study_design_scores_gemma":[0.0007206509,0.00014799513,0.0006788391,0.000009717648,0.0000036585827,0.000015468824,0.00001040893,0.74926937,0.002355908,0.013635342,0.23291239,0.00024023553],"about_ca_topic_score_codex":0.000009500346,"about_ca_topic_score_gemma":0.00000473998,"teacher_disagreement_score":0.74925715,"about_ca_system_score_codex":0.000011901722,"about_ca_system_score_gemma":0.0000070744186,"threshold_uncertainty_score":0.30055842},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000085638676,0.000068782596,0.98466873,0.00046602864,0.0000635684,0.00016567054,0.000002230681,0.000362469,0.014116886],"genre_scores_gemma":[0.033377662,0.000017179755,0.96264356,0.00032264975,0.00009100831,0.000029568004,0.0000026435189,0.0000064140586,0.0035092956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992312,0.000015433467,0.00011844579,0.00024803242,0.00013445455,0.00025243784],"domain_scores_gemma":[0.9994422,0.000077596014,0.00003237989,0.00035456067,0.00003732005,0.000055920093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022205307,0.00007291107,0.00008261517,0.00004063048,0.0002050436,0.00019876502,0.000570189,0.000030660565,0.000055174485],"category_scores_gemma":[0.000025517054,0.0000565684,0.000030750823,0.00011686825,0.000010856719,0.00063208095,0.00033718135,0.00007098186,0.000028522336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022494996,0.00007440951,0.000121272926,0.000015596906,0.0000072500725,0.0000050650056,0.00030494493,0.000067172565,0.0011793108,0.16556323,0.06099862,0.77166086],"study_design_scores_gemma":[0.00011891392,0.000045449793,0.000023959425,0.00001927578,9.212996e-7,0.0000057055495,0.00001049057,0.9333124,0.0031542417,0.0037587604,0.059437297,0.00011258671],"about_ca_topic_score_codex":0.000052708805,"about_ca_topic_score_gemma":0.000001778594,"teacher_disagreement_score":0.93324524,"about_ca_system_score_codex":0.000013197148,"about_ca_system_score_gemma":0.000007715484,"threshold_uncertainty_score":0.23067923},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064899924,0.00001247597,0.9840416,0.0003512635,0.00038041186,0.00014900256,0.00001361794,0.00016940983,0.014233243],"genre_scores_gemma":[0.4080693,0.0000050828226,0.58310115,0.0045390697,0.00028714992,0.00001766153,0.000039863306,0.000016795557,0.003923913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901396,0.000010223588,0.00014552289,0.00029819566,0.00026654126,0.0002655627],"domain_scores_gemma":[0.9990882,0.00017606598,0.00003365441,0.00050771504,0.0000831942,0.000111120644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059322343,0.00009439488,0.000097962664,0.00005391145,0.00014491806,0.00009070464,0.0006203676,0.000051115272,0.000059102946],"category_scores_gemma":[0.00007097018,0.000070043985,0.00005889393,0.00009758383,0.000014831846,0.00027893233,0.00017274929,0.00007507434,0.00004982092],"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":[0.000055563745,0.00020552297,0.00047195144,0.000017459373,0.000017279863,0.000028532888,0.0001773276,0.00003876569,0.0004125099,0.45857537,0.21246591,0.3275338],"study_design_scores_gemma":[0.0015635219,0.0007982437,0.014518356,0.00003653885,0.000010290778,0.000025865633,0.000042093274,0.06867425,0.033288583,0.08687978,0.79342467,0.00073777547],"about_ca_topic_score_codex":0.000017885119,"about_ca_topic_score_gemma":0.000020702812,"teacher_disagreement_score":0.5809588,"about_ca_system_score_codex":0.000017366528,"about_ca_system_score_gemma":0.00003792607,"threshold_uncertainty_score":0.2856311},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008313417,0.000113324866,0.99283093,0.00023800778,0.00023874051,0.00009942905,8.2311846e-7,0.00011572177,0.005531671],"genre_scores_gemma":[0.08121603,7.925445e-7,0.9166088,0.00036006677,0.000067247194,0.000006468083,9.169088e-7,0.000004330584,0.0017353301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994734,0.000015555897,0.000078372585,0.00018727977,0.00009118655,0.00015418296],"domain_scores_gemma":[0.9995024,0.000066876404,0.000021172553,0.0003157652,0.0000147491355,0.000079009274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000959683,0.000060597686,0.00006646865,0.000035804904,0.000091309295,0.000120593955,0.00038955064,0.000021338685,0.000024604959],"category_scores_gemma":[0.000040243434,0.000043388103,0.000032878685,0.000083243445,0.0000043066075,0.00008117516,0.00007033715,0.000038512087,0.000015393956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020955902,0.000015864069,0.00005660116,0.000011970256,0.0000070411843,0.000002330617,0.00024174913,0.00041295905,0.000512783,0.6794623,0.036375135,0.28289914],"study_design_scores_gemma":[0.0010308822,0.00014066878,0.00060999126,0.00004884264,0.0000062170034,0.00008556911,0.000025826645,0.20324303,0.018607808,0.15938702,0.61635274,0.00046141306],"about_ca_topic_score_codex":0.00004923809,"about_ca_topic_score_gemma":0.00000610253,"teacher_disagreement_score":0.5799776,"about_ca_system_score_codex":0.000007042629,"about_ca_system_score_gemma":0.000050087743,"threshold_uncertainty_score":0.17693156},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039225325,0.0003157723,0.99674755,0.00035852063,0.0012962263,0.00036922604,0.000020894327,0.00018676164,0.00031277983],"genre_scores_gemma":[0.26718885,0.000035429526,0.7296284,0.0018925417,0.0011117833,0.000008170642,0.000039299706,0.000059162656,0.000036366222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954247,0.000086641674,0.0006452972,0.0017049874,0.0013144658,0.00082391925],"domain_scores_gemma":[0.9971208,0.0006385713,0.00029644708,0.0013538256,0.0003711687,0.00021921222],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009572686,0.000595633,0.0005489871,0.00095083675,0.00046673926,0.0016346468,0.0024662965,0.000338756,0.0000658972],"category_scores_gemma":[0.0000660633,0.00055177213,0.00013267688,0.00058771943,0.00039810155,0.0018312413,0.0010590805,0.0012003481,0.000070171736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071376408,0.000038088714,0.000011846769,0.000086707754,0.000007257603,0.00013306276,0.00023764017,0.050377525,0.00045314044,0.00027586243,0.0000049918704,0.94836676],"study_design_scores_gemma":[0.00030312515,0.00014981952,0.00003812416,0.0012557337,0.000013575534,0.0000814187,4.730986e-7,0.9737827,0.0038813443,0.01957587,0.00021609887,0.0007017275],"about_ca_topic_score_codex":0.00015146623,"about_ca_topic_score_gemma":0.000120319215,"teacher_disagreement_score":0.94766504,"about_ca_system_score_codex":0.0004823086,"about_ca_system_score_gemma":0.0015765019,"threshold_uncertainty_score":0.9996934},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014111147,0.00018094928,0.9954779,0.0011920533,0.0006887779,0.00029653544,0.0001344353,0.00012929563,0.0004888954],"genre_scores_gemma":[0.055255186,0.000022609272,0.9427999,0.0004482352,0.00096957595,0.000034981433,0.00025442248,0.000019615767,0.00019547128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981591,0.00009004159,0.00027495882,0.00078964065,0.00027151717,0.00041471823],"domain_scores_gemma":[0.9973828,0.0003069689,0.00010083624,0.002019216,0.00006821774,0.00012195004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004731663,0.00020065131,0.00027168184,0.000104536855,0.0001334257,0.0001250293,0.00248622,0.000115292976,0.000010293186],"category_scores_gemma":[0.00018765623,0.00017390159,0.000049547016,0.00026018568,0.000048413967,0.00085294555,0.001082223,0.0002015539,0.000019868328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052397747,0.00024454846,0.00132235,0.00011757027,0.000039195216,0.000022135515,0.0004376281,0.00023030902,0.0009527895,0.08491435,0.054851007,0.8568157],"study_design_scores_gemma":[0.0008910904,0.000074570446,0.0036904693,0.000022152852,0.000007265144,0.000010580617,0.000010979699,0.85528153,0.0007121215,0.015937183,0.12306113,0.00030094924],"about_ca_topic_score_codex":0.00032304332,"about_ca_topic_score_gemma":0.00006828633,"teacher_disagreement_score":0.85651475,"about_ca_system_score_codex":0.000027804434,"about_ca_system_score_gemma":0.000064754786,"threshold_uncertainty_score":0.7091501},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032032796,0.00015560904,0.9915794,0.00038591836,0.005943893,0.00058792566,0.000030918276,0.00023815488,0.0010461197],"genre_scores_gemma":[0.009007205,0.0000307752,0.9883266,0.0007318618,0.0012350549,0.000035137666,0.000037442125,0.000041145544,0.0005547438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961137,0.000020890171,0.0005395293,0.0018085234,0.0008338156,0.00068355363],"domain_scores_gemma":[0.9972428,0.0003792598,0.000356724,0.0014504826,0.00037121965,0.00019950444],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007966762,0.00055270875,0.00050818437,0.0007637277,0.0004767937,0.00080053805,0.0037197135,0.0005047751,0.000026844436],"category_scores_gemma":[0.000081221144,0.00047099128,0.00017807567,0.0004411542,0.000684036,0.0011374648,0.0014054041,0.0010438878,0.000028396606],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066653756,0.000023874989,0.0000063855073,0.000026865373,0.000009771292,0.000024244287,0.00033567974,0.0022308992,0.0011904982,0.008063027,0.000031121028,0.988051],"study_design_scores_gemma":[0.00033308638,0.00028292948,0.00003616225,0.0002963992,0.000008997121,0.000102256075,2.8711338e-7,0.8101804,0.0050962036,0.17432986,0.00861448,0.00071893807],"about_ca_topic_score_codex":0.000056095996,"about_ca_topic_score_gemma":0.00013851254,"teacher_disagreement_score":0.98733205,"about_ca_system_score_codex":0.00020989192,"about_ca_system_score_gemma":0.00050950673,"threshold_uncertainty_score":0.99977416},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013051484,0.00007993587,0.9853302,0.00010599321,0.00024124433,0.00008496201,0.0000079164365,0.000056087196,0.001042149],"genre_scores_gemma":[0.84603196,0.0000071017416,0.15363106,0.000026399719,0.000111081456,0.0000054720035,0.000044364886,0.0000031681702,0.00013941016],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99924815,0.000019327317,0.00021772805,0.00019212216,0.00021031103,0.000112347145],"domain_scores_gemma":[0.99947625,0.000037507194,0.000093449555,0.00031596655,0.000056166024,0.000020645912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009091766,0.00006165803,0.00007553562,0.000043334996,0.000048386497,0.000050980416,0.00024308094,0.00002235458,0.00005864083],"category_scores_gemma":[0.0000016470625,0.00005148526,0.000028236931,0.00017503998,0.00001543525,0.00049459893,0.00008217848,0.00002826329,0.00001174907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007478378,0.00013643815,0.0036477717,0.000018258983,0.000007764739,0.0000050347994,0.0001741022,0.0009845746,0.008344289,0.2875087,0.08535262,0.613813],"study_design_scores_gemma":[0.0020302606,0.00025350103,0.30176437,0.000049040264,0.000010243978,0.000012592496,0.00015417182,0.20376876,0.2429538,0.061560135,0.18670547,0.0007376271],"about_ca_topic_score_codex":0.00038856678,"about_ca_topic_score_gemma":0.00004315996,"teacher_disagreement_score":0.83298045,"about_ca_system_score_codex":0.000019166897,"about_ca_system_score_gemma":0.000014060326,"threshold_uncertainty_score":0.2099508},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008366022,0.0021168229,0.9709146,0.004264144,0.0008677574,0.00065588823,0.0006729255,0.0007097368,0.011432103],"genre_scores_gemma":[0.47642997,0.00013248055,0.52115315,0.0007824694,0.00020560583,0.0000136938825,0.0006930488,0.000017013588,0.0005725976],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982288,0.00006800003,0.00033783962,0.0007395183,0.000361976,0.0002638617],"domain_scores_gemma":[0.99816424,0.000063120664,0.00010026858,0.0014768438,0.000040995794,0.00015454601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022032349,0.00016384933,0.00015421309,0.000068091285,0.00031539082,0.0003175412,0.0014801058,0.00004010403,0.0003471638],"category_scores_gemma":[0.00000937507,0.00013217292,0.000017118935,0.00016518035,0.000084091764,0.0017319613,0.0035573195,0.000092460425,0.000065863445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021851607,0.0005090714,0.00030161903,0.00001412781,0.000034172783,0.000039993367,0.002046767,0.000010245556,0.003082971,0.023635946,0.6065885,0.36371478],"study_design_scores_gemma":[0.0023728518,0.00015525467,0.0016419144,0.000024605775,0.000004858137,0.000059987713,0.00052846014,0.90736514,0.0073312796,0.00091233425,0.07923746,0.0003658427],"about_ca_topic_score_codex":0.0002828418,"about_ca_topic_score_gemma":0.000018544053,"teacher_disagreement_score":0.9073549,"about_ca_system_score_codex":0.000018633498,"about_ca_system_score_gemma":0.000009134621,"threshold_uncertainty_score":0.53898555},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005714241,0.000065745466,0.99122155,0.00039587417,0.0002322158,0.00018702765,0.000023526234,0.000140055,0.0020197968],"genre_scores_gemma":[0.31775975,0.000006504876,0.6778763,0.00077110523,0.00029366603,0.0000761883,0.00004452023,0.000010863856,0.0031611023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992705,0.000008401353,0.00012842848,0.00028122292,0.000121026154,0.00019041005],"domain_scores_gemma":[0.99946743,0.000025151177,0.00003525231,0.0003900833,0.00003852451,0.000043567507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007683593,0.000081758546,0.00007722556,0.000025470295,0.00011214094,0.00010997971,0.0005998787,0.000026969374,0.00003353955],"category_scores_gemma":[0.0000025039524,0.00006380061,0.0000370337,0.00006510116,0.000010968912,0.00037110515,0.00023004398,0.00002609172,0.000052973966],"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":[0.000010934408,0.0001743424,0.00077986775,0.000030876232,0.000015676422,0.000019690033,0.00010346899,0.00052421185,0.0971196,0.59982836,0.21181844,0.089574546],"study_design_scores_gemma":[0.00086047075,0.0001323704,0.0044803633,0.000020602372,0.000005892373,0.000017804185,0.00001678334,0.31292439,0.06147254,0.025358787,0.5941998,0.0005102631],"about_ca_topic_score_codex":0.00010310476,"about_ca_topic_score_gemma":0.0000063240846,"teacher_disagreement_score":0.57446957,"about_ca_system_score_codex":0.00003992579,"about_ca_system_score_gemma":0.000037413338,"threshold_uncertainty_score":0.26017132},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068670517,0.000086796776,0.9546577,0.0024917838,0.00021924406,0.00011488934,0.0000031559625,0.00035681558,0.041382916],"genre_scores_gemma":[0.16843852,0.000032987715,0.8280167,0.0011491453,0.00045782112,0.000013939485,0.000008955389,0.000014133595,0.0018677774],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985948,0.000020295121,0.0003066036,0.0004000454,0.00030407155,0.00037415972],"domain_scores_gemma":[0.99917716,0.000036497448,0.000060046852,0.0005342103,0.00004867703,0.00014340036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027384964,0.0001514375,0.00015149228,0.000068245114,0.00017970375,0.00020087458,0.0008189733,0.00004023076,0.00017734122],"category_scores_gemma":[0.0000075889643,0.000115437666,0.00007649246,0.00020532696,0.0000216412,0.0013939758,0.00025862054,0.00013924103,0.0002848568],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012141304,0.000048190916,0.000013892064,0.0000025621287,0.000005098942,0.000006395911,0.00025897907,0.00016797148,0.0004269768,0.021500539,0.0019072421,0.9756609],"study_design_scores_gemma":[0.0006316937,0.000052872398,0.0001489038,0.000022089725,0.0000038416106,0.00004577756,0.00007264881,0.9354257,0.01290073,0.002813908,0.047579747,0.00030206962],"about_ca_topic_score_codex":0.0001007385,"about_ca_topic_score_gemma":0.00003497601,"teacher_disagreement_score":0.97535884,"about_ca_system_score_codex":0.000037082424,"about_ca_system_score_gemma":0.000036074518,"threshold_uncertainty_score":0.47074115},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09101355,0.00020344314,0.90640384,0.0011367099,0.0005690776,0.00023737932,0.000011705385,0.000103795595,0.00032050253],"genre_scores_gemma":[0.9852419,0.000017250799,0.014135978,0.00043783616,0.0000705073,0.000015132936,0.0000060800053,0.000009696165,0.00006561177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987369,0.000053082502,0.00022239254,0.00041272977,0.00025018468,0.00032470192],"domain_scores_gemma":[0.9987926,0.0003938101,0.0001112287,0.0004925058,0.00007754725,0.00013230114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056305237,0.0001651719,0.000206707,0.00006076982,0.00063075416,0.0003423042,0.0010058949,0.000041602518,5.1132196e-7],"category_scores_gemma":[0.000030328723,0.00011296833,0.000061053746,0.0003758113,0.000060325412,0.00024860076,0.0004586549,0.00013023554,0.0000035498654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023274977,0.000016788335,0.0035529255,0.000018777324,0.000008746626,8.057809e-7,0.00039450976,0.00001275537,0.000018515977,0.9418429,0.0012777206,0.052853234],"study_design_scores_gemma":[0.00062965293,0.000216162,0.009990478,0.00006768542,0.000015677351,0.0000046226314,0.000067842375,0.13917029,0.00011726147,0.7967893,0.052592803,0.00033823767],"about_ca_topic_score_codex":0.00004973652,"about_ca_topic_score_gemma":0.0000018410487,"teacher_disagreement_score":0.89422834,"about_ca_system_score_codex":0.000012884901,"about_ca_system_score_gemma":0.00001522351,"threshold_uncertainty_score":0.48513147},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009300888,0.00005712415,0.9711855,0.0012283308,0.00020235895,0.000044730623,0.0000027344533,0.00025384192,0.01772449],"genre_scores_gemma":[0.2087977,0.000004183136,0.7901696,0.00047573907,0.00009715797,7.7235524e-7,0.0000066229463,0.0000026189923,0.00044562583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920285,0.000019361343,0.00015442033,0.00026682246,0.00015594822,0.00020060615],"domain_scores_gemma":[0.999437,0.00005079918,0.000048874135,0.00035603406,0.00003626099,0.00007104737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015135668,0.00008433515,0.00010472697,0.000042511354,0.00013369723,0.00021438074,0.0005161192,0.000036173733,0.000026683962],"category_scores_gemma":[0.000022447535,0.00006765011,0.000030874016,0.00014543041,0.000019826699,0.0006429906,0.00017374461,0.0000988984,0.00005502466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002430172,0.000024230254,0.00021677917,0.0000016308585,0.00000336701,0.00001713702,0.000099707395,0.00016045161,0.0021211246,0.10915346,0.0024438677,0.88575584],"study_design_scores_gemma":[0.00058656925,0.00015990193,0.0011057596,0.0000811517,0.0000048100173,0.0001536224,0.00026518817,0.9505832,0.011612192,0.008920704,0.026072409,0.0004544865],"about_ca_topic_score_codex":0.000012971072,"about_ca_topic_score_gemma":0.000001178604,"teacher_disagreement_score":0.95042276,"about_ca_system_score_codex":0.000015781136,"about_ca_system_score_gemma":0.000021374399,"threshold_uncertainty_score":0.27586913},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011728093,0.000030327525,0.98499817,0.00008576657,0.00015671067,0.00013606192,0.000021498863,0.000052379317,0.0027910112],"genre_scores_gemma":[0.9174406,0.00010609225,0.08234799,0.000026967924,0.0000027618682,0.000027305863,0.0000042335864,0.0000064113474,0.000037643505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905974,0.00008859131,0.00032888242,0.00016387067,0.00024564695,0.000113252],"domain_scores_gemma":[0.9979736,0.00013698173,0.00017381107,0.0015464388,0.00012071906,0.000048453327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001637341,0.00010250771,0.00014387479,0.00018111947,0.00023436513,0.000015739392,0.001254576,0.0000527554,0.000024153147],"category_scores_gemma":[0.0000022860916,0.000097289405,0.00006659187,0.00032676724,0.0001401057,0.00035083137,0.0000205533,0.00019989786,0.000014543808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002675529,0.008991215,0.00027171787,0.00012694264,0.00026142987,0.0000015114791,0.010258817,0.24016249,0.004470618,0.067813806,0.00044418612,0.6669297],"study_design_scores_gemma":[0.00058586535,0.00076019444,0.0031629729,0.00017320528,0.00002175554,0.000004631405,0.00008644096,0.95109475,0.042434745,0.0011535925,0.00032774254,0.00019412188],"about_ca_topic_score_codex":0.00006517717,"about_ca_topic_score_gemma":0.000007752088,"teacher_disagreement_score":0.9057125,"about_ca_system_score_codex":0.000035746823,"about_ca_system_score_gemma":0.000060082293,"threshold_uncertainty_score":0.39673468},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051558563,0.0003249681,0.1378494,0.0017209991,0.001606973,0.00056591694,0.000034181638,0.000737734,0.85715467],"genre_scores_gemma":[0.0009627616,0.000044059547,0.03337308,0.0076294807,0.0022346654,0.00007531313,0.00015009627,0.00020017062,0.9553304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948124,0.00008054364,0.0011523367,0.0016881555,0.0012982321,0.00096827396],"domain_scores_gemma":[0.9961803,0.0003127598,0.00089097413,0.0018875038,0.0002116182,0.0005168401],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0010452797,0.0009509014,0.0008292912,0.0006233363,0.00035661017,0.000999756,0.0041809496,0.001698402,0.00020842842],"category_scores_gemma":[0.00019949868,0.0008392161,0.00040237614,0.0000673353,0.00022035468,0.0020631244,0.0018147412,0.0052449363,0.00047065233],"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":[0.000041091116,0.000017703018,0.0000018933358,0.00002719903,0.00007945629,0.00008533413,0.00081383693,0.00005692029,0.00004142497,0.30084404,0.32279646,0.37519464],"study_design_scores_gemma":[0.0006986765,0.000091217415,0.0000037072896,0.00050807954,0.00003566689,0.000044200882,0.000011091447,0.016405303,0.00002802147,0.060544595,0.9206248,0.0010046405],"about_ca_topic_score_codex":0.000025590278,"about_ca_topic_score_gemma":0.0000062964036,"teacher_disagreement_score":0.5978283,"about_ca_system_score_codex":0.00032518347,"about_ca_system_score_gemma":0.00039254408,"threshold_uncertainty_score":0.9995976},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019341389,0.00006167707,0.9935594,0.0008757164,0.00021259005,0.00007707245,0.000006807098,0.00023641413,0.003036183],"genre_scores_gemma":[0.37610433,0.0000051443867,0.6219674,0.0011083009,0.00008461796,0.0000066395846,0.000014382161,0.000010151029,0.0006990366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987937,0.000042127864,0.00017159397,0.0003666506,0.0003620385,0.00026385297],"domain_scores_gemma":[0.9991055,0.00010780902,0.0000503144,0.00054044503,0.000074019044,0.000121883386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015246606,0.00012522687,0.0001375635,0.00006958619,0.00019668124,0.00018839203,0.00062911113,0.000045774155,0.0007315852],"category_scores_gemma":[0.000013716277,0.00010254745,0.000051108316,0.00019668273,0.00004728783,0.0006329863,0.0003306767,0.000104603576,0.00039254024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034109933,0.0020260366,0.0008412212,0.000107499574,0.00008008591,0.00043266482,0.0003655087,0.0013134362,0.110177144,0.13662043,0.17640586,0.57159597],"study_design_scores_gemma":[0.0003269147,0.00003312418,0.00034782485,0.000023412806,0.0000027964575,0.00001260814,0.0000019719093,0.9859934,0.00918843,0.00096839044,0.002923724,0.00017739557],"about_ca_topic_score_codex":0.00005907886,"about_ca_topic_score_gemma":0.0000045580846,"teacher_disagreement_score":0.98468,"about_ca_system_score_codex":0.000022137,"about_ca_system_score_gemma":0.000013254509,"threshold_uncertainty_score":0.8010345},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006422093,0.000115749055,0.9969528,0.00040012438,0.0003741432,0.00013349904,0.0000022994398,0.00025898695,0.001120224],"genre_scores_gemma":[0.78299206,9.4329454e-7,0.2166292,0.0001397059,0.00010400049,0.0000029002474,0.0000012780057,0.0000063795037,0.00012350328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988773,0.00003176258,0.00020788155,0.00030538812,0.00030745586,0.00027021448],"domain_scores_gemma":[0.99899113,0.000058653673,0.00006928665,0.00074134907,0.000027403368,0.0001121977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020677556,0.00012166156,0.00013476714,0.000078382545,0.00021561794,0.00027601531,0.0008930978,0.000038113893,0.00002200106],"category_scores_gemma":[0.000011871532,0.00009685473,0.00004186265,0.00015698436,0.000023130124,0.0008224086,0.00067872397,0.000075182565,0.000041131545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035107387,0.000017561195,0.0000061591763,0.000012503462,0.000012048426,0.000008661142,0.00016649757,0.0049157306,0.0001331045,0.9778816,0.001685247,0.01515739],"study_design_scores_gemma":[0.000490991,0.000026857722,0.0000069929542,0.000093080795,0.00000631844,0.000050149112,0.0005055442,0.99089324,0.00012791957,0.006720269,0.0009020223,0.00017658068],"about_ca_topic_score_codex":0.00013784012,"about_ca_topic_score_gemma":0.000029277287,"teacher_disagreement_score":0.98597753,"about_ca_system_score_codex":0.0004667411,"about_ca_system_score_gemma":0.00004135288,"threshold_uncertainty_score":0.39496213},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021859254,0.00015019944,0.9953526,0.0015561852,0.00053396885,0.0011691502,0.000021824306,0.00016628247,0.0010279313],"genre_scores_gemma":[0.010807137,0.00002157473,0.9868465,0.0015248558,0.00023312468,0.000093219984,0.000022348166,0.000041413474,0.00040981077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642056,0.000024447187,0.00037067922,0.0017729014,0.00072295766,0.00068846904],"domain_scores_gemma":[0.9971588,0.0002985965,0.0002491417,0.0017068416,0.0003245584,0.00026202106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055709004,0.0005101575,0.0004846677,0.0006323979,0.00043962544,0.00047759613,0.0027941968,0.00027360593,0.0000030234255],"category_scores_gemma":[0.000030017558,0.00042468298,0.0000911785,0.0006296378,0.00028586277,0.0007126932,0.0010413988,0.00045684417,0.000010261181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041570733,0.000049547107,0.000006336432,0.000049806527,0.000019099483,0.000044106862,0.0006982409,0.26502094,0.00018343584,0.095285706,0.0006362635,0.63796496],"study_design_scores_gemma":[0.00032120055,0.00033111827,0.00001067515,0.0002549002,0.00001116544,0.00012412069,3.649826e-7,0.9368829,0.00042302214,0.05767029,0.0033265788,0.0006436343],"about_ca_topic_score_codex":0.000027139275,"about_ca_topic_score_gemma":0.000039032486,"teacher_disagreement_score":0.671862,"about_ca_system_score_codex":0.00026993523,"about_ca_system_score_gemma":0.00035857156,"threshold_uncertainty_score":0.9998205},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7244434,0.0002266548,0.27235657,0.00028159775,0.00006561861,0.00009018809,0.0000011208901,0.00018306561,0.002351813],"genre_scores_gemma":[0.94403124,0.00005682474,0.05567717,0.00011856404,0.000025766723,0.0000061873493,0.0000012538378,0.0000026884416,0.0000803046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926734,0.000064610365,0.00008204848,0.00030634436,0.00012540435,0.00015427417],"domain_scores_gemma":[0.99946207,0.00019405072,0.000028609471,0.00023341186,0.000013525099,0.000068353474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011561412,0.000105996536,0.00012865002,0.0000329415,0.00020428539,0.00006282144,0.00029327712,0.000035926718,0.000010763809],"category_scores_gemma":[0.000020719723,0.000050812116,0.000016266442,0.000108709275,0.00012787219,0.0002947665,0.00022315742,0.00007019413,0.000011620599],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010906115,0.00018307751,0.2290313,0.00008095392,0.00007165689,0.00131279,0.0008783975,0.00013061157,0.026293771,0.035192944,0.0015283917,0.705187],"study_design_scores_gemma":[0.0021688365,0.003969638,0.29963538,0.00033024733,0.000022575316,0.006223019,0.00005748351,0.64461035,0.028753974,0.005231421,0.0073989867,0.0015980866],"about_ca_topic_score_codex":0.000060179125,"about_ca_topic_score_gemma":0.000004433445,"teacher_disagreement_score":0.70358896,"about_ca_system_score_codex":0.0000056727326,"about_ca_system_score_gemma":0.000015294221,"threshold_uncertainty_score":0.2072058},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013380456,0.000006814454,0.9854558,0.00004991127,0.00014180456,0.000106033054,0.00006248369,0.00011981921,0.00067684526],"genre_scores_gemma":[0.9801653,0.000017701004,0.019452475,0.0002888287,0.000004491734,0.000015379686,0.000035394598,0.000002711297,0.000017699862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990839,0.000044000615,0.00036002832,0.0001083779,0.00027718997,0.00012649727],"domain_scores_gemma":[0.9990495,0.00008604514,0.00016634742,0.00051210047,0.00013289138,0.000053106774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035973833,0.000104708066,0.00017293969,0.00068703806,0.00016842778,0.00006254693,0.00035438203,0.000053129457,0.00005821668],"category_scores_gemma":[0.0000049376476,0.000089579575,0.00013207058,0.0013468786,0.00004699117,0.0018673044,0.0000023564498,0.0001100894,0.000054014778],"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":[0.00006712957,0.00009780487,0.000014014568,0.000037486225,0.0001547381,2.9186393e-7,0.00062904955,0.7887021,0.000103209,0.018610027,0.00001683238,0.19156738],"study_design_scores_gemma":[0.0009681785,0.00022528238,0.0014555494,0.00008713547,0.00021414596,0.000002122421,0.00006960579,0.9584729,0.036119934,0.0014130427,0.00073056587,0.00024151572],"about_ca_topic_score_codex":0.000014770681,"about_ca_topic_score_gemma":0.0000015304906,"teacher_disagreement_score":0.96678483,"about_ca_system_score_codex":0.000047892925,"about_ca_system_score_gemma":0.00006335692,"threshold_uncertainty_score":0.3652949},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0115398085,0.000058439062,0.98497075,0.0020584709,0.0002094267,0.0002643586,0.000020697762,0.00025052275,0.0006275067],"genre_scores_gemma":[0.1910167,0.0000043783048,0.80704635,0.0013840501,0.00016743639,0.000029816154,0.000038451326,0.000014340779,0.00029845588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869776,0.000033564942,0.00023571102,0.00045548935,0.00024112636,0.00033635207],"domain_scores_gemma":[0.99890757,0.00013457955,0.00008335045,0.0006614413,0.00007730334,0.00013574059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019861072,0.00016586979,0.00016724657,0.00006635703,0.0002823216,0.00028469585,0.0007880795,0.00006305103,0.00013158204],"category_scores_gemma":[0.000017249053,0.00013121426,0.00008162717,0.00013899726,0.00003889843,0.0009188407,0.00045226334,0.00009775504,0.00012092424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008974765,0.0008554424,0.0008029669,0.00014133906,0.00002590075,0.000050213064,0.00040129913,0.0011075615,0.12179268,0.0029370757,0.24335839,0.6284374],"study_design_scores_gemma":[0.0008467697,0.000070698916,0.00036915866,0.00007329222,0.0000027079661,0.0000032067453,0.000007878636,0.9347899,0.010211348,0.00006420016,0.053367876,0.00019298658],"about_ca_topic_score_codex":0.000024628807,"about_ca_topic_score_gemma":0.0000026735709,"teacher_disagreement_score":0.9336823,"about_ca_system_score_codex":0.000027915381,"about_ca_system_score_gemma":0.00005551786,"threshold_uncertainty_score":0.5350762},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15397368,0.00003807038,0.843432,0.00035550373,0.00024311393,0.00014484095,0.0000015002703,0.00007765371,0.0017336464],"genre_scores_gemma":[0.7143939,0.0000035289831,0.28540218,0.00014655007,0.00004071652,0.000001495296,9.566576e-7,0.000003818376,0.0000068486397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977008,0.00010144525,0.00028872353,0.00070579094,0.0006216787,0.0005815438],"domain_scores_gemma":[0.99864715,0.0003719794,0.000057306817,0.0005483704,0.00008652196,0.00028867146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016443543,0.00015988105,0.00016858739,0.00036825298,0.00042593418,0.00030766623,0.0013692499,0.000055600576,0.000015335867],"category_scores_gemma":[0.000065721884,0.00012739834,0.000026539075,0.001201112,0.001194872,0.0013603583,0.0017119037,0.00030763104,0.00001509219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000187817,0.00003610618,0.0007409209,0.0000020383998,0.0000017258285,0.00004969975,0.00083202234,0.0001701358,0.0009540371,0.8802775,0.000020407651,0.116896614],"study_design_scores_gemma":[0.0003626225,0.00017493148,0.04595074,0.000043560096,0.0000016154419,0.000036046094,0.000020157942,0.7999246,0.0013009295,0.15195638,0.000042056487,0.00018636503],"about_ca_topic_score_codex":0.00002584893,"about_ca_topic_score_gemma":0.000010697855,"teacher_disagreement_score":0.79975444,"about_ca_system_score_codex":0.00008173695,"about_ca_system_score_gemma":0.00009232801,"threshold_uncertainty_score":0.51951534},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040368063,0.00011248313,0.99276197,0.00062611775,0.000041525327,0.00023044784,0.0000021307035,0.00021452863,0.005607124],"genre_scores_gemma":[0.13911799,0.000008118262,0.86009014,0.00047042326,0.000087062785,0.00004793956,0.000006151139,0.0000025657803,0.0001696084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993082,0.000006434882,0.00012714273,0.0002529442,0.00013046978,0.00017479718],"domain_scores_gemma":[0.9993999,0.000037101992,0.000038634524,0.00039025978,0.00008031749,0.0000537571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011979068,0.000076216966,0.00007970463,0.000026953654,0.00017644784,0.00025931938,0.00051042944,0.00003251696,0.000005814227],"category_scores_gemma":[0.0000059112426,0.00006175486,0.000034549597,0.00012553438,0.000010190914,0.0007977024,0.00006546226,0.000047161917,0.000020671798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017723175,0.000021371734,0.0000021157384,0.000005213471,0.0000029609796,7.023464e-7,0.00012727482,0.0030228351,0.0045182966,0.8996569,0.0006893472,0.09195119],"study_design_scores_gemma":[0.00027398227,0.00007121903,0.000096051794,0.000015059909,0.0000032258993,0.000006654789,0.0002131927,0.7463063,0.0013008881,0.23393355,0.017583469,0.00019636827],"about_ca_topic_score_codex":0.000016147189,"about_ca_topic_score_gemma":0.0000035823975,"teacher_disagreement_score":0.7432835,"about_ca_system_score_codex":0.00004071074,"about_ca_system_score_gemma":0.00019230341,"threshold_uncertainty_score":0.251829},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14644854,0.00005182899,0.85276943,0.000032944554,0.00011262375,0.000082433486,0.000031175077,0.00004817269,0.00042283698],"genre_scores_gemma":[0.7445895,0.0000035907487,0.25534695,0.000011299845,0.00001534908,7.72971e-7,0.0000093099425,0.000005147374,0.000018057443],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988914,0.000009043059,0.0003166955,0.00025548236,0.000340631,0.00018675851],"domain_scores_gemma":[0.99908185,0.000040236613,0.00017103912,0.0005182048,0.0001132845,0.000075358046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008857792,0.00012153896,0.00023270602,0.000079256126,0.00005720022,0.00008317113,0.00070682575,0.00005525354,0.0000063010248],"category_scores_gemma":[0.000012205597,0.00008962157,0.000074590935,0.0002797913,0.00010020084,0.00078985444,0.00060806115,0.00006699518,0.0000025612487],"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":[0.00008677552,0.002910136,0.0040723477,0.00028167004,0.00009668684,0.00003153178,0.001188774,0.021664962,0.49970165,0.20988843,0.00019178508,0.25988525],"study_design_scores_gemma":[0.004667665,0.0005241296,0.005447407,0.0011056629,0.000031449035,0.00014923657,0.0002654237,0.5539442,0.40982246,0.02186469,0.0012869334,0.00089073787],"about_ca_topic_score_codex":0.0003995961,"about_ca_topic_score_gemma":0.0000055109535,"teacher_disagreement_score":0.59814095,"about_ca_system_score_codex":0.000019564532,"about_ca_system_score_gemma":0.000048498234,"threshold_uncertainty_score":0.36546618},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058548927,0.00005573362,0.93906236,0.0007132333,0.0013512607,0.00013988992,0.0000103473485,0.000021684958,0.00009658437],"genre_scores_gemma":[0.25362602,6.4457146e-7,0.745933,0.000053723496,0.00037383047,0.0000015888234,5.2076126e-7,0.000004574351,0.0000060928132],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980601,0.0000624401,0.0005360712,0.00029118007,0.00074320496,0.00030702603],"domain_scores_gemma":[0.9980053,0.00054016284,0.00064915995,0.00026513357,0.00039586736,0.00014443022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041708224,0.0001327863,0.00026982545,0.00030368796,0.00075373636,0.0005205211,0.0012335117,0.000084987856,0.0000050769786],"category_scores_gemma":[0.00067831494,0.00009730236,0.00015539567,0.000595763,0.00017322156,0.0020996958,0.00030144543,0.00035815244,8.0372024e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049962015,0.00024147768,0.022862129,0.0001236013,0.00016210016,0.000021524924,0.0035989597,0.007014392,0.5617933,0.030725218,0.0017982674,0.37160906],"study_design_scores_gemma":[0.00067461486,0.00020413821,0.012450319,0.00026593174,0.000060963874,0.00031428953,0.00018234961,0.9392547,0.020359715,0.024978902,0.00096308085,0.00029096834],"about_ca_topic_score_codex":0.000044106113,"about_ca_topic_score_gemma":0.000056350298,"teacher_disagreement_score":0.9322403,"about_ca_system_score_codex":0.000036906422,"about_ca_system_score_gemma":0.00030577433,"threshold_uncertainty_score":0.5797207},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00512697,0.000009248065,0.98049194,0.0049128267,0.00014371696,0.00022599981,0.000001041655,0.00015430847,0.008933955],"genre_scores_gemma":[0.6297594,7.7512925e-7,0.36732972,0.002743092,0.00014146115,0.0000024080048,4.3596643e-7,0.000003022801,0.000019698962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744445,0.00006326824,0.00015983942,0.0008509338,0.00095966266,0.00052185677],"domain_scores_gemma":[0.9980406,0.00009217625,0.00004344001,0.0013144567,0.00008912375,0.00042017366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082389824,0.00019482308,0.00016741683,0.00011635928,0.0006610235,0.0009446484,0.0040738783,0.000031727952,0.0000108458835],"category_scores_gemma":[0.00003147915,0.00010110896,0.00003761785,0.0012421437,0.00084623613,0.0005287634,0.0008175881,0.0002396158,0.00010749855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015523055,0.00005413383,0.0000046920786,7.791334e-7,0.0000010295864,0.0000036323463,0.0005341162,0.0010848404,0.000034651068,0.8445441,0.000833989,0.1528885],"study_design_scores_gemma":[0.00048431417,0.0015286359,0.005365961,0.00007998934,0.0000054963407,0.00010265118,0.00001935386,0.9173553,0.0016299547,0.06886446,0.0040837275,0.00048015366],"about_ca_topic_score_codex":0.0000067881824,"about_ca_topic_score_gemma":2.611733e-7,"teacher_disagreement_score":0.91627043,"about_ca_system_score_codex":0.00003856521,"about_ca_system_score_gemma":0.00015804982,"threshold_uncertainty_score":0.91092664},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019630888,0.00006657559,0.991681,0.00021998,0.0003914385,0.0000848776,0.0000029501175,0.00008076745,0.0055093463],"genre_scores_gemma":[0.60783654,0.000008975638,0.39130917,0.00026985566,0.000017305703,0.000005240949,0.0000026635316,0.0000040255504,0.00054620224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992116,0.00004064013,0.00017251827,0.00022484516,0.00021194019,0.00013844416],"domain_scores_gemma":[0.9992555,0.00006911737,0.000044718625,0.00044496416,0.00008462594,0.000101083184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011921516,0.000076687356,0.00011955299,0.00006919013,0.00015314715,0.00003568579,0.0003197626,0.000028873257,0.000102357175],"category_scores_gemma":[0.000042814656,0.0000565778,0.000031094172,0.00014078607,0.00002010831,0.00030683188,0.0002659799,0.000051888885,0.00005052689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020035703,0.0004408217,0.001536646,0.000024124296,0.000026331962,0.000016573162,0.0013283686,0.0021606644,0.11109315,0.71165085,0.085179046,0.0865234],"study_design_scores_gemma":[0.0011048319,0.00037320613,0.025322732,0.0003001142,0.000015245358,0.00007511328,0.00025267177,0.52761024,0.13451888,0.025618244,0.2840395,0.0007692047],"about_ca_topic_score_codex":0.000053787928,"about_ca_topic_score_gemma":0.000004054104,"teacher_disagreement_score":0.6860326,"about_ca_system_score_codex":0.000011601552,"about_ca_system_score_gemma":0.000023265864,"threshold_uncertainty_score":0.23071757},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043255966,0.00028389232,0.9619954,0.00042315482,0.00068085757,0.00010974288,0.0000015446159,0.00023881484,0.031940993],"genre_scores_gemma":[0.89790803,0.000022249791,0.09785467,0.00059217325,0.0003279514,0.000012259287,0.000014735313,0.000008831175,0.0032591177],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990923,0.000044021865,0.00013220013,0.00021041383,0.00021041794,0.00031064334],"domain_scores_gemma":[0.9990684,0.00006239126,0.000032231183,0.00061340036,0.000067268884,0.00015633772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026848534,0.00009797301,0.00011362277,0.000049474478,0.00009610322,0.00010515275,0.00058120425,0.000054024695,0.00028136396],"category_scores_gemma":[0.000027366705,0.00006743179,0.000030650088,0.00028257797,0.000010179099,0.0011352221,0.0004663948,0.00009216313,0.00053378515],"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":[0.00006400227,0.00066627667,0.009684529,0.00002875137,0.000066559405,0.0000060193906,0.0016648468,0.000064721295,0.003428793,0.119002424,0.28314427,0.58217883],"study_design_scores_gemma":[0.0051508993,0.00010942371,0.06936842,0.000052625106,0.000021519169,0.00004564792,0.000042735934,0.19520633,0.01821213,0.0023554799,0.7084773,0.0009574821],"about_ca_topic_score_codex":0.000032790038,"about_ca_topic_score_gemma":0.000002426848,"teacher_disagreement_score":0.8935824,"about_ca_system_score_codex":0.000012940674,"about_ca_system_score_gemma":0.000018059367,"threshold_uncertainty_score":0.68609065},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002891141,0.000089572255,0.994388,0.00010472727,0.000077477074,0.00005607581,3.9465525e-7,0.00026960377,0.004725059],"genre_scores_gemma":[0.008451729,0.000041176776,0.9910083,0.00018352874,0.000045546007,0.0000021371143,6.927266e-7,0.0000038098374,0.0002631171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950475,0.000014912781,0.0000913051,0.00017091064,0.00011341598,0.000104707105],"domain_scores_gemma":[0.99957955,0.000008257715,0.000027071212,0.00031926885,0.000029734943,0.000036113634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000033212214,0.000055654742,0.000050603518,0.00004744785,0.00007494756,0.00010203439,0.00032858568,0.000029211702,0.00020317984],"category_scores_gemma":[0.0000042866873,0.00004520879,0.000016441667,0.000151758,0.000010069106,0.00038810066,0.0001860176,0.0000319569,0.000023455828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001117659,0.00014037525,0.00035290996,0.000010500766,0.000008930719,0.000027840648,0.00023295982,0.09243239,0.0019043793,0.0080115395,0.015799271,0.88107777],"study_design_scores_gemma":[0.000033452616,0.000014960106,0.000047126927,0.0000062502227,9.940286e-7,0.0000121122375,0.0000012620774,0.99464947,0.0018187138,0.00017124019,0.003173374,0.00007107105],"about_ca_topic_score_codex":0.00002203388,"about_ca_topic_score_gemma":1.9020976e-7,"teacher_disagreement_score":0.90221703,"about_ca_system_score_codex":0.000013315076,"about_ca_system_score_gemma":0.000004068684,"threshold_uncertainty_score":0.22246768},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09569865,0.00090817816,0.90015864,0.0012264712,0.001404846,0.00008815045,9.948831e-7,0.00003203072,0.00048204127],"genre_scores_gemma":[0.7674095,0.000023337881,0.2317271,0.00035917212,0.00044316016,0.0000012855065,8.467366e-8,0.0000028735035,0.000033508826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985188,0.00007769203,0.00043187218,0.00022411265,0.0005420408,0.00020543256],"domain_scores_gemma":[0.9990026,0.00010008405,0.00031886116,0.00019623099,0.00022265315,0.00015958882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079119904,0.00011012137,0.0002476218,0.00018251486,0.00027957628,0.00093149557,0.0010245158,0.000035029872,0.000009661148],"category_scores_gemma":[0.000004959203,0.00006785585,0.000073986055,0.00030479627,0.00007449319,0.0017938477,0.00028640512,0.00010787008,0.000020794818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013919542,0.00022715978,0.028018419,0.0005069509,0.00013722744,0.00018049031,0.008966522,0.0018742763,0.0013741041,0.066649444,0.22375678,0.6682947],"study_design_scores_gemma":[0.00058198447,0.0007679893,0.013376248,0.000698387,0.000010295291,0.0019913942,0.0005296115,0.96913826,0.0002952874,0.001910945,0.010384308,0.0003152737],"about_ca_topic_score_codex":0.000029987776,"about_ca_topic_score_gemma":2.2989484e-7,"teacher_disagreement_score":0.967264,"about_ca_system_score_codex":0.00001741969,"about_ca_system_score_gemma":0.00007301265,"threshold_uncertainty_score":0.8982433},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014347423,0.000049158105,0.9894154,0.00079211796,0.0000938634,0.00019553876,0.0000047570816,0.00032111906,0.008984557],"genre_scores_gemma":[0.0013708408,0.000052361676,0.99534583,0.00025735697,0.00012740401,0.000013054515,0.000009386321,0.0000047554067,0.0028190278],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936503,0.000012768174,0.000094197356,0.00022582199,0.00014226495,0.00015992358],"domain_scores_gemma":[0.99950975,0.000042141433,0.00001724864,0.00029592754,0.00006072895,0.000074181655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000121179604,0.00006244814,0.000062351304,0.000078994606,0.000081873266,0.000114118215,0.00039652394,0.000040355048,0.00027544843],"category_scores_gemma":[0.00000906381,0.00004969345,0.00003855791,0.00018938702,0.000007712715,0.00055153243,0.00013482243,0.000053035936,0.00010927119],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.4536805e-7,0.000014975922,0.000004265226,0.0000026194064,0.0000013686583,0.0000011349483,0.000023865861,9.7819004e-8,0.0003226458,0.0017280085,0.09659756,0.90130264],"study_design_scores_gemma":[0.00073126744,0.0005525934,0.00015246944,0.000079227124,0.000007208261,0.0000641643,0.00002447577,0.21374246,0.39308506,0.12618178,0.264794,0.00058529794],"about_ca_topic_score_codex":0.00008012814,"about_ca_topic_score_gemma":0.0000034014058,"teacher_disagreement_score":0.9007173,"about_ca_system_score_codex":0.000008659523,"about_ca_system_score_gemma":0.000009292258,"threshold_uncertainty_score":0.30159673},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009632111,0.00012605113,0.9838985,0.00023068774,0.0007575529,0.00016091629,0.000018093177,0.00013640976,0.005039656],"genre_scores_gemma":[0.37110397,0.000024496654,0.6283226,0.00012512857,0.00012615765,6.2815775e-7,0.0000811677,0.000008718328,0.00020710749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794424,0.000035067587,0.0005133023,0.0006321797,0.0005753989,0.00029979378],"domain_scores_gemma":[0.99649435,0.0002405855,0.00020448191,0.0028229868,0.00012049105,0.00011712593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001128383,0.00015778295,0.00024206766,0.00010063982,0.00013653532,0.00008577773,0.0030128807,0.00008636695,0.0001415738],"category_scores_gemma":[0.00003613352,0.00011203932,0.00003872114,0.00034591596,0.000047382502,0.0015741736,0.004470691,0.00014677942,0.000066559514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022315976,0.00054934423,0.0005905047,0.000053459382,0.000032813183,0.00004595285,0.00052156945,0.0004547895,0.027466653,0.17011215,0.068192266,0.73175734],"study_design_scores_gemma":[0.005167917,0.0004167459,0.009696337,0.00051037455,0.000022401111,0.000056896526,0.00017199264,0.5931045,0.3072238,0.015253587,0.06743807,0.0009373938],"about_ca_topic_score_codex":0.0005328589,"about_ca_topic_score_gemma":0.00002287698,"teacher_disagreement_score":0.73081994,"about_ca_system_score_codex":0.000018760165,"about_ca_system_score_gemma":0.00003751655,"threshold_uncertainty_score":0.5598732},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015508839,0.0013765503,0.9824103,0.00021699874,0.0003708484,0.00008244055,0.000008604964,0.000010568806,0.0000148280715],"genre_scores_gemma":[0.79007983,0.00010433341,0.20944843,0.00004988927,0.00030200716,9.740902e-7,0.000002760513,0.000004350151,0.0000073919964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990433,0.000056534183,0.00044183715,0.00012841847,0.00015058545,0.00017936331],"domain_scores_gemma":[0.9988633,0.00027925888,0.00048163277,0.00015551296,0.00015556243,0.00006474811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035388142,0.000097493474,0.00020077011,0.000047159763,0.0001975023,0.0001027741,0.0003927638,0.00004670647,0.0000048227885],"category_scores_gemma":[0.000042941545,0.00006338784,0.00010032132,0.00017575992,0.000033366883,0.0002007278,0.0001809002,0.00015775627,4.1170264e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000128011625,0.00009503181,0.0008655517,0.0000191993,0.00008044251,0.00001822678,0.0005139001,0.06513293,0.000055271586,0.0008222091,0.00559288,0.92679155],"study_design_scores_gemma":[0.00054556265,0.00014106739,0.003489695,0.000075839,0.000017158007,0.00023315848,0.00007112854,0.99346614,0.000017457065,0.000636865,0.0012301217,0.0000757981],"about_ca_topic_score_codex":0.0000063239695,"about_ca_topic_score_gemma":3.9463427e-7,"teacher_disagreement_score":0.9283332,"about_ca_system_score_codex":0.00001657911,"about_ca_system_score_gemma":0.000009820652,"threshold_uncertainty_score":0.25848812},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044434032,0.0000050664416,0.99231416,0.0003103719,0.00017196272,0.00068558834,0.00009288004,0.00025623923,0.005719374],"genre_scores_gemma":[0.61569625,0.0000013860912,0.38242897,0.00015556278,0.00007330792,0.0001445938,0.0013097378,0.000010816528,0.00017938278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861515,0.00012396049,0.00030057793,0.00041597692,0.00029909585,0.00024526875],"domain_scores_gemma":[0.99898994,0.000094705414,0.00013260718,0.0004134989,0.00031334555,0.000055877143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006532223,0.00014548565,0.00012695379,0.00014692328,0.00030290277,0.00019208812,0.00025036698,0.00009615734,0.000012895754],"category_scores_gemma":[0.000078893885,0.00012421273,0.000050188475,0.00039863927,0.00003988592,0.000598071,0.000057165682,0.00007920229,0.000006240605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012704625,0.000923821,0.0034384916,0.00014289869,0.000024125176,0.0000015895795,0.00014572799,0.1954656,0.002874097,0.49230403,0.025109433,0.27944314],"study_design_scores_gemma":[0.0006297211,0.00012675555,0.03151363,0.000017018254,0.0000044642575,0.0000027141193,0.0000055918504,0.96494853,0.00044216716,0.0014951475,0.0006489417,0.0001653101],"about_ca_topic_score_codex":0.0030210456,"about_ca_topic_score_gemma":0.0003890136,"teacher_disagreement_score":0.7694829,"about_ca_system_score_codex":0.000081118276,"about_ca_system_score_gemma":0.00016470878,"threshold_uncertainty_score":0.5065248},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025693611,0.00009313687,0.96301264,0.00003120305,0.00022343549,0.00004337066,4.299535e-7,0.00015897305,0.033867475],"genre_scores_gemma":[0.5089369,0.000009658225,0.48853546,0.00046164604,0.00009456363,0.0000037927878,0.0000021845326,0.0000042408305,0.0019515498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940234,0.0000058735554,0.00010453802,0.00017162599,0.00014531182,0.00017030661],"domain_scores_gemma":[0.99950755,0.000031533596,0.000020944279,0.00035011448,0.00002332148,0.000066562934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026965444,0.000048883925,0.00004996854,0.000039448994,0.00007256,0.0000756744,0.0004186906,0.000022076725,0.000048742804],"category_scores_gemma":[0.0000051652314,0.000036083886,0.00002091591,0.00014910533,0.000009162928,0.0003285348,0.00026065152,0.000046513433,0.000073337455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034381471,0.00007287031,0.000550416,0.000004605035,0.00000572858,0.00006143929,0.00025169938,0.000024578201,0.005372344,0.12417124,0.011635384,0.85784626],"study_design_scores_gemma":[0.00039719735,0.00017952877,0.008339004,0.000031207506,0.0000023885107,0.000041112453,0.00013638765,0.15457395,0.013614229,0.002747629,0.8195225,0.00041488252],"about_ca_topic_score_codex":0.00001177511,"about_ca_topic_score_gemma":0.000004276494,"teacher_disagreement_score":0.85743135,"about_ca_system_score_codex":0.000014663831,"about_ca_system_score_gemma":0.000013019421,"threshold_uncertainty_score":0.14714582},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064319395,0.000058665348,0.9344893,0.0007573992,0.000096948526,0.00009085988,0.000032723758,0.000052055017,0.000102620026],"genre_scores_gemma":[0.7330809,0.00005069024,0.26666418,0.00014164732,0.000022219469,0.000004516174,0.000022879934,0.0000022215422,0.000010692789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992811,0.000027700404,0.0003364741,0.00014697305,0.000097739794,0.00010997738],"domain_scores_gemma":[0.9994114,0.00013682726,0.00012803085,0.0002027376,0.00006683675,0.000054168755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014442847,0.00010332037,0.00013910951,0.0001461348,0.00024838746,0.0000363138,0.00018275625,0.000080408296,0.000007779204],"category_scores_gemma":[0.000006511789,0.00008522448,0.000030373025,0.000114089555,0.0001283785,0.00041010304,0.000018497016,0.0001118126,0.000007082672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014136717,0.0002270535,0.0005416174,0.00010460297,0.00006952951,5.9842523e-7,0.0013955006,0.009770463,0.0035514573,0.033795383,0.00015988316,0.9503698],"study_design_scores_gemma":[0.0005313711,0.00028462254,0.012784037,0.000049672686,0.00001148162,0.000036671085,0.000074913994,0.97238946,0.00274594,0.010438625,0.00047515112,0.00017804699],"about_ca_topic_score_codex":0.000004930753,"about_ca_topic_score_gemma":0.000002715358,"teacher_disagreement_score":0.962619,"about_ca_system_score_codex":0.000014438106,"about_ca_system_score_gemma":0.000026020232,"threshold_uncertainty_score":0.3475353},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62167776,0.09175222,0.026273089,0.018282345,0.23684587,0.00042241946,0.0010877915,0.000029178571,0.0036293427],"genre_scores_gemma":[0.97809947,0.00051005,0.018319236,0.0008346873,0.00030645545,0.000002850555,0.0000075275543,0.000019065628,0.0019006409],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99791586,0.00015123225,0.0006869177,0.0002735741,0.0004913799,0.0004810208],"domain_scores_gemma":[0.99452937,0.003480362,0.0006340171,0.00034097373,0.0005206893,0.0004945659],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005272157,0.00021654884,0.00045285677,0.00020849812,0.0004641166,0.00021729596,0.0007407506,0.0002618787,0.0012384136],"category_scores_gemma":[0.0031642956,0.00018926448,0.000083673076,0.00047009287,0.00020558697,0.00055976503,0.00041713714,0.0012323594,0.000003554058],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004533169,0.00014814713,0.0032177179,0.00005787204,0.00009351571,0.00360161,0.00040610545,0.0005793184,0.00006272776,0.011672997,0.14634444,0.833811],"study_design_scores_gemma":[0.002103598,0.00036914033,0.08146243,0.000026342383,0.000049337348,0.00047975648,0.00041178212,0.040184874,0.00015457069,0.0010099559,0.87342316,0.00032502974],"about_ca_topic_score_codex":0.1436548,"about_ca_topic_score_gemma":0.17036517,"teacher_disagreement_score":0.83348596,"about_ca_system_score_codex":0.00055875187,"about_ca_system_score_gemma":0.006835132,"threshold_uncertainty_score":0.9996746},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014679334,0.0000669841,0.99233806,0.00016866853,0.000062584004,0.00026533392,0.0000025467646,0.00014457136,0.0054833307],"genre_scores_gemma":[0.5265773,3.6822075e-7,0.4708467,0.000020790096,0.00010972562,0.00005456949,0.000010906476,0.0000036154784,0.0023760248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994151,0.000009182528,0.000106596366,0.0002043429,0.00010084578,0.00016392938],"domain_scores_gemma":[0.9996554,0.000012317004,0.000033278902,0.00023648258,0.000037206893,0.000025297077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009347984,0.000062423715,0.000058959882,0.0000296826,0.000109628105,0.00010927585,0.00029697697,0.000031009502,0.000009169782],"category_scores_gemma":[0.0000036991567,0.00004792876,0.000028023716,0.00008532876,0.00000886288,0.0005085994,0.000080463,0.000030109975,0.000019578532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039122206,0.000028727694,0.000034065284,0.0000049751065,0.0000012577198,7.5837295e-7,0.000004188785,0.0008929897,0.0022507203,0.9806287,0.004595498,0.011554187],"study_design_scores_gemma":[0.0003710462,0.000111243404,0.0016389546,0.000015166626,0.0000013540526,0.0000033822105,0.0000073063643,0.73000133,0.002110227,0.259304,0.0062852087,0.00015077749],"about_ca_topic_score_codex":0.00025255565,"about_ca_topic_score_gemma":0.000022630513,"teacher_disagreement_score":0.72910833,"about_ca_system_score_codex":0.00002312958,"about_ca_system_score_gemma":0.000028371014,"threshold_uncertainty_score":0.19544782},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07093951,0.0061500887,0.89562726,0.009207138,0.00048265254,0.001036107,0.000024739835,0.00045928368,0.016073234],"genre_scores_gemma":[0.92299443,0.00049671985,0.07086654,0.0006059538,0.0013881136,0.000042060412,0.00010666263,0.000021477194,0.003478056],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972675,0.00022235136,0.0002285394,0.00060746976,0.0009640348,0.00071010116],"domain_scores_gemma":[0.9982404,0.000055839624,0.000036721372,0.0011051599,0.0003238522,0.00023803543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013060505,0.00013439092,0.00014845833,0.00032266462,0.00050253264,0.00071239227,0.0015652679,0.000090389774,0.00015076612],"category_scores_gemma":[0.000057927267,0.0001173494,0.000052923915,0.00093108334,0.000052630727,0.0010398374,0.00055760966,0.00038905823,0.00080348906],"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":[0.000013636679,0.00020027458,0.000019523077,0.0000128555075,0.000012971918,0.0000885431,0.00078343024,0.00029586794,0.7620985,0.028599812,0.006369177,0.20150541],"study_design_scores_gemma":[0.0013359317,0.0014899786,0.037648622,0.00004036762,0.0000061967226,0.00011333134,0.000108127475,0.2427864,0.007864508,0.024966972,0.6825506,0.0010889791],"about_ca_topic_score_codex":0.000036521997,"about_ca_topic_score_gemma":0.000003793022,"teacher_disagreement_score":0.8520549,"about_ca_system_score_codex":0.00011585998,"about_ca_system_score_gemma":0.00015866429,"threshold_uncertainty_score":0.9999745},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.265947,0.000027429645,0.7161825,0.0005321881,0.00094960403,0.000092483024,0.0000014091266,0.00019939097,0.016068028],"genre_scores_gemma":[0.6662788,0.0000051747716,0.33275223,0.00013422294,0.00008768206,0.0000045741763,0.0000016300191,0.0000036586043,0.0007320563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994271,0.000007763179,0.00009805875,0.00019916845,0.00011713184,0.0001508061],"domain_scores_gemma":[0.9994922,0.00003242968,0.00002120492,0.0003920844,0.000014214358,0.00004786258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012964512,0.000056318193,0.00006210044,0.000053649943,0.000039861574,0.0001349925,0.00067576516,0.00003642082,0.000081447775],"category_scores_gemma":[0.000008505771,0.00004303201,0.000013385713,0.00015463497,0.0000099483705,0.0006485104,0.00039891244,0.00015241765,0.00006507043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006011463,0.00026894858,0.025008969,0.000023482462,0.000008020964,0.00007341205,0.00059188355,0.00033796683,0.032895923,0.3827369,0.0053154808,0.552733],"study_design_scores_gemma":[0.00077582273,0.00004824313,0.0874271,0.0000370116,0.0000013343604,0.000024075565,0.000042481377,0.8212479,0.015733417,0.008840092,0.065374725,0.000447815],"about_ca_topic_score_codex":0.00020802882,"about_ca_topic_score_gemma":0.0001073933,"teacher_disagreement_score":0.8209099,"about_ca_system_score_codex":0.000004470507,"about_ca_system_score_gemma":0.000016126613,"threshold_uncertainty_score":0.17547944},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028597996,0.00008479081,0.9652971,0.00004937545,0.00006306979,0.000110617555,7.4850516e-7,0.00014880349,0.005647488],"genre_scores_gemma":[0.66643643,3.0441407e-7,0.33295074,0.000012005068,0.000078758945,0.0000036914753,0.0000028499826,0.0000031277382,0.00051208254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929714,0.000020000412,0.00012380474,0.00022182624,0.00015636608,0.00018083342],"domain_scores_gemma":[0.99960595,0.000007202555,0.00004220299,0.00028315856,0.000030592208,0.00003086563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090957816,0.000074737014,0.000065806074,0.000043438664,0.00013236496,0.00014684835,0.00031028135,0.000035015477,0.000017746212],"category_scores_gemma":[0.0000022271588,0.000059161455,0.000022861197,0.00015823414,0.000012981644,0.00076954416,0.00014991008,0.000052687305,0.000028625967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030760048,0.000053499414,0.00026000018,0.0000055623464,0.000002484566,0.000009456524,0.0000105034305,0.009303422,0.02034498,0.9587309,0.0007554281,0.0105206845],"study_design_scores_gemma":[0.00013797417,0.000027958977,0.002057182,0.000018279137,0.0000010885446,0.000009902698,0.000006759841,0.9446712,0.001375323,0.051161163,0.00041316732,0.00011998642],"about_ca_topic_score_codex":0.001206024,"about_ca_topic_score_gemma":0.000020565736,"teacher_disagreement_score":0.9353678,"about_ca_system_score_codex":0.000044298562,"about_ca_system_score_gemma":0.000041012787,"threshold_uncertainty_score":0.2412534},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043574325,0.000033677596,0.99158627,0.0008389367,0.000036388483,0.00020030636,0.000003455422,0.00019632184,0.0027471867],"genre_scores_gemma":[0.32949865,0.0000013271701,0.66866493,0.0006200574,0.0000669599,0.00001174805,0.000016506088,0.0000053436574,0.0011144569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904794,0.000007945077,0.00013105279,0.00034003457,0.00019139427,0.00028161803],"domain_scores_gemma":[0.99943644,0.000023288345,0.000054205433,0.00033933847,0.000054353888,0.00009237598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007535529,0.0001273657,0.00012179667,0.00004987945,0.00014840644,0.00019677947,0.00053524645,0.000029673973,0.00001669376],"category_scores_gemma":[0.0000042080346,0.00007665083,0.000032524993,0.00015183195,0.000021259031,0.0005210855,0.000075697775,0.000066662345,0.000011966893],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023127608,0.000050938816,0.00006434562,0.0000067922674,0.000003176727,0.000006981431,0.0001543736,0.0003458562,0.00013023466,0.0041454635,0.0016361778,0.9934325],"study_design_scores_gemma":[0.0017180794,0.0018552459,0.0054235114,0.00008564828,0.000011837677,0.00018936482,0.00005576648,0.9509217,0.0024615931,0.010228328,0.026418354,0.00063055754],"about_ca_topic_score_codex":0.000014180138,"about_ca_topic_score_gemma":0.0000061332253,"teacher_disagreement_score":0.99280196,"about_ca_system_score_codex":0.000010443595,"about_ca_system_score_gemma":0.00007523298,"threshold_uncertainty_score":0.31257302},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019346434,0.000023947883,0.91779876,0.00019950795,0.00011556008,0.00012438331,0.0000013355423,0.000022834449,0.08152021],"genre_scores_gemma":[0.15600689,0.00017528493,0.6264406,0.0002689306,0.00016068917,0.00008234249,0.000010015156,0.000014235889,0.21684104],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999512,0.000073134455,0.00010762135,0.00015603694,0.00007105824,0.000080111044],"domain_scores_gemma":[0.9995188,0.00014624208,0.000047728572,0.0002073314,0.000039322666,0.000040590865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022153118,0.000047977133,0.00011210203,0.000027451353,0.0007555822,0.0003533155,0.00036838074,0.00003208875,0.000060112092],"category_scores_gemma":[0.00007243596,0.00004095336,0.000018866045,0.00028025737,0.000018639565,0.00027348433,0.00048714888,0.00009112965,0.0000022325503],"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":[0.00026140286,0.00037604975,0.0008956156,0.00005293463,0.00010737188,0.0000061347755,0.0013346954,0.010461195,0.00035947017,0.018760428,0.71031195,0.25707275],"study_design_scores_gemma":[0.0015220887,0.00017513294,0.00033668402,0.000025054609,0.000005877756,0.000012344738,0.000024652678,0.8258208,0.0001548541,0.0030365083,0.16877936,0.000106660256],"about_ca_topic_score_codex":0.0011710442,"about_ca_topic_score_gemma":0.00006359443,"teacher_disagreement_score":0.8153596,"about_ca_system_score_codex":0.000004198437,"about_ca_system_score_gemma":0.000025757143,"threshold_uncertainty_score":0.58114034},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08601868,0.0000055281043,0.90986675,0.00022303003,0.00019211783,0.000118961754,9.805682e-7,0.00007411119,0.0034998318],"genre_scores_gemma":[0.52975553,0.0000016746355,0.46968025,0.00036181862,0.000041480827,9.486531e-7,0.0000064834035,0.0000026815646,0.00014913686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915105,0.000026387735,0.00026330652,0.00013018335,0.00022818283,0.00020086001],"domain_scores_gemma":[0.999422,0.000078952326,0.00004683489,0.0003109207,0.00004888873,0.00009239372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009237607,0.00006643609,0.00006681436,0.00029185944,0.00010561749,0.00011352822,0.00032210065,0.00005103921,0.000014651167],"category_scores_gemma":[0.000116614836,0.00005980467,0.000015377556,0.0008210701,0.0000062463655,0.0022284042,0.00025834498,0.00013346226,0.00007096407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016226788,0.00013982321,0.02217546,0.000026077309,0.000008825073,0.000035481316,0.009778858,0.004124174,0.0014808454,0.1708797,0.0047740918,0.7864144],"study_design_scores_gemma":[0.00052307826,0.000045544206,0.12729956,0.00007436931,0.0000016038204,0.000012512211,0.00050851755,0.85485756,0.0014163066,0.0016281527,0.013300249,0.00033255704],"about_ca_topic_score_codex":0.00007322064,"about_ca_topic_score_gemma":0.00003666755,"teacher_disagreement_score":0.8507334,"about_ca_system_score_codex":0.00008196297,"about_ca_system_score_gemma":0.0000310788,"threshold_uncertainty_score":0.24387638},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13884267,0.000027932461,0.8582243,0.00017623673,0.0005808841,0.00012937112,0.0000017545262,0.00008068712,0.0019361879],"genre_scores_gemma":[0.1714498,0.000008414371,0.8279021,0.000294962,0.00010498732,0.0000032700002,0.0000019449424,0.00000796808,0.00022660286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986512,0.000020098241,0.00034525894,0.00042459107,0.00020430403,0.00035451335],"domain_scores_gemma":[0.99928784,0.00004469132,0.00007981103,0.0003742744,0.000050686445,0.00016271445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004097196,0.00012820635,0.00014385024,0.00028562752,0.00022379236,0.00016360127,0.0003196267,0.000065362605,0.000006077617],"category_scores_gemma":[0.0000392543,0.00011834067,0.000022653818,0.0005987436,0.00003510915,0.0009640374,0.000440511,0.00013828957,0.000004874473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017125614,0.00006789883,0.0050089173,0.000020558402,0.000013666786,0.000047296704,0.0017370519,0.0038906387,0.0039182925,0.037102517,0.0006750962,0.94750094],"study_design_scores_gemma":[0.0021691604,0.0001369188,0.037834235,0.00019403019,0.000008940706,0.0006127005,0.0016192325,0.9175687,0.0037251026,0.014629793,0.020500172,0.0010010027],"about_ca_topic_score_codex":0.0013848161,"about_ca_topic_score_gemma":0.00027532582,"teacher_disagreement_score":0.94649994,"about_ca_system_score_codex":0.000070609276,"about_ca_system_score_gemma":0.000041092804,"threshold_uncertainty_score":0.48257923},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082044065,0.000013391426,0.91280675,0.00035568984,0.00035723782,0.00058070023,0.00017435772,0.000113834954,0.0035539933],"genre_scores_gemma":[0.878779,0.000022219854,0.11834676,0.0019530455,0.00013436846,0.00012888972,0.00055708067,0.000021503334,0.00005713933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799573,0.00006473598,0.00071549974,0.00024560193,0.00045823958,0.0005201844],"domain_scores_gemma":[0.99844396,0.00019867296,0.00025804454,0.0008922475,0.000114945884,0.00009214397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010506542,0.00024886965,0.00025558274,0.00019149962,0.00028004934,0.00048006137,0.0015405177,0.00013906966,0.0000060763455],"category_scores_gemma":[0.000086664404,0.00017555249,0.00011685928,0.00029365582,0.000046822828,0.0021294313,0.00039585918,0.00034487218,0.0000925283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011133934,0.0011834842,0.0027001763,0.0006208324,0.0000958379,0.000014535079,0.04555436,0.008683174,0.00013455508,0.06172781,0.011591157,0.86758274],"study_design_scores_gemma":[0.0012036557,0.000112960704,0.0005391553,0.00011633106,0.000007761147,0.00003245866,0.00037421993,0.97857076,0.000106606494,0.009073228,0.0095885545,0.00027432258],"about_ca_topic_score_codex":0.00002115912,"about_ca_topic_score_gemma":0.000016736598,"teacher_disagreement_score":0.96988755,"about_ca_system_score_codex":0.00004939673,"about_ca_system_score_gemma":0.000037645743,"threshold_uncertainty_score":0.71588224},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012862073,0.0005702547,0.9942523,0.0004278544,0.002412896,0.0006429335,0.000037474147,0.00029020917,0.0013531832],"genre_scores_gemma":[0.0008865935,0.000037913676,0.9951976,0.0015091154,0.0013535235,0.000013739183,0.0000675019,0.000059418493,0.0008745913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949394,0.000023554165,0.0007108658,0.0021061287,0.0011376976,0.0010823448],"domain_scores_gemma":[0.99694115,0.00048036664,0.00040491065,0.0016443442,0.0001987516,0.0003304967],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007254051,0.00075167295,0.00067954615,0.00075801194,0.0003452268,0.0011837003,0.0046439436,0.00040431242,0.0000092033215],"category_scores_gemma":[0.000023831655,0.0006855027,0.00023670663,0.00041647244,0.00020330452,0.0011700478,0.0022610978,0.00082821917,0.000027614731],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023692248,0.000016775099,0.000002343122,0.000020802036,0.000012821952,0.0000563547,0.00026636157,0.023862965,0.000105563515,0.0028191158,0.00051783246,0.9723167],"study_design_scores_gemma":[0.0005166701,0.00011413312,0.000025122541,0.0004316219,0.000012462904,0.000052712316,1.5488065e-7,0.88263667,0.0007118782,0.09403626,0.020577013,0.0008852812],"about_ca_topic_score_codex":0.00017493975,"about_ca_topic_score_gemma":0.000058494083,"teacher_disagreement_score":0.97143143,"about_ca_system_score_codex":0.00033725862,"about_ca_system_score_gemma":0.00061719667,"threshold_uncertainty_score":0.9998532},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011153735,0.00014963848,0.9917362,0.0011314237,0.0010440001,0.00044212164,0.00022250309,0.00038414504,0.0037746283],"genre_scores_gemma":[0.9556133,0.000027900633,0.04231541,0.0008385159,0.0001890819,0.000011541323,0.00021264661,0.00003161749,0.00075995486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664086,0.0001319936,0.00038154016,0.0011599668,0.0011280751,0.00055753853],"domain_scores_gemma":[0.99673504,0.0001290648,0.00010701866,0.00263015,0.0000927403,0.0003059971],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039155892,0.00034569454,0.0003299401,0.00019714874,0.0003758707,0.0003074967,0.0033060415,0.00013534984,0.0005046251],"category_scores_gemma":[0.000013060173,0.0002692342,0.00011907078,0.00035091818,0.00010031926,0.0005661478,0.0009915199,0.00032384813,0.00022721881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011076224,0.0019616568,0.000036543763,0.00004431896,0.000075128744,0.00043622413,0.00042503397,0.03431734,0.0005896393,0.010128961,0.022204528,0.92966986],"study_design_scores_gemma":[0.0020017223,0.00021779408,0.00004535453,0.00007447373,0.000018345301,0.0000181231,0.000050936596,0.9746976,0.0008784623,0.000057008892,0.021569239,0.00037094724],"about_ca_topic_score_codex":0.0003921467,"about_ca_topic_score_gemma":0.000034910303,"teacher_disagreement_score":0.95449793,"about_ca_system_score_codex":0.00010778548,"about_ca_system_score_gemma":0.000055908688,"threshold_uncertainty_score":0.999976},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004681034,0.00010428444,0.9299994,0.00059843017,0.0001695391,0.000007585639,0.0000010544344,0.00013617313,0.06893672],"genre_scores_gemma":[0.49457964,0.00018243886,0.47830343,0.0030456886,0.00028594397,0.0000073631427,0.0000030734634,0.000010099092,0.023582328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995741,0.000008582126,0.000059072427,0.00014287986,0.00010901785,0.00010633159],"domain_scores_gemma":[0.999395,0.000020721156,0.000013775037,0.0005141981,0.000012382804,0.000043930657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000029571655,0.00004134987,0.00004096423,0.00002538739,0.000063344676,0.00007766799,0.0007146267,0.00001698714,0.00036037492],"category_scores_gemma":[0.000007544552,0.000031158088,0.000015975482,0.00009797331,0.00000688173,0.00035054926,0.00044026235,0.000024597835,0.00006307957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2310925e-7,0.000020058475,0.000017484368,6.7029237e-7,0.0000016630041,0.000008457502,0.000041273433,0.0000054552593,0.00022144307,0.58324087,0.20856865,0.20787387],"study_design_scores_gemma":[0.0001290368,0.000015681504,0.00008112727,0.0000043237073,4.4434697e-7,0.000008587447,0.0000025123975,0.76678026,0.0015623965,0.006336642,0.22499548,0.00008351363],"about_ca_topic_score_codex":0.000049530587,"about_ca_topic_score_gemma":0.0000035233045,"teacher_disagreement_score":0.7667748,"about_ca_system_score_codex":0.00000537389,"about_ca_system_score_gemma":0.0000018649022,"threshold_uncertainty_score":0.39458528},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05879055,0.000016899829,0.9382022,0.000007768779,0.00045923638,0.000074187534,5.7595815e-7,0.0002795723,0.002169011],"genre_scores_gemma":[0.6407374,4.559157e-7,0.35899282,0.00009587451,0.000036626956,0.0000022542538,3.171737e-7,0.000005494308,0.00012876064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925816,0.000021344118,0.00014275585,0.0002477868,0.00014830327,0.00018162392],"domain_scores_gemma":[0.9993808,0.000015292837,0.000068391455,0.00044358903,0.00003159581,0.000060313683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011508802,0.000088517554,0.00008060217,0.000060926726,0.00014032837,0.00009644493,0.00040314614,0.000041826384,0.00011910018],"category_scores_gemma":[0.000015142651,0.00006988254,0.000035359022,0.00015305814,0.000013551401,0.0011716675,0.00035495198,0.0000667761,0.00005654679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000455482,0.00009442347,0.00024232618,0.000028500845,0.000013191877,0.000017189786,0.000796615,0.000033501627,0.040183492,0.0043228734,0.0002169228,0.9540464],"study_design_scores_gemma":[0.00011288646,0.000037185793,0.0024561367,0.000009504103,0.0000037572458,0.00001933159,0.000016941507,0.9750023,0.021197127,0.0007982677,0.00023030447,0.00011624471],"about_ca_topic_score_codex":0.0008026139,"about_ca_topic_score_gemma":0.000019227471,"teacher_disagreement_score":0.9749688,"about_ca_system_score_codex":0.000035361543,"about_ca_system_score_gemma":0.000028886057,"threshold_uncertainty_score":0.2849727},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028890254,0.00008421274,0.96910846,0.00026970022,0.000047317786,0.0000454294,0.0000033798797,0.00008509633,0.0014661205],"genre_scores_gemma":[0.82259107,0.000016024158,0.17595835,0.000075613134,0.00003401197,0.0000024062062,0.0000059305066,0.000004083836,0.0013125065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933493,0.000024468245,0.000116407544,0.00017397676,0.00023497017,0.000115264935],"domain_scores_gemma":[0.99953234,0.000054475553,0.00006750473,0.00025601307,0.00005116152,0.00003851313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000071347,0.00006084208,0.0000753722,0.000053187676,0.00009215369,0.00003626016,0.00026712177,0.000021745449,0.00010343504],"category_scores_gemma":[0.0000062999347,0.000042939875,0.000012014387,0.0001657634,0.000034061097,0.00043423517,0.00013250821,0.000045603596,0.000017504795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081084836,0.00076887646,0.008337027,0.00012585259,0.00010469585,0.00006501796,0.007202549,0.033774838,0.0074611134,0.4771098,0.07649973,0.38846943],"study_design_scores_gemma":[0.00038043037,0.00018795536,0.0050387355,0.000044094475,0.0000041080552,0.000019581928,0.00008738089,0.9834602,0.0026616591,0.0005725915,0.00739704,0.00014626222],"about_ca_topic_score_codex":0.0001595693,"about_ca_topic_score_gemma":0.0000054748716,"teacher_disagreement_score":0.94968534,"about_ca_system_score_codex":0.000010216837,"about_ca_system_score_gemma":0.000008723278,"threshold_uncertainty_score":0.17510372},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031869877,0.00057511247,0.96697664,0.00023197557,0.0002668297,0.000058111378,0.0000065797735,0.000009849997,0.0000050526073],"genre_scores_gemma":[0.8217993,0.000020578775,0.17787234,0.00007102598,0.00021818191,0.0000011565459,0.000004152056,0.00000564037,0.000007626664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994362,0.000010397349,0.0001889604,0.00010183975,0.000094652096,0.0001679486],"domain_scores_gemma":[0.99928755,0.00010925503,0.00007957166,0.00008697863,0.00018131257,0.00025535646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007247683,0.00008204709,0.00016937063,0.00020429435,0.00011670986,0.00005013537,0.00025444548,0.00004932023,0.0000010047872],"category_scores_gemma":[0.000032883938,0.000072459734,0.000058890626,0.00023729695,0.000014298169,0.00028342186,0.000020996675,0.00015088989,1.1957862e-7],"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":[0.000061648905,0.00024866365,0.015112179,0.00036969883,0.0004741094,0.00068646,0.004260311,0.40656856,0.0028917752,0.084156975,0.084028676,0.40114093],"study_design_scores_gemma":[0.00028241336,0.00022228996,0.020035615,0.00003598554,0.000006322298,0.00027242507,8.859412e-7,0.9719753,0.00040302792,0.00020037021,0.0064624334,0.00010288639],"about_ca_topic_score_codex":0.00006395259,"about_ca_topic_score_gemma":0.000025140604,"teacher_disagreement_score":0.78992945,"about_ca_system_score_codex":0.000033512857,"about_ca_system_score_gemma":0.00023308792,"threshold_uncertainty_score":0.29548222},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23408864,0.000026533009,0.7655149,0.000030597494,0.00007786531,0.000090130176,0.000011403221,0.00007323036,0.00008669682],"genre_scores_gemma":[0.4900183,0.00001919219,0.5093473,0.00008602943,0.00008477749,0.000012680414,0.000018555476,0.0000065960494,0.00040656468],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938214,0.000019851097,0.000116899835,0.00022173238,0.000117150084,0.00014225663],"domain_scores_gemma":[0.9996054,0.00003903721,0.000029706742,0.00026882725,0.000024162038,0.000032863845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009697231,0.000071521914,0.00009449976,0.00006722019,0.00020391528,0.000050813127,0.00026660954,0.00002059535,0.000020177986],"category_scores_gemma":[0.000023113987,0.000058727128,0.000023725626,0.0001574832,0.000033708417,0.0012100519,0.00020508836,0.000038567054,0.000008306925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066386047,0.0019671842,0.06083273,0.00017644207,0.00007593668,0.00031639118,0.0060711154,0.0054209433,0.46859786,0.023163652,0.014005825,0.41870806],"study_design_scores_gemma":[0.00047538787,0.00011642597,0.014180645,0.00002500443,0.0000024126816,0.00011543919,0.000026740336,0.9183828,0.056503702,0.00027074927,0.009671303,0.00022939574],"about_ca_topic_score_codex":0.00040440453,"about_ca_topic_score_gemma":0.00019260691,"teacher_disagreement_score":0.91296184,"about_ca_system_score_codex":0.000022699778,"about_ca_system_score_gemma":0.0000330912,"threshold_uncertainty_score":0.23948228},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004856716,0.00007956601,0.99289113,0.00024932311,0.0010339529,0.00015392817,0.0000031693992,0.00018114198,0.00055106555],"genre_scores_gemma":[0.17679387,0.0000014561756,0.82271993,0.00028595972,0.00017326756,0.000007845536,0.0000020067637,0.000007921478,0.0000077224195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997008,0.00006444636,0.00039264475,0.0007703988,0.0012201639,0.000544294],"domain_scores_gemma":[0.99831265,0.000110554705,0.000091867085,0.00096971483,0.00013782839,0.00037735308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000995373,0.00021868502,0.00025990797,0.00026310314,0.00024048552,0.00062672,0.0027338685,0.000057211844,0.00001741854],"category_scores_gemma":[0.00006962836,0.0001690851,0.000051977047,0.0011092857,0.00034088257,0.001505357,0.001933041,0.00025330877,0.00005313087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002156722,0.00011577166,0.0001565661,0.000022378656,0.000004648291,0.00013089542,0.002117671,0.008667381,0.00013556905,0.2085874,0.00045422418,0.7796053],"study_design_scores_gemma":[0.00018522466,0.000024562758,0.0008580757,0.000027254204,9.2473726e-7,0.00015576597,0.000014160002,0.62185025,0.00011843488,0.3763693,0.00024415337,0.00015187488],"about_ca_topic_score_codex":0.000023328734,"about_ca_topic_score_gemma":6.442939e-7,"teacher_disagreement_score":0.77945346,"about_ca_system_score_codex":0.00015081775,"about_ca_system_score_gemma":0.00019650623,"threshold_uncertainty_score":0.6895091},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03897091,0.0001987523,0.94350743,0.010507637,0.0010701068,0.00029429817,0.00001627123,0.00013894502,0.00529567],"genre_scores_gemma":[0.8240703,0.0000202834,0.17318615,0.0008726891,0.0002487876,0.000009790894,0.0000066587636,0.00000793636,0.0015774426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929196,0.00003734064,0.0001771492,0.00018020936,0.00018376404,0.00012957962],"domain_scores_gemma":[0.99850374,0.00009281684,0.000096562864,0.001229853,0.000037940583,0.000039104132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008804439,0.00007571253,0.00008677624,0.000034001314,0.00006614744,0.00006662159,0.0020320313,0.00003117142,0.000069940135],"category_scores_gemma":[0.00008841026,0.00004821417,0.00006205435,0.00020477736,0.00003574298,0.00051174394,0.0010403144,0.00009569939,0.00009466536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025378408,0.00011015003,0.0011683345,0.00000512992,0.00001816598,0.0000011770875,0.00086534314,0.00008606096,0.0026465498,0.01831538,0.053025313,0.9237559],"study_design_scores_gemma":[0.00058612553,0.00007621153,0.01573877,0.000063822416,0.0000121804405,0.00002374625,0.000041093183,0.14683181,0.024490727,0.008315963,0.80354667,0.00027286526],"about_ca_topic_score_codex":0.00016993382,"about_ca_topic_score_gemma":0.000046243586,"teacher_disagreement_score":0.923483,"about_ca_system_score_codex":0.000022427052,"about_ca_system_score_gemma":0.000047408143,"threshold_uncertainty_score":0.37760535},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009440193,0.00010939786,0.99537796,0.0001272694,0.0021541566,0.0002689719,0.0000071134896,0.00009959121,0.0017611636],"genre_scores_gemma":[0.40470484,0.000031304302,0.59261215,0.0010786746,0.0006676456,0.000010691866,0.00001456002,0.000060427865,0.00081973005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644446,0.000033902827,0.00053744,0.0013057126,0.0011549173,0.0005235685],"domain_scores_gemma":[0.9974045,0.00032048594,0.00040883853,0.0015292238,0.00019625745,0.00014068757],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000816351,0.00044452937,0.00055888173,0.00070366164,0.00019658492,0.00031828237,0.0035182603,0.00026507594,0.000013816645],"category_scores_gemma":[0.000068499976,0.0003754022,0.000110422996,0.00041260297,0.0003589895,0.00047548368,0.0019292678,0.00074576674,0.000018494908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000700272,0.00003107545,0.000026292013,0.000096902484,0.000009638137,0.00002616068,0.00045592658,0.17434412,0.00010647203,0.11442549,0.000054443102,0.7104165],"study_design_scores_gemma":[0.00029578255,0.00024007527,0.0000941822,0.0014148213,0.000003782873,0.000023965436,4.711104e-8,0.8445582,0.0010245827,0.15017566,0.0016480532,0.00052086654],"about_ca_topic_score_codex":0.000028083978,"about_ca_topic_score_gemma":0.000011914927,"teacher_disagreement_score":0.7098956,"about_ca_system_score_codex":0.00015101348,"about_ca_system_score_gemma":0.00029558633,"threshold_uncertainty_score":0.99986976},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15613037,0.0009661766,0.8400698,0.00014954344,0.00079319876,0.00010841396,0.0000099676645,0.000022244374,0.0017502998],"genre_scores_gemma":[0.780368,0.00004551454,0.2194328,0.000027041959,0.00008989586,0.0000011538525,8.1952743e-7,0.0000087916715,0.00002600533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983185,0.0000803538,0.0007035941,0.00017892629,0.00046851014,0.00025010953],"domain_scores_gemma":[0.9987167,0.00006234262,0.0005751201,0.00035658383,0.00016905977,0.00012016917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006944629,0.00014035155,0.00035640807,0.00034181605,0.000042305106,0.000032913737,0.0009816714,0.00006165831,0.00002706053],"category_scores_gemma":[0.000050881852,0.00010246583,0.00012717058,0.00047837684,0.00005423598,0.00033780208,0.00028354785,0.00023533683,0.0000030429737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044807888,0.002448642,0.014726016,0.00014014343,0.00037734018,0.0014095791,0.04386279,0.014175649,0.011159198,0.020520063,0.0013196314,0.8894129],"study_design_scores_gemma":[0.002811808,0.0013142979,0.07083212,0.0006004871,0.00003062523,0.00028133637,0.0009958588,0.911282,0.007735305,0.0029045164,0.0007605631,0.00045109022],"about_ca_topic_score_codex":0.000086218584,"about_ca_topic_score_gemma":0.00000631754,"teacher_disagreement_score":0.89710635,"about_ca_system_score_codex":0.000030752395,"about_ca_system_score_gemma":0.00009614366,"threshold_uncertainty_score":0.41784352},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028797719,0.000013505078,0.99585444,0.00026982217,0.00013103474,0.00024378175,0.000103500504,0.00008502563,0.00041915048],"genre_scores_gemma":[0.97167504,0.000014300711,0.027726375,0.00041230803,0.00001609823,0.00004631322,0.000014207225,0.0000048567267,0.0000904809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922717,0.000057076122,0.00025008302,0.00008605673,0.00023637578,0.00014322586],"domain_scores_gemma":[0.9986823,0.00054317625,0.00017397518,0.0003768887,0.00018088022,0.000042768297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052441354,0.00009880756,0.00009443491,0.00009974446,0.000441997,0.000116526295,0.00037961575,0.00004144133,0.00001043052],"category_scores_gemma":[0.000005574639,0.00006339198,0.00005468705,0.00018903527,0.00011537482,0.0017067622,0.0000021997696,0.00009103943,0.000012115561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005907377,0.00010664884,0.0000065436634,0.0000417844,0.000054744443,1.1462095e-7,0.0016725741,0.15180507,0.000049074886,0.08352174,0.0002979883,0.761853],"study_design_scores_gemma":[0.003115091,0.0007467738,0.00021639004,0.000108833214,0.000052564843,0.00000611289,0.0012863667,0.7880044,0.052941173,0.0050900816,0.14802903,0.00040319312],"about_ca_topic_score_codex":0.000016750128,"about_ca_topic_score_gemma":0.00002418235,"teacher_disagreement_score":0.9687953,"about_ca_system_score_codex":0.000035544246,"about_ca_system_score_gemma":0.00009777715,"threshold_uncertainty_score":0.33995283},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078206565,0.00023829001,0.98588324,0.0012111908,0.0011719503,0.0002608766,0.000025347425,0.00005376555,0.003334715],"genre_scores_gemma":[0.2873559,0.00011717949,0.7105303,0.0004708251,0.0010030984,0.000011316,0.0000036957845,0.000036201287,0.00047148054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775386,0.00011592895,0.000687337,0.00036482947,0.00069258944,0.00038546644],"domain_scores_gemma":[0.99797004,0.000086376414,0.00051084545,0.0006293756,0.00036790365,0.00043545137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056438986,0.00024450486,0.00040052668,0.0002680714,0.0001037379,0.00016445339,0.0019010643,0.00006987717,0.000067234694],"category_scores_gemma":[0.0001629575,0.00017382276,0.00019565206,0.00044562065,0.00010994939,0.0012767718,0.0005587105,0.00031743557,0.00006653698],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007640028,0.0022876945,0.0015796563,0.00014104515,0.0010036862,0.003373124,0.05082411,0.0034355111,0.0025436338,0.071927056,0.08299784,0.77912265],"study_design_scores_gemma":[0.007659576,0.013949709,0.059772816,0.0022167163,0.00033825828,0.002235205,0.0020230394,0.580593,0.020482235,0.22463451,0.08247928,0.0036156552],"about_ca_topic_score_codex":0.00009357937,"about_ca_topic_score_gemma":0.00001085241,"teacher_disagreement_score":0.775507,"about_ca_system_score_codex":0.00007704072,"about_ca_system_score_gemma":0.000120411256,"threshold_uncertainty_score":0.7088286},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045698293,0.000003631576,0.9512501,0.00031993614,0.0001936716,0.0002908971,3.4089754e-7,0.00027995184,0.0019631756],"genre_scores_gemma":[0.6500884,3.7533454e-7,0.34962955,0.00020269664,0.00005044396,0.00001645581,4.265346e-7,0.0000054908046,0.0000061299484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977041,0.000057384616,0.00021716316,0.0007224564,0.0007552378,0.00054365984],"domain_scores_gemma":[0.99876994,0.00014962206,0.00008425176,0.00057764567,0.00018042413,0.00023811968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000676477,0.00017742021,0.00015418259,0.00016301926,0.00057128206,0.0009433327,0.0016014611,0.00003642222,0.000039849263],"category_scores_gemma":[0.000039407732,0.000116379226,0.000025965068,0.001052827,0.0007914348,0.0014780487,0.00066956424,0.00023575114,0.00012657889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024213039,0.000042975636,0.00004629949,0.000005763417,0.000002104451,0.0000013680368,0.00019676321,0.002527428,0.00043117703,0.92164165,0.00005335275,0.07504869],"study_design_scores_gemma":[0.00017465987,0.00039576401,0.0004919685,0.0000691226,0.0000013766222,0.000024791407,0.000005525097,0.89257455,0.0018448664,0.10421051,0.000022571363,0.00018430693],"about_ca_topic_score_codex":0.00001299001,"about_ca_topic_score_gemma":2.6915066e-7,"teacher_disagreement_score":0.89004713,"about_ca_system_score_codex":0.00006256106,"about_ca_system_score_gemma":0.000072927374,"threshold_uncertainty_score":0.90965784},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02115504,0.000019118095,0.9743749,0.00033959866,0.0007488115,0.00006875363,0.0000027669148,0.00010172044,0.0031892832],"genre_scores_gemma":[0.55615973,0.0000013415133,0.44370416,0.00006567616,0.00006212598,0.000001005679,6.4336825e-7,0.0000021917076,0.00000310988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982032,0.00006506768,0.00024010603,0.00045001102,0.00073293963,0.00030865418],"domain_scores_gemma":[0.99849564,0.00008132542,0.00008386807,0.00075557537,0.00029256867,0.00029102335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009359544,0.00011584133,0.00017439979,0.0001448397,0.0001340187,0.00017088608,0.0019045796,0.000036533944,0.000013744676],"category_scores_gemma":[0.000068454174,0.00008706248,0.000037250225,0.0008368757,0.0025347336,0.00086615596,0.001240137,0.00010311367,0.00003207966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004132524,0.000032956832,0.00004147678,0.0000017657142,0.0000012123028,0.0000029998967,0.00022348981,0.00007217574,0.00027301125,0.8651493,0.00010184084,0.13409561],"study_design_scores_gemma":[0.00027737377,0.00028417757,0.0006156827,0.000024792034,0.000002286314,0.00007273489,0.000019975734,0.78312993,0.009332851,0.20579834,0.00029032832,0.00015150022],"about_ca_topic_score_codex":0.0000062522818,"about_ca_topic_score_gemma":2.5278484e-7,"teacher_disagreement_score":0.7830578,"about_ca_system_score_codex":0.000031999207,"about_ca_system_score_gemma":0.00017350327,"threshold_uncertainty_score":0.9339332},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08495747,0.000023302538,0.8686777,0.00057381706,0.0001939427,0.00013597572,0.0000033542312,0.000089658424,0.045344822],"genre_scores_gemma":[0.967197,0.0000023279217,0.032507114,0.00020081122,0.0000060915345,0.0000024934973,0.0000011348159,0.0000027226436,0.00008027545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993322,0.0000629093,0.00013181356,0.00015553996,0.00018431437,0.00013322114],"domain_scores_gemma":[0.9991938,0.00013626672,0.00006425811,0.0005517124,0.000022322925,0.000031648946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030721433,0.00006903695,0.00009726759,0.000028272194,0.00012548048,0.000052334857,0.00061357743,0.000019342371,0.00006683445],"category_scores_gemma":[0.000027045544,0.000038787704,0.000031337557,0.00017580364,0.0000868771,0.00015622986,0.00016402743,0.00008152681,0.000017415978],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010583857,0.00002910791,0.00012092501,0.000002763958,0.0000021347994,6.775855e-7,0.00005302613,0.000016249673,0.00028251344,0.99723566,0.0010114143,0.0012444475],"study_design_scores_gemma":[0.0005260395,0.00015512215,0.004965642,0.000080850594,0.0000045490715,0.000018048342,0.00013238734,0.29723695,0.11046906,0.5797858,0.0062959795,0.00032957288],"about_ca_topic_score_codex":0.000047458474,"about_ca_topic_score_gemma":0.0000030307904,"teacher_disagreement_score":0.8822396,"about_ca_system_score_codex":0.00000933888,"about_ca_system_score_gemma":0.000010045074,"threshold_uncertainty_score":0.15817167},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022651682,0.0003466586,0.9714319,0.0016763369,0.00023730239,0.00020255537,8.284534e-7,0.00007115759,0.0033815904],"genre_scores_gemma":[0.33943108,0.000017026769,0.6600424,0.00010836831,0.00004882652,0.0000127373205,0.0000017251867,0.00000782965,0.0003299949],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977383,0.00049729913,0.00028334305,0.0003975862,0.0007606505,0.00032281782],"domain_scores_gemma":[0.99778885,0.00054416934,0.000074877295,0.00127073,0.00023162524,0.00008972527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002568498,0.000113756236,0.00017476061,0.00013292622,0.00036929437,0.00014126935,0.0023182426,0.000071023926,0.00006850523],"category_scores_gemma":[0.0000756036,0.000060897484,0.000059337228,0.0006249467,0.00022214898,0.00041586685,0.0016311301,0.00028650317,0.000038291288],"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":[0.000035128265,0.0007840737,0.00023329537,0.00006576313,0.000032353135,0.000018304701,0.024503741,0.002061725,0.10989676,0.3897898,0.006298704,0.46628037],"study_design_scores_gemma":[0.0018291436,0.00045287466,0.0016896655,0.00031601757,0.000008985156,0.000017151338,0.0011713064,0.14287554,0.60558,0.21145943,0.03410357,0.0004963293],"about_ca_topic_score_codex":0.0012494745,"about_ca_topic_score_gemma":0.000021780716,"teacher_disagreement_score":0.49568325,"about_ca_system_score_codex":0.000043757755,"about_ca_system_score_gemma":0.00012547703,"threshold_uncertainty_score":0.43079102},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9135783,0.00009331731,0.00146429,0.019255336,0.010482975,0.0005164098,0.00002491101,0.00026555645,0.054318905],"genre_scores_gemma":[0.9957753,0.000023294735,0.0032241286,0.00023682887,0.0003365944,0.000011057028,0.000004719605,0.000012004445,0.00037610618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99794096,0.000020137493,0.0002880844,0.0003594581,0.0011910385,0.00020030318],"domain_scores_gemma":[0.9984881,0.00012073701,0.00015559288,0.00026457108,0.00090197846,0.00006900204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044289388,0.00012287244,0.00016040742,0.00006396863,0.00015932534,0.00033733208,0.0022353493,0.000060801354,0.00004808534],"category_scores_gemma":[0.00023418193,0.00009261622,0.00010344609,0.0004691929,0.000040576506,0.000498024,0.0016252376,0.00025711264,0.000019971581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023434517,0.0002982675,0.0016956324,0.000052736083,0.00006135218,0.0000044855683,0.00031369383,0.000040956143,0.08120106,0.90678316,0.004037677,0.005487527],"study_design_scores_gemma":[0.0019356137,0.00019908755,0.00526637,0.0008579569,0.000016979126,0.000056618584,0.00008797338,0.24941428,0.67703205,0.04922381,0.015516712,0.0003925308],"about_ca_topic_score_codex":0.000023113922,"about_ca_topic_score_gemma":1.2443311e-7,"teacher_disagreement_score":0.8575594,"about_ca_system_score_codex":0.00012262902,"about_ca_system_score_gemma":0.00008619636,"threshold_uncertainty_score":0.4153872},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019591023,0.000067311965,0.99659485,0.00018919546,0.00019172988,0.0007737221,0.000028061784,0.00015960124,0.0019759238],"genre_scores_gemma":[0.0015091919,0.000010705072,0.99785197,0.00011749108,0.0001099018,0.0002515001,0.000040129307,0.000018697707,0.000090405585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998943,0.000011011354,0.00023503689,0.00027430942,0.00031150147,0.00022519565],"domain_scores_gemma":[0.99867153,0.00026935976,0.0001507085,0.00066549896,0.00014608547,0.000096810116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003378282,0.00015931594,0.00017174003,0.00004226321,0.00020316427,0.00019255292,0.00076087425,0.00006255304,0.00000442742],"category_scores_gemma":[0.000036782876,0.000098249424,0.000054075055,0.00023355833,0.000044712036,0.00025614578,0.00031081281,0.00008701758,0.00002241244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021177335,0.0003011281,9.884433e-7,0.00006329181,0.00012878834,0.0000032013927,0.01097836,0.02086437,0.00015863676,0.5249125,0.009313594,0.43325397],"study_design_scores_gemma":[0.00060072105,0.0000323518,0.0000021328258,0.000011531242,0.000020060224,0.0000044591834,0.0006268573,0.96978337,0.000546529,0.026112394,0.0021092203,0.00015035066],"about_ca_topic_score_codex":0.00000671365,"about_ca_topic_score_gemma":7.5014094e-7,"teacher_disagreement_score":0.948919,"about_ca_system_score_codex":0.000038929917,"about_ca_system_score_gemma":0.00005883141,"threshold_uncertainty_score":0.40064952},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019498196,0.000642991,0.2697405,0.000050517952,0.00022019296,0.00042478414,0.00042210546,0.00028799532,0.7280159],"genre_scores_gemma":[0.0037128928,0.00018715931,0.106840275,0.0004340223,0.0002393891,0.000033239343,0.0002587898,0.00015611379,0.8881381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99759483,0.000032395747,0.00053680054,0.00088407326,0.0006158441,0.0003360347],"domain_scores_gemma":[0.99691385,0.00013996275,0.0005336744,0.0020073948,0.00022103322,0.0001841122],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019153052,0.00050180405,0.0008783944,0.0008765014,0.00010981052,0.00011763483,0.0014601885,0.00030356026,0.00037031915],"category_scores_gemma":[0.000006359059,0.00038906114,0.00035296142,0.00013803125,0.00015591041,0.00012926587,0.00054440845,0.00032237405,0.00006435657],"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":[0.000102451544,0.0001928231,0.0003920269,0.00026805868,0.006041303,0.0005472836,0.0012006583,0.0002901369,0.0001134433,0.67148525,0.009390561,0.30997598],"study_design_scores_gemma":[0.0013033841,0.0006733387,0.001227357,0.0009417286,0.0036946838,0.000039381983,0.00001437002,0.06449579,0.00086955755,0.0050316043,0.919228,0.0024808152],"about_ca_topic_score_codex":0.00012842736,"about_ca_topic_score_gemma":0.00015890448,"teacher_disagreement_score":0.9098374,"about_ca_system_score_codex":0.00003985349,"about_ca_system_score_gemma":0.00012262679,"threshold_uncertainty_score":0.9998561},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29276216,0.000050861196,0.70659757,0.00006552293,0.00012407626,0.00028807868,0.000006276474,0.000028589937,0.000076853394],"genre_scores_gemma":[0.19180812,0.000009579891,0.807977,0.00008540947,0.000014938775,3.395199e-7,0.0000073801803,0.0000043360424,0.00009288347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867886,0.00006600908,0.00012284535,0.00043960472,0.0005164911,0.00017621461],"domain_scores_gemma":[0.9982135,0.000038320122,0.000107433734,0.0014913881,0.00006630207,0.000082999686],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00046801634,0.000089579546,0.00017731934,0.00007054327,0.00041889353,0.000050008926,0.005656861,0.000029468583,0.000008523396],"category_scores_gemma":[0.0000116176225,0.00007450706,0.000043210646,0.00022622477,0.00012074711,0.0010273062,0.0023979265,0.000085281295,0.000001980943],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024504532,0.00005727537,0.00023733496,0.00006236826,0.000010001269,0.0000021977685,0.0013461377,0.00008100215,0.00044089646,0.007882968,0.00032998482,0.9895253],"study_design_scores_gemma":[0.0007385411,0.00016779314,0.06014027,0.00025185492,0.000021021928,0.0000058492074,0.00006478246,0.92834467,0.00019331202,0.00038116812,0.009502467,0.00018825385],"about_ca_topic_score_codex":0.00025463794,"about_ca_topic_score_gemma":0.0000040009863,"teacher_disagreement_score":0.9893371,"about_ca_system_score_codex":0.000039169874,"about_ca_system_score_gemma":0.000081202124,"threshold_uncertainty_score":0.999723},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018929955,0.00093714637,0.99250704,0.00034630476,0.00071184296,0.00031978014,0.00001720822,0.000099895915,0.0048714555],"genre_scores_gemma":[0.048995093,0.00029882358,0.94835365,0.0011528886,0.00038557214,0.000009167608,0.000010482201,0.000050984534,0.00074331206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996925,0.000040911247,0.00041412018,0.0014386539,0.0006201097,0.0005612117],"domain_scores_gemma":[0.9979881,0.00028882994,0.00019476039,0.0012188961,0.000116557276,0.00019284833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008362688,0.00044975392,0.00053832005,0.0006199886,0.00015676407,0.00026724796,0.0021415628,0.00030806437,0.000048519327],"category_scores_gemma":[0.00005244136,0.000386993,0.000059992897,0.0004067555,0.0007232598,0.0007152156,0.0023739226,0.0007827964,0.00007025985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032189244,0.000113132795,0.00049653876,0.00007228452,0.0000123756145,0.00093391736,0.0023612143,0.0014212646,0.00030975003,0.07278749,0.00012240728,0.9213374],"study_design_scores_gemma":[0.0008135464,0.00029832553,0.0007880066,0.0008856314,0.000007378598,0.00022781434,1.6096527e-7,0.7766647,0.0005841051,0.21386522,0.00466644,0.001198697],"about_ca_topic_score_codex":0.000116920586,"about_ca_topic_score_gemma":0.000075378885,"teacher_disagreement_score":0.9201387,"about_ca_system_score_codex":0.00012824243,"about_ca_system_score_gemma":0.00030655996,"threshold_uncertainty_score":0.9998582},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010498401,0.00006221985,0.9731924,0.00007370883,0.0018671761,0.001487266,0.0000206217,0.0003335422,0.021913256],"genre_scores_gemma":[0.20804317,0.0001048298,0.5961383,0.007959096,0.004500286,0.005056074,0.009501748,0.0006460106,0.16805045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789304,0.000016970154,0.00028915837,0.0008000611,0.00065217545,0.00034859145],"domain_scores_gemma":[0.9983644,0.000094850126,0.00018148516,0.0009773588,0.00018437886,0.00019753362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016835447,0.0003113086,0.00026563733,0.00024631392,0.00023559538,0.00030903768,0.0011417351,0.00021557054,0.000040685278],"category_scores_gemma":[0.000012718326,0.00023458351,0.000054031203,0.00042861767,0.000011453214,0.00051395874,0.00015197437,0.0003206289,0.00040455296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009794541,0.00032564937,0.0000045545494,0.00012905544,0.00003288349,0.000009138656,0.00035034795,0.00028753155,0.00065009325,0.8295952,0.012797354,0.15572025],"study_design_scores_gemma":[0.010414525,0.0076433695,0.004045085,0.0030399833,0.00025657524,0.000050576462,0.00054501474,0.13687097,0.02845734,0.25926253,0.54015785,0.009256185],"about_ca_topic_score_codex":0.00018392589,"about_ca_topic_score_gemma":0.000043032756,"teacher_disagreement_score":0.57033265,"about_ca_system_score_codex":0.000091307345,"about_ca_system_score_gemma":0.00019312403,"threshold_uncertainty_score":0.95660377},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043842487,0.00031402323,0.9492543,0.0059856274,0.0002824691,0.0002233948,0.000003879982,0.00003042161,0.00006345021],"genre_scores_gemma":[0.8316349,0.000028452065,0.16800594,0.00020061836,0.00007419182,0.000009486016,6.350183e-7,0.000004315254,0.000041498235],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989259,0.000014168334,0.00025550675,0.00029457544,0.00031055135,0.00019924651],"domain_scores_gemma":[0.99849457,0.000053453794,0.00021191343,0.0002442754,0.00070830324,0.00028746796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086630817,0.00008355831,0.00015765321,0.0006926351,0.0001694844,0.00013128448,0.0008582261,0.000081378486,0.000001245614],"category_scores_gemma":[0.0004790326,0.000062980056,0.000011426384,0.0012325632,0.00017306666,0.0011550174,0.00040592212,0.00015854431,0.0000035619123],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052870582,0.000050438593,0.0005974095,0.000012725705,0.000009900243,0.00002048421,0.002095647,0.0000901421,0.045734357,0.079227045,0.0060353214,0.86607367],"study_design_scores_gemma":[0.005455409,0.0041105384,0.0016063984,0.0007900643,0.0000467479,0.0051644263,0.004731482,0.31500322,0.15461096,0.33083928,0.17665483,0.0009866514],"about_ca_topic_score_codex":0.0000094507495,"about_ca_topic_score_gemma":0.0000027196984,"teacher_disagreement_score":0.86508703,"about_ca_system_score_codex":0.000044744163,"about_ca_system_score_gemma":0.00037756236,"threshold_uncertainty_score":0.2568252},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042867876,0.0022393633,0.9930294,0.0006371074,0.002591351,0.00068648753,0.00014254634,0.00011482506,0.00051604584],"genre_scores_gemma":[0.014756852,0.00012663328,0.98218316,0.00074444106,0.0018219113,0.000016930368,0.00013261712,0.00003815751,0.00017931554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953577,0.000047612582,0.00058305106,0.0021314675,0.00092282874,0.00095733633],"domain_scores_gemma":[0.994752,0.0007247175,0.0003247631,0.0037805403,0.00017994747,0.00023806473],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012059001,0.0006169632,0.0006810083,0.00065875705,0.0002543066,0.00042681192,0.007927997,0.0004483411,0.000019066512],"category_scores_gemma":[0.00017363322,0.0005291513,0.000102562095,0.00049135543,0.00044409113,0.0018589563,0.0048414925,0.0009206667,0.000015822987],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002457447,0.00006852217,0.00044038147,0.000142082,0.00001301775,0.000050465114,0.0006161326,0.005926707,0.00013537357,0.028878154,0.0005234705,0.96318114],"study_design_scores_gemma":[0.0006558091,0.00011074711,0.0009961152,0.00032939867,0.00001307267,0.000051179944,2.5351494e-7,0.8528366,0.0004004985,0.1207338,0.02286941,0.0010031183],"about_ca_topic_score_codex":0.00015883827,"about_ca_topic_score_gemma":0.00033137802,"teacher_disagreement_score":0.962178,"about_ca_system_score_codex":0.00020627446,"about_ca_system_score_gemma":0.0005216356,"threshold_uncertainty_score":0.999716},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066763065,0.0000046700466,0.9884107,0.00017909911,0.0037950098,0.0002697907,0.0000072913176,0.00023977245,0.00041736575],"genre_scores_gemma":[0.03563284,0.0000011955356,0.9619583,0.00029911913,0.00029326137,0.00005598566,0.000008460973,0.000009979869,0.0017408655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899054,0.000010101528,0.00016075419,0.00040060337,0.00016930705,0.0002686822],"domain_scores_gemma":[0.9990182,0.00017131283,0.00004396361,0.0005346621,0.000088955945,0.00014292849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019070297,0.000116363815,0.00011445152,0.00010283015,0.00016073814,0.00023640878,0.0005971273,0.000070503935,0.000031234045],"category_scores_gemma":[0.00008069273,0.000096263444,0.00005771316,0.00021760889,0.000011360865,0.00051572605,0.00033318982,0.00016789263,0.00006949052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022942713,0.000030860952,0.00006855535,0.0000018841247,0.0000042793095,0.0000012133473,0.000046420795,0.000021563137,0.00277093,0.0030973502,0.010437315,0.98351735],"study_design_scores_gemma":[0.0003255406,0.00013729557,0.00079243834,0.000012501602,0.000003489653,0.000020686213,0.000011308618,0.89208823,0.028226273,0.0010282615,0.077130936,0.00022302842],"about_ca_topic_score_codex":0.000059405353,"about_ca_topic_score_gemma":0.00003008385,"teacher_disagreement_score":0.9832943,"about_ca_system_score_codex":0.000015045684,"about_ca_system_score_gemma":0.000030871906,"threshold_uncertainty_score":0.39255095},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009692409,0.00035046946,0.9764598,0.01231334,0.00031686312,0.00015966294,0.000019061032,0.00020291988,0.00048547756],"genre_scores_gemma":[0.85150206,0.00012152726,0.14088592,0.005893283,0.00043444725,0.00008092385,0.0008332882,0.000037467726,0.00021107533],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985006,0.00008209611,0.00020098915,0.00038222596,0.00035613246,0.00047794933],"domain_scores_gemma":[0.9991081,0.000047726473,0.00008740667,0.00055662444,0.000064629625,0.00013556116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022279922,0.00015998424,0.00015086282,0.000034242592,0.00020806864,0.00021506324,0.00067752943,0.000054388685,0.000008890418],"category_scores_gemma":[0.000040509552,0.00014301614,0.00006775639,0.00032877293,0.000042263597,0.0009466231,0.0001547805,0.00023233176,0.00007721176],"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":[0.00017011624,0.00044092658,0.00021179755,0.000025807058,0.00015887005,0.00014322436,0.004570584,0.026966752,0.021809192,0.37853816,0.53986025,0.027104316],"study_design_scores_gemma":[0.0062055197,0.000384846,0.0005070127,0.000047934438,0.00004784196,0.00015907118,0.00009500168,0.6293328,0.008120547,0.021253454,0.33277926,0.0010667559],"about_ca_topic_score_codex":0.00003315472,"about_ca_topic_score_gemma":0.0000044427825,"teacher_disagreement_score":0.8418097,"about_ca_system_score_codex":0.00022492754,"about_ca_system_score_gemma":0.00017791145,"threshold_uncertainty_score":0.58320284},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.743376,0.000008483479,0.25165212,0.003959383,0.00008572796,0.00082790427,0.000004250115,0.00006562982,0.000020515941],"genre_scores_gemma":[0.94198066,0.0000010147434,0.055448424,0.0023778616,0.00005569758,0.000089998015,0.000002354143,0.000004957356,0.000039033523],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863917,0.00007884482,0.00020797802,0.0005189616,0.00026449023,0.0002905591],"domain_scores_gemma":[0.9991363,0.000059143338,0.00003253044,0.0005264981,0.00008615322,0.0001593332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024256184,0.00013820277,0.00016795313,0.00012031268,0.00015250346,0.0004199381,0.0003638356,0.000032046664,0.00006310649],"category_scores_gemma":[0.000038757527,0.00010341987,0.00001895884,0.00023779851,0.00006700392,0.0008382277,0.0006572824,0.00013146581,0.00007379015],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027869167,0.011669132,0.23650306,0.0006336736,0.00018664058,0.022508923,0.037464693,0.00417761,0.0212411,0.23157316,0.261217,0.1725463],"study_design_scores_gemma":[0.0024829777,0.00064855925,0.4329076,0.000121569145,0.000013506639,0.0008747629,0.0015845359,0.5498714,0.0007707971,0.0051869024,0.004606011,0.0009314139],"about_ca_topic_score_codex":0.0070836255,"about_ca_topic_score_gemma":0.0018388444,"teacher_disagreement_score":0.54569376,"about_ca_system_score_codex":0.00004880459,"about_ca_system_score_gemma":0.0000228002,"threshold_uncertainty_score":0.9995283},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05918144,0.00003731483,0.9393523,0.000820134,0.0000746855,0.00013550879,0.000024011617,0.00020065732,0.00017395186],"genre_scores_gemma":[0.9619388,0.000034399425,0.03764168,0.00030846318,0.000019077343,0.0000092059245,0.00002937712,0.000003627031,0.000015347598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999219,0.00003297569,0.00029107655,0.0001349069,0.00018190587,0.00014013577],"domain_scores_gemma":[0.9993379,0.00016674187,0.00016412097,0.00018599513,0.00006176982,0.00008346703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021916676,0.00010528402,0.000115243645,0.00012338448,0.00015834803,0.00035445753,0.00020815102,0.000038338476,0.0000017506067],"category_scores_gemma":[0.000036653088,0.00007327677,0.000016043628,0.00010979541,0.00003245411,0.0029560765,0.00031705917,0.000049023012,0.00002136535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045001507,0.000003965709,0.00024297101,0.000023043845,0.0000053469134,8.7594276e-7,0.0014954727,0.00007934416,0.0000127317835,0.008895049,0.00021767554,0.98901904],"study_design_scores_gemma":[0.0019091679,0.00009486603,0.014313,0.00014382612,0.000006313908,0.000033532182,0.00013340042,0.8910925,0.00016999828,0.08409957,0.0077123065,0.00029153813],"about_ca_topic_score_codex":0.000038542727,"about_ca_topic_score_gemma":0.0000022425525,"teacher_disagreement_score":0.9887275,"about_ca_system_score_codex":0.000015727255,"about_ca_system_score_gemma":0.000020400463,"threshold_uncertainty_score":0.3418042},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2614339,0.00006608273,0.73608977,0.000011255473,0.00023799994,0.000103846054,0.00003034405,0.00012392167,0.0019028696],"genre_scores_gemma":[0.9904044,0.000057455392,0.008852594,0.000022217533,0.00002294446,3.8495762e-7,0.000022924904,0.00000797317,0.00060908083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896437,0.000056732813,0.00013999607,0.0005740071,0.00009784413,0.000167022],"domain_scores_gemma":[0.99841255,0.000020925756,0.00021253584,0.0010647483,0.00017633245,0.000112929694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017447252,0.00016926676,0.00022259571,0.00023617341,0.000052798547,0.00004110215,0.0012510995,0.00018498574,0.0000053399267],"category_scores_gemma":[0.000015989786,0.00017959604,0.00011577022,0.00037780553,0.000050336694,0.0003953071,0.0021728552,0.00029998654,0.000013596886],"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":[0.00002524336,0.00010276232,0.00030415904,0.00006541847,0.00004498222,0.000057856294,0.000886727,0.82911,0.0007387188,0.16573985,0.0013580945,0.0015661622],"study_design_scores_gemma":[0.00021475031,0.000025473753,0.0000495535,0.00004660754,0.00001845615,0.0000012555415,0.000039614555,0.89246464,0.00033600567,0.10658367,0.000049562168,0.00017044078],"about_ca_topic_score_codex":0.00030141356,"about_ca_topic_score_gemma":0.000023593087,"teacher_disagreement_score":0.7289705,"about_ca_system_score_codex":0.00007641622,"about_ca_system_score_gemma":0.00020538787,"threshold_uncertainty_score":0.73237145},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009768268,0.001985592,0.9926678,0.00057833816,0.0029008666,0.0006741687,0.00029525382,0.0002102227,0.0006780248],"genre_scores_gemma":[0.017902138,0.00006697383,0.98003787,0.0006703634,0.00059647794,0.000014486615,0.00034971384,0.000048723607,0.0003132827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99474335,0.000036657246,0.0005919494,0.0025530152,0.0013138116,0.00076119823],"domain_scores_gemma":[0.9939285,0.00057647034,0.00039915688,0.0043781474,0.00044240127,0.00027531848],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011806892,0.0006392663,0.000683182,0.0005770427,0.00036042882,0.0009507136,0.0129470285,0.00036174507,0.000018033781],"category_scores_gemma":[0.00016048616,0.000523991,0.00009204691,0.0003978884,0.00075183064,0.0016729864,0.0062486213,0.0006515447,0.000017379301],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014463237,0.000025072295,0.00000751045,0.00007183703,0.00002065668,0.00005353903,0.00024423096,0.027914796,0.00013950048,0.027421836,0.0010981387,0.9429884],"study_design_scores_gemma":[0.00026739217,0.00010753254,0.00002183404,0.00016275223,0.000008234731,0.00004030029,1.219859e-7,0.6696839,0.00009470656,0.31517035,0.013954622,0.00048826216],"about_ca_topic_score_codex":0.000046248046,"about_ca_topic_score_gemma":0.000100568854,"teacher_disagreement_score":0.9425002,"about_ca_system_score_codex":0.0002477257,"about_ca_system_score_gemma":0.0011078161,"threshold_uncertainty_score":0.99972117},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006165963,0.00041730204,0.9913252,0.000008579998,0.0056988695,0.0006998255,0.0000814076,0.00024315574,0.0009090825],"genre_scores_gemma":[0.002562742,0.00014192468,0.96453553,0.00012837315,0.00041666362,0.00031739956,0.004267291,0.000057838937,0.02757226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988088,0.000006344142,0.0003834646,0.00031005274,0.00024078165,0.00025056527],"domain_scores_gemma":[0.9985844,0.000055777455,0.00026029392,0.00080117426,0.00019966337,0.00009868004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001189895,0.0002396262,0.000264625,0.00011602874,0.00016345587,0.00037614754,0.0010213916,0.00037445812,0.000008932168],"category_scores_gemma":[0.00002482368,0.00018250087,0.00011321733,0.00008629783,0.000008848242,0.000357488,0.00010414639,0.00021641272,0.00006362025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012697557,0.00087974087,0.000029270164,0.0069348593,0.0004224027,0.00006119058,0.0075400854,0.0031646881,0.0028774044,0.074991934,0.10904549,0.79392594],"study_design_scores_gemma":[0.00026061115,0.000049017715,0.00001726126,0.000084030435,0.000010094594,0.00001475485,0.00007174695,0.96268135,0.0006583261,0.00012030704,0.035750687,0.00028183154],"about_ca_topic_score_codex":0.00007121771,"about_ca_topic_score_gemma":0.00008527005,"teacher_disagreement_score":0.95951664,"about_ca_system_score_codex":0.000016903383,"about_ca_system_score_gemma":0.000090426096,"threshold_uncertainty_score":0.744217},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008824892,0.00076109974,0.99394125,0.0012321533,0.0013740571,0.00029849375,0.0002500945,0.00026805198,0.0018659881],"genre_scores_gemma":[0.031237496,0.00019030462,0.9627428,0.0027859148,0.0018773378,0.000015747099,0.00036509222,0.000101874146,0.00068344624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99460936,0.000040816212,0.00055597775,0.002629733,0.0013915239,0.00077256636],"domain_scores_gemma":[0.99429125,0.00032969308,0.00039957452,0.004521403,0.00022958596,0.00022850635],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008431176,0.0006480812,0.00057311775,0.00046075313,0.0004807147,0.0010628118,0.008793867,0.0003412719,0.00001700641],"category_scores_gemma":[0.00013529001,0.00046185905,0.0000767493,0.0004875655,0.0007951853,0.0020577267,0.005403867,0.0007711122,0.00005382377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011250921,0.000030946867,0.000007342049,0.0000358011,0.0000064718283,0.00012980896,0.00011098359,0.0006610673,0.00007093654,0.026664369,0.00026086473,0.97201014],"study_design_scores_gemma":[0.0004912246,0.00028044914,0.00012241224,0.002874945,0.000012112688,0.00009933346,1.7380913e-7,0.700038,0.0008522966,0.2539774,0.039915428,0.0013362403],"about_ca_topic_score_codex":0.000010979994,"about_ca_topic_score_gemma":0.000012739893,"teacher_disagreement_score":0.9706739,"about_ca_system_score_codex":0.00022546032,"about_ca_system_score_gemma":0.00085586245,"threshold_uncertainty_score":0.9999742},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051347146,0.00039553145,0.9875371,0.00027307516,0.0013315713,0.0003356584,0.000017218375,0.00011457823,0.009943955],"genre_scores_gemma":[0.108095355,0.000061383034,0.8896368,0.00090619817,0.0004997308,0.000010655609,0.000019630546,0.0000433392,0.000726884],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99631,0.000030400184,0.0006194549,0.0013499354,0.001120406,0.00056978874],"domain_scores_gemma":[0.9966892,0.00027076513,0.00041797818,0.002099502,0.0003306163,0.00019195036],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005545484,0.00046283664,0.0006479445,0.00059769524,0.00018865467,0.0003328544,0.004828305,0.00028028377,0.00016442672],"category_scores_gemma":[0.00004921447,0.00039741764,0.00014109361,0.0004767329,0.0013662102,0.0008841511,0.0026993065,0.0006476292,0.00012803184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020293214,0.000045064106,0.000027646527,0.000054744654,0.000009787162,0.00002814829,0.00033743263,0.0022129319,0.0003091537,0.19244263,0.00017067503,0.8043598],"study_design_scores_gemma":[0.00021239047,0.00014190753,0.00033203297,0.00037441417,0.000004941562,0.00004074269,7.786865e-8,0.4235423,0.0016237843,0.5705121,0.002664945,0.00055034197],"about_ca_topic_score_codex":0.000113991075,"about_ca_topic_score_gemma":0.000024723748,"teacher_disagreement_score":0.8038094,"about_ca_system_score_codex":0.00014955619,"about_ca_system_score_gemma":0.00042286894,"threshold_uncertainty_score":0.99984777},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4002224,0.00074020604,0.5841432,0.0007163105,0.00937468,0.0014432296,0.0007496806,0.0024428559,0.00016740678],"genre_scores_gemma":[0.93121,0.00012240722,0.066500135,0.0008268529,0.0011195027,0.00010747076,0.0000013699553,0.00010374673,0.0000085344445],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573916,0.000104041865,0.0006229038,0.0018132699,0.0008815859,0.0008390532],"domain_scores_gemma":[0.9945027,0.00012386953,0.0005767972,0.0040012402,0.00031580607,0.00047953537],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005637893,0.00085828634,0.000756599,0.00037076086,0.0003256568,0.00083035405,0.0033413116,0.0007928206,0.000040901985],"category_scores_gemma":[0.00012897629,0.0007674906,0.00021370332,0.00044927726,0.0000902491,0.00048019976,0.0030446658,0.0014704453,0.00027232798],"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":[0.00048156563,0.002083192,0.008712052,0.003487946,0.0017552834,0.0024300492,0.0002920479,0.018662322,0.52187234,0.2665739,0.17187996,0.0017693518],"study_design_scores_gemma":[0.00311042,0.00069302385,0.1943491,0.003911166,0.00019820443,5.606862e-7,0.0000029517753,0.25276247,0.21540424,0.0004885798,0.32230562,0.0067736674],"about_ca_topic_score_codex":0.00006128419,"about_ca_topic_score_gemma":0.0000013116608,"teacher_disagreement_score":0.5309876,"about_ca_system_score_codex":0.0002708839,"about_ca_system_score_gemma":0.0005371435,"threshold_uncertainty_score":0.9994776},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67933804,0.005670181,0.30999967,0.004627482,0.00021774812,0.000050382758,0.0000013146641,0.0000095722435,0.00008562086],"genre_scores_gemma":[0.99636096,0.0030313996,0.0004937314,0.000030427122,0.000038547634,3.1469384e-7,4.0923016e-8,0.0000032999967,0.000041274245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992002,0.0001330647,0.00017671035,0.000082140825,0.00018618796,0.000221648],"domain_scores_gemma":[0.9991382,0.00026988293,0.00025765752,0.00019019414,0.00009599328,0.000048087364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062690716,0.000073091054,0.0001214538,0.000048270245,0.00020145708,0.00004888443,0.0005590794,0.000029136267,0.0000012707538],"category_scores_gemma":[0.000031030293,0.00003285989,0.000030733387,0.00016462596,0.00023722385,0.00036918095,0.00016393884,0.00019731912,1.8700617e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008499348,0.000013339811,0.0010062227,0.0000029547246,0.000032077358,0.0000028142229,0.00028518258,0.000012418249,0.0034510775,0.98107076,0.00017497838,0.013939683],"study_design_scores_gemma":[0.0010684717,0.00049952837,0.0040408224,0.00010053162,0.00005466508,0.0015852613,0.00044567135,0.005054657,0.004020416,0.97910184,0.0038914862,0.00013662441],"about_ca_topic_score_codex":0.00002717769,"about_ca_topic_score_gemma":0.0000057269867,"teacher_disagreement_score":0.31702295,"about_ca_system_score_codex":0.00008016562,"about_ca_system_score_gemma":0.00030401789,"threshold_uncertainty_score":0.15494654},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029679243,0.000049338767,0.8471339,0.000092102455,0.00035847616,0.0011207144,0.00083913864,0.00018898094,0.15021443],"genre_scores_gemma":[0.00065347564,0.000072397415,0.5295983,0.0010111387,0.005511278,0.00019839584,0.0017535505,0.00030153076,0.46089995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978752,0.0000033960107,0.0005323238,0.0008324714,0.00041898622,0.00033759564],"domain_scores_gemma":[0.99739647,0.00027578278,0.00046586565,0.0016349454,0.000061422055,0.00016553995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005709008,0.00046418983,0.0006746121,0.000036864367,0.00034304688,0.00031297348,0.0016160649,0.0008375549,0.000013887783],"category_scores_gemma":[0.000012259958,0.00038337108,0.0002847844,0.000015858548,0.0001414735,0.000076025135,0.0019241634,0.00056405365,0.000016497057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006005173,0.000012177327,2.6443942e-8,0.00016285694,0.00013692203,5.4409054e-7,0.00022801117,0.0000010903452,0.0000141634,0.81754017,0.060827035,0.121070996],"study_design_scores_gemma":[0.0011483332,0.000056319215,2.5512243e-8,0.0002064769,0.00013322849,0.000008015225,0.00004538445,0.03851026,0.000052505566,0.28039452,0.6788775,0.000567453],"about_ca_topic_score_codex":0.0000022165452,"about_ca_topic_score_gemma":0.0000013853498,"teacher_disagreement_score":0.61805046,"about_ca_system_score_codex":0.000030480775,"about_ca_system_score_gemma":0.00012985095,"threshold_uncertainty_score":0.99986184},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027187113,0.00083414954,0.99509495,0.00069398346,0.0012511108,0.00089784816,0.000031185496,0.00016558163,0.00075932377],"genre_scores_gemma":[0.19670705,0.00006013439,0.7984476,0.002002547,0.0017155453,0.00003952508,0.0000639762,0.00010583346,0.0008578077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945024,0.000095404255,0.0005107514,0.0024596842,0.0017666157,0.0006651062],"domain_scores_gemma":[0.99110013,0.00044810105,0.0003422083,0.007471748,0.00036631498,0.0002714704],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0020801437,0.0006374537,0.00054774876,0.00039657202,0.0005822994,0.0011719194,0.011166214,0.00018978922,0.000015236468],"category_scores_gemma":[0.00006967499,0.00036487446,0.00005016226,0.0007051577,0.00076942716,0.0014741169,0.009960744,0.0010608212,0.000041555726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020997813,0.0002173787,0.00011007116,0.000020610747,0.00004909238,0.01626709,0.0047601466,0.016750587,0.0000034648326,0.0031652837,0.0014156639,0.9572196],"study_design_scores_gemma":[0.00075545546,0.00066328875,0.00003926223,0.00022367146,0.000033913304,0.0062535126,0.000008024594,0.9566993,0.0000064206024,0.020205567,0.014204023,0.0009075209],"about_ca_topic_score_codex":0.0004706996,"about_ca_topic_score_gemma":0.0008694937,"teacher_disagreement_score":0.9563121,"about_ca_system_score_codex":0.00014597477,"about_ca_system_score_gemma":0.00093091046,"threshold_uncertainty_score":0.9998803},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3037485,0.000067517976,0.65157586,0.0012570443,0.0007907873,0.00043789655,0.0001310482,0.00018876078,0.041802593],"genre_scores_gemma":[0.9476177,0.000003807298,0.05162214,0.000570915,0.0000434525,0.0000068414492,0.000054565364,0.000007860193,0.00007268208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983569,0.000101527534,0.00021097805,0.00052228244,0.00037167603,0.00043662827],"domain_scores_gemma":[0.99856883,0.00008127921,0.000042282227,0.0005027483,0.00019319438,0.00061169016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032565073,0.0001572037,0.00015581117,0.0007627408,0.00015333736,0.00017283995,0.0011467437,0.00009079522,0.0002920375],"category_scores_gemma":[0.000026087595,0.0001613114,0.000029864095,0.0007739718,0.000057986945,0.0006364022,0.00008959229,0.00027806003,0.00021231896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002184799,0.00023547902,0.011589391,0.000013459278,0.000013464828,0.00025712617,0.0015152018,0.004664905,0.00004047942,0.739198,0.0010724129,0.2413782],"study_design_scores_gemma":[0.0004305812,0.00022861174,0.3044531,0.000041288626,0.0000015156904,0.000017951996,0.00009529106,0.671657,0.00008752384,0.021566218,0.0010689404,0.0003519668],"about_ca_topic_score_codex":0.027234552,"about_ca_topic_score_gemma":0.026549043,"teacher_disagreement_score":0.7176318,"about_ca_system_score_codex":0.00018033231,"about_ca_system_score_gemma":0.0014293854,"threshold_uncertainty_score":0.9912139},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005057879,0.00019232593,0.9854662,0.0014124943,0.00026331426,0.00016131732,0.000014083383,0.00043989593,0.0069925147],"genre_scores_gemma":[0.7168956,0.000065285465,0.28189567,0.0007614533,0.00017215771,0.0000046303417,0.00005636079,0.0000067847036,0.00014206787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814004,0.000103936516,0.00036538523,0.0006983179,0.00022461344,0.00046771122],"domain_scores_gemma":[0.9984085,0.00011632723,0.00019496171,0.000908009,0.00021821214,0.00015400563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002794002,0.0002217114,0.00029299263,0.00014100428,0.00034769985,0.00022831874,0.0012516103,0.00013813897,0.00005302955],"category_scores_gemma":[0.00010560682,0.0002136565,0.000066684916,0.00041633745,0.000090531976,0.0005366241,0.00046260015,0.00036796607,0.00008238099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005678921,0.00012942053,0.00032401373,0.000010998743,0.000018311386,0.00014134517,0.00025419105,0.000026515863,0.002207461,0.23305061,0.0021356095,0.76169586],"study_design_scores_gemma":[0.0021595168,0.00085166126,0.08546436,0.0005271128,0.000043291242,0.0007781968,0.00008781558,0.82435745,0.0069717737,0.046549875,0.030555507,0.0016534681],"about_ca_topic_score_codex":0.000026480864,"about_ca_topic_score_gemma":0.0000011517617,"teacher_disagreement_score":0.8243309,"about_ca_system_score_codex":0.000034934674,"about_ca_system_score_gemma":0.00012523122,"threshold_uncertainty_score":0.8712659},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027303087,0.0006985434,0.9938556,0.00034782378,0.0021996698,0.00027356265,0.000007639027,0.00021367826,0.002376196],"genre_scores_gemma":[0.011536276,0.000035969453,0.985484,0.0008269441,0.00092528353,0.000008900489,0.000018527586,0.000038714308,0.0011254065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960748,0.000035316498,0.0004138111,0.0014979383,0.0014127138,0.00056543207],"domain_scores_gemma":[0.9977552,0.00022542287,0.00023000021,0.0010732847,0.00045675697,0.00025933541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092585006,0.0004682368,0.00043455785,0.0006655047,0.0002711295,0.0003163138,0.0022446634,0.00032409758,0.00004873569],"category_scores_gemma":[0.00007293012,0.00039991876,0.000097477496,0.00053047057,0.00034255796,0.00095093716,0.0018808153,0.00076333,0.00015567453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010822502,0.000045235294,0.00004656247,0.000017705985,0.000009299868,0.00008555012,0.0002797013,0.024898913,0.00019207693,0.026854793,0.00080179056,0.94675756],"study_design_scores_gemma":[0.00038811984,0.00015647316,0.00010518245,0.00022814657,0.0000051276447,0.00011444137,4.1569074e-8,0.89159584,0.00037118053,0.08690995,0.01952476,0.0006007546],"about_ca_topic_score_codex":0.000040976567,"about_ca_topic_score_gemma":0.00003481809,"teacher_disagreement_score":0.9461568,"about_ca_system_score_codex":0.00036897557,"about_ca_system_score_gemma":0.0007438547,"threshold_uncertainty_score":0.99984527},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.241695,0.0006321242,0.29473162,0.0027196468,0.0015601736,0.000894024,0.000015967873,0.0012180553,0.45653337],"genre_scores_gemma":[0.8385729,0.00012734329,0.120090246,0.00008999619,0.0012053713,0.000005876714,0.00001190002,0.000039868657,0.039856452],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958825,0.0006549142,0.00030939974,0.0010167685,0.0011267657,0.0010096553],"domain_scores_gemma":[0.9969429,0.00038215052,0.00012959082,0.0014838296,0.00057379087,0.00048777182],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010062619,0.00024829636,0.00027117704,0.0009676596,0.0015653766,0.00055958296,0.0027405897,0.00017056013,0.00005656127],"category_scores_gemma":[0.000113842376,0.00025632646,0.00014362537,0.001860331,0.00031865275,0.002476701,0.0012026699,0.0009193259,0.00024121103],"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":[0.00030293444,0.0012436085,0.010462258,0.0001851135,0.0003291005,0.004900545,0.00471055,0.00063700473,0.2154366,0.34473014,0.040232547,0.37682962],"study_design_scores_gemma":[0.0013594917,0.00031164777,0.0009844813,0.0001903635,0.000014534101,0.000538737,0.0010432471,0.041048266,0.059565734,0.00078636117,0.8933648,0.00079233514],"about_ca_topic_score_codex":0.00031097373,"about_ca_topic_score_gemma":0.000023032497,"teacher_disagreement_score":0.85313225,"about_ca_system_score_codex":0.0005238785,"about_ca_system_score_gemma":0.0004616433,"threshold_uncertainty_score":0.9999889},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027360339,0.000024061737,0.96621454,0.00042441743,0.00051741226,0.00007708599,0.0000035483376,0.00018225746,0.0051963343],"genre_scores_gemma":[0.9804112,0.000008451323,0.019209247,0.00013957344,0.000114935894,0.000010550737,0.000015579748,0.000004910785,0.00008559614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882114,0.00013919968,0.0001892787,0.000415005,0.00016209572,0.00027328476],"domain_scores_gemma":[0.9989704,0.00016683464,0.00009565125,0.00056058064,0.00010584122,0.00010072917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019501224,0.00012595307,0.0001598689,0.00006353271,0.00013499684,0.00012097112,0.0008803538,0.000079778336,0.00004011035],"category_scores_gemma":[0.00015689024,0.000110758076,0.000027404132,0.00014715001,0.000067242654,0.00039466098,0.0004465454,0.00017922549,0.000068362795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055704913,0.000037310918,0.008111449,0.000007333151,0.000008135727,0.0000068296113,0.00014136967,0.0000988154,0.002009978,0.89777076,0.0003192343,0.09148321],"study_design_scores_gemma":[0.0026791927,0.0007349924,0.1448686,0.00009977814,0.000022277609,0.000103504964,0.00004167181,0.71533597,0.011586223,0.05954405,0.06379974,0.0011840113],"about_ca_topic_score_codex":0.0001709418,"about_ca_topic_score_gemma":0.000039581675,"teacher_disagreement_score":0.9530508,"about_ca_system_score_codex":0.000020764668,"about_ca_system_score_gemma":0.00012154128,"threshold_uncertainty_score":0.45165834},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20341788,0.0012241035,0.77859056,0.00009085439,0.006233847,0.001189966,0.00043981368,0.0012642951,0.0075486735],"genre_scores_gemma":[0.17815772,0.0010567588,0.7837119,0.00029683663,0.00170927,0.000005843712,0.016745336,0.0003620845,0.01795423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961012,0.00018501942,0.00046769256,0.0017889375,0.0007490314,0.0007081035],"domain_scores_gemma":[0.99567306,0.00015872784,0.0006457698,0.0029461926,0.00031080924,0.00026544207],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026544312,0.0006302201,0.00062712934,0.0006197882,0.0009385897,0.0005109706,0.0052333735,0.00052275846,0.00009295848],"category_scores_gemma":[0.00006278908,0.0006776137,0.00012364499,0.0010830879,0.000058151098,0.0045512873,0.0029100857,0.00086713646,0.00007687148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057084614,0.0012433867,0.024004921,0.0039613536,0.0020528038,0.008809757,0.00224284,0.025311325,0.010408874,0.03884605,0.20766431,0.67488354],"study_design_scores_gemma":[0.0012956575,0.00008608117,0.00027484525,0.002300739,0.00021073272,2.1614791e-7,0.012244312,0.9012723,0.0053188032,0.00077597535,0.074304126,0.0019162239],"about_ca_topic_score_codex":0.0044680308,"about_ca_topic_score_gemma":0.0041987333,"teacher_disagreement_score":0.87596095,"about_ca_system_score_codex":0.00044786942,"about_ca_system_score_gemma":0.00047687875,"threshold_uncertainty_score":0.9995675},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06752946,0.0005564275,0.9283632,0.0002796243,0.00018452803,0.0000987368,4.247771e-7,0.00009037594,0.0028972346],"genre_scores_gemma":[0.71285546,0.000004219742,0.28650445,0.00037774083,0.00007125823,0.0000031477477,0.000016303862,0.0000054531256,0.00016197542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987861,0.00005780002,0.00030541865,0.000490425,0.00009532848,0.0002649488],"domain_scores_gemma":[0.99921465,0.000014727289,0.00012250873,0.00055366824,0.000020702251,0.00007373601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002752511,0.00011864658,0.00017719614,0.00010612614,0.00004801748,0.00005909112,0.0003247947,0.00009182717,0.000006858803],"category_scores_gemma":[0.00003731222,0.00010483443,0.00004470079,0.00018424768,0.00004308777,0.00013991827,0.00043424938,0.00013796335,0.000008049777],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001441968,0.000438366,0.040095534,0.000036638045,0.00007451312,0.0036036798,0.0036530015,0.00939916,0.04301138,0.07588938,0.007535243,0.8162487],"study_design_scores_gemma":[0.002250354,0.0003624353,0.019033637,0.00022025226,0.000026062422,0.008613651,0.00021241137,0.6770056,0.025592986,0.0610702,0.2033283,0.0022841494],"about_ca_topic_score_codex":0.00014175047,"about_ca_topic_score_gemma":0.0000038660587,"teacher_disagreement_score":0.81396455,"about_ca_system_score_codex":0.000028115717,"about_ca_system_score_gemma":0.00009081132,"threshold_uncertainty_score":0.4275024},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13773441,0.0076354784,0.81161344,0.023730876,0.01707737,0.00018773883,0.000003921582,0.000060832743,0.0019559353],"genre_scores_gemma":[0.9958108,0.00025480107,0.001551268,0.00034977522,0.0006161986,0.0000012137166,6.904821e-7,0.000010056217,0.0014051988],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857396,0.00010120068,0.00028472583,0.00010993227,0.000608813,0.00032135623],"domain_scores_gemma":[0.99842983,0.00021809417,0.00046934726,0.0004838397,0.00020873173,0.00019013938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009772459,0.00013134055,0.00020080393,0.00008244909,0.00031167528,0.0002469897,0.0012090137,0.00006126253,0.000018898969],"category_scores_gemma":[0.00011190483,0.00006552414,0.000120840254,0.00029696294,0.00003982131,0.00153019,0.0005625233,0.00034038522,0.000017556988],"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":[0.00006758726,0.001590264,0.08343574,0.0001565874,0.00034814375,0.00028863407,0.010846455,0.00015804838,0.0021672875,0.24278277,0.46462417,0.19353433],"study_design_scores_gemma":[0.0017896749,0.00036935273,0.06096164,0.00032570082,0.00007313005,0.001165134,0.0005631698,0.0036300053,0.011657647,0.024355086,0.89446,0.0006494632],"about_ca_topic_score_codex":0.0000020938478,"about_ca_topic_score_gemma":0.0000014745358,"teacher_disagreement_score":0.8580764,"about_ca_system_score_codex":0.00011633015,"about_ca_system_score_gemma":0.000060206108,"threshold_uncertainty_score":0.26719967},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16153935,0.000021778575,0.8376385,0.00015317871,0.0002523383,0.00016577443,0.00001004586,0.000071553244,0.00014750706],"genre_scores_gemma":[0.9903046,0.00018511566,0.009282473,0.00007694307,0.00009372513,0.0000151629665,0.000014683644,0.000009427143,0.000017881102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844944,0.000044257475,0.0002972914,0.0007757307,0.00020611545,0.00022715937],"domain_scores_gemma":[0.9983311,0.000114714334,0.00012631304,0.0013272616,0.00003219554,0.00006835992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032360622,0.0001455419,0.00013144662,0.00013387237,0.00010150056,0.000094685354,0.00089223275,0.0000823187,0.000005597423],"category_scores_gemma":[0.00004233921,0.000105804065,0.00001190081,0.00027507372,0.00004540296,0.0004162303,0.00047713888,0.00012414873,0.000031134252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019589976,0.000037321646,0.00013090187,0.0000048333914,0.0000031002432,0.000003880729,0.00012603225,0.00004642957,0.16359012,0.004631651,0.000021900829,0.83138424],"study_design_scores_gemma":[0.00041456873,0.00013015998,0.019947706,0.00032843318,0.00000842753,0.000025117874,0.00015571927,0.6445598,0.32616162,0.0060895015,0.0015582921,0.0006206365],"about_ca_topic_score_codex":0.00015178847,"about_ca_topic_score_gemma":0.00003932772,"teacher_disagreement_score":0.8307636,"about_ca_system_score_codex":0.00006105034,"about_ca_system_score_gemma":0.000029583995,"threshold_uncertainty_score":0.43145645},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25793856,0.0022848763,0.7371692,0.00043883934,0.00092213106,0.000374905,0.000058042067,0.000015748552,0.0007976907],"genre_scores_gemma":[0.9432284,0.00006358913,0.056507923,0.00003247014,0.00014582167,0.0000039370443,0.00001243539,0.0000035854373,0.0000018143353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99612594,0.00021097809,0.000659619,0.00030648863,0.0023724677,0.0003244914],"domain_scores_gemma":[0.9981839,0.00016412098,0.0007256329,0.00067225425,0.00010815213,0.00014590865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010027113,0.00013570035,0.0002889594,0.00022754417,0.00013642662,0.00007881191,0.0023389542,0.000053693297,0.000050581257],"category_scores_gemma":[0.0000858029,0.00009535959,0.000042302854,0.00054595165,0.00018764946,0.0018706139,0.0008862677,0.0001997324,0.000008340533],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044918885,0.0015262355,0.00631895,0.00002843553,0.000047790516,0.000007738805,0.0016058503,0.0134661,0.031059062,0.004653446,0.0036406456,0.93760085],"study_design_scores_gemma":[0.0023280075,0.00028407312,0.07380066,0.00024309002,0.000099022545,0.000072897165,0.0006184162,0.89752215,0.013555625,0.005496673,0.0055970377,0.00038235143],"about_ca_topic_score_codex":0.000016187298,"about_ca_topic_score_gemma":0.0000016670272,"teacher_disagreement_score":0.9372185,"about_ca_system_score_codex":0.000103603685,"about_ca_system_score_gemma":0.00024924977,"threshold_uncertainty_score":0.4346398},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22406065,0.0011796473,0.7738616,0.00018040938,0.00035169072,0.00008200549,0.0000059951853,0.00010865585,0.0001693367],"genre_scores_gemma":[0.9794577,0.00016745922,0.020097481,0.00007293373,0.00013521213,0.00000403809,0.00005166672,0.000005775161,0.000007768284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988016,0.000039465165,0.0002419706,0.00043963533,0.00011225093,0.00036506492],"domain_scores_gemma":[0.99937946,0.000102615304,0.0000757423,0.00025880654,0.000026116772,0.0001572554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022097376,0.00017231074,0.00020411672,0.000049910108,0.00021210936,0.00023368298,0.0003047978,0.000113837836,0.0000043108525],"category_scores_gemma":[0.000016829452,0.00014779664,0.000025321924,0.00020815825,0.000049874237,0.0002482898,0.00055004796,0.00034474971,0.0000015681015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008886149,0.0005529944,0.09674122,0.0000666852,0.00006679758,0.00020078913,0.002594433,0.03421814,0.0008534468,0.05859043,0.004226164,0.8018],"study_design_scores_gemma":[0.0006177013,0.000040097268,0.021763526,0.000054108088,0.0000029333448,0.000030817588,0.000058357993,0.9749356,0.000022993638,0.0012557019,0.0009985085,0.00021967589],"about_ca_topic_score_codex":0.00010273655,"about_ca_topic_score_gemma":0.0000069155067,"teacher_disagreement_score":0.94071746,"about_ca_system_score_codex":0.000008491398,"about_ca_system_score_gemma":0.0000140202965,"threshold_uncertainty_score":0.6026972},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037561533,0.5107988,0.4876159,0.000033232594,0.0007527829,0.00027389737,0.000045558132,0.0003994037,0.00007665821],"genre_scores_gemma":[0.000059582148,0.79595745,0.20316313,0.000043014454,0.00044020946,0.000018325327,0.000192976,0.00004070834,0.00008458816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99212176,0.003385609,0.0013023405,0.0016809356,0.00054295367,0.00096640986],"domain_scores_gemma":[0.99219877,0.003187487,0.0009283496,0.003238962,0.00014733832,0.00029907323],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004055244,0.0008503921,0.002385854,0.00021676451,0.000398474,0.0004145663,0.007551566,0.00056799635,0.00003596581],"category_scores_gemma":[0.00073788647,0.000533419,0.000569458,0.00065370544,0.00018201476,0.00038162983,0.006667841,0.00078808656,0.00084342336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.321018e-7,0.000061778235,0.000055640936,0.00042823458,0.00004795991,0.00005045625,0.00002753533,0.000026207383,2.7162915e-7,0.0007789588,0.0025463963,0.99597585],"study_design_scores_gemma":[0.00023221302,0.00013176804,0.00013643918,0.0075537814,0.000030672796,0.00010593573,0.0000021178548,0.014905055,5.446168e-7,0.00032103554,0.9755732,0.0010072325],"about_ca_topic_score_codex":0.00004882099,"about_ca_topic_score_gemma":0.0000014064315,"teacher_disagreement_score":0.9949686,"about_ca_system_score_codex":0.00015241568,"about_ca_system_score_gemma":0.00033936166,"threshold_uncertainty_score":0.99993455},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035782207,0.000078989535,0.9907901,0.0030577495,0.00039828036,0.00012350961,0.000025531384,0.00029718236,0.0016504081],"genre_scores_gemma":[0.53786063,0.000085580374,0.45576423,0.0007512288,0.0006572008,0.000051994954,0.000013578356,0.000039594404,0.004775915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851644,0.0000661908,0.00018237198,0.00047270226,0.0003797732,0.0003825362],"domain_scores_gemma":[0.99862957,0.00018152667,0.000042667023,0.0008941615,0.00008591428,0.0001661357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023338076,0.00013334391,0.00013525275,0.00009431661,0.00013509349,0.00011967171,0.0012593489,0.00006326395,0.00012182214],"category_scores_gemma":[0.000039136637,0.0000794296,0.000055979257,0.00027710348,0.000057840625,0.0007739418,0.00058991683,0.00007981919,0.0006326485],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004847415,0.000058724167,0.00007605095,0.0000035878847,0.00001175516,0.000026875092,0.000064961896,0.0000017661317,0.0060956907,0.010488495,0.008308404,0.9748588],"study_design_scores_gemma":[0.005127528,0.00069750106,0.010929727,0.00039756767,0.00002183185,0.00018816035,0.000042464406,0.23158842,0.30085278,0.029613897,0.4186902,0.0018499233],"about_ca_topic_score_codex":0.00002992569,"about_ca_topic_score_gemma":0.0000010020049,"teacher_disagreement_score":0.97300893,"about_ca_system_score_codex":0.000035475234,"about_ca_system_score_gemma":0.00007064519,"threshold_uncertainty_score":0.81316274},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27235448,0.006454444,0.6828177,0.0010977522,0.006847974,0.001904982,0.0012756054,0.0008846996,0.02636235],"genre_scores_gemma":[0.4942196,0.0043700403,0.20952031,0.0012037017,0.0018843468,0.00007948994,0.24892753,0.00024797616,0.039547008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986925,0.0000448105,0.0002598349,0.0006120758,0.00023683134,0.00015394788],"domain_scores_gemma":[0.9989045,0.000093476694,0.0001263206,0.00079517945,0.000043508753,0.000037000664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021111139,0.00016033587,0.0001911585,0.00016257014,0.000059824768,0.0002738279,0.00078741106,0.00016161433,0.000028570525],"category_scores_gemma":[0.00005130344,0.00014049532,0.000014163446,0.00019822322,0.000009395451,0.0011871015,0.00030682454,0.00021645012,0.000024109626],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055971952,0.000083862185,0.00030473337,0.00015392393,0.00001038151,0.000053218402,0.00020367956,4.7710415e-7,0.00007298948,0.0000810408,0.009516096,0.9894636],"study_design_scores_gemma":[0.0052701784,0.0005018628,0.31180403,0.004333294,0.00020969831,0.00016666672,0.0014470174,0.60063004,0.008947065,0.028583402,0.033205822,0.004900904],"about_ca_topic_score_codex":0.00084494567,"about_ca_topic_score_gemma":0.0014585878,"teacher_disagreement_score":0.9845627,"about_ca_system_score_codex":0.000019103574,"about_ca_system_score_gemma":0.00006337941,"threshold_uncertainty_score":0.5729233},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052653026,0.000031474563,0.99791,0.00028388068,0.000026179589,0.00043903638,0.00011310895,0.00014252843,0.0005272205],"genre_scores_gemma":[0.03691381,0.0000010206053,0.9621407,0.0002711687,0.0001846337,0.0000879463,0.00035995746,0.000012399905,0.000028369637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985228,0.00001768365,0.00037855512,0.0006212861,0.00022905906,0.00023058461],"domain_scores_gemma":[0.9979228,0.00007098247,0.00021009512,0.0016631203,0.000079488,0.000053545293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013508504,0.00014555105,0.00015840156,0.00010720161,0.00015748384,0.00011487164,0.0019107595,0.00004503397,0.0000057895854],"category_scores_gemma":[4.98636e-7,0.00013749365,0.000047050427,0.00032918956,0.000036153706,0.00029076356,0.000994863,0.000086820975,0.00003035538],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011261703,0.00066594227,0.000039609502,0.00001482206,0.0000068788963,0.0000012937638,0.000019887977,0.0034895407,0.041590728,0.0022865967,0.0036873862,0.9481962],"study_design_scores_gemma":[0.00032688226,0.000068171554,0.00035409283,0.000025978054,0.000006057746,0.0000021838991,0.0000024514611,0.9119914,0.01643547,0.0015427849,0.06908169,0.00016280866],"about_ca_topic_score_codex":0.00011614905,"about_ca_topic_score_gemma":0.000004802044,"teacher_disagreement_score":0.9480334,"about_ca_system_score_codex":0.00003658065,"about_ca_system_score_gemma":0.000048279497,"threshold_uncertainty_score":0.56068283},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080856663,0.00018510489,0.9934082,0.004225551,0.000012748219,0.0004555386,0.000008554953,0.00007879026,0.0008169129],"genre_scores_gemma":[0.08560197,0.000029158771,0.9099615,0.0032526527,0.0003930991,0.0005963413,0.000032931643,0.000008372238,0.00012394582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991425,0.000047609392,0.00019339182,0.00030052336,0.00013108944,0.00018486977],"domain_scores_gemma":[0.99913645,0.000118013464,0.00004408843,0.00064209785,0.0000234696,0.00003586088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002243262,0.0000960154,0.00009271205,0.0000598895,0.00016053999,0.00018140711,0.0015878131,0.000032804084,0.0000058655137],"category_scores_gemma":[3.063489e-7,0.000064594984,0.000041232357,0.00034824465,0.000025733696,0.00030784568,0.00026997452,0.00013019182,0.00022006762],"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":[0.00000262705,0.0002281915,0.00011933838,0.0000041403987,0.0000046740192,0.0000019849085,0.0010178955,0.00049681915,0.00092833024,0.058238737,0.02000477,0.91895247],"study_design_scores_gemma":[0.00047097384,0.0000055673513,0.0017950222,0.000005379889,0.0000016764958,0.000022861137,0.000007054453,0.06915174,0.00025873646,0.0012914247,0.92689574,0.00009380337],"about_ca_topic_score_codex":0.000013802725,"about_ca_topic_score_gemma":0.000025738273,"teacher_disagreement_score":0.9188587,"about_ca_system_score_codex":0.00002438654,"about_ca_system_score_gemma":0.00002208716,"threshold_uncertainty_score":0.29505783},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062304484,0.0012026684,0.99100983,0.0007352438,0.0003393838,0.000056632125,0.0000020181703,0.000014650614,0.00040913266],"genre_scores_gemma":[0.78614354,0.00032116144,0.21341892,0.000031035743,0.000035202862,6.843198e-7,0.000001009057,0.000004358826,0.000044069195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990056,0.000093839015,0.0004959431,0.00008099825,0.00020407344,0.0001195258],"domain_scores_gemma":[0.99784404,0.00055760774,0.000601327,0.00059374346,0.00031569635,0.00008756186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011569704,0.00007571948,0.00019477971,0.00023321263,0.00024289012,0.000056169636,0.0007952291,0.000041477047,0.0000025030472],"category_scores_gemma":[0.00013406316,0.0000652595,0.000061384366,0.00019946386,0.00009979698,0.0004918868,0.00052851613,0.0002730651,0.0000013175901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019116054,0.0013677557,0.002386333,0.00010323864,0.00038886833,0.00002911114,0.02268216,0.004097448,0.022233194,0.07020907,0.008755331,0.86755633],"study_design_scores_gemma":[0.0007574857,0.0004292575,0.01181943,0.0007094016,0.000057079003,0.0004763176,0.003156018,0.96514744,0.0051336437,0.006543988,0.005533046,0.00023688638],"about_ca_topic_score_codex":0.000034344324,"about_ca_topic_score_gemma":0.000024404248,"teacher_disagreement_score":0.96105,"about_ca_system_score_codex":0.000042095027,"about_ca_system_score_gemma":0.000047556026,"threshold_uncertainty_score":0.2661205},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077876827,0.000072149385,0.994631,0.0011725079,0.0000751205,0.0012797962,0.00007108868,0.0004965234,0.001423071],"genre_scores_gemma":[0.059469216,0.000023788387,0.93715787,0.001548355,0.00025671718,0.0008731562,0.00025713013,0.000039789622,0.00037398186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973306,0.00007415933,0.0005131065,0.0010312403,0.00055431854,0.00049656624],"domain_scores_gemma":[0.99790156,0.00010268075,0.00016279609,0.00144458,0.00013343862,0.00025492584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017430788,0.00037207262,0.00032231284,0.00024362997,0.00075178547,0.00016005439,0.0015471698,0.0001349056,0.000035180503],"category_scores_gemma":[4.9688686e-7,0.0003329165,0.00016757112,0.00055034633,0.00009354007,0.00044326432,0.00027337665,0.00031537373,0.00021793692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005669865,0.0022818423,0.00013102544,0.00005580919,0.00006178799,0.000041114676,0.0010944173,0.011524213,0.010071291,0.008202811,0.029461324,0.9370177],"study_design_scores_gemma":[0.0015267861,0.00014265334,0.00049409183,0.000048115642,0.000008493647,0.0000458488,0.00000541729,0.7196243,0.0062773395,0.00060578407,0.27078864,0.00043253927],"about_ca_topic_score_codex":0.000056808087,"about_ca_topic_score_gemma":0.0000020555015,"teacher_disagreement_score":0.9365851,"about_ca_system_score_codex":0.00012280582,"about_ca_system_score_gemma":0.00012904052,"threshold_uncertainty_score":0.99991226},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002551859,0.000007802476,0.9927462,0.00008951037,0.00008688138,0.00028524114,0.0000035679582,0.000041037852,0.004187921],"genre_scores_gemma":[0.32769373,0.000003090833,0.6720174,0.00006279338,0.000012503176,0.000037110756,0.0000024814542,0.0000029122414,0.00016797693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995295,0.000010348099,0.0001388172,0.00012406995,0.00009279987,0.00010445791],"domain_scores_gemma":[0.9994033,0.00008661653,0.000068310575,0.00036706228,0.00005420982,0.000020526732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014934655,0.000051669776,0.000070615824,0.000013060888,0.0000643975,0.000025248466,0.00043258956,0.000023803743,0.000070375536],"category_scores_gemma":[0.000009179205,0.000027688351,0.00004359408,0.00008183426,0.000010436626,0.00034121555,0.00014940492,0.000023934757,0.000011066169],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006767077,0.0001608492,0.00095419656,0.000034592817,0.000036338566,6.00149e-7,0.0016906719,0.000012896189,0.0016655818,0.7776831,0.0025997611,0.21509375],"study_design_scores_gemma":[0.0010602421,0.00015826889,0.006271394,0.00002484693,0.000016524398,0.000011552658,0.000046820194,0.6822977,0.012168803,0.28557593,0.012168267,0.00019965746],"about_ca_topic_score_codex":0.00012435284,"about_ca_topic_score_gemma":0.0000037451691,"teacher_disagreement_score":0.68228483,"about_ca_system_score_codex":0.000003606795,"about_ca_system_score_gemma":0.000014462367,"threshold_uncertainty_score":0.11290982},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9208582,0.000025193416,0.07848842,0.000087879846,0.000105971354,0.00021047285,0.000030905892,0.000058423084,0.00013454302],"genre_scores_gemma":[0.9867591,0.00005794319,0.011137911,0.000009233725,0.00007216408,8.855411e-7,0.000008835911,0.000008586959,0.0019452876],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979068,0.0002692045,0.00014812553,0.00057235995,0.0007123616,0.00039111843],"domain_scores_gemma":[0.9987605,0.00008869221,0.00012142702,0.00057827594,0.00018953235,0.00026152757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036504492,0.0001532082,0.00022060727,0.00020947568,0.00087659137,0.00010752672,0.0009954287,0.000088083034,0.0000074848413],"category_scores_gemma":[0.0000035873425,0.00015227773,0.00005699653,0.00017175969,0.00035628502,0.0011732818,0.0006078205,0.00044803027,0.0000144764645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000644792,0.0023852598,0.064792804,0.0005609468,0.00035980178,0.021177692,0.028326599,0.00034671742,0.058565393,0.0027220335,0.005266009,0.81485194],"study_design_scores_gemma":[0.003800044,0.008572616,0.63414806,0.0014052938,0.000040843584,0.001984617,0.0065392377,0.16068082,0.17653494,0.0014309725,0.0031064975,0.0017560606],"about_ca_topic_score_codex":0.002049549,"about_ca_topic_score_gemma":0.0000038238645,"teacher_disagreement_score":0.81309587,"about_ca_system_score_codex":0.00005367916,"about_ca_system_score_gemma":0.00006859853,"threshold_uncertainty_score":0.67421204},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45685983,0.00061468047,0.5140634,0.01002019,0.0026856554,0.003322613,0.00027742045,0.0015110816,0.010645099],"genre_scores_gemma":[0.952934,0.000076146665,0.044772346,0.0006385566,0.000121449084,0.00025999718,0.000073186275,0.0000633327,0.0010609372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996923,0.00022318983,0.00047710247,0.0011019268,0.00047519404,0.0007995536],"domain_scores_gemma":[0.9978022,0.0002321976,0.00016317508,0.0014066753,0.000088502806,0.0003072566],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038571085,0.00044528098,0.00044050606,0.00045314527,0.00027688657,0.00043298583,0.0011530737,0.00019337423,0.00015343683],"category_scores_gemma":[0.000029639818,0.00037873397,0.00015426138,0.0008690794,0.00012620003,0.0015663056,0.000667551,0.00047986346,0.0010640628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002476123,0.004760347,0.003463912,0.00029134026,0.0005396834,0.02727442,0.0064705177,0.008308977,0.08255586,0.03882865,0.023899274,0.8033594],"study_design_scores_gemma":[0.0012960985,0.00040084144,0.0042051924,0.000112347836,0.000010680278,0.001130639,0.00007700974,0.98470974,0.0008640258,0.0056759333,0.00067295245,0.0008445231],"about_ca_topic_score_codex":0.0017230697,"about_ca_topic_score_gemma":0.000087202076,"teacher_disagreement_score":0.9764008,"about_ca_system_score_codex":0.00015929693,"about_ca_system_score_gemma":0.000067835696,"threshold_uncertainty_score":0.9998665},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7259833,0.0006311177,0.21238576,0.001412252,0.021086369,0.00050024525,0.000009692991,0.00088329555,0.03710795],"genre_scores_gemma":[0.99159485,0.000005260011,0.007907655,0.00026233515,0.000039362192,0.000010548172,0.00000938562,0.0000072152807,0.0001634087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990653,0.000046549518,0.0001266467,0.0002059547,0.00026614923,0.00028940052],"domain_scores_gemma":[0.99918497,0.00004866246,0.000056301553,0.00054482115,0.000034704794,0.00013053116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021065281,0.00010979617,0.000098564706,0.000051763618,0.00013611525,0.000090217174,0.00047833912,0.000054158394,0.000019157853],"category_scores_gemma":[0.000019397294,0.00009510851,0.000035728022,0.00018112188,0.000015231089,0.0009785792,0.00018365266,0.00011575312,0.00053343456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045749944,0.00014967275,0.00087616924,0.0000020069176,0.000005126222,0.000002026207,0.00018748657,0.000007846347,0.00023720034,0.9789487,0.011150294,0.008428856],"study_design_scores_gemma":[0.00227748,0.0007058517,0.059071496,0.00007863486,0.000020064284,0.00004357217,0.000037459373,0.05907676,0.01708534,0.662428,0.19806936,0.0011059642],"about_ca_topic_score_codex":0.000008449518,"about_ca_topic_score_gemma":1.13574984e-7,"teacher_disagreement_score":0.31652072,"about_ca_system_score_codex":0.0000367741,"about_ca_system_score_gemma":0.000019158497,"threshold_uncertainty_score":0.68564004},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026684482,0.000038955724,0.97080225,0.0005862289,0.000254211,0.0010878382,0.00008206454,0.0003357124,0.00012823624],"genre_scores_gemma":[0.52897805,0.0000018500689,0.46915257,0.0009769755,0.00020282615,0.0002505354,0.00030895608,0.000029257726,0.00009895131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719536,0.00013742468,0.00044122458,0.0008237348,0.0003763766,0.0010258886],"domain_scores_gemma":[0.9979271,0.00045834857,0.00020115581,0.00070834835,0.00038279354,0.00032223022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004149379,0.000352487,0.0003404012,0.00016513988,0.0006156443,0.00050185865,0.001444481,0.000110433684,0.000066941255],"category_scores_gemma":[0.000044487973,0.0003445511,0.00014689079,0.00034196652,0.000097596174,0.0006759173,0.0002501634,0.00030905995,0.00007874432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012261396,0.0015195352,0.00010533185,0.000065130924,0.00015029636,0.000012242823,0.00047161028,0.013576011,0.0031061633,0.32574788,0.0045054844,0.6506177],"study_design_scores_gemma":[0.0009161096,0.0011790413,0.0033884428,0.00001042078,0.000008419945,0.000031604523,0.000009558727,0.77366346,0.000286406,0.21880548,0.0013698089,0.00033126207],"about_ca_topic_score_codex":0.00016701914,"about_ca_topic_score_gemma":0.00006780518,"teacher_disagreement_score":0.76008743,"about_ca_system_score_codex":0.00044743504,"about_ca_system_score_gemma":0.0007388256,"threshold_uncertainty_score":0.99990064},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627566,0.0003377104,0.033839058,0.00086471223,0.0005963877,0.00030572765,0.000005501652,0.00023961619,0.0010546957],"genre_scores_gemma":[0.9887284,0.0000067836527,0.0109413015,0.00009602587,0.000015519869,0.000026644724,0.000012567782,0.000009952833,0.00016277577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998877,0.0000573566,0.00019645804,0.00037402494,0.00023320953,0.00026197228],"domain_scores_gemma":[0.99901104,0.00021101967,0.00007981692,0.00047076764,0.00007400783,0.00015336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017461856,0.00013700634,0.00017236092,0.00006809566,0.00021091373,0.00025418997,0.0005433573,0.0000886253,0.000020455414],"category_scores_gemma":[0.000080205544,0.00012355528,0.00002722942,0.00027522762,0.00003751886,0.0011580958,0.0004455547,0.00017801649,0.00015400273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012359461,0.00004067105,0.18208086,0.000015810834,0.000010039365,0.0000043685263,0.0002033416,0.000010760724,0.00023872948,0.80101585,0.004920279,0.011458066],"study_design_scores_gemma":[0.0004128827,0.00004261833,0.50172466,0.000017409011,0.0000041571775,0.000002882849,0.0000069268976,0.029162955,0.00008856995,0.46725032,0.0011328316,0.0001538073],"about_ca_topic_score_codex":0.00013886293,"about_ca_topic_score_gemma":5.649516e-7,"teacher_disagreement_score":0.33376554,"about_ca_system_score_codex":0.000026472657,"about_ca_system_score_gemma":0.000028845283,"threshold_uncertainty_score":0.5038438},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010343954,0.00008707904,0.9967006,0.00046446582,0.0003843175,0.00015240956,0.000064497086,0.00013595061,0.00097628904],"genre_scores_gemma":[0.20221975,0.00001836343,0.79595834,0.0005201433,0.00031223393,0.000010054728,0.00013488074,0.000011738659,0.0008144976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989171,0.000025864314,0.00012415845,0.00048378334,0.00021574608,0.0002333282],"domain_scores_gemma":[0.9977994,0.00019025634,0.000052289543,0.001818764,0.000051319326,0.00008796048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025392562,0.00010844283,0.00013433567,0.00013222585,0.000114474926,0.00019260577,0.0022054003,0.00004774546,0.000029325502],"category_scores_gemma":[0.00013488565,0.000077558594,0.000028221246,0.0003319547,0.000016400834,0.00085194764,0.0011740027,0.000059439586,0.000022910392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000133394515,0.00006847597,0.0002918306,0.000051308878,0.000017419427,0.0000017367768,0.00006567279,0.0005950499,0.0003329626,0.21862625,0.21520649,0.5647295],"study_design_scores_gemma":[0.00038790933,0.00004845573,0.0012637087,0.000007170674,0.0000036186796,0.000003666804,0.0000034074424,0.8968595,0.0012426848,0.010725129,0.08929497,0.00015977745],"about_ca_topic_score_codex":0.00017936146,"about_ca_topic_score_gemma":0.000029757563,"teacher_disagreement_score":0.89626443,"about_ca_system_score_codex":0.000009655539,"about_ca_system_score_gemma":0.000024720013,"threshold_uncertainty_score":0.4098219},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05985162,0.00025843942,0.78900814,0.014616881,0.0022164544,0.0007208008,0.0003371208,0.0007081322,0.13228244],"genre_scores_gemma":[0.96418095,0.0000014492034,0.03108429,0.0029268053,0.00017619669,0.000011989799,0.00022277462,0.000014729592,0.0013808367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830765,0.000069855705,0.00021821377,0.00047536383,0.0005210848,0.00040786312],"domain_scores_gemma":[0.9978467,0.00013170158,0.00007507349,0.0004672437,0.00042183982,0.0010574049],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025975687,0.00018734859,0.0001815843,0.0005108961,0.00017408401,0.00029731734,0.00097364513,0.000092592534,0.00021633906],"category_scores_gemma":[0.00011724177,0.00018388682,0.00004720045,0.00067662995,0.00007400011,0.0004497735,0.00013488454,0.00019439554,0.0022370883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023355013,0.00016653075,0.0017255646,0.000013994258,0.00006106327,0.00033701205,0.00056589424,0.03857445,0.000017479135,0.50041175,0.26659587,0.19150706],"study_design_scores_gemma":[0.00071611797,0.00020945416,0.008213755,0.00004880253,0.000003986155,0.00004293059,0.000051684947,0.876018,0.00002705336,0.04138005,0.07281667,0.00047151797],"about_ca_topic_score_codex":0.0026444343,"about_ca_topic_score_gemma":0.00063965435,"teacher_disagreement_score":0.9043293,"about_ca_system_score_codex":0.00021961724,"about_ca_system_score_gemma":0.00219008,"threshold_uncertainty_score":0.9985398},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039094295,0.000046275116,0.95291376,0.0007616746,0.0004546648,0.0001581603,0.0000045098386,0.00023234317,0.006334334],"genre_scores_gemma":[0.92836833,0.000016607333,0.070862375,0.00024570693,0.00013540534,0.000022493374,0.000011474583,0.000008793922,0.0003288287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814427,0.0002068869,0.00025570477,0.0006594326,0.00020732997,0.0005263531],"domain_scores_gemma":[0.998376,0.00020456749,0.000098251396,0.0009826416,0.00016557911,0.00017294871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004894932,0.00019562231,0.00025022548,0.00011622626,0.00020813465,0.00018274535,0.0016527795,0.000112836635,0.000057453628],"category_scores_gemma":[0.000108615386,0.0001710603,0.000048541515,0.00022267483,0.00013370228,0.0004736647,0.0010786105,0.00036399544,0.00016157003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032163774,0.000120407385,0.0030198733,0.000029115707,0.000034164386,0.000027519744,0.00043729093,0.00028762163,0.015727978,0.65435094,0.00076649,0.32516643],"study_design_scores_gemma":[0.0014521912,0.00034480033,0.012329524,0.000032647768,0.0000070997366,0.000059856615,0.000020247504,0.9648409,0.00471157,0.0071912627,0.008548785,0.00046109932],"about_ca_topic_score_codex":0.00025604473,"about_ca_topic_score_gemma":0.00003010854,"teacher_disagreement_score":0.9645533,"about_ca_system_score_codex":0.000023115426,"about_ca_system_score_gemma":0.00013065946,"threshold_uncertainty_score":0.69756365},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014585338,0.000017832897,0.9801157,0.0030217478,0.00035362938,0.00013736554,0.000001995471,0.00023621894,0.0015301489],"genre_scores_gemma":[0.6872209,0.000006948693,0.31227684,0.0003423348,0.00011988125,0.0000023048867,2.6199947e-7,0.000005727042,0.000024815561],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99702656,0.00007416387,0.0002175178,0.0008729924,0.0011895694,0.0006191979],"domain_scores_gemma":[0.9978685,0.00021329465,0.00006709773,0.0012904993,0.00019444032,0.00036619065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010372022,0.00018396843,0.00019661845,0.00012901751,0.00035082846,0.00043268054,0.0028570907,0.00003993131,0.00007260238],"category_scores_gemma":[0.000044452754,0.00009492773,0.000039285766,0.00089210935,0.0023392255,0.001514149,0.0017407092,0.00011201555,0.0001668749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024103723,0.000037161222,0.000030214638,0.0000018531072,0.0000035296307,0.000013590061,0.000057314843,0.0000055256473,0.001811793,0.89434814,0.00006654185,0.10360022],"study_design_scores_gemma":[0.0027956734,0.0029056736,0.0068036984,0.0006189229,0.00002179294,0.00027310706,0.000006193448,0.14890139,0.091797955,0.74009466,0.0043227645,0.001458195],"about_ca_topic_score_codex":0.0000020793846,"about_ca_topic_score_gemma":1.6573509e-7,"teacher_disagreement_score":0.67263556,"about_ca_system_score_codex":0.00008104506,"about_ca_system_score_gemma":0.00014869095,"threshold_uncertainty_score":0.86189735},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021558865,0.00021463388,0.9962621,0.00022848714,0.00010015641,0.0002734147,0.000027234264,0.00009853799,0.00063957396],"genre_scores_gemma":[0.7011768,0.0005892934,0.29565132,0.00025708516,0.00028282587,0.00036525668,0.0006453578,0.000038604685,0.000993408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991154,0.00007666746,0.00023210951,0.00029512597,0.00014802213,0.0001326724],"domain_scores_gemma":[0.99884444,0.00010932004,0.00016936731,0.0006355505,0.00017237013,0.00006894725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005340186,0.0001347591,0.0001585371,0.00008796949,0.00024612626,0.000102415936,0.0004823998,0.000072414165,0.00003569854],"category_scores_gemma":[0.000015092202,0.000103891136,0.000022396762,0.00037580286,0.0002391932,0.00075748266,0.00018334192,0.00015612379,0.000011002256],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074619975,0.000043448712,0.000072437106,0.000019114554,0.000008171278,2.1375057e-7,0.00014703033,0.0000052865985,0.00083312736,0.7002062,0.00007896509,0.29857853],"study_design_scores_gemma":[0.0010894631,0.00024785427,0.005239478,0.00008013494,0.000106798056,0.00006508523,0.00043695443,0.022237528,0.047552515,0.7316783,0.19038655,0.0008793242],"about_ca_topic_score_codex":0.0000165224,"about_ca_topic_score_gemma":0.000012476319,"teacher_disagreement_score":0.70061076,"about_ca_system_score_codex":0.0000039141023,"about_ca_system_score_gemma":0.000038097314,"threshold_uncertainty_score":0.42365575},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038575132,0.000055061548,0.9947473,0.00013998606,0.0004229163,0.00011043376,0.0000058656474,0.00013648481,0.00052443705],"genre_scores_gemma":[0.36760527,4.1827042e-7,0.6319574,0.00022392957,0.00015769093,0.000012713406,0.0000066232374,0.0000037818932,0.00003216685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999209,0.000012494752,0.00013894477,0.00018159788,0.00017454385,0.00028342297],"domain_scores_gemma":[0.9993007,0.0002593333,0.000053005864,0.00022705278,0.00004871704,0.00011118112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017431387,0.0000842291,0.00008859004,0.000042297044,0.0001448485,0.00011874938,0.00038095884,0.000049711056,0.00003125807],"category_scores_gemma":[0.000050572206,0.00006932678,0.000044118417,0.00010696979,0.0000132361565,0.0008395001,0.00024869049,0.00007173226,0.000033465385],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049301143,0.000077471435,0.0026195722,0.000010996265,0.00000799544,9.998948e-7,0.0004136186,0.0005368203,0.000015066813,0.8470432,0.0018880131,0.14738128],"study_design_scores_gemma":[0.00033767367,0.00009738958,0.01073008,0.000040982075,0.0000042672987,0.000021124619,0.00004271209,0.900401,0.00034234187,0.07064876,0.01707554,0.00025812766],"about_ca_topic_score_codex":0.000003655626,"about_ca_topic_score_gemma":1.4517164e-7,"teacher_disagreement_score":0.8998642,"about_ca_system_score_codex":0.000015026893,"about_ca_system_score_gemma":0.000025573205,"threshold_uncertainty_score":0.2827064},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015808049,0.00045383166,0.4712552,0.0010353088,0.0017142426,0.00051243074,0.00025171114,0.00041733863,0.5227791],"genre_scores_gemma":[0.6671411,0.00070312514,0.11852506,0.00078812847,0.0071714725,0.00009815728,0.0010148142,0.00035577136,0.20420241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99605256,0.0008950298,0.00070871256,0.00094534457,0.00081772084,0.0005806095],"domain_scores_gemma":[0.9972094,0.0004421978,0.00063709106,0.00090288324,0.00033554746,0.00047287563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023881847,0.0006556847,0.00057584094,0.00028043744,0.0005362155,0.00051126786,0.0008548368,0.00080217066,0.00015654047],"category_scores_gemma":[0.000091397174,0.00065822114,0.00025005804,0.000059525584,0.0006623472,0.000611928,0.00041865426,0.0011391202,0.00015871586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014734906,0.00031271842,0.0025062142,0.00016134311,0.00021795604,0.00034042474,0.004107846,0.0033617092,0.0025058496,0.75941026,0.06056022,0.16636813],"study_design_scores_gemma":[0.0012508393,0.0003702491,0.0062199794,0.00091484416,0.000130641,0.0015733583,0.00008198762,0.23050646,0.0005420168,0.08504482,0.6726436,0.00072117854],"about_ca_topic_score_codex":0.0033029886,"about_ca_topic_score_gemma":0.00020966625,"teacher_disagreement_score":0.6743654,"about_ca_system_score_codex":0.0006539237,"about_ca_system_score_gemma":0.0011735578,"threshold_uncertainty_score":0.9995869},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9888307,0.000022044494,0.0040902165,0.0006080356,0.004847041,0.00017231841,0.000007747974,0.0000719713,0.0013499213],"genre_scores_gemma":[0.9929072,0.000004004747,0.006912545,0.00007430606,0.00000820794,0.000005805876,0.0000028370844,0.0000043591044,0.000080734986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913293,0.00005261826,0.00016288258,0.00022946189,0.00029030253,0.00013177887],"domain_scores_gemma":[0.99859613,0.00007218774,0.00012704154,0.0010624725,0.00009645591,0.000045683137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016171036,0.00007513442,0.00009669657,0.000025820942,0.000111627,0.000054370863,0.0011533647,0.00005013542,0.000011245365],"category_scores_gemma":[0.00009435567,0.000051199448,0.000050298095,0.00036909757,0.00006281562,0.00040900247,0.0005044743,0.00018907893,0.000013988723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022198237,0.00006058553,0.0048521925,0.0000048583806,0.0000046070413,0.0000034221162,0.0002595585,0.0000040106984,0.041478463,0.94223326,0.0020273072,0.009069505],"study_design_scores_gemma":[0.0006372242,0.000075439144,0.05984467,0.000043559794,0.000007485531,0.000028082577,0.000024819125,0.030816413,0.06271724,0.8423649,0.003226645,0.00021351154],"about_ca_topic_score_codex":0.000111190006,"about_ca_topic_score_gemma":0.0000043246137,"teacher_disagreement_score":0.09986835,"about_ca_system_score_codex":0.000009328099,"about_ca_system_score_gemma":0.000059374695,"threshold_uncertainty_score":0.21432577},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68908775,0.0022819713,0.19301589,0.0013822347,0.033117265,0.0011650122,0.000011765531,0.0028535402,0.0770846],"genre_scores_gemma":[0.9464302,0.00002117558,0.053241443,0.00011282345,0.000014307657,0.000011215001,0.000003732355,0.0000106952775,0.00015441254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989434,0.000037100515,0.00015828999,0.00038904863,0.00021905483,0.00025312087],"domain_scores_gemma":[0.99886376,0.00002103122,0.000066660745,0.00085586554,0.00010396704,0.000088702596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021524949,0.000118083364,0.00011770715,0.000086497246,0.0001451609,0.0000756271,0.0010175944,0.000045284334,0.000022721157],"category_scores_gemma":[0.00003679007,0.0001029229,0.000036610913,0.00045844106,0.000031996493,0.00072429056,0.00044397992,0.00012703493,0.00012686386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029403034,0.00010996192,0.0006044568,0.000006592005,0.0000076537335,0.00001877737,0.0005678297,4.3876085e-7,0.00025719457,0.9855598,0.0037907544,0.009073575],"study_design_scores_gemma":[0.000501599,0.00013045005,0.0071854056,0.000028036782,0.0000059203435,0.000018187438,0.000023274366,0.002500065,0.011215468,0.96938413,0.008692587,0.00031488453],"about_ca_topic_score_codex":0.00005680428,"about_ca_topic_score_gemma":4.8089436e-7,"teacher_disagreement_score":0.2573425,"about_ca_system_score_codex":0.000013307254,"about_ca_system_score_gemma":0.000041539424,"threshold_uncertainty_score":0.41970742},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029065236,0.00011090557,0.96603084,0.0018365594,0.00005989758,0.00015686438,0.00012757443,0.00009908971,0.0025130128],"genre_scores_gemma":[0.5699123,0.00018329493,0.42984018,0.000025997837,0.00000586701,0.000008256758,0.0000079096,0.0000030932033,0.000013092728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990203,0.00021207344,0.00023988157,0.00021519052,0.00015666483,0.00015589583],"domain_scores_gemma":[0.99739856,0.000570762,0.000090497044,0.0017164622,0.00014885959,0.00007487041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045319466,0.00009050237,0.00014490176,0.00007604777,0.00030159467,0.000065429835,0.0012649442,0.000054866843,0.000008411893],"category_scores_gemma":[0.000100955665,0.0000668682,0.00002149304,0.00022374178,0.0006366302,0.00057074684,0.0009104749,0.00013953539,0.0000035961073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026948892,0.00004678712,0.0005413228,0.000013335739,0.000017854198,2.3300137e-7,0.0004500669,0.000010320915,0.029468926,0.87712896,0.00003829319,0.092281185],"study_design_scores_gemma":[0.0036340219,0.00036694997,0.009210239,0.001138381,0.00007671826,0.0005308478,0.0013469086,0.70047885,0.02566246,0.2380919,0.018100988,0.0013617246],"about_ca_topic_score_codex":0.00023963534,"about_ca_topic_score_gemma":0.000014158794,"teacher_disagreement_score":0.70046854,"about_ca_system_score_codex":0.000024153343,"about_ca_system_score_gemma":0.00009718601,"threshold_uncertainty_score":0.2726806},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07696323,0.0003904802,0.90732586,0.0027774798,0.0007501789,0.00047652356,0.0000064250667,0.00047463796,0.0108351875],"genre_scores_gemma":[0.5808532,0.00011993502,0.41506115,0.0018367752,0.00015602465,0.00006293628,0.00001304916,0.000011537004,0.0018853638],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99931115,0.000019007579,0.0000997273,0.00027186083,0.00013194363,0.00016629035],"domain_scores_gemma":[0.99939317,0.000026123866,0.000027546866,0.00040649573,0.000044774275,0.000101890895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007890953,0.00008134297,0.00008164123,0.000040306582,0.00009297303,0.0002321846,0.00041023735,0.000034988094,0.00011053797],"category_scores_gemma":[0.000009342819,0.000055218352,0.000018828241,0.0001227584,0.00003566949,0.0013352878,0.00046383188,0.00006866998,0.00013267098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021057674,0.00020446115,0.0075444584,0.00002923615,0.00001598344,0.000010529766,0.00026219315,0.0000026040777,0.001057563,0.23021375,0.23404773,0.52660936],"study_design_scores_gemma":[0.0013111418,0.00046415735,0.33214605,0.00006090029,0.000009782873,0.00011398339,0.000058055262,0.32786992,0.004344003,0.2265677,0.10597477,0.0010795462],"about_ca_topic_score_codex":0.0003119213,"about_ca_topic_score_gemma":0.0000050136236,"teacher_disagreement_score":0.52552986,"about_ca_system_score_codex":0.000004377976,"about_ca_system_score_gemma":0.0000124112985,"threshold_uncertainty_score":0.2251739},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010607828,0.00014999832,0.98679715,0.0010685688,0.0009141585,0.000215724,0.00002139225,0.000051987412,0.00017316216],"genre_scores_gemma":[0.38280094,0.00013270398,0.6154502,0.00016265572,0.00042706355,0.00009590281,0.0000013568647,0.000023151977,0.00090604567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988482,0.0000042700144,0.000180191,0.0003027892,0.0002373898,0.00042717386],"domain_scores_gemma":[0.99912024,0.000083837294,0.000060539805,0.00022591371,0.00026714546,0.00024231338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008306421,0.00011016354,0.00012355573,0.00014584704,0.000495366,0.00038244147,0.00077258685,0.000030979303,0.000005758414],"category_scores_gemma":[0.00014081858,0.000070896764,0.00004497103,0.00021473836,0.00004385293,0.0033559487,0.00008366568,0.00006548042,0.0000023012706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017455517,0.00001751686,0.00003975325,0.000047222016,0.000013047275,0.0000052125324,0.00029090926,0.00026556387,0.061758187,0.016843881,0.0068352856,0.913866],"study_design_scores_gemma":[0.00092223386,0.00024653677,0.00031242394,0.00028163398,0.0000061724745,0.00019335352,0.000036371395,0.9395801,0.02147064,0.00784323,0.028730063,0.00037723914],"about_ca_topic_score_codex":0.0000014438399,"about_ca_topic_score_gemma":2.6023656e-7,"teacher_disagreement_score":0.93931454,"about_ca_system_score_codex":0.000053518153,"about_ca_system_score_gemma":0.00014626264,"threshold_uncertainty_score":0.3810005},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002401642,0.000087284694,0.99206233,0.0043290164,0.00082023867,0.00014896702,9.687909e-7,0.000038202044,0.0001113606],"genre_scores_gemma":[0.004405949,0.0000032128476,0.99400777,0.0012903699,0.00025029332,0.000010662836,0.000006566736,0.000004907775,0.000020249305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983282,0.00071160094,0.000190937,0.00042519558,0.0000805171,0.0002635157],"domain_scores_gemma":[0.99889874,0.00008611367,0.00003897357,0.00088356674,0.000027390646,0.00006520419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034596717,0.000090117464,0.00011086328,0.000106152365,0.00006170613,0.000036267043,0.0008671091,0.0000722931,0.000008515343],"category_scores_gemma":[0.000121881196,0.000060688624,0.000025849984,0.00035377798,0.0000308114,0.0000780969,0.0003391398,0.00012197848,0.000009888095],"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":[0.00000697005,0.000037952537,0.000100086094,8.4369026e-7,0.000004098367,0.0000120035675,0.00020685689,0.0002561149,0.4286698,0.08485854,0.00029778585,0.48554894],"study_design_scores_gemma":[0.00027322464,0.00048692676,0.0028450105,0.0000050919557,0.0000047508856,0.00004449573,0.00007914285,0.016336171,0.49845368,0.030159753,0.45100093,0.00031082032],"about_ca_topic_score_codex":0.000039090708,"about_ca_topic_score_gemma":0.000013683814,"teacher_disagreement_score":0.48523813,"about_ca_system_score_codex":0.000034691082,"about_ca_system_score_gemma":0.000013527635,"threshold_uncertainty_score":0.24748102},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49053454,0.00001889614,0.5064001,0.00020974506,0.000109643035,0.0001552959,0.000121867146,0.00004867282,0.0024012637],"genre_scores_gemma":[0.84501994,0.000008211472,0.15449515,0.00010359488,0.0000889582,0.00015262506,0.00006514915,0.000038942107,0.000027437452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767184,0.000042525582,0.00064754445,0.00041409375,0.0008933383,0.0003306291],"domain_scores_gemma":[0.99762887,0.0004480367,0.0006827911,0.0010591721,0.000086807144,0.00009432595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054839364,0.00023871765,0.00021792075,0.000041517247,0.00030206115,0.00014297504,0.0011923023,0.00014688083,0.00001178863],"category_scores_gemma":[0.00008468312,0.00015268021,0.00020217904,0.00030667338,0.00019985074,0.00028223026,0.00089195947,0.00016443207,0.0001227887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034322813,0.00015629512,0.00001395241,0.00026751822,0.00006616217,0.0000015690601,0.0016897375,0.0013762275,0.00060349994,0.9937534,0.00044231245,0.0015950487],"study_design_scores_gemma":[0.00041748385,0.000053754447,0.00022956048,0.0002600166,0.00006535514,0.000030005891,0.00030139566,0.9842518,0.0024025394,0.011369158,0.00041603128,0.00020292809],"about_ca_topic_score_codex":0.000038716258,"about_ca_topic_score_gemma":0.000012026903,"teacher_disagreement_score":0.9828755,"about_ca_system_score_codex":0.000012495385,"about_ca_system_score_gemma":0.00013530125,"threshold_uncertainty_score":0.6226118},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025403759,0.000013634706,0.96912867,0.0025689234,0.00069029257,0.00009167723,0.00000257685,0.0003482126,0.0017522338],"genre_scores_gemma":[0.74145925,0.0000036480276,0.25799555,0.00038570678,0.00012626225,0.0000032660068,2.7256058e-7,0.0000053816407,0.000020680589],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975173,0.00008302043,0.0002385224,0.0008015879,0.00075240637,0.00060716964],"domain_scores_gemma":[0.99802876,0.00027152905,0.000056405042,0.0011629916,0.00014607391,0.00033423663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010443589,0.00017117828,0.00017261006,0.00015298693,0.0004715766,0.00042799735,0.0034541688,0.000044171935,0.00009553515],"category_scores_gemma":[0.000058113055,0.000095010786,0.000056490884,0.0007514118,0.0017131218,0.0015558673,0.0023280387,0.00010817063,0.0003061704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029372345,0.00002364348,0.000018399336,0.0000013619857,0.0000012100402,0.000010655919,0.000092150454,0.0000053917715,0.005721207,0.81815577,0.00010174679,0.17586553],"study_design_scores_gemma":[0.00060941925,0.00018053643,0.0026167438,0.00013556755,0.000003277781,0.000110257126,0.0000033041738,0.34483302,0.013217252,0.63682497,0.001004673,0.00046099233],"about_ca_topic_score_codex":0.000003165789,"about_ca_topic_score_gemma":1.9008988e-7,"teacher_disagreement_score":0.71605545,"about_ca_system_score_codex":0.000055869248,"about_ca_system_score_gemma":0.000094568175,"threshold_uncertainty_score":0.6418763},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046338115,0.00008282806,0.951539,0.00015197785,0.0006913218,0.00030611048,0.000111300345,0.00025474126,0.0005246153],"genre_scores_gemma":[0.99479026,0.00010809525,0.0039607873,0.00006608389,0.000118999465,0.0000017233316,0.0001950016,0.00001855846,0.00074051454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805564,0.00012668318,0.0002219836,0.0011049192,0.00015370995,0.0003370401],"domain_scores_gemma":[0.99826616,0.00010026249,0.00024711693,0.0010249406,0.00015099971,0.00021054922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018759415,0.0002959197,0.00026815463,0.00023517366,0.0003534247,0.0002765727,0.0014595999,0.00024641122,0.00003266334],"category_scores_gemma":[0.000031958625,0.00028658082,0.00008312345,0.00037867433,0.000037800466,0.00086402206,0.002681,0.00028695652,0.00011356811],"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":[0.0002212251,0.0006221283,0.018125987,0.0004687481,0.00030324515,0.00047459244,0.0017599282,0.5403416,0.033655632,0.24729864,0.06688927,0.089839004],"study_design_scores_gemma":[0.0005814264,0.000060660495,0.0006458113,0.00079912296,0.000030470703,0.0000034374757,0.000025381365,0.97844046,0.005273562,0.008565765,0.0048318855,0.000741998],"about_ca_topic_score_codex":0.000071292394,"about_ca_topic_score_gemma":0.00000881861,"teacher_disagreement_score":0.9484521,"about_ca_system_score_codex":0.0002956005,"about_ca_system_score_gemma":0.00010023367,"threshold_uncertainty_score":0.99995863},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90241754,0.000010341452,0.08913787,0.0039022423,0.0039420305,0.0004572272,0.000026679141,0.000077680525,0.000028413404],"genre_scores_gemma":[0.99806154,0.0000045812335,0.0011671168,0.00060414465,0.000039867267,0.000046506335,0.000031708223,0.000008424251,0.000036118778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988163,0.00006163152,0.00021668726,0.00032757112,0.00033193853,0.00024583953],"domain_scores_gemma":[0.9985449,0.000055745237,0.00015691172,0.0008959103,0.00020427714,0.00014228656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003371057,0.00013505973,0.00018926644,0.00008988508,0.00018141468,0.00013471404,0.0010422958,0.00008170648,0.000012531989],"category_scores_gemma":[0.000102175596,0.000099424455,0.000046281464,0.00048839126,0.000022311235,0.00044129413,0.00046269267,0.00017941152,0.00008315233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001660641,0.00021763325,0.0067685065,0.000011338767,0.000012433557,0.0000044335643,0.00081884826,0.0000025157851,0.081709825,0.89522177,0.001167635,0.014048447],"study_design_scores_gemma":[0.0016313776,0.00068036735,0.7613425,0.00017910704,0.00002110931,0.000016896964,0.00008214665,0.012460109,0.06694089,0.08520015,0.07076232,0.00068297546],"about_ca_topic_score_codex":0.000040496165,"about_ca_topic_score_gemma":0.000022716666,"teacher_disagreement_score":0.81002164,"about_ca_system_score_codex":0.00002475627,"about_ca_system_score_gemma":0.000028355,"threshold_uncertainty_score":0.40544114},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95282954,0.000030490604,0.008679268,0.015835153,0.0069339424,0.00042201206,0.00001773065,0.000118452386,0.01513343],"genre_scores_gemma":[0.9966128,0.000017605542,0.002416257,0.00017675376,0.0005225343,0.000018383196,0.000007784513,0.000010563515,0.000217332],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805516,0.000020190873,0.00020176181,0.0004038209,0.0011369524,0.00018211592],"domain_scores_gemma":[0.99832106,0.000053848307,0.0001223884,0.00020171267,0.0012403835,0.000060633316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027754973,0.00012223715,0.00012744845,0.000048010963,0.00019493098,0.00026014773,0.0011641145,0.000058913876,0.000012438899],"category_scores_gemma":[0.000066481916,0.00008329333,0.000060302857,0.0003927167,0.000043067783,0.00053239235,0.0006716879,0.00022034226,0.000008429983],"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":[0.00013399236,0.0004732624,0.0022447857,0.000014923221,0.00006975929,0.0000039028873,0.00045706035,0.0004298382,0.5536497,0.43645564,0.0044239014,0.0016432011],"study_design_scores_gemma":[0.0008483897,0.00018634171,0.0007670566,0.00008514601,0.000006421759,0.000018653569,0.000022729884,0.04258331,0.9496563,0.0027912573,0.0029037825,0.00013058071],"about_ca_topic_score_codex":0.000051590254,"about_ca_topic_score_gemma":0.0000014901301,"teacher_disagreement_score":0.43366438,"about_ca_system_score_codex":0.0001300206,"about_ca_system_score_gemma":0.00013835022,"threshold_uncertainty_score":0.33966035},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015231121,0.000008432409,0.9948446,0.000104783736,0.00042128807,0.00014514256,0.000021076221,0.0001226966,0.0028088428],"genre_scores_gemma":[0.19794689,0.000002323699,0.80126315,0.00056293956,0.00006772754,0.000010867501,0.000017545612,0.0000113171745,0.00011721363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987535,0.00007235009,0.00021852193,0.0003861425,0.0003312357,0.0002382517],"domain_scores_gemma":[0.9984424,0.000041209198,0.00012915189,0.0011709316,0.000109522916,0.00010679122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023095505,0.00014719444,0.00013863629,0.00006528185,0.00023548359,0.00006113519,0.0012255515,0.000071317736,0.00016676002],"category_scores_gemma":[0.00001323808,0.000094035626,0.00008680479,0.00028664418,0.00006809254,0.0005646578,0.00028207764,0.00013704575,0.00002282013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031512256,0.0009995451,0.0004930536,0.000016378659,0.000018866058,0.0000104879755,0.0008354837,0.00020672075,0.007596284,0.003639644,0.0027691892,0.9833828],"study_design_scores_gemma":[0.00040008922,0.00024548417,0.003921945,0.000032499833,0.0000052866603,0.0000021264495,0.000036217683,0.9166553,0.07729,0.0006125658,0.00066278543,0.00013572453],"about_ca_topic_score_codex":0.00026217726,"about_ca_topic_score_gemma":0.0000038827243,"teacher_disagreement_score":0.9832471,"about_ca_system_score_codex":0.00002463162,"about_ca_system_score_gemma":0.000073454496,"threshold_uncertainty_score":0.38346615},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070101514,0.024144279,0.8924686,0.0024354542,0.0052843085,0.0008457819,0.00021621877,0.0005634198,0.0039404673],"genre_scores_gemma":[0.1449197,0.003292716,0.8474748,0.00075391395,0.0012556992,0.00028596717,0.00031635675,0.000078589386,0.0016222796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975728,0.00013122914,0.00042310986,0.0010339322,0.00039558168,0.00044336845],"domain_scores_gemma":[0.998341,0.00013920691,0.00013065927,0.001156281,0.000098575,0.00013425491],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026994883,0.0003834176,0.0005399732,0.00024985863,0.00011075334,0.0007843581,0.0011741432,0.00033153116,0.00002686829],"category_scores_gemma":[0.000036169768,0.0003886388,0.00010135001,0.00020427081,0.000114131566,0.0005865348,0.004302324,0.00076272414,0.000008066376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035327837,0.00066584034,0.0041677905,0.0017401921,0.0002445135,0.002661111,0.013738246,0.00027822034,0.00031359517,0.04482328,0.009176251,0.9221556],"study_design_scores_gemma":[0.00488173,0.00032969375,0.052102488,0.004933999,0.00012858523,0.00066267163,0.0036173805,0.76385814,0.004211473,0.121310174,0.03775396,0.0062097213],"about_ca_topic_score_codex":0.0009706804,"about_ca_topic_score_gemma":0.00008298827,"teacher_disagreement_score":0.9159459,"about_ca_system_score_codex":0.00006963328,"about_ca_system_score_gemma":0.00020502425,"threshold_uncertainty_score":0.99985653},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015926304,0.000026099506,0.9890481,0.0009836768,0.00045979844,0.00007877625,0.000012463001,0.00017987547,0.007618563],"genre_scores_gemma":[0.03550022,0.00007414471,0.96289504,0.00075176725,0.00013476009,0.00000601741,0.000005565042,0.000010314966,0.00062217243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917096,0.000012976666,0.00024183227,0.000114817674,0.00022883376,0.00023057612],"domain_scores_gemma":[0.9990648,0.00009126456,0.000118412136,0.0005725132,0.000054478096,0.000098535136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016575723,0.0000985333,0.00009833964,0.000062517436,0.00011874747,0.0001519373,0.0007825424,0.000043603373,0.000027330629],"category_scores_gemma":[0.000077744575,0.000057420526,0.00003933795,0.00013324399,0.000033271026,0.0019409138,0.00041764978,0.000051667583,0.0006562853],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034440766,0.000028368417,0.00014733238,0.00002059234,0.000011591921,0.00000807387,0.0013092723,0.0000054659067,0.0003509413,0.090192944,0.04403867,0.8638833],"study_design_scores_gemma":[0.0019866305,0.00030190515,0.002878503,0.0007247524,0.000014834663,0.0000920765,0.00034515947,0.31087983,0.009551945,0.025545554,0.64654464,0.0011341504],"about_ca_topic_score_codex":0.0000043204604,"about_ca_topic_score_gemma":7.269779e-7,"teacher_disagreement_score":0.86274916,"about_ca_system_score_codex":0.00003346915,"about_ca_system_score_gemma":0.000039511564,"threshold_uncertainty_score":0.84354395},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009585362,0.00074857747,0.9875603,0.00086928695,0.0010066046,0.000060019287,9.247857e-7,0.00013856593,0.000030412368],"genre_scores_gemma":[0.43929708,0.00004896573,0.5598053,0.00014678559,0.00065271923,0.0000017244352,2.0998621e-7,0.000010896699,0.000036346828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786514,0.00003858417,0.00042803978,0.0004101754,0.00079190615,0.0004661837],"domain_scores_gemma":[0.9985713,0.00044566186,0.000270136,0.0002914104,0.00009889753,0.00032260263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046804736,0.00021512566,0.00029945356,0.00037529666,0.00015866297,0.00036450144,0.0019364856,0.000064117296,0.000015194712],"category_scores_gemma":[0.000063237174,0.00013267674,0.00014229112,0.0010103771,0.000051302468,0.0017524133,0.00023600778,0.00022185057,0.0000072121634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000373783,0.00016998795,0.002114563,0.000027270231,0.00006744131,0.00016467711,0.00020026183,0.11810322,0.0073026842,0.0077583753,0.007049928,0.8570042],"study_design_scores_gemma":[0.0007853166,0.00064629246,0.005461765,0.00032664873,0.000010676967,0.00053607306,7.8120894e-7,0.9751737,0.008251071,0.0007364808,0.0077268467,0.00034435472],"about_ca_topic_score_codex":0.000006935181,"about_ca_topic_score_gemma":1.6050505e-7,"teacher_disagreement_score":0.85707045,"about_ca_system_score_codex":0.000061487204,"about_ca_system_score_gemma":0.00032841944,"threshold_uncertainty_score":0.54104006},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019912008,0.00012134336,0.9762521,0.00006934129,0.0011554278,0.00044530764,0.0001252103,0.00029366053,0.0016256092],"genre_scores_gemma":[0.61168814,0.00035377024,0.3786078,0.00029513665,0.00047969294,0.000006001271,0.00035882392,0.00006209706,0.008148514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980519,0.000048858823,0.00021709566,0.0011972933,0.00008603183,0.00039884142],"domain_scores_gemma":[0.9978512,0.000069506204,0.00025063189,0.0014233625,0.00023441073,0.00017089226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020132813,0.00031566274,0.00032006943,0.00018295672,0.00022333005,0.00015557974,0.0023402278,0.0002969951,0.000037301863],"category_scores_gemma":[0.000015273816,0.0003212723,0.00020925568,0.00028118596,0.00006603097,0.0005249964,0.0031547877,0.0004386672,0.00004430842],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002503251,0.0017143756,0.00072631,0.0006626145,0.00042743058,0.00062218227,0.0007793238,0.053759485,0.00028292046,0.89843947,0.015268315,0.027067253],"study_design_scores_gemma":[0.00083772803,0.00015996868,0.00017520566,0.00028631708,0.00008057456,0.0000047014746,0.000015553487,0.7779612,0.00016441222,0.18672036,0.032827076,0.00076688966],"about_ca_topic_score_codex":0.00014094505,"about_ca_topic_score_gemma":0.00003725253,"teacher_disagreement_score":0.72420174,"about_ca_system_score_codex":0.00010406167,"about_ca_system_score_gemma":0.00021294222,"threshold_uncertainty_score":0.99992394},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049706367,0.00004246117,0.98829746,0.0045418954,0.0004943193,0.00012476221,0.000008891656,0.0002651953,0.0012543907],"genre_scores_gemma":[0.9477995,0.00001747799,0.046068955,0.0055281417,0.00019414295,0.00002355816,0.000016103797,0.00003033903,0.00032176005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983972,0.00010997831,0.00017656734,0.0004683447,0.00034935764,0.0004986048],"domain_scores_gemma":[0.9988097,0.00021814532,0.0000891923,0.00074861466,0.00003989645,0.00009447735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031996833,0.00018027038,0.00017271283,0.00007018434,0.00015178573,0.00010094212,0.000772194,0.00006719806,0.000064809734],"category_scores_gemma":[0.000018324437,0.00011840425,0.000058840305,0.00020434964,0.000033534503,0.0004301386,0.00013405932,0.00017618998,0.00039384124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017622969,0.00024731224,0.0008463619,0.00011704125,0.000099648634,0.00010468423,0.0001346843,0.0013854041,0.13341054,0.59624803,0.23736817,0.02986192],"study_design_scores_gemma":[0.002655358,0.00032146776,0.00011225139,0.0005773863,0.00002195728,0.00004984111,0.000010906005,0.6159001,0.048031095,0.0006382627,0.3308851,0.0007962477],"about_ca_topic_score_codex":0.000020659427,"about_ca_topic_score_gemma":6.3767055e-7,"teacher_disagreement_score":0.9428289,"about_ca_system_score_codex":0.00037986255,"about_ca_system_score_gemma":0.00010944024,"threshold_uncertainty_score":0.50621635},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798232,0.00024763192,0.006198375,0.0026871576,0.0003081243,0.00052694004,0.00010448425,0.00014562737,0.009958503],"genre_scores_gemma":[0.9866727,0.000039911873,0.01254212,0.00021247433,0.000087459535,0.000040305156,0.0000042335596,0.000017198805,0.00038359076],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9979186,0.000025339015,0.0005276441,0.00045595664,0.0005896815,0.00048278132],"domain_scores_gemma":[0.9719942,0.00016231884,0.0007389475,0.0004457899,0.026479347,0.00017940374],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00035499482,0.000292485,0.00046165558,0.00015599489,0.00020636022,0.004034424,0.0044141365,0.00013781125,0.00007727228],"category_scores_gemma":[0.0034477466,0.0002109769,0.00015636462,0.00047660855,0.00031876328,0.017195307,0.002125952,0.00028905444,0.000019577907],"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":[0.0001884171,0.00089129846,0.08727375,0.0011181049,0.000337423,0.0000064448145,0.06746746,0.0001234649,0.36923295,0.12711132,0.16792624,0.17832315],"study_design_scores_gemma":[0.002697658,0.001276307,0.37495995,0.0024789064,0.00013234878,0.00018137589,0.004431719,0.17243533,0.2102273,0.04289107,0.18621622,0.0020718311],"about_ca_topic_score_codex":0.0004269905,"about_ca_topic_score_gemma":0.0000030742153,"teacher_disagreement_score":0.2876862,"about_ca_system_score_codex":0.00003140621,"about_ca_system_score_gemma":0.00016425007,"threshold_uncertainty_score":0.9969995},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.813346e-7,0.00038144813,0.32748488,0.00002101996,0.00061713957,0.00022242952,0.00011651851,0.00019576098,0.6709603],"genre_scores_gemma":[0.000006357108,0.00033445985,0.012762218,0.00010306124,0.0002784437,5.3860623e-7,0.000035480996,0.000033077857,0.9864464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978712,0.000041821575,0.00025244043,0.00074900227,0.0005965919,0.0004888998],"domain_scores_gemma":[0.99729127,0.00020254185,0.00029524954,0.0017339897,0.00022660142,0.0002503472],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030697093,0.0004291731,0.00032485247,0.00014301228,0.0008241879,0.00027047773,0.0030044252,0.0003752266,0.0000017941113],"category_scores_gemma":[0.0000070841884,0.00036227243,0.00023753569,0.000018174109,0.00028374046,0.00027305578,0.0023750882,0.0006922587,0.000049578404],"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":[0.000009430304,0.0000050132526,9.183342e-8,0.000007540731,0.000044807828,0.0004086334,0.000017615834,4.8672894e-7,0.0000025729362,0.756766,0.052319124,0.19041865],"study_design_scores_gemma":[0.0003079828,0.000049628845,0.0000070520296,0.00009302389,0.000039539318,0.00003899295,0.0000096615,0.0069744033,0.000059762002,0.00008182597,0.99189377,0.00044437186],"about_ca_topic_score_codex":0.00012217161,"about_ca_topic_score_gemma":0.0000020910288,"teacher_disagreement_score":0.93957466,"about_ca_system_score_codex":0.00016723853,"about_ca_system_score_gemma":0.00014501193,"threshold_uncertainty_score":0.99988294},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050754945,0.0012583291,0.054936863,0.0002427364,0.00042406813,0.0002751292,0.000027227336,0.00022910193,0.9425558],"genre_scores_gemma":[0.054504003,0.0001437022,0.8416622,0.0013359725,0.0006227293,0.000021299353,0.0000744254,0.00009142411,0.101544224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831045,0.00003604192,0.00042360727,0.0005462441,0.00036387812,0.00031975628],"domain_scores_gemma":[0.9977915,0.00005558273,0.00024889119,0.0016996695,0.00009277824,0.0001115433],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002589842,0.00032203642,0.00039506846,0.00007769291,0.00018142517,0.00028078083,0.0020597172,0.00043166665,0.000016843102],"category_scores_gemma":[0.000011980801,0.00031290328,0.00009170497,0.000030160769,0.00009589871,0.00019909184,0.0016920625,0.00066995516,0.0001886174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035930675,0.000011948908,0.000018724419,0.000010560166,0.000008157974,0.000019598203,0.00007241225,0.000019170611,0.000012387616,0.9701845,0.0015579433,0.028080996],"study_design_scores_gemma":[0.00044468543,0.000042990854,0.00019989924,0.00056760636,0.000009059067,0.00003815575,0.0000043959894,0.016687743,0.000041884618,0.7890272,0.19235393,0.0005824129],"about_ca_topic_score_codex":0.000502118,"about_ca_topic_score_gemma":0.00025728904,"teacher_disagreement_score":0.8410116,"about_ca_system_score_codex":0.00010643104,"about_ca_system_score_gemma":0.000109019275,"threshold_uncertainty_score":0.9999323},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068298504,0.000020744383,0.93028426,0.000070558395,0.00029257164,0.0005407562,0.000012129492,0.00015680879,0.00032366015],"genre_scores_gemma":[0.9838745,0.000029106044,0.015977187,0.00002941047,0.000030369643,0.00000395453,0.000022958246,0.0000072857897,0.000025247644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985998,0.00019722662,0.00026516567,0.0006042765,0.00012474965,0.0002087668],"domain_scores_gemma":[0.9976444,0.0002664256,0.00030526478,0.0014360845,0.00027043626,0.000077345525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073427975,0.00020738052,0.00024239827,0.000099258235,0.0003421539,0.000082612685,0.0013446413,0.00022736214,0.0000039043157],"category_scores_gemma":[0.000039596467,0.00017189015,0.0001829811,0.00030261592,0.00013220814,0.00027071236,0.0006120677,0.0004413988,0.000007908522],"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":[0.0001921827,0.0002242965,0.0010830506,0.00047239728,0.00007328137,0.00000559313,0.00017189041,0.6768389,0.00073587784,0.304602,0.000108977154,0.015491559],"study_design_scores_gemma":[0.00023768342,0.00007016315,0.0014218222,0.00012163997,0.00003825697,0.0000011234428,0.000013188297,0.88010126,0.0015429725,0.11481455,0.0013976987,0.00023962145],"about_ca_topic_score_codex":0.00013318913,"about_ca_topic_score_gemma":0.0000355714,"teacher_disagreement_score":0.915576,"about_ca_system_score_codex":0.00010904863,"about_ca_system_score_gemma":0.00021580316,"threshold_uncertainty_score":0.70094764},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015601985,0.000033771656,0.99592483,0.0013469739,0.000493494,0.00013950048,0.00010460565,0.00014331212,0.00025334163],"genre_scores_gemma":[0.5613422,0.000006996261,0.43769708,0.0002351373,0.00023419586,0.00000535159,0.00008426726,0.0000071140294,0.00038767964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990813,0.000019575227,0.00013926903,0.00041373837,0.00016554465,0.00018057074],"domain_scores_gemma":[0.998834,0.00009927532,0.000046990066,0.00089177175,0.000062329214,0.00006564651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012232248,0.00008673534,0.00009391224,0.00004378229,0.00012473247,0.0001276974,0.00146928,0.000032387747,0.00004266732],"category_scores_gemma":[0.0000254435,0.00004714299,0.000024635825,0.000072718525,0.000020137477,0.000928584,0.0009634647,0.000023031642,0.000028189092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011336185,0.00003496936,0.00012430556,0.000009210009,0.000022289767,0.0000047685253,0.000030524152,0.0000883174,0.0019372791,0.13630012,0.09789441,0.7635425],"study_design_scores_gemma":[0.0016920683,0.00010946777,0.013212393,0.000025135136,0.000012590183,0.00003988228,0.000010272502,0.8294323,0.0016990972,0.11203877,0.04133837,0.00038965337],"about_ca_topic_score_codex":0.00002710711,"about_ca_topic_score_gemma":0.0000043304026,"teacher_disagreement_score":0.829344,"about_ca_system_score_codex":0.000008849995,"about_ca_system_score_gemma":0.000039784656,"threshold_uncertainty_score":0.27303123},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015930581,0.014043211,0.35403585,0.0069507393,0.0066233305,0.0011763024,0.0002731872,0.0012271154,0.6140772],"genre_scores_gemma":[0.0075854002,0.0048980373,0.04706232,0.011386483,0.0040644174,0.000061172934,0.00039023111,0.00022441817,0.9243275],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970885,0.000041784177,0.00053715444,0.00072891463,0.0011058174,0.0004978604],"domain_scores_gemma":[0.99743605,0.000112809525,0.00012473128,0.0010355627,0.00010307031,0.0011877901],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058248045,0.0004444186,0.00051170815,0.00018708513,0.00015943524,0.00012651806,0.0013832714,0.0006168212,0.0012543504],"category_scores_gemma":[0.0000705787,0.00036424928,0.00010628308,0.000102128644,0.00015734187,0.00035520503,0.0022694091,0.0004553883,0.0005704309],"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":[0.00004758885,0.00005690786,0.000009483175,0.000093617826,0.000071816445,0.0009876426,0.0002435857,1.8990897e-7,0.0002647522,0.047098026,0.26642543,0.68470097],"study_design_scores_gemma":[0.00031051156,0.00065941736,0.000084584186,0.0003590672,0.000021063224,0.0009121614,0.0000025603608,0.0008160791,0.000012890989,0.0008164132,0.9955091,0.00049617275],"about_ca_topic_score_codex":0.00009669557,"about_ca_topic_score_gemma":0.0000018482821,"teacher_disagreement_score":0.72908366,"about_ca_system_score_codex":0.00006165765,"about_ca_system_score_gemma":0.00019435247,"threshold_uncertainty_score":0.99988097},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014606655,0.012992241,0.23492526,0.0057435785,0.00689671,0.0011687467,0.00029128228,0.0012750645,0.7352465],"genre_scores_gemma":[0.006180698,0.0047461796,0.049010444,0.011291449,0.004672601,0.00006047122,0.000596138,0.00024120601,0.9232008],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99710065,0.00003963435,0.00053783454,0.0007343394,0.0010813393,0.0005061892],"domain_scores_gemma":[0.9974659,0.00010748131,0.00011791677,0.0010584368,0.00007746386,0.0011728151],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005717848,0.00044958206,0.0005094427,0.0001909878,0.00016220476,0.00011865391,0.0013439694,0.0006473808,0.001553806],"category_scores_gemma":[0.000057964236,0.0003672852,0.00008824545,0.000094737195,0.00014593343,0.0003321177,0.0024033953,0.00045463402,0.0006825246],"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":[0.000048675254,0.00003816232,0.000007786774,0.00009388765,0.00007843379,0.0010509067,0.00019906012,1.9495253e-7,0.00049279886,0.04031836,0.28903735,0.66863436],"study_design_scores_gemma":[0.00029232507,0.00056068104,0.00006425226,0.00028664703,0.000021220822,0.00090423645,0.0000019708684,0.0008519886,0.000021767577,0.000674095,0.99582297,0.0004978492],"about_ca_topic_score_codex":0.00009609174,"about_ca_topic_score_gemma":0.0000017855821,"teacher_disagreement_score":0.7067856,"about_ca_system_score_codex":0.000061019775,"about_ca_system_score_gemma":0.0001804211,"threshold_uncertainty_score":0.9998779},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009710053,0.0000033591605,0.98492193,0.0024783367,0.0017940694,0.00020170232,0.000030278425,0.00025023005,0.00061004533],"genre_scores_gemma":[0.56770766,5.8432965e-7,0.43130904,0.00079289824,0.00017145365,0.000005240973,0.0000018293646,0.000006244721,0.000005040553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961554,0.00032894622,0.00026973282,0.0015966888,0.0010331842,0.0006160812],"domain_scores_gemma":[0.9947888,0.00044267412,0.000056007168,0.0038979137,0.0001972003,0.00061737216],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0036687132,0.00021037976,0.00019164768,0.00030775362,0.00050109247,0.0004940461,0.007630551,0.000042679683,0.000040162347],"category_scores_gemma":[0.00015127532,0.000121559395,0.00003597982,0.0011403136,0.00075560855,0.0007781297,0.004837737,0.00013679273,0.00039442212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010299386,0.00009304376,0.0000034622708,8.573631e-7,0.0000015335021,0.000005269985,0.00013913619,0.00074006314,0.0021418403,0.41339383,0.00022167747,0.583249],"study_design_scores_gemma":[0.00024237389,0.0006029518,0.00066568493,0.00007573508,0.0000039204756,0.000030557665,0.0000039284128,0.970352,0.0045070862,0.022346787,0.00091793475,0.00025106288],"about_ca_topic_score_codex":0.000008381557,"about_ca_topic_score_gemma":0.0000010758813,"teacher_disagreement_score":0.96961194,"about_ca_system_score_codex":0.00008523041,"about_ca_system_score_gemma":0.00013926573,"threshold_uncertainty_score":0.99773866},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023101127,0.000295268,0.97107816,0.005023526,0.0001251268,0.000114474686,0.000009403485,0.000025403056,0.00022753517],"genre_scores_gemma":[0.64801556,0.00013457467,0.35125667,0.00024951546,0.00016207818,0.000008436429,3.7056483e-7,0.000015671152,0.00015712492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986642,0.0000960052,0.0004044386,0.00014914505,0.00048501109,0.00020117789],"domain_scores_gemma":[0.99788535,0.00064472284,0.00043635652,0.00068702974,0.00022707213,0.00011944458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011945828,0.00012226267,0.0002076233,0.00007592264,0.00026827623,0.00017144134,0.0012998331,0.000025923255,0.0000071451295],"category_scores_gemma":[0.00027453605,0.00005198415,0.000057443165,0.0002857526,0.00007144581,0.00062870735,0.00022023536,0.00021363754,0.000021681319],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001637639,0.0011010305,0.0010326465,0.00027737918,0.00022811329,0.0013683626,0.025242051,0.0009626646,0.018554335,0.8659822,0.022749672,0.062337816],"study_design_scores_gemma":[0.005461359,0.005304022,0.0028116894,0.033802703,0.00030609625,0.017969947,0.007933632,0.08261039,0.06849507,0.63712746,0.13516481,0.003012807],"about_ca_topic_score_codex":0.0000037313573,"about_ca_topic_score_gemma":0.000027266582,"teacher_disagreement_score":0.6249144,"about_ca_system_score_codex":0.000060659033,"about_ca_system_score_gemma":0.0000689683,"threshold_uncertainty_score":0.24154349},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.447674,0.00017297566,0.5489865,0.00028158643,0.00088211766,0.00019874607,0.00010660525,0.0003097202,0.0013877547],"genre_scores_gemma":[0.6225443,0.00015108108,0.37481606,0.0003444695,0.0011049028,0.0003256388,0.00027200815,0.00020153413,0.00024000191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621964,0.00004379183,0.0009312519,0.00084582914,0.0011255569,0.0008339453],"domain_scores_gemma":[0.9967373,0.00035873533,0.0006788579,0.0017634658,0.00009273112,0.0003688914],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005243531,0.0005179705,0.0004665526,0.00010219448,0.00056324975,0.0006141387,0.0015720017,0.00039682488,0.000045349156],"category_scores_gemma":[0.00017560704,0.0004296851,0.00027649105,0.00035249602,0.00025654328,0.00073973654,0.0016209546,0.000394847,0.0012345202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065825465,0.00024670982,0.0000016829755,0.00019110223,0.000114127826,0.000020039837,0.0018282161,0.00009457956,0.0022450618,0.977667,0.0032320241,0.014293638],"study_design_scores_gemma":[0.0014001589,0.00021254347,0.000005732711,0.0003633979,0.00010910954,0.0000547773,0.0003578391,0.95681405,0.009321575,0.014918702,0.015829176,0.0006129484],"about_ca_topic_score_codex":0.00014460174,"about_ca_topic_score_gemma":0.000033242803,"teacher_disagreement_score":0.9627483,"about_ca_system_score_codex":0.000029109244,"about_ca_system_score_gemma":0.0003423627,"threshold_uncertainty_score":0.9998155},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034738493,0.00007847439,0.99053437,0.0018719368,0.0006652223,0.00042531075,0.000105196385,0.00043028648,0.0024153495],"genre_scores_gemma":[0.08429391,0.00011179635,0.9101056,0.0005034318,0.0008080706,0.00016196063,0.000022223481,0.0000645329,0.0039284993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804795,0.00006197461,0.0003539856,0.0006651849,0.00031447507,0.0005564329],"domain_scores_gemma":[0.9975579,0.0010205662,0.00015315154,0.00089427124,0.00016713943,0.00020699755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003951757,0.00023432153,0.0002962212,0.00007730331,0.0002486075,0.00013594197,0.0010949778,0.000116776195,0.00009947719],"category_scores_gemma":[0.0001938128,0.00015659157,0.00011558221,0.00021299916,0.00009485445,0.0007135755,0.0005050353,0.000082154336,0.00024670703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006953766,0.000118904594,0.000023323071,0.000015841651,0.00005748323,0.00003200263,0.0001519499,0.0000016090487,0.12459461,0.025011703,0.022462925,0.8274601],"study_design_scores_gemma":[0.015364458,0.0025562865,0.0015825625,0.0010574621,0.0001112739,0.00034368318,0.00008905158,0.3680813,0.14299084,0.123992614,0.340052,0.0037784355],"about_ca_topic_score_codex":0.000019977795,"about_ca_topic_score_gemma":0.0000017533027,"teacher_disagreement_score":0.82368165,"about_ca_system_score_codex":0.00007193412,"about_ca_system_score_gemma":0.00014304863,"threshold_uncertainty_score":0.6385619},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123204686,0.00008552471,0.86664224,0.0002962409,0.0010201874,0.00033422228,0.00004283078,0.00023954637,0.008134508],"genre_scores_gemma":[0.99751353,0.0001763288,0.0011355043,0.00010983055,0.00006693958,0.0000014093531,0.000012454337,0.000010349847,0.0009736639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801594,0.00018414417,0.00019521432,0.0011392736,0.00012343038,0.000341989],"domain_scores_gemma":[0.99804187,0.00029914043,0.00018377218,0.0012846027,0.000059641625,0.00013094912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029588366,0.00028484373,0.00033344264,0.0003111953,0.00009952121,0.000102550366,0.0021932258,0.00024417747,0.00005902132],"category_scores_gemma":[0.000043297237,0.0002383165,0.00014569717,0.00034544163,0.00007786544,0.0004888798,0.0021312695,0.00043865244,0.00015809188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000336264,0.00030119697,0.00515754,0.00009644714,0.00008297777,0.002301247,0.00034611305,0.101206236,0.00007863171,0.87271506,0.0050246767,0.012353588],"study_design_scores_gemma":[0.003155606,0.0001234958,0.0025563831,0.00086539675,0.00001853392,0.00000561741,0.00003517745,0.451166,0.00022228002,0.5387189,0.0022449098,0.0008876993],"about_ca_topic_score_codex":0.00018701714,"about_ca_topic_score_gemma":0.000037804417,"teacher_disagreement_score":0.8743088,"about_ca_system_score_codex":0.00018271428,"about_ca_system_score_gemma":0.00021161516,"threshold_uncertainty_score":0.97182643},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012237205,0.00008262907,0.99412304,0.002611825,0.0010302281,0.0002288209,0.0014879482,0.00025694646,0.000056172525],"genre_scores_gemma":[0.022130849,0.0001197531,0.97658724,0.00031726598,0.00018247477,0.00006634235,0.000045676104,0.000022099715,0.0005282885],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984723,0.000032484175,0.00022575044,0.00067402516,0.0002863865,0.0003090819],"domain_scores_gemma":[0.99632084,0.00034638017,0.000064854125,0.003072193,0.00007980378,0.00011594235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018013948,0.00018511577,0.00016468915,0.000095854855,0.00033496748,0.00013112038,0.002899508,0.000082281964,0.00007211844],"category_scores_gemma":[0.00006673886,0.00011583567,0.00006674135,0.0001775908,0.000065426706,0.0013216673,0.00011224592,0.00009642701,0.000039229264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012474131,0.000053085605,0.0000025511076,0.0000057118227,0.000022709044,0.0000031219088,0.000044860597,0.00001506588,0.00041148727,0.0038509862,0.0026965362,0.9928814],"study_design_scores_gemma":[0.0035896483,0.0008749908,0.002234583,0.00019504636,0.00006870259,0.00010156955,0.00009995509,0.083555065,0.020803114,0.14164266,0.7455099,0.0013247535],"about_ca_topic_score_codex":0.00002525167,"about_ca_topic_score_gemma":0.000010604401,"teacher_disagreement_score":0.99155664,"about_ca_system_score_codex":0.000030779524,"about_ca_system_score_gemma":0.00006946218,"threshold_uncertainty_score":0.53880554},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06403605,0.00013189013,0.92909265,0.00019879469,0.0018351345,0.00045180923,0.000078111276,0.00014755265,0.004028036],"genre_scores_gemma":[0.7080682,0.000037439942,0.29136083,0.000018453244,0.0001261002,0.000021373178,0.00005152126,0.000016158676,0.00029992106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982327,0.00007694298,0.0004553228,0.0006350557,0.0003685788,0.00023137356],"domain_scores_gemma":[0.99735105,0.00013446214,0.0005226667,0.0017942482,0.00011790216,0.0000796874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026441127,0.00024558502,0.0004888286,0.00024011295,0.000089429566,0.00016911834,0.0018519472,0.0002506308,0.00004394765],"category_scores_gemma":[0.00009053133,0.00021303732,0.000090890964,0.000080182115,0.00017457696,0.00013762186,0.0035728195,0.0004044176,0.000041927866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028297558,0.003183588,0.009928459,0.0026715999,0.0003178288,0.0005943312,0.0037709705,0.25604752,0.010623812,0.11467481,0.0065061986,0.59139794],"study_design_scores_gemma":[0.0003333832,0.00003684173,0.003546063,0.0004026697,0.0000074032223,0.000012087659,0.000005252629,0.99026793,0.0021759793,0.0024527349,0.0005020934,0.00025754888],"about_ca_topic_score_codex":0.00029407948,"about_ca_topic_score_gemma":0.000007611771,"teacher_disagreement_score":0.73422045,"about_ca_system_score_codex":0.00004009761,"about_ca_system_score_gemma":0.00021300903,"threshold_uncertainty_score":0.868741},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01959473,0.00024122374,0.97583467,0.0033432997,0.000106817235,0.000060517945,0.000024193225,0.00014485761,0.0006496832],"genre_scores_gemma":[0.8508733,0.0000068981817,0.14600964,0.0028622148,0.00014867297,0.0000010883871,0.000057991045,0.000007756921,0.000032435244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908555,0.000020894962,0.000147188,0.0003212817,0.00027559136,0.00014947371],"domain_scores_gemma":[0.999425,0.00013822113,0.000057689635,0.00012697316,0.000053424836,0.00019872171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000070876464,0.00010582494,0.0001306653,0.00008284172,0.00012738965,0.00017279906,0.00039588177,0.00003212205,0.000026716572],"category_scores_gemma":[0.00003407691,0.000097028154,0.000028048727,0.0004167801,0.000036508696,0.0004313963,0.00019414918,0.000110549096,0.00008890865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006877663,0.0002602852,0.019173522,0.00018944209,0.00016328042,0.00019929018,0.0039822264,0.14096397,0.00091824704,0.29218778,0.17926279,0.36263037],"study_design_scores_gemma":[0.00033533014,0.00007431047,0.03528772,0.000013463329,0.0000027602437,0.00003066453,0.000029211917,0.9497036,0.00004365532,0.0062925634,0.008017562,0.0001691995],"about_ca_topic_score_codex":0.0000061712467,"about_ca_topic_score_gemma":7.859145e-8,"teacher_disagreement_score":0.83127856,"about_ca_system_score_codex":0.000010342816,"about_ca_system_score_gemma":0.000031246433,"threshold_uncertainty_score":0.3956693},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38312465,0.0000787646,0.6058076,0.0057210554,0.00057930656,0.0005763213,0.000014202107,0.00029932914,0.0037987758],"genre_scores_gemma":[0.9447701,0.0000042346096,0.051022265,0.0016797703,0.0013661634,0.00006485397,0.000035736204,0.000021160991,0.0010357016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856955,0.00011738746,0.00019095425,0.00048209072,0.00031479495,0.00032519994],"domain_scores_gemma":[0.99869233,0.000042401756,0.000070382375,0.0010530519,0.000046547084,0.00009529109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026129087,0.00015950741,0.00012965174,0.000074540825,0.00031152822,0.00014356997,0.0011102803,0.00005802084,0.000021536996],"category_scores_gemma":[0.000013984637,0.0001010733,0.000052545503,0.0003116889,0.000031089123,0.00029892495,0.00030255978,0.00018605276,0.0002491099],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003162533,0.0015681373,0.02318375,0.000053542775,0.00005260248,0.00009584003,0.0043033995,0.025201578,0.05375665,0.03482572,0.16117525,0.6954673],"study_design_scores_gemma":[0.0017642584,0.0011142248,0.4589176,0.00018749731,0.000024905052,0.000046101886,0.00004782709,0.042390026,0.021854607,0.010693712,0.46187308,0.0010861617],"about_ca_topic_score_codex":0.00036730923,"about_ca_topic_score_gemma":0.00020550167,"teacher_disagreement_score":0.6943811,"about_ca_system_score_codex":0.000039202285,"about_ca_system_score_gemma":0.000040657866,"threshold_uncertainty_score":0.412165},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005409643,0.000005238783,0.97817093,0.0067556435,0.00009570585,0.00006880217,0.0000011641575,0.000094968724,0.009397928],"genre_scores_gemma":[0.91414183,0.000006478215,0.08253369,0.000870764,0.000062006184,0.000012118131,2.7924685e-7,0.0000052394876,0.0023675964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99946946,0.000023400684,0.000068435635,0.00016628385,0.00014683587,0.00012560774],"domain_scores_gemma":[0.99931604,0.00021998814,0.000029072391,0.00039022573,0.00001544416,0.000029244831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012735977,0.000053770415,0.000039181836,0.000018051001,0.000117230265,0.000093397306,0.0005995798,0.000014376092,0.00008261994],"category_scores_gemma":[0.000011244642,0.000019335303,0.000017919394,0.00006240279,0.000010569061,0.00031763103,0.00033880371,0.000042960924,0.0001893571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1925155e-7,0.0000068049876,0.000008799011,6.1539055e-7,0.0000018699766,0.0000021466085,0.000054817494,0.000012890948,0.0011476056,0.90728813,0.0040345327,0.08744106],"study_design_scores_gemma":[0.0005286477,0.00013493552,0.0010263878,0.00031149082,0.0000023167584,0.000009823497,0.000068688336,0.021861227,0.020965643,0.93271804,0.022019852,0.0003529696],"about_ca_topic_score_codex":0.000014938622,"about_ca_topic_score_gemma":0.0000011384744,"teacher_disagreement_score":0.9087322,"about_ca_system_score_codex":0.000013236085,"about_ca_system_score_gemma":0.000012264531,"threshold_uncertainty_score":0.24338655},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038434297,0.00020219409,0.95733196,0.001084579,0.000096087926,0.00056204246,0.0000045495785,0.00008729402,0.0021970018],"genre_scores_gemma":[0.88470083,0.00002365556,0.11471291,0.00006122986,0.000009746817,0.00013822384,0.0000043893024,0.0000034357993,0.00034560676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952894,0.000024651585,0.00014822153,0.000112935384,0.00008630549,0.00009896768],"domain_scores_gemma":[0.998795,0.00006511384,0.000053865402,0.0009036293,0.00014886195,0.00003353363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008520417,0.00005480601,0.00010727903,0.000024542907,0.00009148381,0.000062278195,0.001153777,0.000022433329,0.00001596634],"category_scores_gemma":[0.00001186842,0.00003568655,0.000034638073,0.00008323619,0.000060183324,0.0005128875,0.00040844863,0.000029208652,0.0000110111905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002767155,0.00054448255,0.00043918914,0.00014764644,0.00006585401,1.3944658e-7,0.0017885336,0.0000673755,0.047564358,0.25235215,0.01964314,0.67735946],"study_design_scores_gemma":[0.0018386983,0.00008228123,0.0005803757,0.00009031739,0.000007058624,0.000001711954,0.0004180608,0.94155693,0.04659692,0.0032270257,0.005394008,0.00020661803],"about_ca_topic_score_codex":0.0003204206,"about_ca_topic_score_gemma":0.000010467056,"teacher_disagreement_score":0.9414896,"about_ca_system_score_codex":0.000005431299,"about_ca_system_score_gemma":0.000026764796,"threshold_uncertainty_score":0.21440239},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021495686,0.00015909215,0.8718733,0.0008386856,0.0060522677,0.0000943855,0.000004558492,0.00019214787,0.118635945],"genre_scores_gemma":[0.10575735,0.000060974675,0.7717828,0.0027981733,0.04158459,0.000012134872,0.000020553765,0.000028891185,0.07795454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999327,0.000014344719,0.00009224792,0.0001410857,0.00016468074,0.00026064605],"domain_scores_gemma":[0.99942935,0.000017616949,0.000025935966,0.00038020802,0.000016089745,0.0001308092],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011630567,0.00007068977,0.00006618382,0.000037381495,0.00006597563,0.00008387426,0.0004878371,0.00003129467,0.0011744084],"category_scores_gemma":[0.0000058567653,0.000053545515,0.000023644214,0.00010787085,0.000012027635,0.0010731902,0.00034237883,0.00006739037,0.0013059177],"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":[0.0000016436866,0.00005973893,0.00070732745,0.0000017512042,0.0000033910003,0.0000034184093,0.00027306474,0.000004106011,0.0001640375,0.014091329,0.68462616,0.30006403],"study_design_scores_gemma":[0.0001367242,0.000020589621,0.0053553325,0.000004399421,0.0000013376979,0.000012435223,0.000024592531,0.0045279646,0.0012637703,0.00021450668,0.9883094,0.00012898361],"about_ca_topic_score_codex":0.0000337609,"about_ca_topic_score_gemma":0.0000017261169,"teacher_disagreement_score":0.30368322,"about_ca_system_score_codex":0.00000973648,"about_ca_system_score_gemma":0.000010662041,"threshold_uncertainty_score":0.99973863},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018047914,0.001630083,0.9936386,0.00061078573,0.0014169096,0.00013074157,0.00009109429,0.00013624715,0.00054076087],"genre_scores_gemma":[0.1966445,0.000027820883,0.8029561,0.00012654484,0.00013768979,0.000002656537,0.000029997085,0.000009826364,0.000064866945],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99753004,0.00056217297,0.0004347248,0.0007279907,0.00046209284,0.00028298082],"domain_scores_gemma":[0.9952176,0.001277655,0.0002973994,0.002967181,0.00014119185,0.00009896495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015010566,0.00018714757,0.00044717014,0.00009483483,0.00011870198,0.00008326065,0.0032558714,0.00031151174,0.00003448227],"category_scores_gemma":[0.0006596757,0.00010857846,0.000049969596,0.00034861974,0.00007295461,0.0016747124,0.0028430473,0.00043873172,0.000011280184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010458221,0.000045497203,0.00025283094,0.000019231209,0.000015749018,0.0000037795055,0.0001089121,0.000016260905,0.09580701,0.027665002,0.009334454,0.8667208],"study_design_scores_gemma":[0.001428167,0.00020212038,0.0061917687,0.0007704207,0.00003845968,0.000029047886,0.00005051258,0.14096864,0.65959984,0.027271604,0.1627463,0.00070310826],"about_ca_topic_score_codex":0.000041441195,"about_ca_topic_score_gemma":0.0000023423418,"teacher_disagreement_score":0.8660177,"about_ca_system_score_codex":0.000055865945,"about_ca_system_score_gemma":0.000098691096,"threshold_uncertainty_score":0.6050273},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13460289,0.00005564319,0.85618824,0.00007747059,0.0034857914,0.00042322246,0.000026134996,0.00013622116,0.0050044106],"genre_scores_gemma":[0.9909252,0.0000041756084,0.008853837,0.000039274128,0.00010436889,0.00002137701,0.0000192785,0.000005474914,0.000027033968],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836963,0.00007836588,0.00062133267,0.00019765506,0.00048113428,0.00025187264],"domain_scores_gemma":[0.9979994,0.000036330293,0.0005679476,0.0011287557,0.0001623632,0.00010517993],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00046855686,0.00015956616,0.00022432255,0.00028383563,0.0007159567,0.0012394711,0.0011259145,0.00011152669,0.0000030111078],"category_scores_gemma":[0.00007560633,0.00013288081,0.000050407136,0.00018049344,0.000055730034,0.0044109765,0.0006376918,0.00020289367,0.00009189754],"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":[0.000047921316,0.00019872095,0.006317354,0.00038221708,0.0000364072,0.000016866787,0.019022627,0.75562704,0.0008453743,0.13468374,0.003769106,0.07905264],"study_design_scores_gemma":[0.00051166146,0.00001903634,0.0038191797,0.00039557705,0.0000021541039,0.000047629357,0.0003530925,0.9707604,0.00007779621,0.00004947537,0.023797192,0.00016681012],"about_ca_topic_score_codex":0.0011727451,"about_ca_topic_score_gemma":0.000011901792,"teacher_disagreement_score":0.8563223,"about_ca_system_score_codex":0.00016764448,"about_ca_system_score_gemma":0.00008730156,"threshold_uncertainty_score":0.99979734},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004932893,0.00030530815,0.98542106,0.0022738702,0.0034110793,0.00048468861,0.000050420702,0.0001755131,0.007828722],"genre_scores_gemma":[0.057195585,0.000044304415,0.9334782,0.005350716,0.0022572493,0.000028088543,0.000018389635,0.00007884018,0.001548652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944241,0.00003453936,0.00062459265,0.002398514,0.0014130445,0.0011051929],"domain_scores_gemma":[0.9947314,0.00050054037,0.00053195335,0.0034433438,0.00032639562,0.00046631866],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00087676087,0.00075677753,0.00076678203,0.0009283666,0.000935806,0.0024741604,0.007888065,0.00042270494,0.00010720041],"category_scores_gemma":[0.00025957433,0.0006635999,0.00023706236,0.00038306194,0.00047911753,0.0018294462,0.0041032364,0.0011201894,0.00013354757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006083138,0.000036933197,0.000062312625,0.00002945024,0.000014694934,0.00015280841,0.0008475392,0.0014767388,0.00011067133,0.0019755433,0.0012070346,0.9940802],"study_design_scores_gemma":[0.0008651321,0.000722696,0.0011148693,0.0025176383,0.000035581532,0.00028954318,6.684322e-7,0.6919974,0.004164075,0.23605062,0.05944149,0.002800269],"about_ca_topic_score_codex":0.00021581312,"about_ca_topic_score_gemma":0.00014434182,"teacher_disagreement_score":0.9912799,"about_ca_system_score_codex":0.00020478384,"about_ca_system_score_gemma":0.00042609024,"threshold_uncertainty_score":0.9995815},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09848851,0.000021083268,0.8959011,0.0011358111,0.00053352694,0.00014894639,0.000007150429,0.00019346499,0.0035704002],"genre_scores_gemma":[0.9126408,0.000010141094,0.08637796,0.00078490656,0.0001162482,0.0000088459055,7.621631e-7,0.000009212757,0.000051083764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969289,0.00007423655,0.0002966177,0.0009816306,0.00091196975,0.0008066503],"domain_scores_gemma":[0.9976251,0.00046719462,0.00008168803,0.0011307265,0.000106004525,0.00058929727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010752465,0.0002614748,0.00022721104,0.00018922647,0.00053021463,0.00051747134,0.002559214,0.00007649208,0.00008298939],"category_scores_gemma":[0.0001463983,0.00014457434,0.000054281423,0.00058963115,0.0021464408,0.0021178008,0.002838955,0.00018647648,0.00013630869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020778076,0.00004739454,0.000044740013,0.000004012389,0.000002167771,0.000008912028,0.00014520941,0.000013275076,0.0003962917,0.831418,0.00018666068,0.1677126],"study_design_scores_gemma":[0.0010841761,0.001189396,0.0027773671,0.00020952681,0.0000059221093,0.0001258456,0.0000036737115,0.35885808,0.007025441,0.6272845,0.00080299156,0.00063306233],"about_ca_topic_score_codex":0.0000028844452,"about_ca_topic_score_gemma":4.7463072e-7,"teacher_disagreement_score":0.81415236,"about_ca_system_score_codex":0.000053135103,"about_ca_system_score_gemma":0.00012501427,"threshold_uncertainty_score":0.79086506},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003368718,0.00024295149,0.9934925,0.0017122871,0.000847343,0.00015690358,0.000044294975,0.000035101148,0.000099888544],"genre_scores_gemma":[0.05054508,0.0001548786,0.9481072,0.00015699613,0.0006175464,0.000014142667,0.0000020856764,0.000020652045,0.00038145608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983596,0.000055213728,0.0005659072,0.00025729113,0.00043212122,0.00032983097],"domain_scores_gemma":[0.99821466,0.00029654804,0.00055960903,0.00045474948,0.0002648914,0.0002095259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057731377,0.00017203261,0.0003431132,0.00014090711,0.000099615216,0.00016006209,0.0011703441,0.00007046901,0.000017284061],"category_scores_gemma":[0.00015852705,0.00009224996,0.00025413928,0.00016228195,0.000047934616,0.0014935799,0.00016024684,0.000115631345,0.000009387378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021198379,0.0001566264,0.00013671664,0.000033081316,0.00018562023,0.00005036541,0.0003618918,0.0000135712,0.12886302,0.0036414447,0.009545245,0.85680044],"study_design_scores_gemma":[0.023479877,0.0075091957,0.004349162,0.0019777522,0.00022808126,0.0013764787,0.00016438693,0.032669634,0.28173864,0.10307121,0.5412311,0.0022044622],"about_ca_topic_score_codex":0.0000038613643,"about_ca_topic_score_gemma":2.998353e-7,"teacher_disagreement_score":0.85459596,"about_ca_system_score_codex":0.000049845006,"about_ca_system_score_gemma":0.00010246898,"threshold_uncertainty_score":0.37618443},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024192093,0.00028209257,0.78295386,0.00020175893,0.0026964082,0.00027527983,0.000020235064,0.00042078228,0.18895747],"genre_scores_gemma":[0.46203884,0.0025454203,0.26822013,0.0003176334,0.0011148305,0.00007657913,0.0018697487,0.00010435229,0.26371247],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992632,0.00001292852,0.00014194779,0.00032016222,0.00015226049,0.00010946656],"domain_scores_gemma":[0.9994719,0.000033897402,0.00009813872,0.0002943098,0.00004917209,0.000052591156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000066206354,0.000118810894,0.000112098925,0.00008562071,0.000072463874,0.00014598237,0.00033765758,0.00011757183,0.00004867581],"category_scores_gemma":[0.000009064133,0.000079819714,0.000022674038,0.000053771204,0.0000069404387,0.00052529486,0.00012380737,0.00007557336,0.000031476367],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018602355,0.000017679795,0.00020514589,0.00004743345,0.000015542233,0.0000058952646,0.0006510778,5.1076917e-8,0.0036038281,0.076234646,0.006667889,0.9125322],"study_design_scores_gemma":[0.004793986,0.0011889411,0.36295292,0.005294742,0.00013791809,0.00007815554,0.0012598243,0.279769,0.031195702,0.1473477,0.159856,0.0061250995],"about_ca_topic_score_codex":0.0001704435,"about_ca_topic_score_gemma":0.000033131815,"teacher_disagreement_score":0.9064071,"about_ca_system_score_codex":0.000013695286,"about_ca_system_score_gemma":0.00003674997,"threshold_uncertainty_score":0.32549536},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31289086,0.000054258126,0.6864137,0.000115676456,0.00011356054,0.000052800122,0.000003181153,0.00006596918,0.00028995087],"genre_scores_gemma":[0.92349726,0.000018940818,0.07633424,0.000029424911,0.000021837952,0.0000012589741,0.000001634182,0.000004376855,0.00009102896],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991735,0.00003630884,0.00018787381,0.00023728894,0.00022692968,0.00013805358],"domain_scores_gemma":[0.9993146,0.00006928688,0.000105949526,0.0003819083,0.000074199364,0.000054034874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000112663336,0.00008308307,0.00010665589,0.00014359682,0.00007935434,0.00002944737,0.000431488,0.000041089235,0.000048604896],"category_scores_gemma":[0.000011178287,0.000047399066,0.000043858934,0.0002631724,0.00004644316,0.000865463,0.00034487416,0.000034275647,0.0000101105725],"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":[0.000011831092,0.00009485415,0.0026593774,0.000017096798,0.000008621671,0.000005236654,0.00012505364,0.00011674826,0.7966795,0.01968241,0.00059215375,0.18000712],"study_design_scores_gemma":[0.001742286,0.00034379627,0.059741013,0.00078674866,0.000014565391,0.00003818596,0.000069637696,0.7417347,0.18337774,0.008310182,0.003288981,0.00055219827],"about_ca_topic_score_codex":0.000058054327,"about_ca_topic_score_gemma":6.734239e-7,"teacher_disagreement_score":0.7416179,"about_ca_system_score_codex":0.000012691422,"about_ca_system_score_gemma":0.000026939451,"threshold_uncertainty_score":0.19328777},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6547908,0.00011577016,0.34034827,0.00075971434,0.00009226957,0.00013170068,0.0000017745097,0.00001219394,0.0037475133],"genre_scores_gemma":[0.9906199,0.000015832931,0.009251096,0.000043192464,0.0000058154183,0.0000028060983,3.6286153e-7,8.8293945e-7,0.00006010026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994984,0.000044198725,0.00010173751,0.00012241924,0.00017305018,0.000060184397],"domain_scores_gemma":[0.9997028,0.00005691497,0.000022660894,0.00016718773,0.000035046203,0.000015404845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050639914,0.00002988675,0.000054178956,0.000060305152,0.0000058327573,0.000008888378,0.00013866325,0.000018760182,0.000023170132],"category_scores_gemma":[0.00003309204,0.000017573859,0.0000045864135,0.000102422855,0.000010158679,0.00043012446,0.00013890708,0.000015726562,0.000004400712],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001355084,0.00013427567,0.011701467,0.000009912091,0.0000025699997,0.000003541621,0.0005028234,0.00008997568,0.07497074,0.019172857,0.0027849395,0.8906134],"study_design_scores_gemma":[0.0032983734,0.00009895431,0.22848107,0.00015740022,0.0000034096604,0.000004665288,0.000028288301,0.67179734,0.04482471,0.049230505,0.001871844,0.00020346223],"about_ca_topic_score_codex":0.00006841913,"about_ca_topic_score_gemma":0.00019444508,"teacher_disagreement_score":0.8904099,"about_ca_system_score_codex":0.000015338941,"about_ca_system_score_gemma":0.000025007435,"threshold_uncertainty_score":0.07166411},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03396001,0.00016830958,0.9492519,0.0042397035,0.0008096794,0.00075751764,0.000023589533,0.0009697038,0.009819571],"genre_scores_gemma":[0.83716214,0.000074157666,0.15789083,0.0007996826,0.00043394006,0.000046607598,0.00004347312,0.000082769184,0.0034664036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994401,0.00044132065,0.0009715592,0.0015471696,0.0015455793,0.0010934034],"domain_scores_gemma":[0.9951321,0.00093521556,0.00045632175,0.002428419,0.0003114783,0.000736496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053446926,0.0007506112,0.00079661957,0.0002840221,0.0008469323,0.00064203434,0.0027072823,0.00031194912,0.00064106623],"category_scores_gemma":[0.000106915,0.00038527412,0.00018628045,0.00060734694,0.00028864323,0.0028121963,0.0023482486,0.0004799094,0.00053539476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007080642,0.0015873327,0.008451409,0.00022431106,0.00019106883,0.000359627,0.00077647064,0.0007471152,0.2909237,0.0730209,0.089985006,0.53302497],"study_design_scores_gemma":[0.011794063,0.001352781,0.02441795,0.0057151453,0.000100038065,0.0005098674,0.00023965848,0.6974327,0.08631575,0.00498064,0.16355953,0.003581871],"about_ca_topic_score_codex":0.000054269112,"about_ca_topic_score_gemma":0.000019633673,"teacher_disagreement_score":0.80320215,"about_ca_system_score_codex":0.00013151712,"about_ca_system_score_gemma":0.00017566705,"threshold_uncertainty_score":0.9998599},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009286324,0.0000115360635,0.9954959,0.0019037791,0.00023501042,0.00024208048,0.000093037655,0.00022663883,0.00086337613],"genre_scores_gemma":[0.19339447,0.000023304126,0.80464953,0.00020459543,0.00011954904,0.00022081855,0.000051180727,0.000014911951,0.0013216247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913746,0.00001310955,0.00019466365,0.00029590458,0.00013885743,0.0002200099],"domain_scores_gemma":[0.99895513,0.00033012373,0.000044695447,0.0005165755,0.00007343392,0.00008005582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009899523,0.00009284502,0.00009122767,0.0001082747,0.00013901074,0.00009162745,0.0004991957,0.000023061426,0.00009491216],"category_scores_gemma":[0.000039631424,0.00006109404,0.00006308475,0.00018871327,0.000013720387,0.0006617707,0.00018685256,0.000025143267,0.000025655674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008663325,0.00011743144,0.00041251915,0.00001883708,0.00006270682,0.0000038768853,0.00020971714,0.00020233294,0.139063,0.5389521,0.1434611,0.17748772],"study_design_scores_gemma":[0.0043090465,0.0001514883,0.010582331,0.000071837196,0.000024408317,0.000016177242,0.000079549216,0.7431401,0.045592897,0.017787343,0.17756136,0.00068345503],"about_ca_topic_score_codex":0.00002243792,"about_ca_topic_score_gemma":0.00002094591,"teacher_disagreement_score":0.7429378,"about_ca_system_score_codex":0.000015390058,"about_ca_system_score_gemma":0.000030452813,"threshold_uncertainty_score":0.24913427},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44509628,0.00007978734,0.40566447,0.022598077,0.001227612,0.0011912236,0.0001712805,0.001210364,0.12276089],"genre_scores_gemma":[0.8850972,0.00013386171,0.03217594,0.0005258771,0.00023448754,9.1045564e-7,0.00017704221,0.000033846663,0.08162084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980485,0.00014424064,0.00021248958,0.0007504645,0.000298043,0.00054627314],"domain_scores_gemma":[0.99749047,0.00031932603,0.00021304794,0.001516153,0.00022084518,0.00024017223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003578003,0.00024374918,0.00023199087,0.00068687316,0.0011692983,0.00017668161,0.0035321699,0.00019541246,0.00019529377],"category_scores_gemma":[0.00006694617,0.00024312118,0.00013282918,0.0023107696,0.00022609258,0.0015661946,0.0021481896,0.0007049977,0.00019274454],"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":[0.000081169936,0.0005662566,0.026261598,0.00002324078,0.00009459431,0.00015777696,0.0015304538,0.00062483427,0.0046116738,0.91976726,0.02486272,0.021418406],"study_design_scores_gemma":[0.00065451476,0.000026582391,0.026549494,0.0000114333625,0.000016505222,0.00001945999,0.00020915458,0.07203703,0.00011037643,0.00017637265,0.8998299,0.00035916406],"about_ca_topic_score_codex":0.00036905636,"about_ca_topic_score_gemma":0.001100689,"teacher_disagreement_score":0.9195909,"about_ca_system_score_codex":0.00031783854,"about_ca_system_score_gemma":0.00024378879,"threshold_uncertainty_score":0.9914194},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0358898,0.000047280526,0.9517279,0.0019738488,0.0005041756,0.00012189386,0.000030753807,0.00026745678,0.009436861],"genre_scores_gemma":[0.9838794,0.000055045948,0.01466102,0.00021975764,0.0000836545,0.000029766501,0.000007782518,0.0000067015235,0.0010568905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99869466,0.00007278482,0.00021716524,0.0005126497,0.00015907573,0.00034368545],"domain_scores_gemma":[0.99860793,0.00019966383,0.00011261774,0.0008543855,0.00010949937,0.00011590595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015901813,0.00014339194,0.00016631957,0.00008424179,0.00015191792,0.00008097967,0.0009765902,0.00010195893,0.00025958323],"category_scores_gemma":[0.00013757717,0.00009830674,0.000046231104,0.00014993927,0.0001219961,0.000670204,0.00062500825,0.00011796256,0.0001669173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010380987,0.000051448536,0.0044423654,0.0000075335856,0.000020366133,0.00004688644,0.000095067684,0.0000015707996,0.011719828,0.86069435,0.0037781408,0.11913206],"study_design_scores_gemma":[0.0075649326,0.0013617213,0.44109425,0.00077406224,0.00005760979,0.00048384105,0.00004867949,0.03595654,0.038348407,0.17107148,0.30050176,0.0027367133],"about_ca_topic_score_codex":0.000047212918,"about_ca_topic_score_gemma":0.000012627999,"teacher_disagreement_score":0.9479896,"about_ca_system_score_codex":0.000030417492,"about_ca_system_score_gemma":0.00011757935,"threshold_uncertainty_score":0.40088323},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005316606,0.000026522695,0.9919922,0.0013474609,0.000025719046,0.0010528457,0.000023316703,0.00011118923,0.00010417155],"genre_scores_gemma":[0.043118928,0.000004331031,0.9563718,0.000087835215,0.000037173082,0.00017906018,0.00001142065,0.000010473439,0.00017899096],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898577,0.00001785951,0.00014659499,0.00048161016,0.00017000355,0.00019818485],"domain_scores_gemma":[0.99931365,0.00008787388,0.00006227101,0.00026019555,0.00018741685,0.00008858276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001953211,0.00013398184,0.000119591605,0.00008088057,0.0002017115,0.00014015728,0.00020191238,0.000029321334,0.000011714361],"category_scores_gemma":[0.000022764958,0.00006890977,0.000026371556,0.00017889595,0.00005777028,0.001110292,0.000045032997,0.000041227144,0.0000020507669],"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":[0.00021782042,0.0002168086,0.00071225583,0.0001280304,0.000018178973,0.0000029215105,0.00039289947,0.000031554227,0.74039,0.0045797224,0.00050832384,0.25280148],"study_design_scores_gemma":[0.0020989832,0.00031142047,0.00032349513,0.00025421043,0.0000053911353,0.000009115713,0.000011363773,0.7534067,0.23958363,0.00028621845,0.0034957407,0.00021370829],"about_ca_topic_score_codex":0.000010252364,"about_ca_topic_score_gemma":0.0000032380221,"teacher_disagreement_score":0.7533752,"about_ca_system_score_codex":0.000012670887,"about_ca_system_score_gemma":0.00006416523,"threshold_uncertainty_score":0.2810059},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18636832,0.000021387448,0.81164545,0.001172362,0.00055504515,0.000022685623,0.000002224882,0.00000831281,0.00020423296],"genre_scores_gemma":[0.98861414,0.000039854996,0.010939822,0.0003482352,0.00005501197,1.4063752e-7,0.0000012529601,7.622587e-7,7.534052e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898905,0.00003941054,0.0003738165,0.00006481519,0.0004646717,0.00006826239],"domain_scores_gemma":[0.9986779,0.00029609652,0.00054902514,0.00004779192,0.00039041933,0.00003875147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008724001,0.000053214753,0.00008175402,0.0002859191,0.000098384604,0.00023805801,0.00035485675,0.000022234148,0.0000026294317],"category_scores_gemma":[0.00014841925,0.000032799297,0.000022793152,0.000119453594,0.000086654814,0.0037043556,0.00009180505,0.00005611584,5.4665514e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001918598,0.000020166635,0.0010022519,0.0000030336246,0.0000053659096,8.0837043e-7,0.00024203725,0.0063848584,0.00012273148,0.0036679027,0.000087691114,0.988444],"study_design_scores_gemma":[0.00052390224,0.00022550572,0.008052297,0.00019187461,0.0000014744759,0.000035851164,0.000029662378,0.98915005,0.00053214264,0.0009892172,0.00021873265,0.00004926464],"about_ca_topic_score_codex":0.000007237416,"about_ca_topic_score_gemma":2.3423459e-7,"teacher_disagreement_score":0.9883947,"about_ca_system_score_codex":0.000014167935,"about_ca_system_score_gemma":0.000029690913,"threshold_uncertainty_score":0.26855683},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4242167,0.00007622624,0.57362294,0.00059690565,0.0007487113,0.0002655441,0.0000069222774,0.00015056842,0.00031550135],"genre_scores_gemma":[0.6329093,0.00004679145,0.3668564,0.00009851179,0.000052499403,0.000011626629,0.0000012727718,0.000010319887,0.000013295438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966019,0.00005599094,0.0005932834,0.0011531445,0.0008569865,0.0007387201],"domain_scores_gemma":[0.9951274,0.00023221504,0.00047339257,0.003774369,0.000117092626,0.00027553816],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021513705,0.00033570133,0.00046305673,0.00029212466,0.0011792313,0.0031429478,0.0077529442,0.000106626285,0.000004788248],"category_scores_gemma":[0.000150746,0.00029612775,0.00004961564,0.00043718278,0.0013239494,0.0031564336,0.0046479916,0.00034640322,0.000054752254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001507104,0.0011639039,0.03494865,0.0005624922,0.000029755543,0.0016098018,0.007752948,0.0016175299,0.0081539815,0.42988062,0.00036940773,0.51389587],"study_design_scores_gemma":[0.00043008217,0.00008035818,0.036610663,0.00036080973,0.0000036340957,0.00034981457,0.000008880369,0.91528654,0.0014467643,0.044966087,0.000046216755,0.00041013627],"about_ca_topic_score_codex":0.00014829561,"about_ca_topic_score_gemma":0.000055510358,"teacher_disagreement_score":0.91366905,"about_ca_system_score_codex":0.00012676533,"about_ca_system_score_gemma":0.00023411095,"threshold_uncertainty_score":0.9999491},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071558137,0.000062302344,0.9867757,0.0033926351,0.00011322524,0.0003232541,0.00029912198,0.0000739158,0.0018040388],"genre_scores_gemma":[0.98903984,0.000519647,0.009189979,0.00071141537,0.000057720372,0.000256941,0.00010204468,0.0000061707938,0.000116231575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990474,0.000043949814,0.000363847,0.00017823112,0.00024520402,0.00012135451],"domain_scores_gemma":[0.9987346,0.00052100705,0.0002006884,0.000294069,0.00016947978,0.00008014199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003795639,0.000106522355,0.0000957091,0.00016853385,0.0001785565,0.00009866996,0.00038593507,0.00006500023,0.000052164065],"category_scores_gemma":[0.000058297177,0.00007333567,0.00003622989,0.00020656579,0.000054248623,0.0018704166,0.0000997443,0.00006930687,0.000049015955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041599313,0.00006803805,0.00009122295,0.000016742319,0.000014446223,1.5204175e-7,0.00031579047,0.00008629632,0.000945025,0.97691596,0.00010880683,0.021395909],"study_design_scores_gemma":[0.0037616023,0.0004667366,0.007433245,0.0006743971,0.000057368903,0.00003392374,0.00043131798,0.08416171,0.0342331,0.47379336,0.3940496,0.0009036446],"about_ca_topic_score_codex":0.0000032209562,"about_ca_topic_score_gemma":4.2661281e-7,"teacher_disagreement_score":0.98188406,"about_ca_system_score_codex":0.000018983768,"about_ca_system_score_gemma":0.000024448991,"threshold_uncertainty_score":0.29905418},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042420093,0.000009493291,0.9902737,0.0004993499,0.0014848198,0.00017700712,0.000030738767,0.00019698079,0.006903692],"genre_scores_gemma":[0.9906826,0.000021990129,0.008570081,0.00020133257,0.00004355449,0.00006015666,0.000017237304,0.000004245075,0.000398809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991227,0.000025659398,0.00029315767,0.00011970557,0.00029220647,0.00014660417],"domain_scores_gemma":[0.99752504,0.000039905066,0.00022406147,0.0020262753,0.00010225551,0.000082487924],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00017314269,0.000104266546,0.00011503285,0.0001434672,0.0009365194,0.0011704578,0.0015748418,0.00006885969,0.000014843206],"category_scores_gemma":[0.00003218886,0.00008679677,0.000049869624,0.00008658378,0.000026637881,0.006682963,0.000030822834,0.000115451774,0.0006995884],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001894363,0.00007892178,0.00008379066,0.00006206226,0.00005047183,0.0000030013066,0.0016838958,0.0038187928,0.000047630936,0.020886201,0.0062634246,0.96700287],"study_design_scores_gemma":[0.0016062055,0.0001590369,0.004204226,0.00017758322,0.000013510727,0.000061626895,0.00032915853,0.58811104,0.001202042,0.00079308706,0.40285495,0.000487555],"about_ca_topic_score_codex":0.00028847513,"about_ca_topic_score_gemma":0.000004368301,"teacher_disagreement_score":0.9902584,"about_ca_system_score_codex":0.000036527734,"about_ca_system_score_gemma":0.000036435944,"threshold_uncertainty_score":0.9998664},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011831258,0.0008779765,0.97109336,0.013910176,0.0012901913,0.00020406889,0.000023910454,0.00004557865,0.0007234545],"genre_scores_gemma":[0.10522024,0.00082274247,0.8920607,0.00048930594,0.0010998335,0.000007173846,0.0000024279936,0.000026260797,0.00027132986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728215,0.00016270977,0.00065585726,0.00046796416,0.0008506373,0.00058067846],"domain_scores_gemma":[0.9969097,0.00022353222,0.00088015676,0.0010044564,0.0002520574,0.0007301115],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015693972,0.00029903455,0.00052151864,0.00020728851,0.00070214865,0.0015994307,0.002025577,0.00014314806,0.000025033603],"category_scores_gemma":[0.0005697858,0.00022350968,0.00015541913,0.00017121636,0.00018632674,0.0034656925,0.0010448421,0.0005562714,0.000017801898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002682064,0.00036285174,0.0027730933,0.00007656132,0.00033885936,0.0028871538,0.0030240056,0.00019871183,0.0032290064,0.0070620016,0.04410786,0.9356717],"study_design_scores_gemma":[0.008365977,0.00475555,0.055303205,0.0016839717,0.0003299242,0.0135616725,0.0013862491,0.71048623,0.010839653,0.023290323,0.16723748,0.0027597388],"about_ca_topic_score_codex":0.0002156208,"about_ca_topic_score_gemma":0.000013371666,"teacher_disagreement_score":0.93291193,"about_ca_system_score_codex":0.00008932915,"about_ca_system_score_gemma":0.00035888702,"threshold_uncertainty_score":0.99943703},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22527264,0.00017439366,0.76063377,0.0031280299,0.0035756119,0.0001372549,0.000002088599,0.00017066798,0.0069055674],"genre_scores_gemma":[0.84576225,0.000028241719,0.15068118,0.0005414424,0.0021461288,2.7205115e-7,0.0000017777701,0.000019923034,0.0008187784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820226,0.00008488561,0.0003497973,0.00034940982,0.0005892697,0.00042438944],"domain_scores_gemma":[0.9980551,0.000108180946,0.0005166119,0.0009688973,0.000114871815,0.00023632517],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009948451,0.00017973773,0.00021915548,0.00009706301,0.0019644855,0.00199953,0.0022772697,0.000062930674,0.000059910635],"category_scores_gemma":[0.0001426118,0.0001428826,0.000120522855,0.0000728713,0.000057236157,0.0009900557,0.0011319557,0.00053856336,0.0003075216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016368348,0.00030061728,0.00075412483,0.00002305601,0.00013112611,0.0014676942,0.0012629358,0.013974339,0.0024310024,0.018151239,0.030317923,0.9310223],"study_design_scores_gemma":[0.0017091925,0.00073490385,0.0074036703,0.0004919949,0.000012626178,0.0010644387,0.00003048252,0.93490946,0.003449104,0.0031873523,0.046371106,0.00063567783],"about_ca_topic_score_codex":0.000003819177,"about_ca_topic_score_gemma":7.932452e-8,"teacher_disagreement_score":0.9303866,"about_ca_system_score_codex":0.00008000729,"about_ca_system_score_gemma":0.00008334249,"threshold_uncertainty_score":0.9993348},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59725213,0.0021262718,0.2848247,0.0019300896,0.011644875,0.0034595963,0.00021621893,0.0019096439,0.096636474],"genre_scores_gemma":[0.9161814,0.00038139158,0.034390986,0.00007051082,0.0010776178,0.000042126638,0.00015876925,0.00013917946,0.047558058],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99091643,0.0014252381,0.0005998972,0.0026791722,0.0027101215,0.0016691134],"domain_scores_gemma":[0.99187565,0.0006295323,0.00038405645,0.0048409337,0.0013696579,0.00090014416],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0018181746,0.00073018955,0.0007785979,0.0023658064,0.0017386577,0.0012542494,0.008163257,0.0011805225,0.00004661393],"category_scores_gemma":[0.00017403913,0.00076075294,0.00048692193,0.0017595219,0.0007500936,0.0005021797,0.015480236,0.005812278,0.00021370735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002725353,0.013036978,0.00394522,0.0069403723,0.0030307788,0.10671884,0.016211547,0.043000367,0.26598138,0.2586324,0.11895969,0.16081707],"study_design_scores_gemma":[0.0018440802,0.00037164145,0.0030574212,0.0009459224,0.00007777269,0.00024997885,0.0004354402,0.8449138,0.003310412,0.0018589239,0.14089078,0.0020438307],"about_ca_topic_score_codex":0.0012771068,"about_ca_topic_score_gemma":0.000095838484,"teacher_disagreement_score":0.80191344,"about_ca_system_score_codex":0.0010918047,"about_ca_system_score_gemma":0.001920978,"threshold_uncertainty_score":0.99978256},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74363524,0.00026334458,0.2319031,0.0060112625,0.0011581412,0.0035153814,0.0025484243,0.0003073005,0.010657813],"genre_scores_gemma":[0.9709241,0.00003206205,0.02859261,0.00017948446,0.00007661846,0.000026343738,0.000047712394,0.000009684044,0.00011143352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982499,0.000017052453,0.00052678736,0.00033847755,0.0005293187,0.00033849722],"domain_scores_gemma":[0.96501595,0.00016796862,0.00089374813,0.00061605073,0.03317967,0.00012660658],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005153861,0.00021748063,0.0003426807,0.00013099708,0.00018536589,0.003155253,0.0052819853,0.00012965113,0.000011496791],"category_scores_gemma":[0.0054926355,0.00015243498,0.00008732172,0.00036095412,0.00018723961,0.050328445,0.0032723467,0.00019885894,0.000007688986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009886369,0.0007142583,0.018723683,0.0014001308,0.00033209045,8.932315e-7,0.068738036,0.000085698615,0.06243717,0.19685657,0.21551211,0.43421072],"study_design_scores_gemma":[0.0027454668,0.0012359888,0.07834763,0.0012784504,0.00010720759,0.000045676603,0.0038891602,0.60153687,0.077186614,0.0258745,0.20667604,0.0010764293],"about_ca_topic_score_codex":0.00017471245,"about_ca_topic_score_gemma":0.0000013753368,"teacher_disagreement_score":0.60145116,"about_ca_system_score_codex":0.000029989891,"about_ca_system_score_gemma":0.0001830249,"threshold_uncertainty_score":0.99787956},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8860305,0.009956194,0.00651771,0.00718214,0.04176061,0.001126283,0.0001545682,0.0004705214,0.046801485],"genre_scores_gemma":[0.9948924,0.00068363926,0.0026949942,0.00016299832,0.000060957158,0.000009690258,0.000007939541,0.00002840176,0.0014589357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99759287,0.000088953144,0.00033698435,0.0008695431,0.0004794903,0.0006321675],"domain_scores_gemma":[0.99607426,0.00010101037,0.000397277,0.0029109528,0.0001405793,0.00037591552],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005098129,0.0003443267,0.00040572067,0.00007253158,0.0019314894,0.0024947976,0.0023836535,0.00021379077,0.000059982904],"category_scores_gemma":[0.00017462896,0.0003295972,0.000084669075,0.00009502901,0.00033230108,0.0021164822,0.0034117587,0.00036088174,0.00026336752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016083755,0.00021356835,0.0066217356,0.00006836917,0.000043699936,0.00018186485,0.00050905993,0.0000015346271,0.00023342411,0.8695397,0.018443622,0.10412735],"study_design_scores_gemma":[0.0029839466,0.00040754865,0.086185746,0.00046214357,0.000056409284,0.000060357008,0.000057084162,0.05014843,0.0011275408,0.8048925,0.052606303,0.0010120127],"about_ca_topic_score_codex":0.0004047201,"about_ca_topic_score_gemma":0.000008251961,"teacher_disagreement_score":0.10886195,"about_ca_system_score_codex":0.000051605686,"about_ca_system_score_gemma":0.00013856174,"threshold_uncertainty_score":0.9999156},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48516685,0.018059654,0.21297823,0.025099574,0.052287564,0.009191524,0.0016803116,0.0058591235,0.18967718],"genre_scores_gemma":[0.8915093,0.004090845,0.06002333,0.0020976197,0.0049787574,0.00020833392,0.0005401575,0.00032102736,0.03623061],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98772496,0.0004053848,0.0028919305,0.0023378148,0.0033358173,0.003304064],"domain_scores_gemma":[0.9879679,0.0007474243,0.0033922794,0.0052754357,0.0010818846,0.0015350463],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","research_integrity"],"category_scores_codex":[0.0022174448,0.0019745294,0.0020003156,0.0009152288,0.0069468245,0.0049535097,0.012062409,0.0013354726,0.00013728482],"category_scores_gemma":[0.0016512019,0.001705126,0.0011408738,0.0006613153,0.0014641926,0.009103854,0.009087523,0.0036556935,0.00095694116],"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":[0.0026680732,0.003177806,0.01194915,0.0009029736,0.0017430049,0.005155546,0.0047417087,0.0010736653,0.051248338,0.11553966,0.09700454,0.70479554],"study_design_scores_gemma":[0.008529314,0.003031474,0.0653453,0.002688985,0.00031185878,0.0028418754,0.00093725533,0.14140445,0.039524447,0.0033461554,0.7270519,0.004986976],"about_ca_topic_score_codex":0.00018984762,"about_ca_topic_score_gemma":0.000045887402,"teacher_disagreement_score":0.69980854,"about_ca_system_score_codex":0.000746413,"about_ca_system_score_gemma":0.0014334661,"threshold_uncertainty_score":0.999961},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047395054,0.00009525475,0.934778,0.0009786763,0.0006002847,0.0009259902,0.00003804763,0.00039849203,0.014790211],"genre_scores_gemma":[0.7561931,0.00019094127,0.14962901,0.00007788092,0.0006876794,0.00006362993,0.000017612849,0.00007031191,0.09306983],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.996265,0.00047044936,0.00027334117,0.0010648691,0.00092935504,0.0009970102],"domain_scores_gemma":[0.9962694,0.0009924154,0.00012766942,0.0014873229,0.00068230525,0.00044086436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089585746,0.00024512742,0.00029915606,0.0007250239,0.0009958443,0.00037044624,0.0026612505,0.00016662989,0.000018375245],"category_scores_gemma":[0.00022893347,0.00018715877,0.00018940486,0.00103706,0.0002986381,0.0017623005,0.0009843564,0.00029987367,0.00006266445],"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":[0.00058901537,0.00039037724,0.00068160094,0.000107593754,0.00014957669,0.00059624633,0.00045104136,0.000008130286,0.831488,0.09149417,0.012172829,0.061871395],"study_design_scores_gemma":[0.003881346,0.000985127,0.0012359637,0.0003250884,0.00002049797,0.000075549666,0.00014224157,0.0024446403,0.2082186,0.0038773657,0.7780835,0.00071005506],"about_ca_topic_score_codex":0.00013445088,"about_ca_topic_score_gemma":0.0000054926927,"teacher_disagreement_score":0.785149,"about_ca_system_score_codex":0.0003957156,"about_ca_system_score_gemma":0.00038322704,"threshold_uncertainty_score":0.7659329},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31531078,0.000010292351,0.682184,0.0001931471,0.0009189884,0.000081005004,0.000013937338,0.0001835106,0.0011043643],"genre_scores_gemma":[0.87297326,0.0000020575337,0.12674843,0.000117909316,0.00014163884,0.0000022387435,0.000003838689,0.000006975976,0.00000364552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972719,0.000115803836,0.00027759233,0.00096183654,0.00075133325,0.0006215419],"domain_scores_gemma":[0.997015,0.00019102191,0.0002534236,0.0019363437,0.00022105446,0.0003831416],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012422726,0.00020778626,0.00024740555,0.00013003816,0.0020161383,0.0028302083,0.006636079,0.00008201687,0.000027056622],"category_scores_gemma":[0.00029407552,0.00017427765,0.00005558661,0.00029474936,0.0020925167,0.0037192646,0.0036809382,0.00029538805,0.000032818643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027576555,0.000037960977,0.0007371766,0.0000012782339,0.0000039632505,0.000031219224,0.0001648305,0.000011772971,0.00061180687,0.7934161,0.000006105313,0.20497505],"study_design_scores_gemma":[0.0003207952,0.00011134402,0.0127883,0.00007259988,0.0000045087836,0.000014856845,0.000010582936,0.81629086,0.008645186,0.16143698,0.000013303683,0.00029066883],"about_ca_topic_score_codex":0.000038062237,"about_ca_topic_score_gemma":0.000004199874,"teacher_disagreement_score":0.8162791,"about_ca_system_score_codex":0.0000617182,"about_ca_system_score_gemma":0.00010186965,"threshold_uncertainty_score":0.9992831},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016852278,0.000007820697,0.9802863,0.00025023945,0.00024413053,0.00018816235,0.00014911647,0.00010006413,0.0019219131],"genre_scores_gemma":[0.3091523,0.0000037119626,0.69071716,0.000037453046,0.000021770804,0.000011123144,0.0000047305666,0.0000036582749,0.00004810126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898237,0.00004655074,0.0002566483,0.00033013933,0.00016961782,0.00021469478],"domain_scores_gemma":[0.99894977,0.00034329866,0.0001372633,0.00037092343,0.00012822932,0.000070518465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036079486,0.00011325791,0.0001788025,0.00006036161,0.00010865767,0.000046547022,0.00045398288,0.00006349588,0.000027964525],"category_scores_gemma":[0.00010596887,0.000071004324,0.00004266574,0.00011919105,0.00018542618,0.0007291911,0.00014660851,0.00004752467,0.0000029362927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001541731,0.000036596037,0.00020763317,0.00003328563,0.000018872624,7.8535913e-7,0.00010648025,0.000009295837,0.06386167,0.7860035,0.0003070286,0.14939944],"study_design_scores_gemma":[0.0045534098,0.0007077781,0.00060202,0.0005306774,0.00004194846,0.00037812808,0.00029004202,0.6594607,0.16720706,0.15583308,0.009373105,0.0010219957],"about_ca_topic_score_codex":0.000052773965,"about_ca_topic_score_gemma":0.0000021118299,"teacher_disagreement_score":0.6594514,"about_ca_system_score_codex":0.00002299455,"about_ca_system_score_gemma":0.00009751759,"threshold_uncertainty_score":0.28954723},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07043975,0.000030237896,0.9103226,0.00013922718,0.0001349896,0.00003976682,3.4101282e-7,0.00002410634,0.018868964],"genre_scores_gemma":[0.9254312,0.000011446308,0.074164644,0.000049813967,0.000020717807,7.528001e-7,2.922897e-7,0.0000018085705,0.00031931736],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995567,0.000006440303,0.000117102885,0.00008538163,0.00011109365,0.00012325397],"domain_scores_gemma":[0.9995774,0.00009394015,0.000025081601,0.00026782867,0.000014996345,0.000020774867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035416725,0.00003049355,0.000039630188,0.000017418233,0.000038528928,0.000027494998,0.00042219117,0.000014873016,0.000011870766],"category_scores_gemma":[0.00000932412,0.000017560205,0.00001289832,0.00016158356,0.000013463273,0.00015337668,0.00023618517,0.000045870784,0.000013886544],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068279264,0.000052718857,0.011610219,0.0000037035275,0.0000032613523,0.000015247023,0.00027813358,0.000015381585,0.00073304534,0.3477848,0.00092635304,0.6385703],"study_design_scores_gemma":[0.0020578662,0.000115299794,0.4647015,0.00016118062,0.0000039396527,0.00008011522,0.00086576614,0.16168182,0.050327267,0.17003483,0.14929333,0.00067709666],"about_ca_topic_score_codex":0.00018675814,"about_ca_topic_score_gemma":0.0001082614,"teacher_disagreement_score":0.85499144,"about_ca_system_score_codex":0.000007258256,"about_ca_system_score_gemma":0.000011451406,"threshold_uncertainty_score":0.07845432},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8305792,0.00024555152,0.16663413,0.00015803313,0.0010443851,0.0007622249,0.00038273382,0.00014467737,0.000049030125],"genre_scores_gemma":[0.9398573,0.00024184122,0.059445605,0.00007020947,0.00018464516,0.00006527471,0.000032092335,0.000042630425,0.000060413124],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615145,0.00007593949,0.00062242016,0.0013831565,0.0006657478,0.0011012589],"domain_scores_gemma":[0.99730194,0.00038736622,0.00045388032,0.0010707967,0.00042516144,0.0003608623],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015397464,0.0006548003,0.00089326926,0.00040096257,0.0029159272,0.0035503337,0.0014079043,0.00021838739,0.000010393522],"category_scores_gemma":[0.00043430287,0.0005445989,0.00005778067,0.00024697641,0.0008334984,0.0032401937,0.001453924,0.00019943852,0.0000018296905],"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":[0.00023239282,0.00006421203,0.0000895257,0.00042970967,0.000019784222,0.000006031461,0.00078831665,0.0036219032,0.9687583,0.017231917,0.000064127606,0.00869381],"study_design_scores_gemma":[0.0012789414,0.0005761588,0.003201775,0.002433399,0.000042218035,0.000077458884,0.00031492717,0.6246037,0.3638148,0.0017478307,0.0009481524,0.0009606513],"about_ca_topic_score_codex":0.00018785623,"about_ca_topic_score_gemma":0.000015500123,"teacher_disagreement_score":0.62098175,"about_ca_system_score_codex":0.000100670455,"about_ca_system_score_gemma":0.00022479605,"threshold_uncertainty_score":0.99970055},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03521422,0.00007784375,0.9532817,0.00014309905,0.010770714,0.00021497102,0.000003148404,0.00004990699,0.00024437302],"genre_scores_gemma":[0.768629,0.000009964267,0.22912434,0.000038950908,0.0021635944,0.000004230285,0.000005699175,0.000020813433,0.0000033930253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977832,0.00008403022,0.00091692834,0.00026806016,0.0006411102,0.00030669096],"domain_scores_gemma":[0.996676,0.0011641824,0.0010238102,0.0002918366,0.00065270613,0.00019141824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015598561,0.00024247238,0.000569817,0.00017905796,0.0003859494,0.00040398154,0.00070827216,0.000121436926,0.0000023906796],"category_scores_gemma":[0.0005500142,0.00021629508,0.00017167252,0.0002086322,0.000051873645,0.00064395164,0.0002831455,0.00026115825,0.0000016595156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027022843,0.00022782652,0.000021272901,0.0000876678,0.000045182627,0.000003522362,0.00070770935,0.00018539299,0.00065108895,0.9897628,0.0004658318,0.007814684],"study_design_scores_gemma":[0.0034918757,0.00072902447,0.000070953516,0.00015765958,0.000028773706,0.000079357225,0.000100211,0.29968,0.0011407329,0.6913482,0.0029274602,0.00024576543],"about_ca_topic_score_codex":0.0000026323673,"about_ca_topic_score_gemma":4.7353364e-8,"teacher_disagreement_score":0.73341477,"about_ca_system_score_codex":0.000060717768,"about_ca_system_score_gemma":0.000099356526,"threshold_uncertainty_score":0.8820258},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12696938,0.000046020858,0.84670466,0.024758434,0.00035811603,0.00012289376,0.0000025721927,0.00012866071,0.0009092543],"genre_scores_gemma":[0.97594094,0.000008939091,0.018766517,0.0051672338,0.00007078122,0.0000067138753,0.0000070702126,0.000003360672,0.000028430675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931294,0.000015835965,0.00016809258,0.00011676835,0.00021714995,0.00016923253],"domain_scores_gemma":[0.9990825,0.000030887128,0.00028862464,0.0005054394,0.000049402843,0.000043143675],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00031821037,0.00009194244,0.00007590703,0.000047861402,0.0016590275,0.00249924,0.00078981783,0.000033042503,0.0000022749693],"category_scores_gemma":[0.00007964961,0.00006296838,0.000017466222,0.000061246006,0.00007815066,0.0073888265,0.00045652804,0.00013736617,0.000025621634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008577386,0.000009163049,0.0039780643,0.000076778444,0.0000068739064,0.000004704506,0.004232529,0.00009911266,0.0005542218,0.0017416773,0.0147907,0.9744976],"study_design_scores_gemma":[0.0010136178,0.000024469387,0.20387267,0.000337965,0.000013164467,0.000097824595,0.00023233808,0.6909168,0.0019483321,0.00083808,0.100161515,0.0005432329],"about_ca_topic_score_codex":0.000041202275,"about_ca_topic_score_gemma":0.0000021371618,"teacher_disagreement_score":0.9739544,"about_ca_system_score_codex":0.000018175297,"about_ca_system_score_gemma":0.000025362859,"threshold_uncertainty_score":0.9996407},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08395961,0.00002661087,0.90958196,0.00057467027,0.0015576043,0.00009777179,0.00000594491,0.00018180745,0.004014034],"genre_scores_gemma":[0.6748343,0.000004075302,0.3247857,0.000107868465,0.0002562476,0.0000021498006,7.094276e-7,0.0000047945564,0.0000041109593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748975,0.000058245096,0.00026524716,0.0009501975,0.0006554326,0.00058114255],"domain_scores_gemma":[0.99697196,0.00020909234,0.00019302791,0.0021607995,0.00015207594,0.00031301967],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00096917385,0.00019044318,0.00022186892,0.00009990585,0.0021451402,0.0025517151,0.006497394,0.00005618356,0.0000667683],"category_scores_gemma":[0.00024645287,0.00015484371,0.00005962894,0.00022544626,0.0016250621,0.0026801974,0.004214851,0.00025541082,0.00011352741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031130253,0.000016796224,0.00022270715,0.000002085973,0.0000027425128,0.000018555353,0.00015563975,0.000021253782,0.0015953651,0.81100386,0.000028631024,0.18692923],"study_design_scores_gemma":[0.00023266739,0.00005014787,0.0018834837,0.000077912024,0.0000026709151,0.000025868476,0.000004761043,0.8550878,0.013488328,0.12878455,0.00013285216,0.00022890832],"about_ca_topic_score_codex":0.000025933588,"about_ca_topic_score_gemma":5.971187e-7,"teacher_disagreement_score":0.8550666,"about_ca_system_score_codex":0.00004342552,"about_ca_system_score_gemma":0.000109289766,"threshold_uncertainty_score":0.9991539},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013802733,0.023179768,0.9547789,0.0000061392698,0.0037302885,0.00042084148,0.000010536675,0.00010524956,0.017630218],"genre_scores_gemma":[0.29796985,0.01737642,0.6720885,0.00014030337,0.0056956746,0.000050933522,0.00023145125,0.00031849006,0.006128373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743974,0.00014714774,0.00087547937,0.00086747576,0.00032406475,0.00034611888],"domain_scores_gemma":[0.99757713,0.00055038574,0.0008994563,0.00069974124,0.00017310734,0.000100154575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010878384,0.00042899512,0.0006405284,0.00027200274,0.0003725422,0.0005087138,0.00063888886,0.00026637124,0.000007530827],"category_scores_gemma":[0.000066786175,0.00041244732,0.00010079523,0.00003977595,0.000055899043,0.0013470666,0.00035434423,0.0004925803,0.00000895228],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047249428,0.000010719616,0.000016783075,0.0003748793,0.000020878664,0.000026278276,0.0018445851,0.001097761,0.000038955037,0.0016638716,0.0000016795215,0.99489886],"study_design_scores_gemma":[0.00027746445,0.0001119613,0.0000070111296,0.010984917,0.000051670493,0.00013905179,0.00035508946,0.9344789,0.0003498533,0.007774994,0.04440212,0.001066983],"about_ca_topic_score_codex":0.00025897782,"about_ca_topic_score_gemma":0.000048302296,"teacher_disagreement_score":0.9938319,"about_ca_system_score_codex":0.00012035474,"about_ca_system_score_gemma":0.000041509782,"threshold_uncertainty_score":0.99983275},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011183884,0.000015564174,0.9847211,0.002596175,0.00023883996,0.00013062535,0.00001959576,0.00011715648,0.000977064],"genre_scores_gemma":[0.62280613,9.87116e-7,0.3759228,0.0011899644,0.000069537506,0.0000019778176,0.0000026897776,0.000004088127,0.000001834209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780536,0.00007477632,0.00034435565,0.00062359165,0.0006824639,0.00046948128],"domain_scores_gemma":[0.99856347,0.00012880139,0.000109343026,0.00070582837,0.00016675067,0.00032581316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000560223,0.00014622115,0.00019887145,0.000094049756,0.00025877095,0.00027371777,0.002481792,0.00003083139,0.00008221243],"category_scores_gemma":[0.00004940547,0.000119316275,0.000067469446,0.000960655,0.0010354922,0.0009310798,0.0020136412,0.00013094427,0.000036374862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008744149,0.000079484045,0.00006332659,0.000010086289,0.0000037012117,0.000008278347,0.0009023723,0.00006917977,0.0024047247,0.97370803,0.0007395682,0.022002487],"study_design_scores_gemma":[0.00047536992,0.00051671773,0.00052420923,0.00002773575,0.0000057217644,0.0000131030765,0.000039136146,0.98385364,0.0073518627,0.0041675996,0.002804585,0.0002203249],"about_ca_topic_score_codex":0.0000027239457,"about_ca_topic_score_gemma":2.3612635e-7,"teacher_disagreement_score":0.98378444,"about_ca_system_score_codex":0.000024772344,"about_ca_system_score_gemma":0.00008045917,"threshold_uncertainty_score":0.48655763},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024003163,0.000003952692,0.973462,0.00006689245,0.0013182468,0.00023282369,0.00006207497,0.0002564492,0.022197232],"genre_scores_gemma":[0.9851705,0.0000330909,0.0105810575,0.001777893,0.000047424594,0.000022682147,0.000037397436,0.000016595237,0.0023133669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987557,0.000092701936,0.0003062348,0.00019531562,0.00039897885,0.0002510513],"domain_scores_gemma":[0.998707,0.00032645446,0.00015033867,0.00062021543,0.00009969788,0.00009627274],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046478372,0.00018082214,0.00014935038,0.0003309024,0.0003112148,0.00023822005,0.00052207324,0.00010606739,0.0003379296],"category_scores_gemma":[0.000006076359,0.0001659931,0.00006420109,0.00038276298,0.000032869277,0.0039782478,0.000008728439,0.00032146514,0.0017506642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029309175,0.0001754383,0.000008055634,0.000058981623,0.00008054213,0.0000011763079,0.0027780803,0.19840777,0.0003134747,0.38139895,0.001442287,0.41504216],"study_design_scores_gemma":[0.0028904653,0.0007083401,0.000105734274,0.00029341673,0.000032312986,0.000029393908,0.0018154441,0.78245103,0.0065759867,0.0043294528,0.1999837,0.00078473246],"about_ca_topic_score_codex":0.00002442665,"about_ca_topic_score_gemma":7.700899e-7,"teacher_disagreement_score":0.9827702,"about_ca_system_score_codex":0.0001072613,"about_ca_system_score_gemma":0.00008874241,"threshold_uncertainty_score":0.9990266},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052099153,0.009034687,0.92568374,0.00018289464,0.011573397,0.00031543264,0.000037315916,0.00012893832,0.00094445917],"genre_scores_gemma":[0.2680689,0.0027029428,0.702337,0.002353473,0.0035799963,0.000014811364,0.02025509,0.00009535773,0.00059240975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979632,0.00013196608,0.0004933238,0.00091155217,0.0001540243,0.00034596806],"domain_scores_gemma":[0.9981087,0.00045572626,0.0003043739,0.0009539084,0.0000635548,0.000113735725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008455479,0.0002949583,0.00058473856,0.00039766246,0.00020320914,0.000026930287,0.0015275956,0.00040306337,0.000008473726],"category_scores_gemma":[0.00010634658,0.00022482238,0.000019881663,0.00028748342,0.00014905848,0.0002528542,0.0008878537,0.0005590438,0.0000016683732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014435711,0.00011777769,0.003203231,0.00029079878,0.00006833887,0.00021947298,0.0023738798,0.00005931104,0.0025722976,0.0045849723,0.009000037,0.97736555],"study_design_scores_gemma":[0.001991752,0.00034724642,0.0100669535,0.0052119996,0.00005785195,0.00029384045,0.0007225195,0.9594406,0.00020873305,0.0046525444,0.016217893,0.0007880554],"about_ca_topic_score_codex":0.0002971556,"about_ca_topic_score_gemma":0.00015074646,"teacher_disagreement_score":0.97657746,"about_ca_system_score_codex":0.000035436013,"about_ca_system_score_gemma":0.00007186814,"threshold_uncertainty_score":0.91679907},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019208437,0.0011227318,0.9915703,0.001291389,0.0026691516,0.00091580156,0.00003618875,0.0002730322,0.0021021834],"genre_scores_gemma":[0.010021832,0.00003831557,0.98705035,0.000712129,0.0012485967,0.00003298413,0.00003470039,0.000058876543,0.0008022029],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99445915,0.000033033535,0.00079881103,0.0023182814,0.0013350133,0.0010557098],"domain_scores_gemma":[0.99599195,0.0006832191,0.00048259177,0.0021474573,0.00038687733,0.00030791177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093574607,0.0007804579,0.00089457823,0.00083636516,0.0004947048,0.0008001233,0.0047992175,0.0004391881,0.0000254204],"category_scores_gemma":[0.00009521379,0.00068318786,0.0002394441,0.0006217117,0.0005384542,0.00051363197,0.0021486497,0.00080413563,0.000062310675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010344405,0.0000804505,0.0000064817814,0.00002844973,0.00001045757,0.000017854745,0.00037601741,0.09288334,0.00006860195,0.013322502,0.00029905827,0.8928964],"study_design_scores_gemma":[0.0006157208,0.0002481092,0.000042376738,0.0002934521,0.000011498125,0.00003384482,2.4744443e-7,0.94610775,0.0010893872,0.019368585,0.031373806,0.0008152407],"about_ca_topic_score_codex":0.000026008907,"about_ca_topic_score_gemma":0.00007483354,"teacher_disagreement_score":0.8920812,"about_ca_system_score_codex":0.00039524765,"about_ca_system_score_gemma":0.00057660334,"threshold_uncertainty_score":0.9995619},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009994427,0.00012879644,0.9883642,0.0003352389,0.00037071822,0.00035201956,0.00008538531,0.00025223845,0.00011697336],"genre_scores_gemma":[0.37937298,0.00008454432,0.61978036,0.00009215436,0.000039213388,0.000112299866,0.000011268226,0.000019052823,0.00048814772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877226,0.000035895027,0.00024568028,0.000490772,0.00017967282,0.00027573595],"domain_scores_gemma":[0.9986624,0.00023422396,0.00007334307,0.0008137616,0.00007763869,0.00013861347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015963268,0.00019365824,0.00017843691,0.00021691255,0.00050208875,0.00008232868,0.0006773675,0.0001121162,0.00005977388],"category_scores_gemma":[0.00002698396,0.00017139007,0.00008099994,0.00029608252,0.00005854993,0.0008216684,0.000042011976,0.00019695249,0.000024198132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057162983,0.00052842766,0.00028126227,0.000014699804,0.000075309035,0.000010837023,0.0013634122,0.00021757609,0.000498174,0.0030524554,0.0003894029,0.99351126],"study_design_scores_gemma":[0.0073251575,0.002778842,0.13634278,0.00023423211,0.00019441171,0.0001195197,0.00046636898,0.7849239,0.022805603,0.026775302,0.016188899,0.0018449982],"about_ca_topic_score_codex":0.00017566782,"about_ca_topic_score_gemma":0.00003755317,"teacher_disagreement_score":0.99166626,"about_ca_system_score_codex":0.00002948634,"about_ca_system_score_gemma":0.000042096613,"threshold_uncertainty_score":0.69890845},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026499005,0.00013525717,0.9910496,0.00023344849,0.0023996758,0.0007764285,0.00021748296,0.0009787316,0.0015594639],"genre_scores_gemma":[0.05357224,0.000052621945,0.9443424,0.00017014387,0.000833516,0.00009556422,0.00038937345,0.00008789602,0.00045627743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640435,0.00015140913,0.0005528585,0.0015317595,0.0007636579,0.00059595023],"domain_scores_gemma":[0.99620116,0.00026835073,0.00053552596,0.0024720985,0.00028545217,0.00023740684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020376573,0.000662426,0.0007875874,0.00022927026,0.00023329945,0.0005328154,0.0024250387,0.00046233123,0.000055507713],"category_scores_gemma":[0.000023135068,0.0005502727,0.00016227682,0.00027126385,0.00015865815,0.0004888816,0.0030148285,0.0009873186,0.00054495863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034536587,0.0016607543,0.0011339805,0.001613237,0.0017095163,0.0009839144,0.0023177466,0.04114086,0.0010697222,0.0085198665,0.01234473,0.9271603],"study_design_scores_gemma":[0.00076214457,0.00028744803,0.0003330837,0.00036718382,0.00007968324,0.00022583426,0.000011617374,0.98886436,0.0006952446,0.0011781533,0.0063386816,0.00085657375],"about_ca_topic_score_codex":0.00006838793,"about_ca_topic_score_gemma":0.0000015510607,"teacher_disagreement_score":0.9477235,"about_ca_system_score_codex":0.000112875015,"about_ca_system_score_gemma":0.0005015259,"threshold_uncertainty_score":0.9996949},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7577396,0.0009061147,0.21769442,0.011637031,0.0022567923,0.0005361802,0.000027020684,0.00007805694,0.009124804],"genre_scores_gemma":[0.9987186,0.00003475754,0.0010773288,0.000103132996,0.00001824265,0.000005400404,3.2505798e-7,0.0000012122409,0.00004095544],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99738973,0.00014739315,0.00022765344,0.00037097177,0.0015404222,0.00032382665],"domain_scores_gemma":[0.99725693,0.00030537523,0.00020299824,0.001976705,0.00009947192,0.0001585335],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0052133542,0.000072051254,0.00013248132,0.00005299084,0.0010521525,0.00032959672,0.009834886,0.00004103728,0.0000094813895],"category_scores_gemma":[0.0030021167,0.00003245674,0.000051497944,0.0012682823,0.001780103,0.0006879766,0.001648013,0.00019753663,0.0000057827474],"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":[0.0000074625914,0.00011020959,0.521431,0.000003355366,0.000025157959,0.000008201086,0.00075815537,0.00008708347,0.0053535174,0.030466672,0.00015641504,0.44159272],"study_design_scores_gemma":[0.00007455161,0.000013233616,0.85419875,0.00003239376,0.000003912232,0.0000021282142,0.00001818145,0.13788304,0.0023670937,0.0040841266,0.0012594123,0.000063196436],"about_ca_topic_score_codex":0.0027136635,"about_ca_topic_score_gemma":0.0021541195,"teacher_disagreement_score":0.44152954,"about_ca_system_score_codex":0.000028053362,"about_ca_system_score_gemma":0.0004960883,"threshold_uncertainty_score":0.9955224},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12105167,0.00012159253,0.87714833,0.00010138784,0.00039116846,0.000095483396,0.00002337759,0.000054562905,0.0010124438],"genre_scores_gemma":[0.92652816,0.000041577423,0.07320848,0.00007624794,0.000060769176,0.0000018760741,0.000011346564,0.000006524478,0.00006504338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989285,0.00004478946,0.00023117587,0.00032661992,0.00027873978,0.00019017393],"domain_scores_gemma":[0.99762523,0.000077368626,0.00025141196,0.0019057207,0.00005929436,0.00008096959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017149479,0.00012379252,0.00022393429,0.00006829877,0.00044018487,0.00019056645,0.0016309939,0.0000314221,0.000047756555],"category_scores_gemma":[0.000041893712,0.00008792734,0.00006835278,0.000052929732,0.00009141246,0.0014074561,0.0015846005,0.00007801871,0.000011206182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009744684,0.00060269976,0.08029473,0.00013588955,0.00008421628,0.000090188834,0.00031597292,0.00030157602,0.11643213,0.009227,0.0068995384,0.7855186],"study_design_scores_gemma":[0.0035046227,0.000058452468,0.036360204,0.00041779454,0.000020528456,0.000034641504,0.000022699944,0.89220536,0.05901934,0.0009911442,0.0069289254,0.0004362689],"about_ca_topic_score_codex":0.0012007344,"about_ca_topic_score_gemma":0.000017233167,"teacher_disagreement_score":0.8919038,"about_ca_system_score_codex":0.000006034689,"about_ca_system_score_gemma":0.000025214284,"threshold_uncertainty_score":0.3585573},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20454505,0.00004947568,0.790995,0.0001471486,0.00090325525,0.00008746448,0.000009662998,0.000060539656,0.00320242],"genre_scores_gemma":[0.61931056,0.000025569876,0.38051653,0.000025626829,0.000045112472,0.0000010679627,0.0000037324614,0.0000044600033,0.00006732294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897856,0.00003060613,0.00026537417,0.0003140602,0.00024202581,0.00016938914],"domain_scores_gemma":[0.99827856,0.00006993364,0.0003091041,0.0011383661,0.00013419293,0.000069857575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017778472,0.00011486071,0.00019372189,0.000076330485,0.00036367564,0.0002385392,0.0010907167,0.00006756568,0.000032764157],"category_scores_gemma":[0.000116299016,0.00009117145,0.000054677872,0.00008467091,0.00015745124,0.0011813912,0.0006184647,0.00008423379,0.000010002143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000658614,0.00015343243,0.010588921,0.00004449742,0.000046453508,0.000018184148,0.00048068402,0.00023696788,0.10953152,0.043913998,0.002387584,0.83253187],"study_design_scores_gemma":[0.0008042576,0.00012322499,0.010938159,0.00031964362,0.000011914264,0.00006495114,0.00015498567,0.90632296,0.073669195,0.005486272,0.0017815976,0.00032283834],"about_ca_topic_score_codex":0.00019695451,"about_ca_topic_score_gemma":0.000006087532,"teacher_disagreement_score":0.90608597,"about_ca_system_score_codex":0.000022445896,"about_ca_system_score_gemma":0.000053751457,"threshold_uncertainty_score":0.37178642},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026565855,0.00003912094,0.94112974,0.0012536367,0.0040028556,0.000853346,0.0009186608,0.00042988715,0.024806911],"genre_scores_gemma":[0.8731352,0.00010336287,0.118604176,0.0026958296,0.0007588646,0.0002816489,0.0007668028,0.000072997085,0.0035811001],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803966,0.000020152367,0.0005977533,0.00030479865,0.00046573352,0.0005719028],"domain_scores_gemma":[0.9966797,0.000088534776,0.00049627596,0.0023346168,0.0001936174,0.00020724443],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003558111,0.0003161521,0.00030863984,0.00014345536,0.0018349079,0.0016016794,0.0022779463,0.00015459362,0.00003095775],"category_scores_gemma":[0.00013993966,0.00025403744,0.00018642069,0.00008713316,0.0001419878,0.0038148921,0.0010536211,0.00032678863,0.00045004726],"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":[0.00032915303,0.001392081,0.009743359,0.0007864496,0.00035586924,0.00004240939,0.0118455775,0.0002580172,0.00012925982,0.3092946,0.24255058,0.4232726],"study_design_scores_gemma":[0.0029596905,0.0006622439,0.008538288,0.00033049632,0.000025727122,0.00005384491,0.0005173674,0.15765563,0.00069212134,0.0032065075,0.82448816,0.0008699011],"about_ca_topic_score_codex":0.00003430063,"about_ca_topic_score_gemma":0.0000115425155,"teacher_disagreement_score":0.84656936,"about_ca_system_score_codex":0.00006502485,"about_ca_system_score_gemma":0.000070795024,"threshold_uncertainty_score":0.9999912},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018813804,0.000022039218,0.97276944,0.004115354,0.0006841915,0.00013296976,0.000007989303,0.00024153538,0.0032126643],"genre_scores_gemma":[0.937162,0.000005709324,0.05658754,0.0058646807,0.00014452383,0.000024435782,0.000078692,0.000011155713,0.00012130678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986783,0.000022633529,0.0003745207,0.00021264362,0.00042965496,0.00028223044],"domain_scores_gemma":[0.9982379,0.0000187374,0.0005368549,0.00093868974,0.00016687441,0.000100964506],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00019507362,0.0001768377,0.00014651594,0.00014188324,0.0010297777,0.0021531277,0.001377355,0.000065650165,0.000016898748],"category_scores_gemma":[0.00006750499,0.00014143824,0.000046234818,0.00009710503,0.00008833708,0.015497233,0.00068048394,0.0002002322,0.00016596972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002388313,0.00004374138,0.0012906732,0.000105353975,0.000012130147,0.000007888279,0.0031111625,0.0003492171,0.0021408685,0.0014182649,0.02494893,0.9665479],"study_design_scores_gemma":[0.0016364623,0.00005654516,0.017595042,0.0007243695,0.000012079491,0.000039622173,0.00018007238,0.71638787,0.0062661176,0.0003560518,0.2560188,0.0007270184],"about_ca_topic_score_codex":0.00003206445,"about_ca_topic_score_gemma":8.237161e-7,"teacher_disagreement_score":0.96582085,"about_ca_system_score_codex":0.00004026932,"about_ca_system_score_gemma":0.000048291313,"threshold_uncertainty_score":0.9988827},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47049978,0.0059816684,0.00965337,0.0042884722,0.0058574285,0.0008834822,0.0012843854,0.00006725389,0.50148416],"genre_scores_gemma":[0.98630613,0.00022938818,0.0011637389,0.0003931039,0.00008636475,0.000010875697,0.0001185556,0.000016216434,0.011675647],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975953,0.00005155871,0.00030162578,0.00032826985,0.0014149706,0.00030824615],"domain_scores_gemma":[0.99916786,0.00013133536,0.00021669336,0.00031994432,3.3643892e-7,0.00016382143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000010753524,0.00022300582,0.0002739722,0.000037415357,0.00009135569,0.0000747614,0.00067445345,0.00004667884,0.000013725614],"category_scores_gemma":[0.0000013499618,0.00019857172,0.00002482242,0.00008801236,0.000022184771,0.0016473712,0.00021883682,0.0001912034,2.662622e-9],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044042032,0.0002184894,0.09187642,0.0018372654,0.00018946343,0.00072830595,0.0016464506,0.000095358,0.02971983,0.2208063,0.0039914204,0.64845026],"study_design_scores_gemma":[0.00071650353,0.000116744435,0.82684445,0.0016427143,0.000032553107,0.000015529451,0.0040817126,0.012444034,0.11668182,0.0055874726,0.030371357,0.0014650833],"about_ca_topic_score_codex":0.011388053,"about_ca_topic_score_gemma":0.13256063,"teacher_disagreement_score":0.73496807,"about_ca_system_score_codex":0.000007153771,"about_ca_system_score_gemma":0.0015462982,"threshold_uncertainty_score":0.9951952},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8351896,0.0066276514,0.15173383,0.0043133916,0.0011348329,0.0002826229,0.000030995205,0.00004990936,0.0006372003],"genre_scores_gemma":[0.85854787,0.0025068903,0.13851981,0.000119376906,0.00020209886,0.0000037740547,0.0000028567138,0.000016901146,0.00008043555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99853474,0.000093963696,0.00043359984,0.0002967291,0.00036667654,0.00027430643],"domain_scores_gemma":[0.998478,0.000081634375,0.0005618497,0.00052573776,0.00015343189,0.00019936606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060179806,0.00018638905,0.00035494223,0.00030543658,0.00035430663,0.0006311904,0.00090971316,0.00009397744,0.0000052999526],"category_scores_gemma":[0.00011155002,0.00013643206,0.000052455336,0.00026456604,0.00018768816,0.0018702626,0.00060197816,0.00035437944,7.9395625e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059941376,0.0006781496,0.12790015,0.00020326972,0.00035869807,0.0026782004,0.0045257737,0.00020921661,0.01101855,0.0043460308,0.0061860555,0.8412965],"study_design_scores_gemma":[0.0054259417,0.0015681406,0.60412025,0.0008835257,0.00005539647,0.0009178726,0.00028713743,0.3674706,0.0006853658,0.01043059,0.0074185813,0.0007366259],"about_ca_topic_score_codex":0.00010594405,"about_ca_topic_score_gemma":0.000064838,"teacher_disagreement_score":0.84055984,"about_ca_system_score_codex":0.000018757648,"about_ca_system_score_gemma":0.00007284461,"threshold_uncertainty_score":0.60865843},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008712611,0.001124206,0.9848859,0.0032152925,0.000063924505,0.00046354794,0.00001635307,0.00006849911,0.0014496949],"genre_scores_gemma":[0.28510576,0.00043247498,0.71303153,0.00081263913,0.00015992115,0.00026414948,0.000009570861,0.000008153536,0.00017578126],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838823,0.00032052104,0.0002700533,0.00072068354,0.00012057034,0.0001799266],"domain_scores_gemma":[0.9972345,0.0010606657,0.000095714655,0.0013449483,0.00013746467,0.0001266816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027452772,0.00015103696,0.00021654094,0.000105907784,0.0006115635,0.00024977897,0.00042230613,0.00009028892,0.000015975314],"category_scores_gemma":[0.00034501893,0.00009170804,0.00003925942,0.00066856295,0.0010012023,0.00031415164,0.000551976,0.00020819106,0.0000067694587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006972691,0.00002366859,0.00060775585,0.0000122784995,0.00000879921,2.7983415e-8,0.00013061783,3.2767296e-8,0.00015954264,0.35971367,0.000094941395,0.6392417],"study_design_scores_gemma":[0.0010753417,0.00014574254,0.025295502,0.00003130297,0.00005577853,0.00007133938,0.00044841968,0.04957295,0.0029762667,0.6946747,0.22522715,0.00042555592],"about_ca_topic_score_codex":0.00013762164,"about_ca_topic_score_gemma":0.0000058488336,"teacher_disagreement_score":0.6388161,"about_ca_system_score_codex":0.000010483389,"about_ca_system_score_gemma":0.00001674709,"threshold_uncertainty_score":0.47037137},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10876864,0.00027085413,0.8857996,0.0006926456,0.0030548822,0.000093061084,0.000007876948,0.00006182386,0.0012506144],"genre_scores_gemma":[0.4892099,0.0002061811,0.5074253,0.00022485536,0.0026809298,0.0000017597371,0.0000044141607,0.000023783809,0.00022284169],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99813604,0.00008719947,0.00053628156,0.0002764677,0.0006512593,0.00031276804],"domain_scores_gemma":[0.9983271,0.000039764425,0.0005603421,0.00045028512,0.0003965024,0.00022605903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038882793,0.00018567825,0.0002799779,0.00024996116,0.00029260493,0.00019597873,0.0008969621,0.00008329511,0.00008514944],"category_scores_gemma":[0.000048856407,0.0001408059,0.00015568259,0.00037691204,0.00015676169,0.0019984017,0.00025673665,0.00031416724,0.000050703507],"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":[0.000520862,0.0004644278,0.0051158792,0.00015196795,0.0005140067,0.00065446296,0.004529148,0.00016477754,0.30367425,0.0052395156,0.0333949,0.6455758],"study_design_scores_gemma":[0.011473597,0.004651333,0.030611586,0.001631544,0.00021357743,0.0077043963,0.001487751,0.19782747,0.6220088,0.018880863,0.10105609,0.0024529777],"about_ca_topic_score_codex":0.00001850712,"about_ca_topic_score_gemma":0.0000014575697,"teacher_disagreement_score":0.6431228,"about_ca_system_score_codex":0.00008395124,"about_ca_system_score_gemma":0.00009156378,"threshold_uncertainty_score":0.5741898},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.6388736e-7,0.00004601289,0.6824634,0.00012750039,0.00023956441,0.0006578992,0.00034160452,0.00023828249,0.3158851],"genre_scores_gemma":[0.0009058275,0.000004557067,0.9792326,0.0013620472,0.00060008775,0.00004216397,0.00018606508,0.00005699671,0.017609634],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977709,0.000016642758,0.00049238116,0.00068503094,0.0005985473,0.00043647917],"domain_scores_gemma":[0.9986355,0.00005387429,0.00026289737,0.00072432804,0.00008802443,0.00023540776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020093778,0.00049872714,0.000426549,0.0001237098,0.00022030676,0.00038195014,0.0009829422,0.0003503798,0.000007657674],"category_scores_gemma":[0.0000025722811,0.00046525113,0.0002583214,0.000033101693,0.000015561205,0.0003275921,0.00010183473,0.00030113442,0.000042398184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011079893,0.000004988251,3.5395814e-8,0.000020693631,0.000009524372,0.000008389797,0.000053766475,0.00013653927,0.0000024834337,0.4757577,0.0013625247,0.5226323],"study_design_scores_gemma":[0.0012938869,0.00041211426,0.0000035515727,0.0008892527,0.000039984385,0.000028683911,0.000003517639,0.1841492,0.00012124775,0.71044594,0.101868406,0.0007441996],"about_ca_topic_score_codex":0.00008003229,"about_ca_topic_score_gemma":0.000015025618,"teacher_disagreement_score":0.5218881,"about_ca_system_score_codex":0.00023727468,"about_ca_system_score_gemma":0.00034605333,"threshold_uncertainty_score":0.99977994},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015714172,0.0004914179,0.7135951,0.26863712,0.0009474801,0.000085281645,0.000022539081,0.000019220952,0.0004876687],"genre_scores_gemma":[0.9660865,0.00003105739,0.0317337,0.0017033301,0.00018933156,0.0000014466489,8.280029e-7,0.000005635151,0.0002481458],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994097,0.000015363441,0.0001744265,0.000107390195,0.00007722235,0.00021594219],"domain_scores_gemma":[0.9985838,0.000017610115,0.00018826024,0.0008688273,0.0000873091,0.0002542186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002042607,0.00006123578,0.00010223748,0.00026266472,0.0006602111,0.00022367324,0.002901999,0.000092619826,0.000012532978],"category_scores_gemma":[0.00022803096,0.000041084688,0.000037035374,0.00013300599,0.00014139022,0.00024892553,0.00014888948,0.00025086387,0.00003339316],"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":[0.000006252898,0.00002723307,0.00052712177,0.000004831279,0.00005279624,0.00093994936,0.0012290981,0.0003379685,0.008097571,0.20055665,0.15602191,0.63219863],"study_design_scores_gemma":[0.00017242378,0.0001237051,0.009289005,0.000015617888,0.000005669845,0.0004749717,0.000051667692,0.0017440345,0.0023407275,0.0062451963,0.9794271,0.00010987232],"about_ca_topic_score_codex":0.0015688039,"about_ca_topic_score_gemma":0.006455509,"teacher_disagreement_score":0.95037234,"about_ca_system_score_codex":0.000042742908,"about_ca_system_score_gemma":0.00039755128,"threshold_uncertainty_score":0.53926843},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015324749,0.00009332048,0.9318512,0.0011572079,0.00075865194,0.000091560374,0.0000041378075,0.00021217267,0.06429926],"genre_scores_gemma":[0.86029077,0.00002246705,0.13442384,0.00044712887,0.00023942653,0.000012772816,0.0000041013723,0.000009351345,0.004550144],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908537,0.000021453665,0.00012824128,0.0003200057,0.00021846229,0.00022644436],"domain_scores_gemma":[0.9976543,0.000030015324,0.0001080377,0.0020511663,0.000045493885,0.00011096032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012589678,0.000104736006,0.0001347336,0.00003370557,0.00063906313,0.00075364334,0.0025800054,0.000042003994,0.000065170185],"category_scores_gemma":[0.000029803776,0.000077025186,0.000044108972,0.000032294887,0.000052164938,0.0010798166,0.00073548773,0.000087413086,0.00035976776],"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":[0.000016114755,0.00034057882,0.0025582789,0.00009602,0.00006530814,0.00013335208,0.0006617093,0.00007724126,0.012760414,0.33908388,0.14809531,0.49611178],"study_design_scores_gemma":[0.0015510574,0.00014154024,0.059470538,0.00016911594,0.000012801354,0.000102946564,0.000030511015,0.18900362,0.04001184,0.01534548,0.69314665,0.00101389],"about_ca_topic_score_codex":0.0002252847,"about_ca_topic_score_gemma":0.000010272667,"teacher_disagreement_score":0.8587583,"about_ca_system_score_codex":0.000011325006,"about_ca_system_score_gemma":0.000023662225,"threshold_uncertainty_score":0.72674},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7470101,0.00047949064,0.24992034,0.0012198179,0.00071690505,0.00023775012,0.000018599601,0.00009450881,0.000302493],"genre_scores_gemma":[0.8932042,0.00005492613,0.10599111,0.00040997865,0.00009580454,0.000016517815,0.00009485138,0.000031262338,0.000101321726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976297,0.00019999695,0.00034192172,0.000970034,0.00022662914,0.0006317295],"domain_scores_gemma":[0.9961841,0.00005770959,0.00026553095,0.003311583,0.000032867,0.00014817023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049565797,0.00021758932,0.00030184846,0.00015842942,0.0006582076,0.00033538433,0.0046123415,0.0002161296,0.000025700285],"category_scores_gemma":[0.00011950946,0.00020711219,0.000047379763,0.00011565019,0.0001383049,0.00071305956,0.0064453953,0.00035275397,0.000063018124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001110445,0.0010716862,0.04266078,0.000111445726,0.00024338646,0.011168916,0.008374601,0.008988252,0.07232487,0.00076170143,0.004245111,0.8499382],"study_design_scores_gemma":[0.00080828014,0.00006351625,0.15571338,0.00006544049,0.0000149409425,0.00011495801,0.000026316613,0.8371074,0.0005960156,0.0011816693,0.003988101,0.00031994696],"about_ca_topic_score_codex":0.0004381998,"about_ca_topic_score_gemma":0.00006742921,"teacher_disagreement_score":0.84961826,"about_ca_system_score_codex":0.00008777206,"about_ca_system_score_gemma":0.00007515209,"threshold_uncertainty_score":0.8570954},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47645354,0.00013605379,0.5184747,0.0001555819,0.0002981908,0.00023548587,0.000018466273,0.00014809416,0.004079914],"genre_scores_gemma":[0.9938043,0.00015434623,0.0046037966,0.00002867508,0.00006165506,2.8467437e-7,0.000013895262,0.000010286876,0.0013228081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985476,0.000096872034,0.0001220768,0.0008692288,0.00008409685,0.00028009806],"domain_scores_gemma":[0.9983684,0.000080144055,0.00015710107,0.0012143711,0.000048911847,0.00013106369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037172323,0.00019270045,0.00024373352,0.00029068315,0.00023579973,0.00039661824,0.0018240467,0.00018595718,0.000012533634],"category_scores_gemma":[0.000042690124,0.00020962623,0.00005427168,0.0001572475,0.000087274704,0.00079855707,0.0061903256,0.00066824333,0.00005442809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023758317,0.0007400541,0.09315201,0.0008175619,0.00030873244,0.00909756,0.0048008044,0.26887488,0.0008533766,0.40314355,0.003456519,0.21451735],"study_design_scores_gemma":[0.00032016833,0.000015761374,0.0070157736,0.0001943588,0.000005792864,0.0000046041705,0.000011393511,0.9719535,0.000025789277,0.019404214,0.0007881619,0.00026045385],"about_ca_topic_score_codex":0.0004614448,"about_ca_topic_score_gemma":0.000028438939,"teacher_disagreement_score":0.7030786,"about_ca_system_score_codex":0.000073488,"about_ca_system_score_gemma":0.00012972731,"threshold_uncertainty_score":0.854831},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049481858,0.000010388164,0.9912985,0.0005245768,0.00030850543,0.00021338931,0.00036527656,0.00006541701,0.0022657898],"genre_scores_gemma":[0.41574767,0.00001033945,0.5813788,0.00041629773,0.00017425719,0.000015997639,0.00046498099,0.00001961331,0.0017720591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998947,0.000006134085,0.00021435121,0.0003714459,0.00017950709,0.00028156463],"domain_scores_gemma":[0.9982354,0.0001415545,0.00012186635,0.0013620796,0.00004947097,0.000089620706],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001768902,0.00012316932,0.0001693826,0.000065580454,0.0002804018,0.0012270211,0.001504316,0.000051260227,0.000010599485],"category_scores_gemma":[0.00026419968,0.00008658719,0.00003771827,0.000088291505,0.00004617773,0.0021335457,0.0011230237,0.000062563005,0.000019111167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007710661,0.0001300513,0.0030716415,0.000033040717,0.000023997698,0.00009258384,0.0001711862,0.00014800236,0.000049039267,0.019193253,0.13282283,0.84418726],"study_design_scores_gemma":[0.0012110849,0.00013567515,0.0038163457,0.000069219546,0.000005752729,0.000010989027,0.00006110901,0.93475586,0.0003076041,0.0034189287,0.055921707,0.00028569225],"about_ca_topic_score_codex":0.000049875453,"about_ca_topic_score_gemma":0.00018958683,"teacher_disagreement_score":0.93460786,"about_ca_system_score_codex":0.000021012149,"about_ca_system_score_gemma":0.00006865464,"threshold_uncertainty_score":0.9998098},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93084085,0.0005183574,0.036425933,0.019606704,0.003896102,0.00096466305,0.00038537025,0.00063244323,0.006729602],"genre_scores_gemma":[0.86165,0.000060834198,0.13232914,0.0016335708,0.0016911859,0.0000738342,0.000027753596,0.00004779823,0.00248589],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99808973,0.000009814596,0.00026481858,0.00075421407,0.00039240913,0.0004889848],"domain_scores_gemma":[0.9984547,0.00006927582,0.00025599223,0.0008304644,0.00016012427,0.00022947651],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00025715702,0.0002564673,0.00026496165,0.0000685341,0.0015131467,0.0012189815,0.0033642869,0.000101422906,0.000101658225],"category_scores_gemma":[0.00026004633,0.00017848895,0.00007568263,0.00013673265,0.00011550645,0.0019508211,0.0025125677,0.00021422467,0.00044084995],"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":[0.00016277915,0.00033387667,0.022407891,0.00011401151,0.00037013265,0.00011296016,0.010967933,0.000015749898,0.1547862,0.24530146,0.3428562,0.22257084],"study_design_scores_gemma":[0.002228165,0.000401627,0.21692057,0.00040416044,0.00004645418,0.00018423366,0.0003303658,0.14968295,0.35584298,0.08836521,0.18364248,0.0019507937],"about_ca_topic_score_codex":0.00014812931,"about_ca_topic_score_gemma":0.000010122629,"teacher_disagreement_score":0.22062004,"about_ca_system_score_codex":0.00007754025,"about_ca_system_score_gemma":0.000050891485,"threshold_uncertainty_score":0.99981785},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5505157,0.00005639301,0.43858048,0.0013249186,0.0016452952,0.0015310558,0.0002563646,0.00026090528,0.005828839],"genre_scores_gemma":[0.90197295,0.000041992247,0.0968206,0.0005359478,0.00014133668,0.00006795054,0.00017177904,0.000028722681,0.00021869739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746805,0.00004236195,0.0008011714,0.00034770856,0.0005737474,0.00076696934],"domain_scores_gemma":[0.99713176,0.00013632995,0.0004924467,0.0018609874,0.00015962026,0.00021883484],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000945221,0.00029990324,0.00042544413,0.0002547922,0.0010251242,0.0012598151,0.0025778562,0.00016905504,0.000015273266],"category_scores_gemma":[0.00017972704,0.00026109107,0.00013441361,0.00013626573,0.000104801235,0.0044119605,0.0021725562,0.00046871076,0.00014286334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090497656,0.0037351686,0.10674929,0.0023028813,0.00043644072,0.0002191608,0.04141696,0.0014715088,0.002945111,0.1563966,0.022494733,0.6609272],"study_design_scores_gemma":[0.0059192316,0.00042622455,0.04512439,0.00070029096,0.000016866858,0.00005082395,0.00032961788,0.8951166,0.0022783075,0.0029826292,0.046168454,0.0008865638],"about_ca_topic_score_codex":0.00015161154,"about_ca_topic_score_gemma":0.000072094546,"teacher_disagreement_score":0.8936451,"about_ca_system_score_codex":0.00011965045,"about_ca_system_score_gemma":0.00008699024,"threshold_uncertainty_score":0.99998415},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2209197,0.000017729077,0.7754998,0.00091432926,0.0002747253,0.00012293822,0.00001087735,0.00014178503,0.0020980663],"genre_scores_gemma":[0.8783286,0.0000070935757,0.1205229,0.0004966646,0.00011057801,0.0000063561192,0.0000070548776,0.0000122651845,0.00050846935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860215,0.000033633652,0.00019335422,0.000467185,0.00032393838,0.00037976538],"domain_scores_gemma":[0.9981331,0.00010255794,0.00009462631,0.0014359652,0.000031765958,0.00020194965],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003382292,0.0001615611,0.00016257234,0.00008351395,0.00095310673,0.0013544459,0.0022071677,0.00004002801,0.000020576592],"category_scores_gemma":[0.00007064939,0.00012963315,0.000052229134,0.000052371848,0.000018762012,0.0012363571,0.0029015692,0.00020670383,0.00016186973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030842923,0.000032685075,0.006251425,0.000014956148,0.000009308707,0.00003591956,0.00075075973,0.0008028133,0.0057041245,0.0011071592,0.00026998704,0.9850178],"study_design_scores_gemma":[0.00077216234,0.00006193631,0.13134776,0.00027693907,0.0000034887773,0.000013954366,0.00012302177,0.8486965,0.009401741,0.002361146,0.006293444,0.00064792845],"about_ca_topic_score_codex":0.0022751584,"about_ca_topic_score_gemma":0.0002104124,"teacher_disagreement_score":0.9843699,"about_ca_system_score_codex":0.00002731803,"about_ca_system_score_gemma":0.00002348457,"threshold_uncertainty_score":0.99968225},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122313775,0.0019806258,0.85632,0.00016911821,0.0024009757,0.0003137614,0.000013751006,0.0007350164,0.01575292],"genre_scores_gemma":[0.95340645,0.00017462295,0.046206247,0.00011626601,0.000013084997,0.000008947322,0.000003391484,0.000008320519,0.00006268897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990836,0.000028799408,0.00014915943,0.00031847405,0.00018015782,0.00023981901],"domain_scores_gemma":[0.99928963,0.000022613018,0.000060364142,0.00043941365,0.00005406676,0.0001339261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001544146,0.00012974004,0.00014256967,0.0000940569,0.00024272343,0.00009246709,0.0005600075,0.000053857028,0.000012971088],"category_scores_gemma":[0.0000064897654,0.00011300392,0.000044190147,0.00036215773,0.00006679994,0.00044229388,0.00045493396,0.0001216708,0.000009601174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015078745,0.00006471114,0.0013684212,0.0000059696986,0.0000066216026,0.000012817799,0.00028520037,5.3885636e-8,0.000022654252,0.97738105,0.0004966392,0.020354342],"study_design_scores_gemma":[0.00038678182,0.00011515302,0.019137656,0.000014331971,0.000005584422,0.000026778984,0.000033058594,0.013626926,0.00034675628,0.96297944,0.0031009319,0.00022659435],"about_ca_topic_score_codex":0.00009903395,"about_ca_topic_score_gemma":0.000001229808,"teacher_disagreement_score":0.83109266,"about_ca_system_score_codex":0.000010331921,"about_ca_system_score_gemma":0.000015374522,"threshold_uncertainty_score":0.46081665},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20664272,0.0007825777,0.7645167,0.018567117,0.0020724616,0.00088144763,0.00002280861,0.00010322944,0.0064109396],"genre_scores_gemma":[0.9973079,0.00027572262,0.0019682255,0.00012962762,0.000081969534,0.000023804352,7.9235326e-7,0.000004876822,0.00020711393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984754,0.00028359293,0.00029340235,0.00037087145,0.0002535192,0.00032321227],"domain_scores_gemma":[0.9966057,0.0005954555,0.00050037727,0.0020734887,0.00016831073,0.000056647008],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008908487,0.0001561126,0.00022158095,0.000016720853,0.0015611856,0.00031295817,0.0038584585,0.00007288576,0.0000066956936],"category_scores_gemma":[0.0007211822,0.000070701244,0.000063014486,0.00007417944,0.0017027381,0.00034138383,0.0012918147,0.00033683807,0.0000061455585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029764668,0.000115833725,0.031827305,0.000055675657,0.00015824921,0.000015255098,0.0026459866,0.00007319391,0.027673623,0.819041,0.0005875106,0.11750873],"study_design_scores_gemma":[0.007463317,0.00052141666,0.6114064,0.00050424767,0.00014314787,0.0002382698,0.00033730143,0.19512184,0.079149686,0.07301827,0.030979563,0.0011165771],"about_ca_topic_score_codex":0.00025762198,"about_ca_topic_score_gemma":0.00013344872,"teacher_disagreement_score":0.79066515,"about_ca_system_score_codex":0.0000076218353,"about_ca_system_score_gemma":0.00018564588,"threshold_uncertainty_score":0.99973863},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04882895,0.00046882918,0.94353974,0.000116346964,0.0022536903,0.0005368293,0.00004054753,0.00036900083,0.0038460393],"genre_scores_gemma":[0.33603966,0.00018881919,0.6441648,0.00065775076,0.0011124855,0.000072409006,0.0009933573,0.00014403334,0.016626664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958083,0.00018515678,0.00083955895,0.0013775923,0.00081942446,0.0009699783],"domain_scores_gemma":[0.9971725,0.00029141843,0.0004020929,0.0012109149,0.00046034987,0.0004627262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005556229,0.00073380966,0.0006827484,0.00024239765,0.00083596393,0.00088163547,0.0022699076,0.0005298176,0.000760519],"category_scores_gemma":[0.0001105004,0.0006520789,0.0002707234,0.0004920817,0.00009301668,0.0007116318,0.0003622758,0.0006396052,0.00065020955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013120388,0.00084249093,0.000526775,0.0007288662,0.00020790553,0.00014158405,0.039304417,0.00018927235,0.003780551,0.0021487405,0.007910457,0.94408774],"study_design_scores_gemma":[0.00083346455,0.00028975424,0.0063425233,0.0010087916,0.00010476388,0.000044858327,0.0027924224,0.9767838,0.0052288626,0.00026966663,0.005292203,0.0010088801],"about_ca_topic_score_codex":0.0005109794,"about_ca_topic_score_gemma":0.0001587386,"teacher_disagreement_score":0.9765945,"about_ca_system_score_codex":0.00009867622,"about_ca_system_score_gemma":0.00041000525,"threshold_uncertainty_score":0.999593},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023264581,0.00002828686,0.9759543,0.00007542592,0.0002659647,0.00021439961,0.000014229335,0.0000364032,0.00014643997],"genre_scores_gemma":[0.62662053,0.000005734862,0.3732504,0.000007498902,0.000020034457,0.0000032860562,0.000003600538,0.0000037869522,0.000085140826],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991213,0.000032941574,0.00027079158,0.00022420411,0.0001751855,0.00017556136],"domain_scores_gemma":[0.9987902,0.00012525701,0.00032699417,0.000581796,0.00012627544,0.000049477803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003224168,0.00009466736,0.00021133746,0.00005176812,0.00021197439,0.00011111043,0.0009810571,0.000061524035,0.000035689696],"category_scores_gemma":[0.000078583325,0.000073832576,0.00007129996,0.000038177746,0.00014499873,0.00047850507,0.00033324235,0.000049260598,0.000002610089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033790444,0.00041308018,0.0019439803,0.00017573027,0.00025215393,0.000020294052,0.001365844,0.015189666,0.64874715,0.276869,0.0031471911,0.05153801],"study_design_scores_gemma":[0.0008219117,0.000126814,0.00028804783,0.00005380774,0.000012749603,0.0000050381036,0.000022279739,0.8820238,0.11601157,0.00043565905,0.00010299599,0.000095310956],"about_ca_topic_score_codex":0.00006292468,"about_ca_topic_score_gemma":3.9030786e-7,"teacher_disagreement_score":0.86683416,"about_ca_system_score_codex":0.0000060787156,"about_ca_system_score_gemma":0.00006058991,"threshold_uncertainty_score":0.30108052},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106934264,0.000004144123,0.88759726,0.001729034,0.00029799438,0.00009847686,6.806501e-7,0.00014798604,0.0031901575],"genre_scores_gemma":[0.84112996,5.3983683e-7,0.15753579,0.0011496205,0.00016870299,0.0000032650878,1.6562457e-7,0.000005112882,0.0000068201607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980033,0.000071821196,0.00014162899,0.0005835265,0.0007443932,0.0004553513],"domain_scores_gemma":[0.99811566,0.00043410802,0.00005156902,0.0011121803,0.00013112185,0.000155381],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0010936507,0.00015282002,0.000115565956,0.00008057445,0.0009953763,0.00073689345,0.0031600364,0.000024902727,0.0000458584],"category_scores_gemma":[0.00003553588,0.00007539307,0.000026088152,0.0007785762,0.0027525637,0.00059387315,0.0012500527,0.00019315573,0.00015104136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069798903,0.00002034487,0.0000052048426,0.0000011116623,0.000001751481,0.0000053321332,0.00044614504,0.000049395316,0.00020184764,0.98095214,0.000100828605,0.018208902],"study_design_scores_gemma":[0.00014238658,0.0005024925,0.00041468604,0.000090545705,0.0000021114056,0.000040912975,0.000017449585,0.48510018,0.009438657,0.5038578,0.00018590194,0.00020689872],"about_ca_topic_score_codex":0.000005199974,"about_ca_topic_score_gemma":5.3585643e-7,"teacher_disagreement_score":0.7341957,"about_ca_system_score_codex":0.000027412854,"about_ca_system_score_gemma":0.00007594396,"threshold_uncertainty_score":0.9999614},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037682917,0.00074287737,0.94723374,0.008091054,0.005389328,0.00012783718,0.000008896471,0.00015433592,0.0005690275],"genre_scores_gemma":[0.6942097,0.000013325933,0.29345846,0.008181618,0.0033443086,0.000015804453,0.0000075246894,0.00002724808,0.00074201106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984183,0.00028096943,0.00022069873,0.00020540654,0.00061606686,0.0002585855],"domain_scores_gemma":[0.9990913,0.00011649655,0.00013427687,0.00050419034,0.000047387384,0.00010630744],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007208966,0.0001133591,0.000117381045,0.000079775615,0.0015471078,0.00030617297,0.0021435646,0.0000109275015,0.0001342767],"category_scores_gemma":[0.000002720436,0.00007136985,0.000095306365,0.00023130115,0.000031846954,0.00031759572,0.002579624,0.0005733503,0.00003101743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032708416,0.00029271218,0.00017712364,0.0000018819383,0.0000893742,0.00047422,0.0012791455,0.27620605,0.00057591015,0.026225854,0.31226698,0.38237807],"study_design_scores_gemma":[0.000654384,0.00018438502,0.001201483,0.000007651088,0.000006090609,0.006212024,0.000014899445,0.9321089,0.000046453893,0.011678877,0.0477169,0.00016796091],"about_ca_topic_score_codex":0.000007678615,"about_ca_topic_score_gemma":6.1418876e-7,"teacher_disagreement_score":0.6565268,"about_ca_system_score_codex":0.000048954324,"about_ca_system_score_gemma":0.00008719818,"threshold_uncertainty_score":0.99975276},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027382132,0.00049140584,0.9916591,0.0003081477,0.00019198959,0.000058455706,0.0005049858,0.00005957181,0.003988096],"genre_scores_gemma":[0.57283676,0.00007390756,0.42533797,0.000037822127,0.00012911929,0.0000064465594,0.0014957113,0.000006130645,0.00007614101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907833,0.000025922322,0.0002080626,0.00039653666,0.00014573004,0.0001454141],"domain_scores_gemma":[0.99871135,0.00005052882,0.00008820221,0.0010545654,0.000053045726,0.000042303214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017734224,0.00008812164,0.000119196186,0.00023899066,0.00015368471,0.00009806311,0.0007470366,0.00001700296,0.00006406432],"category_scores_gemma":[0.000042186242,0.00007556283,0.000009328685,0.00058316725,0.00013798858,0.0018690962,0.0011412302,0.000059700436,0.000007020631],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037365528,0.000115164876,0.0006080514,0.000012829109,0.0000057736383,0.000005376697,0.000118223725,0.0000034095165,0.000048957492,0.041739646,0.0018816572,0.95545715],"study_design_scores_gemma":[0.0010761749,0.00016268542,0.04685558,0.00025514644,0.000020997932,0.00005181508,0.00008413736,0.83026874,0.00034077294,0.0063527864,0.11412361,0.0004075699],"about_ca_topic_score_codex":0.00027986543,"about_ca_topic_score_gemma":0.00037209588,"teacher_disagreement_score":0.95504963,"about_ca_system_score_codex":0.000007879818,"about_ca_system_score_gemma":0.00005023447,"threshold_uncertainty_score":0.30813628},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8838034,0.0008190178,0.022189338,0.01024306,0.050829355,0.0009613647,0.00001501545,0.0012708782,0.02986853],"genre_scores_gemma":[0.9980135,0.00003134322,0.0007014334,0.0004152598,0.0000698332,0.000011706293,0.0000030079855,0.0000114766635,0.0007424645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986001,0.00008405914,0.00019250941,0.00038257756,0.00038678478,0.00035391535],"domain_scores_gemma":[0.9982544,0.00017837404,0.000088145986,0.0012350973,0.00013079178,0.000113145295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029980732,0.00015508423,0.00012798513,0.00004258715,0.00050647405,0.0003615174,0.0015619427,0.00006419143,0.000009305301],"category_scores_gemma":[0.00005611172,0.00009563019,0.00005009249,0.00019049592,0.0001150288,0.000325919,0.00053093216,0.00014297469,0.0009390863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011237055,0.000060816634,0.00016162102,0.0000016345365,0.0000118970265,0.000011589053,0.00047912882,4.4010972e-7,0.00020970701,0.9470641,0.0378031,0.014184721],"study_design_scores_gemma":[0.0006556719,0.00050095585,0.0032641182,0.000041262185,0.0000050521776,0.000007932058,0.00001353002,0.007817766,0.013989518,0.68057895,0.29282367,0.00030158367],"about_ca_topic_score_codex":0.000022895612,"about_ca_topic_score_gemma":0.00000944818,"teacher_disagreement_score":0.26648518,"about_ca_system_score_codex":0.00003984011,"about_ca_system_score_gemma":0.000047147936,"threshold_uncertainty_score":0.99983877},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009919672,0.0013891148,0.9944337,0.00030464932,0.0017399346,0.00022547125,0.00043502086,0.00027031568,0.00020979658],"genre_scores_gemma":[0.88697964,0.0014307714,0.11058173,0.00008390812,0.0003419995,0.00008061206,0.0002495703,0.00007001224,0.00018175294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980478,0.00003339448,0.0003162533,0.0011294341,0.00016592999,0.00030712967],"domain_scores_gemma":[0.99775255,0.00013735698,0.000052945074,0.0018348816,0.000030417132,0.00019182367],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018104662,0.00036108616,0.00040285432,0.00029075495,0.00007622432,0.00020502556,0.0016232971,0.0002381995,0.000009897413],"category_scores_gemma":[0.000011104327,0.00036968765,0.000055537064,0.00032088094,0.000023260587,0.00044747867,0.00028249095,0.00097181834,0.00005668348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074556585,0.0012717184,0.000053767322,0.002733442,0.00034258296,0.0006693196,0.004159573,0.21153057,0.0061079953,0.00371217,0.014397336,0.754947],"study_design_scores_gemma":[0.00035372548,0.000040980918,0.00013063489,0.00040620234,0.000022238619,0.000021696647,0.00000792215,0.9866337,0.0014029713,0.00013113307,0.010395793,0.0004529745],"about_ca_topic_score_codex":0.000046787743,"about_ca_topic_score_gemma":0.000036474972,"teacher_disagreement_score":0.8859877,"about_ca_system_score_codex":0.000052760766,"about_ca_system_score_gemma":0.00011478901,"threshold_uncertainty_score":0.9998755},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035219703,0.0002758053,0.949877,0.000013573703,0.0015548166,0.0000997825,0.0000047589756,0.00014795993,0.012806578],"genre_scores_gemma":[0.09651367,0.000146088,0.8293466,0.0001562515,0.0017832321,0.000015840471,0.00014175015,0.00009381628,0.07180272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986294,0.000039441416,0.00020462785,0.00043733904,0.00042278005,0.0002664261],"domain_scores_gemma":[0.9991213,0.000053195716,0.00012614545,0.00054230104,0.000064327345,0.00009271631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018423176,0.00017549367,0.00016553202,0.00015464574,0.0002149614,0.00028364238,0.0010361625,0.000110385176,0.000102408725],"category_scores_gemma":[0.000014321234,0.00012333847,0.0000687209,0.000093647264,0.000007276042,0.0007624906,0.0002794483,0.00021658409,0.000055502715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001038489,0.000023035698,0.000029431714,0.00006909335,0.000018922903,0.000052607593,0.0004463703,0.0000344634,0.032171372,0.0144979665,0.0003237714,0.9523226],"study_design_scores_gemma":[0.0021100848,0.0001782624,0.006215832,0.0088452995,0.00007059999,0.00017387023,0.0007231821,0.7227907,0.20852506,0.040131275,0.0065287882,0.003707019],"about_ca_topic_score_codex":0.00017935029,"about_ca_topic_score_gemma":0.000011349249,"teacher_disagreement_score":0.94861555,"about_ca_system_score_codex":0.00005043087,"about_ca_system_score_gemma":0.00015063047,"threshold_uncertainty_score":0.5029597},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042592888,0.000004853192,0.9962669,0.00016330185,0.00022404951,0.00029242548,0.000007770044,0.00015184349,0.0024629452],"genre_scores_gemma":[0.06410737,0.0000021615504,0.93457454,0.00039616617,0.00017406259,0.0000092979235,0.00006534098,0.0000041788567,0.0006668767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993353,0.0000069249363,0.00019780226,0.00014397399,0.00016634948,0.00014968641],"domain_scores_gemma":[0.9992806,0.000018582818,0.00007234345,0.00034211695,0.00021349295,0.00007290192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012422391,0.000074900796,0.00006440247,0.00005933901,0.00012915274,0.0001903075,0.00041201917,0.000045976678,0.000023654462],"category_scores_gemma":[0.00007214948,0.000059205908,0.000023729233,0.00018554083,0.000015499736,0.0029159372,0.00013276485,0.000028481309,0.000050775096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046838006,0.000043343633,0.00012571756,0.000062133,0.000008943213,2.8239003e-7,0.0025207323,0.0015936028,0.0008247741,0.79325116,0.03879292,0.16272958],"study_design_scores_gemma":[0.0002575477,0.00009182008,0.00017176633,0.000009920125,0.0000023969242,0.0000021423505,0.0000022171275,0.958465,0.00048199247,0.039326146,0.001098777,0.00009026366],"about_ca_topic_score_codex":0.000028700857,"about_ca_topic_score_gemma":0.000007906128,"teacher_disagreement_score":0.9568714,"about_ca_system_score_codex":0.00002918906,"about_ca_system_score_gemma":0.00014786495,"threshold_uncertainty_score":0.24143468},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030459668,0.054317616,0.7243883,0.0024941089,0.06277531,0.00705899,0.032252453,0.002140968,0.08411261],"genre_scores_gemma":[0.47147542,0.028906714,0.34229428,0.007884105,0.0351797,0.000042502954,0.009924057,0.0010584809,0.10323475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973488,0.000031701147,0.00039733853,0.0013975288,0.0004583301,0.00036630975],"domain_scores_gemma":[0.9963681,0.00009074768,0.00019291167,0.0031267148,0.00007291364,0.00014860033],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00038148626,0.00045773282,0.0005674908,0.0002906203,0.00023691042,0.0002626569,0.0030469743,0.00019066845,0.000026466718],"category_scores_gemma":[0.00005682998,0.00037686233,0.000022877359,0.0001020509,0.00013781326,0.0010486265,0.014271613,0.00049241324,0.000015506235],"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":[0.000087867396,0.0000510983,0.00038957503,0.00046291095,0.0005257869,0.0004029829,0.012506336,0.000077800825,0.0000809576,0.025792407,0.12217063,0.83745164],"study_design_scores_gemma":[0.0013883219,0.0005547893,0.0022523103,0.0036065453,0.00008803891,0.00014211667,0.0013514558,0.008375672,0.00003313652,0.1409148,0.8384836,0.0028092423],"about_ca_topic_score_codex":0.00015258469,"about_ca_topic_score_gemma":0.0006448332,"teacher_disagreement_score":0.8346424,"about_ca_system_score_codex":0.00007709906,"about_ca_system_score_gemma":0.00006257565,"threshold_uncertainty_score":0.99986833},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010693464,0.00002361424,0.9875083,0.0010981903,0.00018931353,0.00012480159,0.0000036887252,0.000092142785,0.0002664949],"genre_scores_gemma":[0.7125269,0.000032224416,0.28674334,0.0005013279,0.000091539594,0.000030748906,0.0000011341083,0.000007983313,0.00006476953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897784,0.00006225507,0.00017452646,0.00033053124,0.0002354214,0.00021945337],"domain_scores_gemma":[0.99920774,0.00010180231,0.00004424588,0.0005532479,0.000045860845,0.000047094567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032407977,0.000116113275,0.00009150013,0.0001292794,0.0004029619,0.00014057058,0.00069082493,0.000060093487,0.00000900023],"category_scores_gemma":[0.000018610515,0.000083631494,0.00003022616,0.00044424745,0.000054464792,0.00054803636,0.000023780769,0.00024152212,0.000020520172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010219484,0.00015448077,0.00004597727,0.0000045592947,0.000008697392,0.00000435644,0.002181353,0.002830668,0.00041766107,0.002105403,0.00019356352,0.9920431],"study_design_scores_gemma":[0.00024334443,0.00013649763,0.0009294055,0.000016246546,0.000004548836,0.000035730558,0.00007030901,0.9888705,0.0010653568,0.007946439,0.000563115,0.00011848267],"about_ca_topic_score_codex":0.00009710474,"about_ca_topic_score_gemma":0.00008690911,"teacher_disagreement_score":0.9919246,"about_ca_system_score_codex":0.000028577273,"about_ca_system_score_gemma":0.000033322845,"threshold_uncertainty_score":0.34103933},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034301654,0.0017548648,0.9841625,0.007130468,0.0005786461,0.00027886912,0.00016309711,0.00020727784,0.002294079],"genre_scores_gemma":[0.58430725,0.00015479665,0.414835,0.0001677621,0.000073001465,0.000007386571,0.00042225272,0.0000066181487,0.000025937692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841297,0.00021127361,0.00034321097,0.00048204768,0.00036404104,0.00018646207],"domain_scores_gemma":[0.98837197,0.00031094192,0.0002679274,0.010513803,0.00046817603,0.00006718647],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00029470943,0.00013587647,0.00020649127,0.00009017819,0.00038875276,0.00011103377,0.0098186815,0.00019039221,0.000013987772],"category_scores_gemma":[0.0001576422,0.000122065474,0.00003748393,0.0007476871,0.00022905864,0.0015650585,0.0061184242,0.0005140111,0.000029099281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070911556,0.0015871978,0.0018450366,0.00005904168,0.00030296465,0.00001246406,0.0029388594,0.00043490477,0.15793203,0.49409747,0.21263401,0.12808512],"study_design_scores_gemma":[0.00051701855,0.00012027038,0.006794227,0.000089566485,0.000034312492,0.00002988557,0.00003763187,0.84386164,0.03149187,0.0024107683,0.11426787,0.00034491715],"about_ca_topic_score_codex":0.00024899276,"about_ca_topic_score_gemma":0.00009925011,"teacher_disagreement_score":0.84342676,"about_ca_system_score_codex":0.000026057523,"about_ca_system_score_gemma":0.00008910273,"threshold_uncertainty_score":0.99553865},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021231072,0.00006750715,0.97021425,0.00009965165,0.0018352234,0.001892315,0.0018442856,0.0002594521,0.0025562511],"genre_scores_gemma":[0.34436804,0.00016092122,0.6497733,0.0008295496,0.0007101103,0.00040254826,0.0033238507,0.0001360759,0.00029562382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567246,0.00004663252,0.0016870026,0.0006734426,0.0010192372,0.0009012162],"domain_scores_gemma":[0.99449646,0.00017236361,0.0015290511,0.0026849036,0.0008095228,0.00030771372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079487375,0.00075693236,0.0010137177,0.00040203633,0.00035726101,0.0006979943,0.0035194517,0.00052776403,0.00003874184],"category_scores_gemma":[0.00006820892,0.0006027505,0.00033416136,0.00031400553,0.00025931688,0.0016329064,0.004555315,0.000963887,0.000074994015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038824894,0.008379561,0.042367723,0.045474406,0.006970486,0.00018975238,0.12992014,0.070668645,0.0005281126,0.10124906,0.12625088,0.46411875],"study_design_scores_gemma":[0.0060587027,0.0012780275,0.0020002024,0.0043803626,0.00015070345,0.00017918932,0.0005157728,0.7967865,0.002904473,0.0046422416,0.17840382,0.0027000112],"about_ca_topic_score_codex":0.00007382107,"about_ca_topic_score_gemma":0.000018959447,"teacher_disagreement_score":0.72611785,"about_ca_system_score_codex":0.00016327218,"about_ca_system_score_gemma":0.00038024096,"threshold_uncertainty_score":0.9996424},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002085314,0.00005443823,0.99595284,0.0007179466,0.0003764195,0.00034362896,0.0000027297513,0.00012031262,0.00034634356],"genre_scores_gemma":[0.4329947,0.0000034080758,0.5664882,0.00020742022,0.00028491308,0.000012942218,3.838623e-7,0.000004694845,0.0000033386661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978481,0.000047030637,0.00023423787,0.00066121743,0.0004248264,0.0007845954],"domain_scores_gemma":[0.99828535,0.00061218435,0.00007696664,0.0006174959,0.00022157581,0.0001864012],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029328668,0.0001501938,0.00013140688,0.000082324965,0.001888991,0.0009996218,0.0020377154,0.000028785946,0.000009396291],"category_scores_gemma":[0.000069238,0.000093792405,0.000034042634,0.0005606416,0.002026445,0.00080973835,0.0024063843,0.00011784173,0.000007506997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025900388,0.000009023955,0.000024939885,0.0000039509373,0.000002769856,8.2464413e-7,0.0003001702,0.000007725637,0.00073240366,0.6898618,0.000061182865,0.30899262],"study_design_scores_gemma":[0.00022702263,0.00025361223,0.0002865948,0.000033502118,0.000005758668,0.000028009737,0.00001899183,0.89772135,0.009144906,0.09077671,0.0013416107,0.00016193687],"about_ca_topic_score_codex":0.000007422278,"about_ca_topic_score_gemma":8.2882957e-7,"teacher_disagreement_score":0.8977136,"about_ca_system_score_codex":0.000025923298,"about_ca_system_score_gemma":0.000086471715,"threshold_uncertainty_score":0.9994104},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002520344,0.004321961,0.981756,0.0036524436,0.0024924318,0.00081810873,0.003177637,0.00072391646,0.0005371786],"genre_scores_gemma":[0.21249343,0.0008067345,0.7804275,0.00095079385,0.0011987832,0.000052791853,0.0038722183,0.00007404217,0.00012367133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99553186,0.00021549164,0.0005501057,0.0024696847,0.00070090935,0.00053195463],"domain_scores_gemma":[0.99415725,0.0001851914,0.00034940508,0.0047788187,0.00012110387,0.00040825],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00031483173,0.00064225827,0.00080521806,0.00013109898,0.00028541393,0.00082105165,0.0069033,0.00046700504,0.000030056013],"category_scores_gemma":[0.00008541578,0.0005990731,0.00010372064,0.00023493849,0.00018548168,0.0007897612,0.028434515,0.0014204755,0.000030256715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008707339,0.00036648277,0.0006289151,0.0015636518,0.00062168366,0.0006746535,0.0011691602,0.00012196421,0.00066972675,0.017820712,0.07202482,0.90425116],"study_design_scores_gemma":[0.00065973325,0.00004901727,0.009017969,0.00008471901,0.0000804177,0.000047422775,0.000014060082,0.920105,0.00009579852,0.05313802,0.015878543,0.0008293206],"about_ca_topic_score_codex":0.00069840613,"about_ca_topic_score_gemma":0.000030377436,"teacher_disagreement_score":0.919983,"about_ca_system_score_codex":0.000060624803,"about_ca_system_score_gemma":0.0002220438,"threshold_uncertainty_score":0.99964607},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035558061,0.000018137556,0.98877895,0.00015464787,0.0004824803,0.00033852202,0.00031173055,0.000067757996,0.0062919445],"genre_scores_gemma":[0.07588331,0.000060924187,0.9229827,0.0006898789,0.00008011636,0.000011684183,0.00019969673,0.000012909758,0.00007876623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983323,0.00003597146,0.0006089664,0.00027978743,0.00034296158,0.0003999629],"domain_scores_gemma":[0.99836373,0.00016522284,0.00027707985,0.00094682456,0.000116695795,0.00013045249],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00047604844,0.0001974201,0.00023907654,0.00021026917,0.00027813,0.0036237414,0.0052074357,0.00004294505,0.00007673353],"category_scores_gemma":[0.00012778577,0.00017114749,0.000018421044,0.0006555845,0.000084920815,0.00916152,0.008388975,0.00016495188,0.00017503841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003046085,0.00019576427,0.0024383627,0.00017941919,0.000025305535,0.00006957389,0.0028847493,0.000087086046,0.00015718363,0.4566005,0.031394575,0.50593704],"study_design_scores_gemma":[0.0012606177,0.00014369626,0.009077887,0.0005128706,0.000012306919,0.000036343787,0.00041250137,0.91989785,0.003730239,0.021881457,0.042150438,0.0008837976],"about_ca_topic_score_codex":0.00075674575,"about_ca_topic_score_gemma":0.0002641683,"teacher_disagreement_score":0.9198108,"about_ca_system_score_codex":0.00005417987,"about_ca_system_score_gemma":0.00014985308,"threshold_uncertainty_score":0.999631},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008648135,0.0001463217,0.9898501,0.0028518112,0.0032618342,0.00033218972,0.00017147827,0.0005677055,0.0019537618],"genre_scores_gemma":[0.4299006,0.000020548692,0.5684486,0.0007985369,0.00072341954,0.000005153061,0.00008588379,0.000014705615,0.0000025858276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932966,0.0002249493,0.0005422737,0.0033067523,0.001790162,0.0008392482],"domain_scores_gemma":[0.99128944,0.00023422904,0.000236474,0.007294496,0.0002340313,0.0007113618],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0015578071,0.0005383532,0.00059863104,0.00018451858,0.00055689644,0.0021911503,0.027310664,0.00023349845,0.00006681593],"category_scores_gemma":[0.00021517869,0.00042183936,0.00010955436,0.000890988,0.002657536,0.0013035052,0.08276959,0.0013171494,0.00009129673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065186987,0.00004006805,0.000014213643,0.00003599978,0.000008893267,0.0000590925,0.0001747027,0.000074843156,0.00007438062,0.8660241,0.0023846037,0.1311026],"study_design_scores_gemma":[0.00010639548,0.00006154421,0.0007218417,0.000052624877,0.00000884001,0.000018589508,0.0000017106734,0.58477485,0.0002164725,0.4131828,0.0005120845,0.00034226762],"about_ca_topic_score_codex":0.000024535595,"about_ca_topic_score_gemma":9.940089e-7,"teacher_disagreement_score":0.5847,"about_ca_system_score_codex":0.00006407539,"about_ca_system_score_gemma":0.0006922157,"threshold_uncertainty_score":0.99982333},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017335014,0.00022469496,0.99437934,0.00022812487,0.00074072834,0.00029203677,0.0000058710752,0.00007429888,0.004037544],"genre_scores_gemma":[0.0048787715,0.0000094426405,0.9932745,0.00025464923,0.00052029133,0.0000028275156,0.0000032614744,0.000022361715,0.0010338657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996803,0.000018909033,0.00054117845,0.0011156822,0.0010657368,0.00045551787],"domain_scores_gemma":[0.99722534,0.0002666816,0.00032021137,0.0017576606,0.00022217068,0.00020794313],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057700754,0.00037942207,0.00053752266,0.00046939502,0.00011046993,0.00024858865,0.0038016532,0.00025177095,0.00022015214],"category_scores_gemma":[0.00007604315,0.00030089205,0.00011067943,0.00042238607,0.00053919177,0.0005637061,0.0024209523,0.00042328238,0.000087880806],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057297098,0.000041467887,0.0000046889336,0.00007276587,0.0000097530865,0.000032962314,0.0010286481,0.0006528309,0.00015294238,0.040894747,0.0005572165,0.95654625],"study_design_scores_gemma":[0.00022121548,0.00027016053,0.000016211854,0.0007126303,0.000006159749,0.000057414436,8.965658e-8,0.43277234,0.0042334725,0.5583964,0.002897095,0.00041683778],"about_ca_topic_score_codex":0.000013712115,"about_ca_topic_score_gemma":0.000009728049,"teacher_disagreement_score":0.95612943,"about_ca_system_score_codex":0.0000906588,"about_ca_system_score_gemma":0.00067848165,"threshold_uncertainty_score":0.9999443},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013618171,0.0014362411,0.98406446,0.00016130335,0.000039033654,0.00020487039,0.00002186758,0.000039766026,0.00041428837],"genre_scores_gemma":[0.9724016,0.00009247495,0.027196944,0.000038573035,0.000037602873,0.00009357768,0.000031339852,0.0000050877966,0.000102790415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99949694,0.000028554356,0.00013133185,0.0001811292,0.00007540761,0.00008662194],"domain_scores_gemma":[0.9992536,0.00023848169,0.000054172127,0.0002931532,0.000090969115,0.00006963054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047426726,0.00006863994,0.00010835739,0.00003237045,0.00015582853,0.000059756356,0.00023006872,0.000027592592,0.0000011550394],"category_scores_gemma":[0.000029995823,0.000054330994,0.000013305184,0.00009425676,0.00012436674,0.000257479,0.00018289084,0.000033336386,9.010705e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022367607,0.00002085629,0.000025911586,0.000018662266,0.0000033863246,6.662723e-8,0.00068610517,0.0000047636418,0.0003780117,0.93680537,0.0001206599,0.06191387],"study_design_scores_gemma":[0.0003757883,0.00010246409,0.00009668676,0.0000143981515,0.000009542567,0.000004818271,0.0007353,0.008910353,0.004806688,0.9519166,0.032917723,0.000109642395],"about_ca_topic_score_codex":0.000009286805,"about_ca_topic_score_gemma":6.2291025e-7,"teacher_disagreement_score":0.95878345,"about_ca_system_score_codex":0.000003480776,"about_ca_system_score_gemma":0.00002280489,"threshold_uncertainty_score":0.22155537},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008289875,0.0009629088,0.9890886,0.00021214182,0.000037729238,0.00037670296,0.000027930973,0.000030409941,0.0009736896],"genre_scores_gemma":[0.9612391,0.00008965249,0.038187582,0.00005707824,0.000033784032,0.00017338549,0.000042793403,0.000006042756,0.00017059132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99946874,0.000033861805,0.00013804091,0.0002018026,0.000070742186,0.00008681102],"domain_scores_gemma":[0.9991943,0.00023551854,0.00006174436,0.0003421254,0.0000932138,0.00007305852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006453386,0.00006970622,0.00012375267,0.000027755013,0.00019239375,0.00014512401,0.0004955434,0.000026410287,0.0000016972743],"category_scores_gemma":[0.00003122344,0.000054793432,0.000010962031,0.000098260505,0.00011683331,0.00044117603,0.00053970405,0.000033527263,9.824226e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030939027,0.000024475063,0.000022456386,0.000014625249,0.000003636136,6.972295e-8,0.0006178807,0.000005095604,0.00022642927,0.9317132,0.00017806419,0.06716311],"study_design_scores_gemma":[0.00046084073,0.00010670825,0.00007422031,0.000015957528,0.000008578708,0.0000039887304,0.00072934333,0.0074718664,0.0034856151,0.94689107,0.04064413,0.00010767181],"about_ca_topic_score_codex":0.0000216112,"about_ca_topic_score_gemma":0.0000011752293,"teacher_disagreement_score":0.9529492,"about_ca_system_score_codex":0.000003868355,"about_ca_system_score_gemma":0.000032338863,"threshold_uncertainty_score":0.22344112},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022226669,0.00076643267,0.97190356,0.002560429,0.0011212073,0.00007419199,3.070959e-7,0.00007520188,0.001271989],"genre_scores_gemma":[0.9711168,0.0013458093,0.024912423,0.00012628736,0.000743811,0.0000074777804,7.981203e-7,0.000017124205,0.0017294984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980876,0.000035038214,0.00016904622,0.00015287171,0.00021489454,0.0013405723],"domain_scores_gemma":[0.9993935,0.000048899965,0.00009250553,0.0003485728,0.00005279137,0.000063736275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014655162,0.00008784241,0.0000687729,0.000032911757,0.0006103891,0.00040981628,0.0014248053,0.000036340174,0.0000056940603],"category_scores_gemma":[0.000028229033,0.00005129852,0.000054865755,0.00012650904,0.000032774984,0.00050477823,0.00030820808,0.002213867,0.000027027942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034822228,0.000013119695,0.000070443886,5.830302e-7,0.000015728176,0.0000019426989,0.000061472456,0.0000058231376,0.0010928985,0.5620257,0.00023861422,0.43647018],"study_design_scores_gemma":[0.00039074224,0.00021378537,0.00028485377,0.000015772737,0.0000049419787,0.0017026752,0.00017612134,0.022226915,0.0003823024,0.84114236,0.13325375,0.0002057955],"about_ca_topic_score_codex":0.000022074319,"about_ca_topic_score_gemma":0.0004920264,"teacher_disagreement_score":0.9488901,"about_ca_system_score_codex":0.00008207676,"about_ca_system_score_gemma":0.00072616886,"threshold_uncertainty_score":0.96182734},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032628086,0.00012504823,0.9855441,0.0005879652,0.00017089151,0.00036564883,0.0000978821,0.0000235722,0.013052284],"genre_scores_gemma":[0.007282464,0.0011718976,0.24515665,0.0011863942,0.0004942394,0.00006202253,0.00021027487,0.00006863829,0.7443674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917287,0.000011694391,0.00022543776,0.00025860523,0.00022072822,0.00011067985],"domain_scores_gemma":[0.99873924,0.00021390062,0.00014772806,0.00073027227,0.00013572643,0.00003311288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013606607,0.00014056294,0.00020229131,0.00006427978,0.00028060973,0.00016691758,0.0006176826,0.00010066464,0.00003988118],"category_scores_gemma":[0.0000034153163,0.00006494538,0.00021284806,0.0000654865,0.00014463348,0.00023651865,0.00021503186,0.00008357349,0.0000021943972],"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":[0.00005014733,0.0000308387,0.000015960193,0.000051416162,0.0010602175,7.820302e-7,0.0004251533,0.000041418007,0.00018804583,0.6881215,0.02843025,0.28158426],"study_design_scores_gemma":[0.00027543618,0.000121003555,0.00026107274,0.00008732296,0.0005260783,0.0000044512076,0.0000035505786,0.14629585,0.0012206719,0.038247835,0.8126724,0.00028435793],"about_ca_topic_score_codex":0.00003498474,"about_ca_topic_score_gemma":0.000095706215,"teacher_disagreement_score":0.78424215,"about_ca_system_score_codex":0.000011344302,"about_ca_system_score_gemma":0.000021971035,"threshold_uncertainty_score":0.2648396},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0130179,0.00003917052,0.9791477,0.000504517,0.0021134603,0.00082460855,0.0001803161,0.00017528287,0.0039970684],"genre_scores_gemma":[0.5390047,0.000115156734,0.44970918,0.006502718,0.0022449489,0.00023784697,0.0014247401,0.000096348194,0.00066434604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997381,0.00006719657,0.0008906518,0.00032051545,0.00066227675,0.0006784017],"domain_scores_gemma":[0.99811786,0.00014038135,0.00033994275,0.0010329497,0.00024962786,0.0001192633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010818208,0.00031935316,0.00029442486,0.00028767958,0.0005404801,0.00080994796,0.002130718,0.00016632922,0.000027095128],"category_scores_gemma":[0.000084233696,0.00022846009,0.00012536287,0.0006517808,0.00013200876,0.0028956286,0.000673662,0.0003371551,0.00017040479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096094795,0.0008830253,0.005311253,0.00039345954,0.00015122604,0.000028656033,0.115205385,0.00013801572,0.0001403403,0.11955343,0.10223181,0.6558673],"study_design_scores_gemma":[0.0020467464,0.00030806244,0.0017417922,0.000160249,0.000014215133,0.000088433175,0.0017040434,0.8025403,0.0006059547,0.0032488129,0.18704759,0.00049382425],"about_ca_topic_score_codex":0.000049552003,"about_ca_topic_score_gemma":0.000026763737,"teacher_disagreement_score":0.80240226,"about_ca_system_score_codex":0.00008212264,"about_ca_system_score_gemma":0.000058527647,"threshold_uncertainty_score":0.93163323},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067137164,0.0001289189,0.9885274,0.00029623127,0.00044992502,0.0042438586,0.000043557586,0.00010698351,0.0055317637],"genre_scores_gemma":[0.29752606,0.000096682816,0.6865284,0.0018226466,0.00078064954,0.0016285704,0.00003517063,0.0002763176,0.011305502],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99776715,0.000005978943,0.00042558563,0.0007149971,0.0007229735,0.0003632897],"domain_scores_gemma":[0.9984194,0.00004590617,0.0003463512,0.00051483104,0.0005659754,0.00010752468],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005668787,0.00048168073,0.00044636987,0.000047173664,0.000653903,0.0002644627,0.0022111526,0.0002538677,0.000050975934],"category_scores_gemma":[0.000012730778,0.00025911635,0.0005755488,0.000085814216,0.000113069436,0.0003255133,0.001360516,0.00034489238,0.0000027877188],"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":[0.00034825818,0.000120618875,7.067325e-7,0.00013491872,0.00034436918,3.9020017e-7,0.006326604,0.000027292688,0.7630072,0.22298591,0.005108751,0.0015949812],"study_design_scores_gemma":[0.00056159514,0.0009111769,3.5821195e-8,0.0012338527,0.0000925283,0.000013634611,0.0005516884,0.06443741,0.9079166,0.020368192,0.0034418772,0.00047140312],"about_ca_topic_score_codex":0.0000063157313,"about_ca_topic_score_gemma":3.5548467e-7,"teacher_disagreement_score":0.301999,"about_ca_system_score_codex":0.00023271288,"about_ca_system_score_gemma":0.00016056985,"threshold_uncertainty_score":0.9999861},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037677342,0.00029715817,0.9943265,0.00011316315,0.0009711499,0.00018978784,0.000042086016,0.00020736932,0.000085067135],"genre_scores_gemma":[0.8997635,0.000051288956,0.09946004,0.000039473118,0.0005206884,0.000042772503,0.000031584448,0.000023021707,0.0000675967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998789,0.000011127034,0.00019921403,0.00062188687,0.00012920452,0.00024955897],"domain_scores_gemma":[0.9987339,0.00009753531,0.00003467944,0.0009291952,0.000097997996,0.00010670897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028269252,0.00017555225,0.00016309407,0.00018582595,0.00061438984,0.00011590813,0.0008979566,0.00006846456,0.0000056448694],"category_scores_gemma":[0.000018398405,0.00016033291,0.000028572093,0.00031925415,0.000026222158,0.0011601275,0.00012793484,0.00015293575,0.000011259977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003489969,0.00018541035,0.000005410312,0.00025696773,0.000040276645,0.0000027198034,0.005691021,0.003761278,0.013651363,0.00035538853,0.00095841207,0.9750568],"study_design_scores_gemma":[0.0003888017,0.00013673524,0.00001762674,0.00016021694,0.000015426413,0.000010374968,0.000020957204,0.94720775,0.03548577,0.00016242266,0.016173506,0.00022043138],"about_ca_topic_score_codex":0.000016604727,"about_ca_topic_score_gemma":0.0000357057,"teacher_disagreement_score":0.9748364,"about_ca_system_score_codex":0.000034208442,"about_ca_system_score_gemma":0.000047687623,"threshold_uncertainty_score":0.65381867},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012258592,0.000096083146,0.9749559,0.012331959,0.0019423104,0.00019316231,0.000003355556,0.00023769354,0.0090136845],"genre_scores_gemma":[0.9263553,0.00005488406,0.064023405,0.0063574086,0.00081690983,0.000023790888,0.000007704743,0.000005605153,0.002354977],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976958,0.00012879526,0.0002917085,0.00049545156,0.0010252494,0.00036299665],"domain_scores_gemma":[0.9989414,0.00018781127,0.000116095754,0.00042095856,0.00008357519,0.00025012097],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0010396242,0.00013110225,0.00013905167,0.00012134173,0.0014774861,0.00033593684,0.0015235491,0.00008594225,0.0002124188],"category_scores_gemma":[0.00011192012,0.00008127882,0.00006018185,0.0030475,0.0003467141,0.0007387675,0.00021343828,0.00018873275,0.00024979177],"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":[0.000027972543,0.00063327956,0.0011374381,0.000006835228,0.00002676337,0.000016383314,0.001619406,0.00023856781,0.0007606843,0.07704878,0.7984765,0.12000736],"study_design_scores_gemma":[0.00082407583,0.0006599255,0.027303591,0.00003492531,0.000013583796,0.00012361273,0.00008806488,0.57743186,0.00012526874,0.0533509,0.33960167,0.0004425584],"about_ca_topic_score_codex":0.000110670786,"about_ca_topic_score_gemma":0.00000725403,"teacher_disagreement_score":0.9251295,"about_ca_system_score_codex":0.000057297526,"about_ca_system_score_gemma":0.0004101739,"threshold_uncertainty_score":0.99982244},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057271052,0.000040391846,0.93168414,0.00023786857,0.00035574153,0.00015218668,0.000016391381,0.00023777655,0.010004475],"genre_scores_gemma":[0.38183483,0.0000038103697,0.6169669,0.0005453918,0.00012701377,0.0000024733122,0.000005066905,0.000008206063,0.0005062999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877286,0.000032412347,0.0001800964,0.00048349545,0.00021994062,0.00031122277],"domain_scores_gemma":[0.99891025,0.00014876024,0.000042306063,0.0005832307,0.00011018507,0.00020524315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014978685,0.00015383204,0.00015859448,0.000075117074,0.00023201988,0.00029186456,0.000660082,0.0000601287,0.00005893777],"category_scores_gemma":[0.000076136326,0.00012139362,0.000016724234,0.0002899936,0.00008340886,0.00046151242,0.0010010753,0.000074119394,0.00010005853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035853096,0.0009322208,0.002695389,0.00005626723,0.00011337844,0.00041685428,0.003538884,0.00093760283,0.2363863,0.10232231,0.045412652,0.6068296],"study_design_scores_gemma":[0.0010030448,0.0011083131,0.0010503357,0.00008176814,0.0000095440055,0.00036774232,0.00009301292,0.8877877,0.022001076,0.0007690587,0.08511453,0.00061389967],"about_ca_topic_score_codex":0.00012715362,"about_ca_topic_score_gemma":0.000045654648,"teacher_disagreement_score":0.88685006,"about_ca_system_score_codex":0.00002310734,"about_ca_system_score_gemma":0.00003491003,"threshold_uncertainty_score":0.4950288},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06230628,0.0005693728,0.93255216,0.0027311638,0.00079278165,0.00006364833,0.000031115014,0.000028273622,0.0009251893],"genre_scores_gemma":[0.5996561,0.00007824077,0.3995249,0.00046080974,0.00020270114,9.767625e-7,0.000019206622,0.0000058067985,0.000051249408],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988384,0.0001227125,0.0004148594,0.00020880588,0.00024685642,0.00016833846],"domain_scores_gemma":[0.99847865,0.00025222657,0.00039487742,0.00038973647,0.0003726186,0.000111883666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032694024,0.00011652473,0.0002206824,0.00015970998,0.00014629899,0.000062771906,0.0012653718,0.00008531808,0.000037880982],"category_scores_gemma":[0.000104328115,0.00008405821,0.00004002731,0.00012386445,0.00017366445,0.0003812675,0.00090234017,0.00016269536,0.000011943349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042066493,0.0005160812,0.0032840928,0.000043767166,0.00027796332,0.000114012364,0.001031879,0.0017995342,0.012472726,0.3824612,0.08583673,0.51174134],"study_design_scores_gemma":[0.0022301932,0.0014645242,0.02726615,0.000110915775,0.000014525688,0.00070744567,0.000025218445,0.17417495,0.00022677466,0.75714153,0.036394138,0.00024361096],"about_ca_topic_score_codex":0.000007801351,"about_ca_topic_score_gemma":0.0000027741694,"teacher_disagreement_score":0.5373498,"about_ca_system_score_codex":0.000030184743,"about_ca_system_score_gemma":0.00008970146,"threshold_uncertainty_score":0.3427794},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077865146,0.00004394076,0.91152185,0.00026895254,0.00036725515,0.0002033971,0.00003424715,0.00027576435,0.00941947],"genre_scores_gemma":[0.3902832,0.000003881723,0.6084516,0.00073907647,0.00012965087,0.000003300116,0.000009722535,0.000010145239,0.00036943887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984925,0.000044020915,0.00022522137,0.00055760733,0.0003117616,0.00036888852],"domain_scores_gemma":[0.9987605,0.00018558654,0.000059677754,0.00062516844,0.00012882253,0.00024021442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022127866,0.00018710515,0.0001877828,0.00010685156,0.00027150728,0.0004163623,0.00088163966,0.00007925184,0.00006064138],"category_scores_gemma":[0.000099988174,0.00015051325,0.000019328241,0.00035443067,0.00009931326,0.00057413377,0.0013950387,0.00009908196,0.000094122835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000298045,0.0010461386,0.0056969956,0.000058359656,0.00017216994,0.00040687475,0.0059293457,0.0006022529,0.123082355,0.08993545,0.03807996,0.73469204],"study_design_scores_gemma":[0.0027203956,0.0030827788,0.0065192543,0.00021872135,0.000032335724,0.00084286794,0.00026854826,0.8022671,0.032812003,0.0021826862,0.14744882,0.0016045293],"about_ca_topic_score_codex":0.00010852037,"about_ca_topic_score_gemma":0.00005783862,"teacher_disagreement_score":0.8016648,"about_ca_system_score_codex":0.00002518681,"about_ca_system_score_gemma":0.000055784716,"threshold_uncertainty_score":0.61377525},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74798626,0.00059187744,0.17989895,0.070661895,0.0005517759,0.000079117846,0.000003507935,0.000016565285,0.00021007961],"genre_scores_gemma":[0.8901476,0.000050240516,0.10845753,0.00082053506,0.00042291576,4.676845e-7,3.8553048e-7,0.00000627086,0.00009403843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914944,0.00007854384,0.00018784178,0.00011928531,0.0003348818,0.0001299995],"domain_scores_gemma":[0.9992245,0.0001200368,0.00014226632,0.00036514908,0.000046540332,0.00010152445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033527432,0.00006840314,0.00012061289,0.00005145335,0.00011286898,0.00018693844,0.0014489722,0.00002463515,0.000015514215],"category_scores_gemma":[0.0003793036,0.000041517425,0.00005540095,0.00019021815,0.000033095803,0.00057490164,0.0015036342,0.0003283125,0.0000043009195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017723251,0.0010499859,0.07432687,0.00016748189,0.00042796665,0.0010838414,0.030312262,0.07202894,0.09296934,0.042309914,0.30250746,0.3810436],"study_design_scores_gemma":[0.003600553,0.0009568328,0.42650452,0.00037270377,0.000031448784,0.0011238493,0.0006977285,0.46586493,0.002579557,0.02350995,0.074268885,0.00048903015],"about_ca_topic_score_codex":0.00001382551,"about_ca_topic_score_gemma":0.0000076083315,"teacher_disagreement_score":0.393836,"about_ca_system_score_codex":0.000024032357,"about_ca_system_score_gemma":0.00010057339,"threshold_uncertainty_score":0.2692575},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10887378,0.000026617025,0.8826635,0.00003004092,0.00020126086,0.00010615594,8.3198773e-7,0.000102234895,0.007995594],"genre_scores_gemma":[0.76924676,0.000004233253,0.230578,0.00005648163,0.000070590664,0.000008157319,3.5705887e-7,0.000004853472,0.000030538762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777734,0.000009340296,0.00028818997,0.0006095386,0.00085090206,0.0004646651],"domain_scores_gemma":[0.99864405,0.000023629833,0.00017268726,0.0008483694,0.00018483143,0.00012643702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094420783,0.00013227966,0.00016199783,0.00014774334,0.0005417921,0.00014180873,0.0022225115,0.000034732526,0.0000066120074],"category_scores_gemma":[0.000022776505,0.00011178715,0.000026993128,0.0007896907,0.00059457845,0.0009253412,0.0010353199,0.000108463326,0.000049947543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013570688,0.00006377389,0.0005068037,0.000020687135,0.000004003383,0.0000014425697,0.0017686614,0.0007218923,0.47609007,0.016001564,0.0000482223,0.5047593],"study_design_scores_gemma":[0.00015308028,0.000052388918,0.002310708,0.000022268077,0.0000013039609,0.000004845811,0.000012216254,0.9135029,0.0808683,0.0028171458,0.00011019589,0.00014467607],"about_ca_topic_score_codex":0.0000132171,"about_ca_topic_score_gemma":0.0000011667256,"teacher_disagreement_score":0.912781,"about_ca_system_score_codex":0.00003814788,"about_ca_system_score_gemma":0.0001617587,"threshold_uncertainty_score":0.45585477},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0727713,0.000047125563,0.9255355,0.00003038637,0.00035421748,0.00018144076,0.000021373846,0.00016071589,0.00089791033],"genre_scores_gemma":[0.9821587,0.00006500609,0.017414562,0.000037436952,0.00001894613,3.788264e-7,0.000044697732,0.00001122045,0.00024903365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983485,0.0001550921,0.00021731004,0.00087793317,0.00012053054,0.00028064268],"domain_scores_gemma":[0.99795437,0.00023980628,0.00041117813,0.0010820985,0.00019586076,0.000116707364],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025351447,0.00025605047,0.00038273848,0.00021797688,0.00011651838,0.00007945398,0.0018580059,0.00023132596,0.000040832016],"category_scores_gemma":[0.000057979018,0.00027959375,0.00016928482,0.00034424342,0.00016788182,0.00031920362,0.0016942391,0.0005444201,0.000041767664],"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":[0.000017461454,0.000046754467,0.003437224,0.000118240096,0.00003451593,0.000109880544,0.00007806585,0.964034,0.00028431616,0.030266965,0.000040401133,0.0015321348],"study_design_scores_gemma":[0.00039987,0.00006106316,0.00031358335,0.00020943927,0.000025603267,0.000002605009,0.00003604773,0.99464357,0.00063710375,0.0031540315,0.00021572619,0.00030136452],"about_ca_topic_score_codex":0.00015514028,"about_ca_topic_score_gemma":0.00001394753,"teacher_disagreement_score":0.9093874,"about_ca_system_score_codex":0.00010086535,"about_ca_system_score_gemma":0.0003092138,"threshold_uncertainty_score":0.9999656},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007661426,0.000008757827,0.9775409,0.000859273,0.0016001062,0.00007930008,0.0000031487298,0.00028474745,0.01196236],"genre_scores_gemma":[0.82775503,0.000001758599,0.17071609,0.0010550475,0.0004267417,0.00000414803,9.1112094e-7,0.000004786377,0.00003545753],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796593,0.00005948678,0.00017042852,0.00069826987,0.0006427075,0.00046319579],"domain_scores_gemma":[0.99824315,0.00013238828,0.000041878142,0.0011290507,0.00020979215,0.00024372031],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006728781,0.00014830033,0.00012610845,0.00014070806,0.00088690844,0.0004976907,0.0021619534,0.000037325848,0.00011080067],"category_scores_gemma":[0.000059709237,0.00010659299,0.000040606905,0.0009455481,0.003432284,0.00081880746,0.0013145204,0.00014719085,0.00079379644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057402876,0.000042251693,0.000011040647,0.0000011540428,0.0000010988824,0.0000042343486,0.00014854172,0.0000067263927,0.00017192004,0.9255411,0.0009875974,0.073078565],"study_design_scores_gemma":[0.00021701626,0.001247664,0.001797082,0.000054009884,0.000002696295,0.000039871244,0.000008033086,0.80985695,0.004962411,0.1731711,0.008309416,0.00033375964],"about_ca_topic_score_codex":0.0000033768167,"about_ca_topic_score_gemma":3.3534414e-7,"teacher_disagreement_score":0.82009363,"about_ca_system_score_codex":0.000035687626,"about_ca_system_score_gemma":0.00009856267,"threshold_uncertainty_score":0.9999842},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021525897,0.00073158287,0.9972164,0.00063520204,0.00034400093,0.0003506186,0.0001317057,0.000112371585,0.00045661844],"genre_scores_gemma":[0.020682009,0.00053941127,0.9765508,0.0002077614,0.00033767722,0.00030552753,0.00015989365,0.000054960456,0.0011619246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981636,0.00011870013,0.00044761156,0.0005681627,0.0003505622,0.00035138923],"domain_scores_gemma":[0.9973592,0.001645298,0.0002467855,0.00043904947,0.00013558648,0.00017407762],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006274314,0.00028270672,0.00052140217,0.000027906122,0.0007054716,0.0010989871,0.0008326463,0.00014636401,0.000007062209],"category_scores_gemma":[0.00040389592,0.00018708421,0.00008586551,0.000056306213,0.00009873241,0.00009907815,0.0017123412,0.0006675862,0.0000047221356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021106234,0.000022988803,7.3803744e-7,0.0001933135,0.00004582643,0.00001216509,0.00045432392,0.0016926065,0.0000054568136,0.8496285,0.0032397301,0.14468326],"study_design_scores_gemma":[0.00029972213,0.000039034738,0.0000019585902,0.00007171684,0.000018631785,0.000004142389,0.000026685831,0.54651546,0.0000042693373,0.44331732,0.009559129,0.00014190772],"about_ca_topic_score_codex":0.00002142626,"about_ca_topic_score_gemma":0.0000013938395,"teacher_disagreement_score":0.5448229,"about_ca_system_score_codex":0.000020330152,"about_ca_system_score_gemma":0.00006785501,"threshold_uncertainty_score":0.99993795},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0415748,0.00016522843,0.95675427,0.00020569685,0.0006044328,0.000054835953,0.0000084364465,0.00003287107,0.00059946254],"genre_scores_gemma":[0.4545929,0.00005681951,0.54417056,0.00012817932,0.0009306954,0.0000010010165,0.000001637006,0.000017262588,0.00010095315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847114,0.000037279166,0.000363686,0.00022000993,0.00060695637,0.00030091903],"domain_scores_gemma":[0.99868125,0.00005470039,0.00039730445,0.0003809042,0.00028896844,0.00019687082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034466057,0.00016298504,0.00025139545,0.00014172128,0.0001712623,0.00026498374,0.0009701677,0.00004818826,0.000026042135],"category_scores_gemma":[0.000025810985,0.00010994105,0.00008805575,0.0003101792,0.000097410164,0.001832586,0.00030575678,0.00024510972,0.000016007993],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011228878,0.0005982207,0.004294204,0.00009296722,0.0012068446,0.002837617,0.0059124543,0.01741388,0.014453791,0.023660604,0.02286393,0.9055426],"study_design_scores_gemma":[0.0066515496,0.011068888,0.00930548,0.0013151702,0.00016823101,0.0046146093,0.0009536905,0.7867134,0.06367407,0.0021934381,0.111495376,0.0018460616],"about_ca_topic_score_codex":0.000018122242,"about_ca_topic_score_gemma":0.0000015383073,"teacher_disagreement_score":0.90369654,"about_ca_system_score_codex":0.000056333858,"about_ca_system_score_gemma":0.0001352242,"threshold_uncertainty_score":0.4483266},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011584121,0.000020548177,0.98622274,0.0005741216,0.0009672803,0.00025171248,0.000011721843,0.00016168729,0.00020606948],"genre_scores_gemma":[0.6918716,0.0000064701107,0.3072076,0.00036571728,0.0005246325,0.000005299556,0.0000039684737,0.0000066461575,0.000008092047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792445,0.0000427288,0.00024730928,0.0008059864,0.0005165606,0.00046293915],"domain_scores_gemma":[0.99843115,0.00029000876,0.000073886586,0.0006565686,0.0003013873,0.00024698075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008705616,0.00018314054,0.00018487897,0.00015527071,0.0006131887,0.00046214196,0.0013600732,0.000056361896,0.000011332044],"category_scores_gemma":[0.000114629715,0.00013873332,0.000034917717,0.0006139327,0.0014536135,0.0007152763,0.00095170696,0.00011688925,0.000019744952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012104912,0.000036314057,0.000006609459,0.0000035518217,0.0000017762736,0.0000011910059,0.0001155256,0.00005521463,0.00039888025,0.679317,0.000036381858,0.3200155],"study_design_scores_gemma":[0.00040424554,0.0010900322,0.00028534705,0.00003606086,0.000002886272,0.0000084755,0.0000021911799,0.8968025,0.0136952875,0.08679037,0.0006988147,0.00018380446],"about_ca_topic_score_codex":0.0000019468719,"about_ca_topic_score_gemma":2.8676033e-7,"teacher_disagreement_score":0.8967473,"about_ca_system_score_codex":0.000034193494,"about_ca_system_score_gemma":0.000072433584,"threshold_uncertainty_score":0.5657381},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014699249,0.00006389248,0.9852185,0.0002337557,0.0006462412,0.00020174056,0.000004363153,0.00032282356,0.011838734],"genre_scores_gemma":[0.4957785,0.000005839539,0.5027296,0.0005991819,0.00040391117,0.000012052901,0.0000026932257,0.000012435176,0.0004558045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682176,0.000018341756,0.00026085012,0.0011112269,0.0011007822,0.00068704755],"domain_scores_gemma":[0.9977878,0.0000388053,0.00012145558,0.0014444835,0.00015614621,0.0004513073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005254174,0.00022662139,0.00020679565,0.00020516291,0.0009344902,0.0006468148,0.0037004764,0.00007138373,0.000046542507],"category_scores_gemma":[0.000016554939,0.00018395155,0.00003958364,0.0011763156,0.0007216627,0.0011945568,0.0020355831,0.00018415073,0.00042965641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059391364,0.000054050874,0.000009819089,0.0000022580034,0.0000020459227,0.000004855835,0.000828713,0.00002388513,0.12773877,0.01542403,0.003226834,0.8526788],"study_design_scores_gemma":[0.00037547588,0.00005342583,0.00055126316,0.000024295752,0.000002205599,0.000014627086,0.0000133907415,0.92325366,0.037070926,0.028555335,0.009793844,0.00029157038],"about_ca_topic_score_codex":0.000067195884,"about_ca_topic_score_gemma":0.0000037601033,"teacher_disagreement_score":0.92322975,"about_ca_system_score_codex":0.00007264088,"about_ca_system_score_gemma":0.0004097271,"threshold_uncertainty_score":0.7501326},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006575392,0.00003601684,0.9901248,0.0009763003,0.0008494473,0.00036820755,0.0002312976,0.00023754186,0.00060097163],"genre_scores_gemma":[0.4953857,0.000002091491,0.5031533,0.0007073692,0.00068673823,0.000003893048,0.000031218886,0.0000112737425,0.000018401413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668705,0.00009217878,0.00031594676,0.0013952197,0.0007167737,0.0007928043],"domain_scores_gemma":[0.99567103,0.00049946026,0.00010721227,0.0029584276,0.00040203103,0.00036180537],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013129722,0.00025931423,0.00030239564,0.00013480734,0.0008270483,0.0005762982,0.007078367,0.00009092203,0.00012493301],"category_scores_gemma":[0.00022765041,0.00019597725,0.0000518023,0.00088262674,0.0038535688,0.0015560844,0.005326063,0.00017743232,0.00010540111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040307572,0.000054089134,0.000022029019,0.000011556987,0.0000075049793,0.0000088873385,0.00031220264,0.0000128695465,0.0033796243,0.9500072,0.006505136,0.039638594],"study_design_scores_gemma":[0.0004107508,0.00030731707,0.00006481345,0.000027047272,0.000006680333,0.0000355749,0.000004336538,0.88980764,0.0027514242,0.09961257,0.0066740867,0.0002977753],"about_ca_topic_score_codex":0.0000062692493,"about_ca_topic_score_gemma":0.0000018385299,"teacher_disagreement_score":0.88979477,"about_ca_system_score_codex":0.000036018697,"about_ca_system_score_gemma":0.00027514328,"threshold_uncertainty_score":0.9988574},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052491983,0.000047104415,0.99544615,0.0002522762,0.0010411761,0.0007282801,0.00009006533,0.0003388686,0.0015311355],"genre_scores_gemma":[0.08060357,0.000018687328,0.9149403,0.0003843428,0.0016909649,0.0005742717,0.00022259614,0.00003053667,0.0015347307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820465,0.000044882123,0.00032718733,0.0006905397,0.00031810097,0.00041466116],"domain_scores_gemma":[0.998289,0.0001299167,0.00011609285,0.0010300785,0.00024796627,0.00018697328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014286565,0.00022387817,0.00024522608,0.00011396868,0.0005263017,0.00027411868,0.0013274936,0.00011431132,0.00006637482],"category_scores_gemma":[0.000008761181,0.00017365624,0.00010168323,0.00027381763,0.00013560159,0.00046861693,0.00071742316,0.0001204137,0.00011546349],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012834623,0.0003283935,0.000020304651,0.000019148138,0.000025927393,0.0000013965805,0.00008309418,0.000013460686,0.0016829614,0.043774243,0.016970938,0.9370673],"study_design_scores_gemma":[0.00082570297,0.0001530457,0.000507245,0.00002278136,0.000013336237,0.000009754137,0.000009155656,0.9292699,0.0057610087,0.0071079982,0.056024604,0.0002954325],"about_ca_topic_score_codex":0.000060838425,"about_ca_topic_score_gemma":0.0000063225984,"teacher_disagreement_score":0.93677187,"about_ca_system_score_codex":0.000030195142,"about_ca_system_score_gemma":0.00004705087,"threshold_uncertainty_score":0.70814955},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074692833,0.000060269245,0.9971479,0.00019370389,0.0007101656,0.00023380847,0.00007962579,0.00012077879,0.00070681993],"genre_scores_gemma":[0.01607756,0.0000152105495,0.98249674,0.00044561567,0.00062257005,0.0000107841715,0.00022090218,0.000006815025,0.000103827755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991232,0.0000093666495,0.00027830063,0.00018587275,0.00019511381,0.00020815927],"domain_scores_gemma":[0.9982447,0.000040699513,0.00012428677,0.0014023059,0.00011468189,0.00007329384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024551226,0.00010206468,0.0001053807,0.000053047082,0.00023098747,0.00041431142,0.0016152527,0.000048171034,0.000007584535],"category_scores_gemma":[0.000056040157,0.00008337503,0.000022978025,0.0001220508,0.00004068995,0.002564783,0.0010711899,0.00004526722,0.00011456797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016717175,0.00012638117,0.00009604392,0.00017065745,0.000040886298,0.0000013034982,0.001805887,0.000058453472,0.0026427119,0.04581898,0.22916602,0.72005594],"study_design_scores_gemma":[0.00019828975,0.000062375846,0.00005742482,0.00001173194,0.000003321231,0.00000279969,0.000016058775,0.7751544,0.0009569521,0.00013158501,0.22330806,0.00009697581],"about_ca_topic_score_codex":0.00001745193,"about_ca_topic_score_gemma":0.000012150121,"teacher_disagreement_score":0.77509594,"about_ca_system_score_codex":0.000013334259,"about_ca_system_score_gemma":0.00005016436,"threshold_uncertainty_score":0.39952147},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044887746,0.000043982873,0.9725305,0.004912164,0.0008659666,0.00014308299,0.000040440984,0.00012639302,0.01684872],"genre_scores_gemma":[0.9366968,0.0000046659306,0.058854476,0.0029853412,0.00040991136,0.0000056146405,0.00010611845,0.000010904643,0.00092611555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984584,0.000038815175,0.00020692241,0.00049236824,0.00042556744,0.00037796807],"domain_scores_gemma":[0.99834806,0.00008552333,0.00008102103,0.00041803264,0.0003918731,0.0006754659],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015143296,0.00016922907,0.00013891567,0.00079088355,0.00033398694,0.00034816194,0.00087463186,0.00008592582,0.00045027645],"category_scores_gemma":[0.00006404268,0.00016910555,0.000048208585,0.0010447707,0.00008207973,0.0004918982,0.00009706984,0.00014978525,0.00081522414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048928473,0.00002363071,0.00017249912,0.0000036768693,0.000018001918,0.000020960495,0.00019450788,0.0012931362,0.000014191921,0.770586,0.058601823,0.16906667],"study_design_scores_gemma":[0.0006496257,0.00035764757,0.02636839,0.000085816595,0.0000062387726,0.00003451479,0.000041864158,0.6625692,0.000105598374,0.24766357,0.061529092,0.0005884013],"about_ca_topic_score_codex":0.011259247,"about_ca_topic_score_gemma":0.009362139,"teacher_disagreement_score":0.93220806,"about_ca_system_score_codex":0.000123846,"about_ca_system_score_gemma":0.0014636066,"threshold_uncertainty_score":0.99996275},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005524688,0.0030197415,0.98703307,0.0005319021,0.002071898,0.000051275067,0.000004371988,0.000034033546,0.0017289945],"genre_scores_gemma":[0.5220187,0.0001971372,0.47502995,0.00042763082,0.0020534182,0.0000018082094,0.000002855664,0.00002045682,0.00024808903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840045,0.0000677532,0.00043878102,0.00012631174,0.00053670694,0.00042997603],"domain_scores_gemma":[0.9987,0.00007816092,0.00037159654,0.000370362,0.00013754731,0.0003423185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007642314,0.00014101037,0.00024811717,0.00015382386,0.00011628113,0.00013718152,0.000979159,0.00006464489,0.00004281416],"category_scores_gemma":[0.0000578226,0.000098379205,0.00014480563,0.0002640481,0.000031017917,0.0028509223,0.0003232523,0.00029222018,0.000041350217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028780561,0.00039155525,0.004326594,0.000025764974,0.00017041995,0.00013653582,0.0022433314,0.000119770404,0.0027878468,0.01645482,0.025899753,0.9474148],"study_design_scores_gemma":[0.004895277,0.0014842977,0.05383761,0.0006469576,0.00016443661,0.0062965215,0.0008590096,0.18845318,0.013990485,0.012733638,0.7146239,0.002014646],"about_ca_topic_score_codex":0.000008276437,"about_ca_topic_score_gemma":2.2185012e-7,"teacher_disagreement_score":0.9454002,"about_ca_system_score_codex":0.000046045978,"about_ca_system_score_gemma":0.00006697736,"threshold_uncertainty_score":0.40117875},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70795214,0.00016772513,0.10254657,0.0067792954,0.0011574031,0.0005856181,0.000009466179,0.00050261145,0.18029916],"genre_scores_gemma":[0.95888287,0.00002020376,0.03738079,0.00056906015,0.00007680582,0.000003898337,7.522355e-7,0.000004834343,0.0030607965],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9994074,0.000003874868,0.00009091104,0.00016333573,0.00022508633,0.0001093841],"domain_scores_gemma":[0.9994476,0.000048458758,0.000048539525,0.00038340958,0.00004000253,0.000032014872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000060612947,0.00006015807,0.00006817792,0.000024790601,0.00010833279,0.000024977751,0.0012810398,0.00002804131,0.000016937089],"category_scores_gemma":[0.00004461874,0.000031695734,0.000030546842,0.0002074696,0.0000306569,0.00022020613,0.00059525523,0.000080131664,0.000017936103],"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":[0.000036090387,0.00043674628,0.01669045,0.00003608415,0.000031358883,0.000016540529,0.0039049836,0.00011588098,0.008175569,0.2727522,0.5221382,0.17566596],"study_design_scores_gemma":[0.0025352105,0.0006725618,0.42956322,0.00087343063,0.000020859987,0.00036139454,0.000758777,0.22687875,0.1335342,0.022676922,0.18057565,0.0015490127],"about_ca_topic_score_codex":0.000014632345,"about_ca_topic_score_gemma":8.272875e-7,"teacher_disagreement_score":0.41287276,"about_ca_system_score_codex":0.000007192098,"about_ca_system_score_gemma":0.000017038787,"threshold_uncertainty_score":0.23805119},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48683688,0.000004851484,0.48580253,0.000588137,0.001703959,0.00018447565,0.000007954169,0.0001083353,0.024762873],"genre_scores_gemma":[0.9961905,8.0220076e-7,0.00337535,0.00020838318,0.00008201217,9.238773e-7,4.1063433e-7,0.0000031074487,0.0001385458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916905,0.0000053933163,0.0001532296,0.00018845608,0.0003249555,0.00015890473],"domain_scores_gemma":[0.99949604,0.000038010934,0.00008771853,0.0002016107,0.00013306165,0.00004355915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029248217,0.000076576696,0.00008570834,0.00003022718,0.000087652,0.00007465905,0.0008213854,0.000036755137,0.00001266639],"category_scores_gemma":[0.000010898155,0.000044639226,0.000030473928,0.00014328182,0.000029394072,0.00035616942,0.00047306524,0.000117365664,0.000008817774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014433997,0.00015181016,0.002135492,0.000016613794,0.0000068297527,0.000002358504,0.0025620048,0.0000029925263,0.0027828617,0.9129296,0.004649863,0.074745156],"study_design_scores_gemma":[0.0051048175,0.0015317271,0.27317506,0.0009599487,0.000023917932,0.00007164988,0.0041653314,0.061239067,0.27652115,0.35584363,0.01971614,0.0016475858],"about_ca_topic_score_codex":0.00008764603,"about_ca_topic_score_gemma":0.000002894031,"teacher_disagreement_score":0.557086,"about_ca_system_score_codex":0.000011914506,"about_ca_system_score_gemma":0.000021410564,"threshold_uncertainty_score":0.18203348},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018302932,0.00011982422,0.98461795,0.002409286,0.0044904454,0.00022501741,0.000006792848,0.0003114905,0.0059889182],"genre_scores_gemma":[0.8427301,0.000010449312,0.15547603,0.0012561494,0.00044275177,0.000015509817,0.0000040413547,0.00001507566,0.00004986998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954332,0.00020404112,0.00041781028,0.0016192031,0.001521651,0.0008040814],"domain_scores_gemma":[0.9946037,0.0004670228,0.00021345461,0.004199912,0.00026686225,0.000249049],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0026682587,0.0003881325,0.00038583874,0.0001947899,0.0007205976,0.0020727667,0.012939252,0.00018476835,0.0000404454],"category_scores_gemma":[0.00009103439,0.00023272623,0.0001515266,0.0008102729,0.002638767,0.0006049199,0.026361672,0.0012461101,0.0002842082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035262674,0.00002589195,0.000058492224,0.000015110648,0.0000056837575,0.000010197713,0.00020816733,0.00456621,0.000023020713,0.9110966,0.00047399793,0.0835131],"study_design_scores_gemma":[0.00010207213,0.00005872148,0.000978025,0.00012591304,0.0000049429595,0.0000261293,0.0000023334376,0.85812193,0.00016917454,0.13850245,0.0015881837,0.00032012674],"about_ca_topic_score_codex":0.00002044854,"about_ca_topic_score_gemma":5.1421296e-7,"teacher_disagreement_score":0.85355574,"about_ca_system_score_codex":0.00009569968,"about_ca_system_score_gemma":0.00053234,"threshold_uncertainty_score":0.9989632},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008755728,0.0008572571,0.98096156,0.00029543386,0.005093556,0.00057140057,0.00031066136,0.00030652844,0.0028479013],"genre_scores_gemma":[0.14877887,0.00041400624,0.8450833,0.0014800348,0.0021227556,0.000114252674,0.00073584553,0.000042907006,0.0012280032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967761,0.00019204034,0.0010525035,0.00048192198,0.000630419,0.0008670314],"domain_scores_gemma":[0.996768,0.000049114347,0.0006149717,0.0012256333,0.00092813116,0.00041416555],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0009436861,0.0004470823,0.0003580183,0.0002395068,0.00088687876,0.0017560378,0.0012595142,0.0003154064,0.00018584235],"category_scores_gemma":[0.00009934938,0.00044730082,0.00010458215,0.0006845254,0.00065465266,0.02092208,0.00073150033,0.00025501216,0.000898565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016662107,0.000081318896,0.000021024945,0.00012437886,0.000036250614,0.000014435893,0.011604851,0.000116551,0.0011619786,0.0062290006,0.0014862124,0.9791073],"study_design_scores_gemma":[0.000551861,0.00090288854,0.0004934697,0.00032116598,0.000026251782,0.0003368977,0.00046645486,0.9018647,0.01018426,0.005422842,0.078830786,0.00059842673],"about_ca_topic_score_codex":0.0013057028,"about_ca_topic_score_gemma":0.000020448933,"teacher_disagreement_score":0.9785089,"about_ca_system_score_codex":0.00063903176,"about_ca_system_score_gemma":0.00040039286,"threshold_uncertainty_score":0.99987936},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009313599,0.000026696076,0.977297,0.0002861106,0.00071823463,0.00008822697,8.39081e-7,0.0002294398,0.012039818],"genre_scores_gemma":[0.6549694,0.0000024820956,0.34459153,0.00036972587,0.000047095513,0.000001987193,2.73931e-7,0.000004127776,0.000013397089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976759,0.00009654709,0.00021852569,0.0007314751,0.0006965526,0.0005810233],"domain_scores_gemma":[0.9982488,0.00014604158,0.000051011662,0.0010888966,0.00013093182,0.00033430502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013975672,0.00015896233,0.0001541109,0.0001415381,0.00047754834,0.00057801383,0.0026344657,0.00003884505,0.000081464335],"category_scores_gemma":[0.00011872223,0.00012283715,0.00004937019,0.001071019,0.0013060363,0.0010657075,0.0010166264,0.0001767154,0.00017792494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.469361e-7,0.000029879086,0.000027539638,0.0000014993392,9.788322e-7,0.000009719382,0.000081537364,0.000029633433,0.00026869387,0.953125,0.00012334816,0.04630132],"study_design_scores_gemma":[0.00033365347,0.00016489676,0.00092115364,0.000029552206,0.000002853693,0.000114006354,0.0000056487097,0.45597628,0.014668705,0.52014536,0.007227182,0.0004107042],"about_ca_topic_score_codex":0.0000020554808,"about_ca_topic_score_gemma":8.571536e-8,"teacher_disagreement_score":0.6456558,"about_ca_system_score_codex":0.00003871112,"about_ca_system_score_gemma":0.00012643969,"threshold_uncertainty_score":0.5573801},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1655562,0.00042767156,0.83093464,0.000101266734,0.00021766691,0.00012954941,0.0000067367523,0.00022663796,0.0023996362],"genre_scores_gemma":[0.9932575,0.000994242,0.00452023,0.000022277694,0.000035464604,3.953825e-7,0.000025512449,0.000010863319,0.0011334787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870986,0.00017057371,0.00012585797,0.00071363273,0.00007176989,0.00020830071],"domain_scores_gemma":[0.99736077,0.0001117706,0.00031548573,0.0019983943,0.0000905244,0.00012302933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034541654,0.00019790091,0.00022137487,0.000118829936,0.00091283105,0.00049369154,0.002691693,0.00017334158,0.0000071473587],"category_scores_gemma":[0.000042556378,0.00022663137,0.000062534724,0.000088059765,0.000093725146,0.0007193637,0.0072742756,0.0009486773,0.00001930585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009931517,0.00010348138,0.008680886,0.00019999986,0.00014213528,0.00027189977,0.0021151241,0.13206606,0.00007965888,0.8040822,0.00064122624,0.0516074],"study_design_scores_gemma":[0.0005712401,0.00003306974,0.0095904125,0.00050980214,0.000048496608,0.000015203322,0.00019303158,0.7993244,0.0000417646,0.18161592,0.007324316,0.00073237316],"about_ca_topic_score_codex":0.0004354105,"about_ca_topic_score_gemma":0.000016331152,"teacher_disagreement_score":0.82770133,"about_ca_system_score_codex":0.000059090864,"about_ca_system_score_gemma":0.00008623415,"threshold_uncertainty_score":0.9241759},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078325205,0.000044092976,0.9202913,0.0000632847,0.00013178571,0.000077587894,0.000002697559,0.0001469796,0.00091706123],"genre_scores_gemma":[0.7569029,0.0000021850612,0.24270788,0.00014210964,0.00011785882,0.000002328422,0.0000145460235,0.0000075387366,0.00010267319],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989787,0.000034405133,0.00017957328,0.00032950685,0.00024925324,0.00022856645],"domain_scores_gemma":[0.99929583,0.00005163493,0.00011104013,0.0003771995,0.00009041592,0.00007386697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014324122,0.00011459314,0.00010504968,0.00005061382,0.0003558059,0.00024001388,0.00037180138,0.000039206396,0.00003613432],"category_scores_gemma":[0.0000124475555,0.0000811655,0.000016764085,0.00023373227,0.000037841935,0.0010513712,0.00026717412,0.00007975677,0.000022732653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011365177,0.00041842723,0.021713097,0.00005689655,0.00008228294,0.000047697853,0.0031118996,0.004155892,0.5272605,0.013111614,0.019351928,0.4105761],"study_design_scores_gemma":[0.00029993278,0.00009409545,0.0002417654,0.00007510178,0.0000033236245,0.000009673292,0.000020701273,0.94777787,0.048084438,0.00016338094,0.0030661994,0.00016352527],"about_ca_topic_score_codex":0.00010744872,"about_ca_topic_score_gemma":0.000008476987,"teacher_disagreement_score":0.943622,"about_ca_system_score_codex":0.000019788253,"about_ca_system_score_gemma":0.000029732986,"threshold_uncertainty_score":0.3309833},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7022836,0.0007929694,0.15490498,0.0039097224,0.0013111682,0.0015387343,0.000053126856,0.00014928145,0.13505638],"genre_scores_gemma":[0.9950638,0.000020141304,0.0047516106,0.000064395004,0.000022923105,0.000008034368,0.0000014594792,0.0000023314838,0.000065332766],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991195,0.00004233348,0.000262048,0.00020299376,0.00020637836,0.00016670571],"domain_scores_gemma":[0.99934983,0.00011576087,0.000079937075,0.00039428397,0.000023582104,0.00003658337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003015322,0.00009098901,0.000115409304,0.000025101206,0.00035340898,0.0000698281,0.0006951831,0.00003419551,0.000011267224],"category_scores_gemma":[0.0000053429994,0.000041937925,0.000021687785,0.00015283676,0.0005974045,0.00019447299,0.00033533113,0.00009676742,0.000003802221],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050326734,0.000599585,0.002714052,0.000032232656,0.000036178495,0.0000019395513,0.01843433,0.000058198904,0.05130795,0.08783729,0.028187755,0.81028724],"study_design_scores_gemma":[0.004411112,0.000356319,0.068322316,0.00020555974,0.00000523809,0.000019449863,0.0042185984,0.40057686,0.48765457,0.0007677076,0.0330809,0.00038136417],"about_ca_topic_score_codex":0.000046768222,"about_ca_topic_score_gemma":0.00005607339,"teacher_disagreement_score":0.8099059,"about_ca_system_score_codex":0.000009802945,"about_ca_system_score_gemma":0.000028201892,"threshold_uncertainty_score":0.27181718},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077581224,0.00014741361,0.98681337,0.00036264313,0.0028068207,0.0009789597,0.00032729196,0.00027089674,0.00053448894],"genre_scores_gemma":[0.23098977,0.00014497798,0.76024216,0.00060610037,0.00064947084,0.000008471509,0.00016162728,0.00006830231,0.007129103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700147,0.00021844801,0.00026939795,0.001836778,0.00016492943,0.00050897885],"domain_scores_gemma":[0.99551874,0.0011663013,0.00052110857,0.0022059332,0.0003174472,0.00027048908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007087324,0.00042787724,0.00046623586,0.0004317158,0.00020988802,0.00040034705,0.0032439057,0.0003163671,0.000023878181],"category_scores_gemma":[0.00039123435,0.00045913414,0.00023628742,0.00066661724,0.000035932193,0.0010837637,0.0056452267,0.00060080405,0.00014654237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000944686,0.00075746694,0.0005889002,0.00036368382,0.0011312403,0.0005097546,0.002206206,0.37033883,0.0018932648,0.5369287,0.008443579,0.07589368],"study_design_scores_gemma":[0.0007537969,0.00013279186,0.000062563355,0.0001403903,0.00009861783,0.0000030122947,0.0001923333,0.93846774,0.00040405968,0.032687575,0.026437825,0.0006193103],"about_ca_topic_score_codex":0.0007634568,"about_ca_topic_score_gemma":0.0000068034933,"teacher_disagreement_score":0.5681289,"about_ca_system_score_codex":0.00024055855,"about_ca_system_score_gemma":0.00020044319,"threshold_uncertainty_score":0.999786},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1292115,0.00014641965,0.86858237,0.00009648049,0.0009825006,0.0007273758,0.000017000548,0.00013509805,0.000101243415],"genre_scores_gemma":[0.60690975,2.9519265e-7,0.3928977,0.000017410446,0.000024869682,0.000022217688,0.000027112617,0.000005838486,0.00009482255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981077,0.00005746947,0.00030210317,0.00062115263,0.0005242379,0.00038738982],"domain_scores_gemma":[0.99875927,0.000085511136,0.00018151723,0.0006168043,0.00026416586,0.000092710885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010881316,0.00013806735,0.00021708391,0.00015153259,0.00032557274,0.0004552007,0.0008830997,0.000054199056,0.0000062120002],"category_scores_gemma":[0.00006824188,0.00011711296,0.00010935735,0.0004982124,0.00020152103,0.0002391988,0.00034213313,0.000104469036,0.000015434114],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038525504,0.00032890707,0.0015254235,0.00034169978,0.000020426194,0.0000012151494,0.0008305719,0.0064383354,0.0052937074,0.0131360805,0.0008832206,0.9711619],"study_design_scores_gemma":[0.0011743323,0.0002310856,0.0033119456,0.00020790282,0.000013258079,0.0000067927785,0.00007714309,0.8906741,0.017290616,0.06766469,0.01890292,0.00044517886],"about_ca_topic_score_codex":0.0000370829,"about_ca_topic_score_gemma":0.000019841655,"teacher_disagreement_score":0.9707167,"about_ca_system_score_codex":0.000023872397,"about_ca_system_score_gemma":0.000094439936,"threshold_uncertainty_score":0.4775728},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065861235,0.0043152,0.9936522,0.0006009746,0.00044337404,0.00017033434,0.000019933968,0.000018468925,0.00012086285],"genre_scores_gemma":[0.39363903,0.0032462238,0.6024775,0.00020579892,0.00025562994,0.0000061634546,0.0000708605,0.000013343001,0.000085435575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908274,0.00009947636,0.0003708472,0.00015855898,0.00014594359,0.00014241246],"domain_scores_gemma":[0.9967127,0.00040052025,0.00037988523,0.0022301145,0.000194273,0.00008252607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070401985,0.000092764305,0.00020234415,0.000079612364,0.00024070835,0.00017482723,0.0028018702,0.00007347702,0.0000051708907],"category_scores_gemma":[0.000013838545,0.00007491885,0.000045238743,0.00015843379,0.000043974214,0.0010415338,0.0013557973,0.00030865864,0.0000022535437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012560188,0.000088571556,0.000063231666,0.000006143225,0.000038580027,6.390345e-7,0.000066371686,0.000506449,0.00017660916,0.00096766854,0.0027603167,0.99531287],"study_design_scores_gemma":[0.0005222247,0.00014998985,0.00041552333,0.000048817117,0.000015444908,0.000049969105,0.000028923323,0.872525,0.000024325687,0.0005075153,0.12562998,0.00008231024],"about_ca_topic_score_codex":0.000011404525,"about_ca_topic_score_gemma":0.000009139552,"teacher_disagreement_score":0.99523056,"about_ca_system_score_codex":0.000014393145,"about_ca_system_score_gemma":0.000039916013,"threshold_uncertainty_score":0.5206619},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6100955,0.0007457954,0.3861124,0.00038012568,0.0017605962,0.00009594031,0.0000033312235,0.000020446056,0.0007858719],"genre_scores_gemma":[0.9130139,0.00018168578,0.08582249,0.00037269815,0.00038827665,9.1192135e-7,5.349455e-7,0.000013547884,0.0002059599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991815,0.000034319215,0.00028477123,0.00011541415,0.00026871118,0.00011528964],"domain_scores_gemma":[0.9990226,0.00021800274,0.00026388787,0.0002171918,0.00015649784,0.000121819015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075149233,0.00009263948,0.00022025919,0.00009873568,0.00010190354,0.0001092177,0.00027458073,0.00004224236,0.000008630444],"category_scores_gemma":[0.00013094333,0.000063668864,0.000028807552,0.00014785444,0.000037361435,0.00020607244,0.00018103313,0.00013588628,0.000003661636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118644835,0.0036107216,0.0025397628,0.00046379387,0.00022019981,0.00032138385,0.022829035,0.0000057714055,0.0014279069,0.36027676,0.27980214,0.32838386],"study_design_scores_gemma":[0.008166826,0.011849829,0.069393694,0.0022132148,0.0001836242,0.0030088504,0.000672476,0.2113752,0.0008698129,0.5068329,0.18346559,0.0019680117],"about_ca_topic_score_codex":0.000012192872,"about_ca_topic_score_gemma":0.0000060777093,"teacher_disagreement_score":0.32641587,"about_ca_system_score_codex":0.000043418797,"about_ca_system_score_gemma":0.00003264068,"threshold_uncertainty_score":0.25963408},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038481176,0.000116205876,0.9577966,0.00024137678,0.0018025408,0.00019338839,0.0000058916153,0.00019546616,0.0011673989],"genre_scores_gemma":[0.25515026,0.00002926215,0.74115866,0.0014617768,0.00048430485,0.000029337602,0.000024618328,0.000030913536,0.0016309005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984526,0.0000389777,0.00025369003,0.0005096608,0.0004032875,0.00034175368],"domain_scores_gemma":[0.9988456,0.00009186216,0.00012799849,0.0007374104,0.0000845811,0.00011258688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002002799,0.00015479286,0.00018095439,0.00007788851,0.00013031712,0.0002592648,0.0014281318,0.00006771899,0.000086995424],"category_scores_gemma":[0.000010928026,0.00012814358,0.00006275775,0.0002305455,0.000021118913,0.0018833425,0.0007164676,0.00016653136,0.000640877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020345626,0.00032245993,0.007666635,0.00004798041,0.00005542036,0.00012402471,0.00034000046,0.005890735,0.006808507,0.012486252,0.021552095,0.9446855],"study_design_scores_gemma":[0.0007819098,0.000046791385,0.0056192605,0.00005957791,0.0000037852726,0.000026381233,0.000007772974,0.9732164,0.004734242,0.0027453124,0.012399635,0.00035894217],"about_ca_topic_score_codex":0.00009439373,"about_ca_topic_score_gemma":0.0000025673307,"teacher_disagreement_score":0.9673256,"about_ca_system_score_codex":0.00002286385,"about_ca_system_score_gemma":0.0000581507,"threshold_uncertainty_score":0.8237391},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101632796,0.0000447234,0.8933343,0.000010436456,0.0005363418,0.00013248,0.000027773227,0.000111430374,0.0041696997],"genre_scores_gemma":[0.99488866,0.00005953814,0.0047073644,0.000050975064,0.000050195955,3.5118526e-7,0.000044372468,0.0000052968353,0.00019321649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907786,0.00010947815,0.00021097186,0.00027216645,0.000100249796,0.00022926524],"domain_scores_gemma":[0.9982389,0.000079937316,0.00035085122,0.0010808898,0.00014202324,0.00010738745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004046055,0.0001825271,0.00021872546,0.00020806323,0.0000861252,0.00006317447,0.0014648888,0.00019638501,0.000037927548],"category_scores_gemma":[0.000025101479,0.000186599,0.00011494614,0.0002749438,0.00006383372,0.001944414,0.0025573915,0.00030955364,0.00006745323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023573706,0.000042501764,0.00055530516,0.0001576969,0.000057590223,0.00001634045,0.0016272286,0.034618832,0.00015494651,0.95079803,0.0002653896,0.011682565],"study_design_scores_gemma":[0.00060843234,0.00005335711,0.0026987428,0.00036277086,0.00010140006,0.000010497357,0.0005223943,0.8015845,0.0026424194,0.18747936,0.003106636,0.00082948734],"about_ca_topic_score_codex":0.00007602555,"about_ca_topic_score_gemma":0.0000017391322,"teacher_disagreement_score":0.8932559,"about_ca_system_score_codex":0.00014230014,"about_ca_system_score_gemma":0.00017795005,"threshold_uncertainty_score":0.7609287},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08740807,0.00067125267,0.9092236,0.0018107641,0.00013550061,0.00012972698,0.0000037981235,0.00015944317,0.00045783276],"genre_scores_gemma":[0.77522993,0.0002921013,0.22301601,0.001117028,0.000041607036,0.0000355177,0.0000010380799,0.000011268092,0.0002555307],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885947,0.00005156523,0.00013905446,0.00048755578,0.00022357621,0.00023878874],"domain_scores_gemma":[0.9987291,0.00048977137,0.00010447436,0.00043599313,0.000098500175,0.00014212416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012479252,0.00014519814,0.00013551065,0.000040603805,0.0002285928,0.00028198483,0.00029865687,0.000042965326,0.000015743717],"category_scores_gemma":[0.00017178936,0.00008377754,0.000012291835,0.00009216792,0.00017967762,0.0030277215,0.0005230812,0.00008301019,0.000015284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034248197,0.00024649664,0.025091697,0.000070514136,0.00008047413,0.00034311847,0.021541502,0.0000069320254,0.007326062,0.0110433195,0.0013442679,0.9325631],"study_design_scores_gemma":[0.009968213,0.0021864923,0.05568221,0.0018018471,0.0001282525,0.004508471,0.011992935,0.010420825,0.017470222,0.0030520728,0.87908345,0.0037050343],"about_ca_topic_score_codex":0.000054813514,"about_ca_topic_score_gemma":0.0000042903607,"teacher_disagreement_score":0.9288581,"about_ca_system_score_codex":0.000009439547,"about_ca_system_score_gemma":0.00003179856,"threshold_uncertainty_score":0.34163487},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06315442,0.00004769914,0.93397826,0.000020042009,0.00044557618,0.00015796772,0.000027394315,0.00012995282,0.0020386968],"genre_scores_gemma":[0.98607904,0.000035873443,0.013476566,0.00003680865,0.000030961422,5.117556e-7,0.000025966072,0.000009412639,0.00030484304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985355,0.0000873841,0.00020640474,0.00081284984,0.00014582726,0.00021203214],"domain_scores_gemma":[0.99767244,0.00010184349,0.00037429642,0.001486366,0.0002531687,0.00011191586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017994903,0.00022131047,0.00027875495,0.00022857968,0.000091275455,0.000055274846,0.0021925156,0.00028620835,0.00007106171],"category_scores_gemma":[0.000026872785,0.0002375455,0.00013601169,0.00037049086,0.000103266946,0.00044038668,0.001967258,0.0004053803,0.000036520694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082815364,0.000537923,0.026728302,0.00032582178,0.00012709589,0.00033956315,0.00036266661,0.426461,0.0002820842,0.53867406,0.0011511082,0.0049275355],"study_design_scores_gemma":[0.00037136386,0.000052378386,0.007559701,0.00018798564,0.00003320589,0.0000012349047,0.000013818219,0.93088126,0.0014078955,0.058848113,0.0002784889,0.0003645464],"about_ca_topic_score_codex":0.0004476297,"about_ca_topic_score_gemma":0.00002882532,"teacher_disagreement_score":0.92292464,"about_ca_system_score_codex":0.000061857136,"about_ca_system_score_gemma":0.00038194307,"threshold_uncertainty_score":0.9686824},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023362455,0.000055937584,0.99518794,0.0006967131,0.00039393202,0.00043781148,0.000021492733,0.00008391835,0.00078598736],"genre_scores_gemma":[0.013211025,0.000009472903,0.9785096,0.000551236,0.000044654153,0.000020261701,0.0001753306,0.000006778237,0.007471643],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908584,0.000014309273,0.0001336266,0.0004788488,0.00012802087,0.00015935082],"domain_scores_gemma":[0.99802387,0.000040882816,0.000020369505,0.0018264637,0.000039837265,0.000048597554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015228642,0.000077225086,0.00007681373,0.000047482805,0.00014244436,0.00015535692,0.0019674418,0.000022602326,0.00006119347],"category_scores_gemma":[0.000006604355,0.00006136886,0.00002135397,0.00007666611,0.00000661532,0.0009425108,0.0037403563,0.00003769243,0.00016860523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036032874,0.0006572977,0.0010611478,0.00017781497,0.00020735113,0.000038929076,0.00030919164,0.046148956,0.0110039525,0.34947214,0.4701195,0.120767675],"study_design_scores_gemma":[0.00042066592,0.000014534267,0.0012263242,0.00001330165,0.0000029926155,0.0000042647407,0.000011920961,0.9587521,0.00004978612,0.0002317758,0.039176933,0.000095400785],"about_ca_topic_score_codex":0.00004608662,"about_ca_topic_score_gemma":0.000014556798,"teacher_disagreement_score":0.91260314,"about_ca_system_score_codex":0.000015221052,"about_ca_system_score_gemma":0.000022788643,"threshold_uncertainty_score":0.46620867},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016695736,0.00025206653,0.9806374,0.00008621055,0.0008509708,0.00046169397,0.000508629,0.0001464081,0.00036094198],"genre_scores_gemma":[0.9275819,0.0005369514,0.068393625,0.000068205896,0.00005339146,0.0000032736798,0.0006555584,0.000020590784,0.0026865262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841046,0.000052143623,0.00012592088,0.0011204324,0.00007485952,0.00021617308],"domain_scores_gemma":[0.9975291,0.00007326809,0.00014269777,0.0019572324,0.00013540928,0.00016230835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020073786,0.00020946052,0.0002177257,0.00021730503,0.00031368036,0.00028749305,0.0022255392,0.00015737559,0.000006816576],"category_scores_gemma":[0.000026858115,0.0002128393,0.000053749696,0.0003607587,0.0000759748,0.0005841717,0.006478104,0.00023698965,0.0000024938909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012013037,0.00016423491,0.00048413195,0.00027292856,0.00040984334,0.00013991309,0.00041101978,0.08320748,0.00003157248,0.82084566,0.0834597,0.010453364],"study_design_scores_gemma":[0.00033689264,0.000033944758,0.0001719789,0.000022536526,0.00004018769,0.0000044894387,0.000025516436,0.61497873,0.0000036351385,0.3791024,0.005083764,0.00019595426],"about_ca_topic_score_codex":0.0002070052,"about_ca_topic_score_gemma":0.00011119695,"teacher_disagreement_score":0.9122437,"about_ca_system_score_codex":0.0000986473,"about_ca_system_score_gemma":0.00021182478,"threshold_uncertainty_score":0.86793345},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007852627,0.000045816243,0.9889531,0.00029497856,0.0007243246,0.00027894948,0.000015196101,0.00028003182,0.0015549421],"genre_scores_gemma":[0.97504824,0.00020385048,0.023121309,0.0007668031,0.0003246236,0.0000017276085,0.00009351806,0.000013388642,0.0004265267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837774,0.00015098127,0.00030608123,0.0006016168,0.00018098048,0.00038257675],"domain_scores_gemma":[0.99777454,0.00006980856,0.00044006694,0.0014317966,0.00015171732,0.00013206106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041094905,0.0002971098,0.0002501378,0.0001469492,0.00041624648,0.00043084123,0.0022866714,0.00024535935,0.000016486943],"category_scores_gemma":[0.00002026482,0.0002436386,0.00017033755,0.00038110756,0.00007882396,0.0015481573,0.0023669829,0.0006978689,0.00016863148],"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":[0.000025171552,0.00011294432,0.00041971722,0.00004615007,0.00009972747,0.00006947469,0.0007307621,0.6111655,0.000010903793,0.23616107,0.0024203213,0.14873825],"study_design_scores_gemma":[0.0002680314,0.000028068647,0.00069477153,0.00006823466,0.0000295831,0.000005480282,0.000077835895,0.9426442,0.00007003118,0.05104374,0.0047489475,0.00032111502],"about_ca_topic_score_codex":0.0001518566,"about_ca_topic_score_gemma":0.000007495176,"teacher_disagreement_score":0.96719563,"about_ca_system_score_codex":0.00012487742,"about_ca_system_score_gemma":0.00019342855,"threshold_uncertainty_score":0.9935294},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051695675,0.00012320759,0.9402656,0.000065549764,0.0010344129,0.00013267547,0.000014474336,0.00029657973,0.006371823],"genre_scores_gemma":[0.9908809,0.00009620249,0.0079144025,0.00005578523,0.00024825378,7.072394e-7,0.000045221284,0.000011141887,0.00074740313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985694,0.00009580342,0.00014825068,0.0007466467,0.000089557776,0.00035028465],"domain_scores_gemma":[0.9983006,0.000053588494,0.00020460648,0.0011863193,0.0000765167,0.00017837533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020300568,0.00022419724,0.00020865111,0.00013080245,0.00018066501,0.00012671307,0.0014311521,0.00021675497,0.00005239095],"category_scores_gemma":[0.000012282856,0.00023607035,0.0001320971,0.00027018157,0.000043533546,0.00081208575,0.0029804413,0.0004148572,0.00023476187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003226527,0.0004059823,0.0065787076,0.0001676129,0.00013596675,0.00044447332,0.0006532979,0.034824263,0.00027853643,0.9073462,0.006015014,0.043117706],"study_design_scores_gemma":[0.00035372406,0.000024987747,0.003564673,0.00014524968,0.000052685264,0.000006613481,0.000025929412,0.931748,0.0003725973,0.05564156,0.0074813874,0.0005826082],"about_ca_topic_score_codex":0.000085948544,"about_ca_topic_score_gemma":0.000012409301,"teacher_disagreement_score":0.9391852,"about_ca_system_score_codex":0.000105059225,"about_ca_system_score_gemma":0.00007186935,"threshold_uncertainty_score":0.9626669},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.408002,0.00015637054,0.59027493,0.00003948645,0.0004291882,0.00014069822,0.000013084442,0.00017634382,0.00076790707],"genre_scores_gemma":[0.9949676,0.00006979335,0.0046267654,0.000059461367,0.00007672639,5.1720355e-7,0.00001189165,0.000014068963,0.00017321623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982648,0.00011216829,0.00017630596,0.00091890345,0.00012324973,0.00040457703],"domain_scores_gemma":[0.99839854,0.00014626214,0.00019404184,0.000927365,0.00008366709,0.00025014085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025122057,0.00028797315,0.00028339928,0.00020782891,0.00022151759,0.00021510493,0.00095608167,0.00024294577,0.000022477494],"category_scores_gemma":[0.000031973843,0.0002931907,0.000089727946,0.0003231449,0.00008718522,0.00036825,0.00397271,0.0005451752,0.000024013734],"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":[0.00014919392,0.0007955832,0.027337799,0.0003408152,0.0003790329,0.0012923891,0.0021532755,0.50169903,0.0011112797,0.44412333,0.00085581077,0.019762477],"study_design_scores_gemma":[0.0003224561,0.000019081717,0.014044765,0.00016131665,0.00004317234,0.000009620625,0.000030887517,0.98155355,0.00006182515,0.002812188,0.00052875397,0.0004123623],"about_ca_topic_score_codex":0.0002149153,"about_ca_topic_score_gemma":0.000011606433,"teacher_disagreement_score":0.58696556,"about_ca_system_score_codex":0.00011530766,"about_ca_system_score_gemma":0.000092541624,"threshold_uncertainty_score":0.999952},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07280155,0.00005516706,0.91484034,0.00003460051,0.00047336463,0.00020283106,0.000017059057,0.0003001884,0.011274885],"genre_scores_gemma":[0.987255,0.000051829047,0.010616276,0.00010467539,0.00009847965,8.7339146e-7,0.000021924334,0.000021950844,0.0018290192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980378,0.00008660842,0.00015234669,0.0012221774,0.00012576528,0.00037528054],"domain_scores_gemma":[0.9975572,0.000039935258,0.00022093025,0.0018451548,0.00014287925,0.00019387668],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015815244,0.0003464745,0.00032211523,0.00022396163,0.0001785022,0.00016295945,0.0023588322,0.00026432736,0.00006217102],"category_scores_gemma":[0.0000067269084,0.0003109182,0.00012301598,0.00038985503,0.00009397582,0.0007303274,0.003999637,0.000643761,0.000107889085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038528853,0.000761656,0.04735568,0.00038641432,0.00082208397,0.0055381316,0.0027241823,0.0927619,0.00009072399,0.8065546,0.008156829,0.03446251],"study_design_scores_gemma":[0.0023516808,0.00043127377,0.03051208,0.0010500221,0.00024459203,0.00008117345,0.00013298576,0.8419238,0.0006303178,0.100831755,0.018809833,0.003000502],"about_ca_topic_score_codex":0.000417482,"about_ca_topic_score_gemma":0.000035827135,"teacher_disagreement_score":0.91445345,"about_ca_system_score_codex":0.00010251067,"about_ca_system_score_gemma":0.00020701447,"threshold_uncertainty_score":0.9999343},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12243548,0.00014297616,0.87507516,0.000032127144,0.00067490834,0.00021348533,0.000030851963,0.000106644424,0.0012883352],"genre_scores_gemma":[0.98886794,0.00020037431,0.010094857,0.000024574227,0.00008332361,5.6665056e-7,0.00010582553,0.000010170165,0.00061236613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865484,0.00011027711,0.00021240131,0.0006937148,0.00013657527,0.00019218987],"domain_scores_gemma":[0.9977996,0.000032115473,0.00030561152,0.0014094056,0.0003138859,0.00013940033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037034968,0.00021130894,0.00032058096,0.00023464471,0.00008766271,0.00006661851,0.0015294561,0.00022487713,0.000011718618],"category_scores_gemma":[0.000021389498,0.00021363786,0.00015557204,0.0004095722,0.00007776637,0.00050031097,0.002003789,0.0002644269,0.00001647247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009745382,0.00019154004,0.00047261262,0.00010694167,0.00013960278,0.00018377,0.00036083904,0.32890925,0.0006769148,0.6551901,0.008865309,0.0048056417],"study_design_scores_gemma":[0.000994237,0.000043914726,0.00007762624,0.00005813071,0.00003587339,0.0000025496151,0.000017656164,0.89410883,0.0008375202,0.1023952,0.0011757272,0.00025274398],"about_ca_topic_score_codex":0.000166478,"about_ca_topic_score_gemma":0.000016763344,"teacher_disagreement_score":0.8664325,"about_ca_system_score_codex":0.00008451041,"about_ca_system_score_gemma":0.00022227234,"threshold_uncertainty_score":0.8711899},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014970705,0.0002522251,0.9938866,0.000297521,0.0041170088,0.0005585346,0.00003732578,0.00033767588,0.00036339488],"genre_scores_gemma":[0.0005516123,0.000019755209,0.9975941,0.00024412462,0.0006434515,0.00020286352,0.000088033055,0.000020625184,0.00063541485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980864,0.00012857797,0.00037995496,0.0009280967,0.00013947372,0.00033750056],"domain_scores_gemma":[0.9974393,0.0003720315,0.00024612702,0.0016127254,0.00020200567,0.0001278027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012160175,0.00029872684,0.00039192894,0.00008722443,0.00023251804,0.0006893241,0.0020198605,0.00040565728,0.000023948602],"category_scores_gemma":[0.00017488777,0.00022579143,0.00018411563,0.000076123484,0.000031006886,0.0002507884,0.003703102,0.00065400096,0.0000043930836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031582713,0.00006265072,0.0000035403627,0.0000971091,0.00002778897,4.7849204e-7,0.0001404772,0.00012548646,0.049699076,0.019475445,0.0025452198,0.92781955],"study_design_scores_gemma":[0.00015436296,0.000048384845,0.0000069709085,0.00003018024,0.000009273931,0.000003040266,0.000005591039,0.947573,0.018597472,0.012879647,0.020373477,0.0003185947],"about_ca_topic_score_codex":0.00026224265,"about_ca_topic_score_gemma":0.000031732885,"teacher_disagreement_score":0.94744754,"about_ca_system_score_codex":0.000022597964,"about_ca_system_score_gemma":0.00018727794,"threshold_uncertainty_score":0.92075074},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64552367,0.00020455125,0.35201687,0.000101863756,0.00028457525,0.0011730759,0.00056297256,0.00004352756,0.00008888153],"genre_scores_gemma":[0.86091053,0.000034997127,0.13741122,0.00011966315,0.000081211634,0.00024394487,0.0011108615,0.000025630963,0.00006195087],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765074,0.00011452971,0.00048583304,0.00087464665,0.00043533606,0.0004388923],"domain_scores_gemma":[0.998012,0.00006761948,0.00013955103,0.0015666132,0.00010915701,0.000105079096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009223762,0.00025788046,0.00040180003,0.0001787551,0.00008867451,0.00008319749,0.0017789636,0.00027442563,0.000014110264],"category_scores_gemma":[0.00012467185,0.00024690767,0.00008721308,0.00022880363,0.000055045093,0.00040561115,0.0035155383,0.00066603394,0.0000058682317],"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":[0.00014904448,0.0017610937,0.8883997,0.0032898746,0.0002847533,0.00014235612,0.001117281,0.0021854467,0.015275414,0.005998481,0.0073681967,0.074028365],"study_design_scores_gemma":[0.0038878603,0.00051668455,0.31563324,0.005621723,0.000066092536,0.000013151932,0.00012147834,0.34650669,0.24255127,0.014152515,0.067599274,0.0033300288],"about_ca_topic_score_codex":0.00018743557,"about_ca_topic_score_gemma":0.00001868996,"teacher_disagreement_score":0.5727665,"about_ca_system_score_codex":0.000102187696,"about_ca_system_score_gemma":0.00033432382,"threshold_uncertainty_score":0.99999833},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34210247,0.0025170264,0.6393553,0.0031213006,0.0043086344,0.0005584074,0.000050145496,0.0012000904,0.006786627],"genre_scores_gemma":[0.9575014,0.0002620207,0.039742813,0.00076452544,0.0007612965,0.000026848495,0.00012373856,0.000024637962,0.0007927154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99776644,0.00009771778,0.00031985732,0.0010008848,0.00038599357,0.0004290866],"domain_scores_gemma":[0.9973245,0.000066919885,0.0002499797,0.0021284982,0.00006859783,0.00016148038],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026368123,0.0003618387,0.00039120734,0.00013221505,0.00016595503,0.0003165039,0.002758692,0.00031254432,0.000039592185],"category_scores_gemma":[0.00003615454,0.0003168733,0.00016899037,0.0002250977,0.00003935134,0.0002750474,0.0034055144,0.00071116985,0.0003285538],"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":[0.000053778793,0.0006260491,0.22805443,0.00013329038,0.00023784794,0.00064120174,0.0018451889,0.0042853365,0.0012064406,0.009864242,0.12548588,0.6275663],"study_design_scores_gemma":[0.0009798799,0.00019754929,0.6624534,0.0011238346,0.00004526538,0.000036201647,0.000029493847,0.08104072,0.0019563725,0.018464977,0.23172298,0.001949343],"about_ca_topic_score_codex":0.00008658333,"about_ca_topic_score_gemma":0.00002193273,"teacher_disagreement_score":0.62561697,"about_ca_system_score_codex":0.00005690713,"about_ca_system_score_gemma":0.00012515846,"threshold_uncertainty_score":0.99992836},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015858077,0.000069155154,0.98125774,0.00013136132,0.00078894955,0.00041828715,0.0000977142,0.00028409003,0.0010946245],"genre_scores_gemma":[0.94274586,0.000007872551,0.05643735,0.00010619047,0.00014102538,0.0000024343803,0.00013457878,0.000019862766,0.00040481676],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980133,0.00013134761,0.00020426695,0.0010925637,0.00014732571,0.0004112036],"domain_scores_gemma":[0.99751514,0.00021476061,0.00024139613,0.0014604743,0.0002829248,0.0002852998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048497226,0.00029264568,0.0003875695,0.00021821285,0.00022218973,0.0002392736,0.002516877,0.00022602794,0.000008522373],"category_scores_gemma":[0.00005205251,0.00030979616,0.00019503164,0.00028802562,0.00007066415,0.00037104057,0.0016376151,0.00053360016,0.00004889467],"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":[0.00013145055,0.00029573566,0.0022067844,0.00020448978,0.00008978989,0.00009800483,0.0004598384,0.9193427,0.00008550517,0.058718286,0.013825487,0.0045419494],"study_design_scores_gemma":[0.00066906307,0.000082390856,0.000116257586,0.00010607347,0.00002610292,7.141436e-7,0.000037360085,0.9670902,0.0002641674,0.024489487,0.006739718,0.00037850073],"about_ca_topic_score_codex":0.00013458385,"about_ca_topic_score_gemma":0.000024191933,"teacher_disagreement_score":0.9268878,"about_ca_system_score_codex":0.00018468432,"about_ca_system_score_gemma":0.0005843279,"threshold_uncertainty_score":0.9999354},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12162164,0.000015862423,0.8737809,0.000024618863,0.0010633161,0.00012886545,0.000013651898,0.00012062466,0.003230513],"genre_scores_gemma":[0.996165,0.000027629294,0.00275566,0.000064149826,0.000055252778,3.6798323e-7,0.000015458432,0.000010999378,0.0009054786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851894,0.00011145461,0.0001812757,0.0008403557,0.0001213035,0.00022668748],"domain_scores_gemma":[0.99778324,0.00009320552,0.000307362,0.0015749593,0.00012825495,0.00011300223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022556826,0.0002284299,0.00034153284,0.00022613972,0.00009601995,0.00006370299,0.0021425972,0.00022695649,0.00002381382],"category_scores_gemma":[0.000032614153,0.00023706043,0.00014812789,0.00029083763,0.00006068522,0.0002467077,0.0028343596,0.0004281825,0.000053424243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056020133,0.00019972201,0.00091067754,0.00018435298,0.00008316746,0.00014601191,0.00018269832,0.21830513,0.000089109046,0.77303123,0.0025664724,0.004245427],"study_design_scores_gemma":[0.00047261437,0.00007231967,0.0009707634,0.00031646682,0.000023829052,0.0000014333873,0.00001025864,0.91558737,0.00045145612,0.080562435,0.0011804608,0.0003506253],"about_ca_topic_score_codex":0.00010568052,"about_ca_topic_score_gemma":0.000004211909,"teacher_disagreement_score":0.87454337,"about_ca_system_score_codex":0.0000704374,"about_ca_system_score_gemma":0.00011236718,"threshold_uncertainty_score":0.9667044},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014298442,0.0002841951,0.9819851,0.00010304551,0.0012440227,0.00045127736,0.0010130001,0.00027042726,0.00035047892],"genre_scores_gemma":[0.9505802,0.00012016886,0.047356367,0.000074414056,0.000116978605,0.0000014925967,0.0012405732,0.000019619409,0.00049018353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975652,0.000099803256,0.00020130024,0.0016429245,0.00013717051,0.00035359443],"domain_scores_gemma":[0.9953865,0.00013401796,0.00028579053,0.0037424762,0.00024647417,0.00020477868],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00031396718,0.00032854377,0.0003702047,0.00015925069,0.00019666845,0.0002799137,0.007847374,0.00026534835,0.000012592814],"category_scores_gemma":[0.000051111412,0.0003238744,0.000096974654,0.0002535666,0.00012237142,0.0009542551,0.010052197,0.0003868364,0.00001677662],"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":[0.00016919133,0.0002374457,0.0006185116,0.0005096037,0.00041459125,0.000458404,0.00044692084,0.59583056,0.00019006437,0.33627167,0.04899323,0.015859807],"study_design_scores_gemma":[0.0003794523,0.00003284771,0.00018796836,0.00005074666,0.000039943716,0.0000036436197,0.000028261771,0.820069,0.000020666832,0.17372121,0.005125451,0.00034082105],"about_ca_topic_score_codex":0.00023757193,"about_ca_topic_score_gemma":0.00006115548,"teacher_disagreement_score":0.93628174,"about_ca_system_score_codex":0.00012658087,"about_ca_system_score_gemma":0.0004179552,"threshold_uncertainty_score":0.9999213},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075281383,0.0000957621,0.9833805,0.00007898996,0.0022681744,0.0002866238,0.00010816264,0.000340542,0.0059131104],"genre_scores_gemma":[0.9941838,0.0001087672,0.0025535144,0.000120376586,0.00013555153,0.0000014708787,0.00016091087,0.000024017469,0.0027116416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977154,0.00018817716,0.0002264291,0.001279977,0.00018130883,0.00040869287],"domain_scores_gemma":[0.9969387,0.000102191116,0.00031456325,0.0018321925,0.0004730088,0.00033933853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002842315,0.0003954507,0.0004151395,0.00024999407,0.00016329564,0.00018375846,0.0029456036,0.00040120317,0.00004364313],"category_scores_gemma":[0.00004161187,0.00041809896,0.00017859618,0.0005490046,0.00011168673,0.00073240796,0.0074995854,0.00085258,0.00027490064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021491703,0.0012646244,0.0012145792,0.0002379093,0.0005567377,0.0034697582,0.0020971664,0.08347542,0.000038730024,0.7473302,0.13968964,0.02041034],"study_design_scores_gemma":[0.0006479553,0.000078842946,0.00018580844,0.00010802367,0.000039939918,0.00000869932,0.000059345344,0.8109041,0.00006160379,0.1777049,0.009635646,0.000565156],"about_ca_topic_score_codex":0.0002043123,"about_ca_topic_score_gemma":0.00001532082,"teacher_disagreement_score":0.9866556,"about_ca_system_score_codex":0.00038290664,"about_ca_system_score_gemma":0.00031672715,"threshold_uncertainty_score":0.9998271},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022864155,0.00027834202,0.9728288,0.0016299286,0.0017969416,0.0002567695,0.00030226508,0.000013663185,0.00002913875],"genre_scores_gemma":[0.41478541,0.000026104828,0.58456326,0.00017293043,0.00031815824,0.000005413329,0.000119547556,0.000007717017,0.0000014318229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998095,0.00013003324,0.0010114785,0.00031622808,0.00028620564,0.00016108411],"domain_scores_gemma":[0.9966672,0.00044308574,0.0018646532,0.00022522482,0.00070370926,0.00009609471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040994317,0.00018982365,0.0005894258,0.00021853887,0.000064151856,0.000044167155,0.00089397904,0.00018229896,0.0000060398543],"category_scores_gemma":[0.00007263859,0.00016092774,0.00025409693,0.00010528235,0.00012362999,0.000044599416,0.00081536704,0.0003308313,0.000001959521],"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":[0.0002491028,0.00019576953,0.00023969676,0.00015853437,0.0003492632,0.0000105362005,0.0003955043,0.83595705,0.0027400528,0.098973945,0.0011416678,0.05958888],"study_design_scores_gemma":[0.00087248196,0.0004621941,0.001354984,0.00010966672,0.00003080803,0.00013347808,0.000022291913,0.75421953,0.00022625139,0.237359,0.0050362716,0.00017302654],"about_ca_topic_score_codex":0.000008897316,"about_ca_topic_score_gemma":2.857675e-7,"teacher_disagreement_score":0.39192125,"about_ca_system_score_codex":0.00011098411,"about_ca_system_score_gemma":0.0005782596,"threshold_uncertainty_score":0.6562443},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26187918,0.00038825948,0.7357491,0.00050888397,0.00020970643,0.001157805,0.0000024356775,0.000009776091,0.000094819356],"genre_scores_gemma":[0.74716175,0.00018721202,0.2522446,0.00001152578,0.00017038638,0.000039791477,3.6419647e-7,0.000013345634,0.0001710519],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981118,0.00016050534,0.00043695734,0.0001879923,0.00083364686,0.00026912318],"domain_scores_gemma":[0.99536556,0.0030196195,0.00025699922,0.0005205887,0.0007523733,0.00008484032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006960162,0.000092074406,0.00023611364,0.00012721927,0.00024814703,0.0003063033,0.00080145744,0.00005654461,0.000008523607],"category_scores_gemma":[0.0011742216,0.00005116355,0.00009630437,0.00023580572,0.00007655876,0.00063893903,0.00046572182,0.00041006214,0.000003335059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010342101,0.0013859804,0.0009991034,0.0027961826,0.0002862961,0.000012984858,0.008916374,0.0009812736,0.010842762,0.15585102,0.0016709832,0.81522286],"study_design_scores_gemma":[0.0020256941,0.0005760079,0.00075827166,0.00031760047,0.000013970323,0.00010470691,0.00048815558,0.21858244,0.004092258,0.77099156,0.0019314009,0.00011792253],"about_ca_topic_score_codex":0.0000058965943,"about_ca_topic_score_gemma":0.0000059548697,"teacher_disagreement_score":0.8151049,"about_ca_system_score_codex":0.000090952955,"about_ca_system_score_gemma":0.00011714878,"threshold_uncertainty_score":0.29536897},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05181351,0.00030697964,0.943736,0.00019844814,0.0013414806,0.00022301116,0.00006301901,0.00037588013,0.0019416531],"genre_scores_gemma":[0.9829668,0.00017893706,0.014664808,0.0003300937,0.00027189596,9.3401934e-7,0.000041715288,0.000022735303,0.001522071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790794,0.00009998436,0.0001944294,0.0011597027,0.00014305316,0.0004949202],"domain_scores_gemma":[0.9972805,0.000069610505,0.00024195322,0.0019858994,0.00014056456,0.00028151585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022920198,0.0003519814,0.0003326078,0.00021384849,0.00022911122,0.00019887445,0.0025503696,0.00033285798,0.00013539364],"category_scores_gemma":[0.000014431542,0.00037656308,0.00023400882,0.00043449577,0.00006187488,0.00081172766,0.005079052,0.0006709429,0.00041037617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014127085,0.0012930696,0.043825198,0.0010681618,0.000763567,0.0015908452,0.005665056,0.123232365,0.00037552416,0.7002799,0.089422375,0.03234268],"study_design_scores_gemma":[0.0007684718,0.00005443256,0.003076274,0.0003508438,0.00012160517,0.000018135212,0.000093783936,0.90451074,0.00044393624,0.038631085,0.050528932,0.0014017647],"about_ca_topic_score_codex":0.00020692126,"about_ca_topic_score_gemma":0.0000058892447,"teacher_disagreement_score":0.9311533,"about_ca_system_score_codex":0.00014595255,"about_ca_system_score_gemma":0.00014257178,"threshold_uncertainty_score":0.99986863},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006318871,0.0048814216,0.22710305,0.00017904547,0.0014347549,0.00052931096,0.00013241859,0.00025580253,0.765421],"genre_scores_gemma":[0.0011693916,0.03699571,0.22380053,0.000089653346,0.0025867093,0.000050265135,0.00008160127,0.00024597743,0.73498017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974698,0.00001825321,0.00062491867,0.0008507772,0.0005763111,0.00045995612],"domain_scores_gemma":[0.9979594,0.00018380728,0.00048092153,0.0009890936,0.00013538508,0.0002513903],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030293173,0.00047227586,0.000584242,0.00025815077,0.00012290587,0.000088140594,0.0010827638,0.0003304941,0.0000716206],"category_scores_gemma":[0.000027464414,0.00037417514,0.00012483732,0.00006222987,0.00014011626,0.0006626847,0.0011539371,0.0003756867,0.000055126286],"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":[0.000003460238,0.000022393746,0.00005898633,0.00012143896,0.00005960287,0.000050756007,0.00018741554,0.00000394557,0.000030138941,0.18073133,0.0009591761,0.8177714],"study_design_scores_gemma":[0.0009351842,0.00026854352,0.00041213018,0.001869459,0.00005816273,0.00008314497,0.0000065036184,0.0020132489,0.00019138189,0.07766221,0.9152496,0.0012504751],"about_ca_topic_score_codex":0.00002415686,"about_ca_topic_score_gemma":0.000003929599,"teacher_disagreement_score":0.91429037,"about_ca_system_score_codex":0.0000561001,"about_ca_system_score_gemma":0.00014450362,"threshold_uncertainty_score":0.999871},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078429915,0.00016177719,0.92018986,0.00012620822,0.00016315893,0.00046278545,0.0001978096,0.000048299702,0.00022018357],"genre_scores_gemma":[0.97358894,0.00009516901,0.026092397,0.000019862942,0.000023146815,0.0000052571345,0.000038885046,0.0000084013545,0.00012792878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885654,0.00006527855,0.00017596576,0.00058884843,0.00007081805,0.00024257158],"domain_scores_gemma":[0.9984671,0.00021557842,0.00019589251,0.000875408,0.00014542401,0.00010060426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014949644,0.00017588589,0.00026831482,0.00022667,0.00012371619,0.00004212866,0.0009334429,0.00016355117,0.000011898859],"category_scores_gemma":[0.00003447134,0.00016895101,0.000054142365,0.0002541985,0.0002618424,0.00047244827,0.0018834915,0.00024185082,0.000002866544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003927169,0.00031365434,0.0012943277,0.00021509705,0.00006578898,0.000033630626,0.00047239775,0.049181443,0.00023369433,0.938362,0.0012420788,0.008546603],"study_design_scores_gemma":[0.0011464122,0.000074933436,0.0025467265,0.0003658572,0.000029804736,0.0000043472432,0.00008211999,0.89649975,0.000045127184,0.098787166,0.00016680713,0.00025095342],"about_ca_topic_score_codex":0.0004151611,"about_ca_topic_score_gemma":0.00009642667,"teacher_disagreement_score":0.89515907,"about_ca_system_score_codex":0.00004675346,"about_ca_system_score_gemma":0.00012887147,"threshold_uncertainty_score":0.6889622},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06854603,0.0011314678,0.92811316,0.0007395137,0.00042101374,0.00015269195,0.0000014010667,0.00008352719,0.00081120356],"genre_scores_gemma":[0.9523371,0.000117910815,0.047103085,0.00036730798,0.000026247619,0.000014871735,0.0000014076792,0.0000036049707,0.000028501076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914193,0.00012838347,0.00016216865,0.00023711103,0.00022025063,0.0001101486],"domain_scores_gemma":[0.99881405,0.00048244404,0.00015561153,0.0003170364,0.00014279854,0.00008807012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041512042,0.00008624544,0.00012284207,0.000026814505,0.0001279525,0.00011492101,0.00030029187,0.000037264464,0.000001959233],"category_scores_gemma":[0.0010037044,0.000052564723,0.000016499589,0.00015171549,0.00026459503,0.001794039,0.0004993422,0.00012619405,0.0000020982907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015193453,0.00028239258,0.0025148485,0.00006377354,0.000061217004,0.000027821057,0.19634849,0.00009675163,0.0016397627,0.04918894,0.005674932,0.7425817],"study_design_scores_gemma":[0.015149408,0.0020993,0.005561611,0.0009158105,0.00015068367,0.0016583685,0.15493432,0.5090496,0.015624195,0.03787835,0.25523832,0.0017400576],"about_ca_topic_score_codex":0.00038337626,"about_ca_topic_score_gemma":0.0000032063192,"teacher_disagreement_score":0.883791,"about_ca_system_score_codex":0.000012015096,"about_ca_system_score_gemma":0.00003707149,"threshold_uncertainty_score":0.21435273},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029570656,0.00014486344,0.9675799,0.00016137034,0.00022271996,0.0011203398,0.00023029173,0.00020967887,0.0007601729],"genre_scores_gemma":[0.93468827,0.00006217051,0.06376473,0.00017421063,0.0002688445,0.000062840045,0.00013717465,0.00002811412,0.0008136644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828374,0.000052832536,0.00016234172,0.00096958294,0.00012395547,0.00040756454],"domain_scores_gemma":[0.9979565,0.000116133575,0.00021524761,0.0012444635,0.00018867437,0.0002789849],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000212452,0.00031033935,0.00031710626,0.00023232479,0.00030571103,0.00015533759,0.0017691592,0.00018773267,0.000029750516],"category_scores_gemma":[0.000008034895,0.0002870218,0.00012415746,0.00046166882,0.00007794531,0.00066655746,0.0018407479,0.00027584465,0.00006735985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006069086,0.0006431225,0.053190604,0.0006111542,0.00036288484,0.0001292718,0.0014555453,0.019414933,0.000043436637,0.89604926,0.0039218487,0.023571057],"study_design_scores_gemma":[0.008607218,0.0010984741,0.12707973,0.0011045908,0.0010288672,0.00010746943,0.0006797637,0.29825085,0.0005509458,0.09403185,0.4604926,0.0069676293],"about_ca_topic_score_codex":0.00013401239,"about_ca_topic_score_gemma":0.00013012266,"teacher_disagreement_score":0.9051176,"about_ca_system_score_codex":0.0000936794,"about_ca_system_score_gemma":0.00016825441,"threshold_uncertainty_score":0.9999582},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17156044,0.00007477724,0.8265035,0.00007989072,0.00052255054,0.00056981033,0.00031350576,0.00017782701,0.00019768061],"genre_scores_gemma":[0.97526443,0.00006009076,0.023799997,0.00004071066,0.000058522743,0.000003425546,0.00018137592,0.000023634595,0.00056784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979448,0.00013995782,0.0002799127,0.0011099258,0.00014897018,0.00037644044],"domain_scores_gemma":[0.99710536,0.0002642855,0.0004898158,0.0016072192,0.000333143,0.00020014776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017430226,0.0003726872,0.00051313057,0.0003419241,0.00019118811,0.00009318358,0.0027276278,0.00035200853,0.000031462685],"category_scores_gemma":[0.000019067355,0.00037655348,0.0003109158,0.0003803149,0.00018851529,0.00053321937,0.0025839775,0.00036363024,0.000016212683],"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":[0.0004915083,0.0010816586,0.002085296,0.00080451404,0.00022860472,0.00028473578,0.00030638193,0.7783696,0.0028098098,0.19583693,0.010817138,0.0068838275],"study_design_scores_gemma":[0.0013269632,0.00016859747,0.0010002485,0.00035295603,0.00006096446,0.0000010562089,0.000047053647,0.9822091,0.00093071413,0.010840608,0.0026263834,0.00043538347],"about_ca_topic_score_codex":0.0003400531,"about_ca_topic_score_gemma":0.00003466367,"teacher_disagreement_score":0.80370396,"about_ca_system_score_codex":0.00012726575,"about_ca_system_score_gemma":0.0002990096,"threshold_uncertainty_score":0.99986863},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20040485,0.000052760537,0.79507124,0.000035018515,0.0010165366,0.0002577218,0.000028030374,0.0005872385,0.002546601],"genre_scores_gemma":[0.99210936,0.00014038481,0.0065516527,0.00007359305,0.00008223732,0.0000013241912,0.000057144844,0.000022959304,0.00096134684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974621,0.00018637202,0.0002421806,0.0014865544,0.0001543547,0.00046846332],"domain_scores_gemma":[0.9970203,0.00009848054,0.0003654399,0.0020991568,0.00016289299,0.00025374882],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025149758,0.00041963984,0.00042394936,0.000373563,0.00023270116,0.00024715712,0.0031371883,0.00038905587,0.000027448626],"category_scores_gemma":[0.000028725402,0.00044824288,0.00022330221,0.00058781466,0.00010430382,0.00055117486,0.0043092766,0.00077240966,0.000098453995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013593714,0.0006723076,0.009255631,0.0005055703,0.0005134944,0.0017389691,0.00082693994,0.20120741,0.0005947387,0.73150706,0.0073858667,0.045656074],"study_design_scores_gemma":[0.00064887357,0.000085919855,0.0043411977,0.00026374462,0.0000656822,0.000009630386,0.000014101678,0.864686,0.00039303862,0.12327759,0.00532126,0.00089297374],"about_ca_topic_score_codex":0.00019070806,"about_ca_topic_score_gemma":0.000024486291,"teacher_disagreement_score":0.79170454,"about_ca_system_score_codex":0.00012414964,"about_ca_system_score_gemma":0.00014869352,"threshold_uncertainty_score":0.9997969},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39766496,0.000309637,0.5824467,0.003712913,0.0045448868,0.00078236504,0.000051201176,0.00044159815,0.010045744],"genre_scores_gemma":[0.99379486,0.00003424606,0.0037289613,0.0010629527,0.0004391458,0.000084870655,0.000049043894,0.000024232582,0.0007816691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799347,0.00016402263,0.00035374914,0.0007751644,0.00037327965,0.00034030588],"domain_scores_gemma":[0.99704957,0.00048154438,0.00023340102,0.0020966001,0.00005458267,0.00008433114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040022697,0.0003353893,0.00033181725,0.0000863425,0.00024437904,0.00028149466,0.0026220107,0.00020320623,0.000037009097],"category_scores_gemma":[0.00011322357,0.00020734397,0.00018642582,0.0001323126,0.000095224525,0.00013163226,0.0025577042,0.00085890485,0.0003876109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005496405,0.0017244248,0.07141564,0.0005913423,0.00062037614,0.001638347,0.003822669,0.009830135,0.0011662651,0.063992076,0.33226705,0.51238203],"study_design_scores_gemma":[0.0043405276,0.00048612212,0.21206488,0.0022564144,0.00016644454,0.00007426354,0.000061460516,0.6062405,0.00385057,0.040649805,0.12657508,0.003233942],"about_ca_topic_score_codex":0.00019026833,"about_ca_topic_score_gemma":0.000009283618,"teacher_disagreement_score":0.59641033,"about_ca_system_score_codex":0.00006148032,"about_ca_system_score_gemma":0.000115999566,"threshold_uncertainty_score":0.8455242},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16855401,0.000053387495,0.8282309,0.00054570416,0.001307891,0.00021677685,0.00003077445,0.00030380292,0.00075674115],"genre_scores_gemma":[0.85455287,0.0001395753,0.14191939,0.001884606,0.0005593972,0.00006758548,0.0006977031,0.000025359142,0.00015354954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824613,0.000058506386,0.00045172722,0.0004746718,0.00042753946,0.00034141107],"domain_scores_gemma":[0.9981835,0.00008251433,0.0002263044,0.001251835,0.00009825631,0.0001575931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019002218,0.0002819158,0.00028609147,0.00019683804,0.00020477014,0.00021778968,0.0015904589,0.00027757592,0.000017090217],"category_scores_gemma":[0.00006058861,0.0002571306,0.00012873934,0.00016084923,0.00006281942,0.0010587606,0.0034667582,0.00078669604,0.0004872471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003123404,0.0009966426,0.11770206,0.0016487371,0.00030628787,0.0006269995,0.011720355,0.10285703,0.0017482208,0.003415692,0.07836322,0.68030244],"study_design_scores_gemma":[0.00042298334,0.000048136062,0.042011462,0.00017413149,0.0000063526,0.000025322619,0.0000066866664,0.9245256,0.0004563267,0.00021848409,0.031673633,0.00043088302],"about_ca_topic_score_codex":0.00007039946,"about_ca_topic_score_gemma":0.0000038341645,"teacher_disagreement_score":0.82166857,"about_ca_system_score_codex":0.000076908036,"about_ca_system_score_gemma":0.0002505266,"threshold_uncertainty_score":0.9999881},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63826394,0.000104670755,0.3410191,0.00022024379,0.0013313793,0.0005998381,0.00007695142,0.00069590344,0.017687991],"genre_scores_gemma":[0.9787746,0.0002715491,0.010946629,0.00028878928,0.0002872983,0.000005423184,0.00012556602,0.000055451816,0.009244714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99582565,0.00022810839,0.00041136227,0.0023806843,0.00034652994,0.0008076525],"domain_scores_gemma":[0.99494416,0.00013520493,0.00063451036,0.003294222,0.00043560052,0.0005563214],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033238786,0.00073183625,0.00074926845,0.00040078405,0.00039320329,0.00053571566,0.0047784313,0.00071853097,0.00022315216],"category_scores_gemma":[0.00006038838,0.0007750366,0.00033936065,0.0007361508,0.00018968064,0.0013924681,0.0069999234,0.0012165935,0.0013890017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000169565,0.0006794057,0.0034504829,0.00047123412,0.0005404253,0.007091336,0.0017604842,0.28399628,0.0012970216,0.68265045,0.013004002,0.0048892796],"study_design_scores_gemma":[0.0012941487,0.0003326637,0.0017299978,0.000859996,0.00020198029,0.00014312017,0.0005296591,0.9334043,0.0026185254,0.044776738,0.0115908235,0.0025179929],"about_ca_topic_score_codex":0.0018800079,"about_ca_topic_score_gemma":0.000037546015,"teacher_disagreement_score":0.64940804,"about_ca_system_score_codex":0.0005595898,"about_ca_system_score_gemma":0.0007135535,"threshold_uncertainty_score":0.99947006},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029367635,0.000029289835,0.9629586,0.00008856605,0.00038245248,0.0001508252,0.000023529996,0.00018382864,0.0068153245],"genre_scores_gemma":[0.993582,0.000542972,0.005301646,0.000040241524,0.000046700214,6.043446e-7,0.000027798545,0.000010500591,0.00044751388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840575,0.00007188652,0.00017802832,0.0009375902,0.00009680046,0.0003099114],"domain_scores_gemma":[0.9985877,0.00006468164,0.00014835819,0.0010361379,0.000043717417,0.000119406126],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001331684,0.00021628282,0.00023235682,0.00037091773,0.00018585517,0.00010037227,0.0013863642,0.00021201106,0.000021070175],"category_scores_gemma":[0.000016057387,0.0002562532,0.000113061695,0.00055882405,0.00008214377,0.0005582679,0.0026778325,0.00059852016,0.000037209185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015354699,0.000120628414,0.0021209584,0.000035253586,0.00002395877,0.001726687,0.0002534876,0.09856342,0.000012044538,0.8957914,0.0011249864,0.00021182525],"study_design_scores_gemma":[0.00058289926,0.000035578756,0.0021836853,0.00025082697,0.000013085776,0.00002517646,0.00011122512,0.7975186,0.000027836571,0.19757675,0.0011593731,0.00051495025],"about_ca_topic_score_codex":0.00025458282,"about_ca_topic_score_gemma":0.00004633996,"teacher_disagreement_score":0.9642144,"about_ca_system_score_codex":0.0005028534,"about_ca_system_score_gemma":0.00017454856,"threshold_uncertainty_score":0.999989},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02804389,0.00048796038,0.96853966,0.0014923051,0.0003808852,0.000096456584,0.0000042910647,0.0002072547,0.00074732717],"genre_scores_gemma":[0.83897746,0.00027921316,0.1585213,0.0019566081,0.00010912492,0.00004126662,0.000005732312,0.000009871101,0.00009941827],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989236,0.000099259196,0.0001559954,0.0004306794,0.00018293019,0.00020752825],"domain_scores_gemma":[0.998584,0.0006115767,0.000096220945,0.00046433453,0.000087887805,0.00015603648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020177831,0.00013131324,0.00012621155,0.000073080046,0.00046070677,0.00033408974,0.0003627697,0.000057852827,0.000010266611],"category_scores_gemma":[0.00047004272,0.000114381146,0.000015106639,0.00022019015,0.00015117931,0.00260086,0.0005972032,0.00018117989,0.0000118109],"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":[0.00007663436,0.00048539275,0.005971269,0.00008320459,0.00006326827,0.000049091883,0.06840532,0.000085591346,0.0029552272,0.091569915,0.007651642,0.82260346],"study_design_scores_gemma":[0.0011934311,0.0006397948,0.0074144397,0.00016175234,0.000038461025,0.0006565494,0.007634459,0.06170084,0.0014708826,0.010886326,0.90723497,0.00096812565],"about_ca_topic_score_codex":0.00021057419,"about_ca_topic_score_gemma":0.000008349101,"teacher_disagreement_score":0.8995833,"about_ca_system_score_codex":0.000009805948,"about_ca_system_score_gemma":0.000023408098,"threshold_uncertainty_score":0.46643278},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056482307,0.005581894,0.9810733,0.00021713592,0.005253977,0.0005368156,0.0011317518,0.00024929756,0.00030760028],"genre_scores_gemma":[0.1759388,0.002944276,0.81451064,0.00078027305,0.0043958556,0.00009671472,0.0011793447,0.00006141418,0.0000926948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659777,0.00018006879,0.0005472214,0.0013931855,0.0006927987,0.0005889875],"domain_scores_gemma":[0.9965684,0.0010357266,0.00046360595,0.0013976946,0.00020762472,0.00032695514],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039140755,0.0006436969,0.0009264762,0.00017646409,0.00040849825,0.0011627959,0.0020606222,0.00077601307,0.00010799869],"category_scores_gemma":[0.00019943703,0.00049573893,0.0001877259,0.00034643925,0.00015521438,0.00038696267,0.0048687058,0.0019672837,0.000007975768],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101491525,0.00004042128,0.00016200342,0.000043506552,0.00023355735,0.00013629395,0.00055674085,0.0022261415,0.000051532905,0.012707492,0.00825419,0.97548664],"study_design_scores_gemma":[0.0034056562,0.00007423253,0.0046650823,0.00019426679,0.00010405837,0.000033730183,0.000017165261,0.52800083,0.00025137558,0.43182132,0.030260677,0.0011716022],"about_ca_topic_score_codex":0.0008466003,"about_ca_topic_score_gemma":0.000036739,"teacher_disagreement_score":0.97431505,"about_ca_system_score_codex":0.000029846475,"about_ca_system_score_gemma":0.00018316775,"threshold_uncertainty_score":0.9998741},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21650398,0.00029779915,0.7784002,0.000654804,0.0006780281,0.00041051843,0.000020992333,0.00052448106,0.0025091958],"genre_scores_gemma":[0.74156266,0.000089881876,0.25524464,0.0017513424,0.0007284118,0.00005512187,0.00013091238,0.000064666,0.00037234006],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972186,0.00007363866,0.00044550223,0.0011513284,0.00056990125,0.00054102927],"domain_scores_gemma":[0.99730796,0.00005862624,0.00043988077,0.0018352205,0.00022008603,0.00013822764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005142851,0.00045939922,0.00046427659,0.000117891956,0.00024071289,0.0005221617,0.0018946102,0.00022909879,0.000026509539],"category_scores_gemma":[0.000034371627,0.0003535848,0.00010643213,0.00021366435,0.00006533444,0.00062949536,0.0025214977,0.0008443005,0.00012587238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004703814,0.003145245,0.5610804,0.0035881419,0.0012883047,0.0030805569,0.017238507,0.021583108,0.0064426027,0.031190159,0.066503845,0.28438875],"study_design_scores_gemma":[0.0022440695,0.0005514644,0.10506547,0.004320686,0.00012448926,0.00022848316,0.00015615225,0.84276575,0.0038981207,0.009131658,0.028062627,0.0034510284],"about_ca_topic_score_codex":0.00015646627,"about_ca_topic_score_gemma":0.000011385061,"teacher_disagreement_score":0.82118267,"about_ca_system_score_codex":0.00009364292,"about_ca_system_score_gemma":0.00019225731,"threshold_uncertainty_score":0.99989164},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025913797,0.0004004982,0.9702483,0.00026523048,0.0015304389,0.00089136505,0.00007668203,0.00030588082,0.0003678279],"genre_scores_gemma":[0.22845148,0.00033084216,0.7677589,0.000504021,0.0006847116,0.0001506418,0.00028226792,0.00008552058,0.0017515821],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976398,0.000053013977,0.00039705556,0.000950522,0.0003859226,0.00057368533],"domain_scores_gemma":[0.9983078,0.0002552009,0.00020081211,0.00081739714,0.00019047603,0.0002282657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038184895,0.0003399392,0.00038669416,0.00017072556,0.00023256501,0.00035221942,0.0008908218,0.00018421315,0.000028989192],"category_scores_gemma":[0.00004771554,0.00030466396,0.00009703155,0.00033640309,0.00004297635,0.0011258386,0.00054420886,0.00019463427,0.00005745386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025479772,0.00017213458,0.0012996421,0.00010250383,0.00007540379,0.000015378688,0.0008592155,0.00008224389,0.0038044278,0.009208415,0.0013605008,0.9829947],"study_design_scores_gemma":[0.0026670627,0.00058391347,0.0036266583,0.00009528816,0.000027717857,0.000049170234,0.00010387364,0.943114,0.008529686,0.0051085395,0.035295118,0.00079899846],"about_ca_topic_score_codex":0.00011204639,"about_ca_topic_score_gemma":0.0000052271466,"teacher_disagreement_score":0.9821957,"about_ca_system_score_codex":0.00006012027,"about_ca_system_score_gemma":0.000078593876,"threshold_uncertainty_score":0.9999406},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001639939,0.00062319695,0.9645638,0.0008819575,0.004329048,0.0005234653,0.00010211876,0.0004739282,0.026862552],"genre_scores_gemma":[0.31269765,0.00028546265,0.67856574,0.0048670187,0.0009459046,0.0002794776,0.00048890704,0.000054195938,0.0018156185],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977863,0.000044530734,0.0006364667,0.00034086054,0.0006171307,0.00057470484],"domain_scores_gemma":[0.99712694,0.00006292078,0.0004023671,0.0020689266,0.000075137985,0.00026371682],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004024888,0.00036909326,0.00036620887,0.00013713661,0.00018100954,0.00076565007,0.0026050913,0.00023885732,0.00026065297],"category_scores_gemma":[0.000023841903,0.00031327218,0.00014322167,0.00014983866,0.00006309336,0.0020586897,0.007162992,0.00073449925,0.0020098824],"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":[0.000030639887,0.0007675297,0.0016275293,0.0019987077,0.00035338837,0.000030016223,0.017413527,0.00077643874,0.00009634478,0.33697253,0.3444603,0.295473],"study_design_scores_gemma":[0.00087715447,0.000095576266,0.0031786906,0.0008845267,0.00005262306,0.00007659951,0.00016717728,0.21419056,0.00080680184,0.02160283,0.7561428,0.0019246646],"about_ca_topic_score_codex":0.00003619325,"about_ca_topic_score_gemma":9.670455e-7,"teacher_disagreement_score":0.4116825,"about_ca_system_score_codex":0.00013095583,"about_ca_system_score_gemma":0.00013432297,"threshold_uncertainty_score":0.99993193},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14568302,0.00004008751,0.8502337,0.0004610826,0.0010049985,0.00027693,0.00009092104,0.00030743558,0.0019018446],"genre_scores_gemma":[0.98314583,0.0001449414,0.013254042,0.00027438652,0.00016745491,0.0000011377441,0.000072121176,0.000022839093,0.0029172436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767244,0.00013294772,0.00019441545,0.0012954199,0.00022414244,0.0004806187],"domain_scores_gemma":[0.9971517,0.00014266903,0.00015345089,0.0021115968,0.00017748518,0.00026312168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002819305,0.00034768664,0.0003538207,0.00024869764,0.00021646431,0.00023827465,0.0031440782,0.0004037211,0.00012542318],"category_scores_gemma":[0.000025103614,0.00035002292,0.00016685012,0.00046266644,0.0001454697,0.0006504969,0.004792543,0.0013535836,0.00011528508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016109941,0.0010060675,0.008925627,0.00047494104,0.00044812248,0.0030870722,0.002260513,0.44457388,0.0014720337,0.4764868,0.033835437,0.027268423],"study_design_scores_gemma":[0.00047073208,0.000053283224,0.003042728,0.00009255939,0.000033718516,0.000005889356,0.000048824862,0.96550363,0.00031809573,0.021695789,0.008165075,0.00056968984],"about_ca_topic_score_codex":0.00043699585,"about_ca_topic_score_gemma":0.00008905814,"teacher_disagreement_score":0.8374628,"about_ca_system_score_codex":0.000113126414,"about_ca_system_score_gemma":0.0002935575,"threshold_uncertainty_score":0.99989516},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49849075,0.011086957,0.39348337,0.004702981,0.032440946,0.0063607944,0.0008596311,0.0035319638,0.049042605],"genre_scores_gemma":[0.72374064,0.00925302,0.21253271,0.010885251,0.006399271,0.0002967873,0.0023570722,0.0006051243,0.033930153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904276,0.00045337362,0.002472241,0.0018646418,0.0022826907,0.0024994344],"domain_scores_gemma":[0.9928868,0.00036080385,0.0016730474,0.0033461608,0.0007178732,0.0010153151],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0011210191,0.0015622145,0.0017028779,0.000917618,0.0010899388,0.0021333776,0.0051332754,0.0011560756,0.0005642121],"category_scores_gemma":[0.00009892637,0.0012854789,0.00082238734,0.001631732,0.0004316326,0.006621328,0.003963728,0.002654502,0.0014667242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018500336,0.0008518322,0.014906662,0.00030537136,0.0004787408,0.0004225871,0.003106373,0.00030665915,0.0038564336,0.0020857807,0.02858923,0.94490534],"study_design_scores_gemma":[0.004868732,0.002318711,0.04000254,0.0013950185,0.00014524789,0.000888491,0.0012225239,0.37484494,0.008709138,0.0002974062,0.5624336,0.0028736487],"about_ca_topic_score_codex":0.0001834702,"about_ca_topic_score_gemma":0.000012839058,"teacher_disagreement_score":0.9420317,"about_ca_system_score_codex":0.00040202006,"about_ca_system_score_gemma":0.0005329525,"threshold_uncertainty_score":0.9997126},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016184651,0.0012210803,0.9874264,0.0014434247,0.0024406188,0.000424005,0.00003098308,0.00015305007,0.0068442705],"genre_scores_gemma":[0.09211573,0.00033629988,0.8937009,0.001968523,0.005194157,0.000024114039,0.00009655341,0.00012392622,0.0064397883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99586886,0.000068415495,0.0005192817,0.0015426243,0.0012630703,0.0007377499],"domain_scores_gemma":[0.9951144,0.0017043601,0.00042333355,0.002348342,0.00024499735,0.0001645718],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00087636325,0.0005392407,0.00052686327,0.00031553695,0.00063379266,0.0008646553,0.005827371,0.00025795345,0.0000109498305],"category_scores_gemma":[0.000115841845,0.00036680506,0.00014306714,0.0005075552,0.00082382455,0.0011282585,0.0031019973,0.0012305863,0.00015370472],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000489154,0.000011297492,0.00027250868,0.000018311763,0.000023985765,0.00006260727,0.000573907,0.0039651464,0.000027673668,0.13214941,0.00026348582,0.8626268],"study_design_scores_gemma":[0.000722713,0.00030183446,0.0007840846,0.0010566202,0.00002427287,0.000037805286,7.7938097e-7,0.53502953,0.0004141922,0.3106351,0.14946131,0.0015317933],"about_ca_topic_score_codex":0.000027774717,"about_ca_topic_score_gemma":0.000082783234,"teacher_disagreement_score":0.86109495,"about_ca_system_score_codex":0.0002627822,"about_ca_system_score_gemma":0.00056949304,"threshold_uncertainty_score":0.9998784},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03835577,0.00006832401,0.9566785,0.00043513218,0.00083237916,0.0013331072,0.0010421847,0.00025817464,0.0009964128],"genre_scores_gemma":[0.35612285,0.00007141148,0.637121,0.0019323281,0.0005891021,0.0003465561,0.0011077821,0.00010672828,0.002602208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979481,0.000019156436,0.0006426795,0.00037838717,0.00028938652,0.0007222659],"domain_scores_gemma":[0.9980727,0.00013237704,0.0003100687,0.0009314406,0.0003200156,0.00023339204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042649018,0.00035689722,0.0003932176,0.00017920505,0.00057560514,0.0006965042,0.0010897105,0.00019160291,0.000014732176],"category_scores_gemma":[0.000064084306,0.0003019993,0.00014780079,0.00019742471,0.00018415079,0.0024042965,0.0007692547,0.00018720295,0.0000797181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024319096,0.0022391796,0.0021243885,0.0040983595,0.0013284051,0.000017931057,0.07829666,0.00018010355,0.013185939,0.07100361,0.1401862,0.6849073],"study_design_scores_gemma":[0.002557492,0.0004979244,0.00014968343,0.000074228745,0.000020871708,0.00003152976,0.0000962943,0.93281406,0.000586033,0.0015441852,0.061220173,0.0004075343],"about_ca_topic_score_codex":0.000027378363,"about_ca_topic_score_gemma":0.000024821544,"teacher_disagreement_score":0.93263394,"about_ca_system_score_codex":0.00008195536,"about_ca_system_score_gemma":0.0000740556,"threshold_uncertainty_score":0.9999432},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009666289,0.00001500139,0.99633086,0.00028823456,0.00019207547,0.00011416155,0.0000027033723,0.00023598572,0.0018543586],"genre_scores_gemma":[0.46781766,0.0000011275508,0.53156793,0.0003637463,0.00006107756,0.000010126731,0.00000757369,0.00000388671,0.00016684558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923307,0.000025090196,0.000122295,0.00028241577,0.00011786121,0.00021927654],"domain_scores_gemma":[0.9992775,0.00019486749,0.000051253413,0.00027226965,0.00013138812,0.00007275946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021548495,0.00008527107,0.00009324018,0.000044029424,0.00027191974,0.0001442937,0.00050189823,0.000036837857,0.00007343715],"category_scores_gemma":[0.00009557396,0.000067923,0.000035749694,0.00012462209,0.00010128641,0.0003044372,0.000115977404,0.00005521725,0.00004341169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003869054,0.000093109375,0.0010116339,0.00003992359,0.000022903167,0.000013394243,0.00044555447,0.002109539,0.01316536,0.18933932,0.0042666276,0.7894539],"study_design_scores_gemma":[0.00029114156,0.00016325706,0.000055218316,0.000014575063,0.0000017275297,0.000004260506,0.000014842853,0.98043025,0.008069894,0.0014688065,0.009374609,0.000111426394],"about_ca_topic_score_codex":0.000022330725,"about_ca_topic_score_gemma":0.000020065758,"teacher_disagreement_score":0.9783207,"about_ca_system_score_codex":0.000016097605,"about_ca_system_score_gemma":0.000057872072,"threshold_uncertainty_score":0.27698195},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30087757,0.00034715602,0.64547205,0.001404947,0.0035834492,0.00018536614,0.000018207082,0.00006573137,0.048045546],"genre_scores_gemma":[0.97698224,0.000021626285,0.02153406,0.00066606334,0.0004618776,0.0000013923842,7.6181914e-7,0.0000064565597,0.00032551138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893475,0.00021552105,0.0002952581,0.00012134743,0.000283819,0.00014932819],"domain_scores_gemma":[0.99884385,0.00052958063,0.00021377037,0.0002446477,0.000097376585,0.000070772454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011909554,0.00008252594,0.00016886648,0.00009136097,0.000058305483,0.00006743646,0.0006439249,0.000040541247,0.00074543856],"category_scores_gemma":[0.0001625682,0.000054511103,0.00006888793,0.00017972474,0.000065233995,0.0005754783,0.000110250534,0.00018878227,0.0001299847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018295114,0.00062416383,0.0037961858,0.000020749434,0.00009967382,0.0008969206,0.0040176655,0.00020184899,0.00074328744,0.4594662,0.13982324,0.38848057],"study_design_scores_gemma":[0.0044599753,0.000940666,0.007672206,0.0006205303,0.000010756057,0.0007210737,0.00022600811,0.0062278863,0.0015799749,0.9284376,0.0487462,0.00035712274],"about_ca_topic_score_codex":0.0000059020267,"about_ca_topic_score_gemma":0.0000026452606,"teacher_disagreement_score":0.67610466,"about_ca_system_score_codex":0.00003213355,"about_ca_system_score_gemma":0.00008345868,"threshold_uncertainty_score":0.81620294},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036800199,0.000014443824,0.9786551,0.00050069595,0.000100557205,0.000385979,0.0000020304406,0.00015284895,0.016508326],"genre_scores_gemma":[0.6868123,0.000006751378,0.30945888,0.001901435,0.00017644286,0.000120354554,0.000007816117,0.000014636024,0.0015014131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989318,0.000037053545,0.00014476385,0.00035943513,0.0003031909,0.00022375611],"domain_scores_gemma":[0.99884045,0.00009889091,0.000043361437,0.00089230173,0.000052015956,0.000072986564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014332047,0.00012235253,0.00009704204,0.00003156816,0.00013914946,0.00023883214,0.0010264949,0.00004525435,0.000057159014],"category_scores_gemma":[0.000020481875,0.00006227982,0.00004194389,0.0001731912,0.000034247867,0.00073906296,0.00049712684,0.00015444761,0.0001979917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046146756,0.0002503219,0.000013705231,0.000016674432,0.000011342392,0.0000017813935,0.0005903435,0.025885561,0.000103010316,0.89467865,0.01748413,0.060959887],"study_design_scores_gemma":[0.00012672704,0.000041814972,0.000270082,0.000008705944,0.0000016320931,0.000002667234,0.000008389287,0.96920764,0.000073307565,0.028674329,0.0014816838,0.00010303546],"about_ca_topic_score_codex":0.0002311634,"about_ca_topic_score_gemma":0.0000010033459,"teacher_disagreement_score":0.94332206,"about_ca_system_score_codex":0.000019509353,"about_ca_system_score_gemma":0.000029812736,"threshold_uncertainty_score":0.2544849},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03883625,0.00014832403,0.9504794,0.00030712568,0.002659872,0.002619969,0.0014226541,0.0004768816,0.0030495136],"genre_scores_gemma":[0.63708776,0.00092109054,0.34771633,0.0049585877,0.001157329,0.0012969553,0.00479278,0.00031321915,0.001755968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659234,0.000065895656,0.001058669,0.00074375595,0.0007428952,0.0007964529],"domain_scores_gemma":[0.9969873,0.00017328314,0.00074653886,0.0015650198,0.00028099795,0.0002468598],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00060280063,0.0007337149,0.0008049615,0.0004247374,0.0003682803,0.0011298029,0.0017333912,0.0006362362,0.000016208478],"category_scores_gemma":[0.000059020367,0.0006313621,0.0002789494,0.00021461376,0.000079433594,0.0016896932,0.0028356458,0.0011621425,0.00012883316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028786766,0.00447645,0.016914465,0.032212604,0.0025629955,0.00006114504,0.0667672,0.05124743,0.00023061049,0.20533538,0.2533746,0.36393845],"study_design_scores_gemma":[0.0026065332,0.00027008416,0.00040454775,0.00061594776,0.00004246262,0.000042514057,0.00007537465,0.97081333,0.00015573896,0.005995882,0.018138614,0.00083894725],"about_ca_topic_score_codex":0.000057754958,"about_ca_topic_score_gemma":0.000009957352,"teacher_disagreement_score":0.9195659,"about_ca_system_score_codex":0.00018252926,"about_ca_system_score_gemma":0.00012928691,"threshold_uncertainty_score":0.99990714},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00749947,0.000092310875,0.9865252,0.0007522916,0.002451909,0.00118778,0.0007743171,0.00016281972,0.0005539362],"genre_scores_gemma":[0.92528665,0.00008857075,0.06864964,0.00052482804,0.0010020908,0.000015371063,0.00065783056,0.000054460954,0.0037205745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995263,0.00033450342,0.0005572217,0.0027361582,0.00030900643,0.00080012414],"domain_scores_gemma":[0.9955804,0.00058124185,0.0007029024,0.0019601197,0.0007429484,0.0004324251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054995675,0.0007676323,0.00058048696,0.00046198058,0.00092105975,0.0003575534,0.0023306876,0.000735266,0.0003607013],"category_scores_gemma":[0.000111325055,0.00072598,0.00053548755,0.0005571756,0.00030672125,0.001034411,0.0014828681,0.0006905532,0.00014387352],"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":[0.00022261441,0.00022640535,0.0005290463,0.00010294584,0.00012795778,0.0000951035,0.00019967403,0.882693,0.0012597106,0.09524679,0.003233448,0.016063312],"study_design_scores_gemma":[0.0018537279,0.00015697391,0.00020594879,0.00028195378,0.0001141398,0.000011976951,0.000009618702,0.9284328,0.00038919266,0.057094835,0.01054563,0.00090320705],"about_ca_topic_score_codex":0.0000589312,"about_ca_topic_score_gemma":0.000062664316,"teacher_disagreement_score":0.9178755,"about_ca_system_score_codex":0.00047011193,"about_ca_system_score_gemma":0.001325735,"threshold_uncertainty_score":0.9995191},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018305773,0.00076657825,0.97356087,0.00008699923,0.0020873449,0.0009617548,0.00018792314,0.0004504081,0.0035923577],"genre_scores_gemma":[0.70888203,0.00012279372,0.28935146,0.000031293293,0.0001965934,0.000072160154,0.00014147388,0.00007850072,0.0011236627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973227,0.0001297289,0.00089417404,0.0006310335,0.0006801568,0.0003422529],"domain_scores_gemma":[0.9962112,0.00026777195,0.00097593176,0.002213524,0.00022326189,0.0001083331],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008409233,0.00039105426,0.000885911,0.0001844306,0.000096803655,0.0003212869,0.001968466,0.00027890093,0.000008403552],"category_scores_gemma":[0.00019850086,0.0003142018,0.00022316462,0.00023525444,0.000045210327,0.00025886454,0.0032728782,0.00058849616,0.00003954372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059983933,0.0016242629,0.00048939546,0.05809068,0.001913606,0.00024965507,0.086351745,0.07826904,0.029856216,0.6897371,0.047603298,0.005755028],"study_design_scores_gemma":[0.00022850808,0.000040154177,0.00001692778,0.002339225,0.00004656252,0.000027537992,0.0003888874,0.9835493,0.0022075472,0.010271533,0.00044306528,0.00044075798],"about_ca_topic_score_codex":0.00018602976,"about_ca_topic_score_gemma":0.0000012947172,"teacher_disagreement_score":0.90528023,"about_ca_system_score_codex":0.000100100944,"about_ca_system_score_gemma":0.0001928957,"threshold_uncertainty_score":0.999931},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054712687,0.000018659304,0.9417726,0.000098871875,0.00013034756,0.000064267704,0.0000043775835,0.000047268593,0.0031509427],"genre_scores_gemma":[0.9934632,0.000021427006,0.006119889,0.00010146054,0.000045188594,1.8852558e-7,0.0000015611015,0.000004258073,0.00024283619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999249,0.00007803038,0.00009580132,0.0003231798,0.00006843516,0.00018554585],"domain_scores_gemma":[0.9988657,0.0002504265,0.00009835132,0.00064069004,0.00008001814,0.000064772226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022600137,0.000096592965,0.00011448955,0.00005721483,0.00021819107,0.000050389648,0.0010175825,0.000039900413,0.0000075394514],"category_scores_gemma":[0.000037250902,0.00007288436,0.000053740867,0.0003697479,0.000084567466,0.0006437102,0.00046116713,0.000098341705,0.000019655457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005840436,0.00008467071,0.0010608252,0.0000069398075,0.000017449565,0.000013160455,0.00042573488,0.057521433,0.0009334677,0.9347018,0.0007023611,0.004526315],"study_design_scores_gemma":[0.00020002447,0.00005686187,0.00034329502,0.000012080187,0.000007938604,0.000001983981,0.0000435629,0.90494263,0.00090942055,0.09281159,0.000578298,0.000092332535],"about_ca_topic_score_codex":0.00006134081,"about_ca_topic_score_gemma":0.000012871909,"teacher_disagreement_score":0.9387505,"about_ca_system_score_codex":0.000026226098,"about_ca_system_score_gemma":0.00003681741,"threshold_uncertainty_score":0.2972138},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06142811,0.000022620425,0.93459135,0.000295889,0.0013524353,0.0009889512,0.00024509567,0.0002888756,0.0007866835],"genre_scores_gemma":[0.84396726,0.000009035416,0.15395047,0.0010144183,0.00041907182,0.0001646965,0.00030984083,0.000056559074,0.000108633496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970459,0.000038873895,0.00095440436,0.00043256272,0.00058709783,0.0009411699],"domain_scores_gemma":[0.99763423,0.00029437942,0.00049170566,0.0011007064,0.00022226789,0.00025672666],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009904244,0.0004227393,0.00047241728,0.00026475862,0.00064897607,0.00086703204,0.0016143259,0.00018811684,0.000006494549],"category_scores_gemma":[0.00009196045,0.00036999336,0.00027335194,0.00023752547,0.000052991385,0.001559658,0.0010335571,0.00035670554,0.000053929907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015180725,0.00075998635,0.0050891526,0.002197051,0.00032472963,0.0000074639283,0.026981896,0.021073185,0.0004276072,0.12821755,0.010062394,0.80470717],"study_design_scores_gemma":[0.0023470973,0.00019744624,0.0004447778,0.00030571915,0.000019770398,0.000024784385,0.0004113867,0.91249985,0.0008283866,0.0016763468,0.080674425,0.0005700057],"about_ca_topic_score_codex":0.000031686912,"about_ca_topic_score_gemma":0.0000063942916,"teacher_disagreement_score":0.8914267,"about_ca_system_score_codex":0.000117544645,"about_ca_system_score_gemma":0.000055157972,"threshold_uncertainty_score":0.9998752},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015806371,0.00014537564,0.9297532,0.008179523,0.0012519732,0.00082951254,0.000018841703,0.00045169823,0.04356351],"genre_scores_gemma":[0.77481085,0.00030574965,0.08250302,0.00088553596,0.0022021849,0.000037510443,0.000012196131,0.000104806386,0.13913815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949281,0.0009490328,0.0002886926,0.0011323307,0.001583202,0.0011186244],"domain_scores_gemma":[0.9954017,0.00084392016,0.000099952114,0.0022835874,0.0007330621,0.0006378271],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012516193,0.00028690865,0.00027712283,0.0007607369,0.0017838536,0.0005305895,0.0049597723,0.00011917813,0.00003435029],"category_scores_gemma":[0.00012097261,0.0001783821,0.00015585039,0.0022616228,0.00038407624,0.0013557998,0.0025465288,0.0005211733,0.00045571147],"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":[0.00034209515,0.0007095092,0.0014597629,0.00006485635,0.00028175858,0.00414797,0.0023823713,0.00013148504,0.23103702,0.19712685,0.16905293,0.3932634],"study_design_scores_gemma":[0.0011242089,0.0005186418,0.0035295407,0.00022402752,0.000011470639,0.00015586695,0.0002511352,0.005324697,0.032384217,0.001131393,0.95478183,0.00056295877],"about_ca_topic_score_codex":0.00045682673,"about_ca_topic_score_gemma":0.000024507055,"teacher_disagreement_score":0.84725016,"about_ca_system_score_codex":0.00048188563,"about_ca_system_score_gemma":0.0003773839,"threshold_uncertainty_score":0.9995157},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39804965,0.0001320586,0.59814787,0.00077597896,0.00056219,0.00049988646,0.000008794048,0.00009303798,0.0017305382],"genre_scores_gemma":[0.9884775,0.000028724633,0.011279211,0.00008848647,0.000044624936,0.000012221532,0.0000045943734,0.0000042094134,0.000060409617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986374,0.0000696213,0.00031787812,0.0005172344,0.00022273105,0.0002351732],"domain_scores_gemma":[0.9990624,0.00022506721,0.000070706126,0.0004990992,0.00006804581,0.00007466533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034103554,0.00013016796,0.0001611506,0.000083600404,0.00006463488,0.00015329814,0.0004955638,0.000050438626,0.00007388305],"category_scores_gemma":[0.00011749366,0.0001110756,0.000028038483,0.00032480666,0.00008898039,0.00046192604,0.00033657555,0.00014286547,0.000116470415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034280278,0.000120364595,0.0064709615,0.000034151813,0.0000054744305,0.000017753193,0.0020741688,0.020373717,0.00061152334,0.5514335,0.000030808245,0.41879326],"study_design_scores_gemma":[0.00003450096,0.00006894036,0.0036231317,0.000054771528,9.724118e-7,0.000005082089,0.00010043637,0.77382183,0.0013939189,0.21993166,0.0007846065,0.00018014002],"about_ca_topic_score_codex":0.0004697556,"about_ca_topic_score_gemma":0.0002487921,"teacher_disagreement_score":0.7534481,"about_ca_system_score_codex":0.000068450674,"about_ca_system_score_gemma":0.00005222094,"threshold_uncertainty_score":0.45295313},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074617425,0.000037126272,0.9827312,0.0054049185,0.0011317208,0.00031760262,0.00049285486,0.0012781112,0.0011446979],"genre_scores_gemma":[0.6258402,0.0010535138,0.3609371,0.0021041746,0.0007480059,0.00018804167,0.00043636633,0.00013628983,0.008556329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976724,0.00012304794,0.00027709783,0.00072166644,0.00069561694,0.00051020697],"domain_scores_gemma":[0.99770314,0.0004637458,0.000040375537,0.0014893656,0.00009924062,0.0002041614],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024015816,0.00027479677,0.00025680554,0.000493737,0.00048808142,0.0001728845,0.0016225098,0.00011198516,0.00013637533],"category_scores_gemma":[0.000025738103,0.00023560105,0.0001546706,0.0013280709,0.0000902915,0.00048564453,0.0000797575,0.0004829372,0.0012712685],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030214202,0.0006572943,0.000007593852,0.0000069884977,0.000056345147,0.000084148094,0.00053045456,0.010542195,0.00047702508,0.005625976,0.0010088099,0.98097295],"study_design_scores_gemma":[0.0027143836,0.0020850745,0.03313168,0.0003147599,0.000038347123,0.000058264442,0.0012191831,0.8880336,0.012817174,0.004179933,0.054181937,0.001225647],"about_ca_topic_score_codex":0.00015271037,"about_ca_topic_score_gemma":0.00014026651,"teacher_disagreement_score":0.9797473,"about_ca_system_score_codex":0.00007126211,"about_ca_system_score_gemma":0.000071098715,"threshold_uncertainty_score":0.99950635},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008541987,0.0012892875,0.98144597,0.00084215915,0.0047189635,0.00017201035,0.000010116382,0.00023952514,0.0027399866],"genre_scores_gemma":[0.56307447,0.000013467395,0.40097874,0.0003095352,0.00016275805,0.000022898757,0.000042788586,0.000026147676,0.035369165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983382,0.00013335724,0.00033403325,0.00061620434,0.00032969288,0.0002485156],"domain_scores_gemma":[0.99892193,0.00018041408,0.00016739496,0.00049589394,0.000113497015,0.00012086034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029226163,0.00023767562,0.00029984518,0.00013157511,0.00007810371,0.0002655304,0.0007858591,0.00008634036,0.00014668501],"category_scores_gemma":[0.00005614618,0.00016536581,0.000066483655,0.00015171,0.00015712982,0.0011438351,0.0009056887,0.000201902,0.0000910339],"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":[0.00016929168,0.00027273342,0.010709997,0.0002068684,0.00013806295,0.00006059971,0.05172239,0.00015907869,0.0011149277,0.59254503,0.1327602,0.21014084],"study_design_scores_gemma":[0.0004202418,0.00022472664,0.0019886382,0.000085725864,0.000009533656,0.00006246653,0.0001693699,0.07166263,0.0002604059,0.0115501685,0.91318107,0.00038501504],"about_ca_topic_score_codex":0.00032602105,"about_ca_topic_score_gemma":0.000018644905,"teacher_disagreement_score":0.7804209,"about_ca_system_score_codex":0.00031314974,"about_ca_system_score_gemma":0.00006651657,"threshold_uncertainty_score":0.6743422},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111697555,0.00017534333,0.8868242,0.0002812772,0.0006891752,0.00020285272,0.000015119716,0.000046550835,0.000067926456],"genre_scores_gemma":[0.19625491,0.00004901866,0.80347025,0.00010319691,0.00005044994,0.000047244583,0.000005472527,0.000006283576,0.000013186556],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986665,0.00011563532,0.00030031224,0.00042500647,0.00026154637,0.00023095512],"domain_scores_gemma":[0.9971451,0.0018306919,0.00023168135,0.00042567035,0.00026331565,0.00010355214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089397206,0.00012377699,0.000185296,0.00008049595,0.00010902864,0.000121342186,0.00034599126,0.00009730403,0.000010431975],"category_scores_gemma":[0.004481739,0.00011074139,0.000025916415,0.00026096465,0.00018370194,0.002734543,0.00024434252,0.0002801152,0.0000022879713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003400828,0.00053451787,0.021203835,0.000050960298,0.000015068236,0.000059777525,0.008160448,0.0000081355565,0.005809449,0.011915168,0.0003295981,0.95157295],"study_design_scores_gemma":[0.010196981,0.0026221238,0.5381816,0.00048241534,0.000091395326,0.0047926903,0.013262011,0.3279763,0.045154296,0.016050326,0.038074646,0.0031152265],"about_ca_topic_score_codex":0.00096908014,"about_ca_topic_score_gemma":0.00018955728,"teacher_disagreement_score":0.9484577,"about_ca_system_score_codex":0.000010280616,"about_ca_system_score_gemma":0.0001517033,"threshold_uncertainty_score":0.53653836},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010688326,0.00002777498,0.97462755,0.00022742835,0.00056906027,0.0002311647,0.000015053971,0.00016596973,0.013447695],"genre_scores_gemma":[0.6337588,0.0000278324,0.35543147,0.0014609932,0.00016226966,0.000014112155,0.000046174275,0.000020255235,0.00907812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991921,0.0000115253715,0.00011602492,0.00029208415,0.00016370905,0.00022452389],"domain_scores_gemma":[0.9992429,0.00013612,0.000048512986,0.00043472365,0.000070992966,0.000066751985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014917171,0.000093466566,0.00011481152,0.00005821113,0.00008167597,0.0001323755,0.00062909187,0.000044598113,0.000106725645],"category_scores_gemma":[0.000009098384,0.00007705531,0.000041152794,0.00013716017,0.000011731014,0.0008570251,0.00030849586,0.000057955513,0.00020692834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039764098,0.00009245518,0.0025187868,0.000059058253,0.000037081525,0.000009070865,0.00047469014,0.00027949899,0.007929923,0.8344213,0.06703311,0.08710529],"study_design_scores_gemma":[0.0011641487,0.00018099073,0.00095256086,0.000041843774,0.000004667565,0.000007792295,0.00009166522,0.65678537,0.0027791774,0.002105372,0.33558813,0.00029831016],"about_ca_topic_score_codex":0.000042289375,"about_ca_topic_score_gemma":0.000004461226,"teacher_disagreement_score":0.8323159,"about_ca_system_score_codex":0.000027651568,"about_ca_system_score_gemma":0.000048200855,"threshold_uncertainty_score":0.31422243},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022668168,0.000014300539,0.9702185,0.000052306095,0.00032238686,0.00007998007,0.0000015069692,0.00013914918,0.0065037385],"genre_scores_gemma":[0.93953145,0.000002521987,0.059438374,0.00014928101,0.000026427088,0.0000031385493,0.000001200185,0.0000022029099,0.00084540347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948204,0.000015102442,0.00006519723,0.00021133533,0.00012130005,0.000105028186],"domain_scores_gemma":[0.99953276,0.00002024452,0.000025196558,0.00035124543,0.00003021179,0.000040338145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000066572415,0.00005147216,0.000051273833,0.000030432573,0.000041186297,0.000054498345,0.00033183556,0.000022386532,0.000091358255],"category_scores_gemma":[0.000003524784,0.000039158185,0.000018370856,0.00013298944,0.000007574918,0.00070622924,0.00016188614,0.00005296464,0.00063186855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011421397,0.000068222966,0.00003201066,0.0000026281045,0.000004726227,0.000007371346,0.00010322044,0.000054737862,0.061396934,0.031419314,0.0004801292,0.9064193],"study_design_scores_gemma":[0.00042695363,0.00022739926,0.00011712035,0.000006805958,7.510039e-7,0.000012678824,0.000016033357,0.95853144,0.031035546,0.0019117328,0.007611042,0.00010248416],"about_ca_topic_score_codex":0.000048617912,"about_ca_topic_score_gemma":0.000002733957,"teacher_disagreement_score":0.9584767,"about_ca_system_score_codex":0.00001690667,"about_ca_system_score_gemma":0.000016715689,"threshold_uncertainty_score":0.81216025},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013120109,0.00006533823,0.9836614,0.000078673285,0.0013515482,0.0003510076,0.00016026197,0.00006780316,0.0011438477],"genre_scores_gemma":[0.81106466,0.0000054125394,0.18822639,0.00001190145,0.00009735705,0.000025294508,0.00009678582,0.0000054585325,0.0004667312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916947,0.000019551373,0.0002237841,0.00024308982,0.00017199155,0.00017209614],"domain_scores_gemma":[0.9992073,0.00008764707,0.000104988874,0.00039470178,0.00014938868,0.000055966022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012077064,0.00008507423,0.0001618672,0.000094719944,0.000077595774,0.00008484559,0.0003891184,0.000049249833,0.000017312908],"category_scores_gemma":[0.000017996052,0.00006807004,0.000058904243,0.00039000637,0.000026110216,0.00047225878,0.00016517908,0.000049628692,0.000034717526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016255066,0.00012569908,0.0027443864,0.00009663012,0.000039787188,9.007392e-7,0.000060993912,0.0014992177,0.0011743471,0.9392146,0.006298985,0.04872823],"study_design_scores_gemma":[0.00076583255,0.0002305569,0.0017096092,0.000048997823,0.000010304029,0.00005049526,0.00018662888,0.9833247,0.0034101328,0.00036666886,0.009684673,0.00021137224],"about_ca_topic_score_codex":0.00008290292,"about_ca_topic_score_gemma":3.0819814e-7,"teacher_disagreement_score":0.98182553,"about_ca_system_score_codex":0.000026011867,"about_ca_system_score_gemma":0.00004345518,"threshold_uncertainty_score":0.27758157},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068843705,0.00018592163,0.99033344,0.00035817514,0.00037654897,0.00045036295,0.000014980122,0.000051291045,0.0013448906],"genre_scores_gemma":[0.51513755,0.000034731667,0.48249882,0.0003323316,0.0000752692,0.000048848786,0.0000040448754,0.0000096364465,0.0018587627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991464,0.000010479476,0.00016581647,0.00027164942,0.00025384224,0.0001518143],"domain_scores_gemma":[0.99822426,0.00044596102,0.00007983714,0.0010938981,0.00012177895,0.00003426276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025314858,0.000084571984,0.00011905979,0.000028220398,0.00008397486,0.00006296886,0.001761475,0.000030933494,0.00001771529],"category_scores_gemma":[0.00008289951,0.000044293825,0.000052962045,0.0001408541,0.000025909383,0.00038149004,0.0007248395,0.000049184764,0.000018630144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017377124,0.00030992148,0.0009869178,0.00024372799,0.00005647268,0.000002031801,0.0013715676,0.0042190338,0.0056127785,0.65564895,0.070786566,0.2605883],"study_design_scores_gemma":[0.0009235273,0.00019422063,0.0012658938,0.00010402035,0.0000058095225,0.000008360842,0.00007211089,0.9177778,0.006536303,0.06845011,0.004517592,0.00014429395],"about_ca_topic_score_codex":0.00003342333,"about_ca_topic_score_gemma":0.000014074617,"teacher_disagreement_score":0.9135587,"about_ca_system_score_codex":0.0000070232095,"about_ca_system_score_gemma":0.00004249004,"threshold_uncertainty_score":0.3273288},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6929343,0.00017672226,0.3050425,0.00007134594,0.0007280456,0.00024213098,0.000049362454,0.00016503491,0.000590566],"genre_scores_gemma":[0.9902922,0.0002554048,0.008488304,0.000072291965,0.000063697094,7.376635e-7,0.000026672855,0.0000137747775,0.0007868993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998408,0.00007221906,0.000104880695,0.0010499777,0.0001308016,0.00023409595],"domain_scores_gemma":[0.998557,0.00011071318,0.0001641663,0.00095491833,0.000079161335,0.0001340457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008391533,0.00029573962,0.000282564,0.00014469973,0.00015563118,0.00008049605,0.0006955257,0.0001588612,0.000012697207],"category_scores_gemma":[0.000007579178,0.0002418041,0.000059770013,0.00018665045,0.00012120466,0.00043312853,0.0014508181,0.00036476282,0.000036842794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091071584,0.00080976036,0.07556206,0.00042443734,0.0004292059,0.00214153,0.0013976571,0.24206729,0.000284167,0.660486,0.005607415,0.009879789],"study_design_scores_gemma":[0.0016338128,0.0006551016,0.058081254,0.00084839674,0.00006542538,0.000018503806,0.000078990764,0.9209538,0.00032424676,0.0049542515,0.011164165,0.0012220639],"about_ca_topic_score_codex":0.00014611082,"about_ca_topic_score_gemma":0.000031361156,"teacher_disagreement_score":0.6788865,"about_ca_system_score_codex":0.000074972995,"about_ca_system_score_gemma":0.000142176,"threshold_uncertainty_score":0.9860485},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3956515,0.00024074201,0.59778273,0.000295948,0.0005213167,0.000829438,0.00006926216,0.00035310167,0.0042559574],"genre_scores_gemma":[0.9349178,0.0001260575,0.06362992,0.00047337357,0.000048516344,0.000031576168,0.00026032646,0.000026633934,0.00048577928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829155,0.000056709214,0.0006173642,0.00024787843,0.0003404154,0.00044605558],"domain_scores_gemma":[0.99814975,0.00020996868,0.0003279969,0.0010137137,0.00014955954,0.00014903057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066591665,0.00024242325,0.00029184457,0.00015459728,0.00052719604,0.0006878875,0.001291236,0.00012511341,0.000020140213],"category_scores_gemma":[0.000046069654,0.00021898234,0.0000809322,0.00019730243,0.000048658745,0.002723784,0.0012313065,0.00055125577,0.00013219516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007194582,0.0005592306,0.056670006,0.0020475537,0.00037103676,0.000007780313,0.07400715,0.003246212,0.00088805595,0.3978469,0.0071120667,0.45717204],"study_design_scores_gemma":[0.005245824,0.00041420315,0.00910229,0.00074173976,0.000032609743,0.00016043318,0.00435998,0.6235982,0.0006767676,0.008056708,0.34625304,0.0013581561],"about_ca_topic_score_codex":0.000030024561,"about_ca_topic_score_gemma":0.0000029646205,"teacher_disagreement_score":0.620352,"about_ca_system_score_codex":0.00004965766,"about_ca_system_score_gemma":0.000041618034,"threshold_uncertainty_score":0.89298403},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008541804,0.00007023732,0.46105903,0.0001816511,0.00037154826,0.00072877103,0.00012377302,0.00033222392,0.5370473],"genre_scores_gemma":[0.27276057,0.0007583909,0.25624663,0.00027422133,0.0013507697,0.000009866038,0.0015931398,0.00016846115,0.46683794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965684,0.00009500242,0.00045128269,0.00044910115,0.00201415,0.0004220946],"domain_scores_gemma":[0.99617213,0.00015208423,0.00051347533,0.0015576018,0.001359392,0.00024530978],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015679379,0.00028090793,0.0005321963,0.001099123,0.0006769861,0.00017190143,0.0019015219,0.00039173043,0.00007253097],"category_scores_gemma":[0.00006649886,0.0002741552,0.00019700859,0.00032048582,0.0003829044,0.00398789,0.0014292464,0.0007594556,0.001057779],"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":[0.00027643793,0.000019278312,0.000035610017,0.001690013,0.00016728938,0.00014040475,0.0018260969,0.00074480043,0.000010060702,0.9350637,0.04007673,0.019949546],"study_design_scores_gemma":[0.001245621,0.0003843623,0.00010260072,0.0026270396,0.000025085656,0.000060657832,0.0011539477,0.07292568,0.000012939706,0.00014038639,0.92089057,0.00043109286],"about_ca_topic_score_codex":0.00044088726,"about_ca_topic_score_gemma":0.00004179835,"teacher_disagreement_score":0.93492335,"about_ca_system_score_codex":0.0004866003,"about_ca_system_score_gemma":0.0012748487,"threshold_uncertainty_score":0.9999711},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0870505,0.000087030865,0.9118011,0.00005547863,0.00015377514,0.0007160554,0.000027124028,0.000048576072,0.00006033621],"genre_scores_gemma":[0.40135384,0.000002647938,0.5983528,0.00007752229,0.000019468462,0.000017823018,0.00014894943,0.000006788514,0.000020200398],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986877,0.00014264918,0.00018303643,0.0004823927,0.0003696511,0.00013459622],"domain_scores_gemma":[0.9981132,0.00015915955,0.00010201338,0.0013203573,0.00023350403,0.00007176159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012501668,0.0000978627,0.00013785665,0.00005984175,0.00007118388,0.00008315033,0.0009935123,0.000049944916,0.00005515639],"category_scores_gemma":[0.000031999196,0.00007343048,0.0000144821815,0.00009255764,0.000012130152,0.0015007688,0.00045407438,0.000038084516,0.0000060697726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013366983,0.00023228649,0.00047136712,0.00009948238,0.000022638573,8.051665e-7,0.00014510714,0.015831148,0.03150319,0.0011672516,0.003753982,0.94663906],"study_design_scores_gemma":[0.0010926863,0.00014529299,0.0010461935,0.000035738143,0.000012924785,8.994768e-7,0.000006461019,0.9644746,0.03160594,0.0007915957,0.00068307057,0.000104565006],"about_ca_topic_score_codex":0.00001677022,"about_ca_topic_score_gemma":0.0000023573516,"teacher_disagreement_score":0.9486435,"about_ca_system_score_codex":0.000011728785,"about_ca_system_score_gemma":0.00014181795,"threshold_uncertainty_score":0.2994408},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6907312,0.00013375642,0.30827928,0.000058819376,0.0001948813,0.00010848515,0.0000077506365,0.00003653842,0.00044927155],"genre_scores_gemma":[0.6539,0.000011794552,0.34585458,0.000049801987,0.000012296625,6.59348e-7,0.0000029915595,0.0000039454303,0.00016391026],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991809,0.00003584437,0.00016153618,0.0002705762,0.00021546295,0.00013569274],"domain_scores_gemma":[0.99932843,0.00010730552,0.000079366815,0.00034749386,0.00007070408,0.00006666806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000100905214,0.00009154988,0.00015891639,0.0000533978,0.00006484622,0.00003374383,0.00025953096,0.000042488125,0.00006403909],"category_scores_gemma":[0.0000071901904,0.0000664309,0.000026175865,0.00009782552,0.00004423265,0.00045713416,0.0007098815,0.00006195244,0.000013010761],"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":[0.00006255119,0.00040760264,0.028051585,0.00016226663,0.000029755403,0.00002180398,0.00049422885,0.0012311027,0.9085945,0.031070055,0.0074430085,0.022431532],"study_design_scores_gemma":[0.0009944601,0.00008789557,0.018365955,0.00016453236,0.000005029409,0.00003425915,0.00006906541,0.9022537,0.0758117,0.0008737114,0.0011235449,0.00021613558],"about_ca_topic_score_codex":0.00010979342,"about_ca_topic_score_gemma":9.497061e-7,"teacher_disagreement_score":0.9010226,"about_ca_system_score_codex":0.000008810059,"about_ca_system_score_gemma":0.00003296011,"threshold_uncertainty_score":0.27089733},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22869503,0.000744536,0.76962054,0.00008586724,0.00036943937,0.00004273479,0.000004958139,0.000019593606,0.0004172808],"genre_scores_gemma":[0.9488093,0.000044419845,0.051019173,0.000074266085,0.000022508822,0.0000020059813,0.000022131166,0.000001925779,0.0000042531474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935114,0.000056253928,0.000168321,0.00019785004,0.00016034633,0.00006610892],"domain_scores_gemma":[0.9994631,0.000100805744,0.00012655614,0.000070835275,0.00020075831,0.000037991962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007261815,0.00005990005,0.000076530705,0.000041413747,0.0001709717,0.00007938264,0.000050274033,0.000027935737,0.0000057013067],"category_scores_gemma":[0.00006009448,0.000061362734,0.000012254051,0.00019431453,0.0000443352,0.0004944036,0.0000802151,0.000053864787,0.0000018351158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030041318,0.00037827197,0.0015790102,0.0001181983,0.000038619968,0.000023206749,0.009650886,0.044668853,0.003956962,0.1658521,0.00030916987,0.7733947],"study_design_scores_gemma":[0.00019420366,0.000028727865,0.0043481924,0.000048149763,0.000009187054,0.00015947492,0.0004906061,0.9922983,0.00016268478,0.0016192682,0.00054574973,0.000095457006],"about_ca_topic_score_codex":0.000025463312,"about_ca_topic_score_gemma":2.705784e-7,"teacher_disagreement_score":0.94762945,"about_ca_system_score_codex":0.000010293997,"about_ca_system_score_gemma":0.000049665086,"threshold_uncertainty_score":0.25022998},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6830275,0.0013440836,0.2916616,0.0009105923,0.012898015,0.0018880296,0.000053656982,0.00058934506,0.0076271794],"genre_scores_gemma":[0.56447893,0.00013764408,0.43455163,0.000013606135,0.00017559025,0.000059382688,0.000040597628,0.000036196645,0.00050644093],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692255,0.000064541025,0.0010624884,0.0010504986,0.0005378018,0.00036209298],"domain_scores_gemma":[0.99571216,0.000037129492,0.001152928,0.0027415694,0.00028805766,0.00006814492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000371263,0.00041659383,0.0010108642,0.0010681885,0.000087954075,0.00005911072,0.0029619625,0.0009872727,0.0000058317883],"category_scores_gemma":[0.00008669918,0.00040002482,0.00019348365,0.0007986918,0.0005275108,0.00036758158,0.0043586385,0.0010263762,0.000034571956],"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":[0.00030155186,0.002507762,0.010321339,0.0032517428,0.0006543064,0.0008526593,0.0009316215,0.4642273,0.3254131,0.084531695,0.00408167,0.10292524],"study_design_scores_gemma":[0.0016633564,0.0003773384,0.0014585898,0.0042433175,0.000091475486,0.00037071688,0.000070497365,0.48703864,0.4811069,0.0029778522,0.019362139,0.0012391709],"about_ca_topic_score_codex":0.00031453787,"about_ca_topic_score_gemma":0.0000035017802,"teacher_disagreement_score":0.15569378,"about_ca_system_score_codex":0.00018814449,"about_ca_system_score_gemma":0.0006241664,"threshold_uncertainty_score":0.99984515},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016695714,0.00037980292,0.9776234,0.0013170493,0.0013137403,0.0008272907,0.0000052863925,0.000072168965,0.016791705],"genre_scores_gemma":[0.80430293,0.00024249658,0.18910733,0.0027696488,0.00046827793,0.00021120103,0.000069697024,0.00001521279,0.0028131756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994094,0.000019705009,0.00007439399,0.00016523531,0.00022687187,0.00010441725],"domain_scores_gemma":[0.99912107,0.0002542883,0.000028527304,0.0004973356,0.00007936262,0.00001940643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004022403,0.000044869106,0.000043168046,0.000013136631,0.000083436484,0.00022393971,0.00053192204,0.000019047138,0.00015850042],"category_scores_gemma":[0.000036467693,0.00002393898,0.000029777846,0.000070660746,0.0000055775304,0.0006837207,0.0001728383,0.000030850137,0.00015696094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016908004,0.0000096871345,0.000017773424,0.0000020962825,0.0000034083816,3.128647e-8,0.00005134768,0.00009952502,0.00015269742,0.1029739,0.004278559,0.89240927],"study_design_scores_gemma":[0.00024448067,0.000026937483,0.0011888909,0.0000045806732,0.0000034424804,8.9076997e-7,0.000079379126,0.7060381,0.00033587113,0.0015600405,0.29046315,0.000054231517],"about_ca_topic_score_codex":0.000010992925,"about_ca_topic_score_gemma":0.0000013141815,"teacher_disagreement_score":0.892355,"about_ca_system_score_codex":0.000013626838,"about_ca_system_score_gemma":0.000034532593,"threshold_uncertainty_score":0.21594559},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025965167,0.00013146953,0.96167576,0.002945682,0.0010059503,0.00051116874,0.00001174031,0.00021141613,0.0075416532],"genre_scores_gemma":[0.9314102,0.000036570524,0.065483,0.0021474394,0.00018020583,0.000032977747,0.000014905177,0.000012522351,0.00068218156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981167,0.00016173354,0.00028272835,0.0006989538,0.0002779551,0.00046193687],"domain_scores_gemma":[0.99793214,0.00024209186,0.00013158577,0.0013779403,0.00016569308,0.00015055537],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042711402,0.00021504384,0.00028062286,0.00009908523,0.00019470454,0.00024280346,0.0023613428,0.00008573389,0.00010549156],"category_scores_gemma":[0.00005907286,0.00014977084,0.00005882145,0.00042579827,0.00006414927,0.0003949935,0.0010129383,0.00034554015,0.0010094354],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056957546,0.0001869292,0.012427483,0.00007463849,0.00012143134,0.000091797854,0.002190315,0.0006006654,0.016728213,0.4654878,0.017977623,0.48405614],"study_design_scores_gemma":[0.0025470033,0.0014722892,0.12014034,0.00047893525,0.00004117515,0.0004328317,0.00019084348,0.3805847,0.012413844,0.012597572,0.46703854,0.0020619503],"about_ca_topic_score_codex":0.00007395827,"about_ca_topic_score_gemma":0.0000056841945,"teacher_disagreement_score":0.90544504,"about_ca_system_score_codex":0.000030449808,"about_ca_system_score_gemma":0.00011316912,"threshold_uncertainty_score":0.9997684},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02165639,0.00008161647,0.9720019,0.00042996596,0.00088135037,0.00015372083,0.00000883384,0.000266952,0.004519276],"genre_scores_gemma":[0.80306387,0.000010131924,0.19613525,0.00021143125,0.00027601485,0.000017644557,0.0000106898915,0.000010081087,0.00026490787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980493,0.00010972533,0.00035724274,0.00068900513,0.0002584142,0.00053627964],"domain_scores_gemma":[0.9983546,0.00010461169,0.00017493805,0.00086174125,0.00035233775,0.0001517635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024243024,0.00023118943,0.00030343793,0.00014006138,0.00028094242,0.00022770755,0.0014692299,0.00014811296,0.00014259166],"category_scores_gemma":[0.000070796756,0.00021023597,0.000041167088,0.0003997987,0.00022954235,0.0006584206,0.0011373765,0.00032252166,0.0003523346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016254458,0.00014290267,0.00606943,0.00001336674,0.000046190577,0.000041381867,0.0012154975,0.000014827568,0.0012913964,0.08042248,0.002050957,0.9086753],"study_design_scores_gemma":[0.0016065399,0.00085743895,0.02460039,0.00011492818,0.000022383796,0.00013510622,0.00019038994,0.89538,0.01197237,0.007249975,0.05689171,0.0009787338],"about_ca_topic_score_codex":0.00008475011,"about_ca_topic_score_gemma":0.000025513633,"teacher_disagreement_score":0.9076966,"about_ca_system_score_codex":0.000030452524,"about_ca_system_score_gemma":0.00015775312,"threshold_uncertainty_score":0.8573174},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007301511,0.000021559126,0.98751014,0.00005741185,0.00028893875,0.00024993572,0.000009746737,0.0000938268,0.0044669164],"genre_scores_gemma":[0.9213485,0.0000026380985,0.07809882,0.00015646876,0.00014168803,0.00002201847,0.000028431377,0.0000063890816,0.00019504243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865574,0.000009325129,0.0001432888,0.0006424436,0.00036632433,0.00018286439],"domain_scores_gemma":[0.99635994,0.00003383271,0.000090642105,0.0033341732,0.00008213073,0.00009928387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005868879,0.00006692327,0.00007708897,0.000038424954,0.00014462357,0.00017574606,0.0016081393,0.000010581114,0.000006139435],"category_scores_gemma":[0.000022540498,0.000058499518,0.000012841689,0.00062070444,0.000032053635,0.0016611542,0.0026949565,0.00006103641,0.0001348827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.815146e-7,0.000076730335,0.001003958,0.0000093141725,0.000005006968,0.000018163293,0.00013507965,0.0006103337,0.011674408,0.53103006,0.0007920976,0.45464385],"study_design_scores_gemma":[0.00017963572,0.0000669547,0.009514557,0.000092989525,0.000012918643,0.00016259185,0.00005021215,0.13748379,0.031951483,0.50196266,0.31765518,0.0008670153],"about_ca_topic_score_codex":0.000009450228,"about_ca_topic_score_gemma":2.5208533e-7,"teacher_disagreement_score":0.914047,"about_ca_system_score_codex":0.000021020402,"about_ca_system_score_gemma":0.00014583282,"threshold_uncertainty_score":0.33590707},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019089406,0.00095005607,0.9914519,0.0017790365,0.0026732348,0.0014939699,0.00004124826,0.00018637019,0.0014050726],"genre_scores_gemma":[0.021859376,0.0003301218,0.972511,0.0023715694,0.0013605142,0.000101272,0.00008484463,0.00009004111,0.0012912671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953604,0.00004726358,0.00064294593,0.0019348098,0.0011924846,0.0008220968],"domain_scores_gemma":[0.9947847,0.0014159564,0.0004988789,0.0027838747,0.00036241207,0.0001541686],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015356762,0.0006264951,0.0005941737,0.00040330758,0.0006999396,0.001281303,0.005540704,0.00036749092,0.000019185078],"category_scores_gemma":[0.0000657895,0.00044171204,0.00020170747,0.00050212286,0.0007554355,0.001197042,0.0018562628,0.0009003403,0.000056714995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014074795,0.000039095765,0.000030086589,0.000086790125,0.000017781733,0.00003853934,0.0003278428,0.0125735635,0.000113993716,0.0645124,0.0001745491,0.9220713],"study_design_scores_gemma":[0.0003679293,0.00030617422,0.00017026487,0.00058202544,0.000015453954,0.00011376688,2.3357745e-7,0.7668657,0.000674535,0.21812956,0.0120789185,0.00069547474],"about_ca_topic_score_codex":0.000079205915,"about_ca_topic_score_gemma":0.00013357571,"teacher_disagreement_score":0.9213758,"about_ca_system_score_codex":0.0003545298,"about_ca_system_score_gemma":0.0007917273,"threshold_uncertainty_score":0.9998398},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007760567,0.00013032662,0.98472977,0.005213722,0.00022939239,0.0009800141,0.000025864218,0.0005701866,0.00036016732],"genre_scores_gemma":[0.1323848,0.000006021136,0.8633466,0.003093684,0.0008166477,0.00006514811,0.00010294085,0.00003907574,0.00014513382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961796,0.00011385484,0.00051194354,0.0013393974,0.0007490722,0.0011061727],"domain_scores_gemma":[0.99681324,0.00036980573,0.00023057073,0.0019920277,0.00017963669,0.00041474693],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026640992,0.000611925,0.0005623343,0.0003329172,0.00048377903,0.0006052965,0.0035676693,0.00013539643,0.000012520768],"category_scores_gemma":[0.000041567324,0.00042282674,0.00020217961,0.0005902563,0.00012642758,0.00058490137,0.00092509156,0.0005942735,0.000019612728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013667213,0.00012975294,0.000116269235,0.000034448338,0.000027155937,0.000049563245,0.0012094437,0.006941472,0.0003056061,0.00073701655,0.002943644,0.98736894],"study_design_scores_gemma":[0.008057834,0.010345873,0.011300181,0.0006123481,0.000085196625,0.0019598834,0.00004483999,0.71212643,0.0021218779,0.08187243,0.16832054,0.0031525618],"about_ca_topic_score_codex":0.000038866423,"about_ca_topic_score_gemma":0.000039133283,"teacher_disagreement_score":0.9842164,"about_ca_system_score_codex":0.000050540122,"about_ca_system_score_gemma":0.0002719778,"threshold_uncertainty_score":0.9998224},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4016393,0.000047232174,0.58926153,0.00064435194,0.0008765637,0.00028621193,0.000010634779,0.0002396908,0.0069944444],"genre_scores_gemma":[0.67075753,0.0000020977445,0.32405624,0.0027961787,0.00011245138,0.000003756171,0.000006622702,0.000008891097,0.0022562458],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989774,0.000022733657,0.0001324477,0.0004025462,0.00023212461,0.00023274224],"domain_scores_gemma":[0.99900466,0.000019891588,0.000033390075,0.0007630102,0.000054493295,0.00012455498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009634816,0.00011334905,0.00012649836,0.00006604582,0.00006547652,0.00019588573,0.00086084916,0.00004504993,0.00043143798],"category_scores_gemma":[0.000006412257,0.00008300433,0.000027992022,0.00025175625,0.0000049338178,0.0006176001,0.00065648166,0.000080069934,0.00048896676],"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":[0.000011051037,0.000019958989,0.00030272658,0.000029687093,0.000025492727,0.000053945267,0.0014410525,0.004906819,0.8826827,0.021754012,0.017603328,0.07116926],"study_design_scores_gemma":[0.0006346247,0.00019431963,0.001744396,0.000055714725,0.0000051705733,0.00009446397,0.00013390716,0.27952805,0.69433564,0.004165529,0.01835494,0.0007532553],"about_ca_topic_score_codex":0.000085061256,"about_ca_topic_score_gemma":0.000007286902,"teacher_disagreement_score":0.27462125,"about_ca_system_score_codex":0.000042839532,"about_ca_system_score_gemma":0.00006633114,"threshold_uncertainty_score":0.62848413},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007003622,0.00025847115,0.98802954,0.00065568165,0.0008244168,0.0002554464,0.00017729765,0.00022474566,0.00257077],"genre_scores_gemma":[0.9536348,0.00048191633,0.044826057,0.0004887588,0.00015188497,3.6618732e-7,0.00027873492,0.000015979618,0.00012151892],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975448,0.000220854,0.00019510463,0.0016364487,0.00013228781,0.0002705067],"domain_scores_gemma":[0.9961647,0.00018472406,0.00026113947,0.0031505837,0.00007964867,0.00015923186],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00025922476,0.00026152644,0.00028647872,0.00020403764,0.000085596315,0.0002046393,0.0054742643,0.00022306126,0.000014848349],"category_scores_gemma":[0.00018187675,0.00027882322,0.000056740166,0.00065203954,0.000050303704,0.0016940762,0.016049162,0.0008813806,0.000048514237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001497379,0.00030718066,0.002550568,0.00025882642,0.00018730455,0.0079087075,0.00083405647,0.072665416,0.00004836487,0.8808985,0.024405489,0.009785877],"study_design_scores_gemma":[0.0003699321,0.000028685927,0.0018148685,0.000100583646,0.000041615138,0.000010491906,0.00010678128,0.9268715,0.00001237255,0.053789977,0.016422337,0.0004308761],"about_ca_topic_score_codex":0.0006583952,"about_ca_topic_score_gemma":0.000029983405,"teacher_disagreement_score":0.94663113,"about_ca_system_score_codex":0.000095694944,"about_ca_system_score_gemma":0.0003071343,"threshold_uncertainty_score":0.9999664},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102522045,0.00010497154,0.8954549,0.00006912483,0.00103658,0.00013690928,0.000042289503,0.0005604126,0.00007278329],"genre_scores_gemma":[0.9380497,2.8609722e-7,0.061570466,0.00014078019,0.00017188932,0.000010844572,0.000031995067,0.000012363897,0.000011732007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792486,0.00015062954,0.00033524752,0.0006460417,0.00053900614,0.00040420724],"domain_scores_gemma":[0.99820477,0.00068924064,0.00020843474,0.0007188094,0.00006150505,0.0001172303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037100172,0.00018440685,0.00021707633,0.00010003492,0.0009588348,0.0002255293,0.0016580735,0.000033484135,0.000016236403],"category_scores_gemma":[0.00011625517,0.00019278853,0.000055718046,0.00045604812,0.000026841819,0.00039911427,0.003761405,0.0003995296,0.00003323702],"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":[0.00001878053,0.00014248032,0.0067464355,0.000053818265,0.00005003414,0.00020937026,0.00456851,0.63020843,0.005639495,0.019504229,0.0004884375,0.33236998],"study_design_scores_gemma":[0.00030877255,0.00003967704,0.0010396537,0.00007747439,0.000003282716,0.0000214628,0.00014552684,0.9968739,0.00015537217,0.0005469891,0.0005499336,0.00023791319],"about_ca_topic_score_codex":0.0004284713,"about_ca_topic_score_gemma":0.000004614304,"teacher_disagreement_score":0.8355276,"about_ca_system_score_codex":0.00018758645,"about_ca_system_score_gemma":0.0001208484,"threshold_uncertainty_score":0.7861688},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1507793,0.0012869498,0.8218467,0.004003727,0.0012319435,0.0007669418,0.00021843551,0.00059739087,0.019268557],"genre_scores_gemma":[0.9125265,0.044212732,0.037210975,0.00037358038,0.00006429568,4.5438767e-7,0.00005576755,0.000023389965,0.0055323336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772763,0.0001065629,0.00016679415,0.00094467413,0.00049984164,0.000554515],"domain_scores_gemma":[0.997778,0.000057569927,0.00037476295,0.0012582152,0.00013390431,0.0003975555],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00021128953,0.0003212808,0.0002927139,0.007819965,0.001770728,0.00025951688,0.0036555163,0.00031752777,0.00003832292],"category_scores_gemma":[0.000009251236,0.00036193168,0.00017555851,0.0048014293,0.00048701625,0.0036079795,0.0027911759,0.0007107611,0.000021432083],"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":[0.0008384642,0.0011940075,0.23023978,0.00051766017,0.0016005835,0.0056976443,0.0051639103,0.00032586584,0.01714828,0.48776832,0.11570865,0.13379684],"study_design_scores_gemma":[0.0038753524,0.00027053023,0.08559069,0.00043680874,0.0002479205,0.00005955245,0.001119353,0.035622247,0.00034530644,0.0026831303,0.8680179,0.0017311784],"about_ca_topic_score_codex":0.00047976308,"about_ca_topic_score_gemma":0.0000259517,"teacher_disagreement_score":0.7846358,"about_ca_system_score_codex":0.00011457937,"about_ca_system_score_gemma":0.00007634644,"threshold_uncertainty_score":0.9998833},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024912355,0.000012009725,0.97113776,0.0005572988,0.00019863571,0.0006580519,0.00022723539,0.000052033025,0.0022445945],"genre_scores_gemma":[0.94874924,0.000007647116,0.051122688,0.00002384477,0.00004142321,0.0000018022271,0.000043904038,0.0000025226575,0.000006932105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841225,0.00009135884,0.00034367037,0.00018760168,0.0007386652,0.00022642776],"domain_scores_gemma":[0.9983291,0.00009873623,0.00031407995,0.00036933954,0.0007313299,0.00015741914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000774647,0.00009239402,0.00024744376,0.00029057087,0.0003695306,0.00005384638,0.0008401344,0.00007935506,0.000008711897],"category_scores_gemma":[0.00011719327,0.00010019475,0.00007889176,0.00055587577,0.00025699535,0.0008021179,0.00057667267,0.00012805412,0.00003180974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017224677,0.00018963375,0.00061180134,0.0045159403,0.00023413634,0.00001977957,0.036303654,0.05588229,0.010110222,0.6643577,0.014980584,0.21107176],"study_design_scores_gemma":[0.0016937249,0.00027615041,0.0005044777,0.00015595171,0.0000074468153,0.000008771123,0.0077677523,0.91786635,0.00061652623,0.00004087187,0.0709364,0.00012558268],"about_ca_topic_score_codex":0.00030897034,"about_ca_topic_score_gemma":0.0000043773834,"teacher_disagreement_score":0.9238369,"about_ca_system_score_codex":0.00020496886,"about_ca_system_score_gemma":0.0003490567,"threshold_uncertainty_score":0.40858236},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23194553,0.000045307657,0.7613164,0.000104145314,0.00017570611,0.00024902713,0.0000061746055,0.00019335441,0.0059643323],"genre_scores_gemma":[0.9496914,0.000011750752,0.04988213,0.00028642718,0.000058507663,0.000015737263,0.00004112253,0.0000066563116,0.000006272197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984303,0.000038303515,0.0006702212,0.0001652602,0.0004523724,0.00024351777],"domain_scores_gemma":[0.99860054,0.00005380736,0.00057329435,0.00029337537,0.00035315065,0.00012585487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023287177,0.00016857592,0.00031004392,0.00009332943,0.0002194607,0.00019669234,0.00056333124,0.00006582307,0.000012452375],"category_scores_gemma":[0.00015820425,0.00013519183,0.000045405563,0.0005383664,0.00008927114,0.005370259,0.0002260928,0.00014919338,0.00007184384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033326098,0.00006265567,0.019678777,0.00078610686,0.00007238719,0.0000039158745,0.043295912,0.013344882,0.0003331291,0.0025107167,0.0013693495,0.9182089],"study_design_scores_gemma":[0.0014290616,0.00043366724,0.0020657124,0.00023905115,0.0000109321445,0.0000162802,0.0006138268,0.9823767,0.009475893,0.00016634328,0.0029163018,0.00025620617],"about_ca_topic_score_codex":0.000060127408,"about_ca_topic_score_gemma":0.0000013825087,"teacher_disagreement_score":0.9690319,"about_ca_system_score_codex":0.00005048099,"about_ca_system_score_gemma":0.00010665017,"threshold_uncertainty_score":0.5512963},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054350165,0.000025991229,0.99287385,0.0004435973,0.00007744938,0.00075362297,0.00004746479,0.00018643412,0.00015658246],"genre_scores_gemma":[0.5954418,7.8316424e-7,0.40400794,0.00039932173,0.000027746391,0.00009902907,0.000016131327,0.000005641722,0.0000015494323],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816614,0.000022867202,0.00019348356,0.0008158841,0.00051748805,0.00028413202],"domain_scores_gemma":[0.9990641,0.00006789378,0.00010102155,0.0004157607,0.00009771359,0.00025350205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042298346,0.00015683481,0.00014150962,0.000100415346,0.00072881236,0.0003684714,0.00096343353,0.000034584285,0.0000024764674],"category_scores_gemma":[0.0000088427,0.00013488226,0.00002220823,0.00039870065,0.0002727952,0.00054322823,0.00033562272,0.00009839362,0.000003305406],"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":[0.000024690473,0.0000901099,0.000024363428,0.000014900675,9.3444766e-7,0.0000010879417,0.00032320654,0.01660132,0.96079195,0.0029183284,0.000074041876,0.019135047],"study_design_scores_gemma":[0.00049622374,0.00009790938,0.00038881495,0.000011078192,0.0000024662993,0.000002765793,0.000020782443,0.7960644,0.20123518,0.0014592524,0.0000749224,0.00014625759],"about_ca_topic_score_codex":0.0000091970915,"about_ca_topic_score_gemma":4.226089e-7,"teacher_disagreement_score":0.77946305,"about_ca_system_score_codex":0.00004368098,"about_ca_system_score_gemma":0.000120297904,"threshold_uncertainty_score":0.5605509},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034824677,0.00015878888,0.9835071,0.009142681,0.00059498934,0.00074120634,0.00031388405,0.00026672214,0.001792177],"genre_scores_gemma":[0.7672529,0.00081380224,0.18988372,0.037665483,0.0012749545,0.0005794758,0.0010060633,0.0001263643,0.0013971963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778426,0.00002701642,0.0007754162,0.00032684562,0.00053912593,0.000547366],"domain_scores_gemma":[0.9979073,0.00015312062,0.00039543683,0.0010672129,0.00022383421,0.00025314273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035697463,0.0002794819,0.0002600031,0.00004286084,0.0007915246,0.00086368545,0.0021497232,0.00011674107,0.000014785318],"category_scores_gemma":[0.00009142469,0.0001941538,0.00016530637,0.00036192243,0.000095130614,0.0019315858,0.00073796377,0.0003100074,0.0002606299],"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":[0.00020127365,0.00032333625,0.0064739846,0.0005151245,0.00025990908,0.000008111325,0.0296419,0.00019114486,0.00030274264,0.17608753,0.5161504,0.26984456],"study_design_scores_gemma":[0.0007687084,0.00009845273,0.0006263185,0.00003175893,0.000008789503,0.0000097118855,0.00019871445,0.30913967,0.00052834395,0.0010958026,0.6872349,0.00025886527],"about_ca_topic_score_codex":0.0000052481423,"about_ca_topic_score_gemma":0.0000027326278,"teacher_disagreement_score":0.7936233,"about_ca_system_score_codex":0.000062654864,"about_ca_system_score_gemma":0.00006170334,"threshold_uncertainty_score":0.83285385},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15509906,0.00077617867,0.83217245,0.0050700167,0.0011427212,0.0025395171,0.00086317514,0.0022784474,0.000058428373],"genre_scores_gemma":[0.61980414,0.000050687362,0.3761178,0.0025748466,0.00071229506,0.00054956286,0.0000031214665,0.0001759741,0.000011548707],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958987,0.00014724818,0.000460599,0.0019972112,0.0008486866,0.0006475109],"domain_scores_gemma":[0.99479806,0.000036204154,0.0004631665,0.0035336053,0.000586547,0.000582439],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033657707,0.0007227522,0.00059768214,0.00018857402,0.00023697093,0.00084820035,0.003072336,0.00032295295,0.000043686105],"category_scores_gemma":[0.00007976131,0.0006407673,0.00008963791,0.0011081384,0.00007293992,0.00089671026,0.004652708,0.0011381003,0.00049395114],"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":[0.00015441111,0.00055885455,0.00051268534,0.0017712774,0.00037278584,0.0015528977,0.000098050536,0.00024005123,0.97166306,0.01964601,0.0033763603,0.000053543034],"study_design_scores_gemma":[0.0036219915,0.00072307885,0.015893107,0.006955753,0.0002878953,4.987581e-7,0.000014802187,0.14307453,0.7195486,0.00006505528,0.10305688,0.0067578033],"about_ca_topic_score_codex":0.0003260231,"about_ca_topic_score_gemma":0.0000057071675,"teacher_disagreement_score":0.46470508,"about_ca_system_score_codex":0.00012403427,"about_ca_system_score_gemma":0.0012198252,"threshold_uncertainty_score":0.99960434},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20232527,0.00017377376,0.79489857,0.0008819925,0.00086072285,0.0004356638,0.00017311919,0.0002429669,0.000007908735],"genre_scores_gemma":[0.7946063,0.000029488192,0.20373438,0.0011596547,0.00033436125,0.000060671104,0.000029196382,0.000040176506,0.0000057472907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974131,0.00012719329,0.00047042753,0.0010440301,0.00044652558,0.00049870217],"domain_scores_gemma":[0.99794847,0.00047704103,0.00030368724,0.0007241817,0.00018171134,0.00036489553],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018818225,0.00038990975,0.0005133869,0.000125859,0.00053988554,0.0009262498,0.0019234307,0.00017959198,0.00003236406],"category_scores_gemma":[0.00009938088,0.00032298686,0.000102951046,0.00041451096,0.00006807442,0.0024218967,0.0009843701,0.00021129452,0.000009191292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010080066,0.00072851975,0.0039809495,0.0015671385,0.00026363638,0.00020061596,0.0011253869,0.08939509,0.16091476,0.0033818118,0.047004018,0.69043005],"study_design_scores_gemma":[0.0012732797,0.000090152265,0.0019889104,0.00035184482,0.00004315442,0.0000049988234,0.000008156841,0.69219,0.29893932,0.0009446633,0.0036061415,0.00055942824],"about_ca_topic_score_codex":0.00027350636,"about_ca_topic_score_gemma":0.00000599848,"teacher_disagreement_score":0.68987066,"about_ca_system_score_codex":0.00004914519,"about_ca_system_score_gemma":0.00011788869,"threshold_uncertainty_score":0.9999222},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014763819,0.000046186735,0.98794484,0.0034819806,0.00070078287,0.0024999513,0.0017882168,0.00044438275,0.0016172501],"genre_scores_gemma":[0.1386376,0.00008109499,0.84530526,0.008035702,0.0011728873,0.0023905912,0.0040628733,0.00011833237,0.0001956451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964224,0.000040393115,0.0010631083,0.0008068056,0.0008169532,0.0008503019],"domain_scores_gemma":[0.9966483,0.00013110603,0.00062991015,0.0017507428,0.00036056683,0.00047937216],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003629158,0.000654259,0.00063401356,0.00039732127,0.0007970807,0.0015013408,0.0031042655,0.00029188444,0.000016009883],"category_scores_gemma":[0.000036261114,0.000576004,0.00023458253,0.00054633984,0.00009385972,0.0015199805,0.005318249,0.0011606538,0.00015392365],"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":[0.00044162385,0.001791727,0.009654961,0.014077582,0.0026078827,0.00023296454,0.07605152,0.06404221,0.0010157073,0.51837885,0.11464318,0.19706179],"study_design_scores_gemma":[0.002359087,0.00038996775,0.0006342481,0.0026091384,0.0001588879,0.00009464208,0.0010104566,0.38619298,0.0009824191,0.0074896314,0.5953196,0.002758929],"about_ca_topic_score_codex":0.00006967045,"about_ca_topic_score_gemma":0.000023011184,"teacher_disagreement_score":0.51088923,"about_ca_system_score_codex":0.00024667266,"about_ca_system_score_gemma":0.00024858062,"threshold_uncertainty_score":0.99966913},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039958,0.000101455546,0.9860117,0.008809224,0.00031385163,0.0003390961,0.00011363542,0.00017534802,0.00013990121],"genre_scores_gemma":[0.386539,0.0000055061537,0.6115785,0.0015213477,0.00030669867,0.000005430265,0.000025110676,0.000010785562,0.000007573464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720794,0.0000885349,0.0002943703,0.0012860085,0.00051058544,0.0006125491],"domain_scores_gemma":[0.9976363,0.0002868238,0.00007521668,0.0015364322,0.00011900105,0.00034620828],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0007714261,0.00022706711,0.00030557252,0.00011475787,0.00029279248,0.0004443823,0.0063111237,0.000077349934,0.000039904575],"category_scores_gemma":[0.000249328,0.00017945809,0.000040839586,0.001162157,0.0012765994,0.0015886056,0.004841669,0.00025285364,0.00003688559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051547977,0.000048427744,0.000049973674,0.00002238061,0.0000045103507,0.000019396015,0.0008051099,0.00023501972,0.001407197,0.92238104,0.0009775348,0.07399785],"study_design_scores_gemma":[0.00045743847,0.00019641312,0.0002616398,0.000027811877,0.0000032531977,0.00001622095,0.000004571183,0.95960075,0.0011519424,0.03571794,0.002315435,0.00024657138],"about_ca_topic_score_codex":0.000009755989,"about_ca_topic_score_gemma":0.0000020668713,"teacher_disagreement_score":0.9593657,"about_ca_system_score_codex":0.00003145323,"about_ca_system_score_gemma":0.00021959425,"threshold_uncertainty_score":0.9990652},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062676785,0.00030565602,0.9795555,0.011086906,0.00083141983,0.00041779646,0.000053635187,0.000038742255,0.0014426748],"genre_scores_gemma":[0.6315614,0.00012370612,0.3593069,0.006469647,0.0014118297,0.00013147485,0.00009109691,0.00003111549,0.0008728347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741554,0.00005641733,0.0006468256,0.00028918253,0.0013764462,0.00021557945],"domain_scores_gemma":[0.9965758,0.0008130662,0.0004888673,0.0004063417,0.0015762709,0.00013965662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004776811,0.00015967597,0.0001890355,0.00029429843,0.0002447211,0.00050863257,0.002828255,0.000051044408,0.000048894508],"category_scores_gemma":[0.000059972004,0.00011980411,0.00014224257,0.0009002766,0.000048609858,0.000909143,0.00051184656,0.00026603238,0.00025169612],"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":[0.00013565646,0.00054641993,0.0021902123,0.000015050275,0.0006233688,0.00002721363,0.0008065109,0.17552646,0.000851276,0.46788752,0.022803959,0.32858637],"study_design_scores_gemma":[0.00078707404,0.00016047603,0.010954636,0.00004432295,0.00001345891,0.00030976676,0.00009249456,0.016779495,0.0002703406,0.0691415,0.9011942,0.0002522336],"about_ca_topic_score_codex":0.000014750831,"about_ca_topic_score_gemma":0.0000020892019,"teacher_disagreement_score":0.87839025,"about_ca_system_score_codex":0.00012802877,"about_ca_system_score_gemma":0.00031350114,"threshold_uncertainty_score":0.5255649},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041232724,0.000013732302,0.95284307,0.00048038547,0.0010431483,0.00018234333,4.3412953e-7,0.0002391367,0.0039650574],"genre_scores_gemma":[0.77515024,0.0000020853324,0.22432204,0.0004009569,0.000085934094,0.000003426914,6.2489715e-7,0.000004057493,0.00003066431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778825,0.000068491965,0.00019964126,0.0007245723,0.00074515236,0.00047386895],"domain_scores_gemma":[0.99872124,0.00010264352,0.00005182482,0.00078401325,0.00013547688,0.00020480857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009841071,0.00014294234,0.00015491998,0.00014213438,0.00028147292,0.00054422027,0.00220822,0.000039189606,0.00020171962],"category_scores_gemma":[0.000016639277,0.000108428976,0.000046978592,0.0009999431,0.00054800423,0.0013274284,0.0013256044,0.00016032715,0.0006984215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004483345,0.000024193598,0.00008437984,0.0000029826551,0.0000021396033,0.0000018665612,0.000086897366,0.00016889519,0.0012719352,0.95811534,0.00009194357,0.04014493],"study_design_scores_gemma":[0.00029918956,0.000222311,0.0013199568,0.0000214967,0.000001759429,0.00003384692,0.0000018426574,0.86891574,0.0059706755,0.12197421,0.0010337711,0.0002051853],"about_ca_topic_score_codex":0.0000046366845,"about_ca_topic_score_gemma":1.336972e-7,"teacher_disagreement_score":0.8687469,"about_ca_system_score_codex":0.00006510509,"about_ca_system_score_gemma":0.000096724434,"threshold_uncertainty_score":0.8977028},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029814828,0.003524005,0.96492887,0.0012525506,0.000076830365,0.00019450265,0.000035229958,0.00008275765,0.0000904434],"genre_scores_gemma":[0.8485987,0.0014748612,0.14958411,0.0002901115,0.000013245453,0.000009738463,0.000017202838,0.0000065555832,0.000005449713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984739,0.00013716267,0.00038599607,0.00042116165,0.00031138843,0.00027038404],"domain_scores_gemma":[0.9987699,0.00018086088,0.00021874456,0.0006344739,0.000080359154,0.00011570196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002566896,0.00016934828,0.00021756097,0.00010812878,0.00106552,0.00029446866,0.0015661333,0.000052756826,0.000011604065],"category_scores_gemma":[0.0000029306404,0.0001584389,0.00005770815,0.0006476236,0.00024893694,0.0009831177,0.00014733462,0.00022781774,0.0000019430727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005061394,0.001380053,0.0006832033,0.000086156564,0.0001730208,0.0000013731802,0.0028474582,0.018512266,0.17916307,0.043498512,0.00055880815,0.7530455],"study_design_scores_gemma":[0.00032777173,0.00049293303,0.00004496006,0.00006389535,0.000015047141,0.0000063222324,0.000082633785,0.9796969,0.015046943,0.00027688898,0.003753308,0.00019235854],"about_ca_topic_score_codex":0.0000940892,"about_ca_topic_score_gemma":0.000013692353,"teacher_disagreement_score":0.9611847,"about_ca_system_score_codex":0.000034259632,"about_ca_system_score_gemma":0.00009973909,"threshold_uncertainty_score":0.81952256},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01709738,0.00021333201,0.9757684,0.0059082396,0.00009863232,0.00044862306,0.00024196228,0.00007882729,0.00014460765],"genre_scores_gemma":[0.40770507,0.00006390299,0.5668379,0.022531379,0.0016991127,0.000050282266,0.0010649918,0.00002985456,0.000017516668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982429,0.000114889175,0.0002160696,0.00084935315,0.00031138564,0.000265406],"domain_scores_gemma":[0.99613684,0.00009809248,0.000022561704,0.0034439135,0.000020708621,0.00027790532],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00057357934,0.00014164209,0.00014428436,0.000038157097,0.00015684115,0.00029837707,0.007149603,0.000041294916,0.000080664],"category_scores_gemma":[0.000067220084,0.00009006466,0.000015452926,0.00065244926,0.000014469995,0.0013163335,0.0033306926,0.0001770009,0.000021410584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006883438,0.0004894698,0.0015736572,0.00011945294,0.00003228545,0.0002018657,0.017879253,0.00097087305,0.0102722,0.0022979723,0.10622148,0.85987264],"study_design_scores_gemma":[0.00028099088,0.000044852535,0.00054674706,0.000025101626,0.000008072617,0.000013607775,0.0005693737,0.89148,0.0001302846,0.000024697407,0.10667887,0.00019738593],"about_ca_topic_score_codex":0.00019318945,"about_ca_topic_score_gemma":0.00010708092,"teacher_disagreement_score":0.8905091,"about_ca_system_score_codex":0.0000096523145,"about_ca_system_score_gemma":0.00007387739,"threshold_uncertainty_score":0.9982222},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012788994,0.0001668732,0.9790742,0.0009794871,0.0017754572,0.0016468754,0.0017237428,0.00051185605,0.0013325047],"genre_scores_gemma":[0.3464793,0.0005011112,0.6402795,0.0049792915,0.0012147684,0.00067991944,0.0052356087,0.00021494324,0.0004156059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996198,0.00005844424,0.0013885691,0.0008305756,0.0006396236,0.0008847945],"domain_scores_gemma":[0.99631953,0.00017599094,0.0008313437,0.0018244826,0.0003129159,0.00053573947],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004808791,0.00080896355,0.0009452865,0.00029906206,0.00038897293,0.0017001842,0.003011472,0.00059920194,0.000018179187],"category_scores_gemma":[0.000111732545,0.00072269875,0.00034091587,0.00026429683,0.0001342631,0.0012562923,0.008175662,0.0013153732,0.00008261382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088067935,0.0017197831,0.017494712,0.016996112,0.002260416,0.00021136978,0.07581278,0.0029901932,0.00020253981,0.09018265,0.06544639,0.72580236],"study_design_scores_gemma":[0.0026118408,0.00021869603,0.0017333456,0.00053956296,0.000059677117,0.00007650203,0.00034882664,0.91017056,0.00016327058,0.008003055,0.074856244,0.0012184251],"about_ca_topic_score_codex":0.00008724203,"about_ca_topic_score_gemma":0.000028324135,"teacher_disagreement_score":0.90718037,"about_ca_system_score_codex":0.000109315275,"about_ca_system_score_gemma":0.00023109766,"threshold_uncertainty_score":0.99984604},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008352546,0.00013655926,0.96766406,0.025408939,0.0044685947,0.001030977,0.000017123934,0.0003900729,0.000048388778],"genre_scores_gemma":[0.32729834,0.000014256174,0.6662455,0.005706451,0.0006475212,0.00005633743,0.0000102722215,0.000020409472,8.7474984e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99324477,0.00024981992,0.0007126765,0.0031236263,0.0016479557,0.0010211527],"domain_scores_gemma":[0.99483246,0.0010165097,0.0003211872,0.0028308125,0.00032108932,0.0006779197],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001135642,0.00065693306,0.00083724456,0.0006764063,0.00034682054,0.0041411677,0.011032592,0.000335095,0.000018070046],"category_scores_gemma":[0.0008781418,0.00055985816,0.0001641107,0.0026856388,0.00030906056,0.0019391386,0.028336493,0.0017508579,0.00008800258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009074,0.00024860384,0.00033923323,0.00013611544,0.000022435815,0.00044262895,0.0015745872,0.33121756,0.001335083,0.00073783303,0.0026539492,0.66120124],"study_design_scores_gemma":[0.0006674783,0.000107280226,0.0016670015,0.00032721472,0.000007293517,0.000042362266,1.8626437e-7,0.95779216,0.007146137,0.030431025,0.0011014234,0.00071045035],"about_ca_topic_score_codex":0.00014059064,"about_ca_topic_score_gemma":0.000028987397,"teacher_disagreement_score":0.6604908,"about_ca_system_score_codex":0.00020979124,"about_ca_system_score_gemma":0.0012524321,"threshold_uncertainty_score":0.9996853},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07795286,0.000066286855,0.9201995,0.00024155452,0.00006647772,0.000902762,0.000050048617,0.0002005567,0.00031991955],"genre_scores_gemma":[0.8644682,0.000015422198,0.13497643,0.00012102817,0.00014122418,0.000029699799,0.00003990113,0.000023926394,0.00018414842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757284,0.00003583394,0.00038006707,0.0015650636,0.00012628689,0.00031990116],"domain_scores_gemma":[0.9977529,0.0001037495,0.0008273233,0.0008136159,0.00022993902,0.00027244844],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032096254,0.00028954938,0.00037879046,0.00016424914,0.0004116609,0.00034287368,0.0010458361,0.00015042986,0.0000041475964],"category_scores_gemma":[0.00006916877,0.0002876609,0.00008748169,0.0005275581,0.000067303714,0.00060336175,0.0024230587,0.00035991712,0.0000051948055],"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":[0.0011652668,0.0004976788,0.08455524,0.0031150207,0.00055065815,0.0011051656,0.0058266902,0.6274229,0.00068218133,0.13647081,0.00082091923,0.13778745],"study_design_scores_gemma":[0.0009997917,0.00012697598,0.006617336,0.00046366386,0.00010784796,0.000033320488,0.0002072025,0.9833621,0.00013809501,0.004668665,0.0024615012,0.0008134994],"about_ca_topic_score_codex":0.000048178317,"about_ca_topic_score_gemma":0.000020849651,"teacher_disagreement_score":0.78651536,"about_ca_system_score_codex":0.000066738314,"about_ca_system_score_gemma":0.00021852624,"threshold_uncertainty_score":0.99995756},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004143951,0.000014858624,0.99154925,0.0015413774,0.00014530026,0.00021283256,0.000043434204,0.00014978429,0.0021991853],"genre_scores_gemma":[0.15349066,0.0000025574707,0.84611714,0.00020646623,0.00007700506,0.000013423016,0.000015583702,0.000014047705,0.00006314054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993002,0.000010168567,0.00015504693,0.00021461424,0.00015413323,0.00016585432],"domain_scores_gemma":[0.99938905,0.000084077714,0.000072865274,0.00029447253,0.000047490874,0.000112030655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059727623,0.00009638882,0.0001277378,0.000026161204,0.00015409419,0.00008933029,0.00046079204,0.000031325922,0.000018073019],"category_scores_gemma":[0.000054919612,0.00008073853,0.00006365667,0.00017950329,0.000047892157,0.00009832898,0.00022952078,0.00005900248,0.000034815064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005751155,0.00006623773,0.000008595303,0.000108679946,0.000027936077,0.0000033530973,0.0035158775,0.007158964,0.0004230052,0.9791291,0.0044488544,0.0051036957],"study_design_scores_gemma":[0.0002952471,0.00004407544,0.000005376278,0.000018368823,0.0000097071,0.0000051553843,0.0008000508,0.98573494,0.00019016325,0.005541553,0.007238384,0.00011699467],"about_ca_topic_score_codex":0.000003750818,"about_ca_topic_score_gemma":4.5188568e-7,"teacher_disagreement_score":0.97857594,"about_ca_system_score_codex":0.000013380241,"about_ca_system_score_gemma":0.0000364362,"threshold_uncertainty_score":0.32924217},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0582457,0.00023480332,0.934013,0.0000893005,0.0016140067,0.00019384474,0.000036878835,0.0003640082,0.0052084313],"genre_scores_gemma":[0.9922932,0.000121858815,0.005916108,0.00009612205,0.0001884461,4.374379e-7,0.000045973244,0.0000145611175,0.0013233244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983062,0.00010242605,0.00014992764,0.00091710506,0.00010260553,0.00042173167],"domain_scores_gemma":[0.9975775,0.000059648137,0.00018704723,0.0018264003,0.00009376919,0.00025561752],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020218224,0.0002889318,0.0002700636,0.000165973,0.00016362013,0.00013681279,0.0025086808,0.0002745591,0.00008062777],"category_scores_gemma":[0.000012458948,0.00029957632,0.00016440258,0.00031249854,0.000051068397,0.0007360632,0.005458395,0.000525265,0.00038969232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059200876,0.0006646146,0.012181497,0.00022719723,0.00026422023,0.0013540576,0.00072845415,0.045363262,0.00015263341,0.8981315,0.015918659,0.024954733],"study_design_scores_gemma":[0.00078923296,0.00005819365,0.013938054,0.0001888683,0.00009930131,0.000026450092,0.000032271717,0.8948955,0.000273886,0.06620482,0.022150883,0.0013425433],"about_ca_topic_score_codex":0.00019398534,"about_ca_topic_score_gemma":0.00001015175,"teacher_disagreement_score":0.93404746,"about_ca_system_score_codex":0.00011962939,"about_ca_system_score_gemma":0.00012483781,"threshold_uncertainty_score":0.99994564},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010654942,0.0029347732,0.9763538,0.0027576557,0.0013295409,0.00046970215,0.00048924045,0.00040792435,0.0046024187],"genre_scores_gemma":[0.54500186,0.00070663466,0.43155438,0.013127176,0.0031072067,0.00003200163,0.005874843,0.00012652812,0.0004693788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662256,0.00026405236,0.0011480876,0.0005559292,0.0007056173,0.0007037225],"domain_scores_gemma":[0.99687797,0.00015856854,0.00060873403,0.0015826031,0.00034153461,0.00043058404],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007263343,0.00040974581,0.0004274316,0.00019369394,0.0007747177,0.0020530033,0.002408031,0.00031497647,0.0001115749],"category_scores_gemma":[0.00070397224,0.0004315006,0.00009220424,0.0013556406,0.00023935598,0.022761203,0.0030499268,0.00049347826,0.00037215013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092910195,0.00007043237,0.00054211984,0.0018456144,0.0001141886,0.000045845776,0.0318065,0.010876347,0.0011928814,0.005967584,0.034060925,0.9133847],"study_design_scores_gemma":[0.00047055216,0.00007789424,0.0002819233,0.00068144867,0.000037283917,0.00007660675,0.0009288334,0.7401212,0.00027588682,0.0002480434,0.2564253,0.00037503234],"about_ca_topic_score_codex":0.00034271445,"about_ca_topic_score_gemma":0.0000034961483,"teacher_disagreement_score":0.91300964,"about_ca_system_score_codex":0.00029154506,"about_ca_system_score_gemma":0.00037670528,"threshold_uncertainty_score":0.9998137},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042057414,0.000029711358,0.9540285,0.0027718765,0.00029176293,0.00037620257,0.000016085467,0.00020294121,0.00022554226],"genre_scores_gemma":[0.45877513,0.000001418803,0.5389462,0.001995129,0.00023672594,0.00002363261,0.0000042909846,0.000009805843,0.000007679361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970227,0.00010989129,0.0004337919,0.0010340537,0.00062314793,0.00077641284],"domain_scores_gemma":[0.9983882,0.00024855405,0.00009504976,0.00063049176,0.00012701785,0.00051069417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011141793,0.00024357752,0.00032794336,0.00014790359,0.000392078,0.0005915668,0.0028035808,0.00007049616,0.000056436897],"category_scores_gemma":[0.00020483683,0.0001965766,0.00008485031,0.001047915,0.0008837681,0.0010160978,0.0018174637,0.00026695343,0.00007842641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001201504,0.00017501686,0.00018559351,0.00003367738,0.000009356464,0.00003985523,0.0029378873,0.005535146,0.021726228,0.7960229,0.0008117808,0.1724024],"study_design_scores_gemma":[0.0006579191,0.00022961022,0.00024774027,0.000031820935,0.0000032466776,0.0000141980345,0.000004770235,0.98735064,0.0019153224,0.008758591,0.000505214,0.00028095313],"about_ca_topic_score_codex":0.0000047800845,"about_ca_topic_score_gemma":0.0000014869353,"teacher_disagreement_score":0.98181546,"about_ca_system_score_codex":0.000052245654,"about_ca_system_score_gemma":0.00022555291,"threshold_uncertainty_score":0.8016161},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010187498,0.000092729555,0.98095137,0.015875127,0.00052175584,0.0005988298,0.000014814953,0.00031058167,0.00061603484],"genre_scores_gemma":[0.5773306,0.000016367438,0.4192583,0.0029296773,0.00039507408,0.000047396657,0.000004974104,0.000011620526,0.00000602374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996866,0.000104625746,0.00038334003,0.0010764737,0.0008773189,0.00069224107],"domain_scores_gemma":[0.9970778,0.0008830001,0.0001290372,0.0012076816,0.00027860817,0.0004238782],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014435108,0.00025447883,0.00026349595,0.0000645697,0.0012187735,0.0011582094,0.005099915,0.00006225645,0.00003412434],"category_scores_gemma":[0.00013167456,0.0001629438,0.00010773804,0.001191867,0.00247104,0.0011782458,0.0017672518,0.00029383056,0.00006252133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013285611,0.000036666257,0.000019768375,0.000013401527,0.0000048572933,0.000010207212,0.00037820695,0.00026574775,0.00032499165,0.91645694,0.0003789383,0.08209702],"study_design_scores_gemma":[0.000270773,0.00035244715,0.00034559413,0.00003273466,0.0000075664598,0.000036547965,0.000008619735,0.8713386,0.00221236,0.12273326,0.0024098435,0.00025162406],"about_ca_topic_score_codex":0.000013836562,"about_ca_topic_score_gemma":0.0000011299414,"teacher_disagreement_score":0.8710729,"about_ca_system_score_codex":0.00005699982,"about_ca_system_score_gemma":0.00019867157,"threshold_uncertainty_score":0.9998787},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012656489,0.00025835805,0.99037343,0.0038522708,0.003770733,0.0007471515,0.00005530839,0.00023575392,0.0006943532],"genre_scores_gemma":[0.0033083467,0.000012403885,0.98517495,0.007729835,0.0033352477,0.000041551222,0.00004691156,0.0000700255,0.00028073616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99479467,0.00003603826,0.0007280509,0.002376646,0.0011463624,0.00091822137],"domain_scores_gemma":[0.9964138,0.00095732574,0.000396092,0.0016252111,0.00029356897,0.0003139984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071157375,0.00073395297,0.0007465343,0.00056813366,0.00040674774,0.0009893008,0.0045131454,0.00042973398,0.000028145574],"category_scores_gemma":[0.00019058828,0.00063339033,0.00027009207,0.00048234468,0.00042234012,0.0012118561,0.0031762354,0.00095283904,0.00007753035],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007823552,0.00002187197,0.0000211365,0.00006370538,0.000018953844,0.00008237162,0.00038306872,0.0024387122,0.0000945933,0.0027961244,0.0010128123,0.9930588],"study_design_scores_gemma":[0.00043614602,0.00024446158,0.000030360514,0.00036748726,0.000013319421,0.000058922808,1.512096e-7,0.8733267,0.0010275984,0.100459374,0.023242591,0.00079289015],"about_ca_topic_score_codex":0.000010531829,"about_ca_topic_score_gemma":0.00000996256,"teacher_disagreement_score":0.99226594,"about_ca_system_score_codex":0.00020722496,"about_ca_system_score_gemma":0.0003304725,"threshold_uncertainty_score":0.99961174},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017527447,0.00010702678,0.9869238,0.0051686093,0.00028338606,0.0008086811,0.000009492705,0.00038332038,0.0045629465],"genre_scores_gemma":[0.05860994,0.000039957253,0.91153896,0.002373417,0.00033035534,0.0005329985,0.000079594356,0.00005157528,0.026443198],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986974,0.000026347327,0.00019674846,0.00044346016,0.00023123727,0.0004047988],"domain_scores_gemma":[0.9989214,0.00011711582,0.0000639012,0.0006415188,0.00008701437,0.00016903089],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016561596,0.0001572979,0.00016021481,0.00006099191,0.00013025048,0.0003220692,0.00092601404,0.00007502761,0.00037832189],"category_scores_gemma":[0.000023334413,0.00011451821,0.000073605224,0.00016355397,0.00003261374,0.0011631725,0.00027871257,0.00008592935,0.0009332635],"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":[0.0000056629847,0.00028753496,0.00010354547,0.000059254067,0.000053420557,0.000004292882,0.0008175645,0.00037398754,0.011188967,0.06137201,0.83889335,0.08684039],"study_design_scores_gemma":[0.0003923477,0.00013475705,0.0004404771,0.00001987886,0.0000042193797,0.000006803501,0.000014100314,0.77202636,0.0018677753,0.007065312,0.2177578,0.00027015372],"about_ca_topic_score_codex":0.00012727255,"about_ca_topic_score_gemma":0.0000033085837,"teacher_disagreement_score":0.7716524,"about_ca_system_score_codex":0.000018749477,"about_ca_system_score_gemma":0.000039276772,"threshold_uncertainty_score":0.9998446},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39472064,0.0026384469,0.25931868,0.2120973,0.004138572,0.0042767455,0.00007334357,0.0018504238,0.12088584],"genre_scores_gemma":[0.9743349,0.000029493069,0.024165077,0.0012222988,0.00011831928,0.0000141071405,4.3230608e-7,0.0000067663377,0.00010859697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912035,0.0000031619763,0.00016569854,0.00023562709,0.0003218358,0.00015332602],"domain_scores_gemma":[0.99956286,0.000013881014,0.00012207487,0.00014074263,0.00007996375,0.00008049859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010890627,0.000089794754,0.00011676552,0.000018139039,0.00008014175,0.000070768816,0.0014069949,0.000022277256,0.000013735927],"category_scores_gemma":[0.00004759439,0.00005511328,0.00006737249,0.0002631085,0.000028380939,0.00033807816,0.0010603406,0.00009060231,0.000019343279],"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":[0.00007525189,0.00034722048,0.0057842545,0.00031831005,0.00010100898,0.000003184765,0.0073113097,0.000074169126,0.28302062,0.45094278,0.16298349,0.089038394],"study_design_scores_gemma":[0.001870915,0.00041238673,0.005575307,0.00018546265,0.000034317687,0.000021121316,0.00026912658,0.07575242,0.73661625,0.013868397,0.16487789,0.0005164161],"about_ca_topic_score_codex":0.000012641496,"about_ca_topic_score_gemma":8.949419e-8,"teacher_disagreement_score":0.5796143,"about_ca_system_score_codex":0.0000147099345,"about_ca_system_score_gemma":0.000016193915,"threshold_uncertainty_score":0.261457},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022586337,0.00018698031,0.9903746,0.0058648605,0.00022360492,0.00037609576,0.000046984416,0.00039012104,0.00027808174],"genre_scores_gemma":[0.10028645,0.000041230338,0.8960391,0.0019171982,0.0009215222,0.00010548266,0.00011284481,0.00006148649,0.0005146852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984206,0.000030005207,0.00024436766,0.0006074594,0.00027305877,0.00042450303],"domain_scores_gemma":[0.99894065,0.00018161423,0.00009132878,0.00045615793,0.0000628452,0.0002674347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018097977,0.00021439041,0.00025740216,0.000062189305,0.00022319198,0.00021358409,0.0010469642,0.00009569277,0.000020324787],"category_scores_gemma":[0.000067071574,0.00019797913,0.00010859602,0.00043755816,0.000033816807,0.0006892328,0.00036265457,0.00019099037,0.00006274001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007552786,0.0003449319,0.0009907763,0.00017793494,0.00020712272,0.0004696675,0.009692206,0.002584214,0.023101721,0.026483558,0.07478246,0.8610899],"study_design_scores_gemma":[0.0004930153,0.00015679949,0.00039707357,0.000038779595,0.000011014334,0.000026011972,0.00004893025,0.9585103,0.0069641247,0.00043056963,0.032591615,0.0003318124],"about_ca_topic_score_codex":0.000022216504,"about_ca_topic_score_gemma":6.059808e-7,"teacher_disagreement_score":0.95592606,"about_ca_system_score_codex":0.000033994245,"about_ca_system_score_gemma":0.00007114232,"threshold_uncertainty_score":0.80733544},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03431583,0.00021305803,0.9638263,0.00060340523,0.00021998471,0.0001071417,0.000009135811,0.00020076675,0.000504362],"genre_scores_gemma":[0.7408081,0.000012664239,0.25871435,0.00025195038,0.00018358445,0.0000014021019,0.0000064879973,0.000010407732,0.000010993728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986068,0.00003276717,0.0003183275,0.0004138731,0.00034381513,0.0002843961],"domain_scores_gemma":[0.99915946,0.00007552447,0.0001554181,0.00036835752,0.00007505309,0.00016618232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001587762,0.00014568721,0.00024687304,0.000055131335,0.000093927134,0.00008138293,0.0009821309,0.000052925992,0.0000171628],"category_scores_gemma":[0.000038112146,0.00013534681,0.00007631976,0.00046348304,0.00003567751,0.00047349875,0.0008062438,0.00016886716,0.000030774598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020754711,0.00012162664,0.0017212224,0.000096897136,0.00005479352,0.0001679296,0.0026727305,0.000644316,0.006680342,0.015012658,0.002049578,0.9707571],"study_design_scores_gemma":[0.0006221523,0.00016700893,0.0026683735,0.000053314805,0.000006875734,0.000027710665,0.00006259247,0.9777567,0.014379499,0.0004200308,0.0035935505,0.00024221551],"about_ca_topic_score_codex":0.00006555879,"about_ca_topic_score_gemma":3.2488842e-7,"teacher_disagreement_score":0.97711235,"about_ca_system_score_codex":0.000015145382,"about_ca_system_score_gemma":0.000043379245,"threshold_uncertainty_score":0.5519283},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31340998,0.0021203668,0.6817876,0.0012039565,0.0011117382,0.00012578431,0.000010909193,0.00005721185,0.00017243327],"genre_scores_gemma":[0.64181226,0.000028429276,0.35740662,0.00025625032,0.00048146388,4.895115e-7,0.0000021703395,0.000009707846,0.0000026216273],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983196,0.000076801945,0.00068465143,0.00021795093,0.0004829601,0.00021801345],"domain_scores_gemma":[0.9985933,0.00011784415,0.00060226466,0.00035392548,0.00012621858,0.0002064544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023127087,0.00016265771,0.0003542609,0.00006802341,0.000092056944,0.000074485855,0.0015245161,0.00006316991,0.000019589299],"category_scores_gemma":[0.000106815154,0.00013761272,0.00015246215,0.000256348,0.00006030006,0.000625869,0.0009680763,0.00024522984,0.000005316128],"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":[0.0003296011,0.0016148419,0.0031079021,0.000088682704,0.00040395305,0.000874932,0.027283287,0.0015806808,0.5773704,0.027565725,0.009981917,0.34979808],"study_design_scores_gemma":[0.002154444,0.0019059333,0.0012397101,0.0001813956,0.000021923188,0.00029621428,0.0010493054,0.45620555,0.53149956,0.0014028082,0.0035925484,0.00045062328],"about_ca_topic_score_codex":0.000012099439,"about_ca_topic_score_gemma":7.2306044e-8,"teacher_disagreement_score":0.45462486,"about_ca_system_score_codex":0.000040568008,"about_ca_system_score_gemma":0.000074928306,"threshold_uncertainty_score":0.5611684},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008631337,0.000022017404,0.6637722,0.0024001685,0.00041284217,0.0009515739,0.00016114485,0.00015357767,0.33211783],"genre_scores_gemma":[0.4859956,0.0008612303,0.36661068,0.002795314,0.003807907,0.00005463814,0.0025192546,0.0002498689,0.13710554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996059,0.00016015435,0.0005717014,0.0005219588,0.00225381,0.000433396],"domain_scores_gemma":[0.99597126,0.00032948254,0.00050064625,0.0011848346,0.0013831235,0.0006306398],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00125745,0.0003120886,0.00068488444,0.0010629087,0.00072515436,0.00057706307,0.0032899794,0.0003834649,0.00013693377],"category_scores_gemma":[0.00038111975,0.00033444868,0.00018877436,0.00047338204,0.00028124655,0.0067649176,0.0039079655,0.00088897574,0.0018148347],"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":[0.0007854207,0.00003208316,0.0000050891863,0.0011030633,0.00013803734,0.00024877515,0.0019058578,0.00043032016,0.000041622512,0.60817796,0.35588455,0.031247215],"study_design_scores_gemma":[0.0020291465,0.00020109052,0.000058262747,0.00090920343,0.000022808848,0.00003544534,0.0003462516,0.048848536,0.00004689262,0.00028738414,0.94683325,0.00038173044],"about_ca_topic_score_codex":0.00027805183,"about_ca_topic_score_gemma":0.000019394474,"teacher_disagreement_score":0.6078906,"about_ca_system_score_codex":0.00036723155,"about_ca_system_score_gemma":0.0011286918,"threshold_uncertainty_score":0.9999108},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027249102,0.000076513235,0.96717614,0.0004630653,0.00052050385,0.00017965861,0.00003998592,0.00038447112,0.0039105806],"genre_scores_gemma":[0.9904545,0.00016247996,0.0078089014,0.00015974723,0.00015190973,4.1477534e-7,0.00004034838,0.000014368481,0.0012073388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981217,0.00011997993,0.00013613337,0.0011795422,0.00013133138,0.0003113251],"domain_scores_gemma":[0.9981201,0.0000670086,0.000098752804,0.0013677394,0.000095670526,0.00025072086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001337817,0.0002499639,0.00027296785,0.0001432164,0.00015347326,0.00019515729,0.002940444,0.00020517508,0.0000506264],"category_scores_gemma":[0.000015984391,0.00026492786,0.00016047612,0.0004727963,0.00007092191,0.0004251218,0.006810618,0.0006595868,0.00031695768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071215676,0.0002741762,0.0027535202,0.00019711893,0.00021119099,0.0029753721,0.00097362156,0.18148687,0.0003129904,0.7781506,0.014946972,0.017646303],"study_design_scores_gemma":[0.00029570828,0.00004955581,0.0017005616,0.00006629204,0.00002048181,0.0000033106357,0.000036467587,0.96107763,0.00017727184,0.03067199,0.005513325,0.00038738624],"about_ca_topic_score_codex":0.0002270267,"about_ca_topic_score_gemma":0.000017585759,"teacher_disagreement_score":0.9632054,"about_ca_system_score_codex":0.00008737874,"about_ca_system_score_gemma":0.00019879939,"threshold_uncertainty_score":0.9999803},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75701785,0.00012785032,0.111868225,0.00057028193,0.0022056084,0.00062282116,0.000009531339,0.0006995782,0.12687826],"genre_scores_gemma":[0.9639314,0.000087590204,0.018579066,0.000041135278,0.0009280817,0.0000033964668,0.000011460586,0.000027867884,0.016390044],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995689,0.000650274,0.0002807093,0.0011003164,0.0013408863,0.00093882356],"domain_scores_gemma":[0.99680233,0.00015353206,0.0001424862,0.0014570942,0.0009694889,0.00047506715],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006189906,0.0002695156,0.00026170976,0.001165312,0.0024184086,0.00044867376,0.0021148368,0.00019223904,0.00008646809],"category_scores_gemma":[0.00007714454,0.00027755238,0.00012878499,0.002127827,0.0008316315,0.0023260985,0.0014238642,0.0007364195,0.000278924],"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":[0.00064273365,0.00052095525,0.007990712,0.00020181015,0.0001952371,0.0027542317,0.0023487476,0.000037350725,0.8840851,0.056155846,0.021495877,0.023571355],"study_design_scores_gemma":[0.0034545555,0.0011186654,0.010542255,0.00044718696,0.00003373529,0.00063707936,0.001764026,0.02148087,0.619961,0.0014957394,0.33776554,0.0012993007],"about_ca_topic_score_codex":0.0004542979,"about_ca_topic_score_gemma":0.000019931316,"teacher_disagreement_score":0.31626967,"about_ca_system_score_codex":0.000585203,"about_ca_system_score_gemma":0.00034140877,"threshold_uncertainty_score":0.9999677},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3952262e-7,0.83445114,0.16179103,0.000048316484,0.00016180729,0.0007039825,0.00018233576,0.0005630442,0.0020980877],"genre_scores_gemma":[9.4363645e-7,0.9187886,0.079686075,0.000043260028,0.00014390991,0.000005382625,0.0003682999,0.000048867834,0.0009146249],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975155,0.00021951008,0.00025815595,0.0010782809,0.00044075638,0.00048778206],"domain_scores_gemma":[0.997925,0.00010071317,0.00035436446,0.0011240437,0.00012868046,0.00036719575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013558262,0.000519898,0.0010863508,0.00040003716,0.00044407323,0.0004987544,0.0032102088,0.00023886742,0.00007192506],"category_scores_gemma":[0.000030605905,0.00042699743,0.00030586717,0.0018495183,0.000048022215,0.0018311923,0.0010631323,0.0008898102,0.00034077666],"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":[0.000003434193,0.000032406737,0.0000023352911,0.0013987141,0.000081860235,0.0007138331,0.00006098922,3.6474125e-7,2.4438913e-7,0.0028005478,0.0005198669,0.9943854],"study_design_scores_gemma":[0.0002222508,0.000107172695,0.0000012213378,0.004379424,0.00014883972,0.000076711374,0.000025351283,0.000025350839,0.0000014096983,0.000011726825,0.99445325,0.0005472705],"about_ca_topic_score_codex":0.000021081976,"about_ca_topic_score_gemma":0.000006117964,"teacher_disagreement_score":0.9939334,"about_ca_system_score_codex":0.00021248027,"about_ca_system_score_gemma":0.000572427,"threshold_uncertainty_score":0.9998182},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0776173,0.000021614309,0.9203515,0.00090548873,0.00024770678,0.0001175421,0.0000053131516,0.00014101343,0.000592499],"genre_scores_gemma":[0.84496164,0.0000025901836,0.154654,0.0003104368,0.000063329906,0.0000010871621,0.0000012126707,0.0000045847046,0.0000011031362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997858,0.00006719463,0.00030405162,0.00063023425,0.0007427757,0.0003977416],"domain_scores_gemma":[0.99856204,0.00021712438,0.00009627057,0.0005947223,0.000155529,0.00037429528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004942152,0.00016481655,0.00027643942,0.00008653905,0.00020204241,0.00021213785,0.0030125796,0.000040667623,0.000052778025],"category_scores_gemma":[0.00013117139,0.00012012963,0.00007390254,0.0011049795,0.0014418025,0.00078185997,0.0019018368,0.0001631384,0.000022187263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027554997,0.00004315382,0.00015026814,0.000011105705,0.000003867733,0.000006857972,0.00077461556,0.00015593215,0.0021776932,0.961908,0.000078716665,0.03466227],"study_design_scores_gemma":[0.00075797027,0.0003223845,0.0021855016,0.000024916244,0.0000043422506,0.0000058533165,0.000012242455,0.9424621,0.027504187,0.026180932,0.00030769737,0.00023188145],"about_ca_topic_score_codex":0.0000053433696,"about_ca_topic_score_gemma":4.2146436e-8,"teacher_disagreement_score":0.94230616,"about_ca_system_score_codex":0.000015292177,"about_ca_system_score_gemma":0.00010834561,"threshold_uncertainty_score":0.55981725},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006937674,0.000036671816,0.9969633,0.00027377313,0.00021378764,0.00034367014,0.0000050672734,0.0002085596,0.0012613566],"genre_scores_gemma":[0.019945249,0.0000042743295,0.9782921,0.00030134222,0.0001233939,0.00016520296,0.000011642983,0.000009268733,0.0011475363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912024,0.0000073313654,0.00014047314,0.00030961796,0.00016605199,0.00025630897],"domain_scores_gemma":[0.99935377,0.00004733412,0.000045226912,0.00031841232,0.00014394367,0.0000913361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094366645,0.000098247496,0.00009986283,0.000046284993,0.00013594255,0.0003115467,0.0006663441,0.000036465663,0.00006694935],"category_scores_gemma":[0.0000106227435,0.00007309055,0.000039644616,0.00013784511,0.000011740794,0.0011688661,0.00019888948,0.000049051425,0.00006204257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.483284e-7,0.00003218094,0.000010920781,0.000009999683,0.000005139725,7.385249e-7,0.00015416653,0.000030403502,0.00023560748,0.005138838,0.004956153,0.9894255],"study_design_scores_gemma":[0.00022076636,0.00005109268,0.000056946716,0.000014463027,0.0000013887558,0.0000040026207,0.00006189448,0.9819949,0.0020104263,0.009959957,0.005487556,0.00013656956],"about_ca_topic_score_codex":0.000047548663,"about_ca_topic_score_gemma":0.0000010102036,"teacher_disagreement_score":0.9892889,"about_ca_system_score_codex":0.000011866909,"about_ca_system_score_gemma":0.000032123335,"threshold_uncertainty_score":0.3004252},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053415787,0.0002688036,0.992283,0.00009079797,0.00054395007,0.00016524378,0.00020250688,0.00022162787,0.00088249607],"genre_scores_gemma":[0.05536975,0.00016137822,0.94248796,0.00011365212,0.000067092,0.000021961083,0.0005299358,0.000016231374,0.0012320624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979299,0.00008114436,0.0002968874,0.00091223663,0.00047298963,0.00030685728],"domain_scores_gemma":[0.99803054,0.00008821227,0.00021087675,0.0013355386,0.00019070269,0.0001441546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014174235,0.00031580316,0.00036583256,0.000083201085,0.00014148535,0.0010268886,0.0015782455,0.00015014877,0.00014152362],"category_scores_gemma":[0.0000121168505,0.00022276229,0.00004187914,0.00014003758,0.000041578645,0.00033274578,0.0036985588,0.00055786205,0.00002334566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068556576,0.0020853532,0.0012534687,0.0015190884,0.0009873251,0.0027176784,0.019035246,0.03641969,0.0020551388,0.073920324,0.004909917,0.8550282],"study_design_scores_gemma":[0.0019388163,0.00035834892,0.022320395,0.0016039667,0.00010847798,0.000121737256,0.0019243995,0.9454809,0.0015252249,0.014589896,0.0066271857,0.0034006664],"about_ca_topic_score_codex":0.0019007032,"about_ca_topic_score_gemma":0.00057729357,"teacher_disagreement_score":0.9090612,"about_ca_system_score_codex":0.00004955149,"about_ca_system_score_gemma":0.00041619354,"threshold_uncertainty_score":0.990231},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003476669,0.0003224738,0.9974496,0.0003442902,0.000047166,0.0008989818,0.00040665103,0.000064868465,0.00011831724],"genre_scores_gemma":[0.017482711,0.000028735918,0.98012346,0.00015419541,0.00007044362,0.001980957,0.00010316423,0.000020362795,0.000035990342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871236,0.000046538717,0.00036947906,0.00034360346,0.00032632,0.00020169945],"domain_scores_gemma":[0.9983282,0.00035698162,0.0002733135,0.0008648288,0.000095630145,0.00008102084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006207136,0.00014539488,0.00020528348,0.00007690226,0.0008900644,0.00014064844,0.0010041877,0.000027035316,0.000009612698],"category_scores_gemma":[0.000012033355,0.00010581299,0.00007534073,0.00041755318,0.000086463275,0.00019211475,0.0003238594,0.00011686687,8.1642764e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002190082,0.00029309664,0.000008526639,0.000047090572,0.000020057007,5.772794e-7,0.0007747479,0.00055290665,0.00031324598,0.27655455,0.0002241163,0.7212089],"study_design_scores_gemma":[0.00032248354,0.00010589183,0.000024115796,0.000011947409,0.000016425482,0.0000082185,0.0005940492,0.946375,0.00052433513,0.03061209,0.02126016,0.00014524418],"about_ca_topic_score_codex":0.000016890082,"about_ca_topic_score_gemma":0.000001527575,"teacher_disagreement_score":0.9458221,"about_ca_system_score_codex":0.000023108343,"about_ca_system_score_gemma":0.00007279421,"threshold_uncertainty_score":0.68457454},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016562486,0.0011446385,0.95526063,0.020369004,0.00032851644,0.0007236487,0.00018029509,0.0004899739,0.0049407934],"genre_scores_gemma":[0.77561533,0.0009098473,0.20050003,0.00051740906,0.000056688736,0.00013386822,0.00010436513,0.0000966627,0.022065792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9882928,0.007405606,0.0008740293,0.0014228619,0.0007644055,0.001240279],"domain_scores_gemma":[0.9893351,0.0034936678,0.0006966097,0.003913895,0.0018188624,0.0007418178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061491732,0.00059685047,0.0005907795,0.00025555887,0.0009847056,0.00093970494,0.0040015983,0.00038040252,0.0004329633],"category_scores_gemma":[0.0016550203,0.0005040631,0.00028976356,0.000766206,0.00048992486,0.0010224367,0.0027120658,0.00052299607,0.00031174833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088460685,0.0046215556,0.010915607,0.00038429056,0.00022926163,0.00009349181,0.018531147,0.00020890073,0.047190692,0.22044021,0.037249494,0.6600469],"study_design_scores_gemma":[0.0049084695,0.0000067871815,0.011416975,0.007588501,0.000105780404,0.00014799448,0.00017786286,0.760232,0.14726712,0.009056746,0.05745841,0.0016333846],"about_ca_topic_score_codex":0.0014581428,"about_ca_topic_score_gemma":0.00036496614,"teacher_disagreement_score":0.76002306,"about_ca_system_score_codex":0.00032487285,"about_ca_system_score_gemma":0.0006093967,"threshold_uncertainty_score":0.9997411},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050247565,0.000027212327,0.9935235,0.004392747,0.00015469673,0.00018063025,0.0000066376056,0.00014320166,0.0010689365],"genre_scores_gemma":[0.18532614,0.0000067110777,0.81250286,0.0016093509,0.00026495423,0.000037613827,0.00002345489,0.0000065569343,0.00022234952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994403,0.00001051755,0.00008753888,0.00026307293,0.000093057184,0.0001054959],"domain_scores_gemma":[0.9995606,0.000033882054,0.0000329106,0.00023693185,0.000057747075,0.000077950936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000049878636,0.000057542387,0.00006173971,0.000013792063,0.00007911305,0.00007483823,0.0004186517,0.000025511124,0.00002444607],"category_scores_gemma":[0.000043378925,0.00004661168,0.000026050378,0.00012898953,0.000011171027,0.00043419364,0.0001310055,0.000037498976,0.00006432595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045518827,0.00008995017,0.000055471945,0.000035134963,0.000017794271,0.000002319388,0.0017533598,0.00024369404,0.008322951,0.42447942,0.100338854,0.46461555],"study_design_scores_gemma":[0.00044413062,0.00015954934,0.0010697268,0.0000067862343,0.0000051809975,0.0000022408394,0.00009526434,0.7665736,0.01541522,0.0030993272,0.21292822,0.0002007588],"about_ca_topic_score_codex":0.000009774506,"about_ca_topic_score_gemma":3.12591e-7,"teacher_disagreement_score":0.7663299,"about_ca_system_score_codex":0.000009918697,"about_ca_system_score_gemma":0.000030631578,"threshold_uncertainty_score":0.19007692},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001419997,0.0018115457,0.99428785,0.0001633703,0.0020766216,0.00026855594,0.000054702195,0.00015895981,0.0011641887],"genre_scores_gemma":[0.0019793664,0.00016719177,0.9957023,0.00085401745,0.0007915375,0.000004626642,0.00008598459,0.000030888503,0.00038407615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953205,0.000057556364,0.00043583463,0.0025952167,0.0009024704,0.0006884225],"domain_scores_gemma":[0.9946761,0.00030235955,0.0002507814,0.004387595,0.00013534646,0.0002478142],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008925715,0.00052984076,0.0005190316,0.00058385334,0.00031324115,0.00085216016,0.010229356,0.00033066227,0.000018247845],"category_scores_gemma":[0.00009433498,0.00042935627,0.000042308384,0.0006638051,0.00079507515,0.001795209,0.012691494,0.00084346184,0.000017925408],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021125409,0.000017169437,0.00002649177,0.000029131445,0.000007112194,0.00007355937,0.0003517766,0.0002649112,0.000014365543,0.0032189535,0.0007949498,0.99519944],"study_design_scores_gemma":[0.00025203332,0.00011317175,0.00053732964,0.00022367339,0.0000090882095,0.00017444995,1.1247744e-7,0.7326692,0.00023928905,0.25144893,0.013606607,0.00072611164],"about_ca_topic_score_codex":0.000078292076,"about_ca_topic_score_gemma":0.0000370273,"teacher_disagreement_score":0.99447334,"about_ca_system_score_codex":0.00012553624,"about_ca_system_score_gemma":0.000978766,"threshold_uncertainty_score":0.9998158},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22981238,0.00002183623,0.76579845,0.0018182029,0.0002488796,0.00015539471,0.00001985799,0.00029366126,0.0018313277],"genre_scores_gemma":[0.9949984,0.000013282614,0.0026769289,0.0021342726,0.000118597745,0.0000139069525,0.0000149160505,0.000010715132,0.000018973758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826896,0.000105201456,0.0002778931,0.0006935011,0.00024153515,0.00041292066],"domain_scores_gemma":[0.9988542,0.00014754295,0.00016430084,0.0005505631,0.000069286376,0.00021406359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014061067,0.00022367663,0.0002629158,0.00006797779,0.00017831617,0.0001915279,0.001448465,0.000116184776,0.00006484335],"category_scores_gemma":[0.00009369144,0.00020427186,0.000051042418,0.00019880231,0.0000569092,0.0004866927,0.001007095,0.00045690296,0.00017285284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000585199,0.00015616119,0.010775922,0.0001002258,0.00006096949,0.0006293489,0.0030048012,0.00065698696,0.0059414846,0.08706306,0.0022503575,0.88930213],"study_design_scores_gemma":[0.004268916,0.0030359435,0.113677755,0.00035300644,0.000042378237,0.0001487751,0.00035301162,0.77110773,0.035055794,0.026620805,0.042586252,0.0027496093],"about_ca_topic_score_codex":0.00006832691,"about_ca_topic_score_gemma":0.0000053317435,"teacher_disagreement_score":0.8865526,"about_ca_system_score_codex":0.000022821929,"about_ca_system_score_gemma":0.00008952483,"threshold_uncertainty_score":0.8329964},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087656766,0.00024083776,0.9074626,0.00231654,0.00016195752,0.0004837202,0.00003415641,0.0003735916,0.0012698228],"genre_scores_gemma":[0.62109894,0.0000022833824,0.37808135,0.0004633204,0.00012469378,0.000011761658,0.000045241875,0.000007755677,0.00016466284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987146,0.000018198567,0.00018147015,0.00044297875,0.00026960904,0.00037312802],"domain_scores_gemma":[0.9988756,0.00014485302,0.00013493029,0.0006682501,0.000061774044,0.00011455951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011983667,0.00018552788,0.00018342205,0.00007306572,0.00022146867,0.0003159854,0.0013433906,0.00004851934,0.000010753947],"category_scores_gemma":[0.000038808455,0.00012336938,0.00003814597,0.0001760979,0.00003703959,0.00076772145,0.00016360219,0.00010954329,0.000018478178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008941359,0.000095292315,0.00059986085,0.00003606324,0.000013256432,0.00003375088,0.0008017978,0.0014508837,0.00028821384,0.0013071732,0.0015149687,0.99376935],"study_design_scores_gemma":[0.0053509874,0.006486821,0.04867863,0.00061061117,0.00012491304,0.00038429952,0.00036943922,0.8463272,0.0057703434,0.02227182,0.061178867,0.0024461101],"about_ca_topic_score_codex":0.00002615033,"about_ca_topic_score_gemma":0.00001795469,"teacher_disagreement_score":0.99132323,"about_ca_system_score_codex":0.000011852784,"about_ca_system_score_gemma":0.00007926704,"threshold_uncertainty_score":0.50308573},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014776785,0.00012775505,0.96935564,0.00041154362,0.0004264753,0.0007562273,0.00008440802,0.00025817912,0.013802992],"genre_scores_gemma":[0.055299476,0.000023022696,0.94012696,0.00055050565,0.0007962716,0.00019745348,0.00007195917,0.00003962531,0.00289472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998923,0.0000069109083,0.00026511186,0.00034462893,0.0002054359,0.00025492162],"domain_scores_gemma":[0.99908876,0.0002303026,0.000111954614,0.00040638485,0.000059573336,0.00010299423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022297254,0.00016650805,0.00027233758,0.000012889084,0.00029836316,0.00024749723,0.00034671312,0.0001775929,0.0000064215496],"category_scores_gemma":[0.000018616041,0.00013961911,0.00018042332,0.00006930091,0.00006874368,0.00007350959,0.0004171095,0.00017412358,0.0000031990119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011122227,0.00018333786,0.0000023961438,0.00011878702,0.00012768258,0.000002481671,0.0030252314,0.00001775113,0.016875006,0.85877734,0.025337474,0.0955214],"study_design_scores_gemma":[0.010638061,0.00022317906,0.000015755562,0.00030935727,0.00020313142,0.000054858854,0.0038289523,0.14555414,0.17463218,0.442821,0.22017658,0.0015428151],"about_ca_topic_score_codex":0.0000022748159,"about_ca_topic_score_gemma":0.0000011588482,"teacher_disagreement_score":0.41595635,"about_ca_system_score_codex":0.000013512398,"about_ca_system_score_gemma":0.00009445684,"threshold_uncertainty_score":0.5693502},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34469184,0.00014307676,0.65049434,0.0019408718,0.00035111647,0.00016186097,0.000009310047,0.000117113654,0.002090465],"genre_scores_gemma":[0.9976418,0.00006015184,0.0016256738,0.000059030393,0.000025175921,8.694891e-7,0.0000020424416,0.0000050159974,0.0005802397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926066,0.00008354187,0.00011209166,0.00024176907,0.00017044839,0.00013146143],"domain_scores_gemma":[0.9991823,0.00017012928,0.00011917994,0.00041213483,0.00005652884,0.000059761463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013954642,0.00009728333,0.0001474985,0.000039926326,0.00015117589,0.000033646524,0.00060153456,0.000052242038,0.000021684415],"category_scores_gemma":[0.000014798112,0.000052432562,0.000055696913,0.00020729029,0.00018786026,0.0008959541,0.00071429193,0.00007587815,0.000009073938],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011088641,0.00001984187,0.00012626151,0.0000072986804,0.000020983274,0.000004372341,0.0005711895,0.0000044340845,0.007345835,0.018412225,0.0016880629,0.9716886],"study_design_scores_gemma":[0.028525975,0.0011306301,0.25989535,0.0020117846,0.00017583538,0.00024367854,0.0020875845,0.4726289,0.033350036,0.03566133,0.16272506,0.0015638339],"about_ca_topic_score_codex":0.0001138896,"about_ca_topic_score_gemma":0.0000090563,"teacher_disagreement_score":0.9701248,"about_ca_system_score_codex":0.00003141934,"about_ca_system_score_gemma":0.00002319331,"threshold_uncertainty_score":0.21381378},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62961704,0.00015771326,0.36603883,0.00039729237,0.0008655062,0.00042260106,0.000027249673,0.00044121698,0.0020325566],"genre_scores_gemma":[0.96659654,0.00004955319,0.032931548,0.00007696053,0.00022282873,0.000013678507,0.00003494561,0.000029927305,0.000044001466],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99631333,0.00013331231,0.00084412086,0.0015681111,0.0006754936,0.00046561647],"domain_scores_gemma":[0.996506,0.0001265212,0.00075786846,0.0021871696,0.00018691261,0.00023554893],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00063690834,0.00043154898,0.0007029193,0.00018312577,0.00012723595,0.00009137118,0.00360867,0.00028614566,0.00008556429],"category_scores_gemma":[0.00017994508,0.00045103347,0.00027490305,0.00034004924,0.00007646556,0.00032986235,0.01998302,0.0011646856,0.00024578435],"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":[0.00020776011,0.0009825064,0.74501663,0.0032636146,0.00075428805,0.00047381,0.011086506,0.013197105,0.07917053,0.046259135,0.0007422277,0.0988459],"study_design_scores_gemma":[0.0011725939,0.000077363184,0.46734494,0.0015636033,0.00007041648,0.00004024263,0.00008474896,0.34209096,0.17010696,0.012573145,0.003445334,0.0014296971],"about_ca_topic_score_codex":0.00033248327,"about_ca_topic_score_gemma":0.0000018023701,"teacher_disagreement_score":0.3369795,"about_ca_system_score_codex":0.000093124116,"about_ca_system_score_gemma":0.00023512827,"threshold_uncertainty_score":0.9997941},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008367762,0.00010846006,0.96736306,0.003388204,0.00045311713,0.00010579993,0.00000889502,0.00023771985,0.019967007],"genre_scores_gemma":[0.36173472,0.00003894652,0.6049171,0.0074725044,0.0005448596,0.000061897146,0.00010276258,0.000041076844,0.025086116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986104,0.000029853538,0.00018755789,0.00054976076,0.00032633118,0.00029611032],"domain_scores_gemma":[0.998853,0.00006976956,0.000043284606,0.0007904909,0.000100590005,0.0001428418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001242502,0.00014278461,0.00015316026,0.000042078154,0.0001406715,0.00017612924,0.00070905156,0.00006885947,0.00025318307],"category_scores_gemma":[0.00006387647,0.00010781622,0.000058155405,0.00029370628,0.000023037208,0.00030596444,0.0004591341,0.00016912202,0.00020029188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022737027,0.000712833,0.0006619163,0.000061691564,0.00003919428,0.0006417299,0.0005866086,0.00025567666,0.00410191,0.6287752,0.18096891,0.1831716],"study_design_scores_gemma":[0.0018844445,0.0003955379,0.0068305507,0.00022572176,0.00001658623,0.00021923009,0.00010285118,0.59433365,0.064960666,0.043479733,0.28633308,0.0012179554],"about_ca_topic_score_codex":0.000029229861,"about_ca_topic_score_gemma":0.00010502497,"teacher_disagreement_score":0.59407794,"about_ca_system_score_codex":0.000025783378,"about_ca_system_score_gemma":0.00020615075,"threshold_uncertainty_score":0.43966177},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008193399,0.00077175593,0.98678446,0.00042784866,0.003284584,0.00033873526,0.000032925593,0.00013095255,0.000035338617],"genre_scores_gemma":[0.44183773,0.000020555954,0.55772674,0.00022317297,0.00015819368,0.000009975327,0.0000145479835,0.000008775933,3.3130922e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951112,0.00018973285,0.00068250246,0.0020215262,0.0012972687,0.000697715],"domain_scores_gemma":[0.9957457,0.00034414418,0.00044965092,0.0026725272,0.0005873028,0.00020064911],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0010016207,0.00048116597,0.0007861927,0.0005371186,0.00021565582,0.0006365059,0.0058614877,0.00030833986,0.000020149784],"category_scores_gemma":[0.00013871031,0.0004352494,0.00018524867,0.0020005226,0.0012097857,0.00083237834,0.013554051,0.0011836132,0.0000050175545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007408052,0.00027586296,0.00032018076,0.00009966557,0.000020908268,0.0001225163,0.002597393,0.18006523,0.0007154817,0.0016250837,0.00002399616,0.81412625],"study_design_scores_gemma":[0.0002106583,0.000100595506,0.0027925358,0.00045870722,0.0000046610157,0.000027815538,0.0000017574206,0.9329017,0.014446175,0.048588846,0.000021174408,0.00044538194],"about_ca_topic_score_codex":0.0005598704,"about_ca_topic_score_gemma":0.00007243204,"teacher_disagreement_score":0.8136809,"about_ca_system_score_codex":0.00020223229,"about_ca_system_score_gemma":0.0011520686,"threshold_uncertainty_score":0.9998099},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056879934,0.0020697205,0.93562096,0.00017595544,0.0027770365,0.0009292638,0.0010553965,0.00049025234,0.0000014501057],"genre_scores_gemma":[0.46622604,0.00046794282,0.5323346,0.00023242997,0.00048121967,0.00013744849,0.00003516426,0.00008098814,0.0000041598278],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99563813,0.00019766795,0.00073120085,0.0021848667,0.00061260274,0.00063555525],"domain_scores_gemma":[0.9926771,0.00021330813,0.0006241207,0.0057709767,0.0004925846,0.00022191313],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043995155,0.0005845394,0.0006335418,0.00014745523,0.00038290364,0.0011452964,0.0037538742,0.0003848575,0.00001804415],"category_scores_gemma":[0.00026218925,0.0005883615,0.0001431267,0.00043046122,0.00005002254,0.0012764791,0.006806023,0.0005567713,0.000019311843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004216843,0.00413052,0.022862729,0.008224318,0.0019328007,0.0020538731,0.0004846983,0.06250963,0.83745575,0.01929816,0.03854012,0.0020857381],"study_design_scores_gemma":[0.001177784,0.00008185397,0.05263597,0.00126358,0.00011738,7.601159e-8,0.0000020043274,0.8786687,0.03576677,0.000101308084,0.028534759,0.0016497975],"about_ca_topic_score_codex":0.00021592178,"about_ca_topic_score_gemma":0.0000035911144,"teacher_disagreement_score":0.81615907,"about_ca_system_score_codex":0.0001270357,"about_ca_system_score_gemma":0.00044644668,"threshold_uncertainty_score":0.99989164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011455585,0.00047685372,0.97634447,0.003070334,0.0017166235,0.0005308336,0.00013040165,0.000688223,0.005586679],"genre_scores_gemma":[0.57400554,0.000051193954,0.41946545,0.00493794,0.0003523146,0.00020981557,0.00011866829,0.00006873098,0.00079033413],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997751,0.00015913711,0.0002572753,0.0007390228,0.00066198804,0.00043158192],"domain_scores_gemma":[0.9987618,0.00014621615,0.00011125653,0.0007609245,0.000043744796,0.00017609641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003953428,0.00023068034,0.0002363947,0.00021207982,0.0010937103,0.0002075799,0.0010726113,0.000046605215,0.00014723306],"category_scores_gemma":[0.000010798953,0.00022212535,0.00007284643,0.00052384916,0.000120949175,0.00044586163,0.0019292046,0.0004707908,0.000026170832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019658268,0.00027947355,0.00014495538,0.000010174277,0.000046842993,0.00011012214,0.0005442039,0.00015332398,0.00012919419,0.31475767,0.006797504,0.6770069],"study_design_scores_gemma":[0.001461983,0.0008735747,0.0046104644,0.000023075521,0.0000142121025,0.00031490123,0.00021878956,0.6787039,0.00044598294,0.21052161,0.10195358,0.0008578969],"about_ca_topic_score_codex":0.00012493054,"about_ca_topic_score_gemma":0.0000022269853,"teacher_disagreement_score":0.6785506,"about_ca_system_score_codex":0.00008207976,"about_ca_system_score_gemma":0.000054252574,"threshold_uncertainty_score":0.9058009},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17843771,0.00008858805,0.79634106,0.0054763844,0.001896745,0.0022795522,0.0010274278,0.00041462458,0.014037921],"genre_scores_gemma":[0.9505057,0.00008918678,0.04485586,0.003112164,0.00023311227,0.0001308463,0.0003898039,0.000052135405,0.00063119456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974833,0.00006699484,0.00067661173,0.00033853002,0.0007307982,0.0007037583],"domain_scores_gemma":[0.9961102,0.0002933359,0.0005691727,0.002641792,0.00019279466,0.00019271573],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011892454,0.00034710832,0.0003452037,0.00015119826,0.002187333,0.0020915242,0.003943301,0.00013819347,0.000036065325],"category_scores_gemma":[0.00027651468,0.00022446294,0.00023676126,0.0001309249,0.00016483889,0.0025815908,0.0016349175,0.00061766076,0.00027047598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053011416,0.0010064165,0.01093917,0.0010936806,0.0005660906,0.00008271827,0.015835548,0.00046840755,0.00023739683,0.41703242,0.056657545,0.49555048],"study_design_scores_gemma":[0.0023466782,0.00024933837,0.011363961,0.0005028741,0.000020779678,0.000055405664,0.00020891424,0.8714051,0.0001317594,0.0032731679,0.109831445,0.0006105274],"about_ca_topic_score_codex":0.00001617994,"about_ca_topic_score_gemma":0.000008370008,"teacher_disagreement_score":0.87093675,"about_ca_system_score_codex":0.00007992251,"about_ca_system_score_gemma":0.00006967917,"threshold_uncertainty_score":0.9991117},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005489112,0.00013295296,0.99643815,0.001191649,0.00039774494,0.00042075737,0.00037214253,0.00034418254,0.00015351227],"genre_scores_gemma":[0.02140493,0.000047341593,0.97705275,0.00031812533,0.00015921879,0.00019756707,0.00010999048,0.000045848723,0.00066424214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714917,0.000117685115,0.0003669676,0.00101256,0.0006430766,0.0007105253],"domain_scores_gemma":[0.99691486,0.00046465092,0.00007891282,0.0018484835,0.00038105887,0.00031204778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026461238,0.00036604193,0.00041930916,0.00020331176,0.0007817433,0.0004078637,0.0013847587,0.00011554779,0.00012515971],"category_scores_gemma":[0.000016338754,0.00031253486,0.00020808587,0.00088967144,0.00010964683,0.00078471797,0.00008881642,0.00044482565,0.00005998086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030651918,0.00062750344,0.000010416743,0.000011377284,0.00012351162,0.00007929176,0.00024758044,0.013504919,0.0002581606,0.0005311375,0.0011305517,0.98344487],"study_design_scores_gemma":[0.002784763,0.0006778021,0.00040268732,0.000053914187,0.000053707987,0.00018859943,0.00035813576,0.9496602,0.020465719,0.0005291899,0.024258591,0.0005666983],"about_ca_topic_score_codex":0.00014881439,"about_ca_topic_score_gemma":0.000099965124,"teacher_disagreement_score":0.9828782,"about_ca_system_score_codex":0.00008538899,"about_ca_system_score_gemma":0.00027725767,"threshold_uncertainty_score":0.99993265},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44911194,0.061818305,0.484876,0.00049634086,0.0032491519,0.0002520292,0.000011150329,0.00003694921,0.00014811954],"genre_scores_gemma":[0.99032474,0.005513771,0.002967113,0.00017057674,0.00089446246,0.000002570864,0.0000040835903,0.000012856643,0.000109846485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983819,0.00019407047,0.0005223073,0.00033594173,0.00029235214,0.0002734427],"domain_scores_gemma":[0.9984268,0.00027053783,0.00049392536,0.00025442085,0.00027721538,0.00027708447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047863598,0.0002037915,0.00047527262,0.000088424174,0.0003036888,0.00058667496,0.00025175468,0.00013989683,0.0000034457032],"category_scores_gemma":[0.0000313977,0.00015383291,0.00006122481,0.00013621227,0.000062864296,0.0008100445,0.0003997522,0.000385417,5.183427e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027872415,0.00046116172,0.038273297,0.0013780342,0.00057489355,0.0061475006,0.010395041,0.00794371,0.059466727,0.0045459694,0.012405879,0.8581291],"study_design_scores_gemma":[0.002625409,0.00058415317,0.051691204,0.0033840567,0.00008873747,0.013403163,0.0012069173,0.8976652,0.00049070065,0.00024848024,0.027843578,0.00076841196],"about_ca_topic_score_codex":0.00005840327,"about_ca_topic_score_gemma":0.0000069925704,"teacher_disagreement_score":0.88972145,"about_ca_system_score_codex":0.000026164396,"about_ca_system_score_gemma":0.000047591675,"threshold_uncertainty_score":0.6273124},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11603205,0.000032992655,0.8796986,0.001599356,0.0005393486,0.00013430006,0.000005529867,0.00020791987,0.0017499059],"genre_scores_gemma":[0.8748688,6.774867e-7,0.12412151,0.00087224634,0.0000946829,0.0000043583213,0.000010513578,0.000006714674,0.000020496376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989928,0.000030126439,0.00014479145,0.00032999733,0.00029341053,0.00020888944],"domain_scores_gemma":[0.99926406,0.000043305612,0.000059881124,0.0005012909,0.000037345824,0.00009408834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015027427,0.0001132132,0.00009467814,0.000081524755,0.00017177737,0.00009985182,0.00042091712,0.000040961306,0.000016381706],"category_scores_gemma":[0.000016034703,0.0000958312,0.000052916606,0.00019715067,0.000018601511,0.000089179084,0.0001359239,0.00011262594,0.00020016267],"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":[0.0000316802,0.0006808717,0.000026673715,0.00001675126,0.000010857936,0.000087035565,0.0007338068,0.9363559,0.0071894266,0.016616866,0.0036891242,0.034561034],"study_design_scores_gemma":[0.0011582333,0.0002903526,0.0009180081,0.0001458335,0.000004525979,0.000012902959,0.000020610432,0.9659368,0.027930262,0.0010110254,0.0023282624,0.00024319185],"about_ca_topic_score_codex":0.00004561663,"about_ca_topic_score_gemma":0.0000021825017,"teacher_disagreement_score":0.75883675,"about_ca_system_score_codex":0.00009796098,"about_ca_system_score_gemma":0.000057061952,"threshold_uncertainty_score":0.3907883},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98898023,0.00011579279,0.005643086,0.0028676793,0.00014116148,0.00021221914,0.000009052142,0.000033502885,0.0019972513],"genre_scores_gemma":[0.99356633,0.00003165136,0.0060198735,0.00026795556,0.000021447473,0.000020509593,7.479634e-7,0.000004473598,0.000067020985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900717,0.00001092691,0.00015349693,0.00026412067,0.00039173407,0.00017255539],"domain_scores_gemma":[0.99941444,0.00012675555,0.00011894208,0.0002559141,0.000057187324,0.00002673627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020715961,0.000106078296,0.00012342719,0.000031351323,0.00013021866,0.00012367564,0.00092454656,0.000011923561,0.000007891535],"category_scores_gemma":[0.000045605077,0.000047999467,0.00002947785,0.00031231588,0.000033993238,0.00033007108,0.0008947942,0.000143876,0.0000017556042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003536715,0.00036875118,0.013821284,0.0000956593,0.000042087162,0.00000960576,0.0020853607,0.00007842822,0.04198414,0.9297407,0.0018799346,0.0098586725],"study_design_scores_gemma":[0.0013334011,0.00023103174,0.035562817,0.002769536,0.000026882808,0.00006431035,0.002456913,0.008515589,0.89671326,0.049749915,0.0020413075,0.00053502707],"about_ca_topic_score_codex":0.0000723674,"about_ca_topic_score_gemma":0.000011594631,"teacher_disagreement_score":0.8799908,"about_ca_system_score_codex":0.000024755931,"about_ca_system_score_gemma":0.000032156273,"threshold_uncertainty_score":0.19573614},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003165173,0.00004810159,0.99285644,0.0049971193,0.00040171685,0.00013495023,0.000089205176,0.00019062335,0.0009653519],"genre_scores_gemma":[0.23878184,0.000026145046,0.7472363,0.009681297,0.0030366166,0.000023666735,0.00074765633,0.00002844772,0.0004380057],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904954,0.000021372374,0.0001342325,0.00044399855,0.0001789727,0.00017189581],"domain_scores_gemma":[0.99915314,0.000060298506,0.00004595664,0.0006091946,0.00003287669,0.00009855007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009877135,0.000087195076,0.00011930746,0.000017018796,0.00019248613,0.00013865413,0.001918322,0.000041611886,0.00002467542],"category_scores_gemma":[0.000030560754,0.00006712516,0.000030560317,0.0001290808,0.000017928896,0.00062267564,0.002224014,0.00006604579,0.00005052755],"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":[0.000024869381,0.00005215026,0.00003488235,0.000022095604,0.0000096446465,0.0000051646225,0.00025645064,0.000014497691,0.0019291647,0.014323357,0.613627,0.36970073],"study_design_scores_gemma":[0.00037846022,0.000040392864,0.00022959453,0.0000060221837,0.000003219433,9.2924415e-7,0.000014332566,0.6419703,0.0006923447,0.0006029467,0.35594785,0.000113601374],"about_ca_topic_score_codex":0.000015022536,"about_ca_topic_score_gemma":0.0000015963783,"teacher_disagreement_score":0.6419558,"about_ca_system_score_codex":0.000005315897,"about_ca_system_score_gemma":0.000041461193,"threshold_uncertainty_score":0.35647514},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008774438,0.000056701105,0.988194,0.0018306327,0.0003908204,0.000031711654,0.000011163745,0.000010300564,0.0007002353],"genre_scores_gemma":[0.98286897,0.00016822826,0.015446886,0.0014630377,0.00003073605,9.3766283e-7,0.0000108260265,0.0000010876406,0.000009278445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922085,0.00003120487,0.0004053779,0.00002608002,0.00023111187,0.0000853896],"domain_scores_gemma":[0.9989418,0.000050992207,0.0003647153,0.00019753246,0.00039040908,0.000054599303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002202672,0.000057756384,0.00008483026,0.000055184762,0.00012715919,0.000491697,0.00041963026,0.000026956885,0.00001886381],"category_scores_gemma":[0.00028771316,0.000035435052,0.000039724415,0.0001987215,0.000030288731,0.0074540367,0.0003624482,0.0001332901,0.000013163587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037183996,0.000045936256,0.0021858427,0.00012707015,0.000051228733,0.000008759132,0.007213858,0.0043327175,0.00020967427,0.1511543,0.008534767,0.8260987],"study_design_scores_gemma":[0.0018095894,0.00013576806,0.031480156,0.00048188894,0.000021793852,0.0014863254,0.000996935,0.69702315,0.003805692,0.019855086,0.24255852,0.0003450738],"about_ca_topic_score_codex":0.0000028283519,"about_ca_topic_score_gemma":5.581011e-7,"teacher_disagreement_score":0.97409457,"about_ca_system_score_codex":0.000018902376,"about_ca_system_score_gemma":0.00014384669,"threshold_uncertainty_score":0.5403997},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014032379,0.00003127708,0.97868395,0.00014116752,0.00016199591,0.00019472135,0.00023400951,0.00008281202,0.0064376877],"genre_scores_gemma":[0.787764,0.000038032333,0.21172732,0.0000144819205,0.000027563217,9.336624e-7,0.00016200611,0.00000327812,0.00026234853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801356,0.00018024932,0.0002441112,0.00022914933,0.0010254893,0.00030746637],"domain_scores_gemma":[0.9977088,0.000113838105,0.00019487913,0.00059078203,0.0012109426,0.00018075027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070481363,0.00011399623,0.00022570566,0.00033132965,0.00068349903,0.00022521468,0.0009334297,0.00007852895,0.000040065977],"category_scores_gemma":[0.00008544067,0.0001090597,0.00003240626,0.00081062637,0.0002015283,0.0032361716,0.00071168283,0.00026710413,0.00013357033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061930116,0.0005093433,0.0013871528,0.0035625524,0.0004031295,0.0012894137,0.061732233,0.0115808295,0.0035368423,0.61897683,0.01195716,0.28444523],"study_design_scores_gemma":[0.010203689,0.0009968376,0.02946433,0.0022066426,0.000054956457,0.0003535537,0.121245205,0.587509,0.0017771274,0.0004518661,0.24437039,0.0013664325],"about_ca_topic_score_codex":0.0014346112,"about_ca_topic_score_gemma":0.00024830812,"teacher_disagreement_score":0.77373165,"about_ca_system_score_codex":0.00018475643,"about_ca_system_score_gemma":0.0008523752,"threshold_uncertainty_score":0.5256991},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018912683,0.0006242048,0.99829847,0.00019308763,0.000017300523,0.000053128384,0.000019915271,0.000041409592,0.0005633602],"genre_scores_gemma":[0.089751214,0.00007179333,0.9096856,0.00026684624,0.00004391826,0.0000046953105,0.00008631043,0.0000037173163,0.00008591074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933034,0.000013100227,0.00013115896,0.0002978191,0.00014487641,0.00008272667],"domain_scores_gemma":[0.99823934,0.000014868842,0.000036154823,0.0015361662,0.00010343088,0.00007004499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011132328,0.000043023945,0.000077847355,0.000029851495,0.000055218,0.00010864528,0.0011873613,0.000014159018,0.000019855586],"category_scores_gemma":[0.00001024211,0.000037165664,0.000008726601,0.0005150426,0.0000057738225,0.0006990144,0.0010671386,0.000031310443,0.0000065974814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.1115018e-7,0.0001198017,0.00017212812,0.000055485456,0.000004787236,0.0000028771256,0.00007227334,0.00031789407,0.0026323076,0.05039159,0.0011763388,0.9450541],"study_design_scores_gemma":[0.00006349942,0.000015159607,0.0011406584,0.000054223892,0.0000061549185,0.0000050912013,0.000051369527,0.9509973,0.005065354,0.0012863578,0.0412106,0.00010422503],"about_ca_topic_score_codex":0.000017471057,"about_ca_topic_score_gemma":0.000013197794,"teacher_disagreement_score":0.9506794,"about_ca_system_score_codex":0.0000057012176,"about_ca_system_score_gemma":0.00009895162,"threshold_uncertainty_score":0.22064325},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001800964,0.0020081513,0.5095618,0.00079506397,0.002131369,0.00707898,0.0010175465,0.00082189246,0.47478426],"genre_scores_gemma":[0.00034990074,0.00015939034,0.7937818,0.00047432806,0.001215054,0.00016028929,0.00027657772,0.0001191769,0.2034635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998252,0.000004032807,0.00045926013,0.00064428075,0.0003634103,0.000277025],"domain_scores_gemma":[0.9986311,0.00033313298,0.00030698878,0.00047510586,0.00008338838,0.00017027916],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034416726,0.0004133069,0.0006188951,0.0000340789,0.00040151738,0.00020065195,0.0003109722,0.0007183531,0.000013851691],"category_scores_gemma":[0.000014851816,0.0003522477,0.0002709959,0.000016795278,0.000169793,0.000060783936,0.0012560568,0.00047584288,0.0000032800094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008005561,0.00002296606,4.969528e-8,0.00013930893,0.00013660717,0.00000197088,0.0006615448,6.131617e-7,0.00065424433,0.9529452,0.0071399068,0.038289625],"study_design_scores_gemma":[0.0052819834,0.0001617094,5.2178945e-7,0.0009368363,0.00030314922,0.00005257765,0.0003287112,0.013288661,0.0029703826,0.56100345,0.41409215,0.001579866],"about_ca_topic_score_codex":0.0000021667822,"about_ca_topic_score_gemma":8.0959956e-7,"teacher_disagreement_score":0.40695223,"about_ca_system_score_codex":0.000031294352,"about_ca_system_score_gemma":0.000152129,"threshold_uncertainty_score":0.99989295},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025566385,0.001249258,0.99487925,0.0007065427,0.0015295694,0.0004691569,0.00003090079,0.00013517692,0.0009745743],"genre_scores_gemma":[0.0030219678,0.00008439893,0.99501157,0.00089253514,0.00054074737,0.000015518908,0.000034490575,0.000032493946,0.00036627604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99619234,0.000032900793,0.00047165214,0.0018955908,0.0007497647,0.0006577463],"domain_scores_gemma":[0.99712646,0.00065321004,0.0002585672,0.0014133905,0.00032113402,0.00022724686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080699637,0.0005164897,0.0006374323,0.00043234986,0.0004917366,0.0008908927,0.0023897935,0.00028428127,0.000013185683],"category_scores_gemma":[0.0001100629,0.00046786288,0.00012142219,0.00036719235,0.00074437883,0.00076577,0.003069363,0.00059768115,0.000005488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034777981,0.000021168144,0.000015186071,0.000056676614,0.000009735286,0.000055144712,0.0002674374,0.0010302606,0.00009161118,0.04220625,0.000057323698,0.9561857],"study_design_scores_gemma":[0.00037644012,0.00013567998,0.00015254154,0.00044792215,0.000007671952,0.000096477124,2.6810787e-7,0.8393177,0.0005457841,0.15073241,0.007590961,0.0005961376],"about_ca_topic_score_codex":0.000029149607,"about_ca_topic_score_gemma":0.000070859096,"teacher_disagreement_score":0.9555896,"about_ca_system_score_codex":0.00013629791,"about_ca_system_score_gemma":0.00041718007,"threshold_uncertainty_score":0.9997773},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030908266,0.00023823361,0.9549515,0.00032404688,0.000695303,0.00053417176,0.000087237575,0.00016619131,0.012095026],"genre_scores_gemma":[0.95596284,0.00010250426,0.04359157,0.00002062555,0.00007548669,0.0000018364757,0.00018887976,0.000005782903,0.000050466442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969717,0.00037504328,0.00043947427,0.0004568606,0.0013605894,0.00039631577],"domain_scores_gemma":[0.99676317,0.0001922379,0.0004561742,0.0011362077,0.0011933122,0.00025887613],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017392499,0.00021993145,0.0004918227,0.00083188096,0.00092521554,0.0007714397,0.0016997396,0.00036114157,0.000013050642],"category_scores_gemma":[0.00022470241,0.0002527983,0.00009939917,0.0005961032,0.00036157478,0.004188735,0.007114585,0.0006207282,0.000025651836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006157809,0.0003698088,0.0021966237,0.024717677,0.0008469265,0.0011416745,0.11575385,0.02211953,0.0036843454,0.23221457,0.03352547,0.56281376],"study_design_scores_gemma":[0.0022234113,0.00013327849,0.0037077225,0.0064967736,0.00003496143,0.00009488935,0.02143677,0.91674,0.000628055,0.00021992158,0.047503058,0.00078118837],"about_ca_topic_score_codex":0.0020008932,"about_ca_topic_score_gemma":0.00003675675,"teacher_disagreement_score":0.9250546,"about_ca_system_score_codex":0.00029869247,"about_ca_system_score_gemma":0.0009207527,"threshold_uncertainty_score":0.99999243},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004152713,0.0004640158,0.99604416,0.00087617215,0.00082123006,0.00058726524,0.000073554824,0.00013462291,0.0005836938],"genre_scores_gemma":[0.071699984,0.000075328346,0.9249966,0.0011664319,0.00050134177,0.00003995021,0.000107585285,0.00006160677,0.0013511428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963552,0.000029844945,0.00038781736,0.0017362143,0.0008876384,0.00060333335],"domain_scores_gemma":[0.99675155,0.00051299605,0.00036066264,0.001302617,0.00085149345,0.00022067523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031871255,0.00050520396,0.00052209315,0.000462707,0.00046476268,0.0007673258,0.0024443436,0.0002474326,0.000025235277],"category_scores_gemma":[0.000127019,0.00041954766,0.000115906754,0.000617546,0.00031681714,0.0009977961,0.0014098427,0.000562395,0.000018776343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007663533,0.00019858852,0.0002639693,0.00021114573,0.0000843387,0.00061261194,0.0022133011,0.13090287,0.00031024855,0.041776285,0.0002839815,0.823066],"study_design_scores_gemma":[0.0011482162,0.00045995347,0.0004864276,0.0012949841,0.00002598342,0.00019873363,0.000006154479,0.97086155,0.001024014,0.015875563,0.0076064253,0.0010120193],"about_ca_topic_score_codex":0.00011048941,"about_ca_topic_score_gemma":0.0003428464,"teacher_disagreement_score":0.83995867,"about_ca_system_score_codex":0.00026808403,"about_ca_system_score_gemma":0.00091602275,"threshold_uncertainty_score":0.99982566},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006469575,0.00019232568,0.9872092,0.0005787958,0.0003590403,0.000044646742,0.000004501802,0.00019897558,0.010765526],"genre_scores_gemma":[0.74961066,0.000023690178,0.24642009,0.00062751275,0.000106073836,0.000004356538,0.000020246964,0.000011729394,0.0031756444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998983,0.000041034764,0.00012447334,0.00037989684,0.0002660983,0.00020546744],"domain_scores_gemma":[0.99900174,0.000046327976,0.00003364443,0.0006808369,0.00010950916,0.0001279563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005161272,0.00010714116,0.00012142381,0.000052724932,0.0001494665,0.00012862943,0.0006259744,0.000046580702,0.000085719446],"category_scores_gemma":[0.0000061671144,0.00008780091,0.00005379317,0.0003257199,0.000024964851,0.00073524675,0.0008477317,0.000107378175,0.000044759487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011568463,0.00033131978,0.000013908706,0.00001574672,0.000044915858,0.00041510424,0.0006170101,0.09173227,0.0024605712,0.8073336,0.04626965,0.050754357],"study_design_scores_gemma":[0.00033208038,0.000020714873,0.00006198323,0.000030650022,0.000004092218,0.000062286024,0.00006245619,0.96893406,0.000792188,0.02691973,0.0026072536,0.00017247995],"about_ca_topic_score_codex":0.000022361884,"about_ca_topic_score_gemma":0.0000039476545,"teacher_disagreement_score":0.8772018,"about_ca_system_score_codex":0.000013441048,"about_ca_system_score_gemma":0.00008541391,"threshold_uncertainty_score":0.35804173},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036922034,0.0009104336,0.9507645,0.00048007348,0.0018213557,0.0020623426,0.006323019,0.00033831643,0.00037794956],"genre_scores_gemma":[0.089616425,0.00046500488,0.88251066,0.00073780405,0.0010267879,0.00013637201,0.024491448,0.00016452724,0.00085097394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955182,0.000087869,0.00135128,0.0012598598,0.0007778593,0.0010049014],"domain_scores_gemma":[0.9940155,0.00052167464,0.00092994637,0.0036527566,0.00035494025,0.00052518985],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00051347865,0.0010072769,0.0013243417,0.00037517707,0.00058499177,0.0023312618,0.005612273,0.0006667014,0.000026099404],"category_scores_gemma":[0.00015267398,0.0009037728,0.00038069233,0.00022644739,0.0002205468,0.0031435548,0.0105054835,0.0008632218,0.000005584618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019169699,0.00114033,0.0031172656,0.005853039,0.002880419,0.00009113294,0.04139351,0.008358068,0.00025997666,0.0066600996,0.2040462,0.724283],"study_design_scores_gemma":[0.0067758304,0.00031824532,0.0014136353,0.00051774736,0.00025330274,0.00008669955,0.002162495,0.8452858,0.00028816235,0.00049085484,0.14113648,0.0012707784],"about_ca_topic_score_codex":0.0002602237,"about_ca_topic_score_gemma":0.00026886677,"teacher_disagreement_score":0.8369277,"about_ca_system_score_codex":0.00012593057,"about_ca_system_score_gemma":0.00050603383,"threshold_uncertainty_score":0.99976784},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9582801,0.0002160109,0.022147631,0.00403226,0.00082453573,0.00032248604,0.000008171796,0.00066324807,0.013505568],"genre_scores_gemma":[0.9637195,0.00006575233,0.03481515,0.000514392,0.00040787662,0.000016189822,0.0000013146887,0.000015434287,0.00044439113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987382,0.0000052008218,0.00017263771,0.0004930038,0.0002636484,0.0003272851],"domain_scores_gemma":[0.99936354,0.000036161153,0.000094971045,0.00020925594,0.00018096917,0.00011512183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019181834,0.00018128964,0.00015787268,0.000084628395,0.00034657362,0.0005078954,0.0005292417,0.00007389446,0.000013044384],"category_scores_gemma":[0.00007113529,0.00015187335,0.000024789864,0.00026173182,0.00014101312,0.002224397,0.00046889603,0.00014785644,0.000070097085],"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":[0.00048206808,0.00032681698,0.015100557,0.0003944981,0.000085154476,0.00005591425,0.033930086,0.0000055710993,0.071072534,0.5163812,0.039025106,0.32314047],"study_design_scores_gemma":[0.0018511948,0.002601425,0.03136992,0.0008160119,0.000038286296,0.00034214868,0.0017418318,0.022819266,0.36500812,0.026106602,0.54538727,0.0019179602],"about_ca_topic_score_codex":0.000027836373,"about_ca_topic_score_gemma":0.0000065055706,"teacher_disagreement_score":0.50636214,"about_ca_system_score_codex":0.000020584816,"about_ca_system_score_gemma":0.00002672551,"threshold_uncertainty_score":0.6193215},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28571123,0.0011429198,0.7108637,0.0008317097,0.0007568922,0.0002453447,0.000053504984,0.00015075844,0.0002439231],"genre_scores_gemma":[0.5980129,0.0010932133,0.40024847,0.00035584185,0.00006620223,0.00008092162,0.00004780596,0.00001995001,0.00007464164],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809676,0.0001105234,0.00033749308,0.00081513746,0.00037676224,0.0002633443],"domain_scores_gemma":[0.9977928,0.0003457964,0.00037722714,0.0010374098,0.0002976056,0.00014915415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017275252,0.00027024338,0.00034547565,0.00012799192,0.0002849407,0.00042552146,0.0007504619,0.00016881316,0.000048864375],"category_scores_gemma":[0.00019741514,0.00022567538,0.0000709479,0.00029366894,0.00019504174,0.002795517,0.0010391498,0.00062092143,0.000001921798],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047366007,0.0021280127,0.006203844,0.0025982566,0.0010274366,0.0006673059,0.5188044,0.0023290068,0.022981152,0.01648241,0.0009669632,0.42533758],"study_design_scores_gemma":[0.008504389,0.003355236,0.041001722,0.01444895,0.0014878842,0.009945011,0.24728575,0.056296352,0.07641231,0.006385112,0.5209576,0.013919712],"about_ca_topic_score_codex":0.00019197726,"about_ca_topic_score_gemma":0.00003201201,"teacher_disagreement_score":0.5199906,"about_ca_system_score_codex":0.000029582832,"about_ca_system_score_gemma":0.00033137348,"threshold_uncertainty_score":0.9202775},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048606336,0.0028121201,0.9895012,0.002174166,0.0018703119,0.00048654305,0.000036514215,0.00021930416,0.0024137713],"genre_scores_gemma":[0.122210994,0.00074440177,0.86294746,0.009808029,0.0015257531,0.00006703186,0.00016679609,0.00016102177,0.0023685156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99469054,0.00017215917,0.000731265,0.0021314665,0.001352341,0.00092220784],"domain_scores_gemma":[0.995463,0.00086126185,0.00034190182,0.002744952,0.0004027278,0.00018615795],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011122171,0.00072443933,0.000730269,0.00079233735,0.00045325392,0.00090457615,0.005289309,0.0004421166,0.000054138734],"category_scores_gemma":[0.00023597007,0.0005083119,0.00013931624,0.002049473,0.00074055983,0.00080993737,0.0038479434,0.0016653367,0.0000429588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028616427,0.00018835303,0.0003154179,0.00008762404,0.000041013536,0.0021452764,0.0031773024,0.041069183,0.0022216316,0.021507433,0.0010518491,0.9281663],"study_design_scores_gemma":[0.0011496266,0.00039409724,0.0027358786,0.002101588,0.000024425426,0.00042089418,0.0000058803985,0.9020949,0.003347174,0.044325292,0.041169625,0.0022306156],"about_ca_topic_score_codex":0.00018883745,"about_ca_topic_score_gemma":0.0015285511,"teacher_disagreement_score":0.9259357,"about_ca_system_score_codex":0.00028189248,"about_ca_system_score_gemma":0.00095820933,"threshold_uncertainty_score":0.99973685},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00904484,0.00062825077,0.98925763,0.00048581863,0.00037904238,0.000065067725,0.000108308835,0.000008714611,0.000022330967],"genre_scores_gemma":[0.08164447,0.00023390999,0.917107,0.00045485597,0.00009535207,9.041375e-7,0.00045159674,0.0000034373388,0.00000847801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989768,0.000042839572,0.0005728714,0.00012961496,0.0001506018,0.00012723789],"domain_scores_gemma":[0.99853045,0.00038675635,0.0004648614,0.00024213904,0.00031773868,0.000058076894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026307,0.000089959976,0.00019868951,0.000062452316,0.00012580321,0.00011368756,0.00045893792,0.00004820405,0.0000043497053],"category_scores_gemma":[0.000091532565,0.000067693036,0.000041978456,0.00010414252,0.000028294224,0.0007404661,0.00043973743,0.00008654092,0.0000017258066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012852426,0.00031063397,0.0030572065,0.00023491606,0.0002415369,0.000061380815,0.001338602,0.11228961,0.00048509752,0.100902684,0.008998459,0.7719514],"study_design_scores_gemma":[0.00060511206,0.00014294357,0.0028916523,0.000035443292,0.000009207252,0.00022489854,0.000020312338,0.9077984,0.000044637378,0.07821823,0.009924853,0.00008428916],"about_ca_topic_score_codex":0.00000395009,"about_ca_topic_score_gemma":6.653696e-7,"teacher_disagreement_score":0.7955088,"about_ca_system_score_codex":0.000010317073,"about_ca_system_score_gemma":0.00010338433,"threshold_uncertainty_score":0.2760442},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5388342,0.000015317473,0.4594725,0.00008942382,0.00011894447,0.000042215248,0.000019215506,0.000049718936,0.001358422],"genre_scores_gemma":[0.9932853,0.00004261092,0.005712759,0.00004812337,0.000015193876,1.6475572e-7,0.000009828229,0.0000055625665,0.00088046206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999264,0.000043441785,0.00009694263,0.00037664923,0.000058393183,0.00016059473],"domain_scores_gemma":[0.9991454,0.000044246884,0.0000684802,0.00053808995,0.0001136583,0.000090108406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048023285,0.0000977008,0.00013129537,0.000110579174,0.00015569245,0.000035331144,0.00042832262,0.000043787644,0.000094442796],"category_scores_gemma":[0.0000043435575,0.00009174048,0.000060762024,0.00069708045,0.000072947136,0.00080541585,0.00014958998,0.00012020018,0.000011049314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071319366,0.00049603527,0.009628048,0.000099659774,0.0002485657,0.0005964423,0.0017896821,0.029735487,0.03549766,0.9142744,0.00049511006,0.0070675905],"study_design_scores_gemma":[0.0064952257,0.00068587146,0.060771577,0.00052322535,0.00027820183,0.00043155078,0.003109237,0.79869586,0.05936243,0.017149335,0.05039139,0.002106091],"about_ca_topic_score_codex":0.000022496259,"about_ca_topic_score_gemma":0.000067404915,"teacher_disagreement_score":0.89712507,"about_ca_system_score_codex":0.000028513594,"about_ca_system_score_gemma":0.000110813504,"threshold_uncertainty_score":0.37410682},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095513166,0.00028184292,0.99005926,0.00070825947,0.002628257,0.0007235035,0.00014069527,0.00029106459,0.0042119627],"genre_scores_gemma":[0.028827315,0.00006212663,0.96661067,0.0005843037,0.0003233426,0.0005516338,0.001462932,0.0000330654,0.0015445834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979306,0.0000894962,0.00034351915,0.0009221622,0.00041751264,0.00029671873],"domain_scores_gemma":[0.9980562,0.00013474355,0.00021641773,0.0013900716,0.00009153596,0.00011104629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029392482,0.00026916878,0.00030287865,0.00013986736,0.00038762976,0.00033011986,0.0019933905,0.00016846565,0.00068180443],"category_scores_gemma":[0.000011682527,0.0002343507,0.0001912022,0.00010467462,0.000018836763,0.00032536153,0.007694897,0.0004548283,0.000028505443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012427215,0.00097086985,0.00017500977,0.00047716466,0.00015354888,0.000041417214,0.0008605466,0.024496535,0.0029329965,0.110251755,0.312136,0.5473799],"study_design_scores_gemma":[0.00045065678,0.00010245759,0.00052992324,0.00009369567,0.000014971718,0.000007865918,0.000014750461,0.7990847,0.0011589396,0.020817872,0.17724438,0.0004797758],"about_ca_topic_score_codex":0.00007234347,"about_ca_topic_score_gemma":0.0000025498828,"teacher_disagreement_score":0.77458817,"about_ca_system_score_codex":0.000104700266,"about_ca_system_score_gemma":0.00011421998,"threshold_uncertainty_score":0.95911384},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094027416,0.00004732203,0.9775656,0.00019697557,0.0019067728,0.00020266944,0.00019617529,0.00034398652,0.018600238],"genre_scores_gemma":[0.03835465,0.000034220033,0.9580331,0.00095784373,0.00026354403,0.000017264898,0.00035992035,0.000029108582,0.0019503616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775594,0.00014357266,0.0003235364,0.0009068876,0.00059008185,0.00027998578],"domain_scores_gemma":[0.9980416,0.0002673929,0.00025070255,0.0012825048,0.00006644823,0.00009134419],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003784733,0.00025571106,0.00027082497,0.0001245652,0.00035266942,0.00040766565,0.0017321986,0.00008914487,0.00040173804],"category_scores_gemma":[0.000033947203,0.00023165613,0.00006559158,0.00011492876,0.000020914553,0.00012433284,0.010752515,0.0009985301,0.00006986078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009299558,0.0001847458,0.00010106825,0.000108153734,0.000050457562,0.0003108809,0.001652933,0.03970249,0.000012993987,0.7066623,0.026774356,0.2244303],"study_design_scores_gemma":[0.00021789662,0.00013141424,0.0016423654,0.00026563008,0.00000934706,0.000016060196,0.000110048306,0.86410785,0.000069981295,0.11528545,0.017453818,0.0006901128],"about_ca_topic_score_codex":0.00024170672,"about_ca_topic_score_gemma":0.000004431771,"teacher_disagreement_score":0.8244054,"about_ca_system_score_codex":0.00012292183,"about_ca_system_score_gemma":0.00014811444,"threshold_uncertainty_score":0.99724835},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010979624,0.00008697955,0.9234628,0.0061830445,0.00013138607,0.0002500067,0.000079590776,0.0019956445,0.06671255],"genre_scores_gemma":[0.93701494,0.00017549032,0.05077191,0.0055413274,0.0010618942,7.543079e-8,0.0019506947,0.0023715587,0.0011121129],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853724,0.000164911,0.00017741606,0.00047368032,0.00035647006,0.00029029665],"domain_scores_gemma":[0.9988545,0.00001425594,0.000066000866,0.00053576095,0.00024424278,0.00028520974],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027074612,0.00011178368,0.00011034533,0.00007718292,0.0013061924,0.0011017452,0.002440324,0.0000439656,0.0034003695],"category_scores_gemma":[0.00026769922,0.000109183406,0.00004124357,0.000566852,0.00005297401,0.00060511456,0.003239331,0.00020687484,0.012087632],"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":[0.000020309128,0.00007738071,9.1906236e-7,0.00003040999,0.000017268138,0.00003581059,0.0011760835,0.000065975124,0.00637375,0.041228827,0.49988544,0.45108783],"study_design_scores_gemma":[0.0002608943,0.00018694757,0.00006180395,0.000009533127,0.000002482711,0.000040431838,0.00004067517,0.02598186,0.0007748716,0.00047399086,0.97202754,0.00013897385],"about_ca_topic_score_codex":0.000004859406,"about_ca_topic_score_gemma":2.1241428e-8,"teacher_disagreement_score":0.93591696,"about_ca_system_score_codex":0.000039361075,"about_ca_system_score_gemma":0.000003005889,"threshold_uncertainty_score":0.999994},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027343602,0.00060469744,0.9968832,0.00062709104,0.000049817627,0.0012919462,0.00011798233,0.00004009017,0.00011171034],"genre_scores_gemma":[0.063484244,0.0006359767,0.9342229,0.00019516244,0.000079574944,0.001068747,0.0002661265,0.0000096086005,0.00003767943],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989307,0.0001413662,0.00020054015,0.00048016725,0.00013406892,0.00011318803],"domain_scores_gemma":[0.9966669,0.0018025486,0.00021790645,0.001025334,0.0002320625,0.000055227487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004891891,0.00009225497,0.0001375343,0.000039146304,0.00029097986,0.00008175591,0.0006739665,0.000060849172,0.0000050954914],"category_scores_gemma":[0.0002094534,0.00007914795,0.000017451224,0.00022200521,0.00004522758,0.00089765183,0.001032942,0.00009028936,0.000004134058],"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":[0.000033817672,0.00027939686,0.000028895956,0.000060699567,0.000018296298,0.0000029640528,0.00013179204,0.0001722665,0.83258843,0.008165657,0.0017029295,0.15681483],"study_design_scores_gemma":[0.0009979693,0.00017278528,0.0006972753,0.00017012104,0.00009019619,0.00014522026,0.0003652281,0.3202349,0.36306223,0.008994672,0.30467206,0.00039735952],"about_ca_topic_score_codex":0.000030380477,"about_ca_topic_score_gemma":0.000001856857,"teacher_disagreement_score":0.46952623,"about_ca_system_score_codex":0.000011134524,"about_ca_system_score_gemma":0.00010219768,"threshold_uncertainty_score":0.32275596},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022157803,0.0016397932,0.4044534,0.000073756775,0.0008559952,0.00023229125,0.00032814546,0.00022320445,0.5921912],"genre_scores_gemma":[0.00023480818,0.0021437977,0.3569519,0.0004859695,0.00037953383,0.0000033069102,0.0016197654,0.000055195185,0.6381257],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985851,0.0000087701965,0.00021635804,0.0007347219,0.00027128213,0.00018375633],"domain_scores_gemma":[0.9977482,0.000053362175,0.0001234421,0.0018741407,0.000039655162,0.00016117614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011190127,0.00024035567,0.0002485584,0.00011218569,0.00007662019,0.00010832423,0.0019950182,0.000165276,0.00038230477],"category_scores_gemma":[0.000006157089,0.00018659822,0.00002613702,0.000018998793,0.000055417993,0.0005616125,0.004260659,0.00021113936,0.00047279592],"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":[0.0000052790724,0.00004403473,0.00001686272,0.000028573413,0.00005726888,0.000097612276,0.00006841105,1.18662456e-7,0.000010967446,0.2893813,0.0785689,0.63172066],"study_design_scores_gemma":[0.00025942444,0.00002400035,0.0001828268,0.00006779768,0.00001621124,0.00002700038,3.525495e-7,0.05562043,0.000005424032,0.011599369,0.9318599,0.00033722603],"about_ca_topic_score_codex":0.00006013725,"about_ca_topic_score_gemma":0.000005103435,"teacher_disagreement_score":0.85329103,"about_ca_system_score_codex":0.000010955862,"about_ca_system_score_gemma":0.000029239993,"threshold_uncertainty_score":0.7609255},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014272933,0.00013163014,0.99197644,0.0014803684,0.004005125,0.00054420653,0.00000886238,0.000092981805,0.0003331014],"genre_scores_gemma":[0.0057154913,0.00013447856,0.9925754,0.00014619519,0.00072521355,0.00023160984,0.00006871864,0.000025768184,0.00037709027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978481,0.000054812834,0.0005763017,0.00065465574,0.00055432494,0.00031180726],"domain_scores_gemma":[0.9980193,0.00005333502,0.00023276766,0.0015089638,0.00009967334,0.00008599601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088601006,0.0002921531,0.00031425603,0.00019295643,0.0001154971,0.00028130485,0.002467739,0.00011197389,0.000006103448],"category_scores_gemma":[0.00015182504,0.00020396296,0.000049891612,0.00025865834,0.000019587955,0.00014954047,0.004727999,0.0005952564,0.00021949409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004560353,0.0006655175,0.0000867869,0.0011114959,0.00004903063,0.0000031101692,0.018311994,0.17207704,0.000017353945,0.0776695,0.24266262,0.487341],"study_design_scores_gemma":[0.000093068644,0.0000045586535,0.00012413759,0.00043477223,0.0000050872263,0.0000027332665,0.000016505208,0.8814734,0.000046663823,0.057966385,0.059523676,0.00030901402],"about_ca_topic_score_codex":0.0000017741437,"about_ca_topic_score_gemma":0.0000028840852,"teacher_disagreement_score":0.70939636,"about_ca_system_score_codex":0.0001600791,"about_ca_system_score_gemma":0.00021017453,"threshold_uncertainty_score":0.8317368},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25561148,0.0003283617,0.74072677,0.0020771257,0.0004521734,0.00022115196,0.000007198407,0.00017173143,0.00040397941],"genre_scores_gemma":[0.91334367,0.00016486428,0.08556841,0.0008013536,0.00008055279,0.000008003293,0.000009115237,0.000016326352,0.0000076856495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977753,0.000064037114,0.00041866413,0.00085166603,0.00039729415,0.00049304636],"domain_scores_gemma":[0.99896866,0.00005318599,0.00015128765,0.00043766104,0.00017800249,0.00021118771],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003304932,0.00033085138,0.0003201105,0.00054628163,0.00041964784,0.0017376941,0.0008154771,0.00013440441,0.000008178799],"category_scores_gemma":[0.000012305933,0.00027863958,0.00005878225,0.000560245,0.00014965294,0.002154818,0.000479029,0.00041923887,0.00001645661],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005543394,0.00045876348,0.00228943,0.00024486714,0.000020387875,0.00055239984,0.010094199,0.00014954587,0.0036965178,0.07338809,0.00022202184,0.9088283],"study_design_scores_gemma":[0.0034669915,0.0010949078,0.056059096,0.004564653,0.000012128874,0.0003194395,0.00018917811,0.8143365,0.002382432,0.114542484,0.0012488278,0.0017833958],"about_ca_topic_score_codex":0.00008806406,"about_ca_topic_score_gemma":0.000029680628,"teacher_disagreement_score":0.90704495,"about_ca_system_score_codex":0.000037085916,"about_ca_system_score_gemma":0.00021019814,"threshold_uncertainty_score":0.99996656},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8744345,0.0038748495,0.066814765,0.0144593455,0.010280262,0.003434639,0.0010433671,0.0054538394,0.02020443],"genre_scores_gemma":[0.9740274,0.00005320569,0.021237541,0.0011622015,0.00058666395,0.000022676852,0.00056512957,0.000025532163,0.0023196295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995777,0.00006927645,0.00073857576,0.0013543881,0.0012308484,0.0008299034],"domain_scores_gemma":[0.995006,0.000077747565,0.00024687714,0.0040334305,0.00011000004,0.0005259403],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037879884,0.00035289983,0.00040311992,0.000036138827,0.00026457792,0.00027593915,0.0026986508,0.00026100568,0.00039799925],"category_scores_gemma":[0.00011464856,0.0002675806,0.00010090671,0.0005629242,0.000058459274,0.0011523961,0.0014764118,0.00056001416,0.000020289322],"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":[0.000024604655,0.00041728464,0.0027309938,0.000048344904,0.00006327525,0.0059341723,0.000111165435,0.00024671017,0.0022312417,0.00044130467,0.8408521,0.14689879],"study_design_scores_gemma":[0.00041657043,0.00010355202,0.123993546,0.00014829199,0.00003729747,0.0017990131,0.00003832334,0.004847936,0.0016173949,0.00086703844,0.8651084,0.0010226383],"about_ca_topic_score_codex":0.16434221,"about_ca_topic_score_gemma":0.24144608,"teacher_disagreement_score":0.14587615,"about_ca_system_score_codex":0.0002549664,"about_ca_system_score_gemma":0.0012720869,"threshold_uncertainty_score":0.99997765},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000093925686,0.0005402301,0.98828477,0.00029662537,0.0024446324,0.00035220728,0.000026370119,0.0001771934,0.007784066],"genre_scores_gemma":[0.09275829,0.00013993881,0.8974917,0.0032178035,0.0026183364,0.00002584794,0.00006979318,0.00013059437,0.0035476782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950328,0.000023190469,0.0005234182,0.0020073643,0.0016287768,0.00078449014],"domain_scores_gemma":[0.9965503,0.00025634767,0.00034799485,0.0020400938,0.00043634765,0.0003689225],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094073836,0.00064564473,0.0006214055,0.0006968863,0.0002465203,0.00078037067,0.0046521197,0.00038359858,0.000057564408],"category_scores_gemma":[0.0000753946,0.0005592461,0.0001347017,0.00057861925,0.00058852666,0.0013518704,0.0039902497,0.000955791,0.00012256161],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013202836,0.000068213725,0.000110778376,0.0000452199,0.000022141494,0.00039201233,0.0010427457,0.007797536,0.0001503782,0.026124574,0.0018412536,0.962392],"study_design_scores_gemma":[0.00085294864,0.0004109224,0.0007436923,0.001073706,0.000014366717,0.000117554155,2.346163e-7,0.765789,0.0012150779,0.18714927,0.040993724,0.0016395227],"about_ca_topic_score_codex":0.000082209175,"about_ca_topic_score_gemma":0.000038444563,"teacher_disagreement_score":0.9607524,"about_ca_system_score_codex":0.00041005865,"about_ca_system_score_gemma":0.00084730395,"threshold_uncertainty_score":0.9996859},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005059853,0.00018113936,0.9965271,0.00025603073,0.0014884094,0.00032923731,0.000015969857,0.00003669418,0.0006594754],"genre_scores_gemma":[0.7178171,0.0000065824793,0.2816005,0.00030744192,0.00016501971,0.000003161712,0.0000041894164,0.000019668492,0.00007629345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968083,0.0000627146,0.00065879634,0.00091545907,0.001199601,0.00035515902],"domain_scores_gemma":[0.99708354,0.00029973802,0.00070505566,0.0015313312,0.00029640473,0.000083921695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007592216,0.0003541082,0.0005294218,0.00034536654,0.00015060036,0.00011596065,0.0033701716,0.00018866968,0.000005058452],"category_scores_gemma":[0.0000598035,0.0002308629,0.0001865899,0.00047579306,0.0007641548,0.00012344478,0.0024857102,0.00043227425,0.0000056833273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008274109,0.000045453457,0.00007111719,0.00012515209,0.000012744317,0.000008872284,0.0010147378,0.44493034,0.0004026409,0.02507088,0.00004111891,0.5282687],"study_design_scores_gemma":[0.00021542555,0.00012288407,0.00044060423,0.0008251939,0.000007949955,0.00001674217,1.2025318e-7,0.9705687,0.001375782,0.025898974,0.0002570289,0.00027060116],"about_ca_topic_score_codex":0.000031093074,"about_ca_topic_score_gemma":0.000008885721,"teacher_disagreement_score":0.71731114,"about_ca_system_score_codex":0.00008268953,"about_ca_system_score_gemma":0.00027492468,"threshold_uncertainty_score":0.94143164},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8113984,0.000823063,0.1874453,0.0001528973,0.000101986,0.000042288215,0.0000030902017,0.0000065907093,0.000026403079],"genre_scores_gemma":[0.87561333,0.000166859,0.1239418,0.00019719267,0.00004476638,9.874817e-7,0.0000022495626,0.000006106838,0.000026692293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900824,0.000048321843,0.00039379156,0.00015531744,0.00026294062,0.00013139368],"domain_scores_gemma":[0.99899316,0.00021121658,0.00027399295,0.00024061509,0.00016704043,0.00011395906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035406457,0.00010381761,0.00034957158,0.00027431425,0.00006276475,0.00024581532,0.00020706444,0.000048918613,0.000018074401],"category_scores_gemma":[0.00009652711,0.000076176504,0.000077499535,0.0005209692,0.000016060772,0.00046840296,0.00021185973,0.00015742646,7.4718207e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020079222,0.013101817,0.047730442,0.004386105,0.0034790738,0.010261457,0.035004202,0.0221427,0.14118192,0.26092377,0.014560573,0.44702712],"study_design_scores_gemma":[0.0011515893,0.00008719452,0.020199403,0.0004573415,0.00018894317,0.00020536291,0.00014395622,0.97013193,0.0012434528,0.0047228714,0.0012522342,0.0002157094],"about_ca_topic_score_codex":0.0000088988145,"about_ca_topic_score_gemma":0.000028851886,"teacher_disagreement_score":0.9479892,"about_ca_system_score_codex":0.000011689029,"about_ca_system_score_gemma":0.000056289486,"threshold_uncertainty_score":0.31063876},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045655415,0.00037551078,0.99693507,0.001210313,0.0008296912,0.00003603932,0.00010820095,0.0000105579675,0.000038078266],"genre_scores_gemma":[0.060923513,0.0002183138,0.93803006,0.00029559864,0.00020094664,0.0000010413233,0.00009264482,0.000008896141,0.0002289825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893975,0.00002923724,0.00031963064,0.00025503774,0.00027950024,0.00017685455],"domain_scores_gemma":[0.9983215,0.000076598175,0.00019350526,0.0010145148,0.0002919176,0.00010199278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004107699,0.000084679246,0.00017008655,0.00005498738,0.000084580184,0.00017445079,0.0019140843,0.00004279893,0.0000038340745],"category_scores_gemma":[0.00016408965,0.000066882196,0.00004084378,0.00020525606,0.000014990829,0.0011344253,0.0016814591,0.00016230988,0.0000025016739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044588687,0.00016818407,0.000034479894,0.00006609669,0.000058350186,0.00047497658,0.00018987327,0.010453339,0.0062742685,0.00088290666,0.02727417,0.9540788],"study_design_scores_gemma":[0.0003053111,0.000029643134,0.00003534748,0.000034036704,0.000009977809,0.00052451243,0.0000096958,0.99038047,0.00007298675,0.0018282988,0.0066829934,0.000086740176],"about_ca_topic_score_codex":0.0000052308264,"about_ca_topic_score_gemma":0.000015875301,"teacher_disagreement_score":0.9799271,"about_ca_system_score_codex":0.000042651216,"about_ca_system_score_gemma":0.00039477387,"threshold_uncertainty_score":0.35568768},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025078792,0.0007234355,0.9908763,0.0009397347,0.0002866701,0.00001945236,0.000005626552,0.000093092545,0.004547768],"genre_scores_gemma":[0.085694544,0.000027733262,0.912382,0.00087789795,0.0005416016,8.15301e-7,0.00007738969,0.000005736045,0.00039226792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927014,0.00003685833,0.00008999039,0.00033197578,0.00011670234,0.00015433138],"domain_scores_gemma":[0.99927634,0.00008123726,0.000027299347,0.00054723414,0.00002596342,0.000041911895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001290873,0.000056245168,0.00008497625,0.000008739155,0.0002798756,0.0003274386,0.00057678256,0.000026621507,0.000021355518],"category_scores_gemma":[0.000015915508,0.000048850154,0.000008363032,0.00013060388,0.000020567835,0.0006617563,0.0030556512,0.00005320717,0.000004016285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002061132,0.000036945694,0.0011103132,0.000012372285,0.000018903364,0.00010082913,0.0005077055,0.00010550788,0.00036292317,0.049538635,0.14720362,0.8010002],"study_design_scores_gemma":[0.0002127604,0.000006106456,0.003823413,0.000028852308,0.0000043298887,0.000030521853,0.0000755599,0.90088266,0.00009665097,0.002278496,0.09240804,0.00015260302],"about_ca_topic_score_codex":0.000010033921,"about_ca_topic_score_gemma":0.000007371291,"teacher_disagreement_score":0.90077716,"about_ca_system_score_codex":0.0000030874241,"about_ca_system_score_gemma":0.000035482353,"threshold_uncertainty_score":0.38086507},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097116904,0.0010809555,0.23391607,0.0005721319,0.00081957877,0.0059305253,0.0012163247,0.000672649,0.7548206],"genre_scores_gemma":[0.00062645355,0.00033527767,0.6182269,0.0003650958,0.0015866014,0.00047345628,0.00028755778,0.00020833535,0.37789032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998313,0.000005055026,0.00035395086,0.0005799558,0.00039717834,0.0003508357],"domain_scores_gemma":[0.99897957,0.00024087838,0.00018363004,0.00040929264,0.00004043293,0.00014619526],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004818834,0.00035335796,0.0005118576,0.000044483586,0.00062624185,0.00027463175,0.00047987336,0.00041742172,0.00004197489],"category_scores_gemma":[0.000005214271,0.0003118332,0.00021088964,0.000025277324,0.00014121746,0.00008101931,0.0011302726,0.00066974,0.0000023993334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014310501,0.0000224,7.35658e-8,0.00012885107,0.00012326191,0.0000010784439,0.0012895357,0.000010891147,0.00015469937,0.93836564,0.01181924,0.048070014],"study_design_scores_gemma":[0.0028920283,0.00041503712,1.7181819e-7,0.00020367155,0.0001891266,0.000042913907,0.00046753162,0.02375992,0.00079808553,0.19894408,0.77116627,0.0011211486],"about_ca_topic_score_codex":0.000007084806,"about_ca_topic_score_gemma":9.195812e-7,"teacher_disagreement_score":0.759347,"about_ca_system_score_codex":0.000046060883,"about_ca_system_score_gemma":0.00015793975,"threshold_uncertainty_score":0.99993336},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7155705,0.0046597086,0.26952663,0.00058779627,0.003947347,0.003502059,0.0007819992,0.0013865744,0.000037396247],"genre_scores_gemma":[0.7305756,0.000097578166,0.26866996,0.00007182579,0.00024543988,0.0002401877,0.0000010191831,0.00008766058,0.000010711777],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957558,0.00028093983,0.0007409885,0.0015452729,0.001020924,0.00065605546],"domain_scores_gemma":[0.9950406,0.00008267488,0.0011063133,0.0030107663,0.00046580654,0.0002938723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005728364,0.00065797986,0.00076699094,0.00045421292,0.00035660347,0.00046153757,0.0033655525,0.00036220465,0.000115321316],"category_scores_gemma":[0.00017811937,0.00063057116,0.00022104186,0.0008833274,0.00014392307,0.0006384881,0.007427082,0.0011833002,0.0000124679145],"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":[0.000027000688,0.000188559,0.00025737868,0.00057944347,0.00006349705,0.00005827979,0.000022483,0.00007285937,0.9930926,0.0046550166,0.00094210403,0.00004075831],"study_design_scores_gemma":[0.0014707576,0.0002827902,0.06570171,0.0010813236,0.0001002653,8.303294e-8,0.0000088097495,0.04164755,0.86405873,0.00015703755,0.023290206,0.002200739],"about_ca_topic_score_codex":0.0001753314,"about_ca_topic_score_gemma":3.8849933e-7,"teacher_disagreement_score":0.1290339,"about_ca_system_score_codex":0.0002403498,"about_ca_system_score_gemma":0.00069912197,"threshold_uncertainty_score":0.99961454},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09860898,0.000019051198,0.8994272,0.0002598106,0.00011718548,0.00020705842,0.000015373844,0.00008871169,0.0012566812],"genre_scores_gemma":[0.9822358,0.00000813487,0.017355936,0.00020448868,0.000005848951,0.0000106454745,0.00015301496,0.0000025374652,0.000023596014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991206,0.000057805377,0.00026965645,0.00010638609,0.0003577813,0.00008776798],"domain_scores_gemma":[0.99940485,0.000058336183,0.0002542774,0.000150967,0.000090060305,0.000041530355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014056152,0.000075563694,0.00011253941,0.0001873985,0.0002656245,0.00013442288,0.00017654122,0.00001444158,0.000022286822],"category_scores_gemma":[0.000007869286,0.000057327412,0.000019845993,0.00052853086,0.000028104636,0.0019297438,0.00011049118,0.00007062158,0.000002297102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005828349,0.00018603564,0.0035567114,0.000091015296,0.00006121425,0.000006575192,0.010342702,0.07857634,0.0001351185,0.07470022,0.005679307,0.82608193],"study_design_scores_gemma":[0.0015954652,0.0006035382,0.023925131,0.000016703712,0.000008244373,0.00008541302,0.0009828409,0.962475,0.0003466268,0.004870439,0.0049222107,0.00016840258],"about_ca_topic_score_codex":0.00010177251,"about_ca_topic_score_gemma":0.0000053214585,"teacher_disagreement_score":0.8838987,"about_ca_system_score_codex":0.00002247369,"about_ca_system_score_gemma":0.000061512386,"threshold_uncertainty_score":0.2337744},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4329878e-7,0.00035994351,0.43496934,0.000012235957,0.0005816935,0.00006403517,0.0000057051857,0.0003330818,0.56367385],"genre_scores_gemma":[0.000004041907,0.00013369902,0.13239425,0.00035014414,0.0001922506,0.000005279607,0.000014346836,0.00010277732,0.8668032],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880916,0.000034019307,0.0001312995,0.0004842802,0.00026345972,0.00027778765],"domain_scores_gemma":[0.99879014,0.0000653529,0.00011139303,0.0009104882,0.000015616404,0.00010701519],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009616331,0.0002156647,0.0002115405,0.00016570711,0.000059198857,0.00017909743,0.0010673909,0.00019109066,0.000556467],"category_scores_gemma":[0.000029324057,0.00016973662,0.00005761656,0.0001816698,0.000021272775,0.00014253336,0.00040940082,0.00015976909,0.0009854086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7194393e-8,0.00001308274,0.0000043286423,0.000009716881,0.000007950681,0.0000107765245,0.000016499313,3.2779923e-7,0.00000491723,0.05660373,0.93883723,0.0044914465],"study_design_scores_gemma":[0.00009627069,0.000012840226,0.000006680287,0.00007360577,0.0000030483889,0.000009277122,0.00000699706,0.0020286273,0.00006177136,0.00044674214,0.9971791,0.000075022916],"about_ca_topic_score_codex":0.00008484894,"about_ca_topic_score_gemma":0.000011574613,"teacher_disagreement_score":0.30312937,"about_ca_system_score_codex":0.000015483763,"about_ca_system_score_gemma":0.000040667474,"threshold_uncertainty_score":0.99979246},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022029078,0.00018033497,0.9853449,0.0025961946,0.0005909357,0.0002918145,0.00012529262,0.00023129865,0.008436328],"genre_scores_gemma":[0.75954473,0.00036271667,0.2313187,0.001393748,0.00034220537,0.000275374,0.0013372657,0.000054714106,0.0053705573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980031,0.00005619074,0.00031770553,0.0008861591,0.00043558696,0.00030125136],"domain_scores_gemma":[0.9986394,0.0001797488,0.00018209605,0.00042646012,0.00042370244,0.00014861587],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021797877,0.00028767102,0.00029000954,0.00011599452,0.00029221052,0.0006617695,0.0008837523,0.000115216164,0.0005737763],"category_scores_gemma":[0.00018106673,0.00026384328,0.00007394987,0.0002567003,0.00005612857,0.0003044776,0.0006118275,0.0005688053,0.00007162882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009824655,0.00013967004,0.00079186837,0.000037941183,0.00008664877,0.000032861295,0.00025264916,0.00040287923,0.008999765,0.43125468,0.002274024,0.5556288],"study_design_scores_gemma":[0.0019879579,0.00019258435,0.0014712146,0.00023651743,0.00001996534,0.000037892085,0.00021196654,0.64698493,0.009547828,0.0131754475,0.32530805,0.00082565146],"about_ca_topic_score_codex":0.000020942112,"about_ca_topic_score_gemma":0.000012631809,"teacher_disagreement_score":0.7573418,"about_ca_system_score_codex":0.000065256725,"about_ca_system_score_gemma":0.00018173843,"threshold_uncertainty_score":0.9999814},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014202583,0.000583789,0.9883428,0.00057437416,0.008625266,0.00033273085,0.00006128771,0.00015153934,0.0013140166],"genre_scores_gemma":[0.00687247,0.00015789871,0.98884654,0.0022842905,0.0009385923,0.000012196603,0.000121393634,0.00004838802,0.00071820157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99560803,0.000038830458,0.00038057897,0.0023786104,0.0010895416,0.00050440384],"domain_scores_gemma":[0.9960021,0.00040951,0.0001883678,0.0030572277,0.00010154918,0.0002412769],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000798676,0.0004435003,0.00040925213,0.0006944746,0.00053265033,0.0007498723,0.0061322097,0.00013960105,0.00008190354],"category_scores_gemma":[0.00013036374,0.00039985095,0.000040790626,0.00057514606,0.00028313737,0.0012665486,0.0135206245,0.00091857364,0.000013410048],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036764811,0.000009679119,0.000014643792,0.000009025259,0.0000053502495,0.00005076916,0.00024732904,0.00672262,0.00002718748,0.005365634,0.0010736198,0.98647046],"study_design_scores_gemma":[0.00016188933,0.0001980936,0.0003271223,0.0001286773,0.000006663995,0.00020336297,2.4218107e-7,0.8951168,0.00011831292,0.04904944,0.054070998,0.0006183759],"about_ca_topic_score_codex":0.00015315111,"about_ca_topic_score_gemma":0.00007604728,"teacher_disagreement_score":0.98585206,"about_ca_system_score_codex":0.00018824934,"about_ca_system_score_gemma":0.00036588477,"threshold_uncertainty_score":0.9998453},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92710716,0.0016419872,0.04626232,0.006132872,0.0003431803,0.0015213051,0.00068796816,0.00024384352,0.016059337],"genre_scores_gemma":[0.996182,0.000047283233,0.0030456912,0.00022804971,0.00005094044,0.00008013233,0.0000040862974,0.000010060536,0.00035174165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986322,0.00005356918,0.0002518075,0.00033834696,0.00047260753,0.0002514964],"domain_scores_gemma":[0.99133074,0.00020948744,0.0003682104,0.00029143013,0.007700574,0.000099571946],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009664253,0.0001516844,0.00022825236,0.00011658511,0.0003939762,0.0013443299,0.002853145,0.000055445005,0.00001861211],"category_scores_gemma":[0.0017795913,0.00011578181,0.0000733973,0.00043718723,0.00022253592,0.005088812,0.0033304335,0.00040169747,7.0550084e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008794404,0.00019458796,0.008588038,0.00016616909,0.000056112185,0.0000012370537,0.022541776,0.000025508194,0.018324787,0.8784927,0.004022894,0.067498244],"study_design_scores_gemma":[0.0012345382,0.0007558353,0.05115083,0.00021597785,0.00008820561,0.00019964462,0.006622494,0.015538573,0.025838893,0.3378529,0.55961835,0.00088379876],"about_ca_topic_score_codex":0.00003221119,"about_ca_topic_score_gemma":6.034365e-7,"teacher_disagreement_score":0.55559546,"about_ca_system_score_codex":0.000027017673,"about_ca_system_score_gemma":0.00015418728,"threshold_uncertainty_score":0.9996924},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71117955,0.00008617957,0.28651598,0.000027049227,0.0005919578,0.0003828383,0.00028781695,0.00024576395,0.00068284676],"genre_scores_gemma":[0.99510545,0.000062339925,0.004368469,0.000036339152,0.000022690501,0.000002493001,0.00033487155,0.000013392749,0.000053963522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962187,0.0007205741,0.00049203873,0.0018924488,0.00026180016,0.0004144755],"domain_scores_gemma":[0.9946466,0.00020653667,0.00055130076,0.004052649,0.0002420317,0.0003008904],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007786813,0.00042439115,0.0007749267,0.00038113148,0.0003225034,0.000091214104,0.0045818486,0.00021958766,0.00013954843],"category_scores_gemma":[0.000027688608,0.0004694606,0.0004337341,0.0011775345,0.00040046126,0.0007734639,0.005778304,0.0009354157,0.000010364126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015592408,0.0019913367,0.12022498,0.00029930923,0.00018814336,0.0001539127,0.0007342245,0.29058373,0.000048294467,0.5835781,0.0005733167,0.0014687058],"study_design_scores_gemma":[0.0005549,0.00021342485,0.08602572,0.000045221976,0.00006445287,0.0000034126492,0.00017688442,0.63791466,0.000060347887,0.27354792,0.0007564252,0.0006366082],"about_ca_topic_score_codex":0.0010891922,"about_ca_topic_score_gemma":0.00012498924,"teacher_disagreement_score":0.34733096,"about_ca_system_score_codex":0.00017430104,"about_ca_system_score_gemma":0.00024354132,"threshold_uncertainty_score":0.9997757},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14802432,0.000057600908,0.8490224,0.0010671379,0.00042966727,0.00020110648,0.00003817347,0.00008009606,0.001079487],"genre_scores_gemma":[0.9136024,0.0000028180857,0.086124845,0.00020356859,0.000045559325,0.000007166676,0.0000017045364,0.000005080671,0.000006820521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973764,0.00015565111,0.00032326742,0.00070407166,0.0010374296,0.00040322513],"domain_scores_gemma":[0.9977987,0.0003746118,0.00010929915,0.001369425,0.00010359099,0.00024437997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012942471,0.00014319154,0.00024497058,0.0001903211,0.0008070197,0.0001892593,0.0031930415,0.000022087765,0.00005710448],"category_scores_gemma":[0.0000769333,0.00011887986,0.000054152762,0.0008941583,0.0022449857,0.0003173436,0.006009173,0.0002367225,0.0000045199545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001183138,0.00014965539,0.00009625027,0.0000066229723,0.0000039790352,0.00000814281,0.00041762553,0.009118673,0.0011751765,0.98231524,0.00024003226,0.00645678],"study_design_scores_gemma":[0.00036821124,0.0002924695,0.005921568,0.000013717385,0.000004639947,0.000052920837,0.000018907913,0.935605,0.00154279,0.055940114,0.00008569995,0.00015399004],"about_ca_topic_score_codex":0.000020250067,"about_ca_topic_score_gemma":2.247807e-7,"teacher_disagreement_score":0.9264863,"about_ca_system_score_codex":0.000050838564,"about_ca_system_score_gemma":0.00018255362,"threshold_uncertainty_score":0.8271743},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29380882,0.006141207,0.47055843,0.00020400064,0.006278106,0.0014885141,0.00016555429,0.0013738623,0.21998152],"genre_scores_gemma":[0.46015558,0.0014121066,0.35122773,0.00029356932,0.0005863358,0.00006500855,0.0058562797,0.00011213738,0.18029125],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893194,0.000026733294,0.00025570643,0.00031698414,0.00032085486,0.0001477756],"domain_scores_gemma":[0.99898005,0.000031164225,0.00018557129,0.000650346,0.00009904495,0.000053847863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005380358,0.00015644474,0.00022913648,0.000117182426,0.00005277049,0.000031640317,0.00087108527,0.00013250996,0.00016163838],"category_scores_gemma":[0.00002214954,0.00012257864,0.00008478841,0.00016736698,0.000012707071,0.00019952975,0.00012567776,0.00016703145,0.000050922714],"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":[0.00010356587,0.0008913124,0.00032558347,0.0006633804,0.00023933225,0.00029791513,0.019917654,0.000033396387,0.061004728,0.22960767,0.08903977,0.5978757],"study_design_scores_gemma":[0.003210408,0.000753425,0.05058213,0.0016866322,0.00010591129,0.00012366925,0.0037559422,0.09746084,0.70889497,0.004671856,0.12537654,0.0033776679],"about_ca_topic_score_codex":0.00023103207,"about_ca_topic_score_gemma":0.000035082925,"teacher_disagreement_score":0.64789027,"about_ca_system_score_codex":0.000014314142,"about_ca_system_score_gemma":0.00008854473,"threshold_uncertainty_score":0.49986118},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009799398,0.0010787596,0.9865865,0.000299208,0.0006590517,0.000085074586,0.000009275151,0.0014706175,0.000012128522],"genre_scores_gemma":[0.4804947,0.00003090808,0.5190737,0.0001316993,0.0001370859,0.000012207064,0.0000060925404,0.000020171321,0.00009342477],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988911,0.000010334666,0.0001702135,0.00035196103,0.00024679315,0.00032957512],"domain_scores_gemma":[0.98994267,0.008677521,0.000039042636,0.001173159,0.000042279946,0.00012531981],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00008265452,0.00018215536,0.00015250761,0.00009648027,0.000092197304,0.00013896229,0.0013960699,0.00007260629,0.00009884702],"category_scores_gemma":[0.020312853,0.00016965433,0.000059339716,0.00029254096,0.000011840527,0.00059315254,0.00068469427,0.0001667426,0.00027602928],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036086187,0.0002656093,0.08216234,0.00016512739,0.00007402762,0.0002150898,0.0010528589,0.0038328532,0.002543983,0.009261565,0.04135983,0.8590631],"study_design_scores_gemma":[0.0016338144,0.00035281127,0.16662453,0.0004419959,0.000032979657,0.00022921091,0.000009860387,0.46658742,0.009545793,0.00036126567,0.3514416,0.0027387065],"about_ca_topic_score_codex":0.000014042635,"about_ca_topic_score_gemma":3.8463713e-7,"teacher_disagreement_score":0.8563244,"about_ca_system_score_codex":0.00002426555,"about_ca_system_score_gemma":0.000006776645,"threshold_uncertainty_score":0.9879395},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0146383e-8,0.00010006166,0.41990313,0.0002470018,0.00027915032,0.000043178694,0.0000073729175,0.000091339985,0.5793288],"genre_scores_gemma":[0.000007997521,0.00009053576,0.040189385,0.00033795275,0.00018025048,0.0000016355664,0.0000045324864,0.000011933103,0.95917577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912137,0.0000032539836,0.0001395028,0.00038286913,0.00022303722,0.00012999283],"domain_scores_gemma":[0.99883854,0.000031133255,0.00006972699,0.00094254984,0.00004153101,0.000076497774],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000062954365,0.00015862998,0.00015178892,0.00005615356,0.00005425756,0.000103503575,0.0013096001,0.00013073864,0.0017649508],"category_scores_gemma":[0.000002447453,0.00009408528,0.000060441093,0.000008168748,0.000022510723,0.0003435124,0.0011700261,0.00009875812,0.0035464338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.501242e-7,0.000001170964,7.792569e-8,0.0000013030088,0.0000037245534,0.000010683788,0.000002531047,2.1683423e-8,0.0000041958874,0.77487135,0.038673107,0.1864316],"study_design_scores_gemma":[0.00005881692,0.000015681786,0.0000015652128,0.00007036613,0.0000015381028,0.000007785596,6.386268e-8,0.0003136329,0.000024623821,0.15371282,0.8456308,0.00016228402],"about_ca_topic_score_codex":0.0000029022017,"about_ca_topic_score_gemma":9.959938e-7,"teacher_disagreement_score":0.8069577,"about_ca_system_score_codex":0.000018687284,"about_ca_system_score_gemma":0.00004882387,"threshold_uncertainty_score":0.9991476},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035522035,0.000022552327,0.9911839,0.0009071293,0.00013000841,0.0003979745,0.00004423876,0.00035867907,0.003403317],"genre_scores_gemma":[0.24462792,0.0000011716245,0.7539924,0.0005386869,0.00011502618,0.000027466713,0.00013428638,0.000009903229,0.00055315025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980179,0.00005265542,0.0002706395,0.0011406883,0.00020873944,0.00030938254],"domain_scores_gemma":[0.9961658,0.00010691857,0.00006603956,0.0034073705,0.0000749263,0.00017891801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007097991,0.00013074833,0.00016211011,0.000047700112,0.00023779873,0.00028537854,0.002944224,0.000054912136,0.000038349488],"category_scores_gemma":[0.00018817307,0.000103676306,0.000025614767,0.00029303008,0.000017914557,0.0014213552,0.0020195511,0.000099786484,0.00006326955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018377274,0.0012190543,0.0011747136,0.00007841792,0.000029569519,0.000002025242,0.00052836456,0.00058995356,0.002067864,0.12840989,0.1464714,0.71941036],"study_design_scores_gemma":[0.00016159231,0.000053141805,0.0011444006,0.0000063955645,0.0000032587504,0.0000039669667,0.000011051476,0.9722728,0.00020013623,0.00014900256,0.025829032,0.00016521978],"about_ca_topic_score_codex":0.00010754145,"about_ca_topic_score_gemma":0.0000053559356,"teacher_disagreement_score":0.97168285,"about_ca_system_score_codex":0.000025287462,"about_ca_system_score_gemma":0.0000114522945,"threshold_uncertainty_score":0.54711497},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24288402,0.006428878,0.7485113,0.0009829511,0.00060953933,0.00033201877,0.00006151108,0.00006772515,0.00012205711],"genre_scores_gemma":[0.7825682,0.001279862,0.21580486,0.000032204167,0.00011995338,0.0000038958115,0.0001621031,0.000013068984,0.00001586027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970122,0.00051747396,0.0010417046,0.00023159041,0.0010468701,0.0001501839],"domain_scores_gemma":[0.9929163,0.00058156997,0.0011103274,0.0026940047,0.0025586768,0.00013916467],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0015719881,0.00014779807,0.00032268968,0.00034312738,0.0002784139,0.00021173555,0.009374331,0.00008355498,0.000003240215],"category_scores_gemma":[0.00013984733,0.0001274171,0.00006784726,0.00033964438,0.00006479067,0.001746409,0.001653103,0.0002710315,0.000003833911],"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":[0.0015587127,0.010114733,0.033716206,0.00021311242,0.0023454803,0.000056617646,0.04359258,0.4262764,0.24646237,0.09848167,0.084842145,0.052339964],"study_design_scores_gemma":[0.001280564,0.00017883761,0.007347121,0.00066278956,0.000014156815,0.00016949259,0.00050234917,0.9772295,0.0011214194,0.000081699,0.01125219,0.00015991401],"about_ca_topic_score_codex":0.00040927756,"about_ca_topic_score_gemma":0.000010310686,"teacher_disagreement_score":0.5509531,"about_ca_system_score_codex":0.00010252927,"about_ca_system_score_gemma":0.00045873955,"threshold_uncertainty_score":0.99598545},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009507803,0.00022997073,0.78479934,0.000102049766,0.0020561037,0.00020412925,0.0000075400203,0.00034179716,0.21224955],"genre_scores_gemma":[0.0047356286,0.00025979194,0.9098414,0.0011264946,0.00073528715,0.000015878542,0.000013450354,0.000071488954,0.083200544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633807,0.000017703049,0.00048897095,0.0015414051,0.0010014734,0.0006124005],"domain_scores_gemma":[0.9966135,0.00007159486,0.00025411148,0.0026774232,0.00014584765,0.0002375317],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00085439574,0.00042384767,0.0004151037,0.00074225536,0.00023177972,0.00046312215,0.007193969,0.00020455607,0.00010951244],"category_scores_gemma":[0.000011138436,0.0003782973,0.000089451365,0.00033990477,0.0005670677,0.0015716817,0.0052934405,0.00050690764,0.0006935781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012071062,0.000027365297,0.0000038187754,0.000009995564,0.0000027528235,0.00010294517,0.00019867608,0.000027479071,0.0000053496988,0.3997848,0.002272464,0.59756315],"study_design_scores_gemma":[0.00049016264,0.00024497168,0.0007763625,0.000742223,0.0000064280807,0.0001631102,3.133502e-7,0.42097563,0.00012335232,0.37280008,0.20234774,0.0013296406],"about_ca_topic_score_codex":0.00002945636,"about_ca_topic_score_gemma":0.000007275794,"teacher_disagreement_score":0.5962335,"about_ca_system_score_codex":0.00015021751,"about_ca_system_score_gemma":0.00048437645,"threshold_uncertainty_score":0.9998669},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000047487847,0.00020038735,0.057066537,0.000028329452,0.0002937167,0.00016400032,0.00008244304,0.00032077913,0.94183904],"genre_scores_gemma":[0.000063452026,0.000103169165,0.004656311,0.00016551437,0.00014422624,1.4840128e-7,0.000034743476,0.000018256042,0.99481416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986018,0.000025174519,0.00015094664,0.0006117636,0.00033592444,0.00027441402],"domain_scores_gemma":[0.9983609,0.000043444474,0.00017252557,0.001113329,0.00013742423,0.00017240766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000067727065,0.00033902636,0.00033470165,0.0001718749,0.00023363177,0.00014449628,0.0015355424,0.00029054738,0.0000022354113],"category_scores_gemma":[0.0000029955222,0.00037454296,0.00017227627,0.000007755546,0.0001101549,0.00030715758,0.0011122482,0.0003867149,0.000035625],"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":[0.000008778824,0.000004362281,6.870357e-8,0.000012298141,0.000026162927,0.00044301173,0.000020974489,0.0000017287966,0.000009790591,0.8969463,0.07497636,0.02755016],"study_design_scores_gemma":[0.00023642486,0.000050645915,0.000008463264,0.00012518417,0.00003721637,0.000036747944,0.000004187104,0.0015217275,0.00012424945,0.00011986477,0.9973054,0.00042987795],"about_ca_topic_score_codex":0.000054486038,"about_ca_topic_score_gemma":5.6026306e-7,"teacher_disagreement_score":0.92232907,"about_ca_system_score_codex":0.00011641071,"about_ca_system_score_gemma":0.00010804585,"threshold_uncertainty_score":0.99987066},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000036008319,0.0065428806,0.124039605,0.000055912547,0.0024265146,0.0006499448,0.0016546705,0.0002526029,0.8643743],"genre_scores_gemma":[0.0005076304,0.00755491,0.042829275,0.00014002746,0.00253367,0.000046618945,0.0041475515,0.00015396679,0.94208634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965082,0.00007011806,0.0010134354,0.0009873701,0.0010166593,0.00040422022],"domain_scores_gemma":[0.9954085,0.00020167319,0.0008268186,0.0031009174,0.00020539184,0.00025672305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038771404,0.0005935852,0.0009767603,0.00032142302,0.00011109848,0.00012110837,0.0024724859,0.00032468606,0.00008253537],"category_scores_gemma":[0.000033407574,0.0005256188,0.00020473557,0.000096779666,0.00008472261,0.000816884,0.00097415876,0.00048944907,0.00026473156],"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":[0.000024188752,0.00016495898,0.00001137412,0.0005953046,0.0001398842,0.00035086027,0.00018348588,0.000072767696,0.00012991425,0.5660435,0.31335342,0.11893037],"study_design_scores_gemma":[0.0004154144,0.0001246394,0.000025979634,0.0011429038,0.000041783962,0.00003937663,0.0000056532936,0.006778546,0.000026701442,0.0010300308,0.98976237,0.00060658995],"about_ca_topic_score_codex":0.0001919457,"about_ca_topic_score_gemma":0.000016187962,"teacher_disagreement_score":0.67640895,"about_ca_system_score_codex":0.000054249223,"about_ca_system_score_gemma":0.0002210143,"threshold_uncertainty_score":0.99971956},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005104156,0.002424592,0.25229618,0.0016496525,0.002850009,0.00023939217,0.003378678,0.0007705843,0.7363858],"genre_scores_gemma":[0.0043341783,0.29236284,0.45646736,0.016811816,0.009045746,0.00054238003,0.11706291,0.00046027545,0.10291251],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982522,0.00006531006,0.00031215118,0.00062745565,0.00043420793,0.000308687],"domain_scores_gemma":[0.99851865,0.00012954195,0.0001574755,0.000897894,0.0000922664,0.0002041537],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000056078366,0.00027811926,0.00033723676,0.00014125758,0.00026370608,0.0002870744,0.0012015795,0.00032667822,0.00032136132],"category_scores_gemma":[0.00006909072,0.00025208312,0.00010846451,0.00059340417,0.000042255182,0.00035636767,0.00080040743,0.0007065434,0.0022385698],"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":[0.0000014953148,0.000024459014,0.0000017525336,0.000031409814,0.00002361316,0.00005815536,0.0000446731,4.8187667e-7,0.0000015369475,0.042129442,0.9427655,0.014917486],"study_design_scores_gemma":[0.00017502553,0.00004272816,0.000039310875,0.0001864281,0.000025624433,0.000022345126,0.0000046650125,0.0019297976,0.000029220502,0.007981276,0.9892314,0.00033217014],"about_ca_topic_score_codex":0.00004099629,"about_ca_topic_score_gemma":0.0000035213645,"teacher_disagreement_score":0.6334733,"about_ca_system_score_codex":0.000047846905,"about_ca_system_score_gemma":0.00032530216,"threshold_uncertainty_score":0.99999315},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003748724,0.0034051884,0.2091788,0.0002913756,0.0028490166,0.00068793836,0.00070293783,0.00016131748,0.7823485],"genre_scores_gemma":[0.037073728,0.0072913254,0.46584213,0.00033370958,0.0024102628,0.000066518565,0.0016353506,0.0002758798,0.4850711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998227,0.000058299007,0.0006555715,0.0005419134,0.00023804519,0.00027914278],"domain_scores_gemma":[0.9977665,0.00012460123,0.0007037979,0.0010208993,0.0002643649,0.00011982329],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031339895,0.00032605338,0.0008277202,0.00018033793,0.00003166963,0.000008776723,0.0015573462,0.00038932447,0.00021614134],"category_scores_gemma":[0.00005540032,0.000272326,0.00016842243,0.000050609382,0.000286373,0.00020420358,0.0008688418,0.00033379326,0.000092592316],"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":[0.0003422043,0.0001682544,0.0001373258,0.00023391185,0.0003750486,0.000118007396,0.0007480449,0.00018043118,0.00908953,0.6267825,0.06517909,0.29664567],"study_design_scores_gemma":[0.0026235546,0.0012248517,0.00008686687,0.0004186461,0.00008279556,0.00010507879,0.000011286139,0.0011950448,0.0009955752,0.054173365,0.9382624,0.00082052196],"about_ca_topic_score_codex":0.000022677954,"about_ca_topic_score_gemma":0.0000036895976,"teacher_disagreement_score":0.87308335,"about_ca_system_score_codex":0.000034673514,"about_ca_system_score_gemma":0.00030842534,"threshold_uncertainty_score":0.9999729},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008485307,0.000074977645,0.90277916,0.000519433,0.00011204631,0.000014259774,1.5648689e-7,0.00014915506,0.09550225],"genre_scores_gemma":[0.6623628,0.000012900305,0.33055204,0.0007268613,0.00008053256,0.0000015181326,4.6990297e-7,0.0000026205341,0.0062602367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996958,0.000005524453,0.000042000625,0.0001037855,0.00007156143,0.00008136749],"domain_scores_gemma":[0.99971354,0.00001197639,0.000008914992,0.00022892268,0.000008758319,0.000027899887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003220178,0.000026759313,0.000025559724,0.00001412285,0.000056322973,0.000059689573,0.00030360481,0.000009678981,0.00035202707],"category_scores_gemma":[0.000005205936,0.000019432528,0.000011112702,0.0000716133,0.0000041390153,0.0002779073,0.00017242967,0.000025951427,0.00040795232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.1622695e-8,0.000032542124,0.00021843755,0.0000015088557,0.00000169013,0.000011581876,0.00025562922,0.00001098051,0.0003942772,0.15897,0.060739797,0.77936345],"study_design_scores_gemma":[0.00005373673,0.000009049736,0.00042488327,0.0000025942782,2.2745472e-7,0.000009598938,0.0000047421136,0.9380633,0.00039480254,0.0007346819,0.06024807,0.00005427867],"about_ca_topic_score_codex":0.000006019396,"about_ca_topic_score_gemma":2.1754131e-7,"teacher_disagreement_score":0.93805236,"about_ca_system_score_codex":0.0000030656802,"about_ca_system_score_gemma":0.0000011276944,"threshold_uncertainty_score":0.52435374},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014533564,0.00008486665,0.14328098,0.000046514924,0.0003184913,0.00014917365,0.00006247189,0.00024129731,0.85581475],"genre_scores_gemma":[0.07481374,0.00007503724,0.32409543,0.02514406,0.004745483,0.00006327313,0.0005362534,0.00016492188,0.5703618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985086,0.0000085656775,0.00036801156,0.00030950346,0.0005073594,0.00029800122],"domain_scores_gemma":[0.99873006,0.000014880666,0.0002519765,0.000751672,0.00010303663,0.00014837933],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000106092106,0.00030322833,0.0002578957,0.00008490593,0.00013232106,0.00038642887,0.001043753,0.00032001853,0.000015321468],"category_scores_gemma":[0.000009231734,0.00027908487,0.00011019235,0.000020868561,0.00003206259,0.00071648497,0.0005564836,0.00027469374,0.00048755997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023594646,0.0000016413011,3.4843333e-7,0.00000420594,0.000006634874,0.000010263639,0.00002537708,0.0000043150353,4.844547e-7,0.6774197,0.0047049327,0.31781968],"study_design_scores_gemma":[0.00021657071,0.0000788096,0.000030415422,0.00016544669,0.000009416551,0.00005355386,0.0000026637322,0.0023165103,0.000009748328,0.44505942,0.5516668,0.00039064995],"about_ca_topic_score_codex":0.000030146928,"about_ca_topic_score_gemma":0.000006968853,"teacher_disagreement_score":0.54696184,"about_ca_system_score_codex":0.00016032725,"about_ca_system_score_gemma":0.00018626403,"threshold_uncertainty_score":0.99996614},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006888872,0.00019542611,0.99131286,0.000097846,0.00026494116,0.0006495408,0.00030426504,0.000090749934,0.0001955103],"genre_scores_gemma":[0.70460105,0.000010369394,0.29398057,0.000017547134,0.000035390214,0.000099529585,0.0012122316,0.000012205461,0.000031113985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817157,0.000033791497,0.00055867067,0.00064389635,0.0004044012,0.00018767943],"domain_scores_gemma":[0.9972428,0.00020985582,0.00055537117,0.001445951,0.00046870194,0.00007733541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017399948,0.00022799127,0.00050813134,0.00010504066,0.000049448772,0.0002120156,0.0014299221,0.00021961115,0.0000055871396],"category_scores_gemma":[0.000028313452,0.00018995277,0.000239384,0.00018082956,0.00008563291,0.00027619602,0.0018032023,0.00016217258,8.322925e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115061426,0.0016559155,0.003352093,0.0030439028,0.00012501175,0.0000042130523,0.00023419343,0.016164185,0.0099341925,0.026378697,0.0012941089,0.9376984],"study_design_scores_gemma":[0.00052442093,0.000081644874,0.0006107595,0.00040279236,0.000020678724,0.0000012440873,0.000034965964,0.9443196,0.0469889,0.0053509106,0.001381383,0.00028268315],"about_ca_topic_score_codex":0.00015018809,"about_ca_topic_score_gemma":0.0000072039215,"teacher_disagreement_score":0.9374157,"about_ca_system_score_codex":0.000021774002,"about_ca_system_score_gemma":0.00016939157,"threshold_uncertainty_score":0.7746049},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3678079,0.00044129716,0.6303857,0.00030498035,0.0006353037,0.00015400838,0.00013629814,0.000021255959,0.00011328243],"genre_scores_gemma":[0.99509895,0.0017055065,0.002445448,0.000077378354,0.0003435447,0.000016174346,0.00028690055,0.00000918962,0.000016904472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976921,0.00016266938,0.00049761694,0.0009952297,0.00038504353,0.00026735512],"domain_scores_gemma":[0.9985378,0.00023040465,0.0002702194,0.00081208325,0.00007096887,0.000078540455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006665058,0.00021625096,0.00032930003,0.00037160006,0.00010978157,0.00020051168,0.0014305526,0.00011528352,0.000024486977],"category_scores_gemma":[0.00007479834,0.00017093058,0.00003075229,0.00044431214,0.00008223562,0.0023798158,0.0008957455,0.00016101782,0.000001598524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006351371,0.00015754871,0.02678201,0.0000030508413,0.00003892453,0.000012749339,0.00037876493,0.0031943794,0.00032972058,0.00029776726,0.000020747058,0.9687208],"study_design_scores_gemma":[0.0010465457,0.00008337958,0.02508793,0.0002184458,0.000015683685,0.0000010185267,0.00027554907,0.9720211,0.000071382805,0.0006039016,0.00033627677,0.00023881196],"about_ca_topic_score_codex":0.00049946393,"about_ca_topic_score_gemma":0.0045879525,"teacher_disagreement_score":0.9688267,"about_ca_system_score_codex":0.00014414336,"about_ca_system_score_gemma":0.000043864366,"threshold_uncertainty_score":0.6970347},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021746566,0.00004142152,0.9934333,0.0003826102,0.00009343184,0.00014522632,0.00026639097,0.00013258817,0.0033303914],"genre_scores_gemma":[0.76464236,0.000058532038,0.23082545,0.000826832,0.000082953055,0.000005071619,0.0032184666,0.000015085294,0.00032523548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988826,0.000025597941,0.0001945276,0.00026171474,0.00042195263,0.00021359086],"domain_scores_gemma":[0.9990093,0.00003882263,0.00008502251,0.0006882178,0.00007019033,0.00010845562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089943984,0.00013569588,0.00011840695,0.000076625874,0.00024353924,0.00024082503,0.0010689683,0.000053569805,0.00014721505],"category_scores_gemma":[0.0000036528882,0.00009926273,0.000017420622,0.00021654229,0.000058197278,0.0073017264,0.00035314905,0.00011618537,0.0000438255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011883784,0.00069556164,0.00038713188,0.00011167572,0.00012670133,0.00008086895,0.0018754867,0.0056563155,0.0028207116,0.055351797,0.34933403,0.5834409],"study_design_scores_gemma":[0.0007407199,0.00004970695,0.00007071023,0.00003499917,0.0000069695157,0.00004539463,0.000059999074,0.9375123,0.0004955891,0.00025601935,0.060546067,0.00018155584],"about_ca_topic_score_codex":0.00020516045,"about_ca_topic_score_gemma":0.000010588879,"teacher_disagreement_score":0.931856,"about_ca_system_score_codex":0.00003818625,"about_ca_system_score_gemma":0.000031903262,"threshold_uncertainty_score":0.52935755},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006888872,0.00019542611,0.99131286,0.000097846,0.00026494116,0.0006495408,0.00030426504,0.000090749934,0.0001955103],"genre_scores_gemma":[0.70460105,0.000010369394,0.29398057,0.000017547134,0.000035390214,0.000099529585,0.0012122316,0.000012205461,0.000031113985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817157,0.000033791497,0.00055867067,0.00064389635,0.0004044012,0.00018767943],"domain_scores_gemma":[0.9972428,0.00020985582,0.00055537117,0.001445951,0.00046870194,0.00007733541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017399948,0.00022799127,0.00050813134,0.00010504066,0.000049448772,0.0002120156,0.0014299221,0.00021961115,0.0000055871396],"category_scores_gemma":[0.000028313452,0.00018995277,0.000239384,0.00018082956,0.00008563291,0.00027619602,0.0018032023,0.00016217258,8.322925e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115061426,0.0016559155,0.003352093,0.0030439028,0.00012501175,0.0000042130523,0.00023419343,0.016164185,0.0099341925,0.026378697,0.0012941089,0.9376984],"study_design_scores_gemma":[0.00052442093,0.000081644874,0.0006107595,0.00040279236,0.000020678724,0.0000012440873,0.000034965964,0.9443196,0.0469889,0.0053509106,0.001381383,0.00028268315],"about_ca_topic_score_codex":0.00015018809,"about_ca_topic_score_gemma":0.0000072039215,"teacher_disagreement_score":0.9374157,"about_ca_system_score_codex":0.000021774002,"about_ca_system_score_gemma":0.00016939157,"threshold_uncertainty_score":0.7746049},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000511885,0.00010881528,0.9950321,0.0019401752,0.00023192236,0.00050186634,0.0000018816045,0.0002523591,0.0014190285],"genre_scores_gemma":[0.17228828,0.000014762044,0.82606,0.00031717625,0.00023782623,0.00015950516,0.0000046877262,0.000015110594,0.00090267655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987924,0.000017691325,0.00019968569,0.00036892612,0.00023194484,0.00038934182],"domain_scores_gemma":[0.99914974,0.00019131666,0.00009292679,0.00046631478,0.00004383576,0.000055876608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030435165,0.00012923173,0.00010514944,0.00004425156,0.0004907614,0.00041146268,0.00081039773,0.00003847206,0.000015323265],"category_scores_gemma":[0.000038528116,0.00007929356,0.00006324394,0.00016759455,0.000019928948,0.00047595712,0.00032370014,0.00014064446,0.00002206083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021602848,0.00006466825,0.000031191303,0.000021538444,0.0000096617705,0.000003286907,0.00048281034,0.00089707127,0.00010258392,0.040322214,0.0028750424,0.9551878],"study_design_scores_gemma":[0.00025916385,0.00009434242,0.000050361003,0.00007502465,0.0000030115098,0.000008916737,0.00008059987,0.97744024,0.00006683781,0.0021778797,0.019612141,0.00013149116],"about_ca_topic_score_codex":0.000019065614,"about_ca_topic_score_gemma":0.000011428503,"teacher_disagreement_score":0.9765432,"about_ca_system_score_codex":0.000031856885,"about_ca_system_score_gemma":0.000009337082,"threshold_uncertainty_score":0.3967744},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093883433,0.0000113889455,0.9934583,0.00083938113,0.00013896586,0.000046754834,5.1762817e-7,0.00029979672,0.0042660953],"genre_scores_gemma":[0.042132728,0.0000012659198,0.95736074,0.00040266494,0.000023030792,0.0000029524185,0.0000026432267,0.000002063138,0.00007189959],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994879,0.000021139791,0.000089676156,0.0001565018,0.00014221942,0.00010256993],"domain_scores_gemma":[0.99955857,0.000024421675,0.000023647546,0.00032949724,0.00002042467,0.000043461703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013964178,0.000049688657,0.00006508794,0.000033719974,0.000069345704,0.00007588989,0.00038429312,0.000018319242,0.000095779855],"category_scores_gemma":[0.000007644516,0.000036824844,0.000021093269,0.00013533766,0.0000065695367,0.00036369628,0.00018162114,0.00003782519,0.0002616366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.1232156e-7,0.00005115184,0.000012194061,0.000005474139,0.000003773464,0.0000068659333,0.0001483833,0.0005032796,0.0008974221,0.63819104,0.0016572939,0.3585228],"study_design_scores_gemma":[0.00036880097,0.000043626536,0.003154572,0.000017950275,0.0000017455343,0.00003697221,0.000008669168,0.9138448,0.0028263724,0.070761606,0.008808598,0.00012626001],"about_ca_topic_score_codex":0.00007821997,"about_ca_topic_score_gemma":0.000002302419,"teacher_disagreement_score":0.9133415,"about_ca_system_score_codex":0.000020549276,"about_ca_system_score_gemma":0.00002134069,"threshold_uncertainty_score":0.33628964},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034589846,0.000039255265,0.9640784,0.0003627127,0.00021539237,0.00019655254,0.000010248327,0.00015271848,0.00035484886],"genre_scores_gemma":[0.5862526,0.0000047596723,0.4122548,0.001356761,0.000023256856,0.00004075222,0.000055383003,0.0000054099964,0.000006205449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881464,0.00002680675,0.00048405185,0.00015868653,0.00027221508,0.0002436004],"domain_scores_gemma":[0.99920964,0.00006966491,0.00038603978,0.0002012852,0.00008600406,0.00004736933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028580058,0.00012931142,0.00015492605,0.0001433787,0.00028772862,0.00032290057,0.00038310158,0.000052389012,0.0000030591273],"category_scores_gemma":[0.000101534664,0.00010729079,0.00006463045,0.00031733245,0.00006312603,0.0055285483,0.00009636244,0.000086618595,0.0000032062521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020356616,0.00013664505,0.00275568,0.00029510757,0.00003708905,0.0000025876975,0.0027992236,0.00049109035,0.0046429355,0.013568265,0.002620644,0.9726304],"study_design_scores_gemma":[0.0033912456,0.00024566398,0.00808904,0.00047962114,0.00003982571,0.00007395594,0.00075290207,0.9068133,0.05453396,0.0064205737,0.018043526,0.0011163348],"about_ca_topic_score_codex":0.000015412785,"about_ca_topic_score_gemma":0.000001265464,"teacher_disagreement_score":0.97151405,"about_ca_system_score_codex":0.00003568714,"about_ca_system_score_gemma":0.000043447235,"threshold_uncertainty_score":0.43751916},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08004923,0.00012814532,0.9132617,0.0010971974,0.00037518473,0.00060532975,0.00004677519,0.0003683292,0.0040680645],"genre_scores_gemma":[0.900243,0.000012094676,0.098475985,0.00023084793,0.00021148512,0.00014453461,0.000019385936,0.000011871007,0.00065078447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998675,0.0000031113018,0.0002246548,0.00052827765,0.0002142833,0.00035467278],"domain_scores_gemma":[0.9992469,0.000020301566,0.00011699103,0.00021479308,0.00031188378,0.00008916091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014380377,0.0001723718,0.00016385026,0.00005938437,0.00020338812,0.00041813691,0.0010965443,0.00006593606,0.000024875955],"category_scores_gemma":[0.000016783813,0.00015255118,0.00005107706,0.00014035292,0.000040969833,0.0009387252,0.00035845026,0.000080713064,0.00004043749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018593099,0.000110286084,0.0026643018,0.00011167527,0.000014031179,0.00000533911,0.0007096001,0.000007680626,0.20412458,0.7143086,0.037420526,0.040504757],"study_design_scores_gemma":[0.0019158062,0.00043247474,0.010975553,0.00027189447,0.000029998917,0.000060855957,0.0002813562,0.3716321,0.1307082,0.13696006,0.3451627,0.0015690302],"about_ca_topic_score_codex":0.000037912054,"about_ca_topic_score_gemma":0.0000014769788,"teacher_disagreement_score":0.82019377,"about_ca_system_score_codex":0.000066685025,"about_ca_system_score_gemma":0.00011045478,"threshold_uncertainty_score":0.6220857},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026003104,0.0075324727,0.19679205,0.00003838065,0.002364649,0.00044744607,0.00093635224,0.00020939438,0.79167664],"genre_scores_gemma":[0.0006164993,0.006841296,0.09150569,0.00016221276,0.0031088954,0.00003207886,0.0029809235,0.0001648815,0.8945875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969179,0.0000582844,0.00090318697,0.00086455647,0.0008971326,0.00035891152],"domain_scores_gemma":[0.99604446,0.00020399917,0.0008096144,0.0025586535,0.00017025296,0.00021302473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037201366,0.00050848356,0.0008260033,0.00028055737,0.00013314173,0.00014845637,0.0019684504,0.0002804174,0.00005859865],"category_scores_gemma":[0.000036423386,0.0004528591,0.0001659743,0.00007702412,0.000078469224,0.00091211055,0.0009837314,0.00046708377,0.00018571095],"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":[0.00001569554,0.00011186776,0.00001103111,0.00069733534,0.00012114118,0.00036946475,0.00022167907,0.0001530342,0.00014557868,0.6420258,0.14998658,0.20614077],"study_design_scores_gemma":[0.000252387,0.0000679839,0.000010749531,0.0018600293,0.000033088687,0.000038460537,0.0000052012338,0.009012443,0.00001987851,0.0012557136,0.9869117,0.00053232745],"about_ca_topic_score_codex":0.00012800342,"about_ca_topic_score_gemma":0.0000039079678,"teacher_disagreement_score":0.83692515,"about_ca_system_score_codex":0.000053046697,"about_ca_system_score_gemma":0.00020378485,"threshold_uncertainty_score":0.99979234},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049317265,0.002588065,0.98977387,0.0011000218,0.0005370849,0.00045069703,0.00007761215,0.00018985951,0.0003510461],"genre_scores_gemma":[0.1584154,0.00039060944,0.8367726,0.0030248247,0.00047067043,0.00033549799,0.000073811425,0.000031322423,0.00048526388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981819,0.00007666371,0.00029739836,0.0005770898,0.00047237077,0.0003945722],"domain_scores_gemma":[0.9976665,0.0010695024,0.00022472243,0.00068334537,0.0002605519,0.00009537898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003878408,0.00022356908,0.00016670402,0.000046390127,0.00097263354,0.00052470225,0.0008982792,0.0000822946,0.000041223575],"category_scores_gemma":[0.00030762894,0.00015268142,0.000055015196,0.0002092243,0.00015814972,0.0032889172,0.00055149413,0.00020343706,0.000017043218],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018961426,0.00086643564,0.0019240731,0.000101986516,0.00007330885,0.00014977362,0.011610769,0.00013493162,0.015485319,0.03301811,0.018202022,0.91824365],"study_design_scores_gemma":[0.0020768761,0.0006249922,0.006135755,0.00017631172,0.00006790239,0.00035857968,0.0073909275,0.109193444,0.0073665,0.0035355082,0.8617945,0.0012787431],"about_ca_topic_score_codex":0.0019236716,"about_ca_topic_score_gemma":0.000019720635,"teacher_disagreement_score":0.9169649,"about_ca_system_score_codex":0.00004052251,"about_ca_system_score_gemma":0.000075572105,"threshold_uncertainty_score":0.7480809},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014699249,0.00006389248,0.9852185,0.0002337557,0.0006462412,0.00020174056,0.000004363153,0.00032282356,0.011838734],"genre_scores_gemma":[0.4957785,0.000005839539,0.5027296,0.0005991819,0.00040391117,0.000012052901,0.0000026932257,0.000012435176,0.0004558045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682176,0.000018341756,0.00026085012,0.0011112269,0.0011007822,0.00068704755],"domain_scores_gemma":[0.9977878,0.0000388053,0.00012145558,0.0014444835,0.00015614621,0.0004513073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005254174,0.00022662139,0.00020679565,0.00020516291,0.0009344902,0.0006468148,0.0037004764,0.00007138373,0.000046542507],"category_scores_gemma":[0.000016554939,0.00018395155,0.00003958364,0.0011763156,0.0007216627,0.0011945568,0.0020355831,0.00018415073,0.00042965641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059391364,0.000054050874,0.000009819089,0.0000022580034,0.0000020459227,0.000004855835,0.000828713,0.00002388513,0.12773877,0.01542403,0.003226834,0.8526788],"study_design_scores_gemma":[0.00037547588,0.00005342583,0.00055126316,0.000024295752,0.000002205599,0.000014627086,0.0000133907415,0.92325366,0.037070926,0.028555335,0.009793844,0.00029157038],"about_ca_topic_score_codex":0.000067195884,"about_ca_topic_score_gemma":0.0000037601033,"teacher_disagreement_score":0.92322975,"about_ca_system_score_codex":0.00007264088,"about_ca_system_score_gemma":0.0004097271,"threshold_uncertainty_score":0.7501326},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1990798,0.00018731368,0.79618376,0.0001681362,0.000040656338,0.000049951774,0.000004683342,0.00006315933,0.004222544],"genre_scores_gemma":[0.9701959,0.000031898053,0.029266512,0.00005176775,0.000011138324,3.819932e-7,8.886472e-7,0.0000027478163,0.00043879487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994813,0.000014250355,0.00007034212,0.00017052254,0.00013603523,0.00012750254],"domain_scores_gemma":[0.99963146,0.000033207198,0.000041694017,0.00021481207,0.000029136547,0.000049706272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059117778,0.00006190158,0.000089707595,0.00004167694,0.000086125845,0.00006176783,0.0002619937,0.000021202039,0.00004805267],"category_scores_gemma":[0.0000023831321,0.0000426934,0.000009729875,0.000126053,0.000043797212,0.000418987,0.00022961806,0.000039104227,0.0000042017045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037310918,0.0005946089,0.026340274,0.00012421081,0.000110248104,0.0001408493,0.006879163,0.0001010643,0.0026325055,0.8120602,0.008196588,0.142783],"study_design_scores_gemma":[0.0024248718,0.00035564843,0.0077963048,0.00013980836,0.000015002108,0.000057224304,0.0007415105,0.9634539,0.007542811,0.0010587989,0.015993427,0.00042072404],"about_ca_topic_score_codex":0.000034975077,"about_ca_topic_score_gemma":0.000013153733,"teacher_disagreement_score":0.9633528,"about_ca_system_score_codex":0.000005348754,"about_ca_system_score_gemma":0.0000061247015,"threshold_uncertainty_score":0.17409863},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000033725817,0.0038210251,0.0833647,0.00005080304,0.0017509138,0.0005025529,0.0011564243,0.00018200942,0.9091682],"genre_scores_gemma":[0.00007104233,0.0022847026,0.013796038,0.00008111755,0.0012591654,0.00001607425,0.001992636,0.000071080845,0.98042816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99675477,0.00004937169,0.00093921565,0.0008815856,0.001010528,0.0003645417],"domain_scores_gemma":[0.9957328,0.00012753034,0.0007492252,0.003007234,0.00015866086,0.00022458578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005630905,0.00048470835,0.00071409345,0.00033287524,0.00012107976,0.0001427757,0.0022051728,0.0003071042,0.0000840259],"category_scores_gemma":[0.00003588771,0.00042771126,0.00017612102,0.00010211686,0.00007231253,0.00089565525,0.0010730802,0.00046782897,0.00032587379],"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":[0.00001313046,0.000063883264,0.00000463445,0.00042819077,0.00008839051,0.00033045773,0.00018117632,0.000041418545,0.000035194258,0.53911823,0.37232137,0.08737392],"study_design_scores_gemma":[0.00021185272,0.000063566724,0.0000075390535,0.0010944546,0.000032619282,0.000061399995,0.0000102943095,0.0019145203,0.00001644356,0.0013893382,0.99472946,0.00046849946],"about_ca_topic_score_codex":0.0001085153,"about_ca_topic_score_gemma":0.000008374438,"teacher_disagreement_score":0.6224081,"about_ca_system_score_codex":0.00006410189,"about_ca_system_score_gemma":0.0001804075,"threshold_uncertainty_score":0.9998175},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03937841,0.000054033142,0.9594457,0.00016891511,0.00048687457,0.0003362071,0.000006007573,0.000071104,0.00005271699],"genre_scores_gemma":[0.47104287,0.0000013947376,0.52878946,0.000031404405,0.00011041735,0.000011630742,0.0000039653332,0.000003736731,0.0000051366915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823785,0.000024866848,0.0004318525,0.00048192084,0.00047161168,0.00035191336],"domain_scores_gemma":[0.99863356,0.000060570306,0.00028064783,0.00060416776,0.0003191855,0.000101884114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006524216,0.00014193797,0.00023430612,0.00024209337,0.00018692495,0.00020409905,0.0017662417,0.00003769071,0.00000217375],"category_scores_gemma":[0.000019645959,0.00012121298,0.00009181899,0.00054446526,0.00032538635,0.0014857504,0.0006149865,0.0000677338,0.0000016758747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050470685,0.000093558294,0.000047753365,0.000029638955,0.0000061662727,2.5092407e-7,0.0008486199,0.0030106425,0.03204997,0.0070690573,0.00023440867,0.9566049],"study_design_scores_gemma":[0.0002859896,0.00023769205,0.0001382936,0.00006541094,0.0000035877972,0.000003927703,0.000014723202,0.91353726,0.081730515,0.00020236784,0.0036486948,0.00013155265],"about_ca_topic_score_codex":0.000012340938,"about_ca_topic_score_gemma":0.0000033880865,"teacher_disagreement_score":0.95647335,"about_ca_system_score_codex":0.000034781708,"about_ca_system_score_gemma":0.00010849526,"threshold_uncertainty_score":0.4942922},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17937668,0.0013603434,0.73924685,0.028141282,0.0032931692,0.0068320604,0.0030149168,0.002681941,0.03605275],"genre_scores_gemma":[0.9167901,0.000073407085,0.07623648,0.00050599553,0.00082845095,0.00020789792,0.0003205968,0.00010705393,0.0049299835],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615,0.00003770514,0.00068916223,0.0010266103,0.0013328819,0.00076362473],"domain_scores_gemma":[0.997339,0.00010914522,0.00069321,0.00093958975,0.00071384,0.0002051975],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042587373,0.0005334148,0.00048138737,0.0003703877,0.0006268645,0.0003444926,0.0028821162,0.000163474,0.000010572268],"category_scores_gemma":[0.00008010958,0.0003596639,0.00025911737,0.001945332,0.00018788336,0.0018119778,0.0012793792,0.00042830256,0.000053888514],"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":[0.00071148225,0.0064637796,0.03606915,0.0009509601,0.0010700563,0.000030136242,0.003120492,0.0061942553,0.020446327,0.075100854,0.60679007,0.24305245],"study_design_scores_gemma":[0.014012379,0.006493737,0.14541243,0.002278304,0.00079002447,0.0004486816,0.0034287507,0.3415755,0.13626613,0.030360445,0.31261078,0.0063228426],"about_ca_topic_score_codex":0.00026645267,"about_ca_topic_score_gemma":0.0000075142375,"teacher_disagreement_score":0.73741347,"about_ca_system_score_codex":0.00015343004,"about_ca_system_score_gemma":0.00009348222,"threshold_uncertainty_score":0.99988556},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015531543,0.00012911297,0.5016745,0.0000057255365,0.0008974433,0.00022904461,0.00017612916,0.00034014255,0.4965324],"genre_scores_gemma":[0.7947498,0.000012288284,0.05784352,0.0004971417,0.0014536723,0.0000917883,0.00017176324,0.00018512113,0.14499493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979508,0.00003231552,0.00038988903,0.00082923647,0.0004732543,0.00032452084],"domain_scores_gemma":[0.9977806,0.000016993486,0.00030401617,0.0014994857,0.00015576923,0.00024312988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014088415,0.0004363788,0.0003738964,0.000075312004,0.0001526446,0.00026156378,0.0015802799,0.00039739403,0.000018597717],"category_scores_gemma":[0.0000034345746,0.00038491286,0.00013753504,0.000017131386,0.000048280486,0.00033198,0.000546744,0.00023254186,0.00031754837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000355299,0.000018486526,0.000012109089,0.000042163152,0.000021542557,0.00009029671,0.00011401473,7.206345e-7,0.000014422043,0.79341173,0.001024641,0.2052463],"study_design_scores_gemma":[0.0045355805,0.0023093373,0.004033248,0.013550976,0.00061610795,0.0015817392,0.00017999725,0.31401122,0.0014946222,0.36750183,0.27821428,0.011971087],"about_ca_topic_score_codex":0.0001706422,"about_ca_topic_score_gemma":0.000032396914,"teacher_disagreement_score":0.79473424,"about_ca_system_score_codex":0.00021267621,"about_ca_system_score_gemma":0.0000781616,"threshold_uncertainty_score":0.9998603},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042658212,0.001327011,0.94859636,0.0002680745,0.003809092,0.00032085853,0.000020600928,0.00028874195,0.04532661],"genre_scores_gemma":[0.0031051566,0.0005211106,0.9199597,0.0013033733,0.0013856473,0.000023066466,0.0000678837,0.00009907374,0.073534966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994145,0.000051262476,0.0007611517,0.0023668522,0.0018220241,0.00085374026],"domain_scores_gemma":[0.9957601,0.0001807726,0.00037633686,0.002929647,0.00038515197,0.00036798796],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009567109,0.0006459828,0.0007441735,0.00080024503,0.00043985687,0.0010873659,0.006351201,0.00033821655,0.00013357746],"category_scores_gemma":[0.000018971308,0.00059144327,0.00016645867,0.00064069155,0.0006923185,0.0016459388,0.0073358,0.00092424185,0.00022608959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000289262,0.00008681061,0.00001116729,0.000040256167,0.000009439842,0.00066224247,0.00023701883,0.00068760756,0.00010177654,0.19576119,0.002927518,0.7994721],"study_design_scores_gemma":[0.000707112,0.00014980984,0.00042117102,0.002052801,0.000009525561,0.0002585955,0.0000020639568,0.83279425,0.0006469767,0.04174176,0.11967987,0.0015360441],"about_ca_topic_score_codex":0.000025513562,"about_ca_topic_score_gemma":0.000009195828,"teacher_disagreement_score":0.83210665,"about_ca_system_score_codex":0.00028748187,"about_ca_system_score_gemma":0.000814857,"threshold_uncertainty_score":0.9999496},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08993967,0.00053970737,0.90218246,0.0014329486,0.0008983496,0.00036057472,0.000011557334,0.00072301674,0.0039117374],"genre_scores_gemma":[0.79667646,0.000047605852,0.20207916,0.00045464904,0.00036736036,0.000021094897,0.000068206245,0.000020526031,0.00026491936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998143,0.000100519384,0.00032311128,0.00056276855,0.0004178797,0.00045267402],"domain_scores_gemma":[0.99788827,0.00033712946,0.00019852296,0.0013362569,0.00007639353,0.00016341823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029528863,0.0002135922,0.00022785703,0.00010242754,0.00035649363,0.00026949996,0.0021987658,0.00010081415,0.00008443875],"category_scores_gemma":[0.00012934075,0.00017351526,0.000057321253,0.00031820068,0.00004226667,0.0011385845,0.0012309625,0.00022752989,0.00021132249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008019148,0.00034485638,0.014051081,0.00009750245,0.00004718126,0.0004710276,0.00096973137,0.0005597559,0.020208646,0.0026232053,0.011196687,0.9493501],"study_design_scores_gemma":[0.0014547774,0.00029535487,0.017406382,0.00036964857,0.000031079355,0.00021255559,0.00010053643,0.87661123,0.010443778,0.00998139,0.08202488,0.0010683796],"about_ca_topic_score_codex":0.00020540065,"about_ca_topic_score_gemma":0.000024017629,"teacher_disagreement_score":0.94828176,"about_ca_system_score_codex":0.000022243237,"about_ca_system_score_gemma":0.000024154564,"threshold_uncertainty_score":0.7075747},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034323107,0.0000141659975,0.9628581,0.0002430004,0.000028726146,0.00013268378,0.00001256773,0.0000335591,0.002354112],"genre_scores_gemma":[0.88673264,0.0000032500425,0.11244034,0.00045838865,0.00000513575,0.0000013159973,0.0000048775237,0.000003831067,0.00035020104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995187,0.00003557798,0.00005125506,0.00014440849,0.0001435136,0.00010655071],"domain_scores_gemma":[0.9991816,0.00035100442,0.000051276962,0.00032041327,0.00006643297,0.000029250856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017341711,0.00006232487,0.000075809825,0.000024627123,0.00016720165,0.000032301457,0.0003916477,0.000019747267,0.000038128248],"category_scores_gemma":[0.000016598826,0.000034861005,0.000024151177,0.00012248839,0.000060027014,0.00012597724,0.000035310615,0.000036004596,0.000004522897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001095115,0.00018247208,0.0014223567,0.000023770439,0.000031022348,0.0000045498455,0.00038906615,0.0026746995,0.00025820694,0.97203773,0.013512982,0.009353619],"study_design_scores_gemma":[0.0042548594,0.0019824423,0.003928419,0.00019615403,0.00004004853,0.0000063628545,0.0010686647,0.5495756,0.0341564,0.017633174,0.38649312,0.0006647058],"about_ca_topic_score_codex":0.000077985074,"about_ca_topic_score_gemma":0.000044624154,"teacher_disagreement_score":0.9544046,"about_ca_system_score_codex":0.000007856482,"about_ca_system_score_gemma":0.000060143346,"threshold_uncertainty_score":0.14215906},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027070392,0.000034561723,0.9782262,0.00072337216,0.0003006952,0.000018796962,6.6861594e-7,0.00017287221,0.01781579],"genre_scores_gemma":[0.24072698,0.000008275209,0.75582355,0.00053641194,0.00043763724,0.0000027524063,0.0000029162754,0.0000028787626,0.002458598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956644,0.000008974799,0.000067176006,0.00014271012,0.000117982905,0.00009674139],"domain_scores_gemma":[0.9997435,0.000014970627,0.000014191845,0.00016885069,0.000017926946,0.000040554354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006943809,0.000038858914,0.000033999084,0.00003386493,0.00008476568,0.000082863764,0.00026690713,0.000016646583,0.00025659936],"category_scores_gemma":[0.000004226943,0.000030942927,0.000020385696,0.00008632841,0.000006476724,0.0005736628,0.0001759765,0.000036147805,0.00025051017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013086411,0.000040296967,0.00018085746,0.0000010342787,0.0000054508123,0.0000035309638,0.000056544213,0.00025925797,0.0024652882,0.1364777,0.0329136,0.8275951],"study_design_scores_gemma":[0.00014969475,0.0000116963665,0.00081365183,0.0000040495647,8.743251e-7,0.000030419567,0.0000024303442,0.6752373,0.01005408,0.0012523402,0.31233495,0.00010850236],"about_ca_topic_score_codex":0.000016262073,"about_ca_topic_score_gemma":0.0000060314105,"teacher_disagreement_score":0.82748663,"about_ca_system_score_codex":0.000017150052,"about_ca_system_score_gemma":0.000018559076,"threshold_uncertainty_score":0.3219885},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36779308,0.00025059917,0.625621,0.0012210374,0.0005241249,0.00019156869,0.000012940508,0.00035017545,0.004035445],"genre_scores_gemma":[0.7970473,0.0000012612926,0.2026271,0.00019696167,0.00006645338,0.000003041337,0.000024141897,0.000004504393,0.000029218103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991679,0.000036115453,0.0001022568,0.00022899255,0.00031816593,0.00014656893],"domain_scores_gemma":[0.9992757,0.00008964507,0.00007492122,0.00038995498,0.00006199308,0.00010780277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014835682,0.0000914287,0.00009005263,0.000046421403,0.000076287244,0.00018513406,0.0007658963,0.000025317011,0.00000541108],"category_scores_gemma":[0.000041439842,0.000064815016,0.000011003653,0.00014115521,0.000028202621,0.0008603332,0.0004006996,0.000061862,0.00008026227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034904692,0.0008114463,0.07640538,0.000115171635,0.0002169407,0.00053099816,0.014018831,0.017205901,0.0017761034,0.03150702,0.12325748,0.73380566],"study_design_scores_gemma":[0.0051958044,0.002303591,0.05451621,0.00024985353,0.000056871082,0.00018317607,0.0017414772,0.8696501,0.0065334914,0.013825704,0.044229206,0.0015144749],"about_ca_topic_score_codex":0.00013947101,"about_ca_topic_score_gemma":0.000023503484,"teacher_disagreement_score":0.85244423,"about_ca_system_score_codex":0.000020345737,"about_ca_system_score_gemma":0.00004890122,"threshold_uncertainty_score":0.26430798},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03760092,0.00024833748,0.9588804,0.00019930249,0.000951774,0.00013267776,0.0000059589297,0.000110345456,0.0018702665],"genre_scores_gemma":[0.6334695,0.000008568251,0.3662929,0.000045417793,0.000037273257,0.000004607027,0.00004793753,0.0000054936672,0.00008826849],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869525,0.000060452854,0.0002720268,0.00046688438,0.00037041557,0.0001349386],"domain_scores_gemma":[0.9987454,0.000040582006,0.0001964845,0.0007475524,0.00021077748,0.000059222642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001742943,0.00014766563,0.00026084305,0.00010136304,0.000037641188,0.00015810241,0.00071181805,0.00012683634,0.000021594231],"category_scores_gemma":[0.000015137414,0.0001264862,0.00009976816,0.00018861836,0.0000226229,0.000052630774,0.00353575,0.00020893598,0.000007887286],"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":[0.0000061043966,0.000440406,0.000121695426,0.00040913883,0.000078165096,0.0000392631,0.0017892434,0.8750149,0.002221821,0.01672724,0.0025472196,0.100604795],"study_design_scores_gemma":[0.00012094582,0.000016418178,0.0013053364,0.00017036355,0.000005413464,0.0000034897914,0.000038024922,0.9953138,0.0022747393,0.0005193877,0.00008601986,0.00014604306],"about_ca_topic_score_codex":0.00014610191,"about_ca_topic_score_gemma":0.0000032694404,"teacher_disagreement_score":0.5958686,"about_ca_system_score_codex":0.000027762024,"about_ca_system_score_gemma":0.00016809207,"threshold_uncertainty_score":0.51579577},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57621574,0.0026164881,0.24776708,0.08083202,0.009403009,0.013389737,0.010511503,0.0044889594,0.054775454],"genre_scores_gemma":[0.9323636,0.0001270232,0.057131656,0.0016408766,0.0013634795,0.00022980756,0.00026890432,0.00014247373,0.006732172],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954686,0.00006195262,0.0008366218,0.0011708807,0.0014301814,0.0010317211],"domain_scores_gemma":[0.99764144,0.00011107832,0.000411563,0.0010429707,0.00055316684,0.00023979842],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064998335,0.00063963706,0.00057577307,0.00028764544,0.0008914202,0.00044489102,0.0040129116,0.00021081959,0.0000246255],"category_scores_gemma":[0.000112080015,0.00045288648,0.00042560694,0.0009773214,0.00014765166,0.0016951212,0.0018176746,0.0005910155,0.00011326103],"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":[0.0004950535,0.0093995705,0.0053230417,0.0006227093,0.0008501148,0.000049110567,0.006130023,0.004943384,0.041348945,0.31981602,0.53970253,0.0713195],"study_design_scores_gemma":[0.01227397,0.0054445844,0.020300774,0.0025660149,0.00041076826,0.0002303789,0.0018541219,0.41948032,0.30016977,0.023714786,0.20845048,0.0051040426],"about_ca_topic_score_codex":0.00015567653,"about_ca_topic_score_gemma":0.000007760523,"teacher_disagreement_score":0.41453692,"about_ca_system_score_codex":0.00013918424,"about_ca_system_score_gemma":0.0000919248,"threshold_uncertainty_score":0.9997923},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90091497,0.0017358771,0.08556395,0.0031976642,0.003418396,0.002308571,0.0013831463,0.0013403068,0.00013712999],"genre_scores_gemma":[0.9733172,0.00031583363,0.023999766,0.0012516526,0.00065207726,0.00026987516,0.0000030562585,0.0001765429,0.000013988651],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99458516,0.00044100525,0.00078436144,0.0018474178,0.0012462052,0.0010958491],"domain_scores_gemma":[0.99516296,0.00022496597,0.00043848524,0.0035867034,0.00025231013,0.00033454338],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013048833,0.0009786795,0.0007976218,0.00032866502,0.0012358829,0.0009903675,0.0036037248,0.00042072494,0.00038795325],"category_scores_gemma":[0.00008182825,0.0007934486,0.00038174618,0.0009865935,0.00022205283,0.00077969005,0.0020255125,0.0020024758,0.00007118937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018139237,0.0064591216,0.01940034,0.004251389,0.004875503,0.0054230774,0.0046525253,0.13113023,0.4366749,0.30599076,0.07849037,0.0008378639],"study_design_scores_gemma":[0.0036303333,0.0006964903,0.026372746,0.0017627464,0.00048363852,0.0000015882227,0.000102373044,0.54891646,0.19320129,0.0003122841,0.2168346,0.007685458],"about_ca_topic_score_codex":0.0002376326,"about_ca_topic_score_gemma":0.0000030395497,"teacher_disagreement_score":0.4177862,"about_ca_system_score_codex":0.00048049737,"about_ca_system_score_gemma":0.0008823775,"threshold_uncertainty_score":0.99945164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046226565,0.0002148887,0.91001743,0.0015770864,0.02749305,0.0016476925,0.000109879235,0.0010689254,0.011644475],"genre_scores_gemma":[0.90494454,3.7138594e-7,0.07915201,0.00057269016,0.0001005798,0.00033487962,0.0005411716,0.000025931968,0.0143278465],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965379,0.00011453726,0.0003453641,0.0012466396,0.0013775711,0.00037795445],"domain_scores_gemma":[0.9966176,0.000021325606,0.00024796053,0.0028796245,0.00006911741,0.0001643342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001958311,0.00015002882,0.00013648719,0.00028200532,0.0012857078,0.00051480293,0.00096031063,0.000022005168,0.00042492096],"category_scores_gemma":[0.00006917872,0.00013482681,0.000074054435,0.001012343,0.00009575077,0.0005985201,0.0011877161,0.00022809433,0.000054277018],"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":[0.00005972016,0.0014888111,0.0007653617,0.0000755186,0.000021410318,0.00724486,0.0005703274,0.013478756,0.39786288,0.008341203,0.46408406,0.1060071],"study_design_scores_gemma":[0.00025859097,0.00016808008,0.00012278621,0.0000421561,0.000004544408,0.0001690778,0.00003588862,0.20635903,0.18448104,0.003903604,0.6040567,0.00039848706],"about_ca_topic_score_codex":0.00003198807,"about_ca_topic_score_gemma":0.0000012625854,"teacher_disagreement_score":0.858718,"about_ca_system_score_codex":0.00009017529,"about_ca_system_score_gemma":0.00032393125,"threshold_uncertainty_score":0.9888755},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98580253,0.00033787388,0.0068035624,0.005246043,0.00085111446,0.00008372662,0.000006032384,0.0000069990338,0.00086214655],"genre_scores_gemma":[0.98584867,0.000013208586,0.01383334,0.00021070476,0.000038608025,0.0000026939522,2.761149e-7,0.0000017704097,0.000050761042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988495,0.00018921633,0.0002674724,0.00018927813,0.00028519568,0.0002193243],"domain_scores_gemma":[0.99922353,0.00029175845,0.00015418242,0.00008971286,0.000028419818,0.00021236917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020318336,0.00006984353,0.00014221633,0.00015193337,0.00066883274,0.0003249129,0.0006627442,0.000017727087,0.000253918],"category_scores_gemma":[0.00040152855,0.000057655772,0.000025438061,0.0006970473,0.00020671764,0.00082446035,0.00008081631,0.00016307947,3.3677523e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039220784,0.00014178362,0.2505969,0.000033428918,0.00003883062,0.0002987862,0.015894815,0.000915188,0.0014380543,0.01765261,0.02397091,0.68897945],"study_design_scores_gemma":[0.0008906725,0.0016557092,0.13188289,0.00010431142,0.00001621674,0.0009383913,0.0050353683,0.76987976,0.0004704192,0.04562602,0.04290863,0.00059158675],"about_ca_topic_score_codex":0.0036106792,"about_ca_topic_score_gemma":0.0034691838,"teacher_disagreement_score":0.7689646,"about_ca_system_score_codex":0.00008235737,"about_ca_system_score_gemma":0.0011673665,"threshold_uncertainty_score":0.5458291},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51344013,0.002523582,0.47566688,0.00063206995,0.0011654643,0.0006336296,0.0055359616,0.0001968285,0.00020546187],"genre_scores_gemma":[0.03875537,0.0008210607,0.9512298,0.000720849,0.0003375409,0.0000322703,0.007849482,0.00004122915,0.00021236489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978149,0.00017969761,0.0002867655,0.0012229601,0.0002264484,0.00026925703],"domain_scores_gemma":[0.9954129,0.00008967697,0.00015599091,0.0042118463,0.000010052965,0.00011956966],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.000627375,0.00018861557,0.0002231134,0.00009969885,0.0004522383,0.0002654116,0.003498631,0.000036880898,0.0000391541],"category_scores_gemma":[0.00002843194,0.00018120765,0.000014359284,0.00011522324,0.000089659174,0.0008359228,0.019260796,0.00018888136,0.00001737778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077585434,0.0005158966,0.01864202,0.00017054111,0.0002468651,0.00013933076,0.00080718554,0.0028213835,0.02596853,0.14871238,0.13987768,0.66132236],"study_design_scores_gemma":[0.002226942,0.00016518922,0.021155544,0.000013614268,0.00003439122,0.00033438345,0.000075175376,0.6264649,0.00002984405,0.003130865,0.34583768,0.000531474],"about_ca_topic_score_codex":0.00021605463,"about_ca_topic_score_gemma":0.000053437892,"teacher_disagreement_score":0.66079086,"about_ca_system_score_codex":0.000047272435,"about_ca_system_score_gemma":0.00014952308,"threshold_uncertainty_score":0.98867124},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019014663,0.000060195154,0.9961226,0.0012959604,0.0005101861,0.00014985529,0.00012884074,0.00013385013,0.0014083503],"genre_scores_gemma":[0.042105466,0.0000057204056,0.9504647,0.002104114,0.00014978697,0.00010999272,0.0005300653,0.000010912632,0.004519238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922323,0.000025503045,0.00009433951,0.00034278654,0.00017710864,0.00013700998],"domain_scores_gemma":[0.99849975,0.00007614355,0.00002892187,0.0013418816,0.000015146262,0.00003815865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002684519,0.000051085408,0.000067241635,0.000029142488,0.00027354129,0.00008763327,0.0025300176,0.00000817728,0.0001958204],"category_scores_gemma":[0.000018095481,0.000041717696,0.000018184506,0.000119623735,0.0000059194576,0.00051554554,0.00450748,0.000054586857,0.000012490527],"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":[0.000018487077,0.00012213884,0.00005355837,0.0000069379257,0.0000116420015,0.000008658903,0.00013252816,0.00009204949,0.0006752518,0.061367,0.6016196,0.33589217],"study_design_scores_gemma":[0.00026869777,0.00003424916,0.000062368046,7.213688e-7,9.806754e-7,0.0000052481478,0.000009734139,0.48424047,0.00008428049,0.0019490628,0.5132853,0.00005889579],"about_ca_topic_score_codex":0.000026309552,"about_ca_topic_score_gemma":0.0000021858225,"teacher_disagreement_score":0.48414844,"about_ca_system_score_codex":0.000012002186,"about_ca_system_score_gemma":0.00004449048,"threshold_uncertainty_score":0.56182516},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80070585,0.0047924626,0.026004432,0.05250406,0.00991946,0.006011425,0.00071622455,0.0021057315,0.097240366],"genre_scores_gemma":[0.987028,0.000030529736,0.010235769,0.00067980523,0.00006971382,0.00012495676,0.0000046074865,0.000013252894,0.0018133613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869895,0.000010233714,0.00019094301,0.00030666514,0.00057452585,0.00021868279],"domain_scores_gemma":[0.9991949,0.00001727809,0.00036199085,0.00030075587,0.00007834909,0.00004672578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003427073,0.00010459943,0.00013917858,0.00005941566,0.00039919332,0.00009004104,0.0019647714,0.000017193417,0.00005707698],"category_scores_gemma":[0.000035297744,0.00007306912,0.000053953605,0.00036559775,0.000031078795,0.00044241312,0.0036688459,0.0001944643,0.000007658596],"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":[0.00012806007,0.0012430145,0.030123476,0.0002852328,0.00015060112,0.000009969118,0.0028658283,0.00088377064,0.07552483,0.49902862,0.3328007,0.056955904],"study_design_scores_gemma":[0.0021625776,0.00046383266,0.015985832,0.00023587016,0.000049644586,0.00013103451,0.0022092252,0.024698097,0.18171312,0.06189088,0.7095927,0.00086719124],"about_ca_topic_score_codex":0.00006755797,"about_ca_topic_score_gemma":7.06538e-7,"teacher_disagreement_score":0.43713775,"about_ca_system_score_codex":0.000067916866,"about_ca_system_score_gemma":0.000024668157,"threshold_uncertainty_score":0.4572954},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042354444,0.8788355,0.00004971702,0.00014384977,0.0011245211,0.0015090709,0.00009411679,0.000028235783,0.11817264],"genre_scores_gemma":[0.0006180863,0.9946627,0.0007541634,0.00020363161,0.0006281629,0.00078892347,0.00027614058,0.00002647758,0.0020417343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98728645,0.00227778,0.0016785446,0.002351372,0.00473705,0.0016688213],"domain_scores_gemma":[0.99473655,0.001375337,0.0007397554,0.0012772243,0.0016391748,0.00023195834],"candidate_categories":["metaepi_narrow","bibliometrics","sts","scholarly_communication","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.022008272,0.0004921394,0.0015698416,0.010847575,0.006312427,0.0016699483,0.006838153,0.00018083266,0.00028779695],"category_scores_gemma":[0.0019366947,0.0004808842,0.00015829183,0.023517987,0.011871084,0.0109490035,0.0041753063,0.0020389888,0.0000059066365],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046330106,0.0004392183,0.00006203034,0.0053729056,0.000007671481,0.000001162899,0.010901973,4.1477438e-7,5.082011e-7,0.29875946,0.0006433284,0.6838067],"study_design_scores_gemma":[0.00015736502,0.000085622676,0.00035199642,0.0047592097,0.00003308043,0.0000044197227,0.03594551,0.00012136107,5.152825e-7,0.018935036,0.9391438,0.00046208355],"about_ca_topic_score_codex":0.0010850298,"about_ca_topic_score_gemma":0.002981132,"teacher_disagreement_score":0.93850046,"about_ca_system_score_codex":0.0024137397,"about_ca_system_score_gemma":0.018757641,"threshold_uncertainty_score":0.99976426},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009745549,0.00044951044,0.97512114,0.000436484,0.005697501,0.0014699543,0.0011837999,0.0005579318,0.0053381193],"genre_scores_gemma":[0.19241466,0.00083213346,0.785697,0.004499148,0.0016123469,0.0009232583,0.011902999,0.00023052655,0.0018879402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504757,0.0000831346,0.0018252253,0.000867002,0.0010655543,0.0011115316],"domain_scores_gemma":[0.9943733,0.00019074132,0.0010395206,0.003314693,0.00066021195,0.00042148936],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.000746536,0.00087703665,0.0010657541,0.00044716764,0.00047135746,0.0025730578,0.0044430746,0.0008618176,0.00007144699],"category_scores_gemma":[0.00014265024,0.0007935391,0.00070442137,0.0004553123,0.00010738934,0.0025045061,0.0087770065,0.0016286548,0.00016009946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025478285,0.0031621621,0.0026292182,0.009851505,0.0019736178,0.00030546286,0.048850607,0.0036828015,0.0001224945,0.039575227,0.18502611,0.704566],"study_design_scores_gemma":[0.0032181877,0.00022422096,0.00048660822,0.0012322973,0.00010059479,0.00015646762,0.00092314184,0.6031,0.0009097628,0.0031315645,0.38452768,0.0019894377],"about_ca_topic_score_codex":0.000059721904,"about_ca_topic_score_gemma":0.000011251079,"teacher_disagreement_score":0.7025766,"about_ca_system_score_codex":0.00023599622,"about_ca_system_score_gemma":0.00048152177,"threshold_uncertainty_score":0.9994516},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05631531,0.00021589454,0.93918014,0.00016948373,0.000513986,0.00041460135,0.00019700342,0.00048007624,0.0025135097],"genre_scores_gemma":[0.88753796,0.000040848037,0.11125504,0.0006810319,0.00002935889,0.00014748634,0.00028530473,0.000010042065,0.00001294888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978599,0.00018001585,0.00053801626,0.0003441275,0.0006909563,0.0003870059],"domain_scores_gemma":[0.9984951,0.00010598734,0.00038118905,0.00066391256,0.00019306263,0.00016077151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058581325,0.00024296094,0.00022769839,0.00037137733,0.0012367867,0.00054435595,0.0010293869,0.00007308657,0.000062545245],"category_scores_gemma":[0.000056686145,0.00022973272,0.000055144377,0.0008528946,0.00017443644,0.0053816326,0.00094977603,0.00033068273,0.000021106829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077290766,0.00011329418,0.001163147,0.00035626348,0.000034564488,0.000041628482,0.0060890354,0.0059823873,0.013306753,0.053875845,0.0026296722,0.9163301],"study_design_scores_gemma":[0.0008457676,0.00035102968,0.002822628,0.00019729928,0.00001088559,0.00015211836,0.0005420187,0.9414209,0.0037312347,0.013180888,0.03608551,0.00065971137],"about_ca_topic_score_codex":0.00017620139,"about_ca_topic_score_gemma":0.0000016979393,"teacher_disagreement_score":0.9354385,"about_ca_system_score_codex":0.00019553081,"about_ca_system_score_gemma":0.00015762598,"threshold_uncertainty_score":0.9512489},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008958215,0.0001481987,0.9963201,0.00014037962,0.00011317564,0.0009154188,0.0004550767,0.00027951575,0.0007322674],"genre_scores_gemma":[0.62301207,0.00019878495,0.3691733,0.00012972456,0.00020994544,0.0000013109485,0.00615115,0.0009342907,0.00018941631],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980681,0.0005047812,0.00024903615,0.00063515117,0.0002833212,0.00025962954],"domain_scores_gemma":[0.9976485,0.00017936532,0.00015312238,0.0013052442,0.00061340205,0.000100372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009154085,0.00012774844,0.00018411665,0.00011450203,0.0010638086,0.00045153062,0.00298069,0.00006302931,0.0002798354],"category_scores_gemma":[0.00054674165,0.000121214754,0.00003366925,0.00041176847,0.000106915875,0.00067086774,0.0051645446,0.00014565808,0.00016085443],"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":[0.000084670544,0.0002452699,0.000003840563,0.00015194621,0.000046798323,0.000023443961,0.0005438348,0.0008798606,0.7552978,0.0028980419,0.045285054,0.19453944],"study_design_scores_gemma":[0.001230749,0.00046250713,0.00044574973,0.00022569622,0.00002036574,0.00018948634,0.00013007935,0.25430456,0.2723096,0.0016018797,0.46868443,0.00039491357],"about_ca_topic_score_codex":0.000011574246,"about_ca_topic_score_gemma":1.3799601e-7,"teacher_disagreement_score":0.62714684,"about_ca_system_score_codex":0.00006332409,"about_ca_system_score_gemma":0.000014906605,"threshold_uncertainty_score":0.81820625},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043876626,0.00012654577,0.8427548,0.0038203415,0.0000914121,0.00064013404,0.00015187748,0.001320028,0.10721827],"genre_scores_gemma":[0.9929186,0.000016896267,0.0063413717,0.000318779,0.000046891,4.134648e-8,0.0001343153,0.00017042758,0.00005268592],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986505,0.00020054818,0.00020136702,0.0003557561,0.0003746817,0.00021714957],"domain_scores_gemma":[0.9988672,0.00002720191,0.00007918295,0.0005636421,0.0003427148,0.00012006636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040482648,0.000104209146,0.00011608778,0.000040647396,0.0011269309,0.00044484728,0.0016051633,0.000033307617,0.0006806541],"category_scores_gemma":[0.00019135915,0.000073738345,0.000025829328,0.00061963405,0.00023487373,0.00054132723,0.0014787285,0.00021773546,0.00020977165],"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":[0.00016978911,0.00016374425,0.00017084971,0.000116286945,0.00008100127,0.000047202804,0.008705875,0.00033376273,0.022778355,0.039368834,0.068684496,0.8593798],"study_design_scores_gemma":[0.0005541214,0.00082550134,0.005291048,0.00012651128,0.00001794381,0.00013279726,0.0015285305,0.17275465,0.013506961,0.00032608677,0.8044541,0.00048177163],"about_ca_topic_score_codex":0.000015660127,"about_ca_topic_score_gemma":1.874265e-7,"teacher_disagreement_score":0.94904196,"about_ca_system_score_codex":0.000019000581,"about_ca_system_score_gemma":0.000011429358,"threshold_uncertainty_score":0.8667556},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09282789,0.00013751435,0.90476495,0.0014344344,0.0006163672,0.00012406503,0.00002960513,0.000015462294,0.00004970917],"genre_scores_gemma":[0.7099292,8.3860107e-7,0.28956082,0.00032866036,0.00014042128,0.0000044627373,0.0000176459,0.0000030827548,0.0000148711015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896777,0.00013558764,0.00036525266,0.00014878713,0.00022959033,0.00015303798],"domain_scores_gemma":[0.9989319,0.00025634194,0.0004584695,0.00008381608,0.00021805275,0.0000514559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062427577,0.000075614,0.00017146634,0.00013610788,0.00030232398,0.00004265044,0.00070937845,0.000023659304,0.000022400282],"category_scores_gemma":[0.000046720932,0.00006359294,0.0000932617,0.00016017503,0.000041167714,0.00022457483,0.00031679135,0.00016937319,0.0000016118454],"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":[0.00020034095,0.00022648144,0.00050423347,0.000018000479,0.00011325321,0.000053071657,0.00039820946,0.57330984,0.011180765,0.3048569,0.00604945,0.103089444],"study_design_scores_gemma":[0.0015905718,0.0020735306,0.0012816072,0.00002084256,0.0000085028305,0.0007830663,0.000103233266,0.59451383,0.0005925374,0.35342777,0.04537496,0.00022953018],"about_ca_topic_score_codex":0.00000408815,"about_ca_topic_score_gemma":1.1849337e-7,"teacher_disagreement_score":0.6171013,"about_ca_system_score_codex":0.000062048166,"about_ca_system_score_gemma":0.0002603124,"threshold_uncertainty_score":0.2593245},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27497232,0.0014674816,0.7151601,0.0002594749,0.0036205803,0.002310545,0.0011467242,0.0010508811,0.000011890236],"genre_scores_gemma":[0.887336,0.0000347968,0.109995455,0.0005625604,0.00064743875,0.0012623214,0.000004036397,0.00014926751,0.000008089298],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99469596,0.0002182526,0.0008170338,0.0023266887,0.0009152396,0.001026849],"domain_scores_gemma":[0.99417573,0.000114403396,0.0005564041,0.003950924,0.00045657303,0.00074594043],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001103618,0.0007673759,0.00088795304,0.0005520022,0.00064537243,0.00084592035,0.0042588483,0.0003801852,0.000052274245],"category_scores_gemma":[0.00008130211,0.00083130127,0.00020271445,0.0009835626,0.000062575324,0.00031844416,0.0054288986,0.0008613603,0.000059016314],"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":[0.00053242844,0.006462043,0.029637828,0.0021538185,0.0009758554,0.00034491345,0.0010085194,0.21808206,0.7049898,0.020429432,0.014568613,0.00081471744],"study_design_scores_gemma":[0.0021293662,0.0011560009,0.12002989,0.00039145866,0.00018024251,6.600199e-8,0.00003319808,0.5058424,0.032788113,0.00002808462,0.33273184,0.0046893354],"about_ca_topic_score_codex":0.000107534404,"about_ca_topic_score_gemma":0.000003798949,"teacher_disagreement_score":0.67220163,"about_ca_system_score_codex":0.0005352431,"about_ca_system_score_gemma":0.0006489116,"threshold_uncertainty_score":0.9994138},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29282746,0.000095575866,0.7038193,0.000204782,0.0003579863,0.00027265816,0.00023690832,0.00009177807,0.00209356],"genre_scores_gemma":[0.9964157,0.00011107911,0.0029685933,0.00002281657,0.000056021385,4.874213e-7,0.000011076367,0.000009621857,0.00040465707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983633,0.00010237404,0.00023393209,0.00090798346,0.00013751711,0.0002548475],"domain_scores_gemma":[0.99719757,0.00022736866,0.00028214365,0.0019784963,0.00013051218,0.00018390376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018857278,0.00022691622,0.0003630086,0.00019420867,0.00013347418,0.00007095291,0.001865761,0.00017197446,0.000017193004],"category_scores_gemma":[0.00004669576,0.00019825122,0.00012711927,0.00021611771,0.00023790763,0.00024114484,0.004307124,0.00026741883,0.000013537223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013966295,0.0006897925,0.009500892,0.00032220295,0.00031650413,0.00028845132,0.0006401938,0.24683009,0.0014045177,0.73164785,0.0053725983,0.0028472554],"study_design_scores_gemma":[0.0011240747,0.00008086673,0.020902298,0.00033247872,0.0000602715,0.0000068638474,0.000032972755,0.92068696,0.0006495997,0.055491924,0.00021956355,0.00041215195],"about_ca_topic_score_codex":0.00018493885,"about_ca_topic_score_gemma":0.000008808434,"teacher_disagreement_score":0.7035882,"about_ca_system_score_codex":0.000071637645,"about_ca_system_score_gemma":0.00019357672,"threshold_uncertainty_score":0.80844504},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042365375,0.000059973805,0.991018,0.0011122277,0.0009393115,0.00040560003,0.00011440941,0.0002010275,0.0019128892],"genre_scores_gemma":[0.029001368,0.000012605005,0.9693454,0.0010338012,0.00009112994,0.00008905225,0.000089567024,0.000012167362,0.00032489924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989079,0.000027481165,0.00028293612,0.00015566543,0.00034774782,0.00027827467],"domain_scores_gemma":[0.99907213,0.00012625208,0.00020519286,0.00045510227,0.000060155304,0.00008114479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038392254,0.0001176658,0.0001404773,0.00009249529,0.0006488346,0.00023444969,0.0010385395,0.0000271843,0.000023014796],"category_scores_gemma":[0.00006475785,0.00010523287,0.00006779752,0.00026086956,0.000028021335,0.0011065297,0.00078056805,0.0001338337,0.000024281377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012250111,0.0003751252,0.0007900332,0.0004752686,0.00017020317,0.00004903406,0.046869166,0.0149929775,0.001662485,0.3858577,0.22312789,0.3255076],"study_design_scores_gemma":[0.00043798794,0.0002069586,0.00017146632,0.000020374968,0.000006488808,0.000023652266,0.0015151467,0.87587893,0.00048861286,0.0044126837,0.11659682,0.000240893],"about_ca_topic_score_codex":0.000019826006,"about_ca_topic_score_gemma":0.0000019488953,"teacher_disagreement_score":0.8608859,"about_ca_system_score_codex":0.00007678084,"about_ca_system_score_gemma":0.00010313956,"threshold_uncertainty_score":0.49903768},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000148101535,0.00042830707,0.3340032,0.00020677596,0.0016234552,0.00031137245,0.00018761224,0.00017155691,0.6630529],"genre_scores_gemma":[0.0004990544,0.0042617004,0.25239363,0.0005636968,0.005003451,0.00004845766,0.00050960144,0.00026724298,0.7364532],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962647,0.000073238465,0.00071387255,0.0010703632,0.0013560709,0.0005217791],"domain_scores_gemma":[0.99702024,0.00036645567,0.0004919333,0.0016651071,0.00015646387,0.00029978124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005733123,0.00063132995,0.00079473277,0.00037017875,0.00019374052,0.00011003257,0.0020866098,0.00038867022,0.00019398452],"category_scores_gemma":[0.00005018471,0.00053080963,0.0003524025,0.00009189243,0.000163522,0.0003373376,0.0011241402,0.00095819996,0.00034999268],"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":[0.000023247878,0.000038837843,0.000018883018,0.000090430585,0.00008190407,0.00010005051,0.00024540172,0.0000584079,0.0000043552704,0.4208194,0.011544933,0.56697416],"study_design_scores_gemma":[0.0006293512,0.0005297104,0.00028340233,0.00067666697,0.000039643022,0.000029296865,0.0000033786773,0.015446622,0.000021949303,0.0243121,0.95708704,0.00094083877],"about_ca_topic_score_codex":0.000027540587,"about_ca_topic_score_gemma":0.0000040640016,"teacher_disagreement_score":0.9455421,"about_ca_system_score_codex":0.000062521576,"about_ca_system_score_gemma":0.00019065656,"threshold_uncertainty_score":0.9997144},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013319841,0.0005306985,0.9793588,0.0028048574,0.0015499488,0.001272467,0.00003923967,0.000055599077,0.0010685703],"genre_scores_gemma":[0.9863576,0.00016263404,0.012748134,0.00030084242,0.00014944546,0.00010906708,0.000010549898,0.000012175258,0.00014952704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812853,0.00024575595,0.00042095635,0.0004919307,0.00035304917,0.0003598035],"domain_scores_gemma":[0.99622697,0.0011858599,0.00029663526,0.0021662454,0.000072610106,0.00005170646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010668836,0.00023799855,0.0003888751,0.00004785862,0.00013390959,0.00017290415,0.0045287944,0.00016577836,0.000011163734],"category_scores_gemma":[0.00011523848,0.000110077366,0.00022154626,0.00016769122,0.00017360684,0.00013918309,0.0032400817,0.0005256116,0.0000015688436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004361981,0.0004433574,0.008087398,0.00040316794,0.00015316058,0.000007941414,0.005000637,0.04214962,0.0001596151,0.5919832,0.005863016,0.34531268],"study_design_scores_gemma":[0.0015266744,0.000049841405,0.016612979,0.00043156385,0.000026941872,0.0000063575408,0.00005942908,0.93708515,0.0013552137,0.03785353,0.0046745525,0.00031776662],"about_ca_topic_score_codex":0.00079177396,"about_ca_topic_score_gemma":0.00054460217,"teacher_disagreement_score":0.9730378,"about_ca_system_score_codex":0.000046014873,"about_ca_system_score_gemma":0.0001862555,"threshold_uncertainty_score":0.84157026},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07698358,0.00010356339,0.9176317,0.0014769511,0.00078207935,0.00020314868,0.000012358786,0.00030798456,0.0024986302],"genre_scores_gemma":[0.8341814,0.000003730752,0.16480906,0.00087377924,0.000067878595,0.000022063181,0.000005834842,0.0000085612755,0.000027637083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969256,0.00027274058,0.0002849996,0.00089465274,0.00098421,0.0006377805],"domain_scores_gemma":[0.99838805,0.00019131218,0.00006578773,0.0010562647,0.00010529285,0.00019327537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015058807,0.00018187468,0.00021128391,0.0003526797,0.00071825285,0.0002798985,0.003793897,0.00003257111,0.00020159726],"category_scores_gemma":[0.000066976565,0.00015231421,0.00003968919,0.00326473,0.0009130723,0.00067727856,0.0050970986,0.00042919224,0.00004106286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015709811,0.00017079143,0.00012992894,0.000003547284,0.0000019515785,0.0001509861,0.0006927768,0.0018271779,0.0020301621,0.9551273,0.00046759984,0.039382096],"study_design_scores_gemma":[0.0004038724,0.0003493012,0.003284711,0.00001839697,0.0000017748227,0.000080962775,0.000037788486,0.9579932,0.00090491824,0.03459925,0.002007669,0.0003181708],"about_ca_topic_score_codex":0.00002382368,"about_ca_topic_score_gemma":0.000002640376,"teacher_disagreement_score":0.956166,"about_ca_system_score_codex":0.000121225276,"about_ca_system_score_gemma":0.00019460439,"threshold_uncertainty_score":0.7050068},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47993773,0.003160778,0.49554124,0.0076634134,0.004341841,0.0053642835,0.00018172924,0.0012901768,0.0025188026],"genre_scores_gemma":[0.9692787,0.000017151373,0.030090375,0.00008755281,0.00008250033,0.00023353864,0.000003842222,0.000015377878,0.00019099672],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981784,0.000017959615,0.00034718643,0.00045544523,0.0007106414,0.00029032637],"domain_scores_gemma":[0.99884295,0.00004930998,0.0005127885,0.0003858281,0.00014079097,0.000068321046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038993263,0.00017036907,0.00018708294,0.000105772786,0.0005141458,0.00015183966,0.0024394253,0.000029889283,0.000024270927],"category_scores_gemma":[0.000027417267,0.00012600957,0.00011118611,0.0005493456,0.000037006528,0.0005447305,0.003000215,0.00021323397,0.000005513974],"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":[0.00008645638,0.0006213713,0.0031540703,0.0003371648,0.00007190499,0.0000020528066,0.0015141878,0.0008478217,0.8288828,0.043166947,0.0052168104,0.11609842],"study_design_scores_gemma":[0.0018594998,0.00031344942,0.0068022925,0.0000814505,0.00006313472,0.00007735246,0.00036994324,0.60135645,0.3591512,0.008561823,0.020667313,0.00069606997],"about_ca_topic_score_codex":0.00026907204,"about_ca_topic_score_gemma":7.2347393e-7,"teacher_disagreement_score":0.60050863,"about_ca_system_score_codex":0.00013474045,"about_ca_system_score_gemma":0.00003206297,"threshold_uncertainty_score":0.5138522},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003958171,0.00045615208,0.9966446,0.0010574143,0.00005813991,0.0007672847,0.0000074949185,0.00010263676,0.0008666933],"genre_scores_gemma":[0.009625872,0.00033430514,0.98666394,0.0007449788,0.00025684794,0.0008715393,0.000008151964,0.000010341783,0.0014840077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993705,0.000010812091,0.00011272178,0.0002592798,0.00009326234,0.00015340793],"domain_scores_gemma":[0.9992472,0.00014879863,0.00003709647,0.00045955923,0.000052386786,0.0000549564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013190157,0.00007862842,0.000074504125,0.0000204598,0.00047306498,0.000102145365,0.0005158668,0.0000300058,0.0000057191037],"category_scores_gemma":[0.0000051945726,0.00004516029,0.000030124162,0.00012487522,0.000052961284,0.0003947258,0.00025007964,0.000052967443,0.0000063077955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050182375,0.00007264541,0.000054251825,0.000016228318,0.000018508828,9.756776e-7,0.00036157283,0.000033112243,0.000661998,0.1503252,0.0108328555,0.83761764],"study_design_scores_gemma":[0.00039948194,0.00004842222,0.0004596779,0.0000030779806,0.000005146678,0.000034746736,0.000022169237,0.8664424,0.00024228249,0.005469207,0.1267602,0.000113198184],"about_ca_topic_score_codex":0.000083024075,"about_ca_topic_score_gemma":0.000002206669,"teacher_disagreement_score":0.8664093,"about_ca_system_score_codex":0.0000054707552,"about_ca_system_score_gemma":0.00003035841,"threshold_uncertainty_score":0.36384812},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013173582,0.00014258928,0.9802296,0.00023623064,0.0012027555,0.00020763342,0.00002145737,0.00015644678,0.0046297153],"genre_scores_gemma":[0.6548976,0.000009237639,0.3444438,0.00008678142,0.00005367254,0.000024579329,0.00009176278,0.000011307205,0.00038128742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985825,0.000077061115,0.00026954172,0.00044939047,0.00048372836,0.00013779603],"domain_scores_gemma":[0.9988385,0.00004748917,0.00023555903,0.0007442896,0.0000826454,0.00005154032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026240182,0.0001430639,0.00022717046,0.00014990618,0.000077280674,0.00007159851,0.0010795776,0.000073183466,0.00011329737],"category_scores_gemma":[0.000010137299,0.00012608657,0.00009144592,0.00020638887,0.000021311014,0.000037222366,0.006388795,0.00029096915,0.000009761894],"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":[0.000005509251,0.00018595434,0.00006873291,0.00011445475,0.00002578552,0.000008666232,0.00063185825,0.9410339,0.0002102854,0.023982706,0.0034384893,0.030293679],"study_design_scores_gemma":[0.00012915212,0.000036065856,0.0010238313,0.000036487727,0.000004614371,0.0000019990391,0.000029195262,0.9953054,0.00025822694,0.001995378,0.0010316463,0.00014797364],"about_ca_topic_score_codex":0.00016426362,"about_ca_topic_score_gemma":0.0000010946274,"teacher_disagreement_score":0.641724,"about_ca_system_score_codex":0.00005116594,"about_ca_system_score_gemma":0.00012717275,"threshold_uncertainty_score":0.7963176},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070814356,0.0001861889,0.9222772,0.00006861534,0.001787123,0.0002090771,0.0003630708,0.00026170042,0.004032686],"genre_scores_gemma":[0.9612435,0.0007166267,0.032947805,0.00019780122,0.00020234498,0.000003493147,0.00045620112,0.000036585978,0.004195612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759346,0.0001353518,0.00021918499,0.0015336691,0.0001592208,0.00035911394],"domain_scores_gemma":[0.9970634,0.00016294143,0.0003029244,0.0022303783,0.00007132137,0.00016901769],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00017699577,0.00033104615,0.00037733003,0.00015804259,0.00036532342,0.000253109,0.0035639203,0.00018158302,0.00041608282],"category_scores_gemma":[0.0000146680895,0.0003820863,0.00021073765,0.0004702052,0.00006201943,0.0008176488,0.008333585,0.00074566196,0.00013734153],"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":[0.0002143081,0.0006330376,0.0063831243,0.00013100973,0.0003694049,0.0024366586,0.0005205571,0.8345892,0.0001705391,0.11506497,0.027137084,0.012350137],"study_design_scores_gemma":[0.00041962927,0.000055515848,0.0018263899,0.00010381314,0.000038863014,0.0000017881197,0.000071940165,0.8552486,0.00008231253,0.1113424,0.030134123,0.0006746549],"about_ca_topic_score_codex":0.0011121598,"about_ca_topic_score_gemma":0.000066024135,"teacher_disagreement_score":0.8904292,"about_ca_system_score_codex":0.00028292622,"about_ca_system_score_gemma":0.0002184008,"threshold_uncertainty_score":0.9998631},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004161669,0.0003327775,0.9857815,0.00036294735,0.0016850708,0.0018508941,0.00012499704,0.0004257468,0.00527438],"genre_scores_gemma":[0.5889996,0.002621017,0.35230738,0.0003202426,0.008516039,0.00014591216,0.0018904422,0.00039795673,0.0448014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932907,0.0011796963,0.00054854766,0.0018380778,0.0018518189,0.00129112],"domain_scores_gemma":[0.9934004,0.0012630182,0.00043050505,0.0027556736,0.001737704,0.00041268568],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013368793,0.00055416726,0.00058133714,0.0009791045,0.0038002678,0.0011307753,0.0060719484,0.00055159937,0.00000633124],"category_scores_gemma":[0.00017060158,0.00048318814,0.00041524356,0.0015016454,0.00049028225,0.0009004737,0.0087105865,0.0021380747,0.000023239874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035221895,0.002064169,0.0017093982,0.001363015,0.0015612332,0.005121874,0.012384648,0.01737325,0.0070490157,0.08396852,0.19325495,0.6737977],"study_design_scores_gemma":[0.0008860194,0.0002380488,0.0008028912,0.00021833874,0.00003344335,0.00008391382,0.00039341723,0.74076813,0.002226438,0.002412333,0.25120667,0.00073038554],"about_ca_topic_score_codex":0.001199884,"about_ca_topic_score_gemma":0.000015928224,"teacher_disagreement_score":0.7233949,"about_ca_system_score_codex":0.0008532206,"about_ca_system_score_gemma":0.0014547695,"threshold_uncertainty_score":0.9999061},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009467236,0.0033984834,0.59779656,0.00032254844,0.0015036712,0.000648045,0.0010625308,0.0002209906,0.3950377],"genre_scores_gemma":[0.015313803,0.013025038,0.8483811,0.00095356477,0.0023210354,0.00010885489,0.001680059,0.00029258928,0.11792397],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761707,0.000043803768,0.00042456685,0.0008815239,0.00074271613,0.0002903313],"domain_scores_gemma":[0.99522114,0.00017903857,0.0004258452,0.0040396918,0.00003812748,0.00009617279],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000348119,0.00039521517,0.000428457,0.00034048842,0.00010434994,0.0001379264,0.0037171852,0.00016950749,0.00048498568],"category_scores_gemma":[0.000026529986,0.00032426743,0.00010583221,0.000049670827,0.00010707558,0.00055881415,0.002964535,0.0002376826,0.00013983372],"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":[0.000015478952,0.000037193495,0.0000023524422,0.00007110956,0.0001373043,0.000016349984,0.000011411826,0.000012052597,0.000013521377,0.33967626,0.009312525,0.65069443],"study_design_scores_gemma":[0.0002236684,0.00008797234,0.00041821742,0.0011763202,0.0002861499,0.000025578829,0.000006903413,0.0019240661,0.0011474976,0.029428052,0.96453637,0.0007392174],"about_ca_topic_score_codex":0.000020989537,"about_ca_topic_score_gemma":0.0000089545765,"teacher_disagreement_score":0.95522386,"about_ca_system_score_codex":0.000053307966,"about_ca_system_score_gemma":0.00002288144,"threshold_uncertainty_score":0.99992096},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30648363,0.000048278245,0.6922302,0.00005383246,0.0002530291,0.00042029796,0.00040936438,0.00006136346,0.000039985942],"genre_scores_gemma":[0.95173055,0.00011080072,0.04751113,0.00008265272,0.00002674892,0.0000013273382,0.0004537669,0.000016307215,0.00006670428],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978959,0.00012590185,0.00024901904,0.0013024679,0.000103216225,0.0003235022],"domain_scores_gemma":[0.99757946,0.00037652347,0.00026648957,0.001619086,0.000049533715,0.00010891597],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00042312904,0.0002641,0.00036019087,0.00028676144,0.00021483433,0.00018419966,0.0028925159,0.00011475554,0.000014295562],"category_scores_gemma":[0.000046505927,0.00029322846,0.000046651796,0.00035510358,0.00006452547,0.000515481,0.01104919,0.00053462415,9.061331e-7],"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":[0.000116382245,0.00026615866,0.015815543,0.0016509467,0.0002484406,0.0011783858,0.003724149,0.7863783,0.000038215694,0.16695338,0.0027916231,0.020838449],"study_design_scores_gemma":[0.00059095555,0.00005198967,0.0049853837,0.00010674202,0.000024454806,0.0000041111775,0.00027712472,0.9417185,0.000007885871,0.05127653,0.0006327644,0.00032351998],"about_ca_topic_score_codex":0.00037800986,"about_ca_topic_score_gemma":0.000056578374,"teacher_disagreement_score":0.6452469,"about_ca_system_score_codex":0.000112974376,"about_ca_system_score_gemma":0.00020640211,"threshold_uncertainty_score":0.99995196},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012369992,0.00041681374,0.46981996,0.00006834135,0.0017862167,0.00020115462,0.0000977208,0.00010641065,0.52749103],"genre_scores_gemma":[0.0015398861,0.004414112,0.2589954,0.00020994867,0.0015514913,0.000030379731,0.00030913542,0.00016629556,0.7327834],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775255,0.000033075197,0.0007876485,0.0005965895,0.0005824304,0.00024769607],"domain_scores_gemma":[0.99732524,0.00016302742,0.0007195094,0.0013452718,0.00029754426,0.00014943155],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022808758,0.00038409693,0.00070476125,0.0003764899,0.000065493725,0.000026543325,0.0015101891,0.00035388995,0.00021003507],"category_scores_gemma":[0.00004906711,0.00035407252,0.0002709477,0.00011724409,0.00018103997,0.0002554542,0.0008426914,0.00041437242,0.00007916753],"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":[0.000014038818,0.000107979366,0.000023678911,0.00024149836,0.00021604558,0.000029445619,0.0008025435,0.000030302721,0.000059300422,0.25330317,0.048519652,0.69665235],"study_design_scores_gemma":[0.0005407672,0.00041905037,0.00017005815,0.00067806966,0.00007505995,0.00003235267,0.000010562571,0.026599463,0.00027179887,0.026660502,0.9438217,0.00072057627],"about_ca_topic_score_codex":0.0001246304,"about_ca_topic_score_gemma":0.000016396156,"teacher_disagreement_score":0.89530206,"about_ca_system_score_codex":0.00004163213,"about_ca_system_score_gemma":0.00015476799,"threshold_uncertainty_score":0.9998911},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020062234,0.0030619854,0.78243095,0.0006470948,0.0015964514,0.0017357676,0.002080688,0.00046517845,0.20797989],"genre_scores_gemma":[0.012169761,0.004884169,0.70778555,0.0048604193,0.0051385285,0.00065464457,0.0068770456,0.0007266267,0.2569033],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968796,0.000026529811,0.00040926936,0.0014201058,0.0007097218,0.0005548216],"domain_scores_gemma":[0.99421424,0.00040135023,0.00034218872,0.0048481054,0.000044043856,0.00015009881],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00047760352,0.0005980671,0.00048423276,0.0003845001,0.00029423033,0.00045378276,0.0058325874,0.0002722003,0.00020731047],"category_scores_gemma":[0.00006335883,0.00049249793,0.00014379324,0.000053288448,0.0000514171,0.0006792674,0.004039479,0.00033378883,0.00009624454],"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":[0.000018993382,0.000017128481,4.333575e-7,0.00013512868,0.00020355431,0.000012624922,0.00001883944,0.000025815518,0.0000031146212,0.42877185,0.048159707,0.5226328],"study_design_scores_gemma":[0.00016065914,0.000035324752,0.000053472508,0.00029372607,0.00015629003,0.0000044958238,0.0000028901975,0.0015304931,0.00027839292,0.050116993,0.94675285,0.0006143974],"about_ca_topic_score_codex":0.000011760791,"about_ca_topic_score_gemma":0.0000064848105,"teacher_disagreement_score":0.8985932,"about_ca_system_score_codex":0.000098728175,"about_ca_system_score_gemma":0.00002783937,"threshold_uncertainty_score":0.99975264},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000057163445,0.009275551,0.4501693,0.00071828,0.0036923352,0.0020673317,0.00090576994,0.0006150591,0.5324992],"genre_scores_gemma":[0.014277492,0.005968921,0.31000173,0.004266876,0.005406738,0.0007683817,0.0034433443,0.0005849036,0.6552816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958301,0.00015877139,0.0005672268,0.0016223951,0.0011040834,0.00071741856],"domain_scores_gemma":[0.99320656,0.0003598903,0.00034340905,0.0058934498,0.000023506473,0.00017319362],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00087765936,0.0006426637,0.00058869156,0.00075761584,0.00015565468,0.00045952812,0.0082651265,0.00030172328,0.0003345846],"category_scores_gemma":[0.00006307257,0.00054202403,0.00010847566,0.0002088848,0.000066601206,0.0009989089,0.007299562,0.0006796124,0.00054913445],"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":[0.00005760664,0.000197523,0.000009089792,0.00023873229,0.00015270486,0.00028852763,0.000067411565,0.00015851448,0.0000097238235,0.021016119,0.19871148,0.77909255],"study_design_scores_gemma":[0.00052326743,0.00010235428,0.0017519052,0.0024859537,0.0001644339,0.000029405106,0.000012436343,0.004394503,0.0003056661,0.010433284,0.9782587,0.0015380849],"about_ca_topic_score_codex":0.00004416426,"about_ca_topic_score_gemma":0.00005672252,"teacher_disagreement_score":0.7795472,"about_ca_system_score_codex":0.00028476745,"about_ca_system_score_gemma":0.00009541548,"threshold_uncertainty_score":0.9997031},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040415186,0.000060713843,0.99286276,0.0012318466,0.000719901,0.00011875814,0.000016626596,0.00043206709,0.00051578763],"genre_scores_gemma":[0.25308776,0.00022108354,0.7453219,0.0005303461,0.00014718882,0.000046338657,0.0000064792507,0.000024563675,0.0006143041],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841696,0.000056637615,0.00023565945,0.00051311817,0.00041850665,0.0003591076],"domain_scores_gemma":[0.99823195,0.00015347634,0.00004052674,0.0013270848,0.000047217796,0.0001997562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011541931,0.00019588477,0.00018299559,0.00019185393,0.00059326726,0.00007379983,0.0013754064,0.000094807896,0.000096942866],"category_scores_gemma":[0.000018188353,0.00017309318,0.00011660683,0.00047762293,0.000087082495,0.0006172143,0.000055459444,0.00040584223,0.0002724046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012193343,0.0003054663,0.00001780508,0.000005438209,0.000027592887,0.00013532086,0.00042416088,0.0008890948,0.0004563938,0.0011995449,0.0005888412,0.9959381],"study_design_scores_gemma":[0.004402859,0.0014485616,0.015018904,0.00019483009,0.000045291497,0.0023095892,0.00010464333,0.8008988,0.048020624,0.021714412,0.10338373,0.0024577654],"about_ca_topic_score_codex":0.000060771385,"about_ca_topic_score_gemma":0.0000026478651,"teacher_disagreement_score":0.9934804,"about_ca_system_score_codex":0.00005374766,"about_ca_system_score_gemma":0.000065638545,"threshold_uncertainty_score":0.7058535},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000337617,0.008421365,0.3757791,0.012482425,0.0037220663,0.002253044,0.0008647426,0.00046991074,0.59600395],"genre_scores_gemma":[0.013624435,0.01354385,0.0834868,0.030431828,0.008432335,0.0007333403,0.0022305744,0.0007329002,0.84678394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638027,0.00017544883,0.00046131524,0.0012116146,0.0011841442,0.0005872201],"domain_scores_gemma":[0.98962116,0.0009301885,0.0003496661,0.008950006,0.00003257233,0.0001163826],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0017733442,0.0006212295,0.0004088223,0.00020968741,0.0007271764,0.0008221956,0.01208655,0.00020638427,0.0005178304],"category_scores_gemma":[0.00008895699,0.00032225842,0.00015927982,0.0000799899,0.00017121,0.00061042374,0.009770766,0.00068209314,0.00053656776],"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":[0.000011124813,0.000019408679,1.5900724e-7,0.000043395587,0.00023458296,0.000021085647,0.00015654671,0.00004041476,0.0000014753931,0.13419908,0.1904884,0.6747843],"study_design_scores_gemma":[0.00009425516,0.000014505292,0.000047665788,0.00033066116,0.00021641447,0.000012233064,0.000029604551,0.0034820044,0.00006576598,0.020921385,0.97431135,0.00047416805],"about_ca_topic_score_codex":0.000049292645,"about_ca_topic_score_gemma":0.000019757259,"teacher_disagreement_score":0.78382295,"about_ca_system_score_codex":0.000104235696,"about_ca_system_score_gemma":0.000038401875,"threshold_uncertainty_score":0.99992293},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058640048,0.000009993737,0.92524284,0.00033888454,0.000040816987,0.000093676084,0.000002137223,0.000021450458,0.015610154],"genre_scores_gemma":[0.88552314,0.0000012321855,0.1141478,0.00015314523,0.000021210186,0.0000071936433,0.0000013538411,0.0000025579739,0.00014239606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941844,0.000028191958,0.000113189235,0.0001950395,0.00013097703,0.00011414381],"domain_scores_gemma":[0.99948025,0.00006281944,0.000027155875,0.0003701429,0.00001655803,0.000043067084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022953884,0.000059590115,0.000088376015,0.000024660148,0.000038892704,0.000057973386,0.00046597706,0.000019211207,0.0000068776326],"category_scores_gemma":[0.000023044251,0.000033446773,0.000012808091,0.0001595288,0.000020243859,0.00014296375,0.0005044423,0.000050855117,0.000009120766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016360129,0.00025571225,0.027867304,0.000056258657,0.000008446629,0.0000015811897,0.0019044038,0.00013298125,0.00019521857,0.51730245,0.009125176,0.44313413],"study_design_scores_gemma":[0.00064516946,0.00009697306,0.24390337,0.000048245136,0.0000036999713,0.000023154056,0.00019172503,0.69495225,0.00037769345,0.011111559,0.04836632,0.0002798533],"about_ca_topic_score_codex":0.0005707205,"about_ca_topic_score_gemma":0.00004103745,"teacher_disagreement_score":0.8268831,"about_ca_system_score_codex":0.0000043259097,"about_ca_system_score_gemma":0.000007059463,"threshold_uncertainty_score":0.13639198},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22716142,0.000021893069,0.7710677,0.000097600256,0.00019629535,0.00014791028,0.00036185145,0.000094605675,0.0008507682],"genre_scores_gemma":[0.9949275,0.00010734572,0.0037931534,0.00007616656,0.000040553445,7.018427e-7,0.00064691395,0.000009683519,0.00039797497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979084,0.00018569884,0.00021200656,0.0011569207,0.00025093032,0.00028603806],"domain_scores_gemma":[0.99631363,0.00012296313,0.00035826862,0.0027246373,0.00026749112,0.00021300487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029920437,0.00026811584,0.0005058191,0.00074014755,0.000290383,0.00017295426,0.003286365,0.00022062467,0.000086205815],"category_scores_gemma":[0.000019569634,0.00027614553,0.00032626226,0.00050212024,0.00018800111,0.0005552366,0.0016188826,0.0004546037,0.000028627155],"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":[0.00005637643,0.0002911268,0.005477918,0.000017692726,0.00058193895,0.00015673178,0.00011816724,0.87446,0.000053418065,0.117420524,0.0005371248,0.00082902773],"study_design_scores_gemma":[0.00033311988,0.00010823909,0.053320516,0.000044489418,0.00021908368,6.523639e-7,0.000023515151,0.93711644,0.0001093155,0.008156321,0.00028050554,0.00028777565],"about_ca_topic_score_codex":0.00059397664,"about_ca_topic_score_gemma":0.000093134164,"teacher_disagreement_score":0.7677661,"about_ca_system_score_codex":0.00009977849,"about_ca_system_score_gemma":0.00020832423,"threshold_uncertainty_score":0.99996907},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068797475,0.00028632878,0.9887768,0.000266989,0.006143159,0.00028910738,0.000012514531,0.00025089257,0.0039054381],"genre_scores_gemma":[0.10505139,0.00021469769,0.8766607,0.0071612974,0.008535579,0.000053839627,0.00014646976,0.00019095938,0.001985062],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99538326,0.000078395875,0.0005369316,0.0017856235,0.0013651022,0.00085070526],"domain_scores_gemma":[0.99702597,0.00038670423,0.00023935335,0.0020048223,0.00011732748,0.00022584651],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007277408,0.00056087045,0.0005723578,0.00064480834,0.0003779347,0.0011221953,0.005392548,0.0003693524,0.000051801006],"category_scores_gemma":[0.000026629312,0.00049539725,0.00013016332,0.00086622057,0.00036697375,0.0011419988,0.0024535013,0.0011243997,0.00015457299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030993815,0.00004741596,0.000014675851,0.000026187545,0.0000051358143,0.00013635751,0.00051099644,0.0073435465,0.000017608027,0.0020250191,0.0005344207,0.98933554],"study_design_scores_gemma":[0.0005607467,0.00016497992,0.00012666086,0.0006403529,0.000006169409,0.00009577671,7.820548e-8,0.50576144,0.00028904187,0.47764525,0.013725191,0.0009843404],"about_ca_topic_score_codex":0.0000788182,"about_ca_topic_score_gemma":0.00001277515,"teacher_disagreement_score":0.9883512,"about_ca_system_score_codex":0.00039483467,"about_ca_system_score_gemma":0.0011383167,"threshold_uncertainty_score":0.99998873},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008567678,0.00075864483,0.41883633,0.000081318736,0.0010168635,0.00029824095,0.00016932031,0.000102062266,0.5787287],"genre_scores_gemma":[0.00095100346,0.006287796,0.5117066,0.00013238558,0.0008218196,0.000044600365,0.00052891456,0.00016311153,0.47936374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971417,0.00004738455,0.0009689958,0.0007298914,0.0008338423,0.00027817418],"domain_scores_gemma":[0.99623805,0.00033205142,0.0009785597,0.001925891,0.00036563489,0.00015983952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002624203,0.0004149321,0.00083335506,0.0003968254,0.00008722913,0.00003388343,0.0018963651,0.00031969213,0.00018965764],"category_scores_gemma":[0.00004616445,0.0003878414,0.00032974352,0.00013977008,0.00023625464,0.00028213527,0.0008258587,0.00037086842,0.000050923045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011173655,0.00009628823,0.00003558738,0.00019264975,0.00016896348,0.00002552507,0.00040838504,0.0001252817,0.00006874062,0.75658756,0.03083561,0.2114442],"study_design_scores_gemma":[0.0010031334,0.00038291086,0.0005044165,0.00066965393,0.00013211199,0.000024996845,0.000013810976,0.024617124,0.00064618915,0.16309991,0.80787444,0.0010313226],"about_ca_topic_score_codex":0.00008926766,"about_ca_topic_score_gemma":0.000003987408,"teacher_disagreement_score":0.7770388,"about_ca_system_score_codex":0.000019400637,"about_ca_system_score_gemma":0.00014323034,"threshold_uncertainty_score":0.99985737},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.5432802e-7,0.0040704277,0.10295114,0.0019112359,0.0005573925,0.0017992238,0.00093849504,0.00020383128,0.8875678],"genre_scores_gemma":[0.0034983843,0.027963499,0.31641397,0.007837078,0.0013635078,0.0005677236,0.003753192,0.00042392203,0.6381787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974716,0.000047260855,0.00031235765,0.0012914685,0.0005179108,0.00035940262],"domain_scores_gemma":[0.99457306,0.00022375968,0.00022863258,0.0047733407,0.000024857334,0.00017637746],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005627107,0.0004431789,0.0004514043,0.00020660262,0.0003580059,0.0008556677,0.0080234315,0.00016942357,0.00040162832],"category_scores_gemma":[0.000030142053,0.00034358192,0.00004367482,0.00004503127,0.00007111806,0.0009914202,0.030773984,0.00028509504,0.00024098213],"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":[0.00000579129,0.000035572506,5.368985e-7,0.00007169686,0.00014060715,0.000024012574,0.00002564083,0.000005599025,0.0000019221002,0.36533037,0.08632303,0.5480352],"study_design_scores_gemma":[0.00012710436,0.000037635713,0.00003805486,0.0005211587,0.000106147265,0.000007851444,0.000002535023,0.0012537164,0.000016751446,0.019629167,0.977811,0.00044891244],"about_ca_topic_score_codex":0.000040305917,"about_ca_topic_score_gemma":0.000019022887,"teacher_disagreement_score":0.89148796,"about_ca_system_score_codex":0.000050814735,"about_ca_system_score_gemma":0.000027457729,"threshold_uncertainty_score":0.9999016},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17693356,0.0012559203,0.8124683,0.00135344,0.00051941816,0.003604331,0.0036180455,0.00014184577,0.00010515438],"genre_scores_gemma":[0.74901366,0.00041598544,0.24733123,0.00007624729,0.00013583516,0.00020336841,0.0027065417,0.000049988113,0.00006715459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588126,0.0005434324,0.00044720975,0.0013703575,0.0010510194,0.00070672797],"domain_scores_gemma":[0.99546117,0.0016560935,0.00015627859,0.0023610904,0.00019262405,0.00017275216],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0032079362,0.000256683,0.0004223182,0.0005946458,0.00042006825,0.00074401515,0.004032202,0.00013993774,0.00002823926],"category_scores_gemma":[0.00046804565,0.00023773682,0.000041071795,0.0005010296,0.00010394003,0.00041014946,0.025483744,0.0016300251,0.0000013984451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029745378,0.0009737977,0.021270888,0.02987454,0.00040149552,0.0013680819,0.031239798,0.051700443,0.00027619366,0.06428776,0.057909537,0.7404],"study_design_scores_gemma":[0.00057706,0.00019224419,0.014790424,0.000701648,0.000004511461,0.0000074952172,0.0008640147,0.93435717,0.00002700142,0.043855324,0.004290032,0.00033309628],"about_ca_topic_score_codex":0.0007885609,"about_ca_topic_score_gemma":0.00007402159,"teacher_disagreement_score":0.8826567,"about_ca_system_score_codex":0.00016727074,"about_ca_system_score_gemma":0.0006323589,"threshold_uncertainty_score":0.982398},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97174996,0.000048490554,0.020183897,0.0028817789,0.0013861395,0.0005857761,0.00010011038,0.00013004892,0.0029337865],"genre_scores_gemma":[0.94776726,0.000022402606,0.051558435,0.0002582126,0.000088120396,0.000060507642,0.000031241365,0.000010491185,0.00020331849],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983688,0.000025155789,0.00030064615,0.00041298015,0.00070403615,0.000188393],"domain_scores_gemma":[0.9989009,0.000082013044,0.0003500842,0.00027187515,0.00032055881,0.00007460407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026332,0.00015799528,0.00016637155,0.000113404094,0.0003923373,0.0002511958,0.0023594198,0.00003988694,0.00013799602],"category_scores_gemma":[0.0002024972,0.00012105944,0.000046487596,0.00021507053,0.000070892194,0.00065631384,0.0032011482,0.00026412346,0.0000035356732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019275598,0.00054338225,0.016124446,0.00008570764,0.00007735221,0.000004144053,0.002287184,0.0012193143,0.60589355,0.09672284,0.005018956,0.27183038],"study_design_scores_gemma":[0.0004794465,0.0000935732,0.004275261,0.0000557469,0.000005205046,0.000016802356,0.00008865415,0.95754385,0.024658144,0.011516277,0.0011005998,0.00016642765],"about_ca_topic_score_codex":0.000051342984,"about_ca_topic_score_gemma":6.6012234e-7,"teacher_disagreement_score":0.9563246,"about_ca_system_score_codex":0.0000547879,"about_ca_system_score_gemma":0.000038295108,"threshold_uncertainty_score":0.49366608},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020799751,0.00026916325,0.93109107,0.0002500638,0.0015177949,0.00038832633,0.000007421033,0.00056992524,0.065885425],"genre_scores_gemma":[0.011805,0.0002376762,0.94287646,0.0023337984,0.001466123,0.000040176838,0.0000257925,0.000101546604,0.04111341],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951338,0.000051297397,0.0007003818,0.0019568764,0.0014344474,0.0007231999],"domain_scores_gemma":[0.9960237,0.00020714887,0.00041164257,0.0028317664,0.00023632486,0.0002893974],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014141995,0.00059321633,0.0006479105,0.0010094718,0.00038319264,0.00071389566,0.0067989063,0.00032040913,0.000061487124],"category_scores_gemma":[0.000022498622,0.000513161,0.00013144224,0.00041423392,0.00069044874,0.0011642085,0.005419564,0.00077261095,0.00026732028],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026528817,0.000024649355,0.0000073378064,0.000025455884,0.0000028341062,0.000049895192,0.00009250885,0.00007427633,0.00012315401,0.17128646,0.0057766363,0.82253414],"study_design_scores_gemma":[0.00042501008,0.00034164445,0.000325708,0.0023500486,0.000008215377,0.00012336094,4.1409706e-7,0.4199041,0.0023538433,0.10777429,0.46481988,0.001573474],"about_ca_topic_score_codex":0.000024311843,"about_ca_topic_score_gemma":0.0000068236595,"teacher_disagreement_score":0.82096064,"about_ca_system_score_codex":0.00022527081,"about_ca_system_score_gemma":0.00035118812,"threshold_uncertainty_score":0.999732},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21189606,0.000026601145,0.77530557,0.00033900258,0.0012972223,0.00035497517,0.00011085737,0.0013914878,0.0092782425],"genre_scores_gemma":[0.96141464,0.000060276456,0.03590392,0.0009614968,0.00008954419,0.000039810307,0.00033147936,0.000017417808,0.0011814428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998975,0.000026244847,0.0002612557,0.00013353274,0.00030789198,0.00029611352],"domain_scores_gemma":[0.9991399,0.00012908982,0.00007139708,0.00053040136,0.000029597395,0.0000996159],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00049561117,0.000098876975,0.00011341825,0.00012439529,0.00015358052,0.0003569,0.00076927774,0.000030678966,0.0000519193],"category_scores_gemma":[0.000058741272,0.00008523805,0.00003076023,0.0006245916,0.000018398283,0.0015085272,0.0009461889,0.000089758236,0.0018989681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041420706,0.00017522149,0.037360042,0.0002947138,0.00014054264,0.00007025485,0.008491366,0.0022491699,0.00042528906,0.16356076,0.34948507,0.43770614],"study_design_scores_gemma":[0.0007257303,0.00011219937,0.1714005,0.00007762915,0.0000032024589,0.000015211141,0.0002101651,0.65697885,0.0005883446,0.0015183361,0.16794474,0.00042507533],"about_ca_topic_score_codex":0.00007117014,"about_ca_topic_score_gemma":0.000004770065,"teacher_disagreement_score":0.7495186,"about_ca_system_score_codex":0.0000347868,"about_ca_system_score_gemma":0.00003829841,"threshold_uncertainty_score":0.9988782},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010555947,0.00006987178,0.9774176,0.0016165607,0.0019339769,0.00030458238,0.00006470726,0.0005563781,0.007480387],"genre_scores_gemma":[0.23944758,0.0003310927,0.75334513,0.0009928289,0.00040615082,0.0003162667,0.0005399339,0.00007352831,0.004547471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823475,0.00006616944,0.00023931151,0.0007625661,0.00042575886,0.00027146545],"domain_scores_gemma":[0.9983173,0.00003485735,0.0001396585,0.0013495892,0.000043173844,0.00011540961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015203428,0.00024985633,0.0002498072,0.00017735174,0.00034325267,0.00033235745,0.0018717422,0.00009786374,0.00032211049],"category_scores_gemma":[0.0000032321832,0.00019920521,0.00009250431,0.00026741138,0.000040228366,0.0005132384,0.0023208067,0.0008308595,0.000012967526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009010195,0.0006835125,0.0014889939,0.00042088845,0.0005541006,0.000339463,0.006397407,0.025666641,0.0010121661,0.5105424,0.009264234,0.44354013],"study_design_scores_gemma":[0.0023510957,0.00049180456,0.012988344,0.00068973954,0.00014765901,0.00043597663,0.00080287096,0.5610804,0.0015559323,0.016384874,0.39936066,0.0037106446],"about_ca_topic_score_codex":0.00018117651,"about_ca_topic_score_gemma":0.000018608178,"teacher_disagreement_score":0.53541374,"about_ca_system_score_codex":0.00008952937,"about_ca_system_score_gemma":0.00021091283,"threshold_uncertainty_score":0.81233525},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028741268,0.00013224347,0.9686652,0.0012014111,0.0007903108,0.00023538423,0.000008697909,0.00017927005,0.000046249723],"genre_scores_gemma":[0.5543458,0.0000026341588,0.44303602,0.00239808,0.00012861064,0.000039376413,0.000008113446,0.000013446913,0.000027944096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967233,0.00011992717,0.0002516652,0.0011395762,0.0011210452,0.0006445076],"domain_scores_gemma":[0.99816316,0.00025959616,0.000121559795,0.0012578487,0.00007161605,0.00012622554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076610164,0.00024260109,0.00024458938,0.00031624167,0.0009401664,0.0003418955,0.0031819683,0.00004078023,0.000083844],"category_scores_gemma":[0.000027385015,0.00019280198,0.00004755355,0.002301112,0.00027269026,0.00093910255,0.0049734935,0.00039814797,0.0000495252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005423307,0.00024615804,0.001956606,0.000015397576,0.000011735216,0.0004102489,0.0024011084,0.29522833,0.0035674719,0.00051338854,0.0013330997,0.6942622],"study_design_scores_gemma":[0.00044484073,0.0003766382,0.0022665034,0.00002875835,0.000002319394,0.0003045883,6.787301e-7,0.9867721,0.0016847949,0.0022603702,0.00547337,0.0003850436],"about_ca_topic_score_codex":0.00006180158,"about_ca_topic_score_gemma":0.000020339505,"teacher_disagreement_score":0.6938772,"about_ca_system_score_codex":0.0003498943,"about_ca_system_score_gemma":0.0003294839,"threshold_uncertainty_score":0.78622365},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042689292,0.0007035353,0.99271095,0.0010282854,0.0034086618,0.0004566,0.000016879989,0.00014374337,0.0011044324],"genre_scores_gemma":[0.5989506,0.00025156856,0.39354992,0.0043936647,0.0015113202,0.000105489526,0.000022487196,0.00011027302,0.001104691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954521,0.000062939325,0.0005193721,0.0016794788,0.0017316756,0.0005544458],"domain_scores_gemma":[0.99806184,0.00015616657,0.00025887357,0.00091651035,0.00033051794,0.00027610184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012011423,0.00050445047,0.00046300224,0.00074408686,0.00041110095,0.0007744256,0.0028061268,0.00015328177,0.00009024201],"category_scores_gemma":[0.0001282489,0.0004534102,0.00008843582,0.00038005758,0.00019941585,0.00100412,0.0049404013,0.00083125586,0.000023989129],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006829203,0.000057091103,0.00007769976,0.00007121935,0.000035442896,0.00015654769,0.0019280717,0.008683524,0.001819899,0.025959112,0.00027573717,0.96086735],"study_design_scores_gemma":[0.0010782295,0.0018915581,0.0010126744,0.0017188614,0.00002674613,0.0006814143,0.0000029267114,0.841609,0.0063527087,0.057129562,0.08629289,0.002203401],"about_ca_topic_score_codex":0.00016512381,"about_ca_topic_score_gemma":0.00019682295,"teacher_disagreement_score":0.95866394,"about_ca_system_score_codex":0.0005690764,"about_ca_system_score_gemma":0.0003479253,"threshold_uncertainty_score":0.99979174},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03135777,0.0010310698,0.95419466,0.0009595753,0.008594226,0.0013722604,0.00068817544,0.0017965141,0.00000575248],"genre_scores_gemma":[0.2496202,0.00033933867,0.74622947,0.00033978987,0.002381792,0.0007781941,0.0000018948879,0.00028610107,0.0000232321],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995517,0.00013375576,0.00068476726,0.0020303929,0.0006478118,0.0009862516],"domain_scores_gemma":[0.9939013,0.00031518584,0.00062151783,0.004139598,0.00064640347,0.00037600994],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010513121,0.00069048064,0.00069915934,0.00047198925,0.00047932338,0.0009579602,0.0040620575,0.00060110673,0.000003078],"category_scores_gemma":[0.0007171226,0.0007260699,0.00027180774,0.000809429,0.000088610665,0.00053587294,0.005262776,0.00077947514,0.000050128314],"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":[0.00023746795,0.0013850615,0.0024569978,0.00489696,0.001458476,0.00071273313,0.00028911539,0.0030341675,0.7318776,0.15579858,0.09650612,0.0013466782],"study_design_scores_gemma":[0.0063519264,0.0006264455,0.038719624,0.010148144,0.0005018973,2.1265835e-7,0.000013343958,0.1950956,0.58120257,0.0049961344,0.15391424,0.008429893],"about_ca_topic_score_codex":0.00006970803,"about_ca_topic_score_gemma":0.0000022866502,"teacher_disagreement_score":0.21826243,"about_ca_system_score_codex":0.00031702043,"about_ca_system_score_gemma":0.00068569696,"threshold_uncertainty_score":0.99951905},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036569901,0.00016509811,0.9658735,0.0070483126,0.00024717534,0.00041462964,0.00017815463,0.0010071073,0.021409076],"genre_scores_gemma":[0.9903682,0.00005125762,0.004713308,0.0019831953,0.0002221987,1.7204255e-7,0.0009141175,0.00058231514,0.0011652623],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983411,0.00031020484,0.00018146553,0.00041652212,0.000496157,0.00025457228],"domain_scores_gemma":[0.99875563,0.000032284148,0.00011903741,0.0008196607,0.00019554881,0.00007782425],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00071134826,0.000091433554,0.00008053084,0.00007260607,0.0061201844,0.0008324588,0.0027932876,0.000017327962,0.002650107],"category_scores_gemma":[0.00008833733,0.00007901694,0.00003670575,0.0006897012,0.00006659548,0.00032494208,0.0048082103,0.0002825347,0.0010655791],"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":[0.000012160042,0.000095456424,0.000007215858,0.000009992715,0.00001534938,0.0000065612066,0.0025644735,0.00046900156,0.00084253546,0.04569786,0.5134848,0.4367946],"study_design_scores_gemma":[0.00016459603,0.00006509473,0.0007634475,0.000004650023,0.0000023433768,0.00007329715,0.0001335845,0.05490669,0.00011108095,0.0006049481,0.9430698,0.0001004525],"about_ca_topic_score_codex":0.000010002478,"about_ca_topic_score_gemma":4.9100638e-8,"teacher_disagreement_score":0.9867112,"about_ca_system_score_codex":0.00012016582,"about_ca_system_score_gemma":0.000004030619,"threshold_uncertainty_score":0.9997122},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22054276,0.0004804787,0.77536154,0.002461881,0.00023831289,0.0002239805,0.000005432925,0.00061526016,0.00007037284],"genre_scores_gemma":[0.9723241,0.00008465866,0.027558345,0.0000024198841,0.000007808488,0.000013252999,0.0000027414408,0.0000026941957,0.000003992166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907494,0.000003922008,0.00016771635,0.00039533467,0.0001498071,0.0002083115],"domain_scores_gemma":[0.9992627,0.00003538768,0.000037117574,0.00061599107,0.00002590998,0.000022890074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005713224,0.000062158375,0.00011965444,0.0010599506,0.000045538072,0.000030452708,0.0013424915,0.00005645397,1.0150727e-7],"category_scores_gemma":[0.000084846346,0.00005149565,0.0000033347012,0.0040601413,0.00013489844,0.00057097495,0.0008999623,0.000093215654,0.0000059221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006154653,0.000078645986,0.0031088556,0.00009895956,0.0000022092809,0.00004129579,0.0006041253,0.008064838,0.12855402,0.41548714,0.000104440805,0.44384933],"study_design_scores_gemma":[0.00024753908,0.000008455,0.0029433717,0.00004970505,3.796728e-7,0.0000054750185,0.000013996392,0.9876633,0.00496282,0.0014443476,0.0025931136,0.000067438334],"about_ca_topic_score_codex":0.000018220255,"about_ca_topic_score_gemma":0.000006344922,"teacher_disagreement_score":0.9795985,"about_ca_system_score_codex":0.000014881423,"about_ca_system_score_gemma":0.000041644886,"threshold_uncertainty_score":0.24947056},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2618206,0.0000067758633,0.7362119,0.00081134046,0.00077599735,0.00011190019,0.0000069433645,0.0001903857,0.00006414053],"genre_scores_gemma":[0.9751778,0.000006028444,0.023903849,0.00077581825,0.0001000048,0.000010851888,0.000004784751,0.000006009937,0.000014842861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978965,0.00006374807,0.00019908846,0.0006814507,0.00066170475,0.0004975216],"domain_scores_gemma":[0.9980829,0.0005997919,0.000062622865,0.0011277463,0.000037658876,0.00008929572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012145826,0.0001373667,0.000113742484,0.00030880235,0.00047295386,0.0005034845,0.0029307827,0.000016238802,0.0000058200803],"category_scores_gemma":[0.00006411265,0.00009131939,0.000030008863,0.0020788012,0.000127842,0.0012513694,0.0028454068,0.00019591818,0.0001941391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048548363,0.00014521906,0.005434042,0.000021873675,0.0000055193923,0.00022461852,0.0029085402,0.02201541,0.0035844652,0.0970525,0.0057052257,0.86289775],"study_design_scores_gemma":[0.00014987441,0.000028610853,0.025466211,0.00010619722,3.5488486e-7,0.000006221283,0.000020258773,0.9689204,0.0014134418,0.0031983342,0.00054022885,0.00014986644],"about_ca_topic_score_codex":0.00018729125,"about_ca_topic_score_gemma":0.000033923734,"teacher_disagreement_score":0.946905,"about_ca_system_score_codex":0.00004337152,"about_ca_system_score_gemma":0.000085739826,"threshold_uncertainty_score":0.54461724},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049529787,0.000049126826,0.9476355,0.00013183037,0.0009297671,0.00021609844,0.000052869254,0.00033056975,0.0011244912],"genre_scores_gemma":[0.9861384,0.00023471979,0.0126539385,0.000034184137,0.000095583775,7.670572e-7,0.000055272933,0.000019551384,0.00076757564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998288,0.000105454244,0.00025826067,0.0009189009,0.0001574744,0.00027194273],"domain_scores_gemma":[0.99729663,0.00009922827,0.00034771962,0.0020096225,0.00017336076,0.00007346318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019015055,0.00025512025,0.00034216253,0.00016653915,0.00017899185,0.0001459831,0.002421939,0.00025911327,0.000016384829],"category_scores_gemma":[0.00004838711,0.0002772439,0.00014831674,0.0005152064,0.000107305445,0.001135542,0.005396281,0.00037715133,0.00002954941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014696197,0.0002985554,0.0075559174,0.0005295199,0.00025311776,0.00037121962,0.0021943694,0.404451,0.00035881385,0.57047087,0.008079992,0.005289662],"study_design_scores_gemma":[0.000509119,0.00007333725,0.0041683773,0.00028465595,0.000039228784,0.0000025863126,0.00011504956,0.7687211,0.0009805739,0.223454,0.0011930517,0.0004588879],"about_ca_topic_score_codex":0.0006995339,"about_ca_topic_score_gemma":0.000091283946,"teacher_disagreement_score":0.9366086,"about_ca_system_score_codex":0.000099690835,"about_ca_system_score_gemma":0.00016262401,"threshold_uncertainty_score":0.999968},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34656143,0.000063482374,0.6517735,0.0011065686,0.00037233502,0.000032988344,0.000003488024,0.000057716963,0.000028467977],"genre_scores_gemma":[0.9884033,0.00015979119,0.011375119,0.0000057168304,0.00003440838,0.000001548629,0.0000026085565,0.000002968431,0.000014516692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986791,0.000047502956,0.00020899935,0.00015878024,0.000707311,0.0001983191],"domain_scores_gemma":[0.99869597,0.00023345834,0.00006124083,0.00044796654,0.00050857564,0.00005279849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038164982,0.000048333484,0.00007255295,0.0032526255,0.00017924282,0.00013694655,0.0035452177,0.000052476513,0.0000015608018],"category_scores_gemma":[0.0031179127,0.000042703283,0.0000065932018,0.003485803,0.00021708869,0.0011024984,0.0024142475,0.00064339663,0.0000026905402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052037656,0.00032115763,0.05547931,0.00006115267,0.000056376004,0.00027786047,0.0018278117,0.09042551,0.12254671,0.2180713,0.0017047954,0.50917596],"study_design_scores_gemma":[0.00017958766,0.00003657612,0.030226167,0.00007064556,3.25915e-7,0.00005795559,0.000035446985,0.95695865,0.0009238069,0.010790979,0.0006765299,0.00004330946],"about_ca_topic_score_codex":0.000012833652,"about_ca_topic_score_gemma":0.0000041735816,"teacher_disagreement_score":0.86653316,"about_ca_system_score_codex":0.00006448457,"about_ca_system_score_gemma":0.00015897732,"threshold_uncertainty_score":0.6587956},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075023324,0.000018531566,0.9969819,0.00013351125,0.00039669365,0.0002579722,0.000015558167,0.0005214252,0.0009241423],"genre_scores_gemma":[0.008843798,0.000020360818,0.99035805,0.00027745203,0.000087925044,0.000033716737,0.00006302705,0.000015185519,0.00030048605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900293,0.000012375935,0.00027947812,0.00013496859,0.00023617224,0.00033407268],"domain_scores_gemma":[0.9991378,0.00014633495,0.00012531599,0.00045020354,0.00005241349,0.000087894594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041891437,0.00011612277,0.00012613463,0.00015728897,0.00022794836,0.00022013723,0.0006059634,0.00006452478,0.0000023362907],"category_scores_gemma":[0.00008107491,0.00009785484,0.00005695167,0.00047183994,0.000019723051,0.0010318949,0.00038575524,0.00008130132,0.00018070657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018479152,0.000050032133,0.00022900171,0.0004229295,0.000051983523,0.000016622536,0.0108929,0.000860657,0.0025666514,0.031426195,0.121830635,0.8316339],"study_design_scores_gemma":[0.00032973173,0.00005746892,0.00022130727,0.00006217392,0.000004581818,0.0000053748568,0.00026866447,0.95319086,0.0038346492,0.0010109721,0.040822174,0.00019203192],"about_ca_topic_score_codex":0.000004098001,"about_ca_topic_score_gemma":4.067939e-7,"teacher_disagreement_score":0.95233023,"about_ca_system_score_codex":0.000028076884,"about_ca_system_score_gemma":0.00006549209,"threshold_uncertainty_score":0.39904046},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16513987,0.000031494368,0.8308478,0.00006609321,0.0016385916,0.00028108258,0.000120690434,0.00049099635,0.001383366],"genre_scores_gemma":[0.9746729,0.000107513944,0.022334436,0.00001601424,0.000107189735,7.045391e-7,0.000049671988,0.00002140256,0.0026901409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849045,0.000089878544,0.00024057284,0.0008450288,0.00010004295,0.00023401166],"domain_scores_gemma":[0.99801606,0.00012591468,0.00036250436,0.0012733112,0.00011380625,0.00010840109],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015817421,0.00023069522,0.0003552929,0.00027177524,0.00010232895,0.000070522634,0.0015671587,0.00022777614,0.000027528547],"category_scores_gemma":[0.000033923592,0.00025617468,0.00016069562,0.00038398895,0.00016650582,0.00030210914,0.002989956,0.0002889612,0.0001860753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006457678,0.0014954606,0.018331785,0.002551076,0.0018044016,0.00447244,0.0023851774,0.34255326,0.00875569,0.4426979,0.08713082,0.0871762],"study_design_scores_gemma":[0.000406489,0.0000750187,0.0019314617,0.00021923156,0.000068096604,0.000014681785,0.000028594868,0.97745544,0.00094342494,0.017696109,0.0007090343,0.00045239797],"about_ca_topic_score_codex":0.00015273855,"about_ca_topic_score_gemma":0.0000025065017,"teacher_disagreement_score":0.80953306,"about_ca_system_score_codex":0.000072499424,"about_ca_system_score_gemma":0.00024098887,"threshold_uncertainty_score":0.99998903},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08124344,0.0015944568,0.896248,0.0048129954,0.003465012,0.0003995479,0.000031958516,0.0009230853,0.01128153],"genre_scores_gemma":[0.99399805,0.0003878836,0.0047689877,0.00027385252,0.000046623558,0.000011389663,0.00001969323,0.0000132694095,0.0004802524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985661,0.00004221689,0.0002778569,0.000264324,0.00055477215,0.00029474407],"domain_scores_gemma":[0.998588,0.00031682776,0.00015508836,0.00049465883,0.00034639615,0.00009900536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005033991,0.00011468323,0.00018308974,0.00041916978,0.00013166245,0.000078179706,0.0009032334,0.000059395818,0.000010080575],"category_scores_gemma":[0.00018355675,0.000109836044,0.00007427811,0.003020913,0.000019957048,0.0006480077,0.00048753727,0.000101836784,0.00012751638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003525848,0.0001229055,0.000984834,0.000037267055,0.00002494322,0.00002147913,0.00010779279,0.00032280135,0.00029291608,0.9170917,0.03934693,0.041642904],"study_design_scores_gemma":[0.00043121527,0.00021348627,0.017650347,0.00005990696,0.0000055930927,0.0000065527224,0.000017946883,0.24860707,0.008053684,0.69629014,0.028345749,0.00031830682],"about_ca_topic_score_codex":0.000019343835,"about_ca_topic_score_gemma":2.7723556e-7,"teacher_disagreement_score":0.9127546,"about_ca_system_score_codex":0.000010919321,"about_ca_system_score_gemma":0.000069305686,"threshold_uncertainty_score":0.4478984},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011328355,0.011550524,0.660169,0.0036295303,0.00031328457,0.00037350098,0.0000749333,0.0011351289,0.32274276],"genre_scores_gemma":[0.04279705,0.461432,0.36912248,0.0047287233,0.00013771569,0.00094594934,0.002790561,0.00018542353,0.11786009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987077,0.000025151583,0.0006356837,0.00020257005,0.0002404293,0.00018843244],"domain_scores_gemma":[0.9973991,0.000108429034,0.0003899737,0.0019422919,0.00012277413,0.00003741441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002966292,0.00021397643,0.0002831006,0.0007956881,0.00020824616,0.00014043965,0.0022581127,0.00040554642,0.000020575255],"category_scores_gemma":[0.00006131665,0.00021328879,0.00003474699,0.00019381738,0.00049585203,0.0026293234,0.0025097544,0.0006080512,0.00013647544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027960011,0.0000027517558,0.000004170136,0.00002418948,0.0000025232466,5.4064174e-7,0.00017735106,0.000018699737,1.18793935e-7,0.64154345,0.00018818206,0.35803524],"study_design_scores_gemma":[0.00022519319,0.000035407862,0.0000135805385,0.00014376466,0.0000019722982,0.000012920038,0.00026752384,0.0056967675,0.000010093348,0.46206427,0.5313525,0.00017598907],"about_ca_topic_score_codex":0.000016528078,"about_ca_topic_score_gemma":0.000063293955,"teacher_disagreement_score":0.53116435,"about_ca_system_score_codex":0.00006964366,"about_ca_system_score_gemma":0.00005886118,"threshold_uncertainty_score":0.8697664},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004117875,0.00019933711,0.98779994,0.00057394634,0.0017293795,0.00014982851,0.000083349114,0.00026304522,0.0050832876],"genre_scores_gemma":[0.08567898,0.0001577857,0.8977708,0.00029901534,0.00030297777,0.000033223943,0.00014628617,0.00003934985,0.0155715775],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987823,0.000034984507,0.00027404082,0.0004821444,0.000245397,0.00018114496],"domain_scores_gemma":[0.9984745,0.00008441491,0.00012793574,0.0011642197,0.000078973186,0.0000699719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001911202,0.00014426652,0.00023810615,0.00013827435,0.00006378057,0.00012906088,0.0012257437,0.00014117618,0.00025967363],"category_scores_gemma":[0.0000144320775,0.00011795629,0.00010650578,0.00012852978,0.000030235762,0.00018529121,0.0041739093,0.0002698391,0.00013666312],"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":[0.000012300367,0.0005233065,0.0011680046,0.0013914646,0.00036714156,0.000115914925,0.005152884,0.0082411915,0.0065232227,0.10880757,0.6663956,0.20130138],"study_design_scores_gemma":[0.00055085024,0.000106360545,0.017187314,0.0011818835,0.000042578056,0.000024558447,0.00014651743,0.7364126,0.0108574955,0.10631723,0.1257223,0.0014503129],"about_ca_topic_score_codex":0.00015395627,"about_ca_topic_score_gemma":0.000022553964,"teacher_disagreement_score":0.7281714,"about_ca_system_score_codex":0.000017204467,"about_ca_system_score_gemma":0.000108583794,"threshold_uncertainty_score":0.52024794},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062678946,0.00017837776,0.99352336,0.002861408,0.0010905159,0.0003244973,0.000048796443,0.00009039803,0.0012558479],"genre_scores_gemma":[0.48876882,0.00086419843,0.4938155,0.0076047163,0.0020065038,0.00004253969,0.00007683905,0.00017504599,0.0066458145],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99695987,0.00005123837,0.0004995066,0.0011931102,0.00086747215,0.00042880885],"domain_scores_gemma":[0.995355,0.002827514,0.00029640528,0.0013241956,0.00007665628,0.00012023366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000994811,0.0003688152,0.00041321266,0.0003904055,0.0001561017,0.00031838383,0.0026831452,0.00019402079,0.000008865757],"category_scores_gemma":[0.00040294876,0.00024153579,0.00006497042,0.0006490628,0.0005960405,0.0005012678,0.0017591821,0.0006570457,0.000033643235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040939158,0.000039490078,0.00023802699,0.000064240834,0.0000114506,0.00019802898,0.0018974093,0.022825198,0.00003279486,0.3533825,0.0004387387,0.6208312],"study_design_scores_gemma":[0.0003564389,0.00013143955,0.00092979515,0.0013025892,0.000003071341,0.000018083365,3.7602348e-7,0.366829,0.0001971109,0.6290769,0.0007611303,0.00039405],"about_ca_topic_score_codex":0.00032897602,"about_ca_topic_score_gemma":0.0001067626,"teacher_disagreement_score":0.62043715,"about_ca_system_score_codex":0.00007740166,"about_ca_system_score_gemma":0.00032590498,"threshold_uncertainty_score":0.98495436},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09464051,0.0001608732,0.9005948,0.0012893269,0.0024828415,0.00019649099,0.000022627362,0.00043952995,0.00017300427],"genre_scores_gemma":[0.83369684,0.0000036013596,0.16453868,0.0005380218,0.0010709265,0.0000072092157,0.00002551754,0.000016299864,0.00010288772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998347,0.00004887649,0.00036290006,0.00032743605,0.00057132554,0.00034245857],"domain_scores_gemma":[0.99827826,0.00082604197,0.00027268246,0.00020284184,0.00032506668,0.00009508151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045771227,0.00018735886,0.00017201222,0.00032651695,0.0003259186,0.00047034837,0.0013658048,0.00004731164,0.0000042356364],"category_scores_gemma":[0.0005979783,0.00013970264,0.00013029222,0.00025613373,0.000014720833,0.0003911544,0.00059460377,0.00045550338,0.000012615341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008288426,0.00017151085,0.00040322443,0.000037963382,0.00015125524,0.00090033066,0.0013061138,0.0459772,0.09716363,0.020739658,0.00672875,0.82633746],"study_design_scores_gemma":[0.0003551221,0.00005901672,0.0009074157,0.0002991143,0.0000032592075,0.00020873103,0.000031850894,0.9909823,0.0056428155,0.0010228546,0.00030461338,0.00018290895],"about_ca_topic_score_codex":0.000006492649,"about_ca_topic_score_gemma":7.465033e-7,"teacher_disagreement_score":0.9450051,"about_ca_system_score_codex":0.00013377833,"about_ca_system_score_gemma":0.000048737133,"threshold_uncertainty_score":0.5696908},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3278368,0.000025417337,0.66359216,0.0007527812,0.0023792638,0.00016672348,0.000010997997,0.0011559142,0.0040799077],"genre_scores_gemma":[0.9902945,0.000026495269,0.007953715,0.0006063271,0.00053204544,0.000013888003,0.00001597162,0.000019612751,0.0005374211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904054,0.000023976494,0.00011850984,0.00031454733,0.00026816333,0.00023428195],"domain_scores_gemma":[0.99924755,0.00011208905,0.000047163834,0.0005011727,0.000028256267,0.000063775755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017523202,0.0000870743,0.00009028288,0.00014274979,0.00015316637,0.00039632214,0.0013838254,0.000041358155,0.000014151447],"category_scores_gemma":[0.00003304582,0.00007424601,0.00002942019,0.0006527239,0.000011177785,0.0009268284,0.00054482534,0.00014562729,0.00026540292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026566198,0.00012768879,0.001731308,0.000043207223,0.000029466179,0.00028361604,0.00048682356,0.018624905,0.0023148875,0.026427936,0.02941482,0.9204888],"study_design_scores_gemma":[0.00053874723,0.00007442134,0.006515919,0.000113935064,0.0000026594903,0.000004883606,0.000012838159,0.94040376,0.01644208,0.019049395,0.016505444,0.00033590823],"about_ca_topic_score_codex":0.00003679121,"about_ca_topic_score_gemma":0.000002849603,"teacher_disagreement_score":0.92177886,"about_ca_system_score_codex":0.000015718228,"about_ca_system_score_gemma":0.000026192774,"threshold_uncertainty_score":0.38217434},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018092882,0.00051964517,0.99376935,0.00035497136,0.0034871595,0.0008638139,0.00031574134,0.00027656974,0.00039468365],"genre_scores_gemma":[0.010841115,0.00009801691,0.986146,0.0008380988,0.0012568379,0.0000359784,0.00015903545,0.00007828348,0.0005466523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994778,0.000031116044,0.0005984563,0.0026336354,0.0011048025,0.000854031],"domain_scores_gemma":[0.99445957,0.0012440148,0.00047990063,0.0033055525,0.00035516365,0.00015577863],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013524024,0.00060986175,0.00069634744,0.0005578864,0.0005428113,0.0007972967,0.009240088,0.00036056203,0.0000075279368],"category_scores_gemma":[0.00025579584,0.000528725,0.000109718756,0.0006347238,0.00061006733,0.0014636806,0.0063916133,0.00067751826,0.000029663895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004508357,0.000020970561,0.000022044183,0.000084681335,0.000027397926,0.00010460226,0.0005250984,0.010700884,0.000060322538,0.054173347,0.0010869442,0.9331486],"study_design_scores_gemma":[0.000461313,0.00014504966,0.00016884485,0.00037759397,0.000012193262,0.00002568641,3.806615e-7,0.8180952,0.00015723148,0.17495361,0.0049801585,0.0006227506],"about_ca_topic_score_codex":0.000056836765,"about_ca_topic_score_gemma":0.00015223133,"teacher_disagreement_score":0.9325259,"about_ca_system_score_codex":0.00018179369,"about_ca_system_score_gemma":0.00062523206,"threshold_uncertainty_score":0.9997164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004628402,0.0005484423,0.9904211,0.0005379878,0.002709986,0.0006373885,0.00013975985,0.00035919205,0.000017709812],"genre_scores_gemma":[0.20571822,0.0038126463,0.7775112,0.00074931403,0.0050855167,0.00065518747,0.0037677358,0.00033825068,0.0023619407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947574,0.00021940566,0.000647198,0.001084055,0.0009154477,0.0023764847],"domain_scores_gemma":[0.99749684,0.00014428454,0.0006740979,0.0011499781,0.00030022388,0.00023455785],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022721202,0.0004884605,0.0005326327,0.00041644304,0.00071537646,0.0005749317,0.002065852,0.0003618873,0.0000078001785],"category_scores_gemma":[0.00003470289,0.00041107918,0.00021701548,0.0003399564,0.000042311047,0.00082730886,0.00081875356,0.0031724165,0.000035196455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001631732,0.00071694545,0.00003414894,0.00007745571,0.0003346647,0.000019412071,0.00014914892,0.05799434,0.0017942134,0.21156332,0.0064607006,0.72069246],"study_design_scores_gemma":[0.00077622593,0.0005012167,0.00012181318,0.00021211166,0.00002100897,0.00004575113,0.000020478052,0.5567153,0.00055024656,0.4403728,0.0003076395,0.00035541487],"about_ca_topic_score_codex":0.00011924222,"about_ca_topic_score_gemma":0.000037202404,"teacher_disagreement_score":0.72033703,"about_ca_system_score_codex":0.00063686946,"about_ca_system_score_gemma":0.0018883684,"threshold_uncertainty_score":0.9998341},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012098577,0.00016527616,0.9661186,0.00045976622,0.007824482,0.0015284398,0.009267345,0.00087470113,0.0016628234],"genre_scores_gemma":[0.055822972,0.0013361605,0.9090617,0.002114317,0.001954788,0.0010767976,0.025051158,0.00037336242,0.0032087853],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494714,0.00005895833,0.0018771372,0.0010160839,0.0009685143,0.0011321466],"domain_scores_gemma":[0.99425966,0.0004202415,0.0012293867,0.003347999,0.00037608107,0.00036665786],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00069750816,0.00090998923,0.0011024988,0.00038444222,0.0005352033,0.0020985433,0.0049352665,0.0007310193,0.000039581144],"category_scores_gemma":[0.00011304585,0.00083500746,0.00057314505,0.0003951422,0.000121171746,0.0028249242,0.007696982,0.0013441879,0.00088810024],"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":[0.0008438802,0.0023566927,0.008052834,0.007740676,0.0029387327,0.00023531687,0.025377741,0.02620607,0.00021496326,0.020067582,0.675168,0.23079751],"study_design_scores_gemma":[0.0019783524,0.00017369611,0.0013841095,0.0017136089,0.00007116664,0.000012951585,0.0003397621,0.7915834,0.0005143656,0.034435827,0.16613577,0.0016569969],"about_ca_topic_score_codex":0.00035030572,"about_ca_topic_score_gemma":0.000091351605,"teacher_disagreement_score":0.76537734,"about_ca_system_score_codex":0.00027905055,"about_ca_system_score_gemma":0.0003016147,"threshold_uncertainty_score":0.99988985},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37699857,0.0016195175,0.6182618,0.00050690357,0.001994651,0.00024083733,0.00005048543,0.0002932872,0.000033890374],"genre_scores_gemma":[0.6007222,0.026473725,0.36948073,0.00022067277,0.001995394,0.00008065044,0.00021226324,0.00019759977,0.0006167305],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946127,0.00030670982,0.0008273763,0.0011651594,0.0005461084,0.0025419665],"domain_scores_gemma":[0.9972896,0.00042445434,0.00088231405,0.0010507526,0.000102117585,0.0002507884],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020964877,0.00053428835,0.0007878932,0.00029476723,0.00043182794,0.0013125967,0.002031914,0.00038656025,0.000014540882],"category_scores_gemma":[0.00021901807,0.00048222553,0.0002584075,0.0002497831,0.0000977211,0.0006353985,0.0027660348,0.0057643633,0.000028602513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032147343,0.00019262705,0.0029885294,0.00012716636,0.002165688,0.00023757009,0.001882039,0.0007424266,0.007711855,0.049440663,0.0004908629,0.9336991],"study_design_scores_gemma":[0.0015268732,0.00022626366,0.0003745013,0.00042582085,0.00008216337,0.0006379771,0.00043449047,0.091159575,0.000282065,0.903412,0.00058368006,0.00085458683],"about_ca_topic_score_codex":0.00067756383,"about_ca_topic_score_gemma":0.00007977413,"teacher_disagreement_score":0.9328445,"about_ca_system_score_codex":0.0005120049,"about_ca_system_score_gemma":0.0019938645,"threshold_uncertainty_score":0.99976295},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031314685,0.00000846446,0.98807496,0.0006997661,0.00035172762,0.000059652386,0.0000021313056,0.0008897933,0.0067820186],"genre_scores_gemma":[0.29980376,0.000005119742,0.69571257,0.0018854457,0.00018348808,0.000028025348,0.000052868607,0.00001687674,0.0023118758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990887,0.0000256478,0.00016031282,0.00027458582,0.00021802238,0.00023271295],"domain_scores_gemma":[0.99923784,0.00012165821,0.00004472408,0.00048097345,0.000045130237,0.00006965117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027764664,0.000078267054,0.00007902518,0.00009473041,0.00016478226,0.00013423162,0.00056099385,0.00003642839,0.00008046121],"category_scores_gemma":[0.00005661177,0.00006221222,0.000026798878,0.0007381122,0.000009960104,0.00039679056,0.0002924547,0.00007309583,0.00049263827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011024954,0.00017995323,0.003485778,0.000055326218,0.000025098974,0.00007301332,0.0002925967,0.015145981,0.009873023,0.59731525,0.07868421,0.29485872],"study_design_scores_gemma":[0.00017260555,0.000019410676,0.0021853761,0.000015546893,0.000001123439,0.0000010300989,0.0000092353885,0.9793052,0.0011524924,0.0049874936,0.012042996,0.00010747465],"about_ca_topic_score_codex":0.00008977884,"about_ca_topic_score_gemma":0.0000027446372,"teacher_disagreement_score":0.96415925,"about_ca_system_score_codex":0.000013541032,"about_ca_system_score_gemma":0.00007348374,"threshold_uncertainty_score":0.63320327},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03973081,0.00004079694,0.9576337,0.0004659612,0.00005137598,0.00006667803,0.0000012868538,0.0005134085,0.0014960378],"genre_scores_gemma":[0.948108,0.0005217319,0.036339313,0.0003918881,0.000055043623,0.000020120702,0.0002889137,0.000013415879,0.014261541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990545,0.00005024593,0.00013968599,0.00034887085,0.00022861526,0.00017808279],"domain_scores_gemma":[0.9994727,0.00005871892,0.000048523907,0.00029785009,0.00004077697,0.000081474616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020470438,0.000086402,0.00012978454,0.00028388278,0.00017090338,0.00017620556,0.00025967057,0.00003797866,0.00011395357],"category_scores_gemma":[0.000047490717,0.000070704205,0.00004508882,0.0018139798,0.000017450751,0.00034862716,0.0003991054,0.000075547876,0.00019333484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033907356,0.0001780866,0.24385636,0.000042615437,0.00093597814,0.00012557702,0.0024359352,0.04799218,0.0013280998,0.14050356,0.020160332,0.5424074],"study_design_scores_gemma":[0.00017504061,0.000053643776,0.084604114,0.0000043474565,0.000033704637,0.0000034656334,0.0000560951,0.89216024,0.000110602,0.0012077963,0.021460665,0.00013026547],"about_ca_topic_score_codex":0.00029131773,"about_ca_topic_score_gemma":0.000034970475,"teacher_disagreement_score":0.92129433,"about_ca_system_score_codex":0.000008327668,"about_ca_system_score_gemma":0.00001733691,"threshold_uncertainty_score":0.28832337},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069294698,0.0009716572,0.9871648,0.00075051346,0.0032927769,0.00015181705,0.000005803543,0.00034084835,0.00039232973],"genre_scores_gemma":[0.9753953,0.010685772,0.004740476,0.00024731408,0.0024709532,0.000046732806,0.000040395564,0.00011590553,0.00625713],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99624276,0.00014226066,0.00035973586,0.00062774913,0.0006030293,0.0020244878],"domain_scores_gemma":[0.99848026,0.00009830724,0.00033206318,0.0008834045,0.00008549414,0.00012047977],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016361788,0.00030159458,0.00027460113,0.00034133877,0.00033159557,0.00043449353,0.0019494317,0.0002609576,0.000006189428],"category_scores_gemma":[0.00007312514,0.00025524228,0.0002246651,0.0002580017,0.000021078748,0.00028337384,0.0012518333,0.0060244678,0.00023456442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004163377,0.00011550774,0.000019417072,0.000017874374,0.00018919651,0.000044300763,0.00013465132,0.0023097803,0.000196715,0.22425719,0.0016088017,0.77106494],"study_design_scores_gemma":[0.000340098,0.00043069848,0.00027648208,0.00011548881,0.0000166227,0.0002495332,0.000045495563,0.04525203,0.00024247609,0.95118374,0.0015024208,0.00034494474],"about_ca_topic_score_codex":0.00012348066,"about_ca_topic_score_gemma":0.00066856184,"teacher_disagreement_score":0.9824243,"about_ca_system_score_codex":0.0011383604,"about_ca_system_score_gemma":0.0019816714,"threshold_uncertainty_score":0.99999},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034064397,0.00016274485,0.96205133,0.0017779811,0.0005598495,0.0005244288,0.000014230706,0.00041425996,0.00043079373],"genre_scores_gemma":[0.9324122,0.00021041361,0.064733595,0.00034692846,0.00031170575,0.00022435459,0.00014980267,0.000041861207,0.0015691579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817926,0.00005491102,0.0003865352,0.0006133346,0.00025625344,0.00050968915],"domain_scores_gemma":[0.9983012,0.00053936924,0.00009719146,0.000712674,0.00019360294,0.0001559477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043844015,0.00017610643,0.00020136069,0.0002226346,0.00053857215,0.0002356959,0.00092346786,0.00008732816,0.000016918322],"category_scores_gemma":[0.00008117318,0.00017075769,0.00010648887,0.0010515825,0.00007720623,0.0004826402,0.00044301592,0.00015926202,0.00073280255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004869086,0.00018782065,0.0017817096,0.00056538114,0.000061240535,0.00009892468,0.018345172,0.32941738,0.032442547,0.21190856,0.018004335,0.38713825],"study_design_scores_gemma":[0.000056902307,0.00009354464,0.00023877255,0.00012071791,0.0000027336812,0.000010005392,0.0006166419,0.8974658,0.07249295,0.004458911,0.024228431,0.00021456007],"about_ca_topic_score_codex":0.00003986165,"about_ca_topic_score_gemma":0.000013470828,"teacher_disagreement_score":0.8983478,"about_ca_system_score_codex":0.000046403544,"about_ca_system_score_gemma":0.00007050538,"threshold_uncertainty_score":0.9418939},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005805857,0.0000039806523,0.988972,0.0002796498,0.0004518663,0.000044389933,0.000009201363,0.00053361227,0.0038994253],"genre_scores_gemma":[0.23053597,0.000010828525,0.765904,0.0009106712,0.0001732185,0.000001956203,0.000041598378,0.000014359355,0.0024074046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915254,0.000024281942,0.00012400687,0.00024448842,0.00023846317,0.00021624769],"domain_scores_gemma":[0.9993489,0.00017109112,0.000033852444,0.00036116532,0.000026275316,0.000058753714],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001800361,0.00007874397,0.000079341255,0.00007472402,0.00016481969,0.00017175787,0.00048023643,0.000023344279,0.000037031587],"category_scores_gemma":[0.000014469427,0.00006178571,0.000016388582,0.0002760218,0.000009013731,0.00019722663,0.0005033972,0.000095089774,0.0010796823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016391476,0.000028845387,0.00009489358,0.000010461102,0.000006609382,0.00006331451,0.0005217449,0.0055971397,0.00020650202,0.5958317,0.123649694,0.27398747],"study_design_scores_gemma":[0.00011898681,0.000034759993,0.006105852,0.000024752657,7.8205636e-7,0.00000339589,0.00003246344,0.97517204,0.00014337114,0.01050734,0.0077324733,0.00012379776],"about_ca_topic_score_codex":0.00006007759,"about_ca_topic_score_gemma":0.0000031570994,"teacher_disagreement_score":0.96957487,"about_ca_system_score_codex":0.0000121809135,"about_ca_system_score_gemma":0.000017460421,"threshold_uncertainty_score":0.9996981},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029402576,0.00022970502,0.9921176,0.0008745641,0.0029378615,0.00029753806,0.000032018634,0.00054766843,0.0029336633],"genre_scores_gemma":[0.038980383,0.00029836656,0.95082515,0.0028922004,0.00085534743,0.000012597709,0.00012004669,0.0001988802,0.005817012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953317,0.000027739861,0.0005503395,0.0018947871,0.001325336,0.0008700931],"domain_scores_gemma":[0.99675417,0.0005168054,0.000307488,0.0019899334,0.0001630964,0.00026849663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007833118,0.00063220924,0.00063857983,0.0010697196,0.00037460242,0.00081332505,0.005250479,0.00035227658,0.000023993853],"category_scores_gemma":[0.000066256034,0.0005512676,0.00015919618,0.0008329293,0.00051955733,0.0009093304,0.0016304153,0.0010056879,0.0003820645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010218136,0.000046868052,0.000041286457,0.00007511614,0.00002907337,0.0006373897,0.0008255409,0.03060995,0.0002740444,0.042009976,0.0009690662,0.9244715],"study_design_scores_gemma":[0.00020121768,0.00011451985,0.00024796266,0.00049475854,0.0000054848633,0.0000792836,1.23608e-7,0.8338043,0.00012433811,0.16068771,0.003557427,0.0006828568],"about_ca_topic_score_codex":0.00005320068,"about_ca_topic_score_gemma":0.00006432948,"teacher_disagreement_score":0.9237886,"about_ca_system_score_codex":0.0003188704,"about_ca_system_score_gemma":0.0004313941,"threshold_uncertainty_score":0.9996939},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032544374,0.00013378335,0.989986,0.004996129,0.0011319335,0.00033284503,0.000008838315,0.00014167091,0.000014351387],"genre_scores_gemma":[0.5388335,0.000017249127,0.46032548,0.00052121904,0.00025745816,0.000023073097,0.000003195701,0.0000102848935,0.000008537682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787444,0.00004601063,0.00027528786,0.0006779576,0.0005891096,0.000537222],"domain_scores_gemma":[0.9974022,0.0012333986,0.000116878,0.001083737,0.00008058937,0.000083198596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011239497,0.00018026587,0.00022830314,0.00027444016,0.0003267021,0.00025071614,0.0030450288,0.000067383065,0.0000061154265],"category_scores_gemma":[0.00015147353,0.000115491275,0.00008601955,0.0025968745,0.00034880434,0.0006043283,0.0007155592,0.00018749473,0.000024938223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010238218,0.00006278394,0.0002778202,0.000029215182,0.000010114631,0.000008079708,0.0022250914,0.110226884,0.03028598,0.0022964336,0.00097803,0.8535893],"study_design_scores_gemma":[0.00022894063,0.00010014502,0.0039864643,0.000046323636,0.000002623297,0.000008954006,9.516461e-7,0.95725423,0.029122131,0.0076827407,0.0014044432,0.00016207369],"about_ca_topic_score_codex":0.0000323752,"about_ca_topic_score_gemma":0.000009957317,"teacher_disagreement_score":0.85342723,"about_ca_system_score_codex":0.00003781904,"about_ca_system_score_gemma":0.00017115907,"threshold_uncertainty_score":0.56584716},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06280087,0.000029582832,0.93490565,0.0006795682,0.00075483863,0.0003969605,0.000010123351,0.00041725053,0.000005176305],"genre_scores_gemma":[0.74964523,0.0000019766749,0.24966826,0.00049204373,0.000121305784,0.000039005175,0.000019880776,0.000011601452,6.960871e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708086,0.000045376004,0.000333636,0.0010292918,0.00062847213,0.0008823474],"domain_scores_gemma":[0.9977611,0.00084175955,0.0001318438,0.0009838705,0.000118157004,0.0001632792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001179464,0.00025493288,0.00028353083,0.00066095847,0.0005083552,0.0007137397,0.002765317,0.0001067818,0.0000024601213],"category_scores_gemma":[0.00015563224,0.000222607,0.000078888435,0.0038373603,0.0002258821,0.00086729607,0.0011099128,0.00026517684,0.000017304157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016843516,0.000075892094,0.012405543,0.000056926638,0.000003386864,0.000046949102,0.00048655362,0.19230959,0.0010696558,0.0009207394,0.00012781935,0.7924801],"study_design_scores_gemma":[0.0004972806,0.00011400463,0.013175308,0.000060670583,0.000001476899,0.000008476748,6.9417257e-7,0.9588229,0.0089589,0.017746704,0.00032867354,0.00028492938],"about_ca_topic_score_codex":0.00010446276,"about_ca_topic_score_gemma":0.000071477014,"teacher_disagreement_score":0.79219514,"about_ca_system_score_codex":0.00011278019,"about_ca_system_score_gemma":0.00021986794,"threshold_uncertainty_score":0.90776503},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036079993,0.00008970743,0.99084306,0.0003199539,0.003964966,0.000260803,0.0000079275005,0.0004548081,0.0040226853],"genre_scores_gemma":[0.21829145,0.00034895513,0.76105165,0.006022486,0.004210267,0.000073521485,0.000064267384,0.00033230783,0.00960509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996067,0.000029616102,0.0004065617,0.0016981148,0.0011884884,0.0006102308],"domain_scores_gemma":[0.99707866,0.00061035214,0.0002171401,0.0017757809,0.0001437735,0.00017432559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006644186,0.00048832543,0.00040945434,0.0010216187,0.0003378798,0.00056371675,0.0032516597,0.0003286305,0.000015122288],"category_scores_gemma":[0.000108395856,0.00041774914,0.00012745475,0.000789875,0.00031008225,0.0005877229,0.0017372138,0.0008794617,0.0003930739],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052132136,0.000017454504,0.0000017783423,0.00001144446,0.0000045170755,0.00009038752,0.00012264623,0.0089869425,0.00011928798,0.020477438,0.00007353088,0.9700894],"study_design_scores_gemma":[0.00022934025,0.00033462615,0.0001356318,0.0003564598,0.000004021396,0.00003557958,5.264959e-8,0.6907585,0.0019312465,0.30354714,0.0020742593,0.0005931182],"about_ca_topic_score_codex":0.00003029538,"about_ca_topic_score_gemma":0.00013746537,"teacher_disagreement_score":0.96949625,"about_ca_system_score_codex":0.00024435416,"about_ca_system_score_gemma":0.00024246557,"threshold_uncertainty_score":0.99982744},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06924202,0.0004967673,0.9239937,0.0001643487,0.0030681628,0.0007930115,0.000045610774,0.00061433355,0.001582006],"genre_scores_gemma":[0.9730782,0.00020997005,0.025722755,0.00014011486,0.00025451105,0.00011251496,0.0004062453,0.000014352111,0.000061330444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983616,0.00007957675,0.000672893,0.00015717174,0.00045046903,0.000278292],"domain_scores_gemma":[0.99913394,0.00003719139,0.00024423798,0.00042262743,0.00010607607,0.000055896387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007175785,0.0001253086,0.0001635167,0.00056792214,0.00014286012,0.0005574579,0.0004844045,0.000059451206,0.000012137381],"category_scores_gemma":[0.00001720102,0.00011717327,0.000037977064,0.001278583,0.000017103242,0.004796571,0.00022212742,0.00008667202,0.0004589459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034345492,0.00012387268,0.04061676,0.0011601391,0.00011511981,0.000043944256,0.07183893,0.10305627,0.0015584873,0.3662514,0.08742417,0.32777658],"study_design_scores_gemma":[0.00039420693,0.000027742853,0.0016863144,0.00013098463,0.0000023257228,0.000010518129,0.002830821,0.8379864,0.00023492276,0.00054060813,0.15596117,0.00019399243],"about_ca_topic_score_codex":0.0009728938,"about_ca_topic_score_gemma":0.000008540146,"teacher_disagreement_score":0.9038362,"about_ca_system_score_codex":0.000069126545,"about_ca_system_score_gemma":0.000034720742,"threshold_uncertainty_score":0.5898974},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.1210644e-7,0.00033980754,0.6482026,0.00034215368,0.002418598,0.00054061995,0.00037124226,0.0012909229,0.34649336],"genre_scores_gemma":[0.016463857,0.00036015626,0.021948017,0.0004912413,0.0026782705,0.00006144231,0.0026306661,0.0005780337,0.9547883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602234,0.00006092233,0.0008312875,0.0012001952,0.0012149101,0.0006703319],"domain_scores_gemma":[0.9968235,0.00033306703,0.0005789036,0.0018538593,0.00012354253,0.00028714084],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004316048,0.00072555774,0.000978849,0.00059198827,0.00065401616,0.0010163519,0.0022743405,0.00041347265,0.00014311119],"category_scores_gemma":[0.00001605049,0.0006758327,0.000280139,0.00014762764,0.00020776568,0.00039072626,0.0013856865,0.00050662115,0.0013191501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037421307,0.000008450985,0.0000022942636,0.00015319792,0.00009689924,0.000116730705,0.00017639979,0.00010535288,0.000026635451,0.87556463,0.123419285,0.0003263748],"study_design_scores_gemma":[0.0005676506,0.00010480275,0.00004821247,0.0014176938,0.000046249497,0.00014961767,0.00030095715,0.26271883,8.317124e-7,0.1756105,0.5577056,0.0013290789],"about_ca_topic_score_codex":0.000115278846,"about_ca_topic_score_gemma":0.00001351321,"teacher_disagreement_score":0.69995415,"about_ca_system_score_codex":0.0007741862,"about_ca_system_score_gemma":0.00012535913,"threshold_uncertainty_score":0.9995693},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3530179e-7,0.00011035135,0.6204407,0.00009447256,0.001030633,0.00040937465,0.00043258705,0.00059395796,0.37688744],"genre_scores_gemma":[0.018115837,0.000362044,0.02813952,0.0003508954,0.0021661718,0.00009623221,0.002200639,0.00056714745,0.9480015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971455,0.000051604682,0.00047055408,0.00095131,0.0009106841,0.00047037686],"domain_scores_gemma":[0.9977359,0.00031468962,0.00047226818,0.0011615555,0.00011528587,0.00020026887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002889931,0.00053737307,0.0006839533,0.0004201927,0.00044688396,0.00076760893,0.0013192949,0.0002727271,0.000083116975],"category_scores_gemma":[0.000011255509,0.00043229497,0.00010736082,0.00012275025,0.00014449205,0.00044238387,0.0006973339,0.00039786796,0.00075515214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009270632,0.0000067753926,0.0000013820609,0.000069120266,0.00013263612,0.00021757341,0.0001857972,0.000035998397,0.0000033487302,0.9615554,0.037505835,0.00027682842],"study_design_scores_gemma":[0.0016565613,0.0005987617,0.000050936535,0.0070300726,0.00011701498,0.00046892202,0.0007507694,0.1522535,0.000003497733,0.3355674,0.49882942,0.0026731102],"about_ca_topic_score_codex":0.00007922631,"about_ca_topic_score_gemma":0.000032184325,"teacher_disagreement_score":0.625988,"about_ca_system_score_codex":0.0005540072,"about_ca_system_score_gemma":0.00017105824,"threshold_uncertainty_score":0.9998129},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21847883,0.00065228797,0.74526876,0.003014047,0.0076814815,0.0031044798,0.00016253504,0.00699595,0.014641635],"genre_scores_gemma":[0.8609662,0.0006387596,0.12537955,0.0006427937,0.002055267,0.00053380104,0.0005357205,0.00021822589,0.009029701],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99569166,0.00022363223,0.000716993,0.0021019906,0.0006736075,0.00059209636],"domain_scores_gemma":[0.99460065,0.00013298736,0.00045071804,0.004339903,0.00023596405,0.00023974467],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001307065,0.0004909408,0.0005802583,0.00029308008,0.00023305805,0.0001697436,0.0039311023,0.00032802307,0.00016658778],"category_scores_gemma":[0.0002839104,0.00046916763,0.00026020888,0.0005035604,0.00005995878,0.0004453058,0.021330971,0.001373847,0.006774109],"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":[0.0002490378,0.0024499495,0.56620437,0.006360362,0.0021301473,0.0025524665,0.01858445,0.07416285,0.063659966,0.11410176,0.020579524,0.1289651],"study_design_scores_gemma":[0.001973906,0.00007685988,0.18819359,0.004945413,0.00013733978,0.00007643676,0.000085002896,0.6393337,0.042500198,0.047264032,0.07155719,0.0038563188],"about_ca_topic_score_codex":0.00027951787,"about_ca_topic_score_gemma":0.0000049594078,"teacher_disagreement_score":0.64248735,"about_ca_system_score_codex":0.00012685971,"about_ca_system_score_gemma":0.00019888856,"threshold_uncertainty_score":0.999776},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032311545,0.0003006102,0.9878312,0.0011646721,0.0011772212,0.00034549527,0.00002444916,0.0021236755,0.0038015523],"genre_scores_gemma":[0.04916169,0.000322174,0.941081,0.0013258298,0.0019141529,0.000108384476,0.0002961559,0.000087047105,0.005703598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983751,0.00005752052,0.00024560094,0.00052526355,0.0003670289,0.00042946692],"domain_scores_gemma":[0.9987632,0.00008949159,0.000076581375,0.00085219357,0.00008392831,0.00013460394],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043514612,0.00016469794,0.00019211289,0.00018014527,0.00022929112,0.00016579247,0.0009950841,0.000057419627,0.00002960748],"category_scores_gemma":[0.000042465228,0.0001390958,0.000070834845,0.0013246775,0.000028379889,0.0006808862,0.00082833273,0.00018002314,0.0014899875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056391564,0.00009387765,0.00021325005,0.000046318328,0.000047453286,0.00053707993,0.000979856,0.0007122492,0.0027634858,0.024864487,0.038490757,0.93124557],"study_design_scores_gemma":[0.00045734545,0.000054608157,0.0006562971,0.0000712754,0.0000049769524,0.00004151888,0.0000277306,0.9385925,0.001289795,0.0024008115,0.05611461,0.0002885412],"about_ca_topic_score_codex":0.00004185836,"about_ca_topic_score_gemma":7.779583e-7,"teacher_disagreement_score":0.9378802,"about_ca_system_score_codex":0.000024729958,"about_ca_system_score_gemma":0.00003719421,"threshold_uncertainty_score":0.9992875},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34600177,0.0025151162,0.6442184,0.0006594812,0.0033660275,0.0009966105,0.00042813606,0.0018025824,0.000011897549],"genre_scores_gemma":[0.9727803,0.00029934398,0.02593302,0.00017482234,0.00049022876,0.0001842605,7.0360977e-7,0.00011768851,0.00001961998],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606204,0.00013651392,0.00054929877,0.0018197674,0.0006665658,0.00076580554],"domain_scores_gemma":[0.9962224,0.00009360582,0.00038684194,0.002520259,0.00031210715,0.00046479015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006881211,0.00064321625,0.0005995707,0.0004461956,0.00032215202,0.0008570401,0.0018880306,0.0005116155,0.000014896874],"category_scores_gemma":[0.00009263693,0.0006316745,0.00012803364,0.00080075796,0.00013425843,0.00026755314,0.0054517644,0.000841527,0.00020252404],"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":[0.00019346381,0.00233161,0.019219704,0.0038856796,0.0015168895,0.0036845896,0.00086906157,0.025133142,0.8956326,0.034091342,0.0118305115,0.0016113756],"study_design_scores_gemma":[0.0013763717,0.0001833282,0.30026147,0.0011809357,0.00011221352,3.3707036e-7,0.0000139324375,0.666823,0.01128536,0.0000391225,0.015510078,0.0032138145],"about_ca_topic_score_codex":0.00015629761,"about_ca_topic_score_gemma":0.000003955381,"teacher_disagreement_score":0.88434726,"about_ca_system_score_codex":0.0001883749,"about_ca_system_score_gemma":0.00045974215,"threshold_uncertainty_score":0.99961346},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058889018,0.000027909293,0.7459433,0.00024404361,0.0012151441,0.0022502663,0.0008640779,0.00050924456,0.24888714],"genre_scores_gemma":[0.000041183543,0.0000106484595,0.16311455,0.0004991017,0.001766718,0.00026483455,0.0005341287,0.000105662904,0.83366317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833006,0.000004219489,0.0003980033,0.00054372713,0.0004378767,0.00028612974],"domain_scores_gemma":[0.9985481,0.0006203179,0.00027966022,0.00041773776,0.00004054639,0.000093670584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003096412,0.00035158088,0.00045640682,0.00004862602,0.00030574386,0.00041163378,0.0005398981,0.00053012726,0.0000023083944],"category_scores_gemma":[0.000011372183,0.00028652,0.00035343986,0.00003673173,0.00010688719,0.00008325922,0.0005222901,0.00045789135,0.000027290658],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000820136,0.000027742888,1.6850176e-8,0.00013649694,0.00010749711,7.426341e-7,0.0004594054,0.00006404085,0.0000074007644,0.74958503,0.23142818,0.018175224],"study_design_scores_gemma":[0.0013554869,0.000110681234,2.0166587e-7,0.00038267893,0.00006855993,0.000003179901,0.00006333639,0.018224599,0.00006638683,0.8762517,0.10295552,0.0005176677],"about_ca_topic_score_codex":5.3813454e-7,"about_ca_topic_score_gemma":1.8353782e-7,"teacher_disagreement_score":0.58477604,"about_ca_system_score_codex":0.00006930798,"about_ca_system_score_gemma":0.00027931272,"threshold_uncertainty_score":0.9999587},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015981372,0.00019051867,0.99540854,0.0008634353,0.000980693,0.0004997317,0.000036693204,0.00034903514,0.00007323737],"genre_scores_gemma":[0.09105132,0.0011097678,0.89708143,0.00042881435,0.0005735671,0.000546857,0.0013155675,0.00006440484,0.007828289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983046,0.00006890182,0.00044505735,0.000632861,0.0001354841,0.00041309284],"domain_scores_gemma":[0.99874216,0.00020240896,0.00014030289,0.00066283654,0.00015715965,0.00009514235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004462382,0.0001807984,0.00018953516,0.00023622488,0.0003251462,0.00015497925,0.0007427888,0.00011376264,0.000040452254],"category_scores_gemma":[0.0000918762,0.00016815578,0.000099002806,0.0009223479,0.00005382235,0.0005383434,0.00034982187,0.00010411659,0.00067399716],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005832321,0.00012642107,0.00012459912,0.000031249696,0.000013894407,0.0000074510526,0.0008015009,0.010545521,0.0064100786,0.018523056,0.0044929967,0.9589174],"study_design_scores_gemma":[0.00006960032,0.00015681499,0.000079806516,0.000041189916,0.0000048421784,0.000004380368,0.00015164459,0.93622243,0.019276118,0.0037767412,0.04001452,0.00020188066],"about_ca_topic_score_codex":0.0000722524,"about_ca_topic_score_gemma":0.000013181703,"teacher_disagreement_score":0.9587155,"about_ca_system_score_codex":0.00004961151,"about_ca_system_score_gemma":0.000046842077,"threshold_uncertainty_score":0.86630946},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020964047,0.00007400072,0.9768392,0.000119046745,0.00030497336,0.00052184134,0.000032580134,0.00038094388,0.00076338224],"genre_scores_gemma":[0.014208965,0.00001983997,0.9854193,0.000040420746,0.000045187255,0.000013868205,0.000034036766,0.0000101500455,0.00020823751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986589,0.000027426971,0.00042292298,0.00016265518,0.00042864302,0.00029943776],"domain_scores_gemma":[0.9987474,0.00007751514,0.00030676436,0.00067097915,0.00010211845,0.00009519357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002151771,0.00015571907,0.00020229461,0.00021511108,0.00012934579,0.00015373566,0.00092160935,0.00007826348,0.0000109981975],"category_scores_gemma":[0.000096052274,0.00011538899,0.000067088375,0.00075624074,0.00006044046,0.0010638572,0.00095329277,0.000120756216,0.00009169982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014509253,0.0004139843,0.0015501265,0.0065448475,0.00010708913,0.00003635749,0.0118724955,0.0022329052,0.14290206,0.109378025,0.112367086,0.61244994],"study_design_scores_gemma":[0.0003837482,0.00006478786,0.0042302636,0.00010272943,0.000003997217,0.0000050996987,0.00014775283,0.9805561,0.009286007,0.0020695247,0.0029788732,0.00017117064],"about_ca_topic_score_codex":0.00002129829,"about_ca_topic_score_gemma":0.0000011400917,"teacher_disagreement_score":0.97832316,"about_ca_system_score_codex":0.000018769075,"about_ca_system_score_gemma":0.00008881646,"threshold_uncertainty_score":0.47054264},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019944606,0.000021869993,0.9933905,0.0026664585,0.0006705953,0.00008392454,0.000016093714,0.00074639363,0.00040970472],"genre_scores_gemma":[0.75126714,0.0016513672,0.2380337,0.0041369414,0.00025263018,0.00014299386,0.00009914319,0.00008155131,0.0043345676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989404,0.000031606243,0.00014856437,0.00032895518,0.00030000662,0.00025043116],"domain_scores_gemma":[0.99855703,0.00015598857,0.000032794196,0.0011133396,0.000047116388,0.00009375312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020448172,0.00011336274,0.00009708711,0.0003805695,0.00036299988,0.00013252025,0.0010019185,0.000073574534,0.000026931397],"category_scores_gemma":[0.00001948038,0.00010368323,0.00009253048,0.0016479203,0.000034522323,0.00048579604,0.000034104956,0.00025173553,0.0006185863],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028006369,0.00046383962,0.0001747972,0.00004573099,0.00012592536,0.00012440734,0.0010045836,0.0089830775,0.0012482747,0.07101778,0.038758073,0.87802553],"study_design_scores_gemma":[0.0011578528,0.0003628653,0.004907104,0.00016029907,0.00003684226,0.0000427665,0.000116557705,0.57969606,0.0044531077,0.11966858,0.288456,0.000941982],"about_ca_topic_score_codex":0.000011040494,"about_ca_topic_score_gemma":0.000009957605,"teacher_disagreement_score":0.87708354,"about_ca_system_score_codex":0.000010183589,"about_ca_system_score_gemma":0.000028452336,"threshold_uncertainty_score":0.7950882},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018585744,0.000082701146,0.9470094,0.0013246861,0.0085152015,0.00026369456,0.0000054638494,0.0006737953,0.04210651],"genre_scores_gemma":[0.0015839429,0.000657969,0.722485,0.0010543211,0.011482058,0.00004338353,0.000035929017,0.00020300927,0.2624544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99572647,0.000016834269,0.000524948,0.001901837,0.001183615,0.0006463043],"domain_scores_gemma":[0.99706936,0.00008314682,0.00024102467,0.0022175338,0.0001904934,0.00019842503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012802175,0.00040469776,0.00040635504,0.001012086,0.00027598708,0.00066980626,0.0040989006,0.00019610484,0.0000586903],"category_scores_gemma":[0.000038601895,0.00040119427,0.00010184987,0.0007219957,0.0004569337,0.0014265977,0.0042357156,0.0006477878,0.000983951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017795343,0.000014943965,0.000005992667,0.000020195632,0.000005208339,0.000103595165,0.000104259314,0.0007251295,0.00004959383,0.6793143,0.0039597503,0.31569526],"study_design_scores_gemma":[0.0003749086,0.00017560352,0.0010244058,0.0004407758,0.0000073148,0.00009212217,9.198103e-7,0.49927068,0.00037744627,0.12835582,0.36850685,0.001373179],"about_ca_topic_score_codex":0.00002594524,"about_ca_topic_score_gemma":0.000011647311,"teacher_disagreement_score":0.55095845,"about_ca_system_score_codex":0.00026435373,"about_ca_system_score_gemma":0.00038004795,"threshold_uncertainty_score":0.999844},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019221239,0.00071896054,0.9934654,0.00046974132,0.0027549989,0.0002919187,0.000009507384,0.0003782275,0.0017190088],"genre_scores_gemma":[0.17638071,0.0010604027,0.8150062,0.0019900422,0.002384671,0.000031604282,0.000045234778,0.00018555879,0.0029156154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99561137,0.00003183801,0.00051039533,0.0019495693,0.0011045265,0.0007922967],"domain_scores_gemma":[0.99718696,0.0005475732,0.00025017,0.0016309869,0.0001176717,0.00026662732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008959617,0.00057143654,0.0005619538,0.00089200377,0.00039316245,0.00097303133,0.0032309128,0.00034165976,0.0000146835755],"category_scores_gemma":[0.00007875097,0.0005138751,0.0000985193,0.00084801216,0.00053681515,0.0009204221,0.0038503516,0.0009204108,0.000067708235],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038264934,0.000013648459,0.00013787423,0.000042084248,0.000009313563,0.00019285029,0.00067464274,0.0022869168,0.00007616999,0.011715216,0.00007965471,0.9847678],"study_design_scores_gemma":[0.0005416573,0.00019399647,0.0011457183,0.0012743056,0.000011158324,0.0001759481,7.7545576e-7,0.79839426,0.0006853565,0.19166036,0.0045163357,0.0014001312],"about_ca_topic_score_codex":0.00006503761,"about_ca_topic_score_gemma":0.00006677255,"teacher_disagreement_score":0.9833677,"about_ca_system_score_codex":0.00015895345,"about_ca_system_score_gemma":0.0003133111,"threshold_uncertainty_score":0.9997313},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003615372,0.00072123995,0.990107,0.0020908418,0.002837277,0.0006377348,0.000017548857,0.000597061,0.0029551317],"genre_scores_gemma":[0.05681795,0.0025719404,0.9210651,0.0030726488,0.0027644832,0.00019055087,0.000103992956,0.00033907391,0.013074276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938353,0.00007393962,0.00079767033,0.002263422,0.0017893525,0.0012403564],"domain_scores_gemma":[0.99461025,0.0011089534,0.00046476908,0.0030802025,0.00044985453,0.00028599135],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019159055,0.0007331949,0.00055254204,0.00056602934,0.0011424413,0.0017807785,0.008824321,0.00039681717,0.000010797422],"category_scores_gemma":[0.0001630954,0.00050684105,0.00016722648,0.0014268247,0.0015648311,0.0011168459,0.0036087558,0.0013220948,0.0002805472],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007838567,0.00002115127,0.000050490657,0.000035413534,0.000017788647,0.0004728803,0.00038465147,0.0122895865,0.00024786688,0.09410202,0.00023316777,0.89213717],"study_design_scores_gemma":[0.00028665175,0.00022610194,0.00032266352,0.0008720766,0.0000109844905,0.00020679826,3.5090665e-7,0.5049376,0.0012053397,0.48261198,0.008103632,0.0012158116],"about_ca_topic_score_codex":0.00012685118,"about_ca_topic_score_gemma":0.00030140046,"teacher_disagreement_score":0.89092135,"about_ca_system_score_codex":0.00036734654,"about_ca_system_score_gemma":0.00097294303,"threshold_uncertainty_score":0.99973834},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3691958,0.00005996334,0.62296945,0.00042484654,0.0016165185,0.0001401729,0.000017221351,0.0015342138,0.0040418017],"genre_scores_gemma":[0.954212,0.000066233384,0.040601034,0.00051049667,0.0006997328,0.00003420209,0.00006117972,0.000040707626,0.0037744069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924743,0.0000102937465,0.00008560065,0.00024119517,0.00017955076,0.00023591267],"domain_scores_gemma":[0.9993322,0.000036198195,0.000031267016,0.0005162737,0.000032995587,0.00005106506],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008030025,0.00007925818,0.00007496375,0.00003326233,0.00014110397,0.00018216755,0.00059984066,0.00002690681,0.000007252183],"category_scores_gemma":[0.000009548856,0.00007120847,0.00003751749,0.0004965856,0.000022924056,0.0004950278,0.0005382591,0.00007308553,0.0011072668],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008198272,0.00011409381,0.0026122099,0.00005681944,0.0000408729,0.0001369634,0.0022823336,0.005085532,0.010041879,0.11599594,0.027053105,0.83657205],"study_design_scores_gemma":[0.00073479663,0.00010415878,0.091224514,0.00006756499,0.0000056341655,0.000009260638,0.000057570924,0.6833593,0.0047071306,0.087267905,0.1317179,0.0007442419],"about_ca_topic_score_codex":0.000040896408,"about_ca_topic_score_gemma":7.4011166e-7,"teacher_disagreement_score":0.8358278,"about_ca_system_score_codex":0.000009390428,"about_ca_system_score_gemma":0.000023130244,"threshold_uncertainty_score":0.9996705},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6915212,0.023934249,0.15233867,0.016282996,0.040916283,0.010608192,0.009798911,0.013135356,0.041464083],"genre_scores_gemma":[0.87693495,0.01168746,0.054705963,0.0067087756,0.008006346,0.0016735045,0.0067043374,0.0018368938,0.03174175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9731642,0.0020264753,0.004957087,0.007096139,0.005511323,0.0072447984],"domain_scores_gemma":[0.98348445,0.002261521,0.0024985757,0.007393523,0.0014267986,0.0029351574],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"category_scores_codex":[0.004573106,0.004155679,0.0038672993,0.003226388,0.0034012543,0.0040375483,0.010126424,0.0019286716,0.0024021186],"category_scores_gemma":[0.0009429392,0.004308691,0.0021438978,0.00930716,0.0012759165,0.0067955484,0.008397485,0.0037987651,0.021967456],"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":[0.0015822423,0.0040144785,0.0072790873,0.0020820086,0.003307175,0.010107113,0.03145446,0.008660046,0.008815556,0.024923827,0.7114042,0.18636978],"study_design_scores_gemma":[0.009627563,0.0016584661,0.04893032,0.0019221102,0.00093510916,0.001210862,0.0042306306,0.39767683,0.004343187,0.0051435623,0.51631063,0.008010747],"about_ca_topic_score_codex":0.0011500643,"about_ca_topic_score_gemma":0.0002486013,"teacher_disagreement_score":0.38901678,"about_ca_system_score_codex":0.00091504434,"about_ca_system_score_gemma":0.0015248368,"threshold_uncertainty_score":0.9996224},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047204413,0.0001497971,0.94983613,0.00017737856,0.0012785092,0.0001939013,0.00002181998,0.00076549297,0.0003725843],"genre_scores_gemma":[0.96817106,0.00038895782,0.030792426,0.00016155133,0.000080294005,0.00004069045,0.000009633658,0.00003886174,0.00031652188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979925,0.00007819258,0.00033929886,0.0005634012,0.0003593614,0.00066720805],"domain_scores_gemma":[0.9988229,0.000166231,0.0001002356,0.00068678206,0.00009038568,0.00013342462],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002329805,0.00024132995,0.00020986453,0.0003932139,0.0011255264,0.00028871588,0.00063875475,0.000118758144,0.00004278851],"category_scores_gemma":[0.00000749174,0.00024868778,0.0001228024,0.0014292691,0.00005371073,0.0009209508,0.000014408787,0.0005913177,0.00015361312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003180215,0.00033210343,0.00007227785,0.000052482723,0.00027466143,0.00004489735,0.0010511602,0.12577383,0.07806188,0.011899752,0.0018790832,0.7805261],"study_design_scores_gemma":[0.000482952,0.00011801157,0.000031207866,0.000055753877,0.00003841826,0.0000872401,0.00006296204,0.9472429,0.040326025,0.0010530367,0.010070606,0.00043084956],"about_ca_topic_score_codex":0.000069991074,"about_ca_topic_score_gemma":0.000080618396,"teacher_disagreement_score":0.9209666,"about_ca_system_score_codex":0.00018362889,"about_ca_system_score_gemma":0.0002800169,"threshold_uncertainty_score":0.99999654},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027129421,0.00012494472,0.9718478,0.00015888586,0.0002418624,0.00011230599,0.00010368929,0.00016861166,0.00011253522],"genre_scores_gemma":[0.018172793,0.00002859408,0.9812373,0.00009772159,0.00012453065,0.00001854539,0.00020092462,0.000012816955,0.00010677456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988693,0.000079417216,0.00020196529,0.00035620987,0.0002830258,0.00021010992],"domain_scores_gemma":[0.99910367,0.00024683625,0.00006551587,0.00035354597,0.00012466237,0.00010580036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024330152,0.00011278105,0.000108323926,0.00012772514,0.00025953574,0.00016958827,0.00023606299,0.000039733623,0.000008834819],"category_scores_gemma":[0.00008086953,0.000103452905,0.000015398744,0.00042798233,0.000029224097,0.00011938663,0.00037360436,0.00011939793,0.000024490151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015327076,0.00056917797,0.0043526515,0.00019036946,0.00013029618,0.00010259865,0.0076974686,0.19823593,0.04995231,0.072824165,0.034145616,0.6317841],"study_design_scores_gemma":[0.00011982357,0.000048175312,0.0038424998,0.000027650904,0.0000072605967,0.0000057467214,0.00011442772,0.99054736,0.0011810086,0.0021733514,0.0018021901,0.00013052535],"about_ca_topic_score_codex":0.000006068558,"about_ca_topic_score_gemma":0.00000967572,"teacher_disagreement_score":0.79231143,"about_ca_system_score_codex":0.0000146310795,"about_ca_system_score_gemma":0.00006089496,"threshold_uncertainty_score":0.4218687},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006849866,0.00054815144,0.99225163,0.00066889153,0.0017463511,0.0009465309,0.00019901806,0.002449188,0.00050525373],"genre_scores_gemma":[0.029403886,0.00026973625,0.9692444,0.000066496235,0.00017730599,0.00019419214,0.00008286637,0.000059014383,0.0005020641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968403,0.000042531356,0.000521011,0.0014901911,0.00045863359,0.0006473592],"domain_scores_gemma":[0.9973574,0.0004880972,0.00041273297,0.0013538367,0.00031300652,0.00007492335],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00047054057,0.00050530076,0.0005773309,0.00048771015,0.0005199535,0.0005246572,0.0027481695,0.0005036089,0.000009213433],"category_scores_gemma":[0.00028391308,0.00043038366,0.00030138405,0.00046889158,0.00011957409,0.0005977631,0.0104125645,0.00073451333,0.000011780223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006187166,0.0002211759,0.0001474514,0.0007597277,0.0007059038,0.00009287716,0.0030722946,0.030745808,0.0019130026,0.27957326,0.010297183,0.6724095],"study_design_scores_gemma":[0.00022730915,0.0000691839,0.000019510604,0.00064324844,0.000025341227,0.0000067035403,0.0008408611,0.88894856,0.0026281995,0.10140616,0.0045589283,0.00062598166],"about_ca_topic_score_codex":0.00015140568,"about_ca_topic_score_gemma":0.000019711864,"teacher_disagreement_score":0.85820276,"about_ca_system_score_codex":0.00022756541,"about_ca_system_score_gemma":0.00018116717,"threshold_uncertainty_score":0.9998148},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022005522,0.0016021496,0.802025,0.010678736,0.005501244,0.00045681608,0.00010365216,0.0013354192,0.17829475],"genre_scores_gemma":[0.0014858645,0.00047185493,0.30890214,0.0059154555,0.052835017,0.00015380133,0.00030470698,0.00073809444,0.62919307],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613225,0.00006218133,0.00047783114,0.0019525136,0.0008553269,0.0005198824],"domain_scores_gemma":[0.99676967,0.00046317675,0.00020783462,0.0022649646,0.00008287226,0.00021147149],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002107774,0.0009564521,0.0007236253,0.00077132543,0.00024854773,0.0006650295,0.0021037927,0.0005900744,0.00046924184],"category_scores_gemma":[0.000027431857,0.00072150846,0.0004940269,0.00013661855,0.000106899344,0.0001473175,0.0011176027,0.0017382707,0.0015929348],"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":[0.000019737554,0.000022485381,4.003527e-8,0.00009677645,0.00017152696,0.00012777344,0.00012514254,0.002457261,0.00003185234,0.26554903,0.15456526,0.57683307],"study_design_scores_gemma":[0.00006359972,0.00016565458,0.0000036938593,0.00046469408,0.00005504464,0.00017322839,2.1279084e-7,0.009336478,0.0005304797,0.17308302,0.8154263,0.0006975936],"about_ca_topic_score_codex":0.0000046665505,"about_ca_topic_score_gemma":0.0000059833383,"teacher_disagreement_score":0.660861,"about_ca_system_score_codex":0.0001361898,"about_ca_system_score_gemma":0.00010028337,"threshold_uncertainty_score":0.9995236},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18330383,0.00093031116,0.8136753,0.00047187772,0.00013109259,0.00024176513,0.000103752136,0.00022155793,0.0009205527],"genre_scores_gemma":[0.9885431,0.00019566095,0.010992176,0.00007812192,0.000027471737,0.000033235425,0.00011110011,0.000006536949,0.000012595352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989918,0.00004709407,0.00025564828,0.00032875457,0.00019863134,0.00017806781],"domain_scores_gemma":[0.9993484,0.00009937181,0.000036683577,0.00042150795,0.000041028903,0.000053000636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017937778,0.00013323253,0.000122018755,0.0001283671,0.000101006866,0.0005092873,0.00057945226,0.000046205074,0.000028797946],"category_scores_gemma":[0.0000064899764,0.000112284455,0.00004178122,0.0005223793,0.00008918702,0.0017460469,0.0003373261,0.00020008997,0.000014214387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007384828,0.001346472,0.0013062776,0.0002200801,0.00015409321,0.00008381384,0.03407929,0.00024634364,0.020680437,0.45943967,0.004025298,0.47834438],"study_design_scores_gemma":[0.0009657141,0.00026769674,0.0027215686,0.0004974222,0.000016913911,0.000019182511,0.00064830756,0.91677517,0.0029777177,0.045854826,0.028757809,0.0004976489],"about_ca_topic_score_codex":0.000051410647,"about_ca_topic_score_gemma":0.000038582824,"teacher_disagreement_score":0.9165289,"about_ca_system_score_codex":0.000033421264,"about_ca_system_score_gemma":0.000039932882,"threshold_uncertainty_score":0.4911069},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006058659,0.0015301986,0.9825153,0.0014353319,0.0059161303,0.00029853403,0.00006877928,0.0003252382,0.007849926],"genre_scores_gemma":[0.0661059,0.00018475905,0.9253058,0.0021985706,0.001997857,0.00001647119,0.00007577535,0.00010658441,0.0040082815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99547285,0.000021286816,0.0004561204,0.0021490685,0.0012390462,0.0006616465],"domain_scores_gemma":[0.9968229,0.0005038941,0.00018277012,0.0020507292,0.00015985421,0.000279856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044823147,0.0005773475,0.0005083534,0.0007692083,0.0003075839,0.0009362162,0.004046029,0.00034498068,0.00011047375],"category_scores_gemma":[0.00004116263,0.00047922687,0.00017564648,0.0006455732,0.0005687845,0.00042284888,0.004355286,0.0010584646,0.0006646479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010802958,0.00009708593,0.000017328914,0.00006737449,0.000048610396,0.0009317888,0.0020379543,0.07087524,0.00048772013,0.27214625,0.0013076025,0.65197223],"study_design_scores_gemma":[0.00015929113,0.0000683372,0.000025166579,0.0006029544,0.000011954943,0.000027323165,2.3138648e-7,0.8301667,0.000703442,0.14523034,0.022438541,0.0005657439],"about_ca_topic_score_codex":0.00010758998,"about_ca_topic_score_gemma":0.000021814067,"teacher_disagreement_score":0.75929147,"about_ca_system_score_codex":0.00030972718,"about_ca_system_score_gemma":0.0005026775,"threshold_uncertainty_score":0.99976593},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004035491,0.0017136943,0.9742312,0.0010201554,0.004458116,0.00023806038,0.00001907131,0.00033046654,0.017985243],"genre_scores_gemma":[0.010964733,0.00021345308,0.973357,0.0028725027,0.0021546355,0.00001793161,0.000036454345,0.00010730799,0.0102759795],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995793,0.00001491943,0.00046066608,0.0019372889,0.0011249796,0.0006691428],"domain_scores_gemma":[0.99731857,0.00022154131,0.00014891362,0.0019494013,0.00015319047,0.00020841652],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005996412,0.0005503794,0.00046110232,0.0008473634,0.00021347258,0.0011623274,0.0043887123,0.00033151775,0.000054445863],"category_scores_gemma":[0.00002741129,0.0004484401,0.00014823253,0.000618626,0.00044919105,0.0008584024,0.0037399738,0.0010611755,0.0005794995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020474004,0.000016945805,0.000004528809,0.000049590588,0.000010345692,0.00030696456,0.0002965237,0.0032315832,0.000061836334,0.14834043,0.0007406958,0.8469385],"study_design_scores_gemma":[0.000110264766,0.00008416743,0.00001421992,0.0005676918,0.000006406228,0.00009807721,4.3535383e-8,0.4045037,0.0003365436,0.53508353,0.05860212,0.00059320603],"about_ca_topic_score_codex":0.000021126172,"about_ca_topic_score_gemma":0.000023230043,"teacher_disagreement_score":0.8463453,"about_ca_system_score_codex":0.00023102584,"about_ca_system_score_gemma":0.00042299114,"threshold_uncertainty_score":0.99987453},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0121034775,0.0012135712,0.9841006,0.00031139125,0.0018846333,0.00008150614,0.00019459955,0.000029543904,0.00008071351],"genre_scores_gemma":[0.5893031,0.00044658835,0.40929744,0.000051000574,0.00077584275,0.000015046042,0.000045316403,0.000022882678,0.00004283738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982759,0.00004727297,0.0007432366,0.00031008114,0.00042087023,0.00020265736],"domain_scores_gemma":[0.9975236,0.00029749147,0.0009417428,0.00059975305,0.00053540437,0.0001020306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020145056,0.0002378319,0.00062963396,0.00016573435,0.00007111508,0.0002637897,0.0012744808,0.00012764202,0.000003415327],"category_scores_gemma":[0.00003245385,0.00020042407,0.0004543037,0.00021327996,0.00003108462,0.0006227496,0.0015047388,0.00049110985,0.0000010419441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029358962,0.00019630672,7.614057e-7,0.00016638545,0.00025820872,0.000012522578,0.000089037916,0.02629026,0.001735541,0.59154975,0.0011140998,0.37855777],"study_design_scores_gemma":[0.00044114303,0.0002509169,0.00003949168,0.0017005452,0.00014684763,0.000019251025,0.00001659876,0.02180528,0.075953424,0.8961977,0.0031366767,0.00029216183],"about_ca_topic_score_codex":0.00003710587,"about_ca_topic_score_gemma":0.0000022879801,"teacher_disagreement_score":0.5771996,"about_ca_system_score_codex":0.00009245686,"about_ca_system_score_gemma":0.00028224222,"threshold_uncertainty_score":0.8173056},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003802812,0.0029009732,0.9907516,0.00094508025,0.0017736409,0.00025262462,0.00004761792,0.00021339883,0.0030770302],"genre_scores_gemma":[0.15633668,0.0007680946,0.83036476,0.0050246036,0.0023901528,0.000035186757,0.000102999285,0.00018696464,0.004790528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965174,0.000014061173,0.00036872932,0.0017636606,0.0008125926,0.00052355585],"domain_scores_gemma":[0.9982446,0.00021557983,0.00005196372,0.0011781893,0.00010213565,0.0002075659],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043971968,0.00049704174,0.00042785722,0.00059858465,0.00021521065,0.0010836282,0.0023980855,0.00029760398,0.00004264207],"category_scores_gemma":[0.000017772983,0.00040086365,0.000096108364,0.00041258844,0.00045762223,0.0007719759,0.00199201,0.0008461437,0.00010803397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003087622,0.0000135262735,0.000012205022,0.00009725047,0.000011606111,0.000258307,0.0006449246,0.0010793405,0.00012457512,0.067360364,0.0001402818,0.9302545],"study_design_scores_gemma":[0.00023821929,0.00016932728,0.0001021718,0.0011552478,0.000015119695,0.00021276205,1.5441846e-7,0.6346798,0.00053500506,0.3355557,0.02642725,0.0009092604],"about_ca_topic_score_codex":0.00001749046,"about_ca_topic_score_gemma":0.000034389122,"teacher_disagreement_score":0.92934525,"about_ca_system_score_codex":0.00011630347,"about_ca_system_score_gemma":0.00023371942,"threshold_uncertainty_score":0.9999533},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027880105,0.00014492488,0.12900862,0.00026053723,0.00045553225,0.00040854272,0.86622936,0.000529167,0.002960505],"genre_scores_gemma":[0.000025889647,0.00031181122,0.0018719875,0.00037266393,0.00034579553,4.207182e-8,0.99573195,0.0006349428,0.0007049279],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99718195,0.00031077032,0.00036839934,0.0009788234,0.0006712036,0.0004888673],"domain_scores_gemma":[0.99631417,0.00005005753,0.00024409342,0.0026955775,0.0004679846,0.00022814525],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006046858,0.00030165602,0.00030555364,0.00034504806,0.0014980546,0.0018037413,0.005327248,0.00012614009,0.010353601],"category_scores_gemma":[0.00038629535,0.00028809396,0.00008077126,0.00053341413,0.00009131301,0.0008228624,0.009257984,0.0005902861,0.04182652],"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":[0.000018097155,0.00011387946,3.4541195e-8,0.000077258774,0.000019161007,0.000024345814,0.00002727983,0.000011424521,0.000054592365,0.0006415694,0.962709,0.03630336],"study_design_scores_gemma":[0.000458415,0.00010754188,0.000008628219,0.00008711456,0.000015078972,0.00011745736,0.000011105272,0.0015410458,0.000028209945,0.000039991748,0.9972458,0.00033962008],"about_ca_topic_score_codex":0.00008206018,"about_ca_topic_score_gemma":5.1871467e-7,"teacher_disagreement_score":0.12950255,"about_ca_system_score_codex":0.00011015392,"about_ca_system_score_gemma":0.000010765986,"threshold_uncertainty_score":0.99995714},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3768764e-9,0.00042546203,0.000038457903,0.00005471654,0.00040428495,0.00010462748,0.9985526,0.00008184441,0.00033800025],"genre_scores_gemma":[2.291901e-7,0.000020212656,0.0008876122,0.0001705004,0.00039774194,0.00007270561,0.99818456,0.0000058411406,0.00026062026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869084,0.000028027307,0.00014657372,0.00052663643,0.00035502136,0.00025288598],"domain_scores_gemma":[0.99700135,0.0000651858,0.00028720615,0.0024596395,0.00007789533,0.00010874439],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000040471197,0.0002236876,0.00021740462,0.000069872556,0.0003002108,0.00086686754,0.005316783,0.00023311318,0.072189614],"category_scores_gemma":[0.0004157893,0.000181319,0.00007703245,0.000059224134,0.000007463101,0.00070754864,0.0022743247,0.00032090186,0.022002365],"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":[2.388882e-7,0.000008267746,3.6450757e-8,0.00007606606,0.000005041717,0.000100818994,0.0000021487454,5.7404725e-7,1.2993287e-7,0.0000024008473,0.99520755,0.0045967572],"study_design_scores_gemma":[0.00004794348,0.00001931286,0.000017372902,0.0016182085,0.000002737952,0.000017760034,2.9116617e-7,0.00040736198,0.00000785698,0.000089277775,0.99752146,0.00025041553],"about_ca_topic_score_codex":0.000062355975,"about_ca_topic_score_gemma":0.000018159093,"teacher_disagreement_score":0.05018725,"about_ca_system_score_codex":0.000022404376,"about_ca_system_score_gemma":0.0001978992,"threshold_uncertainty_score":0.9879995},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.943836e-9,0.00082848396,0.000037396578,0.000033675948,0.00025513244,0.0001759866,0.99857944,0.000043356984,0.000046524026],"genre_scores_gemma":[5.3096375e-8,0.000075855416,0.0011067422,0.00031583093,0.00021480669,0.00006700332,0.9981087,0.000008984466,0.00010202047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984796,0.00003988511,0.00017320391,0.00069229025,0.0003214295,0.00029358236],"domain_scores_gemma":[0.996336,0.00006386085,0.000268286,0.0030453955,0.00010503256,0.00018143235],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00006519756,0.0002847615,0.00027983115,0.00007975282,0.0003222526,0.0009629375,0.0033214185,0.00025611348,0.027890729],"category_scores_gemma":[0.00078247464,0.00024374813,0.000025921869,0.00009378147,0.000013452728,0.0007930069,0.003846786,0.0003746262,0.007267705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.5227384e-7,0.000016802349,1.1073969e-7,0.00011968167,0.000007998974,0.00010907536,0.000001405201,1.5375007e-7,9.801295e-8,0.000002057022,0.9970297,0.002712046],"study_design_scores_gemma":[0.00014393296,0.000025479396,0.00003367279,0.0010868541,0.000006614782,0.000039235347,3.4845715e-7,0.00083823624,0.00000268465,0.000022686936,0.9974849,0.00031534384],"about_ca_topic_score_codex":0.00007080906,"about_ca_topic_score_gemma":0.00004234722,"teacher_disagreement_score":0.020623025,"about_ca_system_score_codex":0.000015238376,"about_ca_system_score_gemma":0.00015713592,"threshold_uncertainty_score":0.99397606},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05284898,0.0011767751,0.9299838,0.0011419994,0.002142723,0.0010093041,0.000072325114,0.0006359836,0.010988113],"genre_scores_gemma":[0.99004793,0.0011452575,0.005127968,0.00009593615,0.00010630044,0.000006536614,0.000021580552,0.00002823467,0.0034202503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978543,0.0001716342,0.00023842775,0.0011835884,0.0001221492,0.0004298807],"domain_scores_gemma":[0.99796885,0.00013236029,0.00014457344,0.001561061,0.00006148134,0.00013169962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040662906,0.00030562366,0.00024793486,0.000263538,0.00020804149,0.00039654106,0.0029087563,0.0002529292,0.000007179649],"category_scores_gemma":[0.000013983019,0.00024297344,0.00019478523,0.0008487727,0.00011906581,0.00027906967,0.0075755618,0.0011439599,0.00012035709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000437162,0.00013987262,0.0012288354,0.00019620643,0.00009167116,0.0013793313,0.00039115062,0.039989166,0.000030052315,0.9405706,0.002338936,0.013600452],"study_design_scores_gemma":[0.00019207578,0.000026305768,0.00079428393,0.0002574449,0.000018721166,0.0000058485875,0.000038615948,0.3212254,0.000022611694,0.67109376,0.0060085775,0.00031634382],"about_ca_topic_score_codex":0.00044722782,"about_ca_topic_score_gemma":0.0001745334,"teacher_disagreement_score":0.93719894,"about_ca_system_score_codex":0.00015126071,"about_ca_system_score_gemma":0.00022682955,"threshold_uncertainty_score":0.99081695},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00401137,0.0013809982,0.99119914,0.00060128694,0.0016213219,0.00033490264,0.000084757114,0.00053111924,0.00023508469],"genre_scores_gemma":[0.57339305,0.000067557965,0.42300972,0.001529299,0.00066093955,0.00012063769,0.0008620291,0.000086012624,0.00027072444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796337,0.00010409016,0.00029411344,0.0009536455,0.00014449343,0.00054030755],"domain_scores_gemma":[0.9987318,0.000084261665,0.000051812098,0.00083299924,0.00012165066,0.00017746365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029987865,0.0002633124,0.00025814437,0.0001980014,0.00016099705,0.00031772707,0.0011960428,0.00024073088,0.000030271507],"category_scores_gemma":[0.000028608469,0.00021882827,0.00014038653,0.00045497768,0.000077336634,0.00051148544,0.00042197303,0.00020397744,0.00006972239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013750334,0.00009527356,0.00002825383,0.000027837052,0.000099399585,0.00015856948,0.000117176285,0.00006926236,0.050799824,0.11046198,0.0013808041,0.8367479],"study_design_scores_gemma":[0.00041750653,0.00055181497,0.00007233661,0.000019816616,0.000016531289,0.00008594305,0.000010639803,0.8494522,0.019590706,0.05195629,0.07741966,0.00040656928],"about_ca_topic_score_codex":0.000080963124,"about_ca_topic_score_gemma":0.000004188752,"teacher_disagreement_score":0.84938294,"about_ca_system_score_codex":0.000036277735,"about_ca_system_score_gemma":0.00009874009,"threshold_uncertainty_score":0.8923558},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042100847,0.0006920575,0.9894993,0.0007008221,0.0003054445,0.0006078132,0.00013452982,0.0004380202,0.0034119645],"genre_scores_gemma":[0.08434637,0.00012698409,0.9142526,0.00015342898,0.00024032414,0.00017920234,0.00007130866,0.000048565133,0.00058123545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984345,0.000012794134,0.0003563419,0.0005572822,0.00028134228,0.00035775846],"domain_scores_gemma":[0.9986965,0.00040654864,0.000095523385,0.0006429831,0.000030184776,0.00012824479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043485413,0.0002451249,0.00032213403,0.000091008886,0.00019005919,0.0006005237,0.0007780984,0.00009578584,0.000016524551],"category_scores_gemma":[0.000023424855,0.00019030216,0.000059415135,0.00024202699,0.00010049263,0.00046530127,0.0004814113,0.00012795474,0.000069525064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031295593,0.0001861712,0.000005906486,0.0017007207,0.00014882459,0.00007814959,0.0040337467,0.000044483517,0.045760512,0.6474236,0.021976562,0.27860996],"study_design_scores_gemma":[0.00039932624,0.0001260218,0.00006740561,0.00034722005,0.000053041545,0.00006546458,0.0001229341,0.9303618,0.0035452554,0.057479713,0.006894796,0.0005370365],"about_ca_topic_score_codex":0.0000120649065,"about_ca_topic_score_gemma":0.0000018584853,"teacher_disagreement_score":0.9303173,"about_ca_system_score_codex":0.000026432208,"about_ca_system_score_gemma":0.00005661816,"threshold_uncertainty_score":0.7760297},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073267415,0.00043366896,0.9743333,0.0011485129,0.0006734901,0.00005356717,0.0000040085843,0.0006030955,0.022017714],"genre_scores_gemma":[0.7695233,0.00006901131,0.20449732,0.0012252565,0.0003765018,0.000031614858,0.000014693103,0.000026126168,0.024236161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916494,0.000019341158,0.00009099905,0.00035205795,0.00021956366,0.00015312023],"domain_scores_gemma":[0.99920297,0.00005772168,0.0000087896215,0.0006384961,0.000013954264,0.00007804343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007942508,0.000083680054,0.000063987725,0.00007014537,0.000090191475,0.0002732558,0.0005537966,0.00003726169,0.00008602922],"category_scores_gemma":[0.0000061872674,0.000054833064,0.000041287905,0.00016341457,0.000011719933,0.00047059887,0.0003437322,0.00010291634,0.0003989919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020794055,0.000049441027,0.0000019515905,0.0000111655545,0.000008494534,0.00009459562,0.00027362784,0.0002321421,0.0055252477,0.37099138,0.105136,0.5176739],"study_design_scores_gemma":[0.000058378737,0.00003949693,0.00004938016,0.00010687257,0.0000015282853,0.000011632359,0.0000051631596,0.80409855,0.005913478,0.037249226,0.15234625,0.000120031276],"about_ca_topic_score_codex":0.0000097843595,"about_ca_topic_score_gemma":4.549207e-7,"teacher_disagreement_score":0.8038664,"about_ca_system_score_codex":0.000013870776,"about_ca_system_score_gemma":0.000029021468,"threshold_uncertainty_score":0.5128367},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122672096,0.00015475038,0.8742416,0.000036931957,0.00034861531,0.00007869034,0.000010919206,0.00018105394,0.0022753451],"genre_scores_gemma":[0.9916867,0.00008757759,0.006292686,0.000030214984,0.00003243529,2.5220675e-7,0.0000069058365,0.000008681638,0.0018545312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989128,0.000041858435,0.00014445887,0.0005598858,0.00012199429,0.00021900052],"domain_scores_gemma":[0.99911636,0.00003957543,0.000056182027,0.0005988806,0.00007410866,0.000114905095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001665725,0.0001371822,0.00014092812,0.00019452741,0.00009851467,0.000097005475,0.0008349688,0.00008393469,0.00003718178],"category_scores_gemma":[0.0000051085044,0.00013053481,0.000103463295,0.000566798,0.000052779567,0.0013199048,0.00041121818,0.00015288548,0.000101000194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025390178,0.00012773878,0.00057826156,0.00007303939,0.000049485134,0.00040109613,0.00038910672,0.14531155,0.0049790065,0.8406725,0.002562039,0.004830791],"study_design_scores_gemma":[0.00018018438,0.00004354214,0.00022204893,0.000059978975,0.000019179128,0.0000073889278,0.000021304015,0.9619342,0.0015304085,0.034615625,0.0012152607,0.00015085816],"about_ca_topic_score_codex":0.00008427698,"about_ca_topic_score_gemma":0.000021729653,"teacher_disagreement_score":0.8690146,"about_ca_system_score_codex":0.000084751184,"about_ca_system_score_gemma":0.00009924563,"threshold_uncertainty_score":0.5323055},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019304374,0.0126793515,0.9650668,0.0005666261,0.00034769485,0.0003957572,0.0000041218727,0.00028572205,0.01872352],"genre_scores_gemma":[0.3927944,0.0014888209,0.6053709,0.00016284025,0.00004326655,0.00009431511,0.0000016466659,0.000011137487,0.000032705422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990234,0.000018039907,0.00029335992,0.0002629529,0.00022667265,0.00017558083],"domain_scores_gemma":[0.9985901,0.00091654167,0.000060018436,0.00039115924,0.000009208836,0.000032932992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052380183,0.00012804239,0.00020068021,0.000058859143,0.000081445956,0.0002860087,0.0005440999,0.000034909277,0.000011623813],"category_scores_gemma":[0.000037459507,0.00007221339,0.000023132856,0.00030348796,0.00024326082,0.000416982,0.0002859858,0.00014963342,0.000030421943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011924678,0.000012775826,0.000005102291,0.00018004201,0.0000033881674,0.000009940823,0.0011448904,0.00003883189,0.000025777796,0.85031796,0.00006144274,0.1481987],"study_design_scores_gemma":[0.00021746675,0.000006226566,0.000005099684,0.00017214665,0.000003961802,0.000025868425,0.00021178856,0.4910202,0.00007452382,0.5027633,0.0054110545,0.00008837847],"about_ca_topic_score_codex":0.0000033672743,"about_ca_topic_score_gemma":0.0000062232016,"teacher_disagreement_score":0.49098137,"about_ca_system_score_codex":0.000019076895,"about_ca_system_score_gemma":0.000035505727,"threshold_uncertainty_score":0.29447767},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007679224,0.0002447462,0.9768919,0.0008398648,0.00028903372,0.000121492616,0.0000023560956,0.0002701999,0.013661233],"genre_scores_gemma":[0.7831793,0.000009423346,0.21295293,0.00029887233,0.00016941193,0.000030046398,0.000018171997,0.000013314238,0.0033285737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999066,0.000029234305,0.000087980676,0.00030102234,0.00038093218,0.00013482485],"domain_scores_gemma":[0.99951744,0.000033275286,0.0000137431725,0.00034506936,0.00004625647,0.000044221273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026536066,0.00008380996,0.00006333294,0.000055986613,0.000048837013,0.00043081425,0.00030926286,0.00002634631,0.00028537912],"category_scores_gemma":[0.0000035757635,0.000050010793,0.000020159638,0.00018656728,0.000014332414,0.0009511948,0.00017382068,0.00006735683,0.00030556694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010119008,0.000048349262,0.00022584673,0.000037158396,0.000030792213,0.00005242021,0.0007092439,0.00017044295,0.0007867113,0.04007247,0.015762202,0.94209427],"study_design_scores_gemma":[0.00016022871,0.000086789136,0.0022243334,0.0000679593,0.000009957647,0.000037687456,0.000036569974,0.9689305,0.0011951842,0.003018052,0.02408707,0.00014568068],"about_ca_topic_score_codex":0.000032853444,"about_ca_topic_score_gemma":0.0000072589005,"teacher_disagreement_score":0.9687601,"about_ca_system_score_codex":0.00002299448,"about_ca_system_score_gemma":0.00006944663,"threshold_uncertainty_score":0.4154352},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004901294,0.0045098728,0.98791647,0.0005501248,0.00059000833,0.00029983537,0.0003486864,0.00045792214,0.0004257863],"genre_scores_gemma":[0.36234745,0.0007532751,0.63466805,0.00075650035,0.00019513765,0.000022777871,0.0008057158,0.000031246782,0.00041981845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988229,0.000021554773,0.00015198674,0.0006501944,0.00016039128,0.00019292804],"domain_scores_gemma":[0.99869287,0.00012178147,0.000022146784,0.0010457012,0.000031131694,0.000086380074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023969934,0.0001278237,0.00012848194,0.000114037124,0.00012854648,0.0005706185,0.0010337513,0.00004473657,0.000025544645],"category_scores_gemma":[0.000024434554,0.00008552481,0.0000348769,0.00030710408,0.000027623386,0.001002209,0.0009848399,0.00008721573,0.0000037769303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005570746,0.000010108596,0.00021908875,0.00009041051,0.000026693928,0.000015820171,0.000069008485,9.933119e-7,0.00027370892,0.6867927,0.094768524,0.2177274],"study_design_scores_gemma":[0.000356111,0.00011813355,0.0050880876,0.00010093557,0.00002374089,0.000055578992,0.000016339416,0.54921883,0.00025229334,0.28407875,0.16035159,0.00033958262],"about_ca_topic_score_codex":0.00004938532,"about_ca_topic_score_gemma":0.0000057221196,"teacher_disagreement_score":0.5492179,"about_ca_system_score_codex":0.000004254714,"about_ca_system_score_gemma":0.000028454013,"threshold_uncertainty_score":0.55024874},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045069107,0.0025528127,0.9904693,0.0010399591,0.0006243327,0.0001405167,0.000117602845,0.00018447939,0.0003641202],"genre_scores_gemma":[0.48046753,0.0001052431,0.51824456,0.0002595821,0.00016966707,0.0000104459305,0.0000875055,0.000013502419,0.00064195436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991669,0.0000090088415,0.000085930726,0.00046670958,0.00012209691,0.00014936921],"domain_scores_gemma":[0.99907047,0.000094080344,0.000011511898,0.00074513326,0.000014895827,0.00006390951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013162926,0.000084172774,0.00007501069,0.00006629335,0.000095701354,0.000427571,0.00074845133,0.000027869997,0.000019920019],"category_scores_gemma":[0.0000142849685,0.000054555603,0.000018373374,0.00011036078,0.00002830682,0.00036240768,0.0010004455,0.00004639974,0.0000060667858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002322132,0.000009850913,0.000021124753,0.00003487623,0.000012023021,0.000005822062,0.00010583719,0.000026273772,0.00043509892,0.8256995,0.043103795,0.13054349],"study_design_scores_gemma":[0.00009448083,0.000030045196,0.0005729326,0.000018057672,0.000005622785,0.000014715054,0.000018180974,0.888256,0.0007667654,0.021203639,0.088910736,0.00010879971],"about_ca_topic_score_codex":0.000038173075,"about_ca_topic_score_gemma":0.0000032459695,"teacher_disagreement_score":0.8882297,"about_ca_system_score_codex":0.000004133615,"about_ca_system_score_gemma":0.000028805862,"threshold_uncertainty_score":0.4123077},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01913398,0.0019389122,0.9662537,0.00046446468,0.008877663,0.0009688794,0.00073739013,0.0016115913,0.000013402254],"genre_scores_gemma":[0.7674927,0.00010971869,0.22958572,0.00023572573,0.0019045215,0.00047581474,0.0000068264194,0.00017725983,0.000011733175],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99558043,0.00013813241,0.0007087489,0.0019735591,0.00063496834,0.0009641388],"domain_scores_gemma":[0.99713683,0.0002813301,0.00046928503,0.0013842607,0.00042564646,0.0003026325],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00085732003,0.00076465926,0.0007098863,0.00031854576,0.0006055308,0.0023423347,0.0017676472,0.000724457,0.000011724244],"category_scores_gemma":[0.00023625858,0.000801615,0.0002666529,0.00077731383,0.00006416789,0.0010055485,0.0018044607,0.0013071278,0.000029020215],"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":[0.00006915164,0.00022070084,0.00010560764,0.00079806516,0.00024407721,0.00000872533,0.00006681177,0.000189462,0.9352064,0.052706067,0.010299504,0.00008543942],"study_design_scores_gemma":[0.0015002595,0.00018529386,0.0005750264,0.0014999899,0.00014687372,4.5494414e-8,0.0000037467983,0.09675731,0.8407416,0.0005937305,0.05604218,0.0019539844],"about_ca_topic_score_codex":0.000038202405,"about_ca_topic_score_gemma":8.6300315e-7,"teacher_disagreement_score":0.7483587,"about_ca_system_score_codex":0.00020030976,"about_ca_system_score_gemma":0.0005285488,"threshold_uncertainty_score":0.9994435},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020644034,0.000011081429,0.05858324,0.00009476909,0.0045937924,0.0006150613,0.93491125,0.00028981664,0.00089890213],"genre_scores_gemma":[0.000018862755,0.0013745043,0.019449973,0.0031955051,0.0019768218,0.00003775611,0.97321224,0.00007261342,0.000661717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99250835,0.00042124864,0.0011623817,0.0028901475,0.0017151891,0.0013026962],"domain_scores_gemma":[0.99066657,0.00027072578,0.00081201066,0.00685036,0.00022970114,0.0011706119],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00059504935,0.0012547376,0.0012531896,0.00033815906,0.0007245713,0.0016968327,0.008585858,0.00074947084,0.029939722],"category_scores_gemma":[0.0004693891,0.0012196463,0.00040797278,0.0010098857,0.00031597068,0.002728593,0.01164479,0.0017576861,0.7772611],"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":[0.00006733284,0.00026183753,0.0000047133112,0.00025934906,0.00013462041,0.0014307866,0.00011799108,0.00001821592,0.000040126833,0.0013049681,0.98790765,0.0084524],"study_design_scores_gemma":[0.0010621655,0.00027970315,0.000043567532,0.00042406667,0.00019898055,0.00012038558,0.0000503389,0.01707303,0.00003448924,0.00022515825,0.97912145,0.0013666647],"about_ca_topic_score_codex":0.0005925379,"about_ca_topic_score_gemma":0.000054596654,"teacher_disagreement_score":0.74732137,"about_ca_system_score_codex":0.00016870917,"about_ca_system_score_gemma":0.0007396562,"threshold_uncertainty_score":0.9993395},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.425809e-8,0.0000020609011,0.04096737,0.000031494914,0.0014753727,0.00017748679,0.9570048,0.00019264784,0.000148672],"genre_scores_gemma":[4.296314e-7,0.00029095664,0.017176399,0.0014731246,0.00050229515,0.000015706755,0.9804173,0.000015061979,0.0001087248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975259,0.00008873429,0.00035376314,0.001007723,0.0006190508,0.0004048876],"domain_scores_gemma":[0.9959584,0.00007195481,0.00022911456,0.0033530276,0.00005917242,0.00032835122],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001703608,0.00039691554,0.00041645343,0.000137706,0.0001765969,0.0004467388,0.004635497,0.0002572238,0.004335979],"category_scores_gemma":[0.00012377072,0.00035928295,0.00012621559,0.0003304048,0.00005656884,0.0010893779,0.004684032,0.00059010624,0.37125343],"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":[0.000006028691,0.000044276774,3.1139058e-7,0.000052035444,0.000026391062,0.00032617207,0.000011489021,0.0000022381535,0.0000062820905,0.00032542544,0.9968087,0.0023906226],"study_design_scores_gemma":[0.00026839648,0.0000538044,0.000008112702,0.00006886013,0.000030309306,0.000027034623,0.000003855156,0.0020712987,0.000016233553,0.00011049736,0.9969121,0.0004295035],"about_ca_topic_score_codex":0.00021932057,"about_ca_topic_score_gemma":0.000013298966,"teacher_disagreement_score":0.36691746,"about_ca_system_score_codex":0.000049333496,"about_ca_system_score_gemma":0.00020454111,"threshold_uncertainty_score":0.9998859},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71075094,0.0055290624,0.25330177,0.0029636018,0.020216843,0.002497228,0.0011805977,0.0034259497,0.00013400182],"genre_scores_gemma":[0.9813156,0.00016944943,0.01685739,0.000526402,0.0007463207,0.0002464538,0.0000012898328,0.00010716471,0.000029945233],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99571556,0.00018769826,0.00074515893,0.0018842837,0.00073910056,0.0007281871],"domain_scores_gemma":[0.9965783,0.00012316633,0.0003051153,0.0023054972,0.00036213687,0.00032578668],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005853999,0.0006987819,0.0006835187,0.00079694815,0.00017672432,0.00089469284,0.0017511599,0.0006162868,0.000060376617],"category_scores_gemma":[0.000080228456,0.000674624,0.00020617383,0.0010092349,0.0000932666,0.0005383666,0.00482008,0.0018935387,0.00032428806],"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":[0.00024696626,0.00377522,0.026126586,0.0030705829,0.001208686,0.0043063634,0.0003751177,0.002316081,0.8854321,0.042995974,0.029304806,0.0008415187],"study_design_scores_gemma":[0.0013825888,0.00007171135,0.5907464,0.0032257414,0.00008373635,3.681251e-7,0.0000033960914,0.32465255,0.026366957,0.00021633426,0.0506142,0.0026359893],"about_ca_topic_score_codex":0.00013696047,"about_ca_topic_score_gemma":0.000004866977,"teacher_disagreement_score":0.8590651,"about_ca_system_score_codex":0.00026979152,"about_ca_system_score_gemma":0.0006918582,"threshold_uncertainty_score":0.9995705},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021531223,0.008483145,0.9891365,0.0010044673,0.00021036381,0.00016089572,0.000015847692,0.00013140896,0.00064202695],"genre_scores_gemma":[0.115846194,0.0076142796,0.8745346,0.0002620434,0.0012970542,0.00013474216,0.000016166288,0.00004194157,0.0002529436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987844,0.00003260363,0.00041359515,0.00027159607,0.0003196982,0.00017806633],"domain_scores_gemma":[0.9990243,0.00009524761,0.00016921945,0.00039303908,0.00015618913,0.00016205676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032940521,0.00014314266,0.00020166904,0.0003229775,0.00025225684,0.00042667988,0.0007515001,0.00006520752,0.000008870595],"category_scores_gemma":[0.000006625787,0.00010354275,0.00012581561,0.00070017297,0.00007515244,0.0009956749,0.0002745465,0.00029513976,0.0000028510508],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036608465,0.0000809899,0.00006683199,0.000058939226,0.00003724749,0.000027087026,0.00014226277,0.000010358162,0.0017858997,0.077420175,0.008637824,0.91172874],"study_design_scores_gemma":[0.00025649398,0.00018025938,0.0011693359,0.0006501028,0.000045639295,0.00043905855,0.00009951044,0.04291753,0.0026961952,0.21497099,0.7362071,0.00036773144],"about_ca_topic_score_codex":0.000011394317,"about_ca_topic_score_gemma":0.00000102936,"teacher_disagreement_score":0.911361,"about_ca_system_score_codex":0.000016076332,"about_ca_system_score_gemma":0.000045722434,"threshold_uncertainty_score":0.42223507},"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":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.397327e-8,0.00004076535,0.30172208,0.00024830372,0.00025629526,0.00010394221,0.6967419,0.00015243034,0.00073426706],"genre_scores_gemma":[0.0000048314687,0.000082470535,0.044974234,0.0010614542,0.00031516782,0.000009902988,0.95341164,0.000010929824,0.0001293442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814975,0.000059220878,0.00025829533,0.0007521327,0.0004723515,0.00030826472],"domain_scores_gemma":[0.9980556,0.00009799146,0.0001864681,0.0014163636,0.000054977172,0.00018859665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013598536,0.00029776306,0.00033396936,0.000073274794,0.0001524358,0.00037842186,0.0020797981,0.0001387832,0.00014495874],"category_scores_gemma":[0.00004862111,0.0001998397,0.000050183546,0.00031195287,0.00003467828,0.00032997425,0.0013150005,0.00040274908,0.00061423384],"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":[0.0000045965385,0.00001747571,3.276566e-7,0.000032252046,0.000015307087,0.00009459368,0.000011514647,0.000006816159,6.2270726e-7,0.0009375076,0.9930632,0.0058158017],"study_design_scores_gemma":[0.00018006477,0.00013057754,0.0000060795855,0.00010363289,0.000018775732,0.000034915665,0.0000048471206,0.012723091,0.000006378182,0.00008611233,0.98638445,0.00032106935],"about_ca_topic_score_codex":0.0005867995,"about_ca_topic_score_gemma":0.000030553223,"teacher_disagreement_score":0.25674784,"about_ca_system_score_codex":0.00002819077,"about_ca_system_score_gemma":0.00015439543,"threshold_uncertainty_score":0.8149227},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040078424,0.0036305636,0.9898285,0.0011548701,0.0007274083,0.000306186,0.000078410565,0.00015736526,0.00010882383],"genre_scores_gemma":[0.10996424,0.000607304,0.88593936,0.00083100185,0.00085284613,0.000011522692,0.000080612845,0.00010266777,0.0016104683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766517,0.00032990432,0.0006197905,0.00035723153,0.00069697853,0.00033090226],"domain_scores_gemma":[0.9964478,0.0009827518,0.00037220854,0.0018155584,0.00018545976,0.00019623821],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002233233,0.00023169871,0.00043325126,0.00014132401,0.00038990992,0.0019567949,0.010995405,0.000075717406,0.00009467826],"category_scores_gemma":[0.00027856164,0.00012822488,0.00011749223,0.00050036336,0.00007135297,0.0036953164,0.0075807427,0.0005843799,0.000046651698],"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":[0.0007622076,0.00020953426,0.000070081645,0.00014445704,0.0003973376,0.00039657918,0.0035514312,0.0066694496,0.00198944,0.00026033277,0.30463398,0.6809152],"study_design_scores_gemma":[0.0032732014,0.00034727386,0.00025099536,0.0017270924,0.00020616548,0.0018782638,0.00040451024,0.5126854,0.0009966582,0.0030943286,0.4745306,0.00060547213],"about_ca_topic_score_codex":0.00007896882,"about_ca_topic_score_gemma":0.000002413362,"teacher_disagreement_score":0.6803097,"about_ca_system_score_codex":0.000052681855,"about_ca_system_score_gemma":0.00029366498,"threshold_uncertainty_score":0.9990793},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53477716,0.0020622096,0.42880616,0.0054152953,0.0013078543,0.00042959367,0.0000023360244,0.0003477135,0.02685168],"genre_scores_gemma":[0.99230945,0.0000366978,0.0065627196,0.00058355014,0.000094297946,0.000008015458,0.0000018431383,0.000006582271,0.00039684615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877965,0.00013705625,0.00026634074,0.00035274346,0.00021110877,0.0002530766],"domain_scores_gemma":[0.998853,0.00061260985,0.00003618828,0.0004626763,0.000013452577,0.000022042514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013116398,0.00010815499,0.00010930304,0.000095970805,0.00006832884,0.00080696394,0.0010745411,0.00003689008,0.000047405356],"category_scores_gemma":[0.00006571786,0.00005367203,0.00004182472,0.0005841514,0.000016414264,0.00051379023,0.00064188323,0.00038152825,0.00014560371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005713663,0.00005503874,0.002970842,0.00006401954,0.000011549637,0.00029361297,0.017492732,0.00074976083,0.00034630997,0.094629526,0.000639073,0.8827418],"study_design_scores_gemma":[0.00011285427,0.000017875343,0.010519511,0.0004242838,0.0000013474129,0.000039093695,0.0004005967,0.9376273,0.00065901317,0.0015772224,0.048487853,0.00013302121],"about_ca_topic_score_codex":0.0006044358,"about_ca_topic_score_gemma":0.00066883134,"teacher_disagreement_score":0.93687755,"about_ca_system_score_codex":0.000013160312,"about_ca_system_score_gemma":0.00002915081,"threshold_uncertainty_score":0.7781572},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008074452,0.007312149,0.98276997,0.005092362,0.002685734,0.00046072516,0.0006410585,0.00014294447,0.000087586835],"genre_scores_gemma":[0.9027198,0.0039394666,0.080344975,0.00020712308,0.0060208743,0.000323868,0.0008480338,0.0001158372,0.0054800296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964009,0.00006472928,0.00046793997,0.0008372425,0.0004222557,0.0018069426],"domain_scores_gemma":[0.99845755,0.000054904653,0.0003241037,0.0008402848,0.00021857693,0.000104566505],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012633262,0.00031825955,0.00030627334,0.00013118109,0.00044041988,0.00081034674,0.0013596308,0.00013940207,0.000008379987],"category_scores_gemma":[0.00006234823,0.0002735409,0.0002995906,0.00024195458,0.000030685333,0.0003327027,0.0014050627,0.0033130462,0.000034409117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017819739,0.00007453172,0.0000062439617,0.0000849159,0.00022047303,0.000003953877,0.0002656553,0.00022184322,0.00020886926,0.9373533,0.0044138534,0.057128534],"study_design_scores_gemma":[0.0002123868,0.00010390391,0.00012767842,0.00013743532,0.000058307734,0.0002547405,0.000017151366,0.08744974,0.00006625482,0.89753014,0.013715613,0.0003266327],"about_ca_topic_score_codex":0.000050598304,"about_ca_topic_score_gemma":0.00003564302,"teacher_disagreement_score":0.902425,"about_ca_system_score_codex":0.0013032524,"about_ca_system_score_gemma":0.0036729726,"threshold_uncertainty_score":0.9999717},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069548655,0.00007058166,0.9844244,0.00060661655,0.0021283058,0.00008907776,0.0000015056106,0.0006149065,0.0051097213],"genre_scores_gemma":[0.94251364,0.0000046044474,0.056868598,0.00036688603,0.00021281258,0.00000497487,5.865163e-7,0.000007040328,0.000020843694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978176,0.000058326623,0.00017257522,0.00082676107,0.00070279685,0.0004219698],"domain_scores_gemma":[0.99859786,0.00030204694,0.000018945953,0.00080464914,0.00006612815,0.00021036452],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008632769,0.00015536745,0.00011815639,0.0002568466,0.0003528243,0.0011314158,0.0018638464,0.000044684395,0.000040868737],"category_scores_gemma":[0.000045658133,0.000110881076,0.00005974756,0.0013171003,0.0008826753,0.00095654465,0.00088339666,0.00024179426,0.00047957213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023458522,0.000017716695,3.191588e-7,0.000003260614,0.0000011300613,0.000019488174,0.0000693192,0.000045575187,0.00065276056,0.6572398,0.00012457122,0.3418237],"study_design_scores_gemma":[0.00005640373,0.00023931554,0.000114319744,0.00004764039,0.0000015834228,0.000036960686,7.970749e-7,0.75873053,0.007588968,0.23208225,0.00096905767,0.00013218628],"about_ca_topic_score_codex":0.0000026079808,"about_ca_topic_score_gemma":4.479671e-7,"teacher_disagreement_score":0.9355588,"about_ca_system_score_codex":0.00006564339,"about_ca_system_score_gemma":0.00008364434,"threshold_uncertainty_score":0.9999055},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001035427,0.000034969173,0.9962697,0.00045937745,0.0002598702,0.0002498353,0.0000036792185,0.0011455026,0.00054162],"genre_scores_gemma":[0.17302032,0.000007040733,0.82217187,0.00019421979,0.0003540604,0.00013731471,0.00016553991,0.000030049801,0.003919577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989102,0.000047521455,0.00010538138,0.00044418778,0.00020922856,0.00028349797],"domain_scores_gemma":[0.9994928,0.00007179342,0.00006150208,0.00023730434,0.000069951835,0.000066604516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033170148,0.00013627067,0.00012443257,0.0001833666,0.0005311408,0.00021064102,0.00033643708,0.000088501445,0.000008613244],"category_scores_gemma":[0.000043122265,0.000111925285,0.000076804405,0.0010006577,0.0000099786785,0.00037621884,0.00013912385,0.00023272663,0.00002183515],"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":[0.00008337126,0.00013567011,0.0015752658,0.00017150215,0.00003849608,0.0000053966583,0.0002663631,0.55347985,0.0043591624,0.004499474,0.009779116,0.4256063],"study_design_scores_gemma":[0.00040390922,0.000114101575,0.000600529,0.000012806897,0.0000041495446,0.000011259541,0.00001522252,0.973525,0.0024893493,0.00007147752,0.022600193,0.00015199337],"about_ca_topic_score_codex":0.000056419623,"about_ca_topic_score_gemma":0.00002476941,"teacher_disagreement_score":0.42545432,"about_ca_system_score_codex":0.000037045385,"about_ca_system_score_gemma":0.00003506607,"threshold_uncertainty_score":0.45641807},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07488401,0.0007000982,0.91906005,0.0039163395,0.0010848542,0.00016808139,0.0000037586094,0.00017333252,0.00000949832],"genre_scores_gemma":[0.65401745,0.000010681876,0.34535727,0.0004119967,0.00018394916,0.0000061455767,0.000001150908,0.000006677411,0.000004691771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976283,0.000032800617,0.00017204718,0.0011228104,0.0005365245,0.0005075718],"domain_scores_gemma":[0.9987753,0.0002614124,0.00001977099,0.0006833866,0.000059260998,0.00020087694],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005087477,0.00022805596,0.00019987802,0.00039953558,0.00021250693,0.002700519,0.0015559862,0.00007197723,0.0000034610784],"category_scores_gemma":[0.00006003302,0.00017497668,0.000036482816,0.0016625251,0.0002034346,0.001630599,0.0016733028,0.0002596018,0.000011328662],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021854014,0.000017123404,0.0014104779,0.00002690767,0.00000283799,0.0001319209,0.00092391175,0.0025802786,0.0017864718,0.00044581172,0.00006263482,0.99260944],"study_design_scores_gemma":[0.000070069094,0.00014172931,0.026982982,0.0002359415,0.0000026126893,0.00016596388,0.00000160971,0.9565374,0.008040637,0.006819048,0.00065596146,0.00034599184],"about_ca_topic_score_codex":0.000036322646,"about_ca_topic_score_gemma":0.000034643283,"teacher_disagreement_score":0.99226344,"about_ca_system_score_codex":0.000063850144,"about_ca_system_score_gemma":0.00013642009,"threshold_uncertainty_score":0.99833477},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17526361,0.0011189042,0.8232915,0.000032047734,0.00007502137,0.000107718595,0.0000019191043,0.00009417716,0.000015092664],"genre_scores_gemma":[0.47954887,0.00017381845,0.5202308,0.000003067258,0.000015523165,0.0000064839005,0.0000015907964,0.000014423278,0.000005404716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990322,0.000021047634,0.0003281505,0.00029331617,0.00014224727,0.00018305094],"domain_scores_gemma":[0.99942434,0.00022670323,0.00003419343,0.00021734182,0.000020605798,0.00007679775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041008226,0.00014430941,0.00024504546,0.00017717887,0.000019658475,0.00012567997,0.00011041098,0.00007923656,0.0000012407705],"category_scores_gemma":[0.000026122641,0.00011943407,0.000029163919,0.00025406884,0.000017885974,0.00027999026,0.00011516742,0.00017509153,7.8841043e-7],"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":[0.0000106530015,0.00020189749,0.000008254812,0.0031541025,0.000044846285,0.000023750925,0.003851131,0.58980083,0.29434636,0.082044594,0.0000059787358,0.026507592],"study_design_scores_gemma":[0.00013762305,0.00003458089,0.0000048500538,0.0008461516,0.000011684984,0.000032242544,0.000012055232,0.9745218,0.0037538335,0.020421958,0.000092247814,0.00013096696],"about_ca_topic_score_codex":0.000052718875,"about_ca_topic_score_gemma":3.1228674e-7,"teacher_disagreement_score":0.38472095,"about_ca_system_score_codex":0.000022418224,"about_ca_system_score_gemma":0.000010954767,"threshold_uncertainty_score":0.48703802},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02278771,0.00011643334,0.97197956,0.0007837436,0.00410703,0.000042975666,0.0000071108525,0.00002797551,0.0001474596],"genre_scores_gemma":[0.7562137,0.000037899852,0.24356207,0.000018536952,0.00015503443,5.4269793e-7,0.0000028029674,0.0000021905084,0.0000071898003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788004,0.00003333685,0.00063818897,0.00018204963,0.001170544,0.00009586766],"domain_scores_gemma":[0.99753845,0.00016317706,0.000477457,0.00024327618,0.0015225746,0.000055069944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007856324,0.00007657374,0.00013993324,0.00077614334,0.00006416417,0.0003868375,0.0020088272,0.000023336199,0.000025358237],"category_scores_gemma":[0.000105617786,0.00006158586,0.00008640621,0.0008033937,0.0002406431,0.003667485,0.00027435002,0.00009025944,0.000004918022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007550743,0.0002022466,0.00081693067,0.000071134935,0.000111649824,0.000039509403,0.0016450685,0.007505513,0.030846648,0.3353862,0.0005142347,0.62285334],"study_design_scores_gemma":[0.00020663759,0.00025541813,0.008626707,0.00082267233,0.0000111970085,0.00028191003,0.000018632583,0.9345309,0.01965296,0.033461884,0.0020065627,0.00012450965],"about_ca_topic_score_codex":0.000013330043,"about_ca_topic_score_gemma":6.6393085e-7,"teacher_disagreement_score":0.9270254,"about_ca_system_score_codex":0.00008728619,"about_ca_system_score_gemma":0.00062738586,"threshold_uncertainty_score":0.3732934},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029209783,0.09794,0.89308184,0.0005406615,0.0020243104,0.00084970595,0.000067391724,0.00007663921,0.0051273303],"genre_scores_gemma":[0.98726434,0.002868064,0.0031207937,0.0005754221,0.004371339,0.00004822532,0.000414869,0.00009753398,0.0012393914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830806,0.000051384024,0.00033598853,0.0007661394,0.00027489068,0.00026351665],"domain_scores_gemma":[0.9981502,0.00051389815,0.00013659472,0.0011300354,0.000020735553,0.000048485188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006414066,0.0003144497,0.00038647343,0.00006220497,0.000105017236,0.00071543106,0.0010056236,0.00029563165,5.8593474e-7],"category_scores_gemma":[0.000013841,0.00017219715,0.000019447063,0.00012901532,0.000077520315,0.0001639173,0.00090449926,0.0010482046,0.0000011300808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003918023,0.000027721479,0.0024250299,0.0009853321,0.00012075461,0.0012524952,0.0028392135,0.081711486,0.0000018260646,0.13286348,0.00163568,0.77609783],"study_design_scores_gemma":[0.00016902525,0.00007589593,0.00009115692,0.004764712,0.000017845534,0.0002549699,0.000013709142,0.9522918,8.6896144e-8,0.010936375,0.031072605,0.000311834],"about_ca_topic_score_codex":0.0004167125,"about_ca_topic_score_gemma":0.0014234184,"teacher_disagreement_score":0.9869723,"about_ca_system_score_codex":0.000018930714,"about_ca_system_score_gemma":0.000029370827,"threshold_uncertainty_score":0.7021996},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041680588,0.0006859409,0.98738784,0.0009145092,0.0014116843,0.00011175323,0.0000144802825,0.0008365721,0.008220415],"genre_scores_gemma":[0.28015587,0.00013528901,0.70674086,0.00067747745,0.000606896,0.000032733173,0.00008916199,0.000033655717,0.011528084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986619,0.000039639755,0.00020307688,0.0004987942,0.00036279578,0.00023381294],"domain_scores_gemma":[0.9991665,0.00009750988,0.000030749874,0.00054771116,0.000051865158,0.00010568028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019853826,0.00014609887,0.00011679221,0.00015309478,0.00014239037,0.0005537024,0.00068996823,0.0000723189,0.00023426859],"category_scores_gemma":[0.000012016766,0.00010296404,0.00005997718,0.00046017757,0.000023844968,0.0012794312,0.0005212176,0.00014983742,0.00072654494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018736943,0.000049617196,0.000016316493,0.00002563578,0.000011448141,0.000038665745,0.0001785445,0.0000838827,0.003722972,0.08895706,0.08793359,0.8189804],"study_design_scores_gemma":[0.00011560437,0.000036111676,0.0007738516,0.00010069731,0.0000031367276,0.000025917883,0.000011988583,0.84877574,0.004222471,0.0036965064,0.14205757,0.00018038166],"about_ca_topic_score_codex":0.000063889725,"about_ca_topic_score_gemma":0.0000025907298,"teacher_disagreement_score":0.8486919,"about_ca_system_score_codex":0.000031865467,"about_ca_system_score_gemma":0.000058592625,"threshold_uncertainty_score":0.93385077},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7531277,0.009441759,0.04335983,0.018805075,0.010622019,0.003834727,0.00008446526,0.0028838352,0.15784056],"genre_scores_gemma":[0.99172914,0.00005895807,0.0063862004,0.00023330362,0.0001313065,0.000040506824,9.954006e-7,0.0000160945,0.0014034695],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987078,0.0000060818456,0.00020677228,0.00036796715,0.0004707212,0.00024070489],"domain_scores_gemma":[0.99950534,0.000046573394,0.000084805935,0.00023222492,0.000067882764,0.00006318471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002934986,0.0001441901,0.0001411505,0.00009534238,0.00013485811,0.00025414556,0.0011042678,0.00004329538,0.000017251055],"category_scores_gemma":[0.00003156433,0.000086584034,0.00008906222,0.00047731178,0.000044452405,0.0005557118,0.00077405176,0.00017929143,0.000036529895],"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":[0.00008827711,0.00056526106,0.0015591816,0.00092710176,0.00023388746,0.000019681056,0.0043554245,0.0002596446,0.098294385,0.35110572,0.08430947,0.45828196],"study_design_scores_gemma":[0.0012188752,0.00036257817,0.0021892688,0.0033726944,0.00006271085,0.00006188518,0.00024580272,0.21362773,0.6969268,0.027336173,0.053905945,0.0006895848],"about_ca_topic_score_codex":0.000040612733,"about_ca_topic_score_gemma":5.117496e-7,"teacher_disagreement_score":0.5986324,"about_ca_system_score_codex":0.0000731481,"about_ca_system_score_gemma":0.000029562127,"threshold_uncertainty_score":0.35307944},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065187213,0.0005447164,0.9929111,0.0022863587,0.0022315802,0.00033199412,0.00011358706,0.000667288,0.00026151974],"genre_scores_gemma":[0.15972097,0.00014327213,0.8364787,0.00038081722,0.00046467705,0.00033517872,0.000033338096,0.00006141005,0.002381604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982151,0.000039503164,0.00027437686,0.0007306785,0.0003294903,0.0004108915],"domain_scores_gemma":[0.9983145,0.000417926,0.00003308113,0.0010227755,0.00006241529,0.00014929555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000295415,0.00024642964,0.00020710111,0.0002599991,0.00050819287,0.0007574212,0.0011364466,0.00012085653,0.000077565826],"category_scores_gemma":[0.000021659274,0.00021232353,0.00022531005,0.00048956857,0.00005005726,0.0011565094,0.00003836103,0.00032607012,0.00015098609],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016881862,0.00013703456,0.0000010321381,0.00004567843,0.00006840654,0.000028832514,0.00049168937,0.00044402143,0.0008617094,0.0027322373,0.002194293,0.99297816],"study_design_scores_gemma":[0.00049544114,0.0004343038,0.00008670036,0.00013675516,0.000040898176,0.000067699744,0.00003903545,0.83947396,0.006944994,0.0054205507,0.14645089,0.00040875934],"about_ca_topic_score_codex":0.00004256565,"about_ca_topic_score_gemma":0.0000054540155,"teacher_disagreement_score":0.99256945,"about_ca_system_score_codex":0.0000870143,"about_ca_system_score_gemma":0.000113615766,"threshold_uncertainty_score":0.8658302},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012486067,0.0060033123,0.97633344,0.0020177488,0.008745578,0.0007025346,0.0009430134,0.0003591175,0.0036466746],"genre_scores_gemma":[0.39089876,0.0047046538,0.581133,0.0005061383,0.0026155787,0.00075352896,0.0021609436,0.00008378852,0.017143581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980634,0.000074286756,0.00075259805,0.00032162535,0.00032312155,0.00046496693],"domain_scores_gemma":[0.99848306,0.00022337787,0.00023338824,0.0004186277,0.00049420365,0.00014734027],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00056310004,0.0002701216,0.00023035862,0.00023626158,0.00072897103,0.002838505,0.00047668067,0.00021135304,0.000107391155],"category_scores_gemma":[0.00028994956,0.00026489334,0.000121545905,0.00085524895,0.00025930553,0.01600972,0.00018291263,0.00019342736,0.00030070677],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002582318,0.000050533643,0.000009600023,0.0019524433,0.00009691007,0.000008588609,0.01722027,0.03074104,0.00017878455,0.14897327,0.021090792,0.77965194],"study_design_scores_gemma":[0.00019652817,0.0001649601,0.00002704766,0.0013059457,0.000054002045,0.00022880684,0.00072559423,0.73350126,0.00049112504,0.011270083,0.2517341,0.0003005258],"about_ca_topic_score_codex":0.00055595336,"about_ca_topic_score_gemma":0.00003410133,"teacher_disagreement_score":0.7793514,"about_ca_system_score_codex":0.0004385657,"about_ca_system_score_gemma":0.0005517728,"threshold_uncertainty_score":0.99998033},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010079062,0.0011055011,0.9843597,0.0017749757,0.0047723604,0.000298717,0.000014492649,0.00053463416,0.0061317533],"genre_scores_gemma":[0.35697708,0.00041273286,0.6198299,0.0016008563,0.004005619,0.00031692692,0.0006657955,0.00007706118,0.016114052],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983501,0.00008446567,0.0002925001,0.00077280373,0.00031611472,0.00018402259],"domain_scores_gemma":[0.99860233,0.00004783836,0.00007180868,0.0011114922,0.00008584378,0.00008070055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037999725,0.00023648242,0.0002727444,0.0001306512,0.0000654489,0.0007989382,0.001087444,0.00022363427,0.00015121524],"category_scores_gemma":[0.00002546896,0.00017021073,0.00014453393,0.00013493169,0.000017385695,0.00017783463,0.005154011,0.00060921436,0.00042632452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038041948,0.00014119032,0.000009648578,0.00036315617,0.00016098496,0.00012208367,0.0018622495,0.0029544448,0.0073039634,0.08068586,0.52929014,0.37706825],"study_design_scores_gemma":[0.00044571474,0.000012096425,0.000011320488,0.00009501999,0.000016525315,0.0000056056588,0.0000052618484,0.9625204,0.002676832,0.024509396,0.009423556,0.00027824217],"about_ca_topic_score_codex":0.00012812312,"about_ca_topic_score_gemma":0.000017761671,"teacher_disagreement_score":0.959566,"about_ca_system_score_codex":0.00004849175,"about_ca_system_score_gemma":0.00014701493,"threshold_uncertainty_score":0.7704179},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028134168,0.000051290383,0.99052924,0.00015265499,0.0031884122,0.000100887075,0.000078085286,0.0006079327,0.002478111],"genre_scores_gemma":[0.9748416,0.00006488333,0.024189794,0.00040652274,0.00009732158,0.00004401912,0.000027778055,0.000009471434,0.00031860225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919057,0.000043364544,0.00026562286,0.00016206193,0.000206718,0.00013165451],"domain_scores_gemma":[0.9993282,0.00016105585,0.000046527482,0.00035686162,0.00004545509,0.00006193183],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022483927,0.00011303862,0.00008054688,0.0002617505,0.00018863319,0.00042953165,0.00027893626,0.00007531786,0.00025014003],"category_scores_gemma":[0.0000032235246,0.00009872072,0.000073750285,0.0003208255,0.000032315544,0.0051557883,0.0000030972749,0.00022549022,0.0012101197],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014239493,0.000011285951,3.624108e-7,0.000010150604,0.000020247167,0.0000011939655,0.00083192944,0.0012958365,0.00011890187,0.027444448,0.00035093533,0.9699005],"study_design_scores_gemma":[0.000699064,0.00016145509,0.00014403889,0.00037804066,0.000041960364,0.00011364362,0.00044305588,0.783376,0.056764692,0.098761104,0.05849309,0.0006238665],"about_ca_topic_score_codex":0.000030162892,"about_ca_topic_score_gemma":0.0000013937804,"teacher_disagreement_score":0.9720282,"about_ca_system_score_codex":0.00005926511,"about_ca_system_score_gemma":0.00005067696,"threshold_uncertainty_score":0.99956757},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002909747,0.00064230023,0.99259466,0.0010758425,0.002695433,0.00030918073,0.000081792845,0.00010058552,0.002209256],"genre_scores_gemma":[0.1431465,0.00009575091,0.85253453,0.0014386617,0.0005913928,0.000009974789,0.000012006006,0.00007227131,0.002098921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639076,0.00003459701,0.0005563023,0.0012803642,0.0012384496,0.0004994983],"domain_scores_gemma":[0.9970958,0.0002618385,0.00029320616,0.002027812,0.00020093488,0.00012038522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006469399,0.00043477776,0.000481561,0.0004071723,0.00022241162,0.00039132748,0.005269292,0.00016643025,0.000029875204],"category_scores_gemma":[0.000037841703,0.00028753822,0.00019766526,0.0007090955,0.0015938568,0.00046145378,0.004992608,0.00080971676,0.000036837584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012945435,0.000064551205,0.000056574972,0.00020658155,0.0000367982,0.000099330755,0.0015202609,0.00828831,0.00044662337,0.13098606,0.00031339237,0.85796857],"study_design_scores_gemma":[0.00012057055,0.000097507334,0.0003481011,0.00062296673,0.000009057397,0.000031756088,1.3329353e-7,0.54382443,0.002633459,0.44784147,0.004082453,0.00038807755],"about_ca_topic_score_codex":0.000074137046,"about_ca_topic_score_gemma":0.00008501911,"teacher_disagreement_score":0.8575805,"about_ca_system_score_codex":0.0001603,"about_ca_system_score_gemma":0.00051328907,"threshold_uncertainty_score":0.9999577},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01587222,0.00017202429,0.9832243,0.000055559314,0.00032199966,0.00018741946,0.000008669167,0.00012475277,0.000033094493],"genre_scores_gemma":[0.14741966,0.0000054053967,0.852353,0.000040455103,0.00013351304,0.000013393135,0.000015316818,0.000009597765,0.000009671502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910265,0.00002287378,0.00025379253,0.00030399513,0.0001545336,0.0001621472],"domain_scores_gemma":[0.99927676,0.0003616819,0.00003334353,0.00023223073,0.000044080243,0.000051934552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035597864,0.00011721828,0.00015297763,0.00011353302,0.0000967046,0.00064140634,0.00022097009,0.000051916333,0.0000012479529],"category_scores_gemma":[0.000010330091,0.000102089856,0.000036241217,0.00014045266,0.000019346391,0.0005419642,0.00012041131,0.00006852811,0.0000013688646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011048785,0.0000540699,0.000008235681,0.00012015269,0.000012723756,0.000008345901,0.0021855405,0.2563619,0.00011710146,0.0946668,0.000051012066,0.646413],"study_design_scores_gemma":[0.00015178615,0.000085177846,0.000030325538,0.0001293496,0.0000049334126,0.000006728223,0.00005605089,0.9842475,0.000034423385,0.014813167,0.00030864042,0.00013189511],"about_ca_topic_score_codex":0.000004919082,"about_ca_topic_score_gemma":4.695705e-7,"teacher_disagreement_score":0.7278856,"about_ca_system_score_codex":0.000023480783,"about_ca_system_score_gemma":0.000022345985,"threshold_uncertainty_score":0.61850965},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015523443,0.040372603,0.95305365,0.0030335314,0.0001786268,0.00038895116,0.0000019935483,0.000119353055,0.0012989676],"genre_scores_gemma":[0.98363596,0.009192402,0.0054016914,0.0011812423,0.00041521975,0.00006911443,0.000016874143,0.000011011974,0.000076468095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904734,0.00012890411,0.00014019602,0.00029901252,0.00024076685,0.00014380431],"domain_scores_gemma":[0.9993263,0.00018747221,0.000046391822,0.0003484524,0.000038897404,0.00005250013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002545176,0.00011767407,0.00020683715,0.00001149082,0.00013624791,0.00025134836,0.0002742357,0.000015422787,0.0000027929696],"category_scores_gemma":[0.000010477173,0.000055611872,0.000043689666,0.00021520095,0.000074899646,0.00086970674,0.00015886354,0.00014765105,0.000021956295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027061267,0.000037874022,0.000002557763,0.00035568795,0.000018214618,0.000006212028,0.0003043193,0.00078075635,0.00031207895,0.78405434,0.018749395,0.19535151],"study_design_scores_gemma":[0.00018353284,0.00004014097,0.000038461883,0.0017363239,0.00002723936,0.000007986923,0.0000023026166,0.8983674,0.00004321075,0.08763863,0.011824884,0.00008985258],"about_ca_topic_score_codex":0.000010477538,"about_ca_topic_score_gemma":6.7743576e-7,"teacher_disagreement_score":0.9820836,"about_ca_system_score_codex":0.000009748921,"about_ca_system_score_gemma":0.000022434502,"threshold_uncertainty_score":0.2423758},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010901577,0.001941226,0.92532074,0.0012202162,0.00542674,0.00025179415,0.00017330748,0.00032368398,0.05444069],"genre_scores_gemma":[0.18333463,0.0002183389,0.8008016,0.0003364557,0.0004959723,0.000035909252,0.00009374869,0.000039727835,0.01464366],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986184,0.000036294517,0.0003086229,0.00059238565,0.00023460711,0.0002096875],"domain_scores_gemma":[0.9985394,0.000056577697,0.000097034994,0.0011399126,0.000088831606,0.00007824448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020880105,0.0001797069,0.00025635347,0.00016477935,0.00006898641,0.00022737705,0.0010998227,0.00016910885,0.00058169174],"category_scores_gemma":[0.000010157035,0.00014091394,0.00014317373,0.00014209791,0.000031583408,0.0001438803,0.0069782203,0.0005030177,0.00012374653],"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":[0.000008543048,0.00029070282,0.00016026098,0.0016913695,0.00026023813,0.00008635449,0.0047259857,0.0007146169,0.0024466421,0.1240142,0.4557483,0.40985277],"study_design_scores_gemma":[0.0002166819,0.00010172868,0.0007853181,0.0014321574,0.000055856504,0.000043737582,0.00014415041,0.5574488,0.005673323,0.21002914,0.22308365,0.0009854801],"about_ca_topic_score_codex":0.00025182732,"about_ca_topic_score_gemma":0.00006710261,"teacher_disagreement_score":0.55673414,"about_ca_system_score_codex":0.00003427717,"about_ca_system_score_gemma":0.00019731562,"threshold_uncertainty_score":0.86978525},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012443826,0.0076104566,0.9502436,0.008190907,0.0031432996,0.0012377278,0.00029216497,0.0009948603,0.027042633],"genre_scores_gemma":[0.9615313,0.00141807,0.031347994,0.00021595224,0.0011858211,0.00019996635,0.00019112385,0.00010583958,0.0038039559],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99512583,0.00037748477,0.00031442632,0.001321103,0.0020992022,0.0007619529],"domain_scores_gemma":[0.9969327,0.00033394125,0.00006791791,0.00211122,0.0002660746,0.00028817],"candidate_categories":["scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001484722,0.0002916372,0.00031207205,0.0007135938,0.00047606017,0.0018231493,0.002726978,0.0003865024,0.00015841966],"category_scores_gemma":[0.00006535796,0.00023496238,0.00018001703,0.00075646077,0.00012341354,0.00025084353,0.025567979,0.0031056989,0.00075415807],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021417698,0.0001790264,0.00013673196,0.0030433922,0.000097275966,0.00052815623,0.0027645738,0.00036012215,0.0004135331,0.25233018,0.71003616,0.0300894],"study_design_scores_gemma":[0.00017191152,0.00009521538,0.00016366268,0.004600138,0.0000063318817,0.00001083835,0.00020984614,0.438865,0.00070330384,0.51498264,0.039767522,0.00042358146],"about_ca_topic_score_codex":0.000164564,"about_ca_topic_score_gemma":0.000005083391,"teacher_disagreement_score":0.9602869,"about_ca_system_score_codex":0.00058420777,"about_ca_system_score_gemma":0.0005146385,"threshold_uncertainty_score":0.99921304},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16784339,0.00006351312,0.82483894,0.0007903174,0.0061053224,0.00014311475,0.00013722235,0.000047301568,0.000030874304],"genre_scores_gemma":[0.82388914,0.00001788292,0.175548,0.00014448196,0.00032800314,0.000002262013,0.000042113308,0.000006101169,0.000021997983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980227,0.00001676664,0.00034658308,0.0005250669,0.000830217,0.0002587138],"domain_scores_gemma":[0.9990532,0.000055473305,0.00008518447,0.00047740526,0.00022114096,0.00010761367],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016414232,0.00009470329,0.00008423843,0.0006328901,0.00027090442,0.0016730628,0.003527741,0.000028355505,0.0000052482765],"category_scores_gemma":[0.00025530628,0.00008369382,0.000026774915,0.00069444627,0.000030391664,0.009709829,0.0013934935,0.00019347126,0.0000065926274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005882229,0.0001086567,0.031002404,0.000041656083,0.000028398952,0.00008430884,0.0005233824,0.0375398,0.024446107,0.055317473,0.0010622322,0.84978676],"study_design_scores_gemma":[0.00012667873,0.000027263288,0.02671529,0.00015700534,0.0000019060398,0.00008231551,0.0000076219108,0.9625881,0.00044856462,0.0014633889,0.008268547,0.000113362476],"about_ca_topic_score_codex":0.0001435648,"about_ca_topic_score_gemma":0.000021647733,"teacher_disagreement_score":0.92504823,"about_ca_system_score_codex":0.0002962203,"about_ca_system_score_gemma":0.00024503184,"threshold_uncertainty_score":0.9993633},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006754923,0.0026101535,0.9868971,0.0010882271,0.0013265501,0.00012794595,0.0000079534375,0.00024275664,0.000944401],"genre_scores_gemma":[0.75778234,0.000047502646,0.2413968,0.00032292373,0.00019367556,0.000021339123,0.0000014494706,0.000011176792,0.00022276984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814224,0.00003698847,0.00017802812,0.000687864,0.0005550766,0.00039977106],"domain_scores_gemma":[0.9988407,0.000082105995,0.000044074102,0.00086048606,0.00003631767,0.0001363217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004318116,0.00013596016,0.000110701796,0.00013947305,0.00024938647,0.00064004475,0.0019668697,0.00004244601,0.000014396917],"category_scores_gemma":[0.0000367055,0.00010947141,0.000047178102,0.00078846834,0.000096721276,0.0014017492,0.0013394806,0.00013322085,0.000064037216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034271882,0.000055899753,0.000120050085,0.00003687206,0.00001218998,0.0001711582,0.0021805505,0.00051630125,0.028985526,0.09869143,0.005596186,0.8636304],"study_design_scores_gemma":[0.00022162737,0.00016155743,0.0019764712,0.0004737081,0.000009445538,0.00015343417,0.000053639844,0.7312619,0.0095708035,0.13847728,0.11709442,0.000545698],"about_ca_topic_score_codex":0.000059105885,"about_ca_topic_score_gemma":0.0000028304273,"teacher_disagreement_score":0.86308473,"about_ca_system_score_codex":0.00010980211,"about_ca_system_score_gemma":0.00010005574,"threshold_uncertainty_score":0.6171966},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014431606,0.002827048,0.99143934,0.0005482925,0.0020501015,0.00023917107,0.000009730548,0.00026540592,0.002476563],"genre_scores_gemma":[0.06824328,0.000246367,0.9283243,0.0010386311,0.0008591869,0.000007517678,0.000005096165,0.000062310035,0.0012133428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962178,0.000016402813,0.0004603601,0.0019320202,0.0007845022,0.00058890047],"domain_scores_gemma":[0.99757844,0.0007504656,0.0001575969,0.001157281,0.00014790331,0.00020831253],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007250054,0.00051505334,0.0004897328,0.0007038123,0.00026812215,0.0011940196,0.0023681144,0.00028687276,0.000012088114],"category_scores_gemma":[0.00011155654,0.00043334631,0.000095235984,0.00044618302,0.00044276804,0.00069739646,0.002953047,0.0009179829,0.00003756649],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027651527,0.000007211494,0.00000516912,0.000057603604,0.000009148722,0.00043002548,0.00036629522,0.0063694497,0.00027603682,0.023185963,0.000017836763,0.9692725],"study_design_scores_gemma":[0.00010070618,0.0000917857,0.00000627851,0.00095092074,0.000008091059,0.0002971107,1.4435774e-7,0.8125879,0.00036198943,0.18059477,0.004525531,0.00047474622],"about_ca_topic_score_codex":0.000030406794,"about_ca_topic_score_gemma":0.000048464983,"teacher_disagreement_score":0.96879774,"about_ca_system_score_codex":0.00019934254,"about_ca_system_score_gemma":0.00028479044,"threshold_uncertainty_score":0.9998428},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028292145,0.0009268984,0.99014604,0.0003816714,0.002040609,0.00023667881,0.000021976091,0.00013111084,0.0060866927],"genre_scores_gemma":[0.12215507,0.00008496489,0.87215626,0.0013629065,0.0009824334,0.000012099274,0.000017327102,0.00009917952,0.0031297633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672246,0.000015011491,0.0005073663,0.0013472652,0.0009629947,0.00044487286],"domain_scores_gemma":[0.9975949,0.0002475777,0.00022442735,0.0016655519,0.00016130236,0.000106252],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005256254,0.0004400934,0.0004996706,0.00074960873,0.000103392835,0.00034474625,0.0034843334,0.00028054792,0.00003262003],"category_scores_gemma":[0.000030181141,0.00035077028,0.00014502076,0.0005530292,0.00053213467,0.00056399725,0.0024845726,0.0006222928,0.00008730613],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050134045,0.000029214889,0.00002113594,0.00009827257,0.000015927028,0.00014571278,0.00032559776,0.0044358126,0.0002423351,0.1537329,0.00020320913,0.84074485],"study_design_scores_gemma":[0.00014944772,0.00015389656,0.00009413289,0.0008071594,0.000007211399,0.000054400818,4.9299423e-8,0.59334004,0.0022999484,0.39576483,0.006854495,0.0004743873],"about_ca_topic_score_codex":0.000029708317,"about_ca_topic_score_gemma":0.00005718233,"teacher_disagreement_score":0.8402705,"about_ca_system_score_codex":0.000121630714,"about_ca_system_score_gemma":0.0003552958,"threshold_uncertainty_score":0.99989444},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012678246,0.00038875834,0.9899959,0.0004755301,0.00035021044,0.00003556766,0.000012108698,0.00022217295,0.0072519006],"genre_scores_gemma":[0.94480264,0.00003475056,0.054551907,0.000018444907,0.000036659527,0.0000026032872,0.000015799711,0.000002855829,0.0005343226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943507,0.00001833617,0.00012237497,0.00018576709,0.00013908566,0.000099389],"domain_scores_gemma":[0.99955505,0.00007398671,0.00001710367,0.00028796104,0.000025869382,0.000040013452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010054476,0.000051621148,0.00006934879,0.000050379535,0.00006391433,0.0000977765,0.0003678651,0.000025068604,0.000075517455],"category_scores_gemma":[0.0000120885525,0.00003617155,0.000037889346,0.00025180695,0.000019926701,0.0004258753,0.0003375191,0.0000698627,0.000045626686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012852747,0.000038011083,0.00005576694,0.000034227734,0.000008402953,0.000012059557,0.00013424321,0.000049101054,0.021253983,0.7912698,0.013747602,0.17339553],"study_design_scores_gemma":[0.000103351194,0.00004345807,0.00065135024,0.00021461182,0.0000044731987,0.000013887266,0.000018935962,0.8577369,0.03822634,0.014292442,0.088562,0.0001322558],"about_ca_topic_score_codex":0.000025429083,"about_ca_topic_score_gemma":5.681507e-7,"teacher_disagreement_score":0.94353485,"about_ca_system_score_codex":0.000010608888,"about_ca_system_score_gemma":0.000028529375,"threshold_uncertainty_score":0.1475033},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52957624,0.00018133143,0.4692279,0.00021007072,0.00020629438,0.00004743804,0.000013721869,0.00003683368,0.00050016644],"genre_scores_gemma":[0.98628855,0.00002050037,0.013563968,0.000013323148,0.00001308158,0.0000032350115,0.0000047644903,0.0000031626068,0.00008938793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908864,0.00004480154,0.000264698,0.00024769947,0.0002249447,0.00012918966],"domain_scores_gemma":[0.99953747,0.00006185591,0.00005060131,0.00029908662,0.000026384603,0.000024602363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023344421,0.00007774713,0.0001407056,0.00013265767,0.00001606363,0.000077569304,0.00040214398,0.00003770785,0.00001779904],"category_scores_gemma":[0.000014032048,0.000057363613,0.00004879239,0.00030967838,0.000031596777,0.0012324136,0.0003369591,0.00006884166,0.0000030510878],"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":[0.000021300282,0.0004458822,0.18434945,0.0013229382,0.0001003531,0.00016154471,0.004333865,0.0007162018,0.25935087,0.35376894,0.0016704747,0.19375817],"study_design_scores_gemma":[0.00027746006,0.00017087915,0.40155214,0.0018504206,0.0000079159045,0.00001785455,0.00038314387,0.49596468,0.074053355,0.025075678,0.00030632844,0.00034016892],"about_ca_topic_score_codex":0.0016356691,"about_ca_topic_score_gemma":0.00024665182,"teacher_disagreement_score":0.49524847,"about_ca_system_score_codex":0.00003597457,"about_ca_system_score_gemma":0.0001221324,"threshold_uncertainty_score":0.24726534},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006706633,0.0001481095,0.98233587,0.00025480601,0.00022327612,0.00013683812,0.000008119043,0.000450552,0.015771782],"genre_scores_gemma":[0.26681817,0.000031411528,0.7325677,0.000119313765,0.00011374873,0.000038411028,0.00003190751,0.00001692816,0.0002623526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915695,0.0000045960805,0.00017410476,0.00026889358,0.0002377165,0.00015774553],"domain_scores_gemma":[0.99932903,0.00007240571,0.000033338372,0.00049764337,0.000015818587,0.000051753617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013878799,0.00011196182,0.00010279034,0.000051614836,0.000076005825,0.00041964772,0.00048225382,0.00004403112,0.00001933245],"category_scores_gemma":[0.0000081922735,0.00008286443,0.000035094825,0.00024332717,0.00002360938,0.00040197064,0.00022095603,0.000108050364,0.00031913642],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6855505e-7,0.000009417748,1.3762588e-7,0.00008076449,0.0000061837195,0.000008758184,0.0008554897,0.000017700913,0.010108155,0.95407003,0.0016083742,0.033234626],"study_design_scores_gemma":[0.000064572465,0.000013915389,0.000007850398,0.00010622117,0.000008954241,0.000024904626,0.000092297225,0.7718403,0.005612133,0.20826566,0.0137482835,0.00021491478],"about_ca_topic_score_codex":0.0000021384656,"about_ca_topic_score_gemma":4.4328254e-7,"teacher_disagreement_score":0.7718226,"about_ca_system_score_codex":0.000022585293,"about_ca_system_score_gemma":0.00003419318,"threshold_uncertainty_score":0.41019595},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013612649,0.0022837266,0.076532036,0.00005030546,0.0008093623,0.00055998814,0.000353248,0.0006142793,0.9187834],"genre_scores_gemma":[0.00011675239,0.00038353636,0.012787357,0.00004387969,0.00011550114,0.0000015742492,0.00010266562,0.000050554525,0.98639816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779946,0.00002912011,0.00022614679,0.0011277378,0.00040611383,0.00041141582],"domain_scores_gemma":[0.9984036,0.000068880654,0.00017840981,0.0009368137,0.00012592385,0.00028636178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012991537,0.0005065901,0.000454629,0.00025033957,0.00028186632,0.0003952262,0.0012884951,0.00037445367,0.0000017358471],"category_scores_gemma":[0.0000037765142,0.0005345556,0.00016858095,0.000023239892,0.00031438307,0.00040951042,0.0028414032,0.00066610874,0.000024729608],"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":[0.000011233991,0.0000075676185,4.794721e-7,0.00012632093,0.00010354902,0.0009839024,0.00010675368,9.998366e-7,0.000010830814,0.8999578,0.01035218,0.08833841],"study_design_scores_gemma":[0.0003594702,0.00008754144,0.000005369791,0.0005278939,0.00011440074,0.00007861858,0.00002170123,0.021672592,0.000020632799,0.00015379257,0.9763442,0.0006137494],"about_ca_topic_score_codex":0.00014758612,"about_ca_topic_score_gemma":0.0000036873482,"teacher_disagreement_score":0.96599203,"about_ca_system_score_codex":0.00016702819,"about_ca_system_score_gemma":0.00011611273,"threshold_uncertainty_score":0.9997106},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051082703,0.00023008272,0.98902947,0.0007328171,0.00035658386,0.00016525222,0.0000036500517,0.00043035537,0.003943546],"genre_scores_gemma":[0.9505805,0.000021973274,0.048849843,0.00036685038,0.00007547596,0.000010616519,0.000076741286,0.000004110668,0.000013923088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991642,0.000041500618,0.00022024286,0.00016913206,0.00027922707,0.00012568058],"domain_scores_gemma":[0.9995927,0.000058210124,0.00006686413,0.00010017368,0.0001303664,0.000051634997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028016613,0.00010042342,0.00008133728,0.00013043536,0.00022776205,0.0009715519,0.00014868373,0.000034750985,0.0000032851615],"category_scores_gemma":[0.00002886227,0.000084614876,0.000027351109,0.00025272305,0.00003040202,0.002979398,0.00009007073,0.00013772414,0.00005178497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055564815,0.00001246222,0.0000135677565,0.000031423777,0.0000075082316,0.0000014774073,0.005771714,0.0019718192,0.00001938765,0.18766633,0.00067162036,0.80382717],"study_design_scores_gemma":[0.00014359028,0.000073155876,0.00065116736,0.00012219725,0.0000023336456,0.000011460527,0.0005056337,0.96911484,0.000057935053,0.016478376,0.0127159245,0.00012338691],"about_ca_topic_score_codex":0.000071542694,"about_ca_topic_score_gemma":0.0000018226006,"teacher_disagreement_score":0.967143,"about_ca_system_score_codex":0.000072101335,"about_ca_system_score_gemma":0.000036745358,"threshold_uncertainty_score":0.9368698},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033091876,0.00046704046,0.97291505,0.0011840241,0.0013089745,0.00009285522,0.0000048699294,0.00044990823,0.023246342],"genre_scores_gemma":[0.27326435,0.00024215855,0.6794374,0.0021024547,0.0012556924,0.000029522667,0.00016924297,0.00005123715,0.043447983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989103,0.000028024599,0.00019927109,0.000393544,0.0002788503,0.00018998908],"domain_scores_gemma":[0.9993542,0.000050398972,0.000019658497,0.00046429725,0.000041910378,0.00006955537],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002111388,0.00011648156,0.000091462316,0.00008765641,0.00008423205,0.0003003168,0.00041473334,0.00005398697,0.0005040794],"category_scores_gemma":[0.0000041596263,0.00008828107,0.0000555535,0.00007443602,0.000013718303,0.0009362534,0.00019259227,0.00011957262,0.0010769778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000927125,0.000120919154,0.00022277229,0.00011902802,0.000044735683,0.00008814531,0.0009834174,0.00013366771,0.00906695,0.057557903,0.11558563,0.8160676],"study_design_scores_gemma":[0.00010278011,0.000054741395,0.0006283293,0.000069553884,0.000004896678,0.0000169486,0.000003807845,0.5827959,0.0013484167,0.002761577,0.41202563,0.00018743874],"about_ca_topic_score_codex":0.00021416413,"about_ca_topic_score_gemma":0.000054164917,"teacher_disagreement_score":0.8158801,"about_ca_system_score_codex":0.000028405262,"about_ca_system_score_gemma":0.000054368717,"threshold_uncertainty_score":0.9997008},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083345234,0.003317098,0.9020515,0.002357355,0.0018880923,0.0025365206,0.0004904721,0.0006998683,0.0033138278],"genre_scores_gemma":[0.9937952,0.00021153997,0.0044556237,0.00009266921,0.00039702523,0.0003867957,0.00016833186,0.00008421745,0.00040859505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929366,0.000814977,0.00068656664,0.0019300116,0.0023095577,0.0013222585],"domain_scores_gemma":[0.996164,0.00041768077,0.0001382501,0.0026362634,0.0003269736,0.00031682328],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023743461,0.00052963156,0.0006547155,0.0012175547,0.00024075966,0.0023636378,0.0041618734,0.00052185584,0.00007525517],"category_scores_gemma":[0.000057490906,0.0004574906,0.00019552675,0.00096444215,0.00013960096,0.0004708346,0.026365243,0.005114038,0.0003406431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015928347,0.0017197649,0.008485258,0.020665625,0.00029845108,0.0055070543,0.019197771,0.013904593,0.00068513275,0.017149355,0.015450957,0.89677674],"study_design_scores_gemma":[0.00065472146,0.00006881598,0.008881366,0.006349986,0.0000055112837,0.000020005009,0.00035089717,0.90177953,0.00020591129,0.078639515,0.0023070066,0.00073676027],"about_ca_topic_score_codex":0.0020850415,"about_ca_topic_score_gemma":0.00013208961,"teacher_disagreement_score":0.91045,"about_ca_system_score_codex":0.00034466636,"about_ca_system_score_gemma":0.00049073756,"threshold_uncertainty_score":0.9997877},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06300517,0.004485995,0.92920625,0.00078505866,0.00074883876,0.000103843624,0.000010163698,0.00021326084,0.00144141],"genre_scores_gemma":[0.9882489,0.00004213731,0.011003753,0.00015804233,0.000075209966,0.000009050371,0.0000010268471,0.000005412503,0.00045648596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985842,0.000022658327,0.00012929585,0.0006008287,0.00036556486,0.00029745742],"domain_scores_gemma":[0.9993129,0.000054787346,0.000024132263,0.00043807636,0.000028571076,0.00014155913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029795774,0.00011444635,0.000092281836,0.0001265101,0.00020860127,0.0006603363,0.0008128362,0.000036477595,0.000020156607],"category_scores_gemma":[0.000015852975,0.00008467979,0.000026694897,0.000690382,0.00014786095,0.00053395855,0.0008503476,0.000118728225,0.00012161017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025336024,0.00005473926,0.00015258348,0.000032797994,0.000005054467,0.00015605755,0.002677634,0.0015181415,0.011777531,0.030548684,0.0014611551,0.95161307],"study_design_scores_gemma":[0.000061023347,0.000048909606,0.003601192,0.00004917953,0.0000018546815,0.000115857925,0.000050493436,0.97393996,0.00020009268,0.0006842799,0.021090122,0.00015701631],"about_ca_topic_score_codex":0.000048808208,"about_ca_topic_score_gemma":0.0000054061557,"teacher_disagreement_score":0.9724218,"about_ca_system_score_codex":0.000029363879,"about_ca_system_score_gemma":0.0000919941,"threshold_uncertainty_score":0.6367638},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054669297,0.000085298714,0.9954054,0.00094958686,0.00070368726,0.0003959735,0.000050986666,0.00088817585,0.0014662371],"genre_scores_gemma":[0.18697035,0.000033719145,0.8103593,0.0013084296,0.00027661046,0.00019374996,0.00015791394,0.00003920647,0.00066068495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988248,0.000032829266,0.00019627858,0.00045329303,0.00022496327,0.00026786854],"domain_scores_gemma":[0.9992077,0.00038343752,0.000022907421,0.00025498794,0.000046322868,0.000084695734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023455075,0.00014997898,0.00013846438,0.0001874048,0.00015775113,0.00034908447,0.00034542158,0.000066317894,0.000033263703],"category_scores_gemma":[0.00002378698,0.00011529626,0.00010464472,0.00037901278,0.00001287524,0.0006559237,0.000023950113,0.00009365405,0.000023522956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007980022,0.00003355525,0.00000674765,0.000018249684,0.00001379515,0.000004271633,0.00004753041,0.00026277456,0.0003723353,0.004321863,0.0019559166,0.99295497],"study_design_scores_gemma":[0.00065045187,0.000110150744,0.00006209701,0.000067794106,0.000011440477,0.000001449726,0.000004518111,0.97520363,0.001507397,0.0004999031,0.021718837,0.00016231995],"about_ca_topic_score_codex":0.000022157237,"about_ca_topic_score_gemma":0.0000048978995,"teacher_disagreement_score":0.99279267,"about_ca_system_score_codex":0.000048785092,"about_ca_system_score_gemma":0.00007422147,"threshold_uncertainty_score":0.4701645},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015879355,0.0018407225,0.9887275,0.0008610343,0.004310724,0.00030330013,0.000016142349,0.00033512965,0.0035895729],"genre_scores_gemma":[0.03476374,0.00017814098,0.95782614,0.0014875645,0.001874997,0.000008792755,0.000032860615,0.00010532303,0.0037224242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956435,0.000025116755,0.00062664255,0.001868306,0.0011629693,0.00067345076],"domain_scores_gemma":[0.9973084,0.00042437972,0.00018112772,0.0016771646,0.00019229628,0.0002166731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008481041,0.00055572414,0.0004934998,0.00089810695,0.00034544934,0.0009456764,0.0031809213,0.00037811953,0.000048091966],"category_scores_gemma":[0.000024516337,0.0004873993,0.00018102364,0.0009052523,0.00042050722,0.0010710327,0.0017797762,0.0011959136,0.00027150515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000091488555,0.00003331384,0.0000062794115,0.00011765911,0.00002484996,0.00032471714,0.0011275266,0.011635103,0.0021204667,0.050791387,0.000095950665,0.9337136],"study_design_scores_gemma":[0.00014348222,0.000098491015,0.000016259095,0.00082956307,0.00001361624,0.00011955222,1.104609e-7,0.694223,0.00486631,0.29134932,0.007618061,0.00072222523],"about_ca_topic_score_codex":0.000025491261,"about_ca_topic_score_gemma":0.00006648303,"teacher_disagreement_score":0.9329914,"about_ca_system_score_codex":0.00025344777,"about_ca_system_score_gemma":0.0005902248,"threshold_uncertainty_score":0.99975777},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06390109,0.007541091,0.9097629,0.0017507485,0.009639585,0.002310888,0.0018615187,0.003117153,0.00011502902],"genre_scores_gemma":[0.8676635,0.00023425932,0.12807094,0.00074361335,0.0021204285,0.00083401526,0.0000032951828,0.0002640917,0.000065841625],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99597234,0.00010517288,0.0006089885,0.0019186819,0.0006651632,0.00072963635],"domain_scores_gemma":[0.996335,0.00016321913,0.00032728608,0.0024878061,0.0003200716,0.0003666089],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008187114,0.0006360975,0.0005331209,0.00039517964,0.00035170733,0.000835329,0.0020385825,0.00048796093,0.000013558713],"category_scores_gemma":[0.000097108845,0.00062415976,0.00032858594,0.00063264265,0.00009946758,0.00018892191,0.003965755,0.0009681239,0.00014462801],"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":[0.000323528,0.0027881041,0.0010319623,0.0069270125,0.0019556016,0.0012306381,0.0003250041,0.02845547,0.474651,0.11218369,0.36896658,0.0011614044],"study_design_scores_gemma":[0.0008747092,0.00017365532,0.004673051,0.001575434,0.00020346399,1.4449978e-7,0.0000050484773,0.48629215,0.053727306,0.00010725887,0.45013902,0.0022287415],"about_ca_topic_score_codex":0.00003424832,"about_ca_topic_score_gemma":2.8903042e-7,"teacher_disagreement_score":0.80376244,"about_ca_system_score_codex":0.0003013665,"about_ca_system_score_gemma":0.0006541343,"threshold_uncertainty_score":0.999621},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027633805,0.0026265373,0.99260265,0.0014048032,0.0017796658,0.00027254128,0.0000310347,0.00006552827,0.0009409042],"genre_scores_gemma":[0.53871655,0.00009663385,0.4592274,0.00074782845,0.0005739162,0.000013016431,0.00006040068,0.0000340339,0.0005302027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976836,0.000041722724,0.00047641576,0.0009163298,0.00068014656,0.00020179416],"domain_scores_gemma":[0.9979633,0.000839502,0.00025527066,0.0007085121,0.000171811,0.000061565246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004362844,0.00027585326,0.00035160908,0.00036562496,0.00018675714,0.00038077033,0.0010979963,0.00014329476,0.000018778437],"category_scores_gemma":[0.000033340697,0.00018557771,0.00009246896,0.00033462103,0.00094368384,0.00052013167,0.0017587041,0.00039652115,0.00001450477],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073038944,0.00004842912,0.00011417073,0.00008340327,0.00010879554,0.00004551192,0.004397234,0.047260758,0.00094680354,0.39661846,0.00031040225,0.549993],"study_design_scores_gemma":[0.00022334381,0.000027086648,0.00031497696,0.00024665525,0.000012784267,0.000008856506,2.6928257e-7,0.6060204,0.0001596944,0.39265728,0.00018771928,0.00014092572],"about_ca_topic_score_codex":0.00017719158,"about_ca_topic_score_gemma":0.000032118704,"teacher_disagreement_score":0.5587597,"about_ca_system_score_codex":0.000051071274,"about_ca_system_score_gemma":0.00013405623,"threshold_uncertainty_score":0.75676394},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0120884385,0.000981138,0.98539937,0.00018433796,0.00111615,0.0000730932,0.0000031413897,0.00006979335,0.000084553285],"genre_scores_gemma":[0.7001188,0.0000071509867,0.29893747,0.000031014548,0.0007868222,0.0000043687724,0.000016175982,0.000010532155,0.00008765874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859715,0.000046785746,0.00041929947,0.00018476747,0.00061526604,0.00013675743],"domain_scores_gemma":[0.99904203,0.00012442366,0.00018907584,0.00018075685,0.00036194103,0.00010177745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059096783,0.0000896561,0.00014427686,0.00019581053,0.00007847473,0.0001830728,0.0003174265,0.000045413813,0.00004486713],"category_scores_gemma":[0.000030053348,0.00006713615,0.000113597765,0.0003761041,0.000032061103,0.0013593193,0.000067461864,0.00019655476,0.0000041506523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005274243,0.00033005554,0.0007452484,0.00007789694,0.00011578067,0.00007656607,0.00033939505,0.005401001,0.0063065495,0.03752469,0.0035129115,0.9455172],"study_design_scores_gemma":[0.0006310527,0.0009810365,0.014565704,0.00040112896,0.000048488884,0.0011120825,0.00006491292,0.71190715,0.0022375742,0.00947585,0.25827983,0.0002951875],"about_ca_topic_score_codex":0.00003335484,"about_ca_topic_score_gemma":0.0000017627785,"teacher_disagreement_score":0.94522196,"about_ca_system_score_codex":0.000041417767,"about_ca_system_score_gemma":0.00021979908,"threshold_uncertainty_score":0.27377328},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010710595,0.00020008224,0.9937241,0.0031168712,0.00007512841,0.00090510474,0.00012822813,0.00013165303,0.0006477718],"genre_scores_gemma":[0.03583068,0.00011980623,0.9570983,0.0024535484,0.0003830303,0.0014075114,0.00015808904,0.000020664493,0.0025283794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900645,0.000017989529,0.00017451624,0.0004494784,0.000120803685,0.000230736],"domain_scores_gemma":[0.9991034,0.00010033305,0.000024161069,0.0004953234,0.00014128734,0.00013546404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014839508,0.00011076182,0.00012984755,0.00010675044,0.00037020113,0.00011336511,0.0005721291,0.00005221341,0.00000789701],"category_scores_gemma":[0.000010844328,0.00010067786,0.000040827246,0.0005043276,0.000028335111,0.00019815659,0.00043504417,0.000088823675,0.000053198386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031171983,0.00008932119,0.000009625344,0.00004341022,0.00001029218,3.0236032e-7,0.00012398341,0.000021503578,0.00059444975,0.55335325,0.0032765672,0.4424742],"study_design_scores_gemma":[0.00050642394,0.0000851835,0.0008698132,0.00004658708,0.000013438276,0.0000041970347,0.00006531834,0.60854375,0.016632222,0.021370932,0.3515646,0.00029758413],"about_ca_topic_score_codex":0.000014059976,"about_ca_topic_score_gemma":0.000002784284,"teacher_disagreement_score":0.60852224,"about_ca_system_score_codex":0.000015351314,"about_ca_system_score_gemma":0.00006826331,"threshold_uncertainty_score":0.4105524},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2112491,0.000034413184,0.78689176,0.0013100889,0.00009125478,0.00006659032,0.0000013406101,0.00011219591,0.0002432548],"genre_scores_gemma":[0.66749746,0.0000040583514,0.33032152,0.0021164434,0.000027046102,0.0000068225945,0.000008537826,0.000004049394,0.000014053951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992984,0.000015490636,0.00020261075,0.00012860198,0.00018674332,0.00016814793],"domain_scores_gemma":[0.99959075,0.000023445482,0.00010943568,0.00017458179,0.000060393795,0.000041400217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013750134,0.0000966059,0.00008473866,0.00024519043,0.00050150254,0.00086709094,0.00024695744,0.00002826682,8.534786e-7],"category_scores_gemma":[0.0000137823345,0.00008026063,0.000011613863,0.000404897,0.00005288783,0.0059150434,0.0001815135,0.00014201179,0.0000019991646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001474902,0.000014777123,0.0020752815,0.000390866,0.000025305444,0.0000034977072,0.0058362233,0.009045444,0.0031319698,0.008335864,0.00048723357,0.9706388],"study_design_scores_gemma":[0.00069454353,0.000017671411,0.0036361574,0.0007761051,0.00001416601,0.000086518965,0.0006820452,0.98355675,0.0025953767,0.0008281288,0.00680882,0.00030369862],"about_ca_topic_score_codex":0.000037262816,"about_ca_topic_score_gemma":9.007436e-7,"teacher_disagreement_score":0.9745113,"about_ca_system_score_codex":0.000040718216,"about_ca_system_score_gemma":0.000094098024,"threshold_uncertainty_score":0.8361378},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010530043,0.0019833732,0.9777918,0.00025766986,0.00039611137,0.000120311626,0.0000045683373,0.00010094028,0.018292224],"genre_scores_gemma":[0.05196775,0.00101878,0.9456346,0.0002734666,0.000047220252,0.00004087626,0.000006155842,0.000010394079,0.0010007641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99909276,0.000021514574,0.0002665789,0.0002430819,0.00017707502,0.00019901029],"domain_scores_gemma":[0.9990163,0.00021276425,0.00007647019,0.0006314429,0.000033515353,0.000029531639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020314127,0.00011370345,0.00018566084,0.00010593714,0.00006929238,0.00008435475,0.0009512864,0.000039883696,0.000008965435],"category_scores_gemma":[0.00007382579,0.00009260358,0.000029555355,0.00041805455,0.000040620518,0.0007953954,0.00043182066,0.000080830774,0.00001794806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001418756,0.0001558537,0.00024236155,0.0001566486,0.000004740532,0.000011295232,0.0005538616,0.00027061542,0.00014453832,0.8723358,0.0007475698,0.12537529],"study_design_scores_gemma":[0.00029650904,0.000014392409,0.00019399144,0.00039599408,0.0000041213507,0.0000056035756,0.00020576017,0.14494538,0.0015096097,0.79512894,0.057107445,0.0001922612],"about_ca_topic_score_codex":0.000005156626,"about_ca_topic_score_gemma":0.000025178588,"teacher_disagreement_score":0.14467478,"about_ca_system_score_codex":0.000026007196,"about_ca_system_score_gemma":0.00003074804,"threshold_uncertainty_score":0.37762642},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004927295,0.00006865758,0.0029420354,0.00038811908,0.0000051961915,0.00012202335,0.00001246808,0.00027433687,0.9961379],"genre_scores_gemma":[0.000024104093,3.4265994e-7,0.011450691,0.00008142374,0.0001297783,0.000010361882,0.000011277944,0.000010689348,0.9882813],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885803,0.000036327583,0.0001692561,0.0003794994,0.0002596797,0.00029721236],"domain_scores_gemma":[0.99892914,0.00003953593,0.00002901313,0.0007781792,0.000038511043,0.00018564473],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00013352472,0.00013807602,0.00014127076,0.00006555303,0.00012727705,0.00016252356,0.0010340452,0.000051404924,0.98335093],"category_scores_gemma":[0.00001253677,0.00012079561,0.00004932609,0.00029180376,0.000019250485,0.00045289393,0.0003110802,0.000100894584,0.9944792],"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":[0.0000066447415,0.000026113046,2.1592538e-8,0.0000012782838,0.0000028875293,0.0000067058163,0.0000119683655,0.00005400621,0.000018658126,0.000009954235,0.3149639,0.68489784],"study_design_scores_gemma":[0.00015315771,0.000090478265,0.0000421255,0.000016652059,0.0000026912167,0.000012107706,1.8605664e-7,0.02142733,0.00010016579,0.000052834966,0.97792804,0.00017421586],"about_ca_topic_score_codex":0.000033124616,"about_ca_topic_score_gemma":8.071474e-8,"teacher_disagreement_score":0.6847236,"about_ca_system_score_codex":0.000022400618,"about_ca_system_score_gemma":0.000032970216,"threshold_uncertainty_score":0.49259022},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11744172,0.00010556748,0.87296176,0.0047970503,0.0012354556,0.00012728207,0.00045487622,0.00030865465,0.002567663],"genre_scores_gemma":[0.930697,0.000040998362,0.061316893,0.0053517614,0.0004568809,0.00045835925,0.0015512842,0.000059247737,0.000067524044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969944,0.000055961882,0.0009325904,0.0005745255,0.00074800546,0.00069451664],"domain_scores_gemma":[0.997675,0.00016816673,0.0008761463,0.00093524734,0.00018222646,0.0001632273],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00072909426,0.0003283225,0.00018352547,0.00021335766,0.0013565674,0.001704031,0.0010326715,0.00027272798,0.000100857855],"category_scores_gemma":[0.0002616111,0.00042206445,0.00023340037,0.00071967905,0.0001847892,0.0054791244,0.0005656137,0.00038949132,0.00025202445],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009528297,0.00006616421,0.0000041324124,0.00064538774,0.00008667792,0.00001550146,0.0023722034,0.0011934709,0.0012306324,0.96046567,0.019937264,0.0138876205],"study_design_scores_gemma":[0.0007488107,0.000104083665,0.00029582033,0.0005524842,0.00010186065,0.00013980217,0.00021010806,0.95739406,0.014562521,0.001044048,0.024348022,0.0004983907],"about_ca_topic_score_codex":0.00013980384,"about_ca_topic_score_gemma":0.000010333603,"teacher_disagreement_score":0.95942163,"about_ca_system_score_codex":0.000039741913,"about_ca_system_score_gemma":0.00049187854,"threshold_uncertainty_score":0.99994355},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009850233,0.00032398725,0.99396706,0.00017758334,0.0026096955,0.0005517236,0.0015124304,0.00011605352,0.00064296764],"genre_scores_gemma":[0.00014289953,0.00014994055,0.9958061,0.0005332688,0.00008245613,0.00001655694,0.003151359,0.000012722841,0.00010468221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978227,0.00003060001,0.0007199498,0.0006336693,0.00031487882,0.00047818126],"domain_scores_gemma":[0.994668,0.00011483618,0.00023438336,0.004763963,0.00008237129,0.00013644472],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009309584,0.00025651496,0.00038315036,0.0003413423,0.00031207426,0.0005086213,0.008756074,0.0001608548,0.0000023868524],"category_scores_gemma":[0.00011572698,0.00023488233,0.00003242559,0.0005013759,0.0000810719,0.0049771834,0.0062451437,0.00024430917,0.000006756262],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015205713,0.00017209229,0.00017466627,0.00010770099,0.00003847426,0.0000038469784,0.00061257713,0.000152338,0.00003406236,0.0025806196,0.1022612,0.8938472],"study_design_scores_gemma":[0.0008964161,0.000035314937,0.000052616546,0.00015330024,0.000014781747,0.0000092049595,0.00049526605,0.8802344,0.00011294289,0.0020308648,0.11570847,0.0002564038],"about_ca_topic_score_codex":0.00007649484,"about_ca_topic_score_gemma":0.00001004272,"teacher_disagreement_score":0.8935908,"about_ca_system_score_codex":0.00009987785,"about_ca_system_score_gemma":0.00033522744,"threshold_uncertainty_score":0.996607},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022571329,0.00008523376,0.97353345,0.0010327064,0.00049704284,0.00034053298,0.000038410846,0.00019948414,0.001701824],"genre_scores_gemma":[0.8307593,0.000051177096,0.15990888,0.006464164,0.00007183025,0.00004488574,0.0022420057,0.000010139373,0.0004476559],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988095,0.000050831735,0.00038925774,0.00028149612,0.00030390723,0.00016496798],"domain_scores_gemma":[0.99910504,0.00009645724,0.00014531794,0.0004239561,0.00013936748,0.000089843634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000252688,0.00013612601,0.00013475669,0.00027008087,0.00030308304,0.00045501802,0.0005415784,0.000058324265,0.000010510354],"category_scores_gemma":[0.000035369634,0.0001315386,0.000018441504,0.0005111073,0.000018662424,0.0036060342,0.0013033138,0.00008599809,0.00009542368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042268883,0.000044162407,0.00033045388,0.000076436576,0.000023428745,0.0000010044394,0.0012886368,0.04023317,0.00016594976,0.017440645,0.0768488,0.86350507],"study_design_scores_gemma":[0.00054741,0.000033452478,0.015648643,0.000039997223,0.0000051978122,0.0000037140005,0.00003777316,0.91882396,0.00013828433,0.0016284953,0.06295101,0.00014203206],"about_ca_topic_score_codex":0.000054071366,"about_ca_topic_score_gemma":0.00000794787,"teacher_disagreement_score":0.8785908,"about_ca_system_score_codex":0.00006597987,"about_ca_system_score_gemma":0.00006443724,"threshold_uncertainty_score":0.5363989},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004085188,0.0002495798,0.99359673,0.00032299248,0.00021431953,0.00020572786,0.000046132554,0.000037029888,0.0012422816],"genre_scores_gemma":[0.05006939,0.000056400364,0.949424,0.00019080422,0.00001722394,0.000016980515,0.000016297985,0.0000029903417,0.00020588345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902284,0.0001041826,0.00024245576,0.00033896603,0.00011196972,0.00017958235],"domain_scores_gemma":[0.99902713,0.000494302,0.000046336634,0.0003204772,0.000065918575,0.00004581362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047164274,0.00009299751,0.00016485697,0.00006175471,0.00011509511,0.00010921029,0.00026883674,0.000046476118,0.0000064450433],"category_scores_gemma":[0.00050092244,0.000082823586,0.000012956821,0.00024484925,0.000073866926,0.00021510065,0.00031174676,0.00015030298,0.0000028663599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032724976,0.00007988011,0.0032414687,0.00008855833,0.0000052720134,0.000014429428,0.00053780223,0.00008910494,0.000013835698,0.66927594,0.0015556181,0.32506534],"study_design_scores_gemma":[0.0014076167,0.000061606755,0.016687583,0.00013784764,0.0000058542173,0.000004415042,0.000039570165,0.2122488,0.00006720946,0.76134974,0.007814878,0.00017489231],"about_ca_topic_score_codex":0.00009850335,"about_ca_topic_score_gemma":0.000065808425,"teacher_disagreement_score":0.32489043,"about_ca_system_score_codex":0.000034175475,"about_ca_system_score_gemma":0.00009624562,"threshold_uncertainty_score":0.33774477},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034009784,0.00023206866,0.9911815,0.0035115283,0.0007334028,0.00019917548,0.000006662898,0.0002135137,0.00052116346],"genre_scores_gemma":[0.95884395,0.00008317736,0.038202964,0.0024073306,0.00007974492,0.000021256157,0.00016736974,0.000004156395,0.00019008097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989447,0.00011044062,0.00024211583,0.00029696888,0.00019727356,0.00020847702],"domain_scores_gemma":[0.9993125,0.000034729925,0.00013557807,0.00041048706,0.000039404244,0.000067255205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034374621,0.00008622606,0.00012356217,0.00011577921,0.00030388316,0.00010995698,0.00024393968,0.000048524453,0.000018144521],"category_scores_gemma":[0.000020701567,0.00008174381,0.00002827058,0.0003465398,0.000010581573,0.0008086372,0.0001028634,0.00009491641,0.00002772887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069285934,0.00006699165,0.008065897,0.00007292245,0.0000053028334,9.454156e-7,0.00029230234,0.00037629963,0.00003159743,0.7280574,0.010746095,0.25227734],"study_design_scores_gemma":[0.00050007174,0.00009740329,0.515457,0.00032620016,0.000003872266,0.0000043394266,0.000040569656,0.19919266,0.00019748701,0.26460874,0.019334598,0.00023709118],"about_ca_topic_score_codex":0.00038539764,"about_ca_topic_score_gemma":0.000037328184,"teacher_disagreement_score":0.95544297,"about_ca_system_score_codex":0.00012343527,"about_ca_system_score_gemma":0.000092442555,"threshold_uncertainty_score":0.3333416},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000066167326,0.0011798387,0.9935199,0.0030887064,0.0005808371,0.00055010215,0.0000469277,0.0005408628,0.00042663983],"genre_scores_gemma":[0.0062608775,0.00003581703,0.9910175,0.00084628037,0.0002878307,0.000161581,0.000049752285,0.000026602671,0.0013137109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836713,0.000057322835,0.00019890927,0.00058920454,0.00039421735,0.00039319118],"domain_scores_gemma":[0.99847096,0.00039509594,0.000020722411,0.00086066034,0.00011924409,0.00013330759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063947355,0.00016891291,0.00012733926,0.00012906682,0.0003521526,0.00084550184,0.001395138,0.00006715207,0.000050140792],"category_scores_gemma":[0.000004885327,0.00009528612,0.00010607012,0.00059651386,0.00006908462,0.0007861032,0.00027567198,0.00019895998,0.000056760415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030510325,0.000066655026,0.0000047137282,0.00002993392,0.000019136045,0.000018440142,0.00021642692,0.0000982251,0.0002290806,0.0551104,0.017261414,0.9269425],"study_design_scores_gemma":[0.00019209817,0.0001668953,0.00003900357,0.00003340996,0.000007852439,0.0000118366415,0.000031492185,0.9151068,0.0014956889,0.0032136254,0.07954322,0.00015808699],"about_ca_topic_score_codex":0.00019972179,"about_ca_topic_score_gemma":0.000013011312,"teacher_disagreement_score":0.92678446,"about_ca_system_score_codex":0.00002414033,"about_ca_system_score_gemma":0.00020692202,"threshold_uncertainty_score":0.81531936},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011441947,0.000413595,0.99164045,0.0018815191,0.0023866494,0.00083271373,0.00007585854,0.00020970253,0.0025480967],"genre_scores_gemma":[0.015069582,0.00024554346,0.97733784,0.0031494123,0.0012100667,0.000085545675,0.00007818203,0.000058690093,0.0027651303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602085,0.00003919557,0.00057966256,0.0016778418,0.0009381764,0.0007442481],"domain_scores_gemma":[0.99529266,0.0018049662,0.00033835572,0.0019367703,0.00047894305,0.00014831193],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00057208666,0.000588434,0.0005644033,0.0005545207,0.00077001675,0.0012956919,0.006449149,0.00031905042,0.000007995577],"category_scores_gemma":[0.00027056498,0.00038440348,0.00018988822,0.0009222868,0.00066815864,0.00076647836,0.0027264664,0.0007786036,0.000011035168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027558315,0.000051179137,0.000037732683,0.00010886143,0.000032592263,0.00003443604,0.0003348856,0.0027022946,0.00008002116,0.16931407,0.002979297,0.8242971],"study_design_scores_gemma":[0.00064408424,0.00021068935,0.00017644402,0.0008233749,0.00002345897,0.000035172194,2.1469702e-7,0.51092637,0.0018707588,0.44308,0.041342743,0.0008666765],"about_ca_topic_score_codex":0.00007502699,"about_ca_topic_score_gemma":0.00003289175,"teacher_disagreement_score":0.8234304,"about_ca_system_score_codex":0.00020100176,"about_ca_system_score_gemma":0.0007284765,"threshold_uncertainty_score":0.99986076},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039247847,0.0001910796,0.9906307,0.0013690976,0.000036376583,0.0003349844,0.0001091963,0.00021874896,0.0031850482],"genre_scores_gemma":[0.841041,0.0000041488925,0.15469672,0.0037696734,0.00002337933,0.000060114668,0.00024004003,0.000012980656,0.00015194518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985735,0.00007143783,0.00042399997,0.00035284628,0.0002995335,0.00027872],"domain_scores_gemma":[0.9991003,0.00008891781,0.00009443161,0.0004677429,0.000057667163,0.00019091567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024724726,0.00024287109,0.00020992433,0.0004652705,0.00055178924,0.00090997125,0.00041781098,0.00008085258,0.000016931688],"category_scores_gemma":[0.00004368199,0.0002173727,0.000039326813,0.00042970723,0.000062579216,0.0014227731,0.000031515156,0.00028121166,0.000008599008],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007260322,0.000102324135,0.000004399563,0.00028714657,0.0000097394895,0.0000031466177,0.0058305515,0.0018998346,0.00013155222,0.00045827797,0.00015005354,0.99105036],"study_design_scores_gemma":[0.001732634,0.000100858866,0.00039892428,0.0005243962,0.00003528757,0.000041208885,0.0016734373,0.9781325,0.002849063,0.00029933942,0.013764773,0.00044758717],"about_ca_topic_score_codex":0.000019781535,"about_ca_topic_score_gemma":0.0000036303063,"teacher_disagreement_score":0.9906028,"about_ca_system_score_codex":0.000038649578,"about_ca_system_score_gemma":0.00007625517,"threshold_uncertainty_score":0.88642013},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044769,0.000440418,0.9534433,0.00014894064,0.0003262985,0.00012982685,0.0000062179956,0.00024320527,0.0004927778],"genre_scores_gemma":[0.93256307,0.00001622205,0.06729671,0.00002377695,0.000059074573,0.0000013401121,0.0000149819125,0.0000052208648,0.000019591373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917746,0.000031218977,0.00017945605,0.00032804496,0.0001363712,0.00014745537],"domain_scores_gemma":[0.99961656,0.00011213095,0.000029300038,0.00016580915,0.000024687428,0.000051524734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027247277,0.000089671856,0.000090849644,0.000056578032,0.00016279754,0.00068626343,0.00010729232,0.000034714256,0.00001307531],"category_scores_gemma":[0.000025786589,0.000073231146,0.000022417238,0.00018258322,0.000025989508,0.00080961594,0.0002625408,0.000093055016,0.000005995363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031407587,0.00003856145,0.00020980573,0.0005304181,0.000031284122,0.00004343149,0.0009991179,0.010294445,0.014073391,0.4616731,0.00036668277,0.51173663],"study_design_scores_gemma":[0.000045522153,0.000011163854,0.00028472114,0.00027247335,0.0000067515766,0.000076139695,0.000018076063,0.9781894,0.00034177024,0.02027555,0.0003739721,0.000104430335],"about_ca_topic_score_codex":0.000047968075,"about_ca_topic_score_gemma":0.0000011138251,"teacher_disagreement_score":0.967895,"about_ca_system_score_codex":0.00006459445,"about_ca_system_score_gemma":0.000037873753,"threshold_uncertainty_score":0.6617654},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070483033,0.0000064157707,0.9674944,0.00070840586,0.0001694335,0.00027641215,0.000009968311,0.00019787377,0.02408878],"genre_scores_gemma":[0.59921145,0.000012293833,0.39903182,0.0011565076,0.0000638483,0.00007259229,0.000017586,0.000025663474,0.00040824895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984506,0.000020019395,0.00035730234,0.00045038117,0.00039197877,0.00032977067],"domain_scores_gemma":[0.99835414,0.00036574432,0.00016971675,0.0009899149,0.000031181156,0.000089296664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000304671,0.00022908016,0.00027496973,0.00012008738,0.00019906802,0.00033448634,0.00080429064,0.00009865631,0.000022437805],"category_scores_gemma":[0.000045682995,0.00018468355,0.000062704705,0.0002473171,0.000039248338,0.00031096517,0.00083496474,0.00032031612,0.00015474983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009628445,0.0002555157,0.0000076263445,0.00022558247,0.00003949103,0.00003628479,0.0015521531,0.000051777686,0.0014890746,0.90579903,0.004597623,0.08593619],"study_design_scores_gemma":[0.002291234,0.00020615217,0.00045897433,0.001286419,0.00010793076,0.00004612296,0.0020008143,0.5390561,0.03085107,0.4034831,0.018619563,0.0015924854],"about_ca_topic_score_codex":0.000007097144,"about_ca_topic_score_gemma":0.000001126258,"teacher_disagreement_score":0.59216315,"about_ca_system_score_codex":0.00004283296,"about_ca_system_score_gemma":0.000053878084,"threshold_uncertainty_score":0.7531177},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052310955,0.022360515,0.96569514,0.0017714673,0.0022449556,0.00026444293,0.000023888251,0.00017062413,0.0022378499],"genre_scores_gemma":[0.7720717,0.13777877,0.05988674,0.0012082661,0.0040609315,0.000096331816,0.000121730154,0.00012084799,0.024654659],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951282,0.00021376881,0.00057460053,0.0009164086,0.0006305131,0.0025364803],"domain_scores_gemma":[0.99803036,0.000104541876,0.00042089273,0.001114216,0.00011087976,0.00021912827],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002030217,0.0004926955,0.00054872734,0.00040182957,0.00043283004,0.00081724225,0.0025481693,0.00037309912,0.000023906463],"category_scores_gemma":[0.000059283797,0.00042836517,0.00021989278,0.00037237894,0.00006834534,0.00053245685,0.0036652603,0.0064295544,0.000012721669],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050855706,0.00013256539,0.00054246554,0.00008542616,0.00035919537,0.00004143756,0.0008718283,0.0002200445,0.000029278215,0.18349451,0.0029468052,0.8112256],"study_design_scores_gemma":[0.0012473749,0.00030349096,0.0005160746,0.00088509725,0.00010591635,0.00093568786,0.00042047002,0.05445384,0.00006661253,0.91224027,0.027761143,0.0010640539],"about_ca_topic_score_codex":0.00025277986,"about_ca_topic_score_gemma":0.00030306156,"teacher_disagreement_score":0.90580845,"about_ca_system_score_codex":0.0009066509,"about_ca_system_score_gemma":0.0051810197,"threshold_uncertainty_score":0.99981683},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045140527,0.00059876894,0.9508958,0.00028805263,0.00089094415,0.00087739533,0.00030615585,0.00095947215,0.000042904965],"genre_scores_gemma":[0.42749587,0.0002635221,0.5708613,0.0005383907,0.00034187367,0.00035571863,0.0000017532518,0.00010423091,0.00003736318],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956837,0.00021552948,0.0005659679,0.0018312552,0.00084450084,0.0008589909],"domain_scores_gemma":[0.995599,0.00009839061,0.00035950582,0.003046924,0.0005659807,0.00033024844],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00075634615,0.00071148865,0.0007945271,0.0003653903,0.00040924057,0.0014277924,0.00297173,0.0004331142,0.0000223264],"category_scores_gemma":[0.000029480632,0.0006654518,0.00014566915,0.00076935976,0.00011956558,0.00065185246,0.0049257316,0.0012674469,0.000039845934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015866962,0.0100024585,0.04445208,0.03526565,0.010228239,0.0076333205,0.0019220684,0.092133515,0.6827989,0.08242183,0.022622043,0.008933182],"study_design_scores_gemma":[0.005617262,0.00027946144,0.018897995,0.009444095,0.00027969104,2.4526977e-7,0.000025589863,0.7738805,0.1762659,0.000037862497,0.009753321,0.005518074],"about_ca_topic_score_codex":0.00019940017,"about_ca_topic_score_gemma":0.0000021756437,"teacher_disagreement_score":0.68174696,"about_ca_system_score_codex":0.00021713071,"about_ca_system_score_gemma":0.0010227314,"threshold_uncertainty_score":0.9996088},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028199787,0.0001721579,0.9943567,0.00016259054,0.0046978947,0.00021532095,0.000008229757,0.000037050395,0.00006807202],"genre_scores_gemma":[0.01885777,0.000060353726,0.98060393,0.00009553284,0.00030080855,0.000010812142,0.000034622048,0.000010125599,0.00002606995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988939,0.00006609914,0.00047119462,0.00017687725,0.000242386,0.00014952211],"domain_scores_gemma":[0.9985905,0.000098287965,0.00044798266,0.00025069402,0.00053684897,0.00007562981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005053507,0.000115810384,0.00021276483,0.00015369907,0.00016002491,0.00033543492,0.0006214704,0.00009202527,0.0000027164238],"category_scores_gemma":[0.00009529393,0.00010346652,0.0000707893,0.0002966058,0.000014360418,0.0023732425,0.00007481955,0.00010983471,2.8679042e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031542117,0.0014345442,0.00005383405,0.00011313596,0.00017038835,0.0000048884876,0.00057137146,0.225487,0.013568643,0.05729539,0.011785174,0.6892002],"study_design_scores_gemma":[0.0018683422,0.0003978321,0.00000962682,0.00004696386,0.000021897227,0.0000031097436,0.000016815848,0.9833885,0.0051487973,0.0064012352,0.002592137,0.00010478639],"about_ca_topic_score_codex":0.0000054804264,"about_ca_topic_score_gemma":4.3030767e-8,"teacher_disagreement_score":0.7579015,"about_ca_system_score_codex":0.00008443047,"about_ca_system_score_gemma":0.00015539174,"threshold_uncertainty_score":0.4219242},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5721704,0.00035888597,0.42597443,0.00022415388,0.000111012654,0.00016380467,0.0000071506415,0.00004440241,0.000945796],"genre_scores_gemma":[0.94009405,0.00011569206,0.059582606,0.00003933106,0.000015537895,0.0000047652575,0.00000923961,0.0000025937086,0.00013616108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990925,0.000030821186,0.00023928522,0.00027649457,0.00019029867,0.00017055376],"domain_scores_gemma":[0.9995135,0.000059373702,0.00005438947,0.00025409594,0.00006640997,0.000052251224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023689703,0.000092667324,0.00015874316,0.0001144313,0.0001613429,0.00010497039,0.00025462607,0.000035562192,0.000011996077],"category_scores_gemma":[0.0000040821656,0.00007759082,0.0000129179525,0.00023561786,0.000042478903,0.0005484843,0.0006084339,0.00010020454,0.0000012617618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071716113,0.00003928539,0.14299446,0.00009725117,0.000015555894,7.818128e-7,0.0008424188,0.000061307146,0.0012610158,0.007844361,0.001647083,0.84518933],"study_design_scores_gemma":[0.00071108714,0.00015886071,0.14533922,0.0000709467,0.00000834822,0.0000035708906,0.0010527885,0.8254899,0.025648266,0.00019172982,0.0011837566,0.00014156991],"about_ca_topic_score_codex":0.0002081119,"about_ca_topic_score_gemma":0.000017651133,"teacher_disagreement_score":0.8450477,"about_ca_system_score_codex":0.000013956394,"about_ca_system_score_gemma":0.000043717908,"threshold_uncertainty_score":0.3164062},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002087122,0.00044523974,0.9881424,0.0005759953,0.00012634127,0.000627454,0.00024237034,0.00007129967,0.009560192],"genre_scores_gemma":[0.016648827,0.00044155665,0.98030794,0.0009369429,0.00005529834,0.000028138405,0.0010585036,0.000012122857,0.00051070174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984033,0.00001980932,0.0006409942,0.00043907354,0.00025768613,0.00023911626],"domain_scores_gemma":[0.9964882,0.00039963395,0.00033164932,0.0024509497,0.0002640909,0.00006545038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010650891,0.00020183843,0.00025167427,0.000760095,0.00053097506,0.0007358107,0.0041974364,0.00012543339,0.0000026894916],"category_scores_gemma":[0.00017699113,0.00019776278,0.00001741501,0.00044139568,0.0002448129,0.006078351,0.007819748,0.00038303694,0.00000201442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005738931,0.000025397476,0.00032981893,0.00014117076,0.0000062101844,2.1390032e-7,0.0018679994,0.0003818875,0.000040118386,0.16712905,0.0015710554,0.82850134],"study_design_scores_gemma":[0.00031856063,0.000025939657,0.0009836009,0.00031049192,0.0000030227393,0.0000115339035,0.00000870562,0.88509685,0.0000052178084,0.0035777944,0.109454885,0.00020337026],"about_ca_topic_score_codex":0.00005408095,"about_ca_topic_score_gemma":0.00011246572,"teacher_disagreement_score":0.88471496,"about_ca_system_score_codex":0.00007760672,"about_ca_system_score_gemma":0.00032108466,"threshold_uncertainty_score":0.9746756},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009632098,0.012155408,0.979853,0.0013547849,0.0013283213,0.00017559632,0.00040162372,0.00023091793,0.0044040494],"genre_scores_gemma":[0.9177517,0.0006180032,0.07554677,0.0034393077,0.00011114988,0.0000124254675,0.00085363525,0.00001882105,0.0016481503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782133,0.00008662524,0.0003251686,0.0009436883,0.00043962136,0.00038353584],"domain_scores_gemma":[0.9967923,0.0001717466,0.000098555254,0.0027183504,0.000115067836,0.00010396818],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00043484574,0.00024500125,0.00023975263,0.00013033359,0.00026948497,0.00024478952,0.0059543774,0.0002826069,0.000037605918],"category_scores_gemma":[0.000082078,0.00019065996,0.00004571112,0.00064820366,0.00004495026,0.001316762,0.0047754147,0.0010100004,0.00003620384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025452155,0.0003579322,0.00014004955,0.000056362427,0.000034880668,0.000037274614,0.00010768336,0.0008731496,0.000577431,0.3338642,0.28961393,0.37431163],"study_design_scores_gemma":[0.000101296944,0.000013090373,0.0000446931,0.00011263961,0.000005857604,0.0000050736403,0.000007683107,0.8540062,0.0049222847,0.027067643,0.11352141,0.00019214657],"about_ca_topic_score_codex":0.00009403581,"about_ca_topic_score_gemma":0.000017651102,"teacher_disagreement_score":0.9176554,"about_ca_system_score_codex":0.00003175387,"about_ca_system_score_gemma":0.00007234986,"threshold_uncertainty_score":0.99942386},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015587288,0.00019393812,0.9785743,0.0006689072,0.00033231726,0.00007432408,0.000004720598,0.00012309816,0.004441139],"genre_scores_gemma":[0.7665294,0.00014974418,0.23117048,0.001447639,0.000033983015,0.0000052741075,0.000011050793,0.0000035364922,0.00064893975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932444,0.000021065523,0.000109566536,0.00029151363,0.00011619815,0.0001372394],"domain_scores_gemma":[0.99948466,0.00006615721,0.000026924297,0.0003606053,0.000025603886,0.000036060108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000605525,0.00008247623,0.000093831324,0.000038423,0.00018818739,0.00014186627,0.00041127572,0.000036559948,0.000025894728],"category_scores_gemma":[0.000006592516,0.00006160709,0.000020197327,0.00010504284,0.000017551509,0.00049284654,0.0010218896,0.00007289913,0.000007357932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018016837,0.00018591175,0.022819815,0.00011160048,0.00005460848,0.00002434739,0.0013132618,0.0001396635,0.007901895,0.60423213,0.019375438,0.3438233],"study_design_scores_gemma":[0.0036435626,0.00018478923,0.22301036,0.0012118275,0.000040436415,0.00002352059,0.0006526687,0.43756044,0.02472389,0.098469324,0.20924553,0.0012336301],"about_ca_topic_score_codex":0.000259876,"about_ca_topic_score_gemma":0.000005103272,"teacher_disagreement_score":0.75094205,"about_ca_system_score_codex":0.000013393203,"about_ca_system_score_gemma":0.000014266664,"threshold_uncertainty_score":0.25122643},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00961052,0.00004586762,0.9695121,0.0011403507,0.00006204339,0.00006163197,0.0000019055153,0.0000712817,0.01949431],"genre_scores_gemma":[0.19891052,0.0000072168773,0.79731995,0.00066329696,0.000025494139,0.000010410402,0.00003276647,0.000003232455,0.003027102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993859,0.000025591557,0.000116453164,0.0002337325,0.00012902936,0.00010930171],"domain_scores_gemma":[0.99953973,0.00009174272,0.000024058709,0.00029938348,0.00002468586,0.00002042368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012936628,0.000057523237,0.00006627848,0.00008929825,0.00008029526,0.00007797226,0.00026031074,0.000014583828,0.00004849911],"category_scores_gemma":[0.00002924645,0.000040673352,0.0000082809875,0.00034665345,0.000012229986,0.00075720827,0.0003137647,0.000092652735,0.000013625669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000902128,0.000074298085,0.021192674,0.000008987889,0.000006746609,0.000019627552,0.00009293008,0.0035805092,0.00024945967,0.90806985,0.006060797,0.060635112],"study_design_scores_gemma":[0.0006363257,0.000025347417,0.052459966,0.00013273019,0.0000015717119,0.0000053996364,0.0000382955,0.9241741,0.0010516151,0.002733777,0.018594636,0.00014628193],"about_ca_topic_score_codex":0.00016298736,"about_ca_topic_score_gemma":0.000090249894,"teacher_disagreement_score":0.92059356,"about_ca_system_score_codex":0.000015453314,"about_ca_system_score_gemma":0.000082915474,"threshold_uncertainty_score":0.16586111},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39229143,0.008238009,0.5985564,0.0005240932,0.00014795862,0.000066942215,0.000018720875,0.000028011204,0.00012845948],"genre_scores_gemma":[0.96748966,0.0002499354,0.032009635,0.000088667475,0.00011710597,0.000005960704,0.0000042710103,0.000010392322,0.00002438501],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992485,0.000018994204,0.00014955232,0.0003121606,0.000121127916,0.00014967039],"domain_scores_gemma":[0.9995296,0.00007115368,0.00002771465,0.00027082447,0.000025514426,0.000075196345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012948645,0.0001118112,0.00011199315,0.00009832217,0.00013544816,0.0002793221,0.00027843946,0.000032990323,0.0000024436936],"category_scores_gemma":[0.000009192496,0.00007733792,0.000035545043,0.00020838816,0.0000358709,0.00008830951,0.0005425467,0.00007431367,0.0000017480969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023860496,0.000006975753,0.0001320001,0.00001589894,0.00004753215,0.0000102201375,0.0020296192,0.0002523059,0.6802415,0.0015811645,0.00015368855,0.31552672],"study_design_scores_gemma":[0.0005457363,0.0005408437,0.036367606,0.0006488658,0.0001039962,0.0000933917,0.002738584,0.8471526,0.04544733,0.012142837,0.053422388,0.0007958237],"about_ca_topic_score_codex":0.000036887748,"about_ca_topic_score_gemma":0.00002839628,"teacher_disagreement_score":0.8469003,"about_ca_system_score_codex":0.0000072286425,"about_ca_system_score_gemma":0.00001561823,"threshold_uncertainty_score":0.31537488},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016954914,0.0006636924,0.9952673,0.00032967026,0.0016370043,0.00009051849,0.0000043507684,0.000023631012,0.00028836148],"genre_scores_gemma":[0.10631365,0.000024727558,0.89276046,0.00029823152,0.0005062213,0.0000019537115,6.719077e-7,0.000002576063,0.00009148267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883276,0.0000700173,0.0004021378,0.00022841542,0.00030169255,0.0001649846],"domain_scores_gemma":[0.99909973,0.0001492591,0.0002250258,0.00019660422,0.00023180107,0.00009757391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013034105,0.00009710176,0.0002499997,0.0002165015,0.0002823479,0.0005214343,0.0010172632,0.000036282407,0.0000011174102],"category_scores_gemma":[0.000005240833,0.00006290451,0.00006573928,0.00029940426,0.0000695068,0.0011242931,0.00015850802,0.0000666504,0.0000013780264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008742233,0.00006509259,0.00012839629,0.0000488872,0.00002353509,0.000013293936,0.0001811293,0.00085304934,0.00008690711,0.025661457,0.009203955,0.96372557],"study_design_scores_gemma":[0.0004142895,0.00057864026,0.00039219428,0.0001818328,0.000007807755,0.00013862763,0.000053324962,0.9880036,0.00012700878,0.0010770864,0.00894501,0.00008054063],"about_ca_topic_score_codex":0.0000041753556,"about_ca_topic_score_gemma":2.1401455e-7,"teacher_disagreement_score":0.9871506,"about_ca_system_score_codex":0.000018848887,"about_ca_system_score_gemma":0.00014649081,"threshold_uncertainty_score":0.5028203},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016940505,0.00031778714,0.99416494,0.00036211658,0.0018820649,0.00033977453,0.00017786272,0.00033431573,0.0007270937],"genre_scores_gemma":[0.8214864,0.00005934491,0.17612056,0.0003174818,0.000090130525,0.000179313,0.00009734052,0.000022279086,0.0016271556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982031,0.00013985946,0.0003548158,0.00061147864,0.000384871,0.00030585867],"domain_scores_gemma":[0.99701834,0.00020575617,0.0000833636,0.0025286477,0.000047613452,0.00011630875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003399167,0.00020764483,0.00021421767,0.00026324965,0.0005152252,0.00023963972,0.0014881358,0.00007260138,0.000019566934],"category_scores_gemma":[0.000019353547,0.00017195172,0.000082073224,0.00044512318,0.000026470632,0.00032125955,0.00012352125,0.00027763552,0.00012537042],"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":[0.00016208495,0.0017984641,0.000034296652,0.0006424569,0.00017312437,0.00014134911,0.0011415291,0.7311589,0.030494003,0.06144535,0.02155403,0.15125439],"study_design_scores_gemma":[0.0016865161,0.00009962344,0.00015005597,0.0024118584,0.000039640487,0.000046987137,0.00052077085,0.92754424,0.008398479,0.0009625379,0.057430796,0.000708504],"about_ca_topic_score_codex":0.00028356165,"about_ca_topic_score_gemma":0.0000060811985,"teacher_disagreement_score":0.81979233,"about_ca_system_score_codex":0.000066088294,"about_ca_system_score_gemma":0.00007072005,"threshold_uncertainty_score":0.70119876},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034897685,0.00057427294,0.9567411,0.0040495414,0.0002911683,0.00033494018,0.0000028690854,0.00021144097,0.0028969983],"genre_scores_gemma":[0.99460536,0.00034768178,0.004476411,0.00039831645,0.00000617392,0.00002362524,0.000041251067,0.0000018694665,0.000099300305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992994,0.000034236327,0.00028734448,0.00012658193,0.00013192545,0.00012052816],"domain_scores_gemma":[0.999441,0.000097717784,0.00012391502,0.00016835709,0.00012785706,0.000041149025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026717145,0.00008283719,0.000068329886,0.000084963474,0.00043333715,0.00058800174,0.0002215507,0.000049352155,8.4986317e-7],"category_scores_gemma":[0.000030305013,0.00005888576,0.000011583316,0.00037196974,0.000077814846,0.0018789192,0.00015570472,0.00009479062,0.000013789338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004186257,0.000008050503,0.0003804143,0.000029525767,0.000010308069,5.727883e-7,0.0008106557,0.0016542149,0.000072599934,0.19084404,0.00072981114,0.8054556],"study_design_scores_gemma":[0.00032608522,0.000029481647,0.024887888,0.000050120627,0.0000035382182,0.00002464783,0.00007044735,0.93262374,0.00008857296,0.03215058,0.009644996,0.00009988468],"about_ca_topic_score_codex":0.000042208198,"about_ca_topic_score_gemma":0.0000042559736,"teacher_disagreement_score":0.9597077,"about_ca_system_score_codex":0.000020409032,"about_ca_system_score_gemma":0.000048192374,"threshold_uncertainty_score":0.5670114},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000118394506,0.00093563803,0.9945971,0.00041388202,0.0019619956,0.00031404075,0.000034064447,0.00015367477,0.0014712093],"genre_scores_gemma":[0.035320867,0.0005475106,0.9609666,0.0022380196,0.00046689133,0.000009544959,0.000030954765,0.000028819299,0.00039083554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964509,0.000033251286,0.0004484453,0.0016995703,0.0008154649,0.00055239693],"domain_scores_gemma":[0.99759966,0.00042570094,0.00023044625,0.0014413479,0.00015327826,0.00014957781],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038242852,0.0005167795,0.0005105637,0.00043931053,0.0004612192,0.000662769,0.0026793708,0.0002927771,0.000022739909],"category_scores_gemma":[0.000041711617,0.00043445633,0.00008929395,0.00030541926,0.00038916853,0.001009038,0.0049825977,0.00075702823,0.000011207524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050421227,0.000029242374,0.00020515002,0.00008902973,0.0000114185395,0.00008247031,0.00065309013,0.004433122,0.00013826496,0.02335508,0.000104491206,0.9708936],"study_design_scores_gemma":[0.00067173695,0.00017953523,0.0008262586,0.0035624246,0.00002089462,0.00007688013,8.7446557e-7,0.77171713,0.0010324102,0.20748386,0.013150523,0.0012774639],"about_ca_topic_score_codex":0.00013699128,"about_ca_topic_score_gemma":0.00003569366,"teacher_disagreement_score":0.9696161,"about_ca_system_score_codex":0.00017070332,"about_ca_system_score_gemma":0.0002591183,"threshold_uncertainty_score":0.9998107},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014875859,0.000018164643,0.5344276,0.00015535814,0.0015472639,0.00010931797,0.00021249194,0.000021255777,0.4635071],"genre_scores_gemma":[0.0024875225,0.0012414458,0.6301426,0.00037138996,0.0008383286,0.000027033606,0.00037638083,0.000022470556,0.36449283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970613,0.000008619581,0.000581374,0.00072373654,0.0013752036,0.00024975484],"domain_scores_gemma":[0.9981504,0.00027032176,0.00029876226,0.0005382964,0.0005881055,0.000154108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005259007,0.00024219751,0.00031134754,0.0003519834,0.00016074051,0.00019768233,0.0024614772,0.0001236638,0.00038692373],"category_scores_gemma":[0.0002825666,0.00020816142,0.000069923226,0.00014023768,0.0004227253,0.00077743374,0.0010548164,0.00025402984,0.00007352844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009162038,0.000021906164,0.0000032727628,0.000010602223,0.000015505802,0.000016338108,0.00003355965,0.00006417867,0.000084389125,0.9057369,0.008103546,0.0859006],"study_design_scores_gemma":[0.00067621964,0.00008719082,0.00025543798,0.00020962501,0.00002542239,0.000011553967,0.0000014659419,0.57377535,0.0001325617,0.15211563,0.272298,0.00041156932],"about_ca_topic_score_codex":0.000071544404,"about_ca_topic_score_gemma":0.000007682187,"teacher_disagreement_score":0.75362134,"about_ca_system_score_codex":0.00014460253,"about_ca_system_score_gemma":0.0007141417,"threshold_uncertainty_score":0.84885764},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020695027,0.0011145099,0.9941497,0.00044473738,0.0018285743,0.00085420907,0.000113492686,0.00013422352,0.0011536115],"genre_scores_gemma":[0.037619907,0.000067286266,0.9613218,0.00041902138,0.0003231545,0.000025418587,0.000031599273,0.000028739563,0.0001631212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951373,0.00008394906,0.0008599666,0.0018992678,0.0011930686,0.0008264734],"domain_scores_gemma":[0.9950929,0.001597392,0.00064104085,0.0019079739,0.0005540653,0.00020660151],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017655446,0.00067673466,0.0009414307,0.0009969572,0.00042315832,0.00048132677,0.0047839475,0.00030965294,0.000008148858],"category_scores_gemma":[0.00015338266,0.0005993244,0.00021574103,0.0009838421,0.0011383137,0.0005850514,0.0024192177,0.0006664081,0.0000053913063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010262848,0.000060686463,0.00004840515,0.000095891235,0.00001574863,0.00006082865,0.00028805787,0.025741816,0.00040436888,0.028571147,0.000028287888,0.9446745],"study_design_scores_gemma":[0.00042614705,0.00021262805,0.000057402,0.0015045785,0.000018015582,0.00008827072,4.1725465e-7,0.9328724,0.0049236575,0.05863158,0.00064656197,0.00061833573],"about_ca_topic_score_codex":0.00045846132,"about_ca_topic_score_gemma":0.00010312321,"teacher_disagreement_score":0.94405615,"about_ca_system_score_codex":0.00035662306,"about_ca_system_score_gemma":0.0012035782,"threshold_uncertainty_score":0.9996458},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012124749,0.00043058518,0.9850541,0.00063734315,0.0007179197,0.00058227393,0.000059417933,0.00012375596,0.00026989632],"genre_scores_gemma":[0.8565545,0.000031646592,0.1402106,0.002471876,0.00008137805,0.00030166353,0.0001926424,0.000034895555,0.00012080128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977434,0.0001523656,0.00046607564,0.0008649936,0.00014075433,0.0006324051],"domain_scores_gemma":[0.9986802,0.00014671817,0.00013272141,0.00086826127,0.000089664056,0.000082451435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034109727,0.0003065774,0.00043467933,0.00033481428,0.00013175464,0.00013624526,0.0013824776,0.00024703672,0.000006241036],"category_scores_gemma":[0.000025217774,0.00027634643,0.00013034172,0.00042906252,0.00008400528,0.00024728104,0.0009954813,0.00027641366,0.000008537359],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000603039,0.00042922114,0.0027079836,0.00017255521,0.00016538841,0.00012955065,0.00047150397,0.00078257616,0.019830307,0.066693455,0.00041526754,0.9081419],"study_design_scores_gemma":[0.0033247229,0.00016331124,0.0031804382,0.00018375099,0.000018775774,0.00002300291,0.000066890374,0.8855392,0.0103363,0.08923618,0.0072632194,0.00066422543],"about_ca_topic_score_codex":0.00027425162,"about_ca_topic_score_gemma":0.000017652697,"teacher_disagreement_score":0.9074777,"about_ca_system_score_codex":0.000052616004,"about_ca_system_score_gemma":0.000078184115,"threshold_uncertainty_score":0.9999689},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023822535,0.0006657918,0.99610627,0.00041758086,0.0003262447,0.000046076653,0.0000011089018,0.000016741293,0.000037921214],"genre_scores_gemma":[0.83890146,0.000024684061,0.16034527,0.0004765832,0.0002114021,8.707659e-7,0.0000016145784,0.0000076110755,0.000030487516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925303,0.00002480867,0.00020616993,0.00016928205,0.00012611708,0.00022057779],"domain_scores_gemma":[0.99916553,0.00018286967,0.000056430974,0.000111455985,0.000060614784,0.00042309612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013144863,0.00012064116,0.00017552622,0.0004902938,0.000111553054,0.0002319087,0.00025206798,0.000057447254,0.00000268747],"category_scores_gemma":[0.000027959419,0.000103170845,0.000033151075,0.00035992023,0.000010312622,0.00023461937,0.000041325315,0.00025964947,3.7985245e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059008303,0.000010752119,0.00062497874,0.000015365667,0.00001600178,0.00008847362,0.00007788755,0.016154043,0.00008351948,0.0061972924,0.0021325646,0.9745932],"study_design_scores_gemma":[0.00043724943,0.0001395492,0.011260822,0.00020333963,0.000005322204,0.000058557896,0.000001113008,0.9833546,0.00009336092,0.00027827293,0.0040626205,0.000105190695],"about_ca_topic_score_codex":0.00023917915,"about_ca_topic_score_gemma":0.000016814158,"teacher_disagreement_score":0.974488,"about_ca_system_score_codex":0.000061126186,"about_ca_system_score_gemma":0.0003283348,"threshold_uncertainty_score":0.42071852},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015055325,0.00017309113,0.9949198,0.0018244418,0.0006389882,0.00015920315,0.000027063348,0.00025594013,0.0004959382],"genre_scores_gemma":[0.12158421,0.0003451053,0.8739098,0.0013019845,0.000072197916,0.00008667275,0.000011344641,0.000021082918,0.0026676594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988001,0.000048406957,0.00020630285,0.0005071131,0.00017098375,0.0002670665],"domain_scores_gemma":[0.99854773,0.00021126546,0.00003813856,0.0010400212,0.00005827446,0.000104570674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014511256,0.00018269157,0.00017998871,0.00023657196,0.00037271212,0.00020953805,0.00092301256,0.00009243596,0.00003076927],"category_scores_gemma":[0.00001976364,0.00016215272,0.000064829415,0.0005001812,0.00006107454,0.00035848064,0.00006596818,0.00024154075,0.0000282875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000781968,0.00010219013,0.000037054564,0.000010131684,0.000029261397,0.0000065949575,0.00011609615,0.00016134577,0.00014265616,0.0028672405,0.00016153068,0.9963581],"study_design_scores_gemma":[0.006362795,0.0008634792,0.032439522,0.00056315144,0.00017555288,0.00015448776,0.00042716533,0.75071985,0.032547787,0.08735671,0.08623747,0.0021520539],"about_ca_topic_score_codex":0.0001303943,"about_ca_topic_score_gemma":0.000036193804,"teacher_disagreement_score":0.994206,"about_ca_system_score_codex":0.000030864896,"about_ca_system_score_gemma":0.000058810085,"threshold_uncertainty_score":0.66123956},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000410456,0.00009654065,0.9971238,0.0003151706,0.0008232952,0.00026384796,0.000017473087,0.000048094782,0.0009013399],"genre_scores_gemma":[0.0012538029,0.000021070022,0.99761844,0.0008321859,0.00002262492,0.000022155315,0.000015602689,0.0000057371553,0.00020839967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876004,0.000019331987,0.00052990037,0.0001943029,0.0001715485,0.00032489415],"domain_scores_gemma":[0.99929464,0.000121351855,0.00012890148,0.00036361872,0.00004336234,0.000048135265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005807553,0.00015264297,0.00025843075,0.0005248299,0.000047945792,0.00013696149,0.0009063955,0.000110694935,7.0297386e-7],"category_scores_gemma":[0.00008132881,0.0001367239,0.000059716207,0.0003991519,0.0000277121,0.0008504672,0.0004925845,0.00022784446,0.0000014046103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016379854,0.00044099995,0.011530325,0.0005455665,0.00014237443,0.000008151907,0.009273064,0.014725435,0.00024462468,0.045988183,0.03370809,0.8832294],"study_design_scores_gemma":[0.0012548363,0.00003003295,0.0012255146,0.00021018453,0.0000045738293,0.0000027447613,0.00047239717,0.98381263,0.00029066988,0.0040421356,0.008504615,0.00014964114],"about_ca_topic_score_codex":0.00010354333,"about_ca_topic_score_gemma":0.000043428547,"teacher_disagreement_score":0.96908724,"about_ca_system_score_codex":0.00015716512,"about_ca_system_score_gemma":0.000109914625,"threshold_uncertainty_score":0.55754393},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049364336,0.000022015254,0.9468206,0.0013466536,0.00016521347,0.0002214712,0.0000024454275,0.00011984822,0.0019373774],"genre_scores_gemma":[0.77019787,0.0000020860207,0.22938816,0.00035273164,0.000028121705,0.000011281355,9.384094e-7,0.0000031955417,0.000015587219],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807453,0.00004808922,0.00025730245,0.00071513763,0.0005512049,0.00035373506],"domain_scores_gemma":[0.9983037,0.00018883838,0.000069747795,0.0010526697,0.00020945525,0.00017559493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068713236,0.000159917,0.0002226381,0.00032487285,0.00026886634,0.00018757841,0.0027054814,0.000036941932,0.000008689479],"category_scores_gemma":[0.000032684555,0.000110875866,0.00003714319,0.0021717243,0.0010653847,0.0005794465,0.0015138412,0.000106932064,0.00001894715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021272748,0.00007197476,0.00023718312,0.0000073501287,0.0000031350824,0.000002783344,0.00020025998,0.0005845967,0.00674274,0.90954286,0.00013575387,0.08245009],"study_design_scores_gemma":[0.0003286219,0.00059950777,0.019919824,0.00016156065,0.000007978855,0.000010849079,0.0000122131005,0.90716547,0.02460145,0.046189144,0.00074538216,0.00025798724],"about_ca_topic_score_codex":0.000018377814,"about_ca_topic_score_gemma":0.0000032849396,"teacher_disagreement_score":0.90658087,"about_ca_system_score_codex":0.000039915543,"about_ca_system_score_gemma":0.00014736425,"threshold_uncertainty_score":0.5027503},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002682843,0.0003215499,0.9911181,0.0025013126,0.0028850257,0.0002782994,0.000003318085,0.0001504743,0.000059120575],"genre_scores_gemma":[0.36939546,0.000004952354,0.6293184,0.0011109833,0.00014651839,0.000015095801,0.0000012828193,0.0000043441432,0.000002930545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774754,0.000040264767,0.0002828624,0.0009408549,0.00039556576,0.000592932],"domain_scores_gemma":[0.9977962,0.0005151825,0.00007940929,0.0013816275,0.00014076055,0.00008681767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078686984,0.00019453102,0.00021787091,0.0004799993,0.0004636652,0.00058108487,0.003600434,0.000072942035,0.0000010654335],"category_scores_gemma":[0.00029736455,0.00016484893,0.00006049954,0.0021872183,0.00019448558,0.00076260534,0.0020585384,0.0001954156,0.0000024113479],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044760363,0.000033559096,0.0003004067,0.000020417,0.0000027609624,0.0000042660004,0.00028005743,0.017288322,0.0012629919,0.0030025032,0.000121755234,0.9776785],"study_design_scores_gemma":[0.00041793758,0.00005156913,0.0010963725,0.0001772012,0.0000023257928,0.000006479083,3.9621662e-7,0.9027466,0.014711753,0.07925416,0.0013432311,0.00019192956],"about_ca_topic_score_codex":0.00004081035,"about_ca_topic_score_gemma":0.000029217372,"teacher_disagreement_score":0.97748655,"about_ca_system_score_codex":0.00013124109,"about_ca_system_score_gemma":0.00036423822,"threshold_uncertainty_score":0.6722344},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034530691,0.00012627697,0.99243915,0.0015366822,0.001965544,0.00029873714,0.0000032264584,0.00014158545,0.00003572655],"genre_scores_gemma":[0.5172762,9.132792e-7,0.4811785,0.0014329436,0.00008732613,0.00001534684,0.0000024571007,0.0000042589104,0.0000020557923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977234,0.000034626253,0.0002834685,0.00095195445,0.00040973967,0.00059680955],"domain_scores_gemma":[0.9980396,0.00074705674,0.00009106751,0.00089768186,0.0001401976,0.00008438219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000901477,0.00020588162,0.00022180958,0.0005510205,0.0005233032,0.00066130445,0.0024832243,0.000084563966,0.0000038430185],"category_scores_gemma":[0.00017736653,0.00017509812,0.00007254887,0.0022522386,0.00019369418,0.0008633942,0.00092895667,0.0002138757,0.0000040607297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060084913,0.00004661294,0.0016421321,0.000030919826,0.000003348865,0.000011047624,0.00019181723,0.05855588,0.001393781,0.0016503695,0.00007293418,0.93639517],"study_design_scores_gemma":[0.00040482232,0.000045896133,0.0035191607,0.00019562973,0.0000024949163,0.000005454999,2.478287e-7,0.95974475,0.026151713,0.00929328,0.00042895888,0.00020760985],"about_ca_topic_score_codex":0.000042943928,"about_ca_topic_score_gemma":0.000027964845,"teacher_disagreement_score":0.93618757,"about_ca_system_score_codex":0.00012831006,"about_ca_system_score_gemma":0.0003573012,"threshold_uncertainty_score":0.71402943},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024188662,0.00047752788,0.9942804,0.0002130333,0.0015502436,0.000330224,0.000012035069,0.00011392318,0.0027807332],"genre_scores_gemma":[0.29891407,0.00002791167,0.7001234,0.00043099013,0.00020112409,0.0000053588037,0.000015794947,0.000021851854,0.0002594835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996607,0.000029384926,0.0006420681,0.0012534913,0.0010258518,0.00044221466],"domain_scores_gemma":[0.9975854,0.00039083525,0.00041131012,0.0011467509,0.00035416867,0.000111523936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065410946,0.0004079623,0.00054943917,0.0009955453,0.00017519132,0.00022308543,0.0027919416,0.00025403744,0.000007130056],"category_scores_gemma":[0.000065503766,0.0003679691,0.00013220105,0.00080125825,0.000451097,0.00021240015,0.0019120467,0.0005254604,0.000012092824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058586184,0.00004255157,0.0000169021,0.0000744811,0.000008132932,0.00002521585,0.00026305602,0.17633757,0.0001708011,0.02284044,0.00004340306,0.8001716],"study_design_scores_gemma":[0.00028444448,0.000091615606,0.00019271148,0.0007997686,0.000006773178,0.000011522691,8.266627e-8,0.9558568,0.0018952874,0.04013429,0.00037148068,0.00035519843],"about_ca_topic_score_codex":0.00003430232,"about_ca_topic_score_gemma":0.0000085344345,"teacher_disagreement_score":0.79981637,"about_ca_system_score_codex":0.00018759561,"about_ca_system_score_gemma":0.0005912725,"threshold_uncertainty_score":0.9998772},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013028789,0.0007064042,0.9435595,0.031006262,0.001129048,0.00038646828,0.00000356071,0.000055444216,0.010124514],"genre_scores_gemma":[0.7211194,0.0000915039,0.27709827,0.0011916144,0.00022514761,0.000012123303,7.420972e-7,0.000008480396,0.00025271755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979128,0.00046971405,0.0006657202,0.00024198923,0.00043129586,0.0002784367],"domain_scores_gemma":[0.99778944,0.00067452126,0.00024268894,0.0007928062,0.00036931087,0.00013121022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030157482,0.00013282763,0.00026486264,0.00004472778,0.0002920818,0.00029090815,0.001838898,0.00007645435,0.00003304627],"category_scores_gemma":[0.0006015617,0.00006876932,0.00018783986,0.0003041624,0.0004968799,0.00035094254,0.0006650407,0.00039222464,0.0000058352693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011897879,0.00011475046,0.00012680364,0.000018675384,0.000024863793,0.000003991922,0.000054769043,0.000060377446,0.0001351247,0.97611725,0.008183372,0.015041041],"study_design_scores_gemma":[0.00041260885,0.00013211949,0.0007422201,0.000057261313,0.000016246146,0.000025271787,0.000006292265,0.019466141,0.0006306789,0.94716877,0.031260174,0.00008219803],"about_ca_topic_score_codex":0.0000066006114,"about_ca_topic_score_gemma":0.0000016975733,"teacher_disagreement_score":0.7080906,"about_ca_system_score_codex":0.00006579835,"about_ca_system_score_gemma":0.00019436516,"threshold_uncertainty_score":0.34171608},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002657776,0.00005391188,0.9961378,0.0017893532,0.00016974342,0.0005837603,0.00070221425,0.00004727078,0.00025014373],"genre_scores_gemma":[0.0013129596,0.000053257645,0.9950843,0.0030780532,0.00001561169,0.000077620374,0.00031947,0.0000060611897,0.000052669875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827564,0.00002402257,0.00059670134,0.0003077715,0.0003297539,0.00046608484],"domain_scores_gemma":[0.9988258,0.00022910294,0.00011459903,0.0006876754,0.00006820758,0.00007465619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007667505,0.00018420983,0.0002461039,0.00029387462,0.00011631446,0.00022656294,0.0011135468,0.000112655645,0.000003019354],"category_scores_gemma":[0.00011292184,0.00017441268,0.000045498673,0.0006755071,0.00006600596,0.0011518681,0.0010154931,0.00022771797,0.000007135857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018158358,0.00039858723,0.00020927226,0.0003835347,0.000020863237,0.000029249228,0.0023148293,0.0018421368,0.00018691228,0.026345773,0.024587559,0.9436631],"study_design_scores_gemma":[0.0011111569,0.000039142295,0.0005156387,0.00027858943,0.0000028432491,0.000006593199,0.0001019787,0.9767326,0.0007929749,0.0018150808,0.018406326,0.00019704168],"about_ca_topic_score_codex":0.0005062384,"about_ca_topic_score_gemma":0.000039358776,"teacher_disagreement_score":0.9748905,"about_ca_system_score_codex":0.0002005111,"about_ca_system_score_gemma":0.0002475402,"threshold_uncertainty_score":0.7112343},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003149491,0.000048117672,0.9905467,0.001593449,0.00061871746,0.00029604332,0.0000061347305,0.00015564609,0.0035856948],"genre_scores_gemma":[0.34540072,0.0000037427108,0.6506708,0.0017768311,0.00013802949,0.000015533838,0.000017675173,0.000008947723,0.0019676844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988031,0.000035643898,0.00021369384,0.00044458077,0.00021950468,0.00028350277],"domain_scores_gemma":[0.9990565,0.00025311176,0.000039411778,0.00046607378,0.000099667166,0.000085221225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002617092,0.00012349318,0.00015640407,0.0001145758,0.00023452345,0.00017379032,0.00064234773,0.000064495274,0.000018665194],"category_scores_gemma":[0.000083757186,0.00009551745,0.00008502416,0.00043376238,0.000043252614,0.00018027186,0.0005845347,0.00014512427,0.000017030714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009120698,0.0002196846,0.00011044207,0.00003156087,0.00003812281,0.000010733349,0.0003062096,0.001260375,0.0016942573,0.7823303,0.013709362,0.20019774],"study_design_scores_gemma":[0.0004247598,0.000066512635,0.0004468364,0.000032090204,0.000005121263,0.000002704876,0.000009121642,0.9671682,0.005167347,0.01637109,0.010178774,0.00012744876],"about_ca_topic_score_codex":0.0000115550665,"about_ca_topic_score_gemma":0.000001956807,"teacher_disagreement_score":0.9659078,"about_ca_system_score_codex":0.00005255988,"about_ca_system_score_gemma":0.000078642246,"threshold_uncertainty_score":0.38950887},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6565502,0.003559729,0.2688667,0.038921095,0.0044299676,0.011770957,0.000198728,0.008548141,0.0071544563],"genre_scores_gemma":[0.50256157,0.00000756883,0.49527925,0.00050182414,0.00015152512,0.00028030854,0.000013353904,0.000018469007,0.0011861203],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99899924,0.0000060827183,0.00021707792,0.0003351557,0.0002222823,0.00022016487],"domain_scores_gemma":[0.99896985,0.000062508894,0.00018625191,0.00054438424,0.00020840815,0.000028591627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003197208,0.00013129014,0.00015125117,0.000090630274,0.00021020483,0.00023225167,0.00221354,0.00006799896,0.0000011720797],"category_scores_gemma":[0.0008449892,0.00008665887,0.000079368634,0.00039534026,0.000040895364,0.00032271567,0.0009538286,0.000093125374,0.0000010906545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004727316,0.00037689446,0.0009941664,0.0005102969,0.00009479608,8.00859e-7,0.0014163852,0.000056028675,0.06628951,0.17179449,0.08059334,0.67782605],"study_design_scores_gemma":[0.0011700839,0.00036287415,0.0015896271,0.00066950114,0.0000583426,0.0000066641364,0.00039822003,0.34485388,0.5750922,0.0068063796,0.068589754,0.0004025074],"about_ca_topic_score_codex":0.00001396631,"about_ca_topic_score_gemma":0.000001781982,"teacher_disagreement_score":0.67742354,"about_ca_system_score_codex":0.000034745153,"about_ca_system_score_gemma":0.000040270923,"threshold_uncertainty_score":0.41133448},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087573834,0.0023373838,0.9021867,0.0011945656,0.0021877738,0.00033627835,0.00044463202,0.0006150704,0.0031237896],"genre_scores_gemma":[0.867324,0.00046612104,0.12626971,0.0013761078,0.00049466576,0.0001407878,0.0012168349,0.000041303418,0.0026704434],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755174,0.0001488109,0.00045790017,0.0010655023,0.00034635753,0.00042970415],"domain_scores_gemma":[0.99735814,0.00022848604,0.00025169857,0.001867043,0.00012666467,0.00016795658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017777216,0.00040412162,0.00044860115,0.00015873135,0.00044666624,0.00045060628,0.0024763658,0.00028602412,0.000036261186],"category_scores_gemma":[0.000032368036,0.00038039105,0.00018913613,0.00025735807,0.00007760669,0.00045415305,0.005180586,0.0007751523,0.00008491801],"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":[0.00006233098,0.0031796126,0.18929306,0.0009202671,0.0007843763,0.0003672098,0.0033469796,0.0098455055,0.019547392,0.017333813,0.56371605,0.1916034],"study_design_scores_gemma":[0.0019829567,0.00020710328,0.14410488,0.0046276203,0.0002188415,0.000032770036,0.00009530614,0.6068185,0.013219152,0.0099554425,0.21524246,0.0034949442],"about_ca_topic_score_codex":0.0002894177,"about_ca_topic_score_gemma":0.0000140953725,"teacher_disagreement_score":0.77975017,"about_ca_system_score_codex":0.00008620727,"about_ca_system_score_gemma":0.00021161228,"threshold_uncertainty_score":0.9998648},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09458575,0.000046875844,0.9021638,0.0015858401,0.00055246544,0.0006852169,0.000023428003,0.000018017503,0.0003385857],"genre_scores_gemma":[0.788037,0.000006129798,0.21174346,0.00008083709,0.000023270553,0.000067226334,0.0000048680627,0.000002091833,0.000035121775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836195,0.0007355285,0.00037763471,0.00030071952,0.00006581115,0.00015839026],"domain_scores_gemma":[0.98956054,0.009690873,0.00017295247,0.0004798859,0.00007793066,0.000017842187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045791804,0.0000926285,0.00025523486,0.000019692709,0.0004764956,0.000024050289,0.00046105185,0.000060275976,0.00000200079],"category_scores_gemma":[0.0014229375,0.00004903308,0.000054991753,0.00046403595,0.00042367564,0.000028852266,0.0007775724,0.0002164291,2.3112894e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018666897,0.00007649199,0.013076994,0.00006446045,0.00003236436,3.5042703e-8,0.00058563973,0.00054861937,0.00024925196,0.53130627,0.00062375393,0.45324948],"study_design_scores_gemma":[0.00084872736,0.000029904802,0.11869928,0.00010581727,0.00004321892,0.000007139152,0.000101402744,0.53014165,0.0014483205,0.3471793,0.0012846604,0.00011059791],"about_ca_topic_score_codex":0.0002008072,"about_ca_topic_score_gemma":0.00003778546,"teacher_disagreement_score":0.6934513,"about_ca_system_score_codex":0.000024414065,"about_ca_system_score_gemma":0.000054611563,"threshold_uncertainty_score":0.3664867},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058554425,0.0018257049,0.9851064,0.00106677,0.0018367213,0.001541758,0.00008312722,0.00017818152,0.002505893],"genre_scores_gemma":[0.7250403,0.00015995748,0.2530662,0.00044486712,0.00040422572,0.00014663461,0.000058460148,0.0000529914,0.020626344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961357,0.000106365,0.00109713,0.0013949001,0.0005730693,0.0006928229],"domain_scores_gemma":[0.9960888,0.00076886854,0.00039635718,0.001966042,0.00059574755,0.00018416905],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004953847,0.0005089637,0.0008132213,0.00034389264,0.00046333455,0.00027557684,0.0020148722,0.0001910245,0.0002453486],"category_scores_gemma":[0.00014507458,0.00041314407,0.0002278346,0.0009029053,0.00018035067,0.0010625882,0.0021792462,0.00018777428,0.000030541712],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017146807,0.0011139985,0.00023094055,0.0006832139,0.00009172495,0.0000067862966,0.00052441796,0.00017177667,0.23448285,0.0034460253,0.029390993,0.7296858],"study_design_scores_gemma":[0.001045393,0.00021223068,0.0005199772,0.0010133657,0.000032394066,0.0000053059334,0.0000267581,0.69916546,0.280194,0.00068487204,0.016723312,0.00037692464],"about_ca_topic_score_codex":0.00010124098,"about_ca_topic_score_gemma":0.0000024189285,"teacher_disagreement_score":0.7320402,"about_ca_system_score_codex":0.00007401859,"about_ca_system_score_gemma":0.00027053573,"threshold_uncertainty_score":0.99983203},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011794138,0.015400844,0.9396143,0.006594948,0.0064099752,0.0010253513,0.00010746676,0.000878113,0.018174848],"genre_scores_gemma":[0.8042926,0.014692803,0.107970506,0.009770993,0.0051107616,0.00079166587,0.00070034934,0.00016229025,0.056508023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794054,0.00018161543,0.00037261844,0.0007617014,0.00041453092,0.00032898795],"domain_scores_gemma":[0.9965335,0.00026033216,0.00021566337,0.0026876188,0.00020968616,0.000093203394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000694492,0.00026927463,0.00029570932,0.00007774159,0.0004426884,0.00038626775,0.0034305328,0.00021589824,0.0000112924945],"category_scores_gemma":[0.00022772739,0.00017620274,0.00016404681,0.0003350209,0.00005695211,0.0001987807,0.0052506975,0.0007576436,0.00013633404],"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":[0.00005946746,0.00022135777,0.0409036,0.0003299626,0.00038344992,0.00010546413,0.00057205843,0.0002520979,0.00022375696,0.044514596,0.25120407,0.6612301],"study_design_scores_gemma":[0.0006336731,0.00005110496,0.07436016,0.0012748892,0.00006748288,0.000008154303,0.00001805033,0.04136221,0.0011214224,0.013157833,0.86704695,0.0008980535],"about_ca_topic_score_codex":0.000068781934,"about_ca_topic_score_gemma":0.0000050235376,"teacher_disagreement_score":0.8316438,"about_ca_system_score_codex":0.000057095895,"about_ca_system_score_gemma":0.00028450586,"threshold_uncertainty_score":0.7185339},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19163358,0.00042023367,0.7955685,0.0015119375,0.00079436373,0.00008391623,0.00000236905,0.00023398922,0.009751072],"genre_scores_gemma":[0.9736782,0.000026036456,0.023310643,0.00072126294,0.000067791465,0.0000085185,0.0000029159376,0.000004984119,0.0021796972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99914384,0.000031563854,0.00013960099,0.00033580163,0.0001346977,0.00021450031],"domain_scores_gemma":[0.9992632,0.00005903822,0.000041846306,0.0005338932,0.000048828893,0.000053185966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012437032,0.00010022411,0.000109964356,0.000082820465,0.00017323061,0.00006566411,0.0007651925,0.000040163857,0.000019218245],"category_scores_gemma":[0.00003312587,0.00008596951,0.000040661922,0.00037040515,0.000025396901,0.0004834297,0.00062710885,0.00011500562,0.00017611256],"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":[0.000041775907,0.00031403592,0.26685953,0.000060805516,0.00012998802,0.00015642321,0.0010898219,0.0002952026,0.015787384,0.34041312,0.054131746,0.32072017],"study_design_scores_gemma":[0.0008647979,0.00010381996,0.5935192,0.0002501369,0.000017087756,0.000008523148,0.000085139865,0.104532324,0.018158255,0.0059998496,0.2759334,0.0005274546],"about_ca_topic_score_codex":0.000053714193,"about_ca_topic_score_gemma":0.0000029738305,"teacher_disagreement_score":0.7820446,"about_ca_system_score_codex":0.000024245232,"about_ca_system_score_gemma":0.000058935762,"threshold_uncertainty_score":0.35057348},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010677862,0.000019065046,0.9867974,0.0014787116,0.0003235699,0.000112351096,0.000045844856,0.000012385998,0.0005327963],"genre_scores_gemma":[0.9739582,0.000015114386,0.025143651,0.0008329894,0.000003779973,0.0000046277178,0.0000014487224,0.0000010239054,0.00003916634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994707,0.000048004484,0.00024445273,0.00007492177,0.00009168833,0.000070226524],"domain_scores_gemma":[0.99838096,0.0012186045,0.00010618407,0.00021697342,0.00006398324,0.000013297848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013396695,0.000070624665,0.00009899061,0.00005484528,0.00017894896,0.00001292659,0.00034301548,0.000053069234,0.000008091982],"category_scores_gemma":[0.000016190861,0.000035487785,0.000052404346,0.00028116105,0.00016274073,0.000079874946,0.000010934941,0.000121509554,0.0000019310253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007905065,0.0003121581,0.00013328076,0.000097419535,0.00015761642,1.8943729e-7,0.00083464145,0.053638507,0.00024469724,0.6291762,0.0012007136,0.31412554],"study_design_scores_gemma":[0.00043554459,0.00018201195,0.003781653,0.00013078275,0.000016536022,0.000004356755,0.00006494506,0.908143,0.004333616,0.08251711,0.00030127133,0.00008920098],"about_ca_topic_score_codex":0.0000048364714,"about_ca_topic_score_gemma":0.0000012327239,"teacher_disagreement_score":0.9632803,"about_ca_system_score_codex":0.00000643134,"about_ca_system_score_gemma":0.00006544284,"threshold_uncertainty_score":0.144715},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1231559,0.0012225289,0.86524683,0.0018197165,0.000956004,0.00024594736,0.00005768057,0.0005658507,0.006729566],"genre_scores_gemma":[0.95184463,0.00015968332,0.043316845,0.0004805669,0.00053983164,0.00003376502,0.00010616764,0.000023626984,0.0034948858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842185,0.00004527776,0.00023010971,0.00048883545,0.00046576443,0.0003481373],"domain_scores_gemma":[0.99830747,0.000086352215,0.000052900254,0.0013028508,0.000036904068,0.00021355375],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036521017,0.00013127415,0.00014702938,0.0003339876,0.00029004275,0.00014852082,0.0012982961,0.000071319555,0.0008062768],"category_scores_gemma":[0.00008513081,0.00011003173,0.00007209666,0.0019702169,0.000050296436,0.00018868162,0.00030373453,0.00015409704,0.0009209674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001245823,0.00029472768,0.000120373705,0.000007451303,0.000023947136,0.00003067259,0.00013067784,0.0010405403,0.0005830864,0.004892143,0.026669832,0.9661941],"study_design_scores_gemma":[0.0014480294,0.000226515,0.01951621,0.00007752608,0.000027824115,0.00016676431,0.000036004778,0.32816195,0.0028996991,0.0019396679,0.64477634,0.0007234486],"about_ca_topic_score_codex":0.00010156158,"about_ca_topic_score_gemma":0.0000018521346,"teacher_disagreement_score":0.9654706,"about_ca_system_score_codex":0.000034714423,"about_ca_system_score_gemma":0.000048545207,"threshold_uncertainty_score":0.99985695},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004267791,0.00034327604,0.9962614,0.0006625506,0.00061989104,0.00025655245,0.000006701364,0.000048014106,0.0013747951],"genre_scores_gemma":[0.90581584,0.00010657665,0.091292806,0.002033523,0.0004237458,0.000007855318,0.0000042300508,0.000033315824,0.0002821063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973719,0.000054805416,0.00039567958,0.00097527966,0.0008533995,0.00034894893],"domain_scores_gemma":[0.9966368,0.0013582933,0.000324003,0.0014533602,0.00012693099,0.0001006298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007761458,0.00037081496,0.00044658783,0.00044510642,0.0002414686,0.00026765568,0.002772207,0.00021335075,0.000014677552],"category_scores_gemma":[0.000095697374,0.00022091363,0.000080303274,0.0003720115,0.00066366943,0.00021877258,0.0013073668,0.0005237896,0.000008017071],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010676325,0.000023029914,0.000043302858,0.000017228058,0.000008232997,0.000015031438,0.00033528497,0.0031520776,0.000043140775,0.16330026,0.00009774234,0.832954],"study_design_scores_gemma":[0.00030063145,0.00029128807,0.0005668211,0.00036981565,0.000005647831,0.000016949545,1.07176625e-7,0.61414635,0.0006941136,0.3808333,0.0023901367,0.0003848366],"about_ca_topic_score_codex":0.000034099536,"about_ca_topic_score_gemma":0.000034880726,"teacher_disagreement_score":0.9053891,"about_ca_system_score_codex":0.00005083452,"about_ca_system_score_gemma":0.00016982928,"threshold_uncertainty_score":0.90085965},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9326764,0.0018343197,0.06270368,0.00087253423,0.0010873048,0.00015298293,8.490688e-7,0.0002759136,0.00039602225],"genre_scores_gemma":[0.9179614,0.000002746962,0.08160036,0.00023164868,0.0001510391,6.121592e-7,0.0000017859958,0.000003957327,0.000046457426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988759,0.00007647663,0.00016006223,0.0003678093,0.00030211714,0.0002175968],"domain_scores_gemma":[0.9992393,0.000059401227,0.0000611226,0.0003467572,0.00015189327,0.00014150229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040608074,0.0001200866,0.00013794008,0.000039976432,0.00020087442,0.00019813259,0.00049744715,0.000056660967,0.0000010627799],"category_scores_gemma":[0.00012733761,0.0000849985,0.000029643314,0.00019389113,0.000052053667,0.0005755968,0.0010770321,0.0002328026,0.000013331658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008250624,0.00013728492,0.035112552,0.00011800654,0.00003936143,0.0000763161,0.0052871443,0.0005304534,0.002854027,0.010314058,0.02465542,0.9207929],"study_design_scores_gemma":[0.00048741224,0.000073028736,0.007981049,0.00006359043,0.0000032821713,0.000056451947,0.00010637172,0.9846503,0.0010196951,0.00144558,0.003888374,0.00022484134],"about_ca_topic_score_codex":0.000044428296,"about_ca_topic_score_gemma":0.0000024895533,"teacher_disagreement_score":0.9841199,"about_ca_system_score_codex":0.000041228544,"about_ca_system_score_gemma":0.00005473102,"threshold_uncertainty_score":0.34661382},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032908563,0.0005577309,0.9962597,0.0010700889,0.00067913294,0.00051074615,0.000035622466,0.00008051743,0.00047738428],"genre_scores_gemma":[0.10802205,0.0001541265,0.8906265,0.00023075196,0.0005534144,0.000012909605,0.0000218481,0.00003332393,0.00034507643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669397,0.00004519737,0.00051782373,0.001468218,0.00078910217,0.00048571787],"domain_scores_gemma":[0.99631333,0.0015114294,0.00046934138,0.001293489,0.00024505932,0.00016736696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007675657,0.00041863363,0.0006681516,0.0004844724,0.00021117339,0.00028265294,0.0021373646,0.0002858846,0.0000036852277],"category_scores_gemma":[0.00018058762,0.0003726883,0.00009284394,0.00041837507,0.00068831793,0.0006852791,0.0014050408,0.00040172975,0.0000031899535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013167076,0.00002497505,0.00054017024,0.00022109888,0.000017266186,0.0000093633425,0.0004984555,0.00177075,0.000850487,0.066765286,0.00016085795,0.9291281],"study_design_scores_gemma":[0.0008442747,0.0005928804,0.0014801244,0.0010300012,0.000034278033,0.000033716293,6.341209e-7,0.7421303,0.009709602,0.23949297,0.0037787622,0.000872482],"about_ca_topic_score_codex":0.000042292337,"about_ca_topic_score_gemma":0.000012683943,"teacher_disagreement_score":0.9282556,"about_ca_system_score_codex":0.000084772415,"about_ca_system_score_gemma":0.00029090364,"threshold_uncertainty_score":0.9998725},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000119205564,0.0023967063,0.9936188,0.0004123246,0.0012415419,0.00020150587,0.000006865202,0.00012320763,0.0018798333],"genre_scores_gemma":[0.13710904,0.00032922745,0.8595389,0.0014177227,0.001286366,0.0000065780832,0.000009347321,0.000042984593,0.00025984106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970026,0.000023127488,0.00038911976,0.001208782,0.00072565145,0.0006507025],"domain_scores_gemma":[0.9979837,0.000317626,0.00024365485,0.0010882902,0.00011693173,0.00024982382],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006506875,0.0004461964,0.00040842796,0.0004179769,0.0003625145,0.0007965066,0.0020578173,0.00035031428,0.000023443787],"category_scores_gemma":[0.000051328727,0.0003849706,0.000061247614,0.00028444792,0.00037880737,0.0013015389,0.0026588305,0.00096905604,0.00002987336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012315832,0.000011705255,0.00007923717,0.00001958143,0.0000038627004,0.000026197526,0.00034131217,0.0005406046,0.000114696835,0.03301488,0.00001653408,0.96583015],"study_design_scores_gemma":[0.0005163655,0.00023641158,0.0011081786,0.00089403254,0.000016114285,0.00032298337,2.9758132e-7,0.83258694,0.0017478754,0.14485575,0.016099727,0.0016153334],"about_ca_topic_score_codex":0.000035961446,"about_ca_topic_score_gemma":0.000013787127,"teacher_disagreement_score":0.9642148,"about_ca_system_score_codex":0.00010909781,"about_ca_system_score_gemma":0.00021426173,"threshold_uncertainty_score":0.9998602},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000949248,0.00057244644,0.288631,0.000120481986,0.0019804465,0.00021946146,0.00023798626,0.000110582805,0.7081181],"genre_scores_gemma":[0.00063590007,0.005883337,0.12538028,0.000106583095,0.001185292,0.000025367848,0.000103144615,0.00012358249,0.8665565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997797,0.000026089217,0.0007555018,0.00059457816,0.00056803576,0.00025876221],"domain_scores_gemma":[0.99741405,0.00016875134,0.0006801044,0.0012839852,0.000305157,0.00014797541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017603938,0.0003754862,0.00062857737,0.00037637804,0.00006125304,0.000020983607,0.0014689378,0.00033956527,0.00033125386],"category_scores_gemma":[0.000042317744,0.00029562705,0.00026516934,0.00010076174,0.00020288274,0.00044632968,0.00088978384,0.00030692952,0.00010508174],"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":[0.000014362479,0.0000993839,0.000019467916,0.00012896789,0.00019541645,0.000039729755,0.00053826516,0.0000030403835,0.00011731783,0.23778592,0.025643107,0.73541504],"study_design_scores_gemma":[0.00081089,0.0004376628,0.00018738607,0.0013490648,0.00007689465,0.000042529562,0.000011704425,0.0043569733,0.00057382265,0.07021912,0.9210374,0.00089656113],"about_ca_topic_score_codex":0.000051833707,"about_ca_topic_score_gemma":0.000010076391,"teacher_disagreement_score":0.89539427,"about_ca_system_score_codex":0.0000541101,"about_ca_system_score_gemma":0.00019995942,"threshold_uncertainty_score":0.9999496},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009804719,0.0779752,0.6393825,0.00035170547,0.0024378255,0.00041110683,0.00015954311,0.00048096312,0.27870315],"genre_scores_gemma":[0.06434829,0.2461267,0.4350603,0.00454645,0.037468065,0.0005952168,0.008434861,0.0010480308,0.20237212],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829316,0.000022793458,0.00040547908,0.0007023356,0.00031676152,0.00025946432],"domain_scores_gemma":[0.9991329,0.000035895806,0.00032090483,0.0003415777,0.0000935998,0.00007517885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021807478,0.0003380697,0.00035274055,0.0003986481,0.00010361993,0.00015263267,0.0003600958,0.0002969278,0.000042228367],"category_scores_gemma":[0.0000027818,0.00030536528,0.000050284983,0.000096509866,0.000052443404,0.0015788715,0.00018559737,0.00039711263,0.000040840274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004823209,0.00000920671,0.00002421143,0.00030330918,0.000003994069,0.000072766125,0.00008940749,9.175815e-7,0.0000019587205,0.0009462206,0.000046208406,0.99849695],"study_design_scores_gemma":[0.0012637716,0.00029173415,0.00071521796,0.010341598,0.00006537873,0.0004739403,0.0001414366,0.016542641,0.00022686482,0.02401638,0.9438824,0.0020386428],"about_ca_topic_score_codex":0.000016836859,"about_ca_topic_score_gemma":0.000069843896,"teacher_disagreement_score":0.99645835,"about_ca_system_score_codex":0.00008529374,"about_ca_system_score_gemma":0.000019652989,"threshold_uncertainty_score":0.99993986},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08137037,0.00013163062,0.9141344,0.00049000175,0.0004661355,0.0013037893,0.00047812867,0.00011895889,0.0015066171],"genre_scores_gemma":[0.7519723,0.00009602569,0.2461034,0.0007008699,0.000042934622,0.00012683161,0.00082247896,0.000016699905,0.000118439464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803936,0.000038321,0.00093487435,0.0003013831,0.0003143481,0.00037170094],"domain_scores_gemma":[0.998351,0.00013409586,0.00035265728,0.0008022512,0.0002619436,0.0000980894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048056978,0.00024114978,0.00035294727,0.00019400094,0.00023889261,0.0002057425,0.00093599875,0.000106213556,0.00000984625],"category_scores_gemma":[0.00005318853,0.00021016756,0.00008268636,0.00037618048,0.0001741389,0.0017003098,0.0008540798,0.00017440227,0.0000040222326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041029448,0.0030691673,0.19306614,0.013319795,0.0006486025,0.000008437158,0.028819935,0.0020371429,0.0011876186,0.35799795,0.020739038,0.37869588],"study_design_scores_gemma":[0.0046377517,0.0004272969,0.01729448,0.00070580794,0.000057009747,0.00002849817,0.0008756571,0.91286296,0.0036395683,0.012064107,0.046703536,0.0007033584],"about_ca_topic_score_codex":0.00005813863,"about_ca_topic_score_gemma":0.000016509957,"teacher_disagreement_score":0.9108258,"about_ca_system_score_codex":0.00006402258,"about_ca_system_score_gemma":0.000084922445,"threshold_uncertainty_score":0.85703844},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028047625,0.000069151756,0.98985946,0.0015992522,0.0012262376,0.002584314,0.00063461025,0.00061854074,0.00060368166],"genre_scores_gemma":[0.11691121,0.00041691822,0.8684203,0.0026545373,0.0012074802,0.0040497375,0.004249345,0.00017093422,0.0019195274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971327,0.000031469088,0.0009238931,0.0003972519,0.00063278235,0.0008818778],"domain_scores_gemma":[0.9972912,0.00048063637,0.00044183937,0.0012465934,0.00037129837,0.00016839949],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012385717,0.00037167742,0.0003373098,0.00023010289,0.00092127966,0.00087526406,0.0023204363,0.00018330189,0.000008134223],"category_scores_gemma":[0.00010938151,0.00025787504,0.00023066177,0.0007826544,0.00012279907,0.0028247978,0.00081906235,0.00030452327,0.00021072986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016915215,0.0005351896,0.0011726483,0.0020847942,0.00038785188,0.000015011273,0.021364275,0.004703751,0.00034434258,0.1726294,0.10363042,0.6929632],"study_design_scores_gemma":[0.0013506125,0.00017419814,0.00058809586,0.00010911222,0.00002250209,0.00003269599,0.00046740976,0.8827728,0.00061393843,0.0053990087,0.10807515,0.0003944827],"about_ca_topic_score_codex":0.000024316068,"about_ca_topic_score_gemma":0.0000088493725,"teacher_disagreement_score":0.87806904,"about_ca_system_score_codex":0.000094062954,"about_ca_system_score_gemma":0.00010589864,"threshold_uncertainty_score":0.99998736},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.7072215e-7,0.0034692613,0.21969749,0.00055720896,0.0016480313,0.00024626107,0.773793,0.00016310587,0.00042548156],"genre_scores_gemma":[6.586246e-8,0.0049375007,0.119749755,0.0010092459,0.00041189208,0.000031601412,0.8706271,0.000011367931,0.003221461],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953143,0.0007590145,0.00056759577,0.002012799,0.00071371533,0.0006326023],"domain_scores_gemma":[0.985053,0.0010289054,0.00033114207,0.013249494,0.00015039102,0.00018708788],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0024819914,0.0005883303,0.0006867391,0.00024101562,0.0002097812,0.00047304094,0.018817438,0.0010735079,0.000104310515],"category_scores_gemma":[0.0012617745,0.0005391661,0.00009935671,0.0012217317,0.00009136997,0.0014487329,0.009529412,0.0024098551,0.00025292783],"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":[0.000004542348,0.00008948399,0.0000014705824,0.00023560185,0.000038678343,0.000049618295,0.000008593324,0.0000028248005,0.000003479114,0.00014969,0.93109626,0.06831977],"study_design_scores_gemma":[0.00026132018,0.000028211107,0.000016417418,0.0005112988,0.00004008883,0.000015890613,0.0000025748436,0.0074370974,0.000021499694,0.00060537277,0.9904901,0.00057013],"about_ca_topic_score_codex":0.0006308676,"about_ca_topic_score_gemma":0.00006109971,"teacher_disagreement_score":0.09994773,"about_ca_system_score_codex":0.0001841259,"about_ca_system_score_gemma":0.00091517146,"threshold_uncertainty_score":0.99989164},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1785238,0.0016639349,0.8002672,0.0036635858,0.0028037585,0.0009303421,0.0004394231,0.0017954665,0.009912441],"genre_scores_gemma":[0.9850178,0.008622096,0.0028764498,0.00034167024,0.00024378291,7.520098e-7,0.00010890097,0.000030892777,0.0027576608],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706453,0.00023693568,0.00027726145,0.0011100929,0.0006659278,0.0006452333],"domain_scores_gemma":[0.9985066,0.00025329797,0.00012697278,0.0006169014,0.00012981938,0.00036643088],"candidate_categories":["metaepi_narrow","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.000287468,0.00037042386,0.000357868,0.030023195,0.00040087738,0.00018788537,0.001924029,0.00042532737,0.00011379789],"category_scores_gemma":[0.0000058683745,0.00041155124,0.00036023618,0.030691227,0.00020047472,0.00337722,0.0014303935,0.0013855938,0.00008120365],"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":[0.00074225926,0.0014422463,0.43359092,0.00043896187,0.0014202255,0.007477392,0.0035432104,0.0012364888,0.005288955,0.2675702,0.2123872,0.06486194],"study_design_scores_gemma":[0.0015027811,0.00007180739,0.22683434,0.00046796259,0.000083763385,0.000029876708,0.00043281462,0.029558998,0.000088782705,0.0011499681,0.7390319,0.0007469741],"about_ca_topic_score_codex":0.00027730587,"about_ca_topic_score_gemma":0.000013958491,"teacher_disagreement_score":0.806494,"about_ca_system_score_codex":0.00017020297,"about_ca_system_score_gemma":0.000133613,"threshold_uncertainty_score":0.99983364},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005625027,0.00019199456,0.9871271,0.00045253773,0.0016481456,0.0006293294,0.0034723224,0.00021901214,0.000634487],"genre_scores_gemma":[0.17395198,0.000121326724,0.8083318,0.0025112291,0.0008594422,0.0001714857,0.013543611,0.00008002535,0.00042914017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99725515,0.00003207799,0.0009191504,0.00052450027,0.00053150934,0.00073763786],"domain_scores_gemma":[0.9965469,0.00026049805,0.00037598258,0.0021413984,0.00048350435,0.00019166998],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000532137,0.00035466516,0.00044263367,0.00010348221,0.0006075731,0.0010920665,0.0025535948,0.00019187294,0.000021608937],"category_scores_gemma":[0.00029653896,0.00029868455,0.00014946065,0.00029529905,0.00008149857,0.0037401395,0.0024978698,0.00030176455,0.00002412236],"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":[0.00021707412,0.0007580242,0.0037809638,0.0025293361,0.00052853714,0.00007967753,0.010772221,0.00035054816,0.00046666726,0.5549714,0.23603578,0.1895098],"study_design_scores_gemma":[0.001742684,0.00011200756,0.0004740163,0.00007153949,0.000032313637,0.00013232924,0.00073658,0.41177815,0.00092911994,0.008097453,0.5753491,0.0005446976],"about_ca_topic_score_codex":0.000020895845,"about_ca_topic_score_gemma":0.00002070149,"teacher_disagreement_score":0.5468739,"about_ca_system_score_codex":0.00006976259,"about_ca_system_score_gemma":0.00025003566,"threshold_uncertainty_score":0.99994653},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037228333,0.00008221761,0.00027243845,0.000046304765,0.000048068156,0.00006430117,0.9966615,0.000055645683,0.002765793],"genre_scores_gemma":[0.00074627064,7.157423e-7,0.013544643,0.000033260178,0.00006040414,0.00014983868,0.98469543,0.0000064592073,0.00076297286],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992434,0.000021871721,0.00017192561,0.00022166868,0.00025028866,0.000090886904],"domain_scores_gemma":[0.99851376,0.0009911328,0.0000781145,0.00030085345,0.00008153739,0.000034621273],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000015391819,0.00006685001,0.000095652795,0.00007221609,0.000029184495,0.00004679278,0.00035213353,0.00004399906,0.9718763],"category_scores_gemma":[0.0004509984,0.00005859358,0.00005804435,0.0002874014,0.0000071109,0.00042476825,0.0002594738,0.00006430333,0.0015784579],"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":[0.0000010436089,0.00001401957,1.2734404e-7,0.00008545444,0.000006764417,0.000008837125,0.00007420282,0.000009560737,0.00003095794,0.000054770262,0.9824201,0.017294172],"study_design_scores_gemma":[0.00004588709,0.000027122507,0.0005058226,0.003197005,0.0000014363533,0.000009507872,0.000018273817,0.07432179,0.0008707021,0.0003979892,0.92052305,0.00008141283],"about_ca_topic_score_codex":0.000004407384,"about_ca_topic_score_gemma":8.933894e-7,"teacher_disagreement_score":0.9702979,"about_ca_system_score_codex":0.0000087536355,"about_ca_system_score_gemma":0.00008146845,"threshold_uncertainty_score":0.9991989},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037184484,0.00008117357,0.00026881797,0.00004630769,0.000048015398,0.00006413029,0.9967127,0.000055625354,0.0027195425],"genre_scores_gemma":[0.0007200051,7.021085e-7,0.013657111,0.000033076,0.000060027596,0.00015225787,0.984609,0.0000064314927,0.00076139404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924356,0.000021876967,0.00017176697,0.0002217175,0.00025022918,0.000090874804],"domain_scores_gemma":[0.99850386,0.0010004758,0.000078087214,0.0003012529,0.00008169739,0.000034616496],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000015375872,0.00006684692,0.00009559723,0.000072210045,0.000029174787,0.00004664996,0.00035220798,0.000043999164,0.97343606],"category_scores_gemma":[0.0004564339,0.000058593636,0.000058039313,0.00028744148,0.0000071082836,0.00042427407,0.00025954767,0.00006430643,0.0016049895],"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":[0.0000010369441,0.000013942343,1.2770559e-7,0.00008453523,0.0000067707024,0.000008684927,0.00007390619,0.000009735979,0.00003121354,0.000052359297,0.9827095,0.017008172],"study_design_scores_gemma":[0.00004512858,0.000026911823,0.000498345,0.0031782086,0.0000014305757,0.000009453811,0.000018168517,0.074582495,0.00086477,0.00038994153,0.92030424,0.000080922604],"about_ca_topic_score_codex":0.0000042975403,"about_ca_topic_score_gemma":8.610153e-7,"teacher_disagreement_score":0.9718311,"about_ca_system_score_codex":0.000008763513,"about_ca_system_score_gemma":0.000081650156,"threshold_uncertainty_score":0.9991724},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000065257525,0.0002284934,0.16465698,0.00020618385,0.0022589557,0.0007829156,0.831719,0.000057125766,0.000025123882],"genre_scores_gemma":[0.00007859411,0.00018495377,0.009570056,0.00057175744,0.00042386982,0.00006634538,0.9882313,0.000049159447,0.0008239911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99572927,0.0001628166,0.0007203545,0.001843788,0.0006359644,0.00090783526],"domain_scores_gemma":[0.9948841,0.00044437728,0.00056418264,0.0036094303,0.00018516483,0.00031276894],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010950821,0.0007866922,0.00092795934,0.0003652188,0.00031780533,0.00094870257,0.0038816137,0.0005447537,0.00007672857],"category_scores_gemma":[0.00012302416,0.0006759632,0.00021481772,0.0002465009,0.00011409091,0.0019187299,0.002598171,0.00061022554,0.00032172343],"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":[0.000042443036,0.000092003924,0.00010210337,0.00020618575,0.00007561624,0.000016322234,0.00006545435,0.000001022621,0.0000094081515,0.000060806015,0.9979377,0.0013909662],"study_design_scores_gemma":[0.0012275786,0.0003214701,0.0015594951,0.00024356172,0.00006529969,0.0000941021,0.00001800469,0.0062522986,0.000023054552,0.00023220804,0.9890883,0.00087463146],"about_ca_topic_score_codex":0.0013880816,"about_ca_topic_score_gemma":0.0003610964,"teacher_disagreement_score":0.1565123,"about_ca_system_score_codex":0.0000510144,"about_ca_system_score_gemma":0.00012375491,"threshold_uncertainty_score":0.9995692},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000055356373,0.00024104833,0.009705637,0.000046432142,0.00079254585,0.000095621326,0.9890466,0.00000932846,0.0000074681043],"genre_scores_gemma":[0.00080607494,0.00015449454,0.00199185,0.000064227504,0.00003741194,0.0000058774895,0.99684286,0.0000066476705,0.00009057412],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988958,0.00003661096,0.00018491254,0.0002684649,0.00048668738,0.00012751504],"domain_scores_gemma":[0.999359,0.00013949577,0.00016586554,0.00021550742,0.000047378355,0.000072757866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000717439,0.00012903684,0.00012762564,0.000053611595,0.00021894732,0.00010239541,0.00016948894,0.00004182381,0.0003605838],"category_scores_gemma":[0.000074477575,0.00013848268,0.0000038261687,0.00009577695,0.00000715577,0.000115620605,0.00013648048,0.00012866991,1.7634426e-7],"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":[7.987709e-7,0.0000029688588,0.00009702702,0.00004683859,0.000004002269,0.00001626404,0.0000047217654,0.000022317578,1.64987e-7,0.00093885156,0.982314,0.016552031],"study_design_scores_gemma":[0.00005748752,0.000010909101,0.034063224,0.000044712357,0.000020958354,0.0000089629675,0.00001683968,0.012680555,7.1882164e-7,0.00050250924,0.9523433,0.00024981378],"about_ca_topic_score_codex":0.98890185,"about_ca_topic_score_gemma":0.9941608,"teacher_disagreement_score":0.0339662,"about_ca_system_score_codex":0.00031985698,"about_ca_system_score_gemma":0.000301246,"threshold_uncertainty_score":0.564716},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75435793,0.00002281008,0.24469559,0.00033011776,0.000042505762,0.000109155604,0.0000181578,0.000004719239,0.00041901166],"genre_scores_gemma":[0.99789816,0.00004489347,0.0017470404,0.000016273656,0.000004692551,3.894536e-7,0.0000034752054,0.0000015117674,0.00028356034],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992524,0.0002371659,0.00010031219,0.00022173535,0.000104167026,0.0000842414],"domain_scores_gemma":[0.9991386,0.00038339198,0.00012768169,0.00027850142,0.000024765788,0.00004705861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012315504,0.000065791544,0.0001591994,0.00011522675,0.00023458051,0.000028389264,0.00045172806,0.000024955938,0.000010683186],"category_scores_gemma":[0.000010882469,0.000044879056,0.000045004526,0.00023292234,0.00010373922,0.00036139615,0.00075389456,0.00005074622,3.5469805e-7],"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":[0.00009315168,0.00042083857,0.908139,0.000056774563,0.00033962753,0.000033772067,0.004349498,0.00014387882,0.056750465,0.01753171,0.0009827663,0.0111585315],"study_design_scores_gemma":[0.00033879344,0.000056074587,0.992337,0.00006959778,0.00006493094,0.0000047175345,0.0002085615,0.0025523629,0.0025789402,0.0016688659,0.000048151112,0.00007199778],"about_ca_topic_score_codex":0.0006967185,"about_ca_topic_score_gemma":0.00027767924,"teacher_disagreement_score":0.24354023,"about_ca_system_score_codex":0.0000127374,"about_ca_system_score_gemma":0.00002002866,"threshold_uncertainty_score":0.18301149},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00929398,0.0005214469,0.6383652,0.0014164018,0.0007416103,0.0006575476,0.00012613052,0.0031008173,0.34577686],"genre_scores_gemma":[0.94987315,0.00019409879,0.04203018,0.00078384764,0.0003432232,1.0467378e-7,0.0014377644,0.0018765852,0.0034610734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832755,0.00027011542,0.00019139913,0.0004665187,0.00037690235,0.00036753117],"domain_scores_gemma":[0.99866503,0.000021064932,0.00007526173,0.00078604516,0.00027430718,0.00017831549],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005704295,0.00012912997,0.000115179406,0.0001500497,0.0017455561,0.0011223725,0.0017713673,0.000047651287,0.0034357975],"category_scores_gemma":[0.00031650515,0.00012283606,0.000044342778,0.0005444228,0.00007600081,0.000695451,0.0014301483,0.00018315187,0.0073343082],"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":[0.000023767067,0.00034655098,0.0000038181156,0.00005423594,0.000039331702,0.00008381887,0.0011812821,0.00006771921,0.011259691,0.30677307,0.36706007,0.31310666],"study_design_scores_gemma":[0.00032357534,0.00011371331,0.00017629816,0.000014873604,0.000002871883,0.00017563305,0.000048649308,0.002672871,0.001298245,0.0012274382,0.9937811,0.00016472256],"about_ca_topic_score_codex":0.000011477194,"about_ca_topic_score_gemma":6.944371e-8,"teacher_disagreement_score":0.9405791,"about_ca_system_score_codex":0.000064412394,"about_ca_system_score_gemma":0.0000037178042,"threshold_uncertainty_score":0.9999146},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009320851,0.00043925626,0.89501566,0.012550214,0.0008123947,0.001139535,0.0011072309,0.0046621677,0.07495272],"genre_scores_gemma":[0.95442426,0.00021354335,0.027330924,0.0060680793,0.00050400663,9.490638e-7,0.005134528,0.0022799056,0.004043774],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969464,0.00067881105,0.00031026884,0.0007435136,0.00082884624,0.00049218565],"domain_scores_gemma":[0.99794817,0.000060464467,0.00014450899,0.0010985561,0.00022920925,0.0005190724],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011162412,0.0001840343,0.00018184951,0.00026284877,0.00487581,0.000974513,0.0036365231,0.00004413633,0.027585233],"category_scores_gemma":[0.0006942022,0.00019721744,0.00006456908,0.0010831134,0.00011886135,0.0005385232,0.009194899,0.00045106752,0.0026040282],"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":[0.00006210799,0.0003148907,0.000007245907,0.000045040655,0.00004080009,0.00019003567,0.0024475076,0.0008058434,0.0022059977,0.04346531,0.663449,0.28696626],"study_design_scores_gemma":[0.00058990606,0.00030798037,0.00021660076,0.0000063040516,0.000005509157,0.00026160106,0.00024597291,0.014033987,0.00023678956,0.00093055476,0.9829216,0.00024319031],"about_ca_topic_score_codex":0.000038214614,"about_ca_topic_score_gemma":1.2087708e-7,"teacher_disagreement_score":0.94510347,"about_ca_system_score_codex":0.00034241713,"about_ca_system_score_gemma":0.000028888004,"threshold_uncertainty_score":0.9988185},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013887353,0.00006827162,0.00014524702,0.000042109114,0.000025722878,0.000075335265,0.99930596,0.00002659791,0.00017186905],"genre_scores_gemma":[0.00014951266,0.0000031157713,0.061373647,0.0001053025,0.00004266803,0.00013747923,0.9381076,0.000004453231,0.000076236945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993153,0.000041130173,0.00010629286,0.0002995007,0.00015135926,0.0000864148],"domain_scores_gemma":[0.99912703,0.00027065532,0.0000987596,0.00044533232,0.00001704063,0.000041159354],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002356301,0.00006855548,0.00008831559,0.000043594326,0.00015283274,0.000043122873,0.00045159753,0.000018944982,0.79715496],"category_scores_gemma":[0.00013962464,0.00006563765,0.000011612725,0.00007328271,0.000010837243,0.00026340655,0.0018710858,0.0000824733,0.000036784688],"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":[0.000005619936,0.000012285571,0.0000014485194,0.000009432745,0.0000043244186,0.0000038210546,0.000010535351,0.000026480493,0.00001653146,0.0003234019,0.9834332,0.016152935],"study_design_scores_gemma":[0.00020598924,0.000051562933,0.0025550227,0.000110146364,0.0000011199027,0.00004204102,0.000005416987,0.050991785,0.000008679053,0.00032050628,0.94562054,0.000087222834],"about_ca_topic_score_codex":0.0000056016343,"about_ca_topic_score_gemma":0.0000019963688,"teacher_disagreement_score":0.7971182,"about_ca_system_score_codex":0.000011382583,"about_ca_system_score_gemma":0.00005645761,"threshold_uncertainty_score":0.26766255},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.075352e-7,0.000013339458,0.0003637295,0.00003014584,0.000032332173,0.000059622653,0.9988803,0.000022819753,0.0005969914],"genre_scores_gemma":[0.00014181511,8.765278e-7,0.020720042,0.00026255494,0.000019605162,0.00042448,0.9782724,0.0000021608757,0.000156079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925506,0.00003291195,0.00021437992,0.00007112826,0.00035001617,0.00007650926],"domain_scores_gemma":[0.99855477,0.00072510465,0.0002737953,0.000272726,0.0001587762,0.000014850764],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000002991294,0.00005485982,0.000062236184,0.00004656297,0.0001657899,0.0000280095,0.00043406695,0.000021541318,0.93259275],"category_scores_gemma":[0.000616213,0.00004346461,0.00004035653,0.00032804327,0.000008023166,0.0021352929,0.000659825,0.000053637847,0.000057396515],"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":[0.000002804164,0.000015128229,1.3219123e-7,0.000012069217,0.0000035855214,2.0756998e-7,0.00012620226,0.00406112,6.9999665e-8,0.00054610474,0.9889739,0.0062586586],"study_design_scores_gemma":[0.00005209045,0.000027940763,0.00033418572,0.00011406608,5.816343e-7,0.000005286198,0.00002235616,0.16387708,0.000009059526,0.000089250156,0.8354257,0.000042435637],"about_ca_topic_score_codex":0.000019053572,"about_ca_topic_score_gemma":0.0000010805481,"teacher_disagreement_score":0.93253535,"about_ca_system_score_codex":0.00002892113,"about_ca_system_score_gemma":0.00019547719,"threshold_uncertainty_score":0.17724353},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.075352e-7,0.000013339458,0.0003637295,0.00003014584,0.000032332173,0.000059622653,0.9988803,0.000022819753,0.0005969914],"genre_scores_gemma":[0.00014181511,8.765278e-7,0.020720042,0.00026255494,0.000019605162,0.00042448,0.9782724,0.0000021608757,0.000156079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925506,0.00003291195,0.00021437992,0.00007112826,0.00035001617,0.00007650926],"domain_scores_gemma":[0.99855477,0.00072510465,0.0002737953,0.000272726,0.0001587762,0.000014850764],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000002991294,0.00005485982,0.000062236184,0.00004656297,0.0001657899,0.0000280095,0.00043406695,0.000021541318,0.93259275],"category_scores_gemma":[0.000616213,0.00004346461,0.00004035653,0.00032804327,0.000008023166,0.0021352929,0.000659825,0.000053637847,0.000057396515],"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":[0.000002804164,0.000015128229,1.3219123e-7,0.000012069217,0.0000035855214,2.0756998e-7,0.00012620226,0.00406112,6.9999665e-8,0.00054610474,0.9889739,0.0062586586],"study_design_scores_gemma":[0.00005209045,0.000027940763,0.00033418572,0.00011406608,5.816343e-7,0.000005286198,0.00002235616,0.16387708,0.000009059526,0.000089250156,0.8354257,0.000042435637],"about_ca_topic_score_codex":0.000019053572,"about_ca_topic_score_gemma":0.0000010805481,"teacher_disagreement_score":0.93253535,"about_ca_system_score_codex":0.00002892113,"about_ca_system_score_gemma":0.00019547719,"threshold_uncertainty_score":0.17724353},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056892756,0.0010509716,0.00036231888,0.00028720632,0.000090347705,0.0010217893,0.9964548,0.000079026555,0.00008463653],"genre_scores_gemma":[0.5792078,0.00002801552,0.02597689,0.00025333773,0.00073489116,0.012258579,0.3813347,0.000035138026,0.00017069191],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989488,0.00009833591,0.00015064485,0.0002951597,0.00040876315,0.00009828488],"domain_scores_gemma":[0.9967585,0.002362001,0.0001432633,0.00036169906,0.0003396523,0.00003483783],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006671444,0.00009869242,0.00011386669,0.000034843502,0.00007565664,0.00017177025,0.00045314795,0.00002454198,0.17811835],"category_scores_gemma":[0.0012038625,0.00005820569,0.000052157236,0.00032106476,0.000025336753,0.0010770058,0.00017659654,0.00012527805,0.00006092069],"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":[0.000004263548,0.00087957334,0.000028782006,0.00005990345,0.000012594508,0.000008041663,0.0003113004,0.0000015992816,0.0000035725143,0.00007951594,0.8309795,0.16763136],"study_design_scores_gemma":[0.00047554602,0.0028472466,0.09511205,0.027635397,0.00010880776,0.00014227023,0.0015011491,0.12797982,0.00025745033,0.000508115,0.7428167,0.0006154546],"about_ca_topic_score_codex":0.00005156895,"about_ca_topic_score_gemma":0.0000023065306,"teacher_disagreement_score":0.61512005,"about_ca_system_score_codex":0.000012886214,"about_ca_system_score_gemma":0.00047063467,"threshold_uncertainty_score":0.82263297},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035920715,0.00028509257,0.35025972,0.0010606833,0.0064460407,0.0013877442,0.00003295546,0.00009191627,0.64039993],"genre_scores_gemma":[0.0061172605,0.00023822144,0.37652928,0.0013847451,0.00093782775,0.000050778093,0.000028035767,0.0001549411,0.61455894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99281627,0.000115062954,0.0006400681,0.0030833103,0.0021671376,0.0011781798],"domain_scores_gemma":[0.99189967,0.00022090483,0.0009439936,0.0061456114,0.0002797175,0.00051009323],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0027969312,0.00062703405,0.0007014746,0.00046656252,0.0010442479,0.010848081,0.02846794,0.00067256036,0.00413481],"category_scores_gemma":[0.0007786817,0.0005533972,0.00012677247,0.003093393,0.0008489661,0.004392848,0.012950568,0.0011848749,0.011993765],"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":[0.000022834965,0.00022730273,0.000348195,0.00008376255,0.00003133007,0.000040612136,0.0010497075,0.00016515348,0.00034291478,0.595683,0.22443828,0.17756692],"study_design_scores_gemma":[0.00032663665,0.00020417066,0.0011492319,0.0029553259,0.000020846814,0.000022062808,0.00012151724,0.048591126,0.00019538758,0.011749573,0.93349874,0.0011653684],"about_ca_topic_score_codex":0.0007867795,"about_ca_topic_score_gemma":0.000024432904,"teacher_disagreement_score":0.7090605,"about_ca_system_score_codex":0.0002873626,"about_ca_system_score_gemma":0.0023821301,"threshold_uncertainty_score":0.9996917},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10816008,0.00042932504,0.87649465,0.0018679292,0.001969065,0.0024926106,0.003767365,0.0010480287,0.0037709277],"genre_scores_gemma":[0.5168743,0.0013859866,0.47041273,0.0033620265,0.0004722958,0.00024972606,0.00680865,0.00013145639,0.00030284873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975059,0.00006330512,0.00077563385,0.00047151884,0.0005086573,0.0006750035],"domain_scores_gemma":[0.9972424,0.00034382683,0.00032618444,0.0017980684,0.00011564672,0.00017388111],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009858186,0.00031965654,0.00036936277,0.00035631997,0.00025794466,0.0006781371,0.002069218,0.00016581641,0.000005357409],"category_scores_gemma":[0.000274637,0.00026796883,0.000053996362,0.00055966765,0.00007794971,0.007091201,0.00292346,0.0003911927,0.000049982496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011437718,0.00150043,0.024365047,0.004933052,0.0008165616,0.0004121944,0.0799528,0.005815953,0.0002793676,0.18552026,0.2223926,0.47286797],"study_design_scores_gemma":[0.0018365376,0.00007084322,0.0022439014,0.000108673325,0.000017858441,0.00008242644,0.00097371975,0.9257866,0.000056821533,0.0024046034,0.0660211,0.00039688166],"about_ca_topic_score_codex":0.000121536366,"about_ca_topic_score_gemma":0.000026008962,"teacher_disagreement_score":0.9199707,"about_ca_system_score_codex":0.0000496786,"about_ca_system_score_gemma":0.000073184085,"threshold_uncertainty_score":0.99997723},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9034837e-7,0.00009968134,0.000063306776,0.0000052578903,0.00002202399,0.00017158761,0.96930146,0.000018907254,0.030317478],"genre_scores_gemma":[0.000048513564,9.837585e-7,0.0028564273,0.000025423184,0.000051128653,0.00040441006,0.9855205,0.000029253759,0.011063405],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929404,0.000056815643,0.000128347,0.00017491239,0.00027505466,0.00007080834],"domain_scores_gemma":[0.9992398,0.00020999831,0.00018783212,0.00031609388,0.000026842736,0.000019416077],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000013426636,0.000079534344,0.00011541932,0.00011625064,0.000021421385,0.000009001452,0.00056986173,0.00006681967,0.9950815],"category_scores_gemma":[0.00020110614,0.00006378684,0.000054423213,0.00025591443,0.0000022904042,0.000066220964,0.000291325,0.00008963905,0.00014887776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.191865e-7,0.000019521969,0.0000010947597,0.000027068143,0.000003822435,2.6499063e-7,0.00004474897,0.0000075527037,0.0000058223964,0.000020884048,0.9860114,0.013857043],"study_design_scores_gemma":[0.00004159059,0.000012248418,0.0047919247,0.0013072646,0.0000013963402,3.763388e-7,0.000004036989,0.003090172,0.00006452058,0.000067587665,0.99055123,0.00006764735],"about_ca_topic_score_codex":0.000036839312,"about_ca_topic_score_gemma":0.000059104048,"teacher_disagreement_score":0.99493265,"about_ca_system_score_codex":0.00002021415,"about_ca_system_score_gemma":0.00006206646,"threshold_uncertainty_score":0.2601152},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883834,0.0006273657,0.00021253448,0.0027215304,0.0004748085,0.00051743974,0.000027337452,0.00003927454,0.006996314],"genre_scores_gemma":[0.9321327,0.0024583254,0.008830844,0.0018048922,0.000099577686,0.0000053704216,0.0064752265,0.00006330836,0.04812972],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984547,0.0001961891,0.00020086784,0.000525074,0.00034078528,0.00028240768],"domain_scores_gemma":[0.99881893,0.00028992965,0.0001991853,0.0005820573,0.000017202008,0.00009268485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008151231,0.00022748233,0.00026802934,0.00016840993,0.00025663892,0.000094021045,0.0017747455,0.0001303206,0.00050716643],"category_scores_gemma":[0.000009937702,0.0002017846,0.000079469915,0.00028163168,0.00008129888,0.0013365366,0.0006649934,0.00033931286,0.000010141975],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026069512,0.0023952993,0.029673714,0.0012753477,0.000603104,0.0033542027,0.55773276,0.0011791759,0.0034825003,0.042873442,0.29175133,0.0630722],"study_design_scores_gemma":[0.008577713,0.0015900247,0.40236482,0.0016663367,0.00041112807,0.00022886888,0.04831923,0.089469925,0.0032750824,0.0041978834,0.43566173,0.0042372243],"about_ca_topic_score_codex":0.034008637,"about_ca_topic_score_gemma":0.003111652,"teacher_disagreement_score":0.5094135,"about_ca_system_score_codex":0.000030093915,"about_ca_system_score_gemma":0.00020074651,"threshold_uncertainty_score":0.972424},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003341957,0.0006604327,0.054997925,0.0037019395,0.00031996478,0.0001655277,0.00020727993,0.00006113565,0.93985236],"genre_scores_gemma":[0.037393507,0.00062636455,0.09431868,0.0024335294,0.0002972143,0.000010447225,0.00005471982,0.00017438283,0.86469114],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751025,0.000036481048,0.00022447988,0.00043532523,0.0014745708,0.0003188647],"domain_scores_gemma":[0.9989225,0.00008452971,0.00017456678,0.0005098054,3.880098e-7,0.0003081541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000076328815,0.00030064577,0.00035532247,0.000041412044,0.00008448075,0.00006772557,0.00083352736,0.00007240473,0.0000923031],"category_scores_gemma":[0.00000255624,0.00025134603,0.000030842006,0.00010389149,0.00005807674,0.00029233826,0.00041815967,0.0002352987,1.0997173e-8],"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":[0.00006638511,0.00005309613,0.00032053632,0.0001343728,0.00009178165,0.00022822441,0.00003372623,0.000008283578,0.0011865048,0.3441196,0.3525819,0.3011756],"study_design_scores_gemma":[0.00026599527,0.00008280346,0.0009176636,0.00046364078,0.000013495136,0.000012720972,0.00014350051,0.0124213565,0.0057787853,0.0013721614,0.97804433,0.0004835419],"about_ca_topic_score_codex":0.005970925,"about_ca_topic_score_gemma":0.014065652,"teacher_disagreement_score":0.6254624,"about_ca_system_score_codex":0.0000061213127,"about_ca_system_score_gemma":0.0015307668,"threshold_uncertainty_score":0.99999386},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777866,0.0004906262,0.00036685079,0.000021868897,0.002023683,0.0024272865,0.0008290148,0.00063876645,0.015415306],"genre_scores_gemma":[0.9638098,0.000053347376,0.030069645,0.0001247294,0.00012171696,0.0003065538,0.002456746,0.0001695295,0.0028879717],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947495,0.00026924274,0.0014347222,0.0016507108,0.00084380154,0.0010520619],"domain_scores_gemma":[0.9964794,0.0008746766,0.0008288317,0.001218756,0.00037949573,0.0002188228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015011969,0.0008520958,0.0011578957,0.00060737046,0.0010713893,0.00040948426,0.0022932333,0.00070853333,0.00001122166],"category_scores_gemma":[0.0003479884,0.0008803645,0.00040399437,0.00076373067,0.000053061096,0.0017077432,0.00052416656,0.0010568202,0.000027458993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005974827,0.0006642283,0.00027221136,0.0016294108,0.000116371404,0.00009512152,0.00007863567,0.0011351552,0.004961386,0.35071182,0.00007722174,0.63966095],"study_design_scores_gemma":[0.030728193,0.0013778824,0.017510414,0.009292544,0.0003743769,0.0001283289,0.00091983593,0.058075823,0.17912257,0.4616594,0.23048775,0.010322873],"about_ca_topic_score_codex":0.0015598717,"about_ca_topic_score_gemma":0.001758039,"teacher_disagreement_score":0.6293381,"about_ca_system_score_codex":0.0006096762,"about_ca_system_score_gemma":0.000108401524,"threshold_uncertainty_score":0.99936473},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68612444,0.000056661906,0.31284815,0.00018871219,0.0001333738,0.0002302228,0.0003144261,0.000031490057,0.00007250075],"genre_scores_gemma":[0.98144543,0.0000043092664,0.017476033,0.00004074327,0.000015617006,0.0000016444537,0.000013550344,0.0000088763745,0.0009938112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984535,0.00013210287,0.00011994709,0.00035566793,0.00069763884,0.00024115563],"domain_scores_gemma":[0.99915564,0.000040190283,0.00013666338,0.0005378222,0.000070177186,0.000059534512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017573005,0.00015295859,0.00020014598,0.00012013517,0.00085165125,0.000026347561,0.0012373176,0.000025070916,0.00005185774],"category_scores_gemma":[0.000002566846,0.00012259967,0.000111647845,0.00063740136,0.0000955498,0.001302706,0.00070833036,0.00017231925,0.0000019536615],"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":[0.0052188192,0.0028312781,0.039702646,0.00023775538,0.0013515777,0.0020866708,0.014325439,0.85675913,0.039434783,0.023664873,0.007855969,0.006531083],"study_design_scores_gemma":[0.010006035,0.0019570482,0.048151407,0.00015715096,0.00036247703,0.00020295705,0.01252653,0.89375556,0.00910223,0.00006864293,0.022134429,0.0015755395],"about_ca_topic_score_codex":0.00055604195,"about_ca_topic_score_gemma":0.00014315861,"teacher_disagreement_score":0.29537213,"about_ca_system_score_codex":0.00017884804,"about_ca_system_score_gemma":0.00020635308,"threshold_uncertainty_score":0.6550299},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002069592,0.00024960164,0.00013557146,0.00012882808,0.00097472814,0.00041817824,0.00015664047,0.0006976487,0.9972367],"genre_scores_gemma":[0.000016691754,0.00030235024,0.007994679,0.00023054918,0.0001638881,0.000026531841,0.00009291853,0.00018261113,0.9909898],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997854,0.00006183638,0.00054360286,0.00040496798,0.00072294456,0.0004126569],"domain_scores_gemma":[0.9980105,0.00011330045,0.00058651785,0.00093216443,0.00015731981,0.00020020832],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019425454,0.0004327951,0.00049177516,0.00012466335,0.00012024376,0.00017192854,0.000988966,0.00035236753,0.19010974],"category_scores_gemma":[0.000059574348,0.0003573701,0.000119569755,0.000026670561,0.00016440146,0.0000014757957,0.0004169194,0.00032988368,0.020820064],"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":[0.00002943896,0.000029853152,0.0000025964569,0.00016001542,0.00006100693,0.000057069297,0.00007149703,0.00018414132,8.45402e-8,0.000048059876,0.9942314,0.0051248264],"study_design_scores_gemma":[0.0006585626,0.00014901486,0.000009953934,0.0004174648,0.000030759667,0.000043249438,0.000041715306,0.0006222973,0.0000035417072,0.000009400425,0.9975535,0.00046051835],"about_ca_topic_score_codex":0.011238549,"about_ca_topic_score_gemma":0.0083371,"teacher_disagreement_score":0.16928968,"about_ca_system_score_codex":0.000057607955,"about_ca_system_score_gemma":0.00009386084,"threshold_uncertainty_score":0.9998878},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019255903,0.037364133,0.6896496,0.02635161,0.0008279911,0.002281914,0.00004600391,0.0011918197,0.2420944],"genre_scores_gemma":[0.004728211,0.08528592,0.78126806,0.00031645555,0.00017752247,0.00011784299,0.000015957832,0.00018444269,0.12790556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99828255,0.000015597878,0.00048668866,0.00061702763,0.00026906823,0.00032905646],"domain_scores_gemma":[0.99827707,0.00022367477,0.0002873273,0.0011009721,0.00005182562,0.000059131984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003417587,0.00039922984,0.00064906664,0.00043794012,0.0002196772,0.00012157597,0.0009250714,0.00044893287,0.0000073230503],"category_scores_gemma":[0.000036108915,0.00027216022,0.00006110862,0.00014036227,0.0008146822,0.00013098332,0.001683195,0.00071456295,0.000025955458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015859728,0.000021466054,0.000001778572,0.000045630662,0.000029848808,0.00007340086,0.00011889539,3.2565075e-7,0.000004596142,0.8096649,0.00040098472,0.18963659],"study_design_scores_gemma":[0.0009456058,0.000037240592,0.0000042883657,0.0002502204,0.000019197307,0.00027163385,0.000010458851,0.037151285,0.000021882397,0.91432136,0.046641484,0.00032532937],"about_ca_topic_score_codex":0.000010452956,"about_ca_topic_score_gemma":0.0000118410935,"teacher_disagreement_score":0.18931127,"about_ca_system_score_codex":0.000030497298,"about_ca_system_score_gemma":0.000043027176,"threshold_uncertainty_score":0.99997306},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09364005,0.0005485223,0.8998337,0.00020784175,0.0007523221,0.00024319162,0.00013050053,0.00023123928,0.004412638],"genre_scores_gemma":[0.90007246,0.0000077419445,0.09926492,0.00014065592,0.00020148042,0.000011815451,0.00014386197,0.00001161406,0.00014547097],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860233,0.00011218022,0.00022892385,0.00044828226,0.00031042958,0.00029783725],"domain_scores_gemma":[0.9993305,0.000061377184,0.00008394118,0.00038404152,0.00003175327,0.00010839038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020931519,0.00016433593,0.00022761393,0.000060944178,0.00017881254,0.00022574657,0.00046711921,0.000070361806,0.000064844346],"category_scores_gemma":[0.0000054230004,0.00015232107,0.00003135185,0.00013975409,0.00007912703,0.00040282492,0.00032569634,0.00012244712,0.000021405303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015122272,0.002243835,0.02375734,0.000059524526,0.00012507166,0.00042045256,0.0030516041,0.00006300137,0.34121826,0.07644097,0.2548279,0.29764083],"study_design_scores_gemma":[0.002823305,0.0004620112,0.058001623,0.000047257934,0.000010010943,0.00012854331,0.00010907306,0.80128497,0.106072366,0.0042774803,0.02582492,0.00095846277],"about_ca_topic_score_codex":0.0011833925,"about_ca_topic_score_gemma":0.00003839736,"teacher_disagreement_score":0.80643237,"about_ca_system_score_codex":0.000021611755,"about_ca_system_score_gemma":0.000032998403,"threshold_uncertainty_score":0.6211473},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020523944,0.0049523255,0.20453396,0.0011245776,0.0021839999,0.002763615,0.08360859,0.0060506593,0.69457704],"genre_scores_gemma":[0.0040438557,0.00009455494,0.12662701,0.0031692337,0.0025844898,0.00084131444,0.026228033,0.0029040596,0.8335075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99683154,0.00011515868,0.00044349,0.0012259162,0.00072533154,0.00065857667],"domain_scores_gemma":[0.9974403,0.00021341727,0.00037788175,0.001581898,0.000022097302,0.00036442364],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012033371,0.0006452937,0.0005805322,0.00047421418,0.00032861982,0.0022626333,0.003587378,0.0003293013,0.0047783083],"category_scores_gemma":[0.00008665049,0.00054745836,0.00034967682,0.00043251712,0.00008141546,0.0009382081,0.003246547,0.00080593274,0.0007189949],"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":[0.00004160429,0.00016193035,0.000772266,0.00019077504,0.000058238984,0.00005002423,0.000012539326,0.000021978447,0.000006885994,0.0023816042,0.94050497,0.055797163],"study_design_scores_gemma":[0.00055884424,0.00009286314,0.000069205766,0.00025242442,0.000011993651,0.000017116301,0.0000047447943,0.0013982584,0.00010550584,0.007902325,0.9888692,0.00071755034],"about_ca_topic_score_codex":0.000005331746,"about_ca_topic_score_gemma":0.0000010137138,"teacher_disagreement_score":0.13893043,"about_ca_system_score_codex":0.000039827868,"about_ca_system_score_gemma":0.00015952019,"threshold_uncertainty_score":0.9996977},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021340122,0.0010369845,0.8853684,0.0051658256,0.0014512266,0.00019890718,0.00005733166,0.0011574706,0.084223725],"genre_scores_gemma":[0.952515,0.0003669369,0.04145712,0.0004316934,0.00050675205,0.000010643955,0.000048700098,0.000042989028,0.004620133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998339,0.00015101467,0.00013790128,0.00058745145,0.0003413172,0.00044332288],"domain_scores_gemma":[0.9987158,0.000254158,0.000045535548,0.00073228177,0.000036106652,0.00021611212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031681402,0.00021506297,0.00019314991,0.00027837206,0.00022974252,0.0008104993,0.0012046127,0.00017044539,0.00010898484],"category_scores_gemma":[0.000024840416,0.00020172985,0.00014344239,0.0007237878,0.0001360806,0.0015924453,0.0006175607,0.00035711878,0.0003884079],"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":[0.00001770669,0.00009119984,0.00022535745,0.000059267586,0.00007436222,0.0013289422,0.0034454772,0.000115856594,0.0025513102,0.6559221,0.09883441,0.237334],"study_design_scores_gemma":[0.00042445425,0.000088027235,0.0027873241,0.00013800897,0.00002845832,0.00013370441,0.00020819803,0.18285358,0.00058414054,0.019550184,0.7927259,0.0004780221],"about_ca_topic_score_codex":0.0001730225,"about_ca_topic_score_gemma":0.000024313453,"teacher_disagreement_score":0.93117493,"about_ca_system_score_codex":0.00011229758,"about_ca_system_score_gemma":0.00020332464,"threshold_uncertainty_score":0.82263047},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027191512,0.00022436502,0.028778752,0.0015231719,0.0004552793,0.0011816708,0.00011146742,0.000118342956,0.9675798],"genre_scores_gemma":[0.0003907358,0.0004133184,0.05638256,0.000071582515,0.00022870663,0.0000024622345,0.000115074545,0.0001234095,0.9422721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99614704,0.0005078593,0.00020808046,0.0011653304,0.0011977941,0.0007739191],"domain_scores_gemma":[0.9964827,0.00020922325,0.00026018624,0.002438529,0.00023131291,0.000378078],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00087771245,0.00034672744,0.000657355,0.00076583505,0.00036918186,0.00048164168,0.010028954,0.00042733792,0.003410931],"category_scores_gemma":[0.000042677322,0.00036575584,0.00016997418,0.00073564576,0.00024531805,0.0011241185,0.007371522,0.00071078754,0.00079501874],"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":[0.000039195413,0.00013572314,0.000029987797,0.00004822983,0.00006757208,0.00013859605,0.0005523882,5.6613146e-7,0.00006358688,0.004099756,0.9657227,0.029101737],"study_design_scores_gemma":[0.00079487,0.00028748118,0.00031364712,0.00047828926,0.000012660079,0.0000052227037,0.000102921265,0.00060027,0.000030434763,0.0008526947,0.9960981,0.0004233962],"about_ca_topic_score_codex":0.046086974,"about_ca_topic_score_gemma":0.0023428358,"teacher_disagreement_score":0.04374414,"about_ca_system_score_codex":0.00013412093,"about_ca_system_score_gemma":0.00032027593,"threshold_uncertainty_score":0.99998295},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98720676,0.0018888992,0.00038709748,0.00058702007,0.0028905966,0.0018925308,0.0010758889,0.00027318878,0.003797993],"genre_scores_gemma":[0.9954149,0.0012674358,0.0007732909,0.0002309242,0.000061716506,0.00015807949,0.00032317394,0.00006213596,0.0017083171],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99648505,0.0006024404,0.0007140213,0.0008013569,0.0010697403,0.00032737164],"domain_scores_gemma":[0.9969088,0.00056313735,0.00073174323,0.0012135297,0.00048610292,0.000096701835],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001532772,0.00042076042,0.00039698524,0.00014904073,0.002886307,0.0005215695,0.0017376749,0.00025701482,0.000027677012],"category_scores_gemma":[0.00057434995,0.00024056065,0.0001728003,0.0006892384,0.00032707624,0.0018377737,0.00091888785,0.00068143685,0.000023756014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012406797,0.000080278995,0.00015899785,0.0003905626,0.00019254647,0.0000076944125,0.00067524426,0.00026194393,0.0037877322,0.85245425,0.00023639113,0.14163029],"study_design_scores_gemma":[0.0024679063,0.00013614104,0.066084124,0.0013157986,0.0004423106,0.00006513255,0.0020669498,0.01654805,0.008974622,0.88880116,0.011756224,0.0013415945],"about_ca_topic_score_codex":0.0010763227,"about_ca_topic_score_gemma":0.0039774445,"teacher_disagreement_score":0.1402887,"about_ca_system_score_codex":0.00007115278,"about_ca_system_score_gemma":0.00006418624,"threshold_uncertainty_score":0.9984118},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22428292,0.0008991868,0.74756575,0.011400058,0.0015828643,0.0013801495,0.00038973437,0.0012769034,0.011222438],"genre_scores_gemma":[0.76433665,0.00021594661,0.22326934,0.00014823546,0.00075098814,0.0000041118674,0.00012791675,0.00004155495,0.01110527],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792236,0.0001033347,0.00021458637,0.0007237467,0.0005724381,0.0004635553],"domain_scores_gemma":[0.99825567,0.00006496334,0.00025104606,0.00090517494,0.00028069364,0.00024242378],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017087864,0.00023619314,0.00033448412,0.00024782488,0.0007237215,0.000087550485,0.0011983776,0.0001303546,0.00031913962],"category_scores_gemma":[0.000024101893,0.00025234968,0.000086088105,0.0012709006,0.00022654152,0.0010681973,0.00043875273,0.0002251113,0.00012865536],"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":[0.000751839,0.002721674,0.002782365,0.00019550507,0.000553383,0.0003841586,0.009557588,0.0019367882,0.041424617,0.101241454,0.79211485,0.046335798],"study_design_scores_gemma":[0.00488442,0.0009050206,0.07342462,0.0004378773,0.00013634058,0.00008382061,0.0003791822,0.15343215,0.0010254998,0.0006249945,0.7632944,0.0013716954],"about_ca_topic_score_codex":0.000048475824,"about_ca_topic_score_gemma":0.00092972314,"teacher_disagreement_score":0.5400537,"about_ca_system_score_codex":0.000088092755,"about_ca_system_score_gemma":0.00010746171,"threshold_uncertainty_score":0.99999285},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023672098,0.0027353044,0.059985995,0.00077886245,0.0021678093,0.00029034284,0.00010213652,0.0002896809,0.9336475],"genre_scores_gemma":[0.00013526945,0.00020843472,0.019925034,0.00046372804,0.00023448512,0.000012452241,0.000062449784,0.00016974403,0.9787884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985875,0.000038004022,0.00016565068,0.0006231112,0.00022437681,0.00036139038],"domain_scores_gemma":[0.9988295,0.000008696482,0.000044854376,0.0008745276,0.000011862016,0.00023057188],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016151252,0.00021902475,0.0002212731,0.0006938236,0.000031950323,0.0002715847,0.0011773537,0.00024432773,0.0018830773],"category_scores_gemma":[0.000006077669,0.00017987927,0.000047234644,0.00037591247,0.000013443272,0.0001724941,0.0005032247,0.00030149694,0.0027135243],"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":[2.3337142e-7,0.000008017965,0.000008604233,0.000022308384,0.000006709382,0.00024820826,0.0000532186,0.0000022519093,0.0000022123968,0.003042366,0.9880176,0.008588247],"study_design_scores_gemma":[0.000078560886,0.000014283319,0.000031212097,0.0003025123,0.000002940472,0.0000075376197,0.00000827875,0.008351308,0.0000058422706,0.00048693383,0.99046034,0.00025027213],"about_ca_topic_score_codex":0.45536536,"about_ca_topic_score_gemma":0.5676571,"teacher_disagreement_score":0.112291776,"about_ca_system_score_codex":0.00018669284,"about_ca_system_score_gemma":0.00028605203,"threshold_uncertainty_score":0.99902934},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014429877,0.0050630765,0.000014524166,0.0012393715,0.00021672153,0.0009200189,0.0005848843,0.000014249237,0.99050415],"genre_scores_gemma":[0.12904128,0.007656399,0.0013118447,0.00071174797,0.00013132548,0.000027138107,0.000060423394,0.00007066491,0.86098915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856746,0.00011420324,0.00044735416,0.00016843936,0.00049081375,0.00021172377],"domain_scores_gemma":[0.99790823,0.00022779829,0.0010272501,0.0007096537,0.00006248159,0.000064579675],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032481685,0.000222535,0.00046540174,0.000020056395,0.00013985293,0.00008327408,0.0008462957,0.00008226415,0.0009956395],"category_scores_gemma":[0.00007129473,0.000111627836,0.00008236567,0.000008125082,0.00026385943,0.0000014420514,0.0004217838,0.00021111517,0.000007766556],"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":[0.000057623147,0.000007338649,0.00013682902,0.0001536402,0.000050255872,0.0000029139828,0.0019712143,0.00006479767,1.7263305e-8,0.00009214555,0.9910579,0.0064053405],"study_design_scores_gemma":[0.0015284928,0.00010134539,0.000704151,0.00037545103,0.000019042142,0.000023048402,0.0005399942,0.0008261828,0.0000024431995,0.000011791346,0.9957264,0.00014162896],"about_ca_topic_score_codex":0.92538214,"about_ca_topic_score_gemma":0.4668325,"teacher_disagreement_score":0.45854965,"about_ca_system_score_codex":0.00013555221,"about_ca_system_score_gemma":0.00028196847,"threshold_uncertainty_score":0.99991757},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9326606,0.00009134657,0.017956316,0.0019162557,0.0010067495,0.00054661266,0.00012218517,0.00035157762,0.04534835],"genre_scores_gemma":[0.99558026,0.00005632105,0.003686807,0.00005023429,0.0003285253,0.000081164064,0.000059344977,0.00003411096,0.00012325164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99613637,0.0002894101,0.0007204916,0.0010005292,0.0011158576,0.0007373245],"domain_scores_gemma":[0.99514425,0.00022064577,0.0009345398,0.0027392267,0.0004494701,0.00051184697],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0008505636,0.0004954139,0.0006857806,0.00039098243,0.0013565912,0.0007588529,0.0029550944,0.00037315823,0.000023921184],"category_scores_gemma":[0.0005825998,0.00041596175,0.00044752084,0.0004396506,0.000051775864,0.001894227,0.0012337854,0.0005812788,0.000013086424],"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":[0.00016133483,0.0011461584,0.07053015,0.00009734998,0.00039468153,0.00015876743,0.0043833046,0.00035687428,0.0016174352,0.910063,0.0021133323,0.008977607],"study_design_scores_gemma":[0.0015796344,0.00028709063,0.9358749,0.00030092278,0.000044632197,0.00017960835,0.00008810213,0.013454576,0.0015420071,0.0009694925,0.04495473,0.0007243402],"about_ca_topic_score_codex":0.000060461854,"about_ca_topic_score_gemma":0.00018765572,"teacher_disagreement_score":0.9090935,"about_ca_system_score_codex":0.00040618965,"about_ca_system_score_gemma":0.0006108521,"threshold_uncertainty_score":0.9999435},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95984054,0.0019609092,0.0149790365,0.0058706207,0.0012329972,0.0013343263,0.0012612729,0.002020475,0.011499817],"genre_scores_gemma":[0.9795333,0.003714541,0.010024533,0.0010783685,0.0007341679,0.00015775123,0.00036788874,0.00021220956,0.004177207],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9889537,0.0016129437,0.0013038061,0.0027785834,0.0014793904,0.0038715918],"domain_scores_gemma":[0.99138445,0.0023210733,0.0008791603,0.0025373057,0.00079954456,0.0020784726],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.0015611249,0.0017040273,0.0019838565,0.0019539422,0.001995392,0.0019424328,0.0051436448,0.0013848637,0.0020808908],"category_scores_gemma":[0.0009282799,0.0018245047,0.00083773886,0.005300846,0.0027566992,0.00196242,0.0028380551,0.002333237,0.0012052889],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009387762,0.0018698554,0.2856013,0.0007516499,0.0023038927,0.006922116,0.01901192,0.0006860213,0.07050913,0.12739135,0.13339509,0.35061893],"study_design_scores_gemma":[0.00707042,0.0010681191,0.45881936,0.0014456398,0.0008546011,0.0011632595,0.014787482,0.23279305,0.0025837298,0.004452808,0.26984674,0.005114795],"about_ca_topic_score_codex":0.002778697,"about_ca_topic_score_gemma":0.00020145685,"teacher_disagreement_score":0.34550413,"about_ca_system_score_codex":0.0013316746,"about_ca_system_score_gemma":0.0077360263,"threshold_uncertainty_score":0.9999684},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000060155758,0.000002990907,0.38994113,0.000075995194,0.0005652732,0.00038941004,0.000026338863,0.0005536331,0.6084392],"genre_scores_gemma":[0.00006177631,0.00014719242,0.10510194,0.00018983726,0.00034218724,0.00010773007,0.00003884106,0.00025113145,0.89375937],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99414235,0.00029253325,0.00051406026,0.003700922,0.00072372175,0.00062639033],"domain_scores_gemma":[0.9883637,0.00012079355,0.00047167877,0.010590031,0.000115648916,0.00033815726],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0018599929,0.0005821983,0.00059879577,0.00034463624,0.00017349212,0.00034974862,0.0058706854,0.00063296955,0.55584747],"category_scores_gemma":[0.00042836115,0.0005861686,0.00023841098,0.00028140182,0.00019240323,0.0004200587,0.008109185,0.0005063494,0.9308513],"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":[0.00000822456,0.000147408,0.00007114945,0.000059730115,0.00008179318,0.000021801994,0.00017315069,0.00024343962,0.00010520875,0.005992073,0.96386856,0.029227445],"study_design_scores_gemma":[0.0002821525,7.27891e-7,0.000048685466,0.00022156369,0.000024048546,0.000021959284,0.000003932798,0.12138964,0.00036117857,0.007082516,0.8699848,0.00057879783],"about_ca_topic_score_codex":0.000268455,"about_ca_topic_score_gemma":0.00004133194,"teacher_disagreement_score":0.37500378,"about_ca_system_score_codex":0.0001382505,"about_ca_system_score_gemma":0.00028975162,"threshold_uncertainty_score":0.99991304},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045640105,0.000018096769,0.9541863,0.00015358254,0.00016051627,0.00002205156,2.2533523e-7,0.00015352423,0.040741693],"genre_scores_gemma":[0.52172583,0.0000037075677,0.47528514,0.0006779955,0.00009932854,4.6643282e-7,0.000001478755,0.0000034071152,0.002202624],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99951553,0.0000035575622,0.00008067429,0.00013918364,0.00011867044,0.00014235624],"domain_scores_gemma":[0.9995767,0.000031702595,0.000016776654,0.00029411595,0.000018237735,0.000062489715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022712474,0.000039188708,0.00003684069,0.000034802062,0.000048389902,0.000058276426,0.00043432464,0.000017346974,0.000041936233],"category_scores_gemma":[0.000007105656,0.000029230883,0.000015226251,0.00012382641,0.000007070833,0.0003280808,0.00025495878,0.00004052041,0.00012170471],"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":[0.0000015483636,0.000027407228,0.0006550691,0.0000015669293,0.0000023242867,0.000027251492,0.00009100123,0.0000032128985,0.00093333033,0.37492242,0.011673218,0.6116617],"study_design_scores_gemma":[0.0007343272,0.00014727513,0.060483243,0.00002546586,0.000002722756,0.00005978305,0.00007931277,0.07777627,0.04976005,0.023332171,0.7870298,0.0005695537],"about_ca_topic_score_codex":0.0000353369,"about_ca_topic_score_gemma":0.0000043925656,"teacher_disagreement_score":0.7753566,"about_ca_system_score_codex":0.0000071171416,"about_ca_system_score_gemma":0.00000756051,"threshold_uncertainty_score":0.15643084},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013938512,0.000038004026,0.9940442,0.00036960648,0.0000815211,0.00008626054,0.000001609804,0.000060460858,0.003924495],"genre_scores_gemma":[0.6321584,0.0002445998,0.36704332,0.00010295879,0.00002436552,0.000027969018,0.0000026177568,0.0000028988488,0.00039285462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995968,0.000021881799,0.00013924259,0.00006451987,0.00010192743,0.00007564452],"domain_scores_gemma":[0.9996236,0.000041023886,0.000030097448,0.0002509792,0.00003441869,0.00001989047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012406218,0.000036675214,0.000052454132,0.000022695902,0.00021008342,0.000020563682,0.000476781,0.000015858186,0.000009147575],"category_scores_gemma":[0.0000058671462,0.000020441046,0.000033004573,0.00011053232,0.000035823577,0.00029884296,0.000089331654,0.00004089175,0.000003932952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009005061,0.00007270535,0.00009054823,0.000011960014,0.00001784979,0.0000057693373,0.0017598926,0.00007212929,0.026869608,0.8580202,0.023741012,0.08932931],"study_design_scores_gemma":[0.0006697056,0.00013269002,0.0012186188,0.000053139414,0.0000043914742,0.00020866746,0.000070351016,0.5523424,0.32676876,0.012242391,0.106016055,0.00027280173],"about_ca_topic_score_codex":0.000029206294,"about_ca_topic_score_gemma":0.0000029782914,"teacher_disagreement_score":0.8457778,"about_ca_system_score_codex":0.0000051852726,"about_ca_system_score_gemma":0.000019984247,"threshold_uncertainty_score":0.16158131},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017172858,0.000052055275,0.9480152,0.00014046051,0.000097112956,0.000044604825,4.974001e-7,0.00012512974,0.04980762],"genre_scores_gemma":[0.29961506,0.0000063242937,0.69768775,0.0005410621,0.000019236559,0.0000056927997,0.0000016773166,0.0000051411216,0.0021180545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994252,0.00002108265,0.000060844675,0.0002045585,0.0001465176,0.00014179871],"domain_scores_gemma":[0.9994338,0.000017305763,0.000018657758,0.00044183285,0.0000261205,0.00006224097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008034798,0.000062762534,0.000059052047,0.00002359831,0.00006220145,0.00007934346,0.00032621948,0.000017119251,0.00011128781],"category_scores_gemma":[0.0000062603685,0.000038152055,0.000012121588,0.00014647926,0.000013676133,0.00038504347,0.0000721114,0.000042034637,0.00008233986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036484355,0.00011195239,0.00042074203,0.0000035692767,0.000010707571,0.000040852803,0.00009958773,0.000027889897,0.00042451321,0.8741857,0.019451361,0.105219476],"study_design_scores_gemma":[0.0026304815,0.00075638527,0.01381439,0.000059475784,0.000011548338,0.00033643644,0.0001139491,0.105116256,0.03298003,0.07353114,0.76952285,0.0011270723],"about_ca_topic_score_codex":0.000010090695,"about_ca_topic_score_gemma":0.000002676715,"teacher_disagreement_score":0.80065453,"about_ca_system_score_codex":0.0000058127093,"about_ca_system_score_gemma":0.00003103502,"threshold_uncertainty_score":0.15557957},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002377717,0.0016391102,0.95239466,0.005712958,0.0009106189,0.00042985947,0.000013599004,0.0009803579,0.037681065],"genre_scores_gemma":[0.12890159,0.0010735373,0.85559314,0.0012166951,0.00049737626,0.00007152502,0.00010806212,0.000023729175,0.012514346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990437,0.00004078832,0.00012635856,0.00032826106,0.0002512356,0.00020964528],"domain_scores_gemma":[0.99739003,0.00010123781,0.0000392921,0.0023745506,0.000027091075,0.00006779985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017887229,0.000076450815,0.00005977599,0.000013758213,0.000408369,0.00043138498,0.0034472134,0.000026432412,0.00007355645],"category_scores_gemma":[0.000020819863,0.00003792582,0.00001593839,0.00015346029,0.000039304952,0.00074068806,0.0026080676,0.00009270686,0.00022202922],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.8932643e-7,0.000052296822,0.000022044087,7.714632e-7,0.0000020352009,0.0000024268948,0.000018085762,0.0000015507306,0.000017323362,0.006593488,0.19635905,0.79693055],"study_design_scores_gemma":[0.00006000597,0.000018264438,0.00018275742,0.0000046569753,6.03797e-7,0.0000041190456,0.0000037436598,0.5257689,0.000039617185,0.00033408837,0.47353902,0.00004422304],"about_ca_topic_score_codex":0.000022652179,"about_ca_topic_score_gemma":0.00000603363,"teacher_disagreement_score":0.7968863,"about_ca_system_score_codex":0.000004859545,"about_ca_system_score_gemma":0.0000056509903,"threshold_uncertainty_score":0.64058375},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9389748,0.000041075356,0.060673527,0.000018467357,0.00006999903,0.000055443805,0.0000025032602,0.000018462933,0.00014575104],"genre_scores_gemma":[0.9960675,0.000003162703,0.003845517,0.000018008834,0.000017701632,1.55475e-7,0.000009921186,0.000001993937,0.00003598563],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995869,0.000032331394,0.000097442666,0.00014133724,0.00006231764,0.000079697566],"domain_scores_gemma":[0.999688,0.00004767046,0.00005274679,0.00019008756,0.0000023890204,0.000019071422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059487153,0.000054892942,0.000070261805,0.000023888002,0.00013938523,0.000011123514,0.00018091108,0.000025587275,0.000024501458],"category_scores_gemma":[0.0000033527785,0.00003175521,0.0000174833,0.000029844517,0.000055971977,0.00017749405,0.00020678864,0.000043390603,0.000003274804],"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":[9.614362e-7,0.000032983586,0.95675707,0.0000024740432,0.0000062043337,7.3574324e-7,0.0005963494,0.0000098945,0.02994839,0.0050501963,0.00009220518,0.007502558],"study_design_scores_gemma":[0.00011141915,0.000059855964,0.99206746,0.0000030795215,0.0000014504799,0.000010390486,0.000036947953,0.0019043195,0.005452394,0.00023359702,0.00006497456,0.00005413017],"about_ca_topic_score_codex":0.0014062619,"about_ca_topic_score_gemma":0.000043326516,"teacher_disagreement_score":0.057092786,"about_ca_system_score_codex":0.000008025432,"about_ca_system_score_gemma":0.0000022815532,"threshold_uncertainty_score":0.21258567},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42553893,0.00004680795,0.5265311,0.004766632,0.0030910845,0.00020294091,0.000026870892,0.00018151622,0.039614107],"genre_scores_gemma":[0.9374853,0.0000014898151,0.06069572,0.00029479922,0.000033184548,8.0953714e-7,5.221355e-7,0.0000016742623,0.0014865206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99968183,0.000008162146,0.0000571989,0.00008345192,0.00011024482,0.000059124617],"domain_scores_gemma":[0.99935734,0.000023454768,0.000026249685,0.0005349057,0.000038987266,0.000019064375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006463297,0.000029441964,0.000033760796,0.00000994042,0.000043929314,0.000027226102,0.00078287686,0.000017218701,0.000071303424],"category_scores_gemma":[0.000016799908,0.000014409843,0.000020975367,0.00007144836,0.000025335137,0.00017197483,0.00044397693,0.00007047768,0.0000137375855],"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":[0.0000016331549,0.00008514917,0.0062723677,0.000007372177,0.0000057199522,0.0000015164921,0.0002764303,0.000005687367,0.25191388,0.5157567,0.008718045,0.2169555],"study_design_scores_gemma":[0.000517744,0.00012779175,0.32089308,0.000030322923,0.0000055449505,0.000030011568,0.00006032594,0.051937044,0.39433402,0.013299243,0.21839297,0.00037190167],"about_ca_topic_score_codex":0.00007425929,"about_ca_topic_score_gemma":0.000023769899,"teacher_disagreement_score":0.5119463,"about_ca_system_score_codex":8.815957e-7,"about_ca_system_score_gemma":0.000019001458,"threshold_uncertainty_score":0.1454793},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020715224,0.00004685492,0.9772456,0.00048049472,0.0002611174,0.000043951448,0.0000050039184,0.00005531269,0.0011464161],"genre_scores_gemma":[0.9211508,0.0000023029727,0.07809425,0.00067895977,0.000046201996,0.0000037233856,0.000008192952,0.0000021328863,0.000013450949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999466,0.000033430213,0.0001104898,0.00010585674,0.00014913696,0.00013507552],"domain_scores_gemma":[0.9995556,0.000049989496,0.00005476564,0.00024093309,0.000042806165,0.00005593166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015014365,0.000052191896,0.00006668969,0.00004241648,0.00003299987,0.000027582968,0.00025213254,0.000025015866,0.00014300049],"category_scores_gemma":[0.000008396288,0.000038416056,0.000024191684,0.0001065439,0.000015264248,0.0008786325,0.00007342053,0.00004328249,0.00008470716],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000393646,0.00023201223,0.012561814,0.00004378691,0.000009803548,0.000002909326,0.00028244132,0.000010783281,0.0032285673,0.0016758393,0.00227944,0.9796687],"study_design_scores_gemma":[0.0016949119,0.0006555093,0.056465875,0.0005174122,0.00003928102,0.0000725165,0.00027550213,0.4673579,0.42927137,0.020504389,0.021757694,0.0013876397],"about_ca_topic_score_codex":0.00010971649,"about_ca_topic_score_gemma":0.0000026803095,"teacher_disagreement_score":0.978281,"about_ca_system_score_codex":0.00000863999,"about_ca_system_score_gemma":0.000021762151,"threshold_uncertainty_score":0.15665613},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013313845,0.0005494065,0.97619593,0.0016281132,0.0017182236,0.0010850703,0.00019399359,0.00033087985,0.016967019],"genre_scores_gemma":[0.60116327,0.0019278493,0.3495975,0.02441834,0.0013906469,0.0013354382,0.0020862948,0.00020790235,0.017872749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751264,0.000058627105,0.00095401605,0.00028691988,0.0005274227,0.00066035445],"domain_scores_gemma":[0.99724776,0.00034765835,0.00031405283,0.0015677183,0.00038246313,0.00014034286],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001045372,0.00031014738,0.00033625204,0.00018713783,0.0010693874,0.0011031864,0.002511284,0.00016057696,0.000007816479],"category_scores_gemma":[0.00023719751,0.00020444927,0.0002185129,0.00066778564,0.000108003514,0.001637564,0.001020837,0.0003810802,0.00010507474],"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":[0.00016225752,0.00025773508,0.001169208,0.0003862287,0.00028571443,0.000005999424,0.0020561349,0.00004963343,0.000056979527,0.31855872,0.22868294,0.44832844],"study_design_scores_gemma":[0.0018409257,0.00008494594,0.00059399096,0.00025083066,0.00002414737,0.000013729275,0.0001962127,0.13489464,0.00052021706,0.005027633,0.8562262,0.00032653182],"about_ca_topic_score_codex":0.000009867402,"about_ca_topic_score_gemma":0.0000051023458,"teacher_disagreement_score":0.6275433,"about_ca_system_score_codex":0.000092788076,"about_ca_system_score_gemma":0.0001442258,"threshold_uncertainty_score":0.9999338},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035040868,0.0003127064,0.9619851,0.00216212,0.0015212648,0.0004869606,0.00000940773,0.00033021186,0.029688137],"genre_scores_gemma":[0.9543646,0.000040990144,0.034042418,0.0026579187,0.0002170721,0.00089004607,0.000020446376,0.0000149767275,0.0077515566],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987305,0.000051086423,0.00019733353,0.00040527602,0.00021704179,0.00039879646],"domain_scores_gemma":[0.9988927,0.00008324602,0.000053558084,0.0008064145,0.000053840875,0.00011022837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021233896,0.00013362945,0.00016310807,0.000118574775,0.00013051892,0.0002465371,0.0011430851,0.000058413236,0.000012053065],"category_scores_gemma":[0.000033573593,0.0001116604,0.000054298584,0.0003581916,0.000035416437,0.0005061569,0.0006563623,0.0001389189,0.000039667015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012388258,0.00014655585,0.0011390505,0.000026400197,0.000036974496,0.000014735738,0.00012964242,0.00007129835,0.000076854434,0.02960168,0.04126507,0.9274793],"study_design_scores_gemma":[0.001528043,0.000021746357,0.28692853,0.000046947618,0.000018709236,0.0000074757586,0.0000333166,0.07400903,0.0034755797,0.006693962,0.6267159,0.00052075175],"about_ca_topic_score_codex":0.000025816027,"about_ca_topic_score_gemma":0.0000028060408,"teacher_disagreement_score":0.9508605,"about_ca_system_score_codex":0.0000297248,"about_ca_system_score_gemma":0.000030150199,"threshold_uncertainty_score":0.4553379},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0129968,0.010731941,0.9706222,0.0005963612,0.0016699077,0.0008567537,0.000017496335,0.00025026526,0.0022582957],"genre_scores_gemma":[0.4092036,0.0099575315,0.5768231,0.00074080535,0.0003477073,0.00039355553,0.00002562091,0.00007764597,0.0024304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954243,0.00024405637,0.0008020831,0.0017836327,0.00080380496,0.0009421651],"domain_scores_gemma":[0.9972803,0.0002638015,0.00024554526,0.0015674463,0.00028909912,0.00035382816],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043156702,0.0007257378,0.00082721893,0.00054885,0.0012381827,0.0010674855,0.0015224925,0.0001930351,0.00009066358],"category_scores_gemma":[0.000029892131,0.0005240421,0.00012377954,0.0019748262,0.00051804015,0.0017025816,0.0022319448,0.00048739955,0.000019482199],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018046828,0.00038668822,0.00097066484,0.00022616793,0.000084403095,0.00011186087,0.0006367537,0.0006791851,0.00015285921,0.0040923976,0.0012834852,0.9911951],"study_design_scores_gemma":[0.009227356,0.00047347439,0.014400126,0.0025108964,0.00015543401,0.00009954409,0.00033294197,0.95904386,0.0018154439,0.0028428608,0.00797335,0.0011247294],"about_ca_topic_score_codex":0.00028221536,"about_ca_topic_score_gemma":0.000011508061,"teacher_disagreement_score":0.99007034,"about_ca_system_score_codex":0.000046301062,"about_ca_system_score_gemma":0.00032715953,"threshold_uncertainty_score":0.9999695},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23819762,0.032066513,0.080217674,0.00006125599,0.029845905,0.002434945,0.003031873,0.00044008935,0.61370414],"genre_scores_gemma":[0.82568604,0.000116518975,0.04549863,0.00015255118,0.00287153,0.000089721456,0.008003365,0.00020663028,0.11737504],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9905516,0.0004292968,0.0031874387,0.0018056929,0.0033905513,0.00063543336],"domain_scores_gemma":[0.9873235,0.0012970711,0.0033860186,0.0014248217,0.006068893,0.0004996548],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009138033,0.001069949,0.0013365926,0.0012482546,0.0007130419,0.0015121372,0.0019288308,0.0011927392,0.000044026543],"category_scores_gemma":[0.0006362593,0.0010654146,0.001006741,0.0013722824,0.00045552963,0.004967085,0.00044729427,0.0011624412,0.000017340319],"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":[0.00683028,0.013948331,0.0027176144,0.0072969785,0.0040140115,0.0031949636,0.019979509,0.00048643837,0.5956935,0.062314153,0.01648098,0.2670432],"study_design_scores_gemma":[0.0054701925,0.004565073,0.018277988,0.010667997,0.0005185503,0.005122454,0.00087115995,0.02106229,0.7649557,0.011492169,0.15300885,0.003987568],"about_ca_topic_score_codex":0.00003485155,"about_ca_topic_score_gemma":0.0000012123165,"teacher_disagreement_score":0.5874884,"about_ca_system_score_codex":0.00033871023,"about_ca_system_score_gemma":0.0017533469,"threshold_uncertainty_score":0.9995244},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037399072,0.0010865667,0.95814383,0.00033111664,0.0016205317,0.00020652647,0.00052277785,0.00027998615,0.00040956776],"genre_scores_gemma":[0.84233755,0.00008683739,0.1527822,0.0004499892,0.0013963814,0.00002343119,0.0028408195,0.000022601032,0.000060209855],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780566,0.00007629465,0.00046699485,0.0006591098,0.0006865815,0.00030534557],"domain_scores_gemma":[0.9987091,0.000078468125,0.00022034158,0.00053554185,0.0002152519,0.00024131867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015440077,0.00023488949,0.00022523857,0.000055197248,0.0009897375,0.00047128525,0.0007225122,0.0000841224,0.000021752403],"category_scores_gemma":[0.00018816673,0.0002195863,0.000058344685,0.00043958312,0.000108616485,0.0033789172,0.0007254676,0.00023342183,0.000020364574],"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":[0.000091333895,0.00022475849,0.005493807,0.00011317547,0.00007247721,0.00024605295,0.000471919,0.0036107895,0.9026603,0.061203785,0.019166695,0.0066448855],"study_design_scores_gemma":[0.0011097095,0.00009062105,0.0005818928,0.00041263955,0.00003858051,0.0001501965,0.0000586892,0.5757229,0.16960882,0.00020467755,0.25125208,0.00076919765],"about_ca_topic_score_codex":0.00049377506,"about_ca_topic_score_gemma":0.000005818362,"teacher_disagreement_score":0.8053616,"about_ca_system_score_codex":0.00009438864,"about_ca_system_score_gemma":0.00026986786,"threshold_uncertainty_score":0.89544696},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007598049,0.008703608,0.9159338,0.0007955235,0.007302967,0.0006666552,0.000058408445,0.00018119001,0.06628191],"genre_scores_gemma":[0.03357193,0.0072255586,0.022218356,0.0008811238,0.0004414318,0.0002406529,0.0015290295,0.000051999257,0.9338399],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99654365,0.00015507471,0.00074541324,0.0011488757,0.0007814242,0.0006255765],"domain_scores_gemma":[0.99612486,0.0005593991,0.00041261353,0.0023042327,0.00045123952,0.00014766044],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039157888,0.00053415843,0.00048388404,0.000099780555,0.002288328,0.001678289,0.003923992,0.0002971141,0.00012884813],"category_scores_gemma":[0.0000888603,0.00032128708,0.00036276726,0.00094927376,0.00008562111,0.0006024204,0.0006383029,0.00061238144,0.00014555648],"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":[0.0000743695,0.00012986636,0.00001815869,0.0001265287,0.00078151363,0.000018507628,0.0005114092,0.000040094874,0.000041029645,0.46219096,0.027396444,0.5086711],"study_design_scores_gemma":[0.00039077713,0.00008842937,0.0013749633,0.00034180406,0.0006447131,0.0000033941678,0.0005356693,0.39185438,0.0006226969,0.011833373,0.5914219,0.00088789914],"about_ca_topic_score_codex":0.00030527957,"about_ca_topic_score_gemma":0.00088213565,"teacher_disagreement_score":0.8937154,"about_ca_system_score_codex":0.000054828884,"about_ca_system_score_gemma":0.0005744445,"threshold_uncertainty_score":0.99992394},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016979922,0.00030251034,0.117558174,0.0002641669,0.0008098316,0.00067373575,0.00015690533,0.000570304,0.8796474],"genre_scores_gemma":[0.0017867964,0.0001460169,0.014025403,0.0011945609,0.00081691303,0.00004158158,0.00006290078,0.00015377984,0.98177207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964246,0.00008194445,0.00053315586,0.001243189,0.0011131263,0.0006039509],"domain_scores_gemma":[0.9966449,0.00038274538,0.00020936028,0.0022856544,0.00014905781,0.00032829033],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040661864,0.00069747254,0.00068146014,0.00044847533,0.0003030789,0.00036528124,0.001999779,0.00048704763,0.00048129994],"category_scores_gemma":[0.00002182845,0.00057958945,0.0003553301,0.00003948522,0.00013567402,0.00020382834,0.0009144095,0.0008756183,0.0020118693],"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":[0.00020553157,0.0001256999,0.0000036576375,0.00008336231,0.0001294176,0.0007241627,0.0007728687,0.00006013139,0.00013094499,0.511959,0.05581782,0.42998737],"study_design_scores_gemma":[0.0024335925,0.0003593632,0.000026452257,0.0006214457,0.000041335683,0.00003986095,0.0000021083156,0.028386448,0.00055391237,0.008987351,0.9574566,0.0010915601],"about_ca_topic_score_codex":0.000056797817,"about_ca_topic_score_gemma":0.000021489179,"teacher_disagreement_score":0.90163875,"about_ca_system_score_codex":0.00010539921,"about_ca_system_score_gemma":0.00016332165,"threshold_uncertainty_score":0.99966556},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009023382,0.0013451288,0.14350277,0.00046298126,0.00073459244,0.0005672773,0.00002023346,0.0002838155,0.8530742],"genre_scores_gemma":[0.100004636,0.00007300233,0.041047864,0.0013752548,0.0024854187,0.00015932716,0.00011570263,0.0003055727,0.85443324],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969084,0.000049856695,0.00095782283,0.0006098895,0.0010578993,0.00041612462],"domain_scores_gemma":[0.9976512,0.000057262067,0.0008813905,0.0010247538,0.0002428996,0.00014249158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062779145,0.0004484587,0.000501583,0.00025563728,0.0002711102,0.00051276135,0.0034429373,0.0008712875,0.000019741208],"category_scores_gemma":[0.000022828921,0.00031861107,0.00026467486,0.00007138176,0.00015015356,0.0032277063,0.00061513286,0.0015759729,0.000014273008],"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":[0.000014422664,0.00000948019,0.000008270614,0.0005622373,0.00007151763,0.000004354581,0.002904823,0.00009031415,0.000120957506,0.2691106,0.039915476,0.68718755],"study_design_scores_gemma":[0.0011732515,0.00005464151,0.00011514911,0.005000161,0.00015219286,0.00013204588,0.00017678751,0.12607683,0.0002947745,0.015517749,0.85006076,0.0012456394],"about_ca_topic_score_codex":0.00001511976,"about_ca_topic_score_gemma":0.000004341427,"teacher_disagreement_score":0.8101453,"about_ca_system_score_codex":0.00025825747,"about_ca_system_score_gemma":0.0004029704,"threshold_uncertainty_score":0.99992657},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033925627,0.00015568396,0.99480414,0.00066874275,0.00071909727,0.00011383182,0.00003704003,0.000025595118,0.000083308434],"genre_scores_gemma":[0.36196038,0.00002517365,0.6370452,0.00024574852,0.00065064046,0.000005884713,0.000037932376,0.000007385652,0.000021676142],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855506,0.000039071834,0.000506372,0.0001566232,0.0006500571,0.00009280157],"domain_scores_gemma":[0.99738115,0.00006533285,0.0005513395,0.00032047054,0.0015563216,0.00012541359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018681533,0.00009820924,0.00016889458,0.0001950632,0.00003440501,0.0001297086,0.0019491422,0.00003277121,0.000012441847],"category_scores_gemma":[0.000024496288,0.000082960134,0.000076721444,0.00015066293,0.000032774147,0.00076453516,0.00039639857,0.00012445568,0.00000843389],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007794133,0.00058777456,0.0023188617,0.000021337522,0.0003462474,0.000059839615,0.0010081795,0.045388162,0.0008820431,0.11803597,0.056144442,0.7751292],"study_design_scores_gemma":[0.004022849,0.0005231161,0.008097544,0.00025219022,0.000052403808,0.0020553852,0.000043436376,0.38331535,0.007245599,0.19335645,0.40040702,0.0006286723],"about_ca_topic_score_codex":0.000008121216,"about_ca_topic_score_gemma":7.504822e-7,"teacher_disagreement_score":0.77450055,"about_ca_system_score_codex":0.000055684224,"about_ca_system_score_gemma":0.00019896596,"threshold_uncertainty_score":0.36220238},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027034162,0.00011691821,0.52312475,0.0002726896,0.000097327276,0.00009956587,0.000020324533,0.00014332947,0.4761224],"genre_scores_gemma":[0.00054004503,0.000065101645,0.22005771,0.000111074514,0.00021614158,0.0000050399,0.000019343684,0.00003327417,0.7789523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981126,0.000015241986,0.0002271694,0.0006979642,0.0006152367,0.00033178352],"domain_scores_gemma":[0.998286,0.000095409225,0.000098832534,0.0012168285,0.00012129884,0.00018164502],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013043369,0.00033815173,0.00036552455,0.00014393176,0.00014120238,0.00022354418,0.0014651894,0.00018373468,0.0007784382],"category_scores_gemma":[0.0000016045725,0.00018642267,0.000080365244,0.00003193181,0.00012252123,0.00043298528,0.00097633107,0.00030082263,0.0009090008],"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":[0.000019196677,0.000021053871,0.000011589743,0.000009525065,0.00005170804,0.00007300112,0.00003786759,0.000042363874,0.000012536601,0.86202794,0.04996733,0.08772586],"study_design_scores_gemma":[0.00058634556,0.00036761165,0.000111581976,0.00040472698,0.000015693726,0.000070665585,0.0000053256513,0.018087229,0.0001738392,0.0019420631,0.97747195,0.00076299615],"about_ca_topic_score_codex":0.000020438521,"about_ca_topic_score_gemma":0.000019881812,"teacher_disagreement_score":0.9275046,"about_ca_system_score_codex":0.000039246388,"about_ca_system_score_gemma":0.000116304596,"threshold_uncertainty_score":0.9998689},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32704195,0.000053514985,0.67166907,0.0006055378,0.00021418334,0.00018323008,9.945173e-7,0.00009642867,0.0001350835],"genre_scores_gemma":[0.9374645,0.0000015125453,0.06186655,0.00044091823,0.00015276055,0.000010958587,0.0000013499267,0.000010178234,0.00005126688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883556,0.000045199995,0.00019514536,0.0003540231,0.00023716602,0.00033290873],"domain_scores_gemma":[0.9991358,0.00014717336,0.000072553645,0.00044392538,0.000035815752,0.00016473382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057588797,0.00012251627,0.00012313256,0.00002003917,0.000399911,0.0007939621,0.00060014945,0.000025996998,3.9805363e-7],"category_scores_gemma":[0.000034389264,0.00008360315,0.000021618025,0.00014090294,0.000030189303,0.00037075003,0.0014714807,0.00012730091,0.00003444788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036593592,0.00008013618,0.0020462917,0.000024651285,0.000029614032,0.000020812442,0.008929904,0.054176535,0.0037511191,0.013881257,0.002650386,0.9143727],"study_design_scores_gemma":[0.0008166264,0.0000815799,0.002516411,0.000084954045,0.000005758666,0.000025350371,0.000428297,0.9799679,0.0044723777,0.008537207,0.002662926,0.00040060596],"about_ca_topic_score_codex":0.00006551255,"about_ca_topic_score_gemma":0.0000028484,"teacher_disagreement_score":0.9257914,"about_ca_system_score_codex":0.000027773092,"about_ca_system_score_gemma":0.000038800554,"threshold_uncertainty_score":0.7656195},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020977633,0.000048754944,0.97563195,0.0014330897,0.0005474216,0.0003365561,0.000005959309,0.00022639483,0.00079226296],"genre_scores_gemma":[0.60418075,0.0000029908435,0.39421612,0.000997429,0.00053572515,0.000039702314,0.000005108172,0.000009202854,0.0000129583295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758166,0.00009244618,0.00028629586,0.000725656,0.0007745288,0.0005394331],"domain_scores_gemma":[0.9972298,0.0002063099,0.00009417694,0.0017764011,0.00027064036,0.00042264364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017158152,0.00019208292,0.00018406153,0.000104363986,0.00087192626,0.0009163247,0.0032891997,0.000047073238,0.000022323955],"category_scores_gemma":[0.000062262465,0.00011936469,0.00006174592,0.0010895627,0.0017208265,0.00095483894,0.0023616953,0.00023449924,0.00019055602],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004408985,0.00003865061,0.000014915447,0.000002168359,0.0000026441958,0.00004464478,0.0004150731,0.00006537784,0.00040661945,0.9433306,0.0003452497,0.05532966],"study_design_scores_gemma":[0.00029163974,0.000064904365,0.00020554652,0.000013608365,0.0000047887397,0.001154362,0.00001103807,0.8332849,0.0001642032,0.15348189,0.011083521,0.00023960667],"about_ca_topic_score_codex":0.000041268722,"about_ca_topic_score_gemma":0.0000076293045,"teacher_disagreement_score":0.8332195,"about_ca_system_score_codex":0.00006462317,"about_ca_system_score_gemma":0.00020367879,"threshold_uncertainty_score":0.883614},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020395545,0.0005726718,0.99769807,0.000052033884,0.00041432862,0.00015078945,0.00001079464,0.00006368524,0.0008336848],"genre_scores_gemma":[0.089893706,0.000061464525,0.90905756,0.00023225845,0.00031394124,0.000011272565,0.000023920244,0.000017369182,0.00038853867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909854,0.000038219474,0.00020531115,0.0002504386,0.00015031792,0.00025716043],"domain_scores_gemma":[0.99910754,0.00018041069,0.000102045226,0.00043563513,0.00009387348,0.00008049512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023590281,0.000113241294,0.0001952138,0.000041826555,0.00009464452,0.000044981913,0.0004660615,0.00007416118,0.0000142962745],"category_scores_gemma":[0.00003306256,0.00009397068,0.00007455022,0.00026014587,0.000031353953,0.00025751957,0.00006886236,0.00009455376,0.0000033992624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018060031,0.00032878763,0.0008344718,0.000037104077,0.00007046055,0.000011319438,0.0004135356,0.02339812,0.00013630872,0.02229117,0.0785772,0.8738835],"study_design_scores_gemma":[0.0004132901,0.00010716136,0.00022390495,0.00003644912,0.0000053987915,0.0000063398634,0.000006456755,0.92076015,0.0006033173,0.00085814577,0.07685971,0.000119683034],"about_ca_topic_score_codex":0.000019285742,"about_ca_topic_score_gemma":0.000004196806,"teacher_disagreement_score":0.897362,"about_ca_system_score_codex":0.000011645775,"about_ca_system_score_gemma":0.000045961267,"threshold_uncertainty_score":0.3832013},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000066101393,0.0010388171,0.25003493,0.00014299662,0.0011278054,0.00032535126,0.00040994032,0.000106107356,0.74680746],"genre_scores_gemma":[0.00046963818,0.009841667,0.30223644,0.00007974142,0.0007424636,0.000044008004,0.00020990311,0.00014339907,0.68623275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99720126,0.00003746478,0.0009297513,0.00072746567,0.00081356394,0.00029049462],"domain_scores_gemma":[0.9963586,0.0003437215,0.0009254651,0.0018390763,0.00037486744,0.0001583015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020308256,0.00040571918,0.0007439919,0.00039673978,0.00008161527,0.000026842188,0.0018450739,0.00030688228,0.00029749877],"category_scores_gemma":[0.00003987756,0.00032437645,0.00032277775,0.000120252625,0.00026454666,0.0004916131,0.0008717031,0.00027540777,0.00006731615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012253193,0.00009514334,0.000031605003,0.0001108879,0.00016398118,0.000036877394,0.00029459575,0.000013761314,0.00014554893,0.73387873,0.01748489,0.24773175],"study_design_scores_gemma":[0.0012949602,0.00034538945,0.00048217844,0.0011428044,0.000116944975,0.000028339256,0.000013207848,0.0035270923,0.0011742343,0.35290036,0.63786733,0.0011071783],"about_ca_topic_score_codex":0.000037265854,"about_ca_topic_score_gemma":0.0000024647416,"teacher_disagreement_score":0.6203824,"about_ca_system_score_codex":0.000025147501,"about_ca_system_score_gemma":0.00018433983,"threshold_uncertainty_score":0.99992085},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013212765,0.0005725579,0.24476841,0.0034963777,0.003625864,0.00046603248,0.00013628248,0.00007540121,0.74684584],"genre_scores_gemma":[0.05318533,0.0949937,0.6500324,0.016965471,0.0033404583,0.00016739941,0.0011529394,0.00011425732,0.18004803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976417,0.000013330431,0.0006189961,0.00044263317,0.0010891093,0.00019421862],"domain_scores_gemma":[0.9980122,0.00006285232,0.00037793038,0.00114296,0.0003562667,0.000047780708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075570244,0.00023952841,0.00026781787,0.0005214127,0.00023957073,0.00034836054,0.003952678,0.000054321496,0.000019166024],"category_scores_gemma":[0.000011529354,0.00016845843,0.000034234086,0.00021922513,0.0008007914,0.008001614,0.0056573534,0.00019664648,0.000036610836],"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":[0.000014951151,0.000013409709,0.000009854808,0.000035272504,0.000059184833,0.000008068904,0.0013148069,0.00007975448,2.06596e-7,0.5825204,0.007836259,0.40810782],"study_design_scores_gemma":[0.00026799677,0.00010740546,0.00052947085,0.00039680788,0.00000696678,0.00004724604,0.0002898004,0.031862777,0.0000049130695,0.014168755,0.9520589,0.00025896024],"about_ca_topic_score_codex":0.000008356455,"about_ca_topic_score_gemma":0.0000086521295,"teacher_disagreement_score":0.9442226,"about_ca_system_score_codex":0.0000878947,"about_ca_system_score_gemma":0.000043257758,"threshold_uncertainty_score":0.7345125},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01637092,0.00018936023,0.4044782,0.0556435,0.00024349603,0.00049548276,0.000018428556,0.00048546723,0.5220751],"genre_scores_gemma":[0.82854366,0.00013018388,0.11170621,0.010956383,0.0002990954,0.000063073094,0.000015353999,0.000029769366,0.04825628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990706,0.00007405844,0.00011949459,0.00023772665,0.0003183754,0.00017976157],"domain_scores_gemma":[0.9988221,0.00029464872,0.000012490912,0.0008007732,0.000013556932,0.00005641301],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024875536,0.000086369575,0.00006867215,0.00005748042,0.00016265169,0.00012057413,0.0010588318,0.000022436172,0.0023887956],"category_scores_gemma":[0.0000063231105,0.000049161205,0.00004856238,0.00032620362,0.000030665928,0.00036109824,0.000034965506,0.00013930112,0.00028285215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020235182,0.000071719805,0.000010438367,0.0000030408353,0.0000071066333,0.000007514213,0.00043492942,0.00025173704,0.0003842099,0.028728617,0.055671394,0.91440904],"study_design_scores_gemma":[0.0008620176,0.000118925534,0.0014132141,0.00005185564,0.0000050657777,0.0000054782836,0.000025311869,0.56106347,0.004869786,0.012898663,0.41840386,0.00028237118],"about_ca_topic_score_codex":0.000037170154,"about_ca_topic_score_gemma":0.00014421728,"teacher_disagreement_score":0.9141267,"about_ca_system_score_codex":0.000008756659,"about_ca_system_score_gemma":0.000030068917,"threshold_uncertainty_score":0.9985232},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15341513,0.042418506,0.7829149,0.008021551,0.010740229,0.0005249222,0.00030853134,0.000045911205,0.001610355],"genre_scores_gemma":[0.63243806,0.0026058888,0.3566302,0.0015612391,0.005685927,0.0000044631233,0.000028978337,0.00011288036,0.0009323918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969624,0.00016179697,0.0009887945,0.00035489365,0.0011608127,0.00037126557],"domain_scores_gemma":[0.9968602,0.0001751432,0.0011612223,0.00058996363,0.00063325814,0.0005802302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010069144,0.00031999644,0.00069215905,0.00027933356,0.00008711681,0.00023250429,0.0010047817,0.00016530849,0.000028353095],"category_scores_gemma":[0.00019283881,0.00023261912,0.00021253132,0.00031661591,0.0002079146,0.0009514901,0.00058953,0.0005535024,0.000029585759],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015706344,0.0017042977,0.0016821136,0.00047238462,0.0014149068,0.002342054,0.0140187,0.0010540232,0.0022073002,0.008675102,0.25638157,0.7084769],"study_design_scores_gemma":[0.026612503,0.027033819,0.011899858,0.0077791964,0.0013345979,0.003274347,0.0027254631,0.64554197,0.023279764,0.06351226,0.1836017,0.0034045207],"about_ca_topic_score_codex":0.00003618547,"about_ca_topic_score_gemma":7.561487e-7,"teacher_disagreement_score":0.7050724,"about_ca_system_score_codex":0.00006310073,"about_ca_system_score_gemma":0.00031371528,"threshold_uncertainty_score":0.94859326},"labels":[],"label_agreement":null}]}