{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1336,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":1336,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"3b3b69ad4986","filters":{"topic":"Algorithms and Data Compression"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05573241774715602,"gpt":0.2719552118369395,"spread":0.2162227940897835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001355826,0.000519898,0.001086351,0.0004000372,0.0004440732,0.0004987544,0.003210209,0.0002388674,0.00007192506],"category_scores_gemma":[0.0000306059,0.0004269974,0.0003058672,0.001849518,0.00004802222,0.001831192,0.001063132,0.0008898102,0.0003407767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002124803,"about_ca_system_score_gemma":0.000572427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002108198,"about_ca_topic_score_gemma":0.000006117964,"domain_scores_codex":[0.9975155,0.0002195101,0.000258156,0.001078281,0.0004407564,0.0004877821],"domain_scores_gemma":[0.997925,0.0001007132,0.0003543645,0.001124044,0.0001286805,0.0003671958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003434193,0.00003240674,0.000002335291,0.001398714,0.00008186023,0.0007138331,0.00006098922,3.647413e-7,2.443891e-7,0.002800548,0.0005198669,0.9943854],"study_design_scores_gemma":[0.0002222508,0.0001071727,0.000001221338,0.004379424,0.0001488397,0.00007671137,0.00002535128,0.00002535084,0.000001409698,0.00001172682,0.9944533,0.0005472705],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.395226e-7,0.8344511,0.161791,0.00004831648,0.0001618073,0.0007039825,0.0001823358,0.0005630442,0.002098088],"genre_scores_gemma":[9.436365e-7,0.9187886,0.07968608,0.00004326003,0.0001439099,0.000005382625,0.0003682999,0.00004886783,0.0009146249],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9939334,"threshold_uncertainty_score":0.9998182,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01257153537582592,"gpt":0.2570000966085654,"spread":0.2444285612327395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002877924,0.0001029329,0.000201606,0.00009956268,0.00009007094,0.00004028133,0.0005906328,0.00003510354,0.00002417345],"category_scores_gemma":[0.00006904569,0.00008832983,0.00005645952,0.0002182876,0.00001942016,0.0002962335,0.0003119447,0.0001695971,0.000004779636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008426187,"about_ca_system_score_gemma":0.00001472367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001433479,"about_ca_topic_score_gemma":0.000006045932,"domain_scores_codex":[0.9990502,0.0000799035,0.0002547769,0.0002183046,0.0002262018,0.0001705955],"domain_scores_gemma":[0.9993237,0.0000561207,0.0001733539,0.0003496883,0.00004867672,0.00004845458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000361148,0.0001476012,0.0223073,0.00009879423,0.00002144139,0.00002945185,0.00217315,0.02789392,0.02091124,0.007085649,0.0004690984,0.9188262],"study_design_scores_gemma":[0.0004402649,0.0003240778,0.021916,0.0001310633,0.000006084716,0.00001740623,0.00003018395,0.9600604,0.004901212,0.000777822,0.0111894,0.0002060849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07549964,0.0004412319,0.9213738,0.0003280406,0.0002323205,0.00006994044,0.000003568863,0.0001317409,0.001919711],"genre_scores_gemma":[0.9626423,0.00001524472,0.03705162,0.00006543299,0.00004169533,7.022889e-7,0.000008362369,0.000005963895,0.0001686986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9321665,"threshold_uncertainty_score":0.3601986,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2085239895237908,"gpt":0.3744306107962284,"spread":0.1659066212724375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00130605,0.0001343909,0.0001484583,0.0003226646,0.0005025326,0.0007123923,0.001565268,0.00009038977,0.0001507661],"category_scores_gemma":[0.00005792727,0.0001173494,0.00005292392,0.0009310833,0.00005263073,0.001039837,0.0005576097,0.0003890582,0.0008034891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011586,"about_ca_system_score_gemma":0.0001586643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000036522,"about_ca_topic_score_gemma":0.000003793022,"domain_scores_codex":[0.9972675,0.0002223514,0.0002285394,0.0006074698,0.0009640348,0.0007101012],"domain_scores_gemma":[0.9982404,0.00005583962,0.00003672137,0.00110516,0.0003238522,0.0002380354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001363668,0.0002002746,0.00001952308,0.00001285551,0.00001297192,0.0000885431,0.0007834302,0.0002958679,0.7620985,0.02859981,0.006369177,0.2015054],"study_design_scores_gemma":[0.001335932,0.001489979,0.03764862,0.00004036762,0.000006196723,0.0001133313,0.0001081275,0.2427864,0.007864508,0.02496697,0.6825506,0.001088979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07093951,0.006150089,0.8956273,0.009207138,0.0004826525,0.001036107,0.00002473983,0.0004592837,0.01607323],"genre_scores_gemma":[0.9229944,0.0004967198,0.07086654,0.0006059538,0.001388114,0.00004206041,0.0001066626,0.00002147719,0.003478056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8520549,"threshold_uncertainty_score":0.9999745,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1153428195483115,"gpt":0.3164656778829131,"spread":0.2011228583346016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000309192,0.0001670044,0.0001248814,0.0001311076,0.0003014723,0.0003905984,0.001622319,0.0001018411,0.00005738358],"category_scores_gemma":[0.0004714458,0.0001459261,0.00004387678,0.0004782535,0.00006592059,0.001579198,0.0003574228,0.0003864329,0.0006626029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001728727,"about_ca_system_score_gemma":0.00007111704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001528657,"about_ca_topic_score_gemma":0.0001443024,"domain_scores_codex":[0.9984847,0.0001274977,0.0002609176,0.0005394504,0.0003320378,0.0002554012],"domain_scores_gemma":[0.9969554,0.0003475122,0.0001081661,0.002364704,0.0001134299,0.0001107791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002166147,0.000342248,0.004535983,0.000006223268,0.0000227202,0.00002629025,0.0009542956,0.0001100088,0.4519017,0.08969273,0.3611196,0.09126659],"study_design_scores_gemma":[0.001638819,0.0004179095,0.4225212,0.00007307317,0.00001995684,0.00004848029,0.00005968312,0.1549614,0.05240729,0.0209223,0.3450294,0.001900528],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09228618,0.000009077189,0.8682058,0.03535791,0.001794282,0.0003715891,0.00007363215,0.0004644681,0.001437004],"genre_scores_gemma":[0.8942145,0.000008327051,0.09627791,0.008443297,0.0003719966,0.00009980443,0.0003324892,0.00001980526,0.0002319422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8019282,"threshold_uncertainty_score":0.8516641,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0167703244268879,"gpt":0.2608292871613097,"spread":0.2440589627344218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002934815,0.0002500488,0.0002028549,0.0002942,0.0007601408,0.0002026925,0.000736518,0.00009881325,0.00002200085],"category_scores_gemma":[0.00001350855,0.0002089819,0.00004492034,0.0007761644,0.00007860581,0.0008448109,0.00006394739,0.0002854784,0.00003766082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007350184,"about_ca_system_score_gemma":0.00007264358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002441733,"about_ca_topic_score_gemma":0.0002411228,"domain_scores_codex":[0.9981673,0.0000291885,0.0002834296,0.0006858741,0.000410869,0.0004233779],"domain_scores_gemma":[0.9981143,0.0002724414,0.00006960762,0.001055865,0.000100613,0.0003871014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006698267,0.0003366775,0.0003384356,0.00001479561,0.00005210418,0.00001898752,0.0006571586,0.001830945,0.0008252467,0.001440907,0.0002761323,0.9941416],"study_design_scores_gemma":[0.0102209,0.004235323,0.1271848,0.0007662281,0.0003071533,0.00136146,0.001655443,0.1672382,0.05943922,0.009770387,0.6127023,0.005118605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001609334,0.0001354578,0.9958677,0.0008610297,0.0001981171,0.0005260885,0.000063876,0.0003250101,0.0004133626],"genre_scores_gemma":[0.3288807,0.0001079788,0.6693892,0.0006814072,0.0001196107,0.0002365651,0.00002372218,0.00003245772,0.0005283624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.989023,"threshold_uncertainty_score":0.8522035,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03584947236627194,"gpt":0.3315742707934994,"spread":0.2957247984272275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004726377,0.0001202965,0.0001284726,0.0001275745,0.0008159103,0.0008115542,0.0005164207,0.00005459868,0.0003949217],"category_scores_gemma":[0.00003747647,0.00008583366,0.00001651913,0.0006712871,0.0001477293,0.001405755,0.0002479553,0.0002857234,0.0001832335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003110489,"about_ca_system_score_gemma":0.00004482328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004465804,"about_ca_topic_score_gemma":0.0004219021,"domain_scores_codex":[0.9980927,0.0002602666,0.0001521229,0.0004932821,0.0006170481,0.0003845638],"domain_scores_gemma":[0.9984814,0.00009666265,0.00001174411,0.0008896836,0.000297725,0.0002228091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002451788,0.003153918,0.04994977,0.00007730133,0.0001617148,0.0009673906,0.0126487,0.003254668,0.008355089,0.09514139,0.02073332,0.8053116],"study_design_scores_gemma":[0.002009255,0.0003410314,0.007737054,0.00004609321,0.000004065006,0.00009574076,0.0002442499,0.9845737,0.00221627,0.00007524116,0.002414615,0.0002426771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5107361,0.0002087228,0.483281,0.0005631644,0.00006446425,0.0004811745,0.00002186672,0.0001111624,0.004532382],"genre_scores_gemma":[0.9699847,0.0001584362,0.02726181,0.0000300403,0.00007494852,0.00006666726,0.00004519847,0.00001277245,0.002365466],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.981319,"threshold_uncertainty_score":0.7825836,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07356066266408752,"gpt":0.287019720484159,"spread":0.2134590578200715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003797966,0.0003604875,0.001735713,0.0005018602,0.0001768271,0.00008651624,0.003956224,0.0003139968,0.0001076591],"category_scores_gemma":[0.00002506765,0.0003540583,0.0005361752,0.0007720087,0.0002618825,0.001395292,0.001280806,0.0003215756,0.00002490405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006860647,"about_ca_system_score_gemma":0.0003176693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005915336,"about_ca_topic_score_gemma":0.00002926637,"domain_scores_codex":[0.9979572,0.0002172149,0.0004796963,0.0006296829,0.0004288833,0.000287357],"domain_scores_gemma":[0.9968958,0.0001710053,0.001435513,0.001089134,0.0002538369,0.0001547077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002648093,0.00005538295,0.000008688434,0.003019175,0.00009221764,0.0000113968,0.00006404397,0.000003456053,0.000002345035,0.001246236,0.001548569,0.9939458],"study_design_scores_gemma":[0.0003303484,0.00005718248,0.00001770463,0.00411896,0.0002304161,0.00005990859,0.00005703968,0.00175315,0.00001046115,0.0001199902,0.9928812,0.0003635715],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000008042973,0.3895606,0.6085314,0.00003305568,0.0004242393,0.0003217353,0.00005051969,0.00004678317,0.001023647],"genre_scores_gemma":[0.00001241498,0.8195707,0.1796879,0.000007737845,0.000134134,0.000001975777,0.00006954404,0.00001660707,0.0004989099],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9935822,"threshold_uncertainty_score":0.9998912,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03950130813966558,"gpt":0.2181354447543569,"spread":0.1786341366146914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003362756,0.00004801954,0.00006303655,0.00002447455,0.0001568055,0.0001315655,0.002029828,0.00001498877,0.00001013617],"category_scores_gemma":[0.0002874046,0.00002025819,0.00003801023,0.0001008479,0.00001782529,0.0002583225,0.0008172501,0.0002026585,0.000004395015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001385439,"about_ca_system_score_gemma":0.000006827659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003278549,"about_ca_topic_score_gemma":5.497822e-7,"domain_scores_codex":[0.9994441,0.00003951869,0.0001356554,0.00006282618,0.0002165239,0.0001013997],"domain_scores_gemma":[0.9988925,0.0001835498,0.0001652877,0.0006920411,0.00002903083,0.00003758422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003772558,0.0005459099,0.01367378,0.00006278468,0.000201363,0.0001420923,0.006269922,0.006943602,0.01118348,0.1155013,0.2071373,0.6383007],"study_design_scores_gemma":[0.003642634,0.0012968,0.1415029,0.002753377,0.00008861007,0.002851995,0.0003020833,0.3028559,0.02184817,0.4132554,0.1086545,0.0009475606],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9546607,0.00121018,0.01802999,0.02440606,0.0008676545,0.0001137391,9.613982e-7,0.00001600886,0.0006947476],"genre_scores_gemma":[0.9947934,0.00009733003,0.004653426,0.0002485104,0.0001123749,3.400501e-7,1.244884e-8,0.000002685344,0.00009197501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6373531,"threshold_uncertainty_score":0.3771958,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0130856715713156,"gpt":0.2360714225352947,"spread":0.2229857509639791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001944419,0.00005978956,0.00005041523,0.00008101902,0.0001923338,0.0004115827,0.00007700154,0.00002687078,0.000002621973],"category_scores_gemma":[0.00004962961,0.00005585283,0.00001071152,0.0001977474,0.00000688814,0.002802794,0.00003859657,0.00006035636,0.00001512828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001954578,"about_ca_system_score_gemma":0.00002276012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001663589,"about_ca_topic_score_gemma":0.000001226853,"domain_scores_codex":[0.9994743,0.00002721859,0.0001852671,0.00008430855,0.000136023,0.00009291395],"domain_scores_gemma":[0.9996867,0.0000260788,0.0001027494,0.0000603164,0.00008431679,0.0000398976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001892869,0.00001864705,0.001204217,0.0000452079,0.000006021415,3.263847e-7,0.002068381,0.02273725,0.0000658127,0.2949246,0.0005534595,0.6783742],"study_design_scores_gemma":[0.0002598437,0.00002982658,0.003166568,0.00002235265,0.000001460821,0.00002429241,0.00006321479,0.9698035,0.0001726772,0.008047234,0.01830435,0.0001047363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01270667,0.00002325369,0.9840382,0.00005533399,0.0001618884,0.00008896536,6.640166e-7,0.000140259,0.002784748],"genre_scores_gemma":[0.9022503,0.000006884106,0.09756918,0.0001247919,0.00001198607,0.000005526522,0.00001844332,0.000001707715,0.00001110528],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9470662,"threshold_uncertainty_score":0.3968902,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01561185102377989,"gpt":0.273821400177054,"spread":0.2582095491532741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005603561,0.00009356069,0.00008578249,0.0001161652,0.0001146189,0.0001186644,0.0004435837,0.00005121906,0.0002237491],"category_scores_gemma":[0.000009811008,0.00007101169,0.00003013062,0.0002540165,0.00003247772,0.0003181859,0.00008553061,0.0001085081,0.0003080104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005000397,"about_ca_system_score_gemma":0.00006042922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005851829,"about_ca_topic_score_gemma":0.000003741088,"domain_scores_codex":[0.9988275,0.00003637141,0.0001728936,0.000268086,0.0004451453,0.0002500511],"domain_scores_gemma":[0.9991506,0.0001604407,0.00002779284,0.0004823023,0.00006445113,0.000114417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001873669,0.00006134553,0.000008866842,0.000003334766,0.000001434583,0.00001932885,0.00003063794,0.000477056,0.00009348353,0.008873465,0.001156827,0.9892724],"study_design_scores_gemma":[0.0002814019,0.0001158292,0.001861961,0.00001620178,8.256899e-7,0.000003941533,0.00001967382,0.9873565,0.008209765,0.0002324407,0.001800656,0.0001007417],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004566096,0.000005942824,0.98807,0.0003621448,0.000201913,0.0001102855,0.000001622648,0.0002636464,0.01052786],"genre_scores_gemma":[0.4724939,6.363888e-7,0.5259946,0.001089153,0.00007199188,0.00000318305,0.00001713539,0.00000625456,0.0003231914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9891716,"threshold_uncertainty_score":0.3958953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01574918514338506,"gpt":0.2803758415423402,"spread":0.2646266563989551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009419401,0.00009239838,0.0001041553,0.00003906438,0.0001661245,0.0001638087,0.0003251716,0.00004450536,0.0001926101],"category_scores_gemma":[0.0004957374,0.00007490659,0.00002075258,0.0002180989,0.00007142655,0.005740998,0.0002712323,0.00009664096,0.00003106697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001299031,"about_ca_system_score_gemma":0.00003482341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002418854,"about_ca_topic_score_gemma":0.000002205814,"domain_scores_codex":[0.9991642,0.00004310345,0.0001783408,0.0002804928,0.0001773879,0.0001564708],"domain_scores_gemma":[0.9989421,0.0003457417,0.000139509,0.0003400427,0.0001709368,0.00006164024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005353809,0.0006503753,0.01126833,0.0002136449,0.00009310754,0.00003226975,0.2343934,0.0001342087,0.05028265,0.08455782,0.01334963,0.604971],"study_design_scores_gemma":[0.002555855,0.001428869,0.02549001,0.0007436132,0.00008927903,0.0007347002,0.06568194,0.08565506,0.1091863,0.03845217,0.6668377,0.003144526],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05378804,0.0003898899,0.9442469,0.0004369846,0.0003013934,0.0001154197,0.000002372346,0.00007772211,0.0006412659],"genre_scores_gemma":[0.6088639,0.0001773437,0.3903575,0.0004542365,0.00003457112,0.00003410336,0.000003396886,0.000005604189,0.00006930596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6534881,"threshold_uncertainty_score":0.4162085,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02148647027400059,"gpt":0.238584043247377,"spread":0.2170975729733765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001193897,0.0001708158,0.0001764739,0.00008412843,0.0002248146,0.0002554013,0.0006145733,0.00007364666,0.00002590631],"category_scores_gemma":[0.00002556237,0.0001314849,0.00003371138,0.000190399,0.00007764463,0.001573849,0.0006807072,0.0001414352,0.0001471081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002409514,"about_ca_system_score_gemma":0.000007257479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007805942,"about_ca_topic_score_gemma":4.270295e-7,"domain_scores_codex":[0.9989472,0.00003578318,0.0002707783,0.0001985672,0.0002867859,0.0002608841],"domain_scores_gemma":[0.9990066,0.0001112664,0.0001313754,0.0005524023,0.00005228383,0.0001461258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003643261,0.00007185995,0.0001776538,0.0001054138,0.00001525547,0.00001216761,0.003080603,0.00009029593,0.000985178,0.005785489,0.01157638,0.9780961],"study_design_scores_gemma":[0.0003522176,0.00008035877,0.0009750561,0.00009714007,0.000004155529,0.00004943498,0.00005306657,0.9814395,0.001191696,0.0003502422,0.01520043,0.000206682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01014077,0.0004212996,0.9797127,0.0002464429,0.0004198195,0.0004226744,0.00003044639,0.0003308486,0.008274978],"genre_scores_gemma":[0.4831351,0.0004203085,0.5148339,0.0009265328,0.0001521107,0.00004883166,0.00002694529,0.00002064825,0.000435598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9813492,"threshold_uncertainty_score":0.5361799,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.125841513504027,"gpt":0.326270749231966,"spread":0.200429235727939,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006866207,0.00008331861,0.000108157,0.00003777754,0.0001646623,0.00006152405,0.0007749632,0.00003761768,0.0001266991],"category_scores_gemma":[0.00004694941,0.00004669423,0.00005663539,0.0001701579,0.00003829916,0.000315317,0.0002286929,0.00005083454,0.00001362689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707914,"about_ca_system_score_gemma":0.00001752514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003691091,"about_ca_topic_score_gemma":0.000002709492,"domain_scores_codex":[0.9988036,0.00006581896,0.0001957799,0.0002228212,0.0005699323,0.0001420258],"domain_scores_gemma":[0.9986304,0.0002791527,0.0001108326,0.0006241729,0.0003184415,0.00003697086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003471672,0.00009342821,0.000036159,0.000007843476,0.00001210139,2.508832e-7,0.000211842,0.0009117508,0.000716382,0.008575198,0.01249126,0.9769403],"study_design_scores_gemma":[0.0006043383,0.00004794286,0.0008071303,0.00001880346,0.00001643736,0.000003852299,0.00001826461,0.9846759,0.003307327,0.002171629,0.00825726,0.00007112412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001312245,0.001046666,0.9949529,0.0005454665,0.0004516458,0.0004762967,0.000009919913,0.00005111498,0.001153792],"genre_scores_gemma":[0.8531061,0.0001099907,0.1455445,0.0002329611,0.0001641707,0.000139517,0.00001077778,0.00001111827,0.0006808886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9837641,"threshold_uncertainty_score":0.1904135,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02422048326305505,"gpt":0.2379167837357343,"spread":0.2136963004726792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001384733,0.0001044948,0.0002058251,0.0000950003,0.000589972,0.0008894406,0.0008087544,0.00003724661,0.000001811849],"category_scores_gemma":[0.00000667225,0.00005279009,0.00005367041,0.0002348557,0.0001664884,0.001005543,0.0002246073,0.00009802489,8.060415e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001132638,"about_ca_system_score_gemma":0.0000283137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003836641,"about_ca_topic_score_gemma":3.809919e-7,"domain_scores_codex":[0.9987456,0.00006277658,0.0004269774,0.000217311,0.0003555976,0.0001917502],"domain_scores_gemma":[0.9990142,0.0002662175,0.0003459383,0.0001509266,0.0001300842,0.00009265587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003188392,0.0003115401,0.00241172,0.0008569917,0.0003155924,0.00006556592,0.01760254,0.03450052,0.000293217,0.1690557,0.03927964,0.7352751],"study_design_scores_gemma":[0.0004179859,0.0005637092,0.0005754994,0.0002185315,0.0000120347,0.001242165,0.0001142004,0.9912538,0.000009933506,0.0007830718,0.004718457,0.00009060106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01302014,0.006389637,0.9769832,0.001745619,0.0009346958,0.0002966806,0.000002201964,0.00002989883,0.0005979491],"genre_scores_gemma":[0.7948976,0.0002147503,0.2044459,0.00005845481,0.0002392778,0.00000712162,1.259594e-7,0.00000438416,0.0001324516],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9567533,"threshold_uncertainty_score":0.8576897,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008969900852929844,"gpt":0.2570800764681503,"spread":0.2481101756152204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004621488,0.0003986147,0.0003465864,0.0002276178,0.0007731514,0.0005946356,0.001088927,0.0001568163,0.00002903456],"category_scores_gemma":[0.00003810518,0.0003288819,0.0002052313,0.000460554,0.00004312114,0.0009085161,0.0002862464,0.0002693249,0.0001281529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078982,"about_ca_system_score_gemma":0.0001046873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001057569,"about_ca_topic_score_gemma":0.00002218427,"domain_scores_codex":[0.9970716,0.00009971038,0.0004888374,0.0009739427,0.0005790313,0.0007869253],"domain_scores_gemma":[0.9983193,0.0002199132,0.0001075594,0.001083206,0.0001405232,0.000129444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003387009,0.002317634,0.0003193447,0.0001334883,0.0002374163,0.0001054098,0.001138558,0.03625705,0.03504686,0.713357,0.08281572,0.1279328],"study_design_scores_gemma":[0.003038549,0.001304524,0.0008025909,0.0001681269,0.00002868795,0.00001756974,0.00002950123,0.9078004,0.01573731,0.003731263,0.06640255,0.0009389583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003877284,0.0001458977,0.9877126,0.002408786,0.0008979346,0.0009985911,0.0003434785,0.0003987123,0.003216733],"genre_scores_gemma":[0.6749784,0.0001077132,0.3080802,0.004397094,0.002994128,0.00124882,0.001201826,0.0001967221,0.006795134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8715433,"threshold_uncertainty_score":0.9999163,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05730906861657043,"gpt":0.2577674707612815,"spread":0.2004584021447111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002389308,0.0001748319,0.0004201671,0.00008478585,0.0005583684,0.0004675139,0.00157977,0.00004497973,0.000001965757],"category_scores_gemma":[0.00003658526,0.00008121676,0.00008451517,0.0004291325,0.001073265,0.0005990492,0.0003031442,0.0002307632,5.71121e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002508097,"about_ca_system_score_gemma":0.0001020055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000614888,"about_ca_topic_score_gemma":0.00001241909,"domain_scores_codex":[0.9975501,0.0006387925,0.0006069323,0.0002758775,0.0006932274,0.000235091],"domain_scores_gemma":[0.9980454,0.0006880417,0.0005612278,0.0004587963,0.000136298,0.0001101957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000394333,0.0002885869,0.0511069,0.0002519882,0.00008545555,0.00006798549,0.003264406,0.002812968,0.004877517,0.9225376,0.001094238,0.01357297],"study_design_scores_gemma":[0.002408261,0.004346396,0.1546685,0.004789976,0.0000874859,0.006721364,0.001467532,0.7662385,0.007367019,0.04954441,0.001302289,0.001058314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9333168,0.0006595729,0.0636157,0.001071249,0.0006950746,0.0002742839,0.000007185147,0.00001581143,0.0003443419],"genre_scores_gemma":[0.9876013,0.00003204457,0.01214637,0.0001761095,0.00003483626,0.000002238449,1.671085e-7,0.000003273857,0.000003638755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8729931,"threshold_uncertainty_score":0.4508248,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0231628126247053,"gpt":0.2617781121611502,"spread":0.2386152995364449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002383254,0.0001466638,0.0001205683,0.00005339286,0.0002149292,0.0003179163,0.0004998901,0.00004450558,0.000004760724],"category_scores_gemma":[0.0002088221,0.0001073661,0.0000101474,0.0002735302,0.00008790059,0.0053246,0.0004834881,0.0001712923,0.00004463556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002173391,"about_ca_system_score_gemma":0.00008305573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008264626,"about_ca_topic_score_gemma":0.000001796797,"domain_scores_codex":[0.9987321,0.00003951997,0.0001389817,0.000435368,0.0003764058,0.0002775684],"domain_scores_gemma":[0.9988816,0.0001289354,0.0001023866,0.0005333729,0.0001514365,0.0002022243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002415003,0.0002808107,0.04760084,0.00006622591,0.0000407927,0.0003318615,0.05265972,0.0002118279,0.000373018,0.003272197,0.005238773,0.8896824],"study_design_scores_gemma":[0.002866982,0.002351311,0.01452788,0.0004264241,0.00005166004,0.002523985,0.008756831,0.05902491,0.007319412,0.001648924,0.8983601,0.00214157],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2812159,0.0004780611,0.7150019,0.001604311,0.000292926,0.000117829,0.00000127068,0.0002749654,0.001012828],"genre_scores_gemma":[0.533895,0.00009398048,0.4641506,0.0016042,0.00009326728,0.00003737684,0.000002794991,0.00001062834,0.0001121026],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8931214,"threshold_uncertainty_score":0.4378264,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08296651646590367,"gpt":0.3066863161757942,"spread":0.2237197997098906,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005529899,0.0002186725,0.0002246641,0.0001147398,0.0004313738,0.000280014,0.0007810478,0.0001030753,0.00001268978],"category_scores_gemma":[0.000075468,0.0001778625,0.00007204158,0.0003075712,0.00007516307,0.002973367,0.0009538991,0.0001980353,0.00008781949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091662,"about_ca_system_score_gemma":0.00009455502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590806,"about_ca_topic_score_gemma":2.361942e-7,"domain_scores_codex":[0.9980853,0.00004511655,0.0005603871,0.0001774751,0.0005204983,0.0006112811],"domain_scores_gemma":[0.9985444,0.0001187491,0.0002989297,0.0006333629,0.0001148338,0.0002897028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001795611,0.0005325272,0.007545118,0.000794589,0.0001114274,0.00005260268,0.01289847,0.005487966,0.03012035,0.03243376,0.006466916,0.9035383],"study_design_scores_gemma":[0.0002320954,0.00002646766,0.0004018914,0.0002699235,0.000009116056,0.0001415485,0.0001763543,0.991502,0.002525733,0.00008464232,0.004350548,0.0002796676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006716708,0.000303426,0.9895922,0.00004388452,0.000981133,0.0001849794,0.00001369808,0.0002255267,0.001938446],"genre_scores_gemma":[0.1924294,0.00002801652,0.8069463,0.0003533696,0.0001826346,0.000003968202,0.00001668309,0.00001079889,0.00002877481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860141,"threshold_uncertainty_score":0.7253024,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick; University of Waterloo","funders":"","keywords":"Set (abstract data type); Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02080502840567923,"gpt":0.2353265507327696,"spread":0.2145215223270904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004332036,0.00005633124,0.00005663768,0.00003012838,0.0001088035,0.00008423069,0.0002272573,0.00002020608,0.0003194753],"category_scores_gemma":[0.000002165118,0.00003935272,0.0000112797,0.0000950117,0.00002737336,0.0003959283,0.0001211341,0.00005138983,0.00004695917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005195822,"about_ca_system_score_gemma":0.000008858026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001910621,"about_ca_topic_score_gemma":0.00001675853,"domain_scores_codex":[0.9995615,0.00002646184,0.00006657272,0.0001827082,0.00007445558,0.00008826686],"domain_scores_gemma":[0.9997022,0.00003148523,0.00001134356,0.0001920895,0.00001175702,0.00005119492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007764317,0.00004490583,0.001355069,0.000002850919,0.00001271189,0.000006433777,0.0007142043,0.000005998962,0.00003292149,0.06073378,0.01344637,0.923637],"study_design_scores_gemma":[0.0007526667,0.0005301069,0.111343,0.00009298691,0.000009563953,0.0001353389,0.001016048,0.7857427,0.0004175926,0.02785046,0.07147337,0.000636199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1221271,0.0002633154,0.8569506,0.0008734821,0.0002217555,0.0000968513,0.0000119938,0.0002589645,0.01919596],"genre_scores_gemma":[0.9584692,0.0001608324,0.03838206,0.0002717337,0.00003272354,0.00000469303,0.00000298572,0.000002131613,0.002673616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9230008,"threshold_uncertainty_score":0.349803,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02766122019691645,"gpt":0.2810312807924654,"spread":0.253370060595549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004148503,0.000167966,0.0002066762,0.00005959116,0.0001870482,0.0001440567,0.00058079,0.00007469211,0.00002078992],"category_scores_gemma":[0.00006010764,0.0001324099,0.0000660783,0.0001842372,0.00003160425,0.0001221484,0.0001597577,0.0001318075,0.00006442283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002540173,"about_ca_system_score_gemma":0.00004179353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001365607,"about_ca_topic_score_gemma":6.010126e-7,"domain_scores_codex":[0.9987946,0.00001482261,0.0002021884,0.0003341395,0.0003284591,0.0003258111],"domain_scores_gemma":[0.9986517,0.0002961988,0.00006777184,0.0008318623,0.00004471605,0.0001077376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004450343,0.00008366148,9.684965e-7,0.00006145417,0.000009314784,0.000001028687,0.0004976132,0.0001146072,0.001013631,0.9949217,0.001731796,0.001559781],"study_design_scores_gemma":[0.00130898,0.0001784598,0.0000260395,0.00006890174,0.0000202618,0.000008302149,0.0004088776,0.2906895,0.03560638,0.6592716,0.01182306,0.0005895906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002715544,0.00001119458,0.9731091,0.0001403098,0.00009606295,0.0004941036,0.00001912468,0.000123966,0.02329058],"genre_scores_gemma":[0.130215,0.000004965872,0.8690807,0.0002616863,0.00003454103,0.00008935147,0.00001877777,0.00002404326,0.000270968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3356501,"threshold_uncertainty_score":0.5399518,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006188313789722419,"gpt":0.2324596412625818,"spread":0.2262713274728593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003857109,0.000445281,0.0004405061,0.0004531453,0.0002768866,0.0004329858,0.001153074,0.0001933742,0.0001534368],"category_scores_gemma":[0.00002963982,0.000378734,0.0001542614,0.0008690794,0.0001262,0.001566306,0.000667551,0.0004798635,0.001064063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001592969,"about_ca_system_score_gemma":0.0000678357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00172307,"about_ca_topic_score_gemma":0.00008720208,"domain_scores_codex":[0.996923,0.0002231898,0.0004771025,0.001101927,0.000475194,0.0007995536],"domain_scores_gemma":[0.9978022,0.0002321976,0.0001631751,0.001406675,0.00008850281,0.0003072566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002476123,0.004760347,0.003463912,0.0002913403,0.0005396834,0.02727442,0.006470518,0.008308977,0.08255586,0.03882865,0.02389927,0.8033594],"study_design_scores_gemma":[0.001296098,0.0004008414,0.004205192,0.0001123478,0.00001068028,0.001130639,0.00007700974,0.9847097,0.0008640258,0.005675933,0.0006729524,0.0008445231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4568598,0.0006146805,0.5140634,0.01002019,0.002685655,0.003322613,0.0002774204,0.001511082,0.0106451],"genre_scores_gemma":[0.952934,0.00007614667,0.04477235,0.0006385566,0.0001214491,0.0002599972,0.00007318627,0.0000633327,0.001060937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9764008,"threshold_uncertainty_score":0.9998665,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05043055801681404,"gpt":0.2647240296950133,"spread":0.2142934716781993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100544,0.00009388738,0.0002293818,0.0003071947,0.0002220575,0.0003910535,0.0009454823,0.00003336961,0.000003468197],"category_scores_gemma":[0.000007749937,0.00006176317,0.00004955903,0.0004754137,0.00009724248,0.001297873,0.0001929477,0.0001204542,0.000003674039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002720152,"about_ca_system_score_gemma":0.00003044511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001206312,"about_ca_topic_score_gemma":0.000001870663,"domain_scores_codex":[0.9986388,0.0001060128,0.000424402,0.0002042578,0.0004291128,0.0001974216],"domain_scores_gemma":[0.9992965,0.0001297799,0.0002678615,0.0001488941,0.00005914202,0.00009775546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001646541,0.000426395,0.03478491,0.0003759205,0.00007929279,0.002553932,0.01795238,0.01424464,0.0007225266,0.4983366,0.03474648,0.3957605],"study_design_scores_gemma":[0.0003020554,0.000286341,0.003311555,0.0005415668,0.000003225205,0.001450887,0.0003683663,0.9904628,0.00004199517,0.001114239,0.001974275,0.0001426919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0752771,0.002346128,0.9178856,0.001423304,0.0012951,0.00007380483,9.20997e-7,0.00002848768,0.001669582],"genre_scores_gemma":[0.923916,0.0001111568,0.07567155,0.00008653112,0.0001875221,5.440299e-7,4.051169e-8,0.000001711252,0.0000249929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9762182,"threshold_uncertainty_score":0.3770938,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03092524817749018,"gpt":0.2482270717439886,"spread":0.2173018235664985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003352743,0.00006840314,0.0001206129,0.00005145335,0.000112869,0.0001869384,0.001448972,0.00002463515,0.00001551422],"category_scores_gemma":[0.0003793036,0.00004151743,0.00005540095,0.0001902182,0.0000330958,0.0005749016,0.001503634,0.0003283125,0.000004300919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002403236,"about_ca_system_score_gemma":0.0001005734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001382551,"about_ca_topic_score_gemma":0.000007608332,"domain_scores_codex":[0.9991494,0.00007854384,0.0001878418,0.0001192853,0.0003348818,0.0001299995],"domain_scores_gemma":[0.9992245,0.0001200368,0.0001422663,0.0003651491,0.00004654033,0.0001015244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001772325,0.001049986,0.07432687,0.0001674819,0.0004279666,0.001083841,0.03031226,0.07202894,0.09296934,0.04230991,0.3025075,0.3810436],"study_design_scores_gemma":[0.003600553,0.0009568328,0.4265045,0.0003727038,0.00003144878,0.001123849,0.0006977285,0.4658649,0.002579557,0.02350995,0.07426888,0.0004890301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7479863,0.0005918774,0.1798989,0.07066189,0.0005517759,0.00007911785,0.000003507935,0.00001656529,0.0002100796],"genre_scores_gemma":[0.8901476,0.00005024052,0.1084575,0.0008205351,0.0004229158,4.676845e-7,3.855305e-7,0.00000627086,0.00009403843],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.393836,"threshold_uncertainty_score":0.2692575,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03986754876128853,"gpt":0.3207699015752767,"spread":0.2809023528139882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005868879,0.00006692327,0.00007708897,0.00003842495,0.0001446236,0.0001757461,0.001608139,0.00001058111,0.000006139435],"category_scores_gemma":[0.0000225405,0.00005849952,0.00001284169,0.0006207044,0.00003205363,0.001661154,0.002694956,0.00006103641,0.0001348827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000210204,"about_ca_system_score_gemma":0.0001458328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009450228,"about_ca_topic_score_gemma":2.520853e-7,"domain_scores_codex":[0.9986557,0.000009325129,0.0001432888,0.0006424436,0.0003663243,0.0001828644],"domain_scores_gemma":[0.9963599,0.00003383271,0.0000906421,0.003334173,0.00008213073,0.00009928387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[9.815146e-7,0.00007673034,0.001003958,0.000009314173,0.000005006968,0.00001816329,0.0001350797,0.0006103337,0.01167441,0.5310301,0.0007920976,0.4546438],"study_design_scores_gemma":[0.0001796357,0.0000669547,0.009514557,0.00009298953,0.00001291864,0.0001625919,0.00005021215,0.1374838,0.03195148,0.5019627,0.3176552,0.0008670153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007301511,0.00002155913,0.9875101,0.00005741185,0.0002889388,0.0002499357,0.000009746737,0.0000938268,0.004466916],"genre_scores_gemma":[0.9213485,0.000002638099,0.07809882,0.0001564688,0.000141688,0.00002201847,0.00002843138,0.000006389082,0.0001950424],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.914047,"threshold_uncertainty_score":0.3359071,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02480372966182174,"gpt":0.2668883885277947,"spread":0.242084658865973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001548354,0.0001835492,0.0002213163,0.0003297111,0.0002566723,0.0002498372,0.0004455705,0.00005870864,0.000301853],"category_scores_gemma":[0.000003617657,0.0001437647,0.0001423617,0.0007376987,0.00004334184,0.0006268311,0.00001071062,0.0002172896,0.0001714245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001978763,"about_ca_system_score_gemma":0.00001299367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002665224,"about_ca_topic_score_gemma":0.0004883815,"domain_scores_codex":[0.9986936,0.00007602169,0.0002960023,0.0004904288,0.0002397004,0.0002042673],"domain_scores_gemma":[0.9990509,0.00007235454,0.00009019429,0.0005535998,0.00009592291,0.0001369911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002111502,0.0002187972,0.0003249863,0.000008245541,0.0001452499,0.000004472243,0.0001726639,0.005631236,0.0008865207,0.00003436419,0.00002417781,0.9925472],"study_design_scores_gemma":[0.00008415773,0.00007753142,0.005898833,0.00001367568,0.0001100607,0.000006135095,0.00002168682,0.9239802,0.06936496,0.0001436197,0.00007850431,0.0002205904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004210732,0.0000475373,0.9949234,0.0003308533,0.0001536593,0.0001771651,0.00002415912,0.0001033668,0.00002911882],"genre_scores_gemma":[0.9793191,0.0001421616,0.0199966,0.0003012123,0.00001340754,0.00004385842,0.000008621713,0.000006925631,0.0001680923],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9923266,"threshold_uncertainty_score":0.5862556,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01946566761545364,"gpt":0.2503981644689971,"spread":0.2309324968535434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002373143,0.0001501679,0.0003044177,0.0002063673,0.0005155596,0.0005480775,0.0008435989,0.00003991002,0.000003079097],"category_scores_gemma":[0.00002218923,0.00009116226,0.00008175758,0.0003118013,0.00006677273,0.0008771485,0.0001534977,0.0001678139,0.000004737578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002019279,"about_ca_system_score_gemma":0.00008952658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000060077,"about_ca_topic_score_gemma":0.000001416321,"domain_scores_codex":[0.9981098,0.0002499387,0.0004793132,0.0002743892,0.0006007084,0.0002858258],"domain_scores_gemma":[0.9989448,0.0001826958,0.0003823187,0.000212889,0.000124881,0.0001524378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003402946,0.0005290747,0.008456799,0.0003515458,0.00010714,0.0003291575,0.005152564,0.01904068,0.0003640444,0.8509945,0.0148496,0.09979083],"study_design_scores_gemma":[0.0009251205,0.0008742666,0.001446885,0.0005684764,0.000007336855,0.001099792,0.0001883313,0.983655,0.00004183199,0.00206209,0.008894972,0.0002358876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01319561,0.0008298297,0.9824403,0.0002472735,0.001432543,0.00009780414,0.000001656653,0.00003488854,0.001720124],"genre_scores_gemma":[0.8134448,0.00003114947,0.1860708,0.000183251,0.0002176875,0.000001343277,2.138218e-7,0.00000424784,0.00004653095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9646143,"threshold_uncertainty_score":0.5285124,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1614176675957748,"gpt":0.4801760690923179,"spread":0.3187584014965431,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001501057,0.0001871476,0.0004471701,0.00009483483,0.000118702,0.00008326065,0.003255871,0.0003115117,0.00003448227],"category_scores_gemma":[0.0006596757,0.0001085785,0.0000499696,0.0003486197,0.00007295461,0.001674712,0.002843047,0.0004387317,0.00001128018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005586594,"about_ca_system_score_gemma":0.0000986911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000414412,"about_ca_topic_score_gemma":0.000002342342,"domain_scores_codex":[0.99753,0.000562173,0.0004347248,0.0007279907,0.0004620928,0.0002829808],"domain_scores_gemma":[0.9952176,0.001277655,0.0002973994,0.002967181,0.0001411918,0.00009896495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001045822,0.0000454972,0.0002528309,0.00001923121,0.00001574902,0.000003779506,0.0001089121,0.0000162609,0.09580701,0.027665,0.009334454,0.8667208],"study_design_scores_gemma":[0.001428167,0.0002021204,0.006191769,0.0007704207,0.00003845968,0.00002904789,0.00005051258,0.1409686,0.6595998,0.0272716,0.1627463,0.0007031083],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001804791,0.001630083,0.9936386,0.0006107857,0.00141691,0.0001307416,0.00009109429,0.0001362472,0.0005407609],"genre_scores_gemma":[0.1966445,0.00002782088,0.8029561,0.0001265448,0.0001376898,0.000002656537,0.00002999709,0.000009826364,0.00006486694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8660177,"threshold_uncertainty_score":0.6050273,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Diversity (politics); Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.05953039391184662,"gpt":0.2397432936762116,"spread":0.180212899764365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001021894,0.00004660597,0.00004455008,0.00004018897,0.0002362283,0.0000286536,0.0007692998,0.00001958782,0.0002617377],"category_scores_gemma":[0.000001844953,0.00003447533,0.00002156394,0.0001276575,0.00001933412,0.0001040757,0.002674719,0.00005221226,0.000354754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009249571,"about_ca_system_score_gemma":0.00001311781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002413494,"about_ca_topic_score_gemma":0.000001753767,"domain_scores_codex":[0.9994054,0.00001750769,0.00004965754,0.0001884761,0.0001933307,0.0001455818],"domain_scores_gemma":[0.9994988,0.00001164897,0.000009702653,0.0003696333,0.00003726276,0.00007290567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003632801,0.00152104,0.03968898,0.00004128418,0.00004514046,0.0003723472,0.02424195,0.0009378924,0.0003770077,0.4728274,0.03412555,0.4257851],"study_design_scores_gemma":[0.0003124287,0.00008939298,0.04125544,0.00001024988,0.00000224645,0.000008744037,0.0001339856,0.953394,0.002253044,0.00106235,0.001269823,0.0002083103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02992259,0.000009220972,0.9495593,0.00004611325,0.0001593337,0.00004163624,0.000001170261,0.0001291575,0.02013149],"genre_scores_gemma":[0.9264748,0.000001322442,0.07269544,0.0001227563,0.0000160754,6.793348e-7,8.383624e-7,0.000001698765,0.0006864181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9524561,"threshold_uncertainty_score":0.4559762,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06367548601671887,"gpt":0.2947418912688785,"spread":0.2310664052521596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001824664,0.000133248,0.0001312761,0.0001119389,0.0007604567,0.000153933,0.002182788,0.00004824937,0.00003978256],"category_scores_gemma":[0.00000769034,0.0001274273,0.00007574198,0.0005551966,0.0001141427,0.0006385387,0.00002764259,0.000325371,0.0001659521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005835419,"about_ca_system_score_gemma":0.0000537757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062098,"about_ca_topic_score_gemma":0.000249491,"domain_scores_codex":[0.9989164,0.0001330645,0.0002286923,0.0003074456,0.0002034187,0.0002110086],"domain_scores_gemma":[0.9958832,0.0001631677,0.0000663769,0.003681252,0.000109398,0.00009665752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003376193,0.004803995,0.00008509872,0.00001421235,0.00009025519,0.000007373648,0.001101715,0.00230458,0.009377117,0.01520882,0.005193464,0.9617796],"study_design_scores_gemma":[0.001286086,0.0005380831,0.002216283,0.0001703964,0.00007660017,0.0002019675,0.0001442392,0.3626121,0.06177067,0.01004232,0.5597365,0.001204701],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009536304,0.0002381076,0.9861854,0.004759132,0.0003207405,0.0001858958,0.00002017596,0.0003609863,0.00697595],"genre_scores_gemma":[0.8935543,0.0006578708,0.1046372,0.0002168022,0.00002741232,0.00007214242,0.00001157143,0.00001077357,0.0008119034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9605749,"threshold_uncertainty_score":0.5848895,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03454588049591423,"gpt":0.27938073763913,"spread":0.2448348571432157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001150333,0.0001174859,0.0001263988,0.00006097061,0.0001941564,0.000107983,0.0007930741,0.00004799416,0.0005070831],"category_scores_gemma":[0.00003133056,0.00008883355,0.00004866232,0.0001494752,0.00002733913,0.0006917492,0.000572825,0.00008026859,0.0003049416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000171566,"about_ca_system_score_gemma":0.000009793699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002066031,"about_ca_topic_score_gemma":8.985705e-7,"domain_scores_codex":[0.9989907,0.00002779897,0.0001831679,0.0003337011,0.000223937,0.0002407553],"domain_scores_gemma":[0.999155,0.0001489476,0.000051919,0.0004790282,0.00005972791,0.0001053933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002272786,0.0005659166,0.0004642822,0.00003768689,0.00002646803,0.00001102255,0.0004538993,0.0001891924,0.02991826,0.04515882,0.2309615,0.6921902],"study_design_scores_gemma":[0.0004386963,0.0001058951,0.0001555274,0.00002631289,0.000001701248,0.000003408732,0.000003099228,0.9427969,0.005875425,0.001133685,0.04930864,0.000150648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001808846,0.0001019067,0.9900811,0.0004507896,0.0001953301,0.0002304425,0.00001427065,0.0002300426,0.006887224],"genre_scores_gemma":[0.1909542,0.00004832269,0.8020197,0.0008692757,0.0002015446,0.0000478603,0.00004075541,0.00001355068,0.005804841],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9426078,"threshold_uncertainty_score":0.5552204,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Space (punctuation); Computer science; Suffix tree; Artificial intelligence; Mathematics; Combinatorics; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01461430931628228,"gpt":0.2550175803153401,"spread":0.2404032709990578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532933,0.0001431509,0.0002518429,0.0002047758,0.0001154866,0.000176401,0.00109397,0.0000579452,0.00004191485],"category_scores_gemma":[0.00005010357,0.000102865,0.0001462411,0.0004328592,0.00003616105,0.000539145,0.0002498618,0.0002550907,0.00004409507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005400351,"about_ca_system_score_gemma":0.00009498464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001506679,"about_ca_topic_score_gemma":0.000001331436,"domain_scores_codex":[0.9984152,0.00005821914,0.000423128,0.0001944132,0.000627315,0.000281665],"domain_scores_gemma":[0.9986703,0.00008882173,0.0003608662,0.0004215573,0.0002480759,0.0002104284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001054952,0.001431972,0.001372004,0.00001789955,0.0001629235,0.003005179,0.002184517,0.01655254,0.004415274,0.01428351,0.0406463,0.9158224],"study_design_scores_gemma":[0.002202529,0.001005101,0.01154974,0.0001920001,0.00003307231,0.004137198,0.0002121139,0.7194228,0.003439207,0.002406405,0.2548571,0.0005427315],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03197483,0.0008876005,0.962519,0.00192448,0.001448762,0.00005676291,0.000002247514,0.0000435877,0.001142665],"genre_scores_gemma":[0.3307252,0.0006837249,0.6649441,0.0004282363,0.001917217,0.000002328869,0.000002221731,0.00002989315,0.001267019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9152797,"threshold_uncertainty_score":0.4194713,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico","keywords":"Computer science; Theoretical computer science; Graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01849260082025904,"gpt":0.2626085176005849,"spread":0.2441159167803258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001542336,0.0001014016,0.00008252308,0.00009241621,0.0005201815,0.0001741584,0.0008729194,0.00004447282,0.0001330585],"category_scores_gemma":[0.00002172089,0.00006710457,0.00005398748,0.0002990574,0.00009782111,0.000383067,0.00002553146,0.0003479453,0.00006106264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004603372,"about_ca_system_score_gemma":0.00003776263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000599464,"about_ca_topic_score_gemma":0.0001045017,"domain_scores_codex":[0.9992465,0.00004838473,0.000119491,0.0002582855,0.0001741753,0.0001531603],"domain_scores_gemma":[0.9982662,0.0003015983,0.00003739986,0.001275716,0.0000345462,0.00008449468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005976198,0.001104137,0.001076701,0.00002629601,0.000250578,0.00003036481,0.00321502,0.002450829,0.1510811,0.1172781,0.03465953,0.6887676],"study_design_scores_gemma":[0.003374208,0.0005254003,0.03857554,0.00013592,0.0001527274,0.0005135348,0.001183667,0.6594412,0.03702135,0.1249829,0.1324196,0.001673963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05796655,0.00003563292,0.9208007,0.01725786,0.0008918822,0.0002301631,0.00007689882,0.0002448643,0.00249546],"genre_scores_gemma":[0.98037,0.00006950821,0.01881794,0.00032449,0.00003953585,0.00001356747,0.000003037144,0.000007393778,0.0003545297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9224035,"threshold_uncertainty_score":0.4000868,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02623472200375592,"gpt":0.242439027781114,"spread":0.2162043057773581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007547612,0.0003337759,0.00025153,0.0003782393,0.0006146493,0.0002733529,0.001061294,0.00011443,0.0001050994],"category_scores_gemma":[0.00000443987,0.0002632742,0.00008998843,0.0004744696,0.0001407143,0.002882619,0.00001066499,0.0004082618,0.00009999248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221869,"about_ca_system_score_gemma":0.0002376845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004636192,"about_ca_topic_score_gemma":0.00001124604,"domain_scores_codex":[0.9976165,0.0002843662,0.0004727748,0.0004467329,0.0007892936,0.0003903871],"domain_scores_gemma":[0.9977238,0.0002014363,0.0001908916,0.001509619,0.0001677308,0.0002065648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003698326,0.0002791502,2.209975e-7,0.00002094687,0.00003250262,0.000006175139,0.0005973238,0.8354628,0.00001880876,0.03389608,0.0002113354,0.1291048],"study_design_scores_gemma":[0.003094454,0.0003289031,0.000001408187,0.0001541711,0.00003324141,0.00002383309,0.0003017697,0.9864451,0.003205988,0.0009907171,0.005062479,0.0003579881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006721205,0.00001045508,0.993987,0.0001193114,0.001019409,0.0005672753,0.0004517245,0.0002774289,0.002895279],"genre_scores_gemma":[0.9728691,0.000009045784,0.02600628,0.000740456,0.00002944634,0.0000468834,0.0001804809,0.00002130278,0.0000969985],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972197,"threshold_uncertainty_score":0.9999819,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01298618704765494,"gpt":0.2229243720543181,"spread":0.2099381850066632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001010094,0.0001047673,0.0001027895,0.00007121294,0.0002011922,0.0001640517,0.0004764911,0.00005145857,0.00005987194],"category_scores_gemma":[0.000004710996,0.00008518699,0.00002735517,0.0003088235,0.00004543341,0.0004802193,0.0003589209,0.0001035799,0.00008441601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001099356,"about_ca_system_score_gemma":0.000008097446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001363162,"about_ca_topic_score_gemma":0.000009714193,"domain_scores_codex":[0.9991077,0.00002459282,0.0001348269,0.0003723713,0.0001699467,0.0001906091],"domain_scores_gemma":[0.9991578,0.00004385181,0.00003824085,0.0005844077,0.00004487885,0.0001308146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[1.534844e-7,0.00008445813,0.0001489896,0.000004107675,0.000005088746,0.00000402496,0.000125083,0.000001775315,0.00005164068,0.02600531,0.005318687,0.9682507],"study_design_scores_gemma":[0.0005078424,0.00008074192,0.004054802,0.00001219975,0.000009441635,0.0001050272,0.00003161208,0.7788239,0.0004177915,0.01820521,0.1972885,0.0004629245],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002644538,0.0007257582,0.9934719,0.0005251134,0.00007568721,0.000180569,0.000008137242,0.0002376068,0.004510793],"genre_scores_gemma":[0.04783614,0.0005547662,0.9485596,0.0006342067,0.0001653732,0.00009509718,0.000009610067,0.00001194329,0.002133243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9677877,"threshold_uncertainty_score":0.3473825,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01160689930725286,"gpt":0.2518886837407619,"spread":0.240281784433509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003998731,0.00005338231,0.00007602148,0.00004060989,0.00003120541,0.00003721633,0.0003256657,0.00002802016,0.00009020674],"category_scores_gemma":[0.00001112803,0.00003832421,0.00002275197,0.0001630043,0.00001423342,0.0004723307,0.0001690551,0.00006379592,0.00003838448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006941635,"about_ca_system_score_gemma":0.00001207336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008024178,"about_ca_topic_score_gemma":0.00003780917,"domain_scores_codex":[0.9994952,0.00001722804,0.0001012414,0.0001591352,0.0001390975,0.00008806238],"domain_scores_gemma":[0.9995514,0.00003555012,0.00004223362,0.0003188968,0.00002676434,0.00002520991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001292255,0.0001556417,0.003650177,0.00001031633,0.00002748543,0.00004901901,0.001300375,0.00002894044,0.1006851,0.009348195,0.009354208,0.8753776],"study_design_scores_gemma":[0.001388422,0.0001838595,0.195807,0.0001540126,0.00002159165,0.00008282068,0.001234292,0.6602108,0.109305,0.006212696,0.02469066,0.0007089264],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6291516,0.0004592318,0.3671739,0.0002686324,0.0005050724,0.00004401263,0.000002735481,0.0001026375,0.002292144],"genre_scores_gemma":[0.9619918,0.00001965484,0.03722697,0.00008063487,0.00008092372,7.870721e-7,0.00001026064,0.00000229316,0.0005866075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8746687,"threshold_uncertainty_score":0.1562816,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01728474627139232,"gpt":0.2344576880311056,"spread":0.2171729417597133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001657572,0.0000985333,0.00009833964,0.00006251744,0.0001187475,0.0001519373,0.0007825424,0.00004360337,0.00002733063],"category_scores_gemma":[0.00007774457,0.00005742053,0.00003933795,0.000133244,0.00003327103,0.001940914,0.0004176498,0.00005166758,0.0006562853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003346915,"about_ca_system_score_gemma":0.00003951156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000432046,"about_ca_topic_score_gemma":7.269779e-7,"domain_scores_codex":[0.999171,0.00001297667,0.0002418323,0.0001148177,0.0002288338,0.0002305761],"domain_scores_gemma":[0.9990648,0.00009126456,0.0001184121,0.0005725132,0.0000544781,0.00009853514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003444077,0.00002836842,0.0001473324,0.00002059234,0.00001159192,0.00000807387,0.001309272,0.000005465907,0.0003509413,0.09019294,0.04403867,0.8638833],"study_design_scores_gemma":[0.00198663,0.0003019052,0.002878503,0.0007247524,0.00001483466,0.0000920765,0.0003451595,0.3108798,0.009551945,0.02554555,0.6465446,0.00113415],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00159263,0.00002609951,0.9890481,0.0009836768,0.0004597984,0.00007877625,0.000012463,0.0001798755,0.007618563],"genre_scores_gemma":[0.03550022,0.00007414471,0.962895,0.0007517672,0.0001347601,0.00000601741,0.000005565042,0.00001031497,0.0006221724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8627492,"threshold_uncertainty_score":0.8435439,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03041967066636761,"gpt":0.2243386128071558,"spread":0.1939189421407882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002324742,0.0001961682,0.0001890641,0.0001323948,0.0002411446,0.0002148307,0.001278912,0.00007616918,0.0002801978],"category_scores_gemma":[0.00001243138,0.0001537369,0.00007350944,0.0002586793,0.00004283225,0.001788214,0.0005862907,0.0001655174,0.0006550656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005593705,"about_ca_system_score_gemma":0.00007597244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003556385,"about_ca_topic_score_gemma":0.000001263792,"domain_scores_codex":[0.9984992,0.00004155832,0.0004317111,0.0002178613,0.0004295523,0.0003800727],"domain_scores_gemma":[0.9985622,0.00005382331,0.0001808813,0.0009390097,0.00005907525,0.0002049788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002755629,0.003778557,0.01356913,0.001098509,0.0003011696,0.0001425446,0.03502806,0.0001851889,0.0008825703,0.2831717,0.09996286,0.5616041],"study_design_scores_gemma":[0.001889502,0.0003714121,0.006435939,0.0001430915,0.0000187604,0.00002277692,0.0001925459,0.7938842,0.007321088,0.002962858,0.1861156,0.0006422822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006266039,0.00003504575,0.9552984,0.0001292536,0.0006627993,0.0003868763,0.00001402024,0.0007784965,0.03642904],"genre_scores_gemma":[0.2961221,0.000009427145,0.7020909,0.001517623,0.00004818085,0.00004577403,0.00005023573,0.00001329463,0.0001024484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.793699,"threshold_uncertainty_score":0.8419761,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0562830034262234,"gpt":0.3208830209361637,"spread":0.2646000175099403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001128383,0.000157783,0.0002420677,0.0001006398,0.0001365353,0.00008577773,0.003012881,0.00008636695,0.0001415738],"category_scores_gemma":[0.00003613352,0.0001120393,0.00003872114,0.000345916,0.0000473825,0.001574174,0.004470691,0.0001467794,0.00006655951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001876017,"about_ca_system_score_gemma":0.00003751655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005328589,"about_ca_topic_score_gemma":0.00002287698,"domain_scores_codex":[0.9979442,0.00003506759,0.0005133023,0.0006321797,0.0005753989,0.0002997938],"domain_scores_gemma":[0.9964944,0.0002405855,0.0002044819,0.002822987,0.0001204911,0.0001171259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002231598,0.0005493442,0.0005905047,0.00005345938,0.00003281318,0.00004595285,0.0005215695,0.0004547895,0.02746665,0.1701121,0.06819227,0.7317573],"study_design_scores_gemma":[0.005167917,0.0004167459,0.009696337,0.0005103745,0.00002240111,0.00005689653,0.0001719926,0.5931045,0.3072238,0.01525359,0.06743807,0.0009373938],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009632111,0.0001260511,0.9838985,0.0002306877,0.0007575529,0.0001609163,0.00001809318,0.0001364098,0.005039656],"genre_scores_gemma":[0.371104,0.00002449665,0.6283226,0.0001251286,0.0001261577,6.281577e-7,0.0000811677,0.000008718328,0.0002071075],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7308199,"threshold_uncertainty_score":0.5598732,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03680986124003464,"gpt":0.2978930809314662,"spread":0.2610832196914316,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002743586,0.0001385971,0.0002419317,0.0001663781,0.00004328055,0.00001270287,0.0002996794,0.00008623773,0.00000663521],"category_scores_gemma":[0.00004504891,0.00009507135,0.00001823365,0.0002223009,0.00006063917,0.0001563757,0.00007936682,0.0001193593,0.000003187067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189758,"about_ca_system_score_gemma":0.00001099445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002175032,"about_ca_topic_score_gemma":0.000003002207,"domain_scores_codex":[0.9991498,0.00001855905,0.0002111654,0.0003082316,0.00006002766,0.0002521952],"domain_scores_gemma":[0.9994644,0.0001854329,0.00003935409,0.0002049324,0.0000319522,0.00007394508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002329852,0.00008699087,0.002410171,0.00007663673,0.00003001491,0.00009486858,0.0004252522,0.000852007,0.0836068,0.004572535,0.01198783,0.8958336],"study_design_scores_gemma":[0.001347021,0.0004260615,0.002906639,0.0001818775,0.000004971056,0.00009515448,0.000008480581,0.9160757,0.000458655,0.0009460784,0.07736477,0.0001845676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02000068,0.0009796889,0.9769934,0.0009741589,0.0006885107,0.0001506457,0.000004126189,0.00009985234,0.0001089712],"genre_scores_gemma":[0.3527358,0.003050052,0.6397606,0.001390394,0.002237295,0.000172559,0.0001165419,0.00003900169,0.0004978229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9152237,"threshold_uncertainty_score":0.3876897,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1701892097079504,"gpt":0.3126197987859841,"spread":0.1424305890780337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455123,0.0001020647,0.0001053807,0.00005304708,0.0002309875,0.0004143114,0.001615253,0.00004817103,0.000007584535],"category_scores_gemma":[0.00005604016,0.00008337503,0.00002297803,0.0001220508,0.00004068995,0.002564783,0.00107119,0.00004526722,0.000114568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001333426,"about_ca_system_score_gemma":0.00005016436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745193,"about_ca_topic_score_gemma":0.00001215012,"domain_scores_codex":[0.9991232,0.000009366649,0.0002783006,0.0001858727,0.0001951138,0.0002081593],"domain_scores_gemma":[0.9982447,0.00004069951,0.0001242868,0.001402306,0.0001146819,0.00007329384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001671717,0.0001263812,0.00009604392,0.0001706575,0.0000408863,0.000001303498,0.001805887,0.00005845347,0.002642712,0.04581898,0.229166,0.7200559],"study_design_scores_gemma":[0.0001982898,0.00006237585,0.00005742482,0.00001173194,0.000003321231,0.00000279969,0.00001605878,0.7751544,0.0009569521,0.000131585,0.2233081,0.00009697581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007469283,0.00006026925,0.9971479,0.0001937039,0.0007101656,0.0002338085,0.00007962579,0.0001207788,0.0007068199],"genre_scores_gemma":[0.01607756,0.00001521055,0.9824967,0.0004456157,0.00062257,0.00001078417,0.0002209022,0.000006815025,0.0001038278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7750959,"threshold_uncertainty_score":0.3995215,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007480600463049214,"gpt":0.2068424045391989,"spread":0.1993618040761496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003834943,0.00004410241,0.00004010072,0.00002900078,0.00005624277,0.00006868877,0.0002381435,0.00002066082,0.00006082504],"category_scores_gemma":[0.000001343625,0.00003493854,0.00001682066,0.00009313485,0.00001302895,0.0002308893,0.0001049883,0.00002804193,0.00007217794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007120017,"about_ca_system_score_gemma":0.00001071148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007029436,"about_ca_topic_score_gemma":0.000002848866,"domain_scores_codex":[0.9995737,0.000009830904,0.00007889936,0.000159933,0.00008006748,0.00009758829],"domain_scores_gemma":[0.9996952,0.000008615605,0.00002030399,0.0002359496,0.0000188314,0.00002107053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002315105,0.00006389181,0.001783313,0.000003453287,0.000003994723,0.00001019752,0.00001883536,0.002795652,0.009849767,0.1027787,0.0167727,0.8659172],"study_design_scores_gemma":[0.0004124607,0.00007650137,0.02758615,0.00001203652,0.000002908456,0.0002187823,0.00001107246,0.9023848,0.02460434,0.01267146,0.03170924,0.0003102887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03780209,0.00004920314,0.9478774,0.0001213728,0.000303836,0.00002948542,6.385158e-7,0.0001149487,0.01370105],"genre_scores_gemma":[0.2974263,0.00000349429,0.7013372,0.00005126415,0.0001246457,0.000002712411,0.000002726062,0.000002350447,0.001049423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8995891,"threshold_uncertainty_score":0.1424752,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cuckoo; Hash function; Cuckoo search; Theoretical computer science; Algorithm; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.00865126449561512,"gpt":0.2204994529410758,"spread":0.2118481884454607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002619623,0.0001009529,0.000108705,0.0002929765,0.0001885211,0.0007612088,0.0004226921,0.0000355329,0.00002701773],"category_scores_gemma":[0.00003701741,0.00008558577,0.00005748196,0.0009997587,0.000022058,0.006225945,0.0000594862,0.00009473004,0.0001045891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002913989,"about_ca_system_score_gemma":0.00004111243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008520559,"about_ca_topic_score_gemma":5.013276e-7,"domain_scores_codex":[0.9990841,0.00003039117,0.0002651256,0.0001318342,0.0002995869,0.0001890263],"domain_scores_gemma":[0.9993524,0.00001698016,0.0001752218,0.0003252914,0.00007103628,0.00005907811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001226235,0.00009973594,0.009207245,0.0001558711,0.0002904043,0.00001221767,0.02229653,0.0279057,0.00163917,0.02407226,0.02513928,0.8891693],"study_design_scores_gemma":[0.0006290104,0.00002039677,0.005888114,0.00004676618,0.00008057831,0.00002209924,0.0002228993,0.6652657,0.002031127,0.0006936958,0.3245089,0.0005906934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005632772,0.00004848624,0.9899861,0.001699063,0.0001269289,0.00004898944,0.000001515953,0.00016988,0.002286329],"genre_scores_gemma":[0.797756,0.000004761312,0.1919169,0.0101952,0.00003015328,0.00001300324,0.00003521869,0.000005585204,0.00004324734],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8885786,"threshold_uncertainty_score":0.7340354,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02284381078697994,"gpt":0.281223494833351,"spread":0.258379684046371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002341323,0.00007260102,0.0000764205,0.00008123834,0.0001807721,0.00007199232,0.0002273597,0.00004502742,0.000009487474],"category_scores_gemma":[0.00002754576,0.00005575041,0.00001968456,0.0001364767,0.00001786606,0.0004877521,0.0002067896,0.00005193018,0.000005831343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001094461,"about_ca_system_score_gemma":0.00001690579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007142362,"about_ca_topic_score_gemma":0.0001019368,"domain_scores_codex":[0.9993834,0.000007804398,0.000134565,0.0002224891,0.00008642544,0.0001652373],"domain_scores_gemma":[0.9994515,0.0001738162,0.00003704133,0.0002286991,0.00003893476,0.00007000883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005782196,0.0004946013,0.05596939,0.00002955019,0.00004777079,0.00002618748,0.0009440426,0.0001470006,0.01149554,0.231974,0.01528549,0.6835287],"study_design_scores_gemma":[0.001765495,0.0002063494,0.310828,0.00002648377,0.000007673943,0.00001153673,0.00006586456,0.6693389,0.003186743,0.00168022,0.01260429,0.0002783612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07639174,0.0001556747,0.9226547,0.0002061527,0.00009870562,0.0001453525,0.000005572785,0.00011127,0.0002307712],"genre_scores_gemma":[0.4588437,0.0000100471,0.5397695,0.00007415374,0.0000336522,0.00000517925,0.000008686767,0.000004278237,0.001250844],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6832503,"threshold_uncertainty_score":0.2273436,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01936819052923327,"gpt":0.2530895295810157,"spread":0.2337213390517824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000255875,0.0001627922,0.0001678476,0.00009105574,0.0002270564,0.0002087974,0.000655595,0.0000679199,0.0002572726],"category_scores_gemma":[0.0000534375,0.0001254226,0.00005738798,0.0003396069,0.0000538967,0.0005218966,0.0001911843,0.0001556889,0.0001119265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461651,"about_ca_system_score_gemma":0.0000859607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002917261,"about_ca_topic_score_gemma":0.000002772177,"domain_scores_codex":[0.9985674,0.0001073962,0.0002364601,0.0004480523,0.0003175263,0.0003231751],"domain_scores_gemma":[0.99883,0.0001538519,0.00008959581,0.0007062177,0.00007329122,0.0001470837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000487418,0.0001543457,0.002089447,0.00001619094,0.00001211378,0.00004051498,0.00007632637,0.000299536,0.001350079,0.2923489,0.007978644,0.6956291],"study_design_scores_gemma":[0.001305614,0.00006539536,0.0004903737,0.0001004522,0.000005454125,0.00007494427,0.0001557574,0.8713452,0.04561935,0.00480142,0.07547303,0.000563056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001372324,0.00009056591,0.9711008,0.0002119861,0.0006197543,0.0001089255,0.000003193258,0.0003156112,0.02617686],"genre_scores_gemma":[0.1928249,0.00000288417,0.8061996,0.0004523873,0.00004439057,0.000007912588,0.000008148889,0.00001022735,0.0004495303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8710456,"threshold_uncertainty_score":0.5114585,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006358395880270913,"gpt":0.2351972356445886,"spread":0.2288388397643177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006499834,0.0006396371,0.0005757731,0.0002876454,0.0008914202,0.000444891,0.004012912,0.0002108196,0.0000246255],"category_scores_gemma":[0.00011208,0.0004528865,0.0004256069,0.0009773214,0.0001476517,0.001695121,0.001817675,0.0005910155,0.000113261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001391842,"about_ca_system_score_gemma":0.0000919248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001556765,"about_ca_topic_score_gemma":0.000007760523,"domain_scores_codex":[0.9954686,0.00006195262,0.0008366218,0.001170881,0.001430181,0.001031721],"domain_scores_gemma":[0.9976414,0.0001110783,0.000411563,0.001042971,0.0005531668,0.0002397984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004950535,0.009399571,0.005323042,0.0006227093,0.0008501148,0.00004911057,0.006130023,0.004943384,0.04134895,0.319816,0.5397025,0.0713195],"study_design_scores_gemma":[0.01227397,0.005444584,0.02030077,0.002566015,0.0004107683,0.0002303789,0.001854122,0.4194803,0.3001698,0.02371479,0.2084505,0.005104043],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5762157,0.002616488,0.2477671,0.08083202,0.009403009,0.01338974,0.0105115,0.004488959,0.05477545],"genre_scores_gemma":[0.9323636,0.0001270232,0.05713166,0.001640877,0.00136348,0.0002298076,0.0002689043,0.0001424737,0.006732172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4145369,"threshold_uncertainty_score":0.9997923,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007316668029087797,"gpt":0.2601985053427479,"spread":0.2528818373136601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00236935,0.0001681062,0.000179003,0.0001606685,0.0005838955,0.0006244772,0.001608865,0.0000597811,0.00001023578],"category_scores_gemma":[0.00007121933,0.000129063,0.00004586515,0.0006557016,0.001753954,0.0008723389,0.001165959,0.0001440136,0.000009061354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003169372,"about_ca_system_score_gemma":0.00008935645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002326927,"about_ca_topic_score_gemma":4.376581e-7,"domain_scores_codex":[0.9978408,0.00002695037,0.0002343788,0.000724851,0.0004973995,0.0006756825],"domain_scores_gemma":[0.9984781,0.0004121867,0.00005126259,0.0005735732,0.0001736721,0.0003112525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003039319,0.00004143381,0.00004537272,0.000005205252,0.000002464937,0.000008041648,0.0001698899,0.00003894886,0.000595662,0.9013503,0.0001453977,0.09756687],"study_design_scores_gemma":[0.0006059979,0.0006197638,0.001962294,0.00002954593,0.000004913131,0.00008241127,0.000004050008,0.9104412,0.00635826,0.07727003,0.002283003,0.0003385531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05595393,0.00005376359,0.9422053,0.0003415271,0.00062637,0.0001858987,0.000002560322,0.0001364455,0.000494269],"genre_scores_gemma":[0.5822266,0.000002640876,0.4173099,0.0003129503,0.0001321687,0.000003020226,6.855835e-7,0.000004549452,0.000007488164],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9104022,"threshold_uncertainty_score":0.6462516,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.003248471905147706,"gpt":0.1557511980705495,"spread":0.1525027261654018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001395464,0.00009728333,0.0001474985,0.00003992633,0.0001511759,0.00003364652,0.0006015346,0.00005224204,0.00002168441],"category_scores_gemma":[0.00001479811,0.00005243256,0.00005569691,0.0002072903,0.0001878603,0.0008959541,0.0007142919,0.00007587815,0.000009073938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003141934,"about_ca_system_score_gemma":0.00002319331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001138896,"about_ca_topic_score_gemma":0.0000090563,"domain_scores_codex":[0.9992607,0.00008354187,0.0001120917,0.0002417691,0.0001704484,0.0001314614],"domain_scores_gemma":[0.9991823,0.0001701293,0.0001191799,0.0004121348,0.00005652884,0.00005976146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001108864,0.00001984187,0.0001262615,0.00000729868,0.00002098327,0.000004372341,0.0005711895,0.000004434085,0.007345835,0.01841222,0.001688063,0.9716886],"study_design_scores_gemma":[0.02852597,0.00113063,0.2598954,0.002011785,0.0001758354,0.0002436785,0.002087584,0.4726289,0.03335004,0.03566133,0.1627251,0.001563834],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3446918,0.0001430768,0.6504943,0.001940872,0.0003511165,0.000161861,0.000009310047,0.0001171137,0.002090465],"genre_scores_gemma":[0.9976418,0.00006015184,0.001625674,0.00005903039,0.00002517592,8.694891e-7,0.000002042442,0.000005015997,0.0005802397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9701248,"threshold_uncertainty_score":0.2138138,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics; Combinatorics; Necklace; Alphabet; Permutation (music); Algorithm; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01128066133810982,"gpt":0.2575280766633357,"spread":0.2462474153252258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001103193,0.0004485161,0.0007589398,0.0004367206,0.0003273809,0.0007739387,0.0015422,0.000181806,0.000399034],"category_scores_gemma":[0.00005291653,0.0003617124,0.000185948,0.0008638393,0.00008440263,0.002051366,0.0004568794,0.0004942092,0.0001065264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216125,"about_ca_system_score_gemma":0.000279517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001661195,"about_ca_topic_score_gemma":0.000005749015,"domain_scores_codex":[0.9963835,0.0001795058,0.001080631,0.0006958219,0.0009360369,0.0007244547],"domain_scores_gemma":[0.9974239,0.0001272355,0.0004920425,0.0008263938,0.0003103511,0.0008200455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001007276,0.0002581525,0.0001615194,0.00001796835,0.0001209028,0.0002623814,0.0008049802,0.001447919,0.003423872,0.0002407755,0.0448735,0.9482873],"study_design_scores_gemma":[0.008751879,0.003280756,0.01337137,0.000678158,0.0001759516,0.003659684,0.0002597121,0.3790326,0.01658377,0.00206959,0.5696835,0.002453035],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5164453,0.01063307,0.4542044,0.009247213,0.005449508,0.0009968819,0.0001649502,0.000299811,0.002558904],"genre_scores_gemma":[0.03517928,0.002829263,0.9484095,0.002772768,0.003735807,0.00001964966,0.00001704988,0.0001075149,0.006929172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9458343,"threshold_uncertainty_score":0.9998835,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01642296285742713,"gpt":0.2544252547356321,"spread":0.238002291878205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001442576,0.0001772349,0.0002135267,0.0001398067,0.0001573238,0.00005982874,0.0006232479,0.0001237193,0.00005280459],"category_scores_gemma":[0.00001137534,0.0001625318,0.00009430265,0.0005529066,0.00007699702,0.0005526276,0.000007579736,0.0002003095,0.00008271399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008565868,"about_ca_system_score_gemma":0.0001390566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002800786,"about_ca_topic_score_gemma":0.00006383382,"domain_scores_codex":[0.9985167,0.00005167955,0.0003235911,0.0003900642,0.0004595155,0.0002584739],"domain_scores_gemma":[0.9989468,0.00005995626,0.0001227384,0.0005766211,0.0001601622,0.0001336729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008376309,0.0008944091,0.00001922679,0.0000319022,0.00006981103,0.0000166192,0.0008716767,0.6904095,0.0224899,0.0003180471,0.0001989788,0.2845961],"study_design_scores_gemma":[0.00212969,0.000320901,0.0006980697,0.0001628167,0.0000292471,0.00001442041,0.00005026856,0.7999492,0.1955445,0.0004434894,0.0003286639,0.0003286367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01881803,0.00002498524,0.979607,0.0002746527,0.0005177532,0.0002930339,0.0001398404,0.000210362,0.0001142979],"genre_scores_gemma":[0.6325518,0.00002507526,0.3671941,0.00004744808,0.00003087865,0.00002770814,0.00001783851,0.00001385617,0.00009120631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6137338,"threshold_uncertainty_score":0.6627856,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01491292570024554,"gpt":0.2482037933123638,"spread":0.2332908676121183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003525734,0.0001156416,0.0001324832,0.00003948867,0.0001862986,0.000209423,0.0005381719,0.00004233614,0.00002528548],"category_scores_gemma":[0.00007722557,0.00009087849,0.0000538982,0.0002251618,0.00001917648,0.0006473481,0.0001182354,0.00007135347,0.00002360929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001836128,"about_ca_system_score_gemma":0.00004639633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008441734,"about_ca_topic_score_gemma":0.000001461065,"domain_scores_codex":[0.998902,0.00002643795,0.0002132041,0.0003686599,0.000202642,0.0002870915],"domain_scores_gemma":[0.999161,0.0001021223,0.00007296547,0.0004871734,0.00008821298,0.0000884937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001448726,0.00008566769,0.00002259298,0.00001722122,0.000008385879,0.000003422145,0.0001009828,0.00002167441,0.0001667745,0.3493327,0.01991879,0.6303203],"study_design_scores_gemma":[0.0002582598,0.00003662186,0.00001026018,0.00001097154,0.000001599832,0.000007333214,0.00002214317,0.788049,0.001739349,0.006700237,0.2030222,0.0001420216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002935968,0.0001150091,0.993771,0.000152593,0.0005758943,0.0002095001,0.00001332224,0.0001804012,0.00495299],"genre_scores_gemma":[0.001543341,0.00000464766,0.9966773,0.0001949573,0.0001618157,0.00004512654,0.00001025977,0.000008784915,0.001353796],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7880273,"threshold_uncertainty_score":0.3705917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}