{"meta":{"query_hash":"45fc18fbc93e","filters":{"venue":"Journal of Automated Reasoning"},"cohort_total":27,"direct_labels_cover":0,"predictions_cover":27,"exported":27,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/45fc18fbc93e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Automated+Reasoning"},"results":[{"id":"W1505627668","doi":"10.1023/a:1027357912519","title":"Theorem Proving Modulo","year":2003,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":214,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prevention of Organ Failure","funders":"","keywords":"Modulo; Sequent calculus; Sequent; Cut-elimination theorem; Mathematics; Mathematical proof; Axiom; Congruence (geometry); Natural deduction; Calculus (dental); Automated theorem proving; Proof theory; Completeness (order theory); Algebra over a field; Resolution (logic); Proof complexity; Discrete mathematics; Algorithm; Computer science; Pure mathematics; Programming language","score_opus":0.011645318810620517,"score_gpt":0.24429414951481207,"score_spread":0.23264883070419157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505627668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07068948,0.0016929569,0.8962251,0.00020765414,0.0024324358,0.00019532174,1.2769753e-7,0.00086820597,0.027688734],"genre_scores_gemma":[0.96566916,0.000010524329,0.034019444,0.0000438474,0.00009597849,0.0000011746703,1.1711606e-7,0.000010635153,0.00014910051],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860084,0.00019280736,0.00042090125,0.00015005468,0.00034909538,0.00028627424],"domain_scores_gemma":[0.9988013,0.000073258285,0.00054215424,0.0002459397,0.0002157427,0.00012159218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013980592,0.00012334505,0.0002380304,0.00014266756,0.00013512521,0.00027437296,0.00052679837,0.0000741501,0.000009496168],"category_scores_gemma":[0.00039584396,0.000087372864,0.00011822793,0.0003460719,0.000026045996,0.0005554072,0.00004692918,0.00021927312,0.00002019551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070819947,0.00010006604,0.002703099,0.000036782687,0.0001078579,0.00035139162,0.0020285673,0.0008229424,0.0023023041,0.96864504,0.0013795793,0.021515273],"study_design_scores_gemma":[0.0045400555,0.0018611741,0.008858267,0.0005742827,0.00014053221,0.019433603,0.0016704042,0.74021673,0.038242135,0.10461507,0.07814989,0.0016978605],"about_ca_topic_score_codex":0.0000074231884,"about_ca_topic_score_gemma":7.773012e-7,"teacher_disagreement_score":0.8949797,"about_ca_system_score_codex":0.0000624724,"about_ca_system_score_gemma":0.00016512531,"threshold_uncertainty_score":0.3562962},"labels":[],"label_agreement":null},{"id":"W1510672616","doi":"10.1023/a:1006279127474","title":"A Hyperbase for Binary Lattice Hyperidentities","year":2000,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Advanced Algebra and Logic","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Arity; Variety (cybernetics); Identity (music); Binary relation; Combinatorics; Binary number; Discrete mathematics; Mathematics; Set (abstract data type); Computer science; Physics; Arithmetic; Programming language","score_opus":0.01094980265880392,"score_gpt":0.26148411851399683,"score_spread":0.2505343158551929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510672616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94990367,0.0013679094,0.045782495,0.00063891086,0.00047869328,0.000096691045,0.0000017896698,0.0004016152,0.0013282432],"genre_scores_gemma":[0.76419175,0.00013200754,0.23440456,0.00029063853,0.00020222642,0.000003789327,7.75366e-7,0.00001456645,0.0007596867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990658,0.000041123625,0.00032847314,0.00012729598,0.00020493887,0.00023235772],"domain_scores_gemma":[0.99921006,0.00016177147,0.00021908988,0.00017072137,0.0001434562,0.000094893185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030865482,0.000107098545,0.0002111736,0.000110308,0.00015735181,0.00012879654,0.00047690346,0.000047000827,0.000057979625],"category_scores_gemma":[0.00011640376,0.00008507427,0.00013000869,0.00024349091,0.000028953682,0.00096485915,0.00003328784,0.00013311916,0.000021151887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009533056,0.0013864646,0.0023497622,0.0004558018,0.00091513677,0.0044939485,0.0093901185,0.09356059,0.045651335,0.14007998,0.04543446,0.6553291],"study_design_scores_gemma":[0.0026111654,0.0012453493,0.0067983237,0.00065041106,0.00008845578,0.0040842784,0.0003462834,0.93591136,0.0046117804,0.010451918,0.032638274,0.00056241796],"about_ca_topic_score_codex":0.0000022306701,"about_ca_topic_score_gemma":2.8661455e-7,"teacher_disagreement_score":0.8423508,"about_ca_system_score_codex":0.0000370719,"about_ca_system_score_gemma":0.00008209394,"threshold_uncertainty_score":0.3469228},"labels":[],"label_agreement":null},{"id":"W1551936078","doi":"10.1007/s10817-015-9327-3","title":"The Next 700 Challenge Problems for Reasoning with Higher-Order Abstract Syntax Representations","year":2015,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Syntax; Computer science; Variety (cybernetics); Context (archaeology); Automated reasoning; Order (exchange); Reasoning system; Abstract syntax; Programming language; Artificial intelligence; Natural language processing","score_opus":0.05308342773294895,"score_gpt":0.29909218086303746,"score_spread":0.24600875313008852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1551936078","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05541998,0.018954534,0.85594594,0.01609241,0.007177722,0.0028575445,0.0000035963067,0.002852927,0.04069534],"genre_scores_gemma":[0.9575792,0.00007427404,0.04146432,0.00003070071,0.00034140013,0.00003148507,0.0000016343304,0.000026076836,0.0004509361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980955,0.0001024588,0.0005733751,0.00024320513,0.0005639549,0.000421483],"domain_scores_gemma":[0.9971253,0.00033491972,0.0009923795,0.00039023577,0.00093298516,0.0002241776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017378983,0.00018536109,0.00028947275,0.00010611462,0.00044061,0.00076144334,0.0007744856,0.00009402956,0.0000027990004],"category_scores_gemma":[0.00032065337,0.00010638594,0.00010904988,0.0004253547,0.00006977512,0.0009790743,0.00007892673,0.00028717358,0.00000982928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005135267,0.00096059334,0.0057310686,0.0003893026,0.0021652475,0.00085484807,0.029087117,0.036601536,0.0010686393,0.7272596,0.03711289,0.15825565],"study_design_scores_gemma":[0.0103244195,0.005538289,0.019506838,0.0016459377,0.0003853669,0.005966263,0.008779748,0.538832,0.0010792818,0.0289054,0.37707046,0.0019659891],"about_ca_topic_score_codex":0.00008591863,"about_ca_topic_score_gemma":0.00003067193,"teacher_disagreement_score":0.9021592,"about_ca_system_score_codex":0.00010427457,"about_ca_system_score_gemma":0.00035636438,"threshold_uncertainty_score":0.7342616},"labels":[],"label_agreement":null},{"id":"W1576724046","doi":"10.1023/a:1010624702918","title":"Current Trends in Logical Frameworks and Metalanguages","year":2001,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Mathematics","score_opus":0.015101783410440592,"score_gpt":0.29959176747971816,"score_spread":0.28448998406927756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576724046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93288267,0.019895336,0.040840358,0.000717488,0.00097103725,0.000053604446,4.4158313e-7,0.00033889583,0.004300202],"genre_scores_gemma":[0.9860952,0.00065305753,0.0129706655,0.00005523794,0.000155592,0.0000010659318,5.950407e-7,0.000007821886,0.00006075643],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986178,0.00013516813,0.00043548862,0.00020992562,0.0002786283,0.00032293386],"domain_scores_gemma":[0.9990727,0.00014631906,0.0003260315,0.00017894852,0.00010578454,0.0001702346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071869505,0.00016286258,0.00035856038,0.00045264358,0.00007533865,0.00019587166,0.00046778156,0.00017902956,0.000038485436],"category_scores_gemma":[0.00028291822,0.00011461956,0.00011083538,0.00079555885,0.00004853224,0.0005035582,0.00014445321,0.0007902592,0.000005762428],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056690016,0.0005066805,0.06578331,0.00002530213,0.00011315246,0.002379723,0.005767103,0.00067358545,0.0005794705,0.021719458,0.0030510207,0.8993445],"study_design_scores_gemma":[0.0022311257,0.00056743284,0.54562247,0.0010723446,0.00006242903,0.0061878036,0.00029987955,0.4320608,0.00032494526,0.003074351,0.007895595,0.00060079404],"about_ca_topic_score_codex":0.0000070893298,"about_ca_topic_score_gemma":0.0000060039188,"teacher_disagreement_score":0.8987437,"about_ca_system_score_codex":0.000058259917,"about_ca_system_score_gemma":0.000044171033,"threshold_uncertainty_score":0.467405},"labels":[],"label_agreement":null},{"id":"W1585415359","doi":"10.1023/a:1021966832558","title":"A Compendium of Continuous Lattices in MIZAR","year":2002,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Advanced Algebra and Logic","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Compendium; Mathematical proof; Programming language; Computer science; Correctness; Simple (philosophy); Proof assistant; Calculus (dental); Mathematics; Linguistics; Philosophy; Epistemology","score_opus":0.013289680983207519,"score_gpt":0.2462505761073052,"score_spread":0.23296089512409768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585415359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9681269,0.0028570811,0.025050025,0.00047025582,0.00043180608,0.00007420857,6.749723e-7,0.00017115034,0.0028179272],"genre_scores_gemma":[0.9484464,0.000074845884,0.051355492,0.00005002049,0.000031395884,3.3916308e-7,9.5837834e-8,0.0000051735033,0.000036217607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889517,0.00007544737,0.00049320183,0.00010336591,0.00023812901,0.00019469966],"domain_scores_gemma":[0.9989174,0.00013981774,0.000617979,0.0001505492,0.000110262044,0.00006398138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003214743,0.00009093823,0.00031839177,0.00021553958,0.000032958724,0.000040260733,0.00050576386,0.000048711427,0.000032128624],"category_scores_gemma":[0.00013774574,0.000071631366,0.00007464003,0.00040563938,0.000033035914,0.0005143932,0.00006270823,0.00019719377,0.000008179494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033832554,0.005138068,0.18176453,0.0006857764,0.0010452892,0.014261584,0.044451807,0.1299058,0.104697555,0.19275111,0.018702948,0.30625722],"study_design_scores_gemma":[0.0019775915,0.0005011848,0.034832884,0.0008267308,0.000020188123,0.001256597,0.00026836246,0.9530478,0.0046003796,0.0013815903,0.0010270044,0.0002596959],"about_ca_topic_score_codex":0.000005582528,"about_ca_topic_score_gemma":0.0000016468972,"teacher_disagreement_score":0.823142,"about_ca_system_score_codex":0.00002855073,"about_ca_system_score_gemma":0.000021151209,"threshold_uncertainty_score":0.29210424},"labels":[],"label_agreement":null},{"id":"W1588366745","doi":"10.1023/a:1026517200045","title":"Structured Theory Development for a Mechanized Logic","year":2001,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Structuring; Correctness; Computer science; Automated theorem proving; Programming language; Theoretical computer science","score_opus":0.019583075904262302,"score_gpt":0.26718545928573706,"score_spread":0.24760238338147475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588366745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018728778,0.0005175932,0.9785566,0.0001236543,0.0009575631,0.00018696739,1.3206646e-7,0.00035276596,0.0005759505],"genre_scores_gemma":[0.8243628,0.000010551884,0.17525083,0.00008592296,0.00012253007,0.0000053669187,8.1809526e-7,0.000010296422,0.00015088555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863565,0.000113086426,0.0004920924,0.00016284554,0.00029292912,0.00030342024],"domain_scores_gemma":[0.9986849,0.00013097696,0.0005903967,0.00017812852,0.0003027152,0.000112886795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014478829,0.00014139032,0.00029325645,0.00016128573,0.00017807569,0.00018585152,0.0006037076,0.00009328993,0.00001269186],"category_scores_gemma":[0.00025544243,0.00009680832,0.000119348886,0.0002880258,0.000015279895,0.00029262344,0.000068837726,0.00013483847,0.000007345603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019084329,0.00012830022,0.00043751477,0.000066655404,0.00040375305,0.00038421847,0.0046788994,0.00042464148,0.006131251,0.8341465,0.0013627632,0.15164466],"study_design_scores_gemma":[0.010842056,0.0019607788,0.0062366305,0.0004014347,0.0001873274,0.013498563,0.001511205,0.30193308,0.033454675,0.5106934,0.11760951,0.0016713438],"about_ca_topic_score_codex":0.000002087621,"about_ca_topic_score_gemma":0.0000018497288,"teacher_disagreement_score":0.805634,"about_ca_system_score_codex":0.00008664657,"about_ca_system_score_gemma":0.00020152527,"threshold_uncertainty_score":0.3947729},"labels":[],"label_agreement":null},{"id":"W1589528070","doi":"10.1023/a:1020116927466","title":"SLT-Resolution for the Well-Founded Semantics","year":2002,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Prolog; Computer science; Resolution (logic); Computation; Semantics (computer science); Programming language; Algorithm; Extension (predicate logic); Theoretical computer science","score_opus":0.023214735034764365,"score_gpt":0.2570563489167325,"score_spread":0.23384161388196814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589528070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02683329,0.006960704,0.94876134,0.004059337,0.0037109307,0.00038178702,0.0000014675771,0.00076044194,0.008530686],"genre_scores_gemma":[0.95997924,0.0002955203,0.038375165,0.00015627727,0.0004801048,0.0000041525727,4.3518736e-7,0.000017347249,0.0006917729],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985232,0.00009870543,0.00046582162,0.00017233509,0.00036393563,0.0003760106],"domain_scores_gemma":[0.9980156,0.0005392631,0.0005986464,0.00033406558,0.0003984799,0.000113944785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010355593,0.0001627145,0.0002600723,0.0001338666,0.00044573928,0.00031953896,0.00097353687,0.00011481418,0.000031633597],"category_scores_gemma":[0.00054500136,0.0001011023,0.00023344152,0.0004020251,0.00005628475,0.0005219286,0.00010718899,0.00030044877,0.000051429066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018375319,0.0013140183,0.003563041,0.00027540658,0.0016555941,0.00053871656,0.020357162,0.0414739,0.005361182,0.3157883,0.48344237,0.12604655],"study_design_scores_gemma":[0.00073547265,0.00024208252,0.0013539654,0.00013412152,0.000055669145,0.0006398631,0.00009674077,0.97758275,0.00048767807,0.0007249854,0.017801926,0.00014474361],"about_ca_topic_score_codex":0.0000056260915,"about_ca_topic_score_gemma":0.0000036703161,"teacher_disagreement_score":0.9361088,"about_ca_system_score_codex":0.00009700094,"about_ca_system_score_gemma":0.00006115922,"threshold_uncertainty_score":0.41228318},"labels":[],"label_agreement":null},{"id":"W1608678069","doi":"10.1023/a:1006241826565","title":"Efficient Algorithms to Detect and Restore Minimality, an Extension of the Regular Restriction of Resolution","year":2000,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical proof; Binary tree; Mathematics; Tree (set theory); Resolution (logic); Algorithm; Completeness (order theory); Binary number; Redundancy (engineering); K-ary tree; Discrete mathematics; Computer science; Combinatorics; Tree structure; Arithmetic; Artificial intelligence","score_opus":0.015968935075559625,"score_gpt":0.2606211021731402,"score_spread":0.2446521670975806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1608678069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96181524,0.00046130878,0.03697601,0.00011802145,0.00030369082,0.0001321002,4.1567384e-7,0.00006276829,0.00013047317],"genre_scores_gemma":[0.97517526,0.000023479059,0.024701644,0.000010819643,0.000057026034,7.130691e-7,1.7708079e-7,0.0000057423626,0.000025125868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984931,0.00025048162,0.00049434614,0.00016170075,0.00044830114,0.00015209262],"domain_scores_gemma":[0.99873626,0.000044869943,0.0005274351,0.0003297566,0.0002720457,0.0000896262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012441229,0.00008892,0.00021992101,0.00013948375,0.00011706378,0.000043944518,0.00034063068,0.00007811744,0.0000018228858],"category_scores_gemma":[0.00014287775,0.000057689438,0.00007558623,0.00052984915,0.000049824965,0.00013391985,0.00007041412,0.00012299464,6.901492e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005637521,0.00051016733,0.005254589,0.00025669986,0.0002004205,0.00017963973,0.011642037,0.124786325,0.13623038,0.012855656,0.0014565592,0.70606375],"study_design_scores_gemma":[0.00083911314,0.0017935148,0.20760588,0.00046664392,0.000057368663,0.00088755204,0.0002439699,0.77151054,0.0142806405,0.0008432201,0.0012665305,0.0002050281],"about_ca_topic_score_codex":0.0001246629,"about_ca_topic_score_gemma":0.000005228793,"teacher_disagreement_score":0.70585877,"about_ca_system_score_codex":0.00005160955,"about_ca_system_score_gemma":0.0000694936,"threshold_uncertainty_score":0.2352507},"labels":[],"label_agreement":null},{"id":"W1946985707","doi":"10.1023/a:1015736313131","title":"The IJCAR ATP System Competition","year":2002,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Programming language; Mathematics","score_opus":0.01484449246328016,"score_gpt":0.23039942048336498,"score_spread":0.21555492802008483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1946985707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07132954,0.01822915,0.8204706,0.0046670455,0.014378248,0.0007090608,0.0000010598285,0.004448195,0.065767124],"genre_scores_gemma":[0.9966967,0.000053625117,0.0027919442,0.000029985176,0.00024362616,0.0000016549607,1.7260734e-7,0.000008064338,0.00017424497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862933,0.00015682056,0.00044835953,0.00011255579,0.00040619526,0.00024674283],"domain_scores_gemma":[0.99868655,0.0001311106,0.0005997515,0.0002563047,0.00023284396,0.000093409224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008938497,0.000103921346,0.00019567723,0.00007797056,0.00036911698,0.0004311482,0.0006692662,0.000062165534,0.0000050278054],"category_scores_gemma":[0.000081177874,0.0000611867,0.00011961417,0.00029136817,0.00003465745,0.0003577248,0.00006181301,0.00019484998,0.000076161916],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011296686,0.0001005765,0.0009292257,0.00010017466,0.00022239714,0.00057901436,0.0041199634,0.0007812206,0.00074271625,0.9368878,0.010188069,0.04533756],"study_design_scores_gemma":[0.000697043,0.00030333493,0.001480714,0.00022369965,0.00003087897,0.0045745745,0.00076097593,0.92234725,0.0004756487,0.0004454023,0.06844022,0.00022027292],"about_ca_topic_score_codex":0.000011324801,"about_ca_topic_score_gemma":0.0000012994797,"teacher_disagreement_score":0.9364424,"about_ca_system_score_codex":0.00010432165,"about_ca_system_score_gemma":0.000027062106,"threshold_uncertainty_score":0.41575718},"labels":[],"label_agreement":null},{"id":"W1970823361","doi":"10.1007/s10817-010-9212-z","title":"Preface: Special Issue of Selected Extended Papers of CADE-22","year":2010,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Presentation (obstetrics); Implementation; Automated theorem proving; Process (computing); Automated reasoning; Library science; Operations research; Information retrieval; Software engineering; Artificial intelligence; Programming language; Mathematics; Medicine","score_opus":0.0038877114493820015,"score_gpt":0.23696334589476348,"score_spread":0.23307563444538149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970823361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.390627,0.00006886974,0.60673404,0.00011688215,0.00089828373,0.00011736776,0.0000029095713,0.0006678852,0.0007667582],"genre_scores_gemma":[0.5441373,0.0000171387,0.45549983,0.000007404151,0.00028127368,9.934307e-7,4.918018e-7,0.000014940248,0.000040623683],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983246,0.000060269933,0.0006945648,0.00016258369,0.00051815785,0.00023984104],"domain_scores_gemma":[0.9979843,0.00008409392,0.0008430776,0.00036277136,0.0006090651,0.00011668572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005688304,0.0001642585,0.00042901663,0.00030386544,0.000039857172,0.00003442205,0.0008949636,0.0001693509,0.000075473734],"category_scores_gemma":[0.00018424912,0.00014404077,0.00012359355,0.00065306533,0.00005932789,0.00036984798,0.000117316005,0.00057102286,0.0000016524085],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057945384,0.0002422279,0.001478788,0.00013722597,0.00023718148,0.0001097041,0.002488094,0.0046498133,0.90791446,0.012471113,0.010142693,0.060070768],"study_design_scores_gemma":[0.0011946996,0.0007856799,0.055465564,0.00089146604,0.000077587545,0.001056544,0.000023829482,0.33767045,0.5746896,0.00027821332,0.027356064,0.00051029085],"about_ca_topic_score_codex":0.000013950844,"about_ca_topic_score_gemma":0.0000023118791,"teacher_disagreement_score":0.33322483,"about_ca_system_score_codex":0.00004342947,"about_ca_system_score_gemma":0.00022147731,"threshold_uncertainty_score":0.5873812},"labels":[],"label_agreement":null},{"id":"W1983313062","doi":"10.1007/s10817-009-9158-1","title":"Preface: Special Issue on Uncertain Reasoning","year":2009,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of Guelph","funders":"","keywords":"Computer science; Cognitive science; Management science; Epistemology; Psychology; Philosophy; Economics","score_opus":0.010693111983015832,"score_gpt":0.2717349721788356,"score_spread":0.26104186019581976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983313062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58288145,0.0041266736,0.17757912,0.025893798,0.012681366,0.0009479289,0.000014062887,0.006182565,0.18969303],"genre_scores_gemma":[0.8041727,0.000051182822,0.18837927,0.0011686094,0.0054588625,0.0000011248834,0.0000033730375,0.000029331872,0.00073555205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777585,0.00019080234,0.0006138465,0.0002807344,0.00065656926,0.00048217102],"domain_scores_gemma":[0.9982185,0.00023240385,0.00074711913,0.0003515502,0.00022094206,0.00022952737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012953214,0.00024672196,0.0003923975,0.00032321128,0.00030575934,0.00035573347,0.00089963985,0.00014739907,0.000060872288],"category_scores_gemma":[0.00048605964,0.00020547686,0.00015793928,0.0005913647,0.00002400565,0.0006787638,0.00005282707,0.000671492,0.00006249416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041890857,0.00049528293,0.0025081532,0.00006105902,0.00028504262,0.0033686266,0.011258845,0.20483755,0.004081266,0.022025205,0.32950056,0.42115954],"study_design_scores_gemma":[0.0022101442,0.0030658955,0.014622799,0.004672665,0.00006716401,0.0022276621,0.00025687198,0.8949203,0.0064627994,0.0017744304,0.06878798,0.000931283],"about_ca_topic_score_codex":0.000009361751,"about_ca_topic_score_gemma":5.2285054e-7,"teacher_disagreement_score":0.6900828,"about_ca_system_score_codex":0.00015376454,"about_ca_system_score_gemma":0.00024124968,"threshold_uncertainty_score":0.8379103},"labels":[],"label_agreement":null},{"id":"W1997780525","doi":"10.1007/s10817-007-9082-1","title":"Inferring Phylogenetic Trees Using Answer Set Programming","year":2007,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Austrian Science Fund; National Science Foundation","keywords":"Cladistics; Phylogenetic tree; Computer science; Taxon; Set (abstract data type); Formalism (music); Phylogenetics; Theoretical computer science; Representation (politics); Artificial intelligence; Programming language; Biology; Paleontology","score_opus":0.023768570543806867,"score_gpt":0.2980693273525292,"score_spread":0.27430075680872235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997780525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73943204,0.00128332,0.25665665,0.000036531466,0.00090983044,0.00010022438,3.213003e-7,0.00041615922,0.0011649131],"genre_scores_gemma":[0.8451947,0.000018265897,0.15435313,0.00004143908,0.0003409506,5.711451e-7,4.607996e-7,0.000021278407,0.000029202436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767095,0.000101690726,0.00076933583,0.0002687712,0.00051131705,0.00067795505],"domain_scores_gemma":[0.9980382,0.00017914729,0.0007935509,0.00031445778,0.00039496497,0.0002797109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019367277,0.00025280984,0.00040717723,0.00045254454,0.00027303706,0.0003500698,0.00084149925,0.0001496094,0.000009029505],"category_scores_gemma":[0.0003463748,0.00020547785,0.0002091831,0.00083488843,0.00006319574,0.0007125559,0.00019365919,0.00039476482,0.000009359329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002011122,0.0009882543,0.24004658,0.00026376703,0.0011735769,0.005924863,0.031172464,0.03687591,0.15971145,0.015498462,0.0012386708,0.5069049],"study_design_scores_gemma":[0.0022664098,0.0007836327,0.102186404,0.001463708,0.00015912198,0.007137577,0.00080264086,0.8507912,0.026785728,0.00054278347,0.0060346266,0.001046149],"about_ca_topic_score_codex":0.000024605226,"about_ca_topic_score_gemma":0.000018592758,"teacher_disagreement_score":0.8139153,"about_ca_system_score_codex":0.00018151487,"about_ca_system_score_gemma":0.00022146423,"threshold_uncertainty_score":0.8379143},"labels":[],"label_agreement":null},{"id":"W1998720940","doi":"10.1007/s10817-004-3243-2","title":"Octopus: Combining Learning and Parallel Search","year":2004,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"octopus (software); Automated theorem proving; Computer science; Artificial intelligence; Theoretical computer science","score_opus":0.016793824533640863,"score_gpt":0.2775686066946598,"score_spread":0.26077478216101896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998720940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42644644,0.002845412,0.5652433,0.0006950031,0.00084497617,0.00015492424,8.426343e-8,0.0008060578,0.002963826],"genre_scores_gemma":[0.96232677,0.0000774183,0.037389472,0.000032094424,0.00008935656,8.236074e-7,3.3601464e-7,0.000010744388,0.00007297039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860585,0.00012404434,0.0003990302,0.00017023688,0.00038525215,0.00031559917],"domain_scores_gemma":[0.9990886,0.00008641114,0.00035399018,0.0001239067,0.00018337903,0.00016375414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011402793,0.0001271794,0.0002741186,0.00017763463,0.00023843003,0.0003590849,0.00037362633,0.00008285764,0.0000033358097],"category_scores_gemma":[0.0001621889,0.00009936091,0.0000758983,0.00030776844,0.00004610646,0.00050950854,0.00013178047,0.0004406802,0.000012346504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010003295,0.00045875288,0.06372007,0.00027903751,0.000667096,0.0033024552,0.035570327,0.063533954,0.008419163,0.71317434,0.0005622136,0.11021255],"study_design_scores_gemma":[0.020035747,0.006712616,0.055950604,0.0019099618,0.00019065241,0.033983435,0.008470089,0.7969128,0.0076964605,0.041428994,0.024200274,0.0025083544],"about_ca_topic_score_codex":0.00004621613,"about_ca_topic_score_gemma":0.000001452689,"teacher_disagreement_score":0.7333789,"about_ca_system_score_codex":0.000067043766,"about_ca_system_score_gemma":0.0001469275,"threshold_uncertainty_score":0.40518203},"labels":[],"label_agreement":null},{"id":"W2015771391","doi":"10.1007/s10817-009-9134-9","title":"Faster and More Complete Extended Static Checking for the Java Modeling Language","year":2009,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Programming language; Computer science; Java Modeling Language; Java; Programming language specification; Model checking; Generics in Java; Real time Java; Java annotation","score_opus":0.026200420908421347,"score_gpt":0.2924356150562363,"score_spread":0.26623519414781494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015771391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06640595,0.0018233155,0.93017274,0.0008526134,0.00026839325,0.00018014059,5.572036e-7,0.00016363536,0.00013262978],"genre_scores_gemma":[0.96981907,0.00001795104,0.029782223,0.00022189652,0.00012021015,0.0000017743372,6.718453e-7,0.000007662672,0.000028527633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897116,0.000049199345,0.00036175502,0.00013309042,0.00024083351,0.00024394102],"domain_scores_gemma":[0.9991223,0.00013347104,0.0003380385,0.00017883215,0.00015531527,0.00007200094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007749048,0.00011581012,0.0002229494,0.000082653576,0.0002010174,0.0003230235,0.0003879055,0.00004347232,0.000001295658],"category_scores_gemma":[0.00010347737,0.00006917332,0.00007572126,0.00013524259,0.000020899291,0.00033950704,0.00004338916,0.00015654437,0.0000011596322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019134881,0.00034476476,0.00073333905,0.00034531186,0.0008165889,0.00070524233,0.103338815,0.08413235,0.021970453,0.10662976,0.0023523627,0.6784397],"study_design_scores_gemma":[0.0004815258,0.00018115598,0.0006637785,0.00006014078,0.00002597132,0.00044472952,0.0010622594,0.9955311,0.0001253804,0.0011120241,0.00021762185,0.00009430919],"about_ca_topic_score_codex":0.000015302678,"about_ca_topic_score_gemma":0.000001376737,"teacher_disagreement_score":0.91139877,"about_ca_system_score_codex":0.00002766012,"about_ca_system_score_gemma":0.00004260712,"threshold_uncertainty_score":0.3114923},"labels":[],"label_agreement":null},{"id":"W2016884416","doi":"10.1007/s10817-012-9258-1","title":"Specification and Verification of Concurrent Programs Through Refinements","year":2012,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Programming language; Correctness; Automated theorem proving; Predicate abstraction; Gas meter prover; Predicate (mathematical logic); Predicate transformer semantics; TRACE (psycholinguistics); Proof theory; Proof assistant; Separation logic; Automated proof checking; Theoretical computer science; Model checking; Mathematical proof; Operational semantics; Mathematics; Semantics (computer science)","score_opus":0.04461471312132197,"score_gpt":0.3306390048068866,"score_spread":0.28602429168556465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016884416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41013795,0.0015924624,0.58599186,0.0001438164,0.0010911701,0.00017248889,6.7958456e-7,0.00014614855,0.0007234049],"genre_scores_gemma":[0.5760812,0.000105595565,0.42374456,0.000006655809,0.00005054832,0.00000188073,0.0000012860346,0.0000040064233,0.0000042702573],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99873805,0.00012991077,0.0005485727,0.00009846048,0.00031793278,0.00016704548],"domain_scores_gemma":[0.99833465,0.000038033795,0.0010664216,0.00022550306,0.00026486884,0.00007051572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012224673,0.00008624521,0.00017172201,0.000091040434,0.000056618326,0.000050580886,0.00029878962,0.000054799824,0.0000031618174],"category_scores_gemma":[0.00020482732,0.00007265792,0.00004127602,0.00032040433,0.000050279992,0.0013390828,0.000048366288,0.0001252562,0.000002994377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045164976,0.0007021028,0.019131266,0.00017596272,0.00014180288,0.0000026973532,0.010970258,0.00009899564,0.06827241,0.30453166,0.0006592055,0.5952684],"study_design_scores_gemma":[0.002026791,0.0009904747,0.5081579,0.0012749971,0.00012743063,0.0007550016,0.0009070005,0.27945858,0.18717939,0.0009371709,0.01762431,0.0005609428],"about_ca_topic_score_codex":0.0000039021384,"about_ca_topic_score_gemma":6.807824e-8,"teacher_disagreement_score":0.5947075,"about_ca_system_score_codex":0.000059438382,"about_ca_system_score_gemma":0.00003670729,"threshold_uncertainty_score":0.29629037},"labels":[],"label_agreement":null},{"id":"W2063428900","doi":"10.1007/s10817-009-9121-1","title":"Interprocedural and Flow-Sensitive Type Analysis for Memory and Type Safety of C Code","year":2009,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Memory safety; Type safety; Programming language; Type inference; Alias; Static analysis; Control flow; Source code; Data type; Compiler; Parallel computing; Algorithm; Inference; Artificial intelligence; Data mining","score_opus":0.010342703078796884,"score_gpt":0.28285217948543406,"score_spread":0.2725094764066372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063428900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89329666,0.0005572576,0.10559665,0.00022744216,0.00013410595,0.00006580834,0.000002266607,0.00009740962,0.000022423168],"genre_scores_gemma":[0.9233479,0.000051039337,0.07652856,0.000025609643,0.00002670142,1.445317e-7,6.12118e-7,0.0000048742872,0.000014563086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992235,0.000031183103,0.00027779516,0.00012163438,0.00019397255,0.00015194828],"domain_scores_gemma":[0.9986751,0.00044101494,0.0001777945,0.00011422857,0.00050097395,0.00009088145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005628993,0.00008304926,0.00029007558,0.00032299026,0.000045219775,0.000054249173,0.00017218573,0.000047426234,0.0000013569628],"category_scores_gemma":[0.0013537005,0.00006871747,0.00005749916,0.00071766734,0.000028551704,0.0002293459,0.00005031076,0.00013327508,2.7010856e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050921803,0.0006166128,0.18181422,0.0008493121,0.010365907,0.0010402607,0.036313333,0.2853833,0.124742106,0.0037021823,0.0067561036,0.34332448],"study_design_scores_gemma":[0.0003691307,0.00043250324,0.18420686,0.00016624811,0.000081434846,0.00021454916,0.00006253281,0.81111944,0.0032089017,0.00004207737,0.000016665303,0.00007966047],"about_ca_topic_score_codex":0.0000036070185,"about_ca_topic_score_gemma":0.000001394765,"teacher_disagreement_score":0.52573615,"about_ca_system_score_codex":0.000036209094,"about_ca_system_score_gemma":0.00008719764,"threshold_uncertainty_score":0.2802217},"labels":[],"label_agreement":null},{"id":"W2066986855","doi":"10.1007/s10817-014-9304-2","title":"Absorption for ABoxes","year":2014,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARQL; Description logic; RDF; Conjunctive query; Negation; Computer science; Logical consequence; Knowledge base; Web Ontology Language; RDF Schema; Ontology; Theoretical computer science; Graph; Class (philosophy); Semantics (computer science); Semantic Web; Relational database; Information retrieval; Programming language; Artificial intelligence; Epistemology","score_opus":0.010980371768939567,"score_gpt":0.26614270668747114,"score_spread":0.2551623349185316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066986855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20921068,0.00017411353,0.7878705,0.0008557107,0.0008098369,0.000047488156,1.30638e-7,0.00030741325,0.0007240813],"genre_scores_gemma":[0.8195812,0.000013041034,0.18012843,0.000095864176,0.00014389852,9.187763e-7,1.8259898e-7,0.0000042805777,0.000032188276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993059,0.000039575334,0.0002585993,0.000084105246,0.00016090782,0.00015088257],"domain_scores_gemma":[0.99909836,0.0002164499,0.00032139613,0.00013504262,0.00018171429,0.000047026366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007243473,0.00006606425,0.00016551142,0.0001043654,0.00007237116,0.00011052742,0.00039028045,0.000047654088,0.0000026437122],"category_scores_gemma":[0.0005127962,0.00004853909,0.00008752971,0.00011405225,0.000015290085,0.00037242332,0.00003116594,0.00007391178,0.0000074632894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001410551,0.00027012153,0.008380249,0.00019887232,0.00035569744,0.000084004714,0.0040268465,0.008238626,0.05349097,0.30309427,0.039281525,0.58243775],"study_design_scores_gemma":[0.0007527416,0.00033968742,0.02535824,0.0002054025,0.000020105346,0.0003756181,0.0000662777,0.95467263,0.006730563,0.0049640886,0.006383947,0.00013067051],"about_ca_topic_score_codex":0.0000034114794,"about_ca_topic_score_gemma":9.222826e-7,"teacher_disagreement_score":0.946434,"about_ca_system_score_codex":0.000021175149,"about_ca_system_score_gemma":0.000040980223,"threshold_uncertainty_score":0.19793667},"labels":[],"label_agreement":null},{"id":"W2073165288","doi":"10.1007/s10817-007-9092-z","title":"On Keys and Functional Dependencies as First-Class Citizens in Description Logics","year":2007,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Decidability; Negation; Dependency theory (database theory); Identification (biology); Scope (computer science); Class (philosophy); Functional dependency; Constraint (computer-aided design); Monotone polygon; Computer science; Conjunctive normal form; Mathematics; Theoretical computer science; Logical consequence; Simple (philosophy); Discrete mathematics; Programming language; Artificial intelligence; Epistemology; Data mining","score_opus":0.01880295743059998,"score_gpt":0.24981032957761376,"score_spread":0.23100737214701378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073165288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92728233,0.00034413813,0.06909461,0.0005094128,0.00059382763,0.000039161703,1.2020584e-7,0.00014439381,0.001992006],"genre_scores_gemma":[0.9861332,0.00006239579,0.013538237,0.00016455332,0.000056257795,3.529796e-7,2.240098e-7,0.000004447003,0.00004032801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99888253,0.000042610944,0.00035083547,0.00013943951,0.00035162823,0.00023294904],"domain_scores_gemma":[0.9990662,0.00037363853,0.00025352702,0.000108130414,0.00012356204,0.000074971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010525511,0.000104452825,0.00018150537,0.00030986796,0.00010910599,0.00013733534,0.00019881163,0.000096491116,0.000010551882],"category_scores_gemma":[0.0006131862,0.00008145263,0.000048175527,0.00026245695,0.000040462928,0.00041987342,0.000059623177,0.0002469801,0.000010119153],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013653092,0.0010998383,0.34351438,0.00024430046,0.00046218862,0.012452845,0.01405584,0.04454249,0.028122673,0.448601,0.013875907,0.09166323],"study_design_scores_gemma":[0.0010793973,0.00051894697,0.85451627,0.0005486595,0.000013445382,0.0027610979,0.0006822149,0.12718333,0.0024913216,0.009767387,0.00023740287,0.00020049205],"about_ca_topic_score_codex":0.000028046381,"about_ca_topic_score_gemma":0.00006241712,"teacher_disagreement_score":0.51100194,"about_ca_system_score_codex":0.000108552966,"about_ca_system_score_gemma":0.0000718104,"threshold_uncertainty_score":0.33215418},"labels":[],"label_agreement":null},{"id":"W2115178223","doi":"10.1007/s10817-008-9113-6","title":"Using Theorem Proving to Verify Expectation and Variance for Discrete Random Variables","year":2008,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"HOL; Variance (accounting); Random variable; Probabilistic logic; Computer science; Mathematics; Automated theorem proving; Variable (mathematics); Probabilistic analysis of algorithms; Theoretical computer science; Statistics","score_opus":0.035131381346365564,"score_gpt":0.32424610219894545,"score_spread":0.2891147208525799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115178223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1666564,0.00010424475,0.83243126,0.00009046312,0.00033014317,0.00018209383,6.6804927e-7,0.000104533334,0.000100212616],"genre_scores_gemma":[0.38902056,0.000010760853,0.61086094,0.000025850757,0.00006466359,0.0000037533105,2.2136753e-7,0.000007637327,0.000005632465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988554,0.00015728576,0.00040729067,0.0001647473,0.00022320895,0.00019207156],"domain_scores_gemma":[0.9987575,0.00024393036,0.0004922618,0.00016618834,0.00024670668,0.000093448616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00134819,0.00010730215,0.00022700249,0.00016413316,0.0002758785,0.0001164359,0.00030239506,0.00006462233,0.0000010818698],"category_scores_gemma":[0.0012674088,0.00008969048,0.00005240994,0.00031560851,0.00003107144,0.0010460337,0.000058093923,0.00012445568,3.9057858e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021395243,0.00021207206,0.0041788626,0.00038287163,0.00046501152,0.00020849405,0.05143698,0.1522971,0.5323291,0.20145689,0.0009895245,0.05390358],"study_design_scores_gemma":[0.0009933808,0.00015241766,0.0034953335,0.00027530853,0.000018169378,0.00084488833,0.000109982626,0.98183835,0.011355521,0.00066457194,0.0001248913,0.00012717438],"about_ca_topic_score_codex":0.0000053494123,"about_ca_topic_score_gemma":1.4848956e-7,"teacher_disagreement_score":0.82954127,"about_ca_system_score_codex":0.00007692173,"about_ca_system_score_gemma":0.00012009679,"threshold_uncertainty_score":0.36574715},"labels":[],"label_agreement":null},{"id":"W2136755926","doi":"10.1007/s10817-008-9105-6","title":"Performance Analysis and Functional Verification of the Stop-and-Wait Protocol in HOL","year":2008,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"HOL; Correctness; Computer science; Automated theorem proving; Protocol (science); Theoretical computer science; Proof assistant; Relation (database); Process (computing); Programming language; Distributed computing; Mathematics; Data mining; Mathematical proof","score_opus":0.022932527700165545,"score_gpt":0.28076397970697303,"score_spread":0.25783145200680746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136755926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96260065,0.000017383161,0.035728246,0.00007740724,0.00006876046,0.0013778238,2.6352689e-7,0.000026844702,0.00010263237],"genre_scores_gemma":[0.8818407,0.000014585622,0.11793769,0.000011696574,0.000014254837,0.00016720292,1.415406e-7,0.0000027512897,0.00001098741],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989914,0.00013369168,0.00039950703,0.000103937346,0.00028269677,0.00008879511],"domain_scores_gemma":[0.9989906,0.00004961291,0.00058510434,0.00018761662,0.00015449332,0.000032594206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009042248,0.00006533065,0.00016422056,0.00026703955,0.000105196734,0.000023444267,0.00021944249,0.0000454129,0.0000025431355],"category_scores_gemma":[0.0001773068,0.000044924298,0.000048969967,0.0009877627,0.000075598145,0.0005512501,0.000056847322,0.0001644371,3.259173e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017035421,0.0001762943,0.9118321,0.00011068854,0.00025266,0.000010528014,0.004423068,0.023469876,0.024731172,0.004053934,0.000104602004,0.030664729],"study_design_scores_gemma":[0.00017700973,0.000037744867,0.57989496,0.000046295485,0.000013704226,0.00010809142,0.000013819048,0.41491428,0.0047244993,0.0000116640895,0.000028775114,0.000029162893],"about_ca_topic_score_codex":0.000008010478,"about_ca_topic_score_gemma":5.7499125e-7,"teacher_disagreement_score":0.3914444,"about_ca_system_score_codex":0.00004225402,"about_ca_system_score_gemma":0.00008555025,"threshold_uncertainty_score":0.18319598},"labels":[],"label_agreement":null},{"id":"W2140849218","doi":"10.1007/s10817-010-9194-x","title":"Hybrid","year":2010,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Soundness; HOL; Syntax; Type theory; Abstract syntax; Object (grammar); Semantics (computer science); Theoretical computer science; Type (biology); Artificial intelligence","score_opus":0.01017665470751357,"score_gpt":0.25082584540069075,"score_spread":0.24064919069317717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140849218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.575277,0.0005126318,0.401433,0.000743735,0.008619469,0.00014396347,2.9918357e-7,0.0012516745,0.012018245],"genre_scores_gemma":[0.9723277,0.0000054134894,0.02720773,0.000050881732,0.00029449674,6.105858e-7,2.140813e-7,0.0000074501404,0.00010546505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897355,0.000046750578,0.00034657703,0.00011427317,0.00030016727,0.0002186597],"domain_scores_gemma":[0.9989052,0.000056146953,0.00044847716,0.00024470975,0.00021384445,0.00013162055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080942817,0.00009404924,0.00019173604,0.00012726274,0.00009872808,0.00024314698,0.00068118586,0.000054726355,0.000015144448],"category_scores_gemma":[0.00020225966,0.00006762028,0.0001044365,0.00017095314,0.000026838361,0.00047834156,0.000073930496,0.0003749864,0.00004237694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029287794,0.0003668357,0.010053312,0.00007626668,0.00033245143,0.002738287,0.0030139794,0.00033333505,0.07419311,0.6809053,0.0306152,0.19734263],"study_design_scores_gemma":[0.0031999922,0.0011704613,0.025108958,0.00015912669,0.00008980238,0.036286972,0.00019884788,0.63006234,0.058749225,0.0316909,0.21212226,0.0011611293],"about_ca_topic_score_codex":0.000012912059,"about_ca_topic_score_gemma":0.0000018845683,"teacher_disagreement_score":0.6492144,"about_ca_system_score_codex":0.000017962391,"about_ca_system_score_gemma":0.00011255515,"threshold_uncertainty_score":0.2757475},"labels":[],"label_agreement":null},{"id":"W2142949137","doi":"10.1007/s10817-005-0084-6","title":"Tool-Assisted Specification and Verification of Typed Low-Level Languages","year":2006,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bytecode; Correctness; Computer science; Programming language; Java Card; Java bytecode; Java; Automated theorem proving; Mathematical proof; Java applet; Java annotation","score_opus":0.016383695167651317,"score_gpt":0.2659575518394582,"score_spread":0.24957385667180687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142949137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.867323,0.0005278231,0.13080421,0.00029509512,0.00020724811,0.00005432449,0.000001546573,0.00013665138,0.00065010856],"genre_scores_gemma":[0.91401654,0.000021852478,0.085823916,0.0000142459185,0.00009369348,5.121985e-7,0.0000024448852,0.000005163167,0.000021651877],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99897814,0.000075369506,0.0004915003,0.00012349171,0.00022925925,0.000102266196],"domain_scores_gemma":[0.9986154,0.00011476016,0.00074581394,0.00020157851,0.00029234527,0.000030112093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005611507,0.00007587957,0.00015883462,0.00015588514,0.000078513505,0.00008739866,0.0002788759,0.000060305112,0.000004518679],"category_scores_gemma":[0.000132959,0.00006957627,0.00004481495,0.0003408198,0.00003557441,0.00025635277,0.000033293105,0.00011040396,0.0000027907843],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012465572,0.00079356815,0.013631078,0.00033097077,0.00019908628,0.000073895455,0.0049103657,0.0057344073,0.53650993,0.2331229,0.0057119112,0.19885725],"study_design_scores_gemma":[0.0006287973,0.00007730115,0.6315052,0.0003340144,0.000021365131,0.00030729698,0.0002028127,0.32935688,0.0362994,0.0006919226,0.00040539994,0.00016965334],"about_ca_topic_score_codex":0.000021672575,"about_ca_topic_score_gemma":9.560061e-7,"teacher_disagreement_score":0.6178741,"about_ca_system_score_codex":0.000037978687,"about_ca_system_score_gemma":0.000065379616,"threshold_uncertainty_score":0.2837238},"labels":[],"label_agreement":null},{"id":"W2904404870","doi":"10.1007/s10817-019-09527-x","title":"Formalization of Metatheory of the Quipper Quantum Programming Language in a Linear Logic","year":2019,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Soundness; Programming language; Metatheory; Dependent type; Computer science; Linear logic; Syntax; Lambda calculus; Type theory; Theoretical computer science; Typed lambda calculus; Type (biology); Artificial intelligence","score_opus":0.010669031447320055,"score_gpt":0.26377637250171027,"score_spread":0.2531073410543902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904404870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93334943,0.001088708,0.063984536,0.00006496391,0.00074788154,0.00026480402,2.6274012e-7,0.00007870327,0.00042068854],"genre_scores_gemma":[0.99200296,0.00000862891,0.007899047,0.000016578,0.000026204383,0.000001029202,3.694721e-7,0.00000705437,0.000038150778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986111,0.00018524888,0.00059171754,0.00010020689,0.00033163754,0.0001800823],"domain_scores_gemma":[0.9984558,0.00007791663,0.0010030378,0.00024315911,0.00018837333,0.00003170981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014550753,0.00009114637,0.00030173763,0.00016595941,0.000028423694,0.000032736047,0.00053491205,0.0000703195,0.00000499195],"category_scores_gemma":[0.0001971679,0.00005349122,0.00014002081,0.00056703534,0.000033895154,0.0003515038,0.00009479815,0.00015922834,0.0000027310339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013626817,0.0008016652,0.15356559,0.001062396,0.00040456746,0.00013633727,0.054100275,0.016151333,0.05360391,0.67747015,0.00013225923,0.042435277],"study_design_scores_gemma":[0.002406315,0.001076097,0.0285699,0.00094092614,0.0000764651,0.000640467,0.004730608,0.93088484,0.025198342,0.004149821,0.0009552059,0.00037103676],"about_ca_topic_score_codex":0.000053794192,"about_ca_topic_score_gemma":0.0000059195563,"teacher_disagreement_score":0.91473347,"about_ca_system_score_codex":0.000031664484,"about_ca_system_score_gemma":0.000100784055,"threshold_uncertainty_score":0.21813087},"labels":[],"label_agreement":null},{"id":"W2905126952","doi":"10.1007/s10817-008-9104-7","title":"On the Scalability of Description Logic Instance Retrieval","year":2008,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Description logic; Computer science; Scalability; Ontology; Semantic Web; Web Ontology Language; Ontology language; Information retrieval; Knowledge representation and reasoning; Implementation; Representation (politics); OWL-S; Theoretical computer science; Programming language; Semantic Web Stack; Database; Artificial intelligence","score_opus":0.03488639177182947,"score_gpt":0.2576629082741037,"score_spread":0.22277651650227423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905126952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688576,0.00024679932,0.02861795,0.0009178774,0.00037962408,0.000049596394,1.9770837e-7,0.000114757815,0.00081561506],"genre_scores_gemma":[0.98506695,0.000057544232,0.014709912,0.00011939914,0.000028189963,2.0257684e-7,6.307266e-8,0.0000030135452,0.000014713468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99878716,0.00015499568,0.00040426166,0.00010809691,0.00039674214,0.00014872737],"domain_scores_gemma":[0.9985204,0.00038003764,0.00052135036,0.00027718718,0.0002622101,0.000038845727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009645483,0.00008400542,0.00021525708,0.00008438407,0.00013486948,0.000034633933,0.00059146853,0.000058576177,0.000008043018],"category_scores_gemma":[0.001490852,0.00004760207,0.00009797153,0.0003956781,0.00012301868,0.00033981673,0.000055581837,0.00021935238,0.0000050577264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016207776,0.0019629768,0.11559776,0.00023672558,0.00064562407,0.0019811408,0.019458745,0.014362977,0.12650868,0.6696681,0.023818357,0.02413815],"study_design_scores_gemma":[0.0011191005,0.0011763048,0.668391,0.0008272301,0.000029768082,0.0023324841,0.00039531462,0.2683909,0.038671512,0.018220587,0.00016807979,0.00027771745],"about_ca_topic_score_codex":0.00000646164,"about_ca_topic_score_gemma":7.9783297e-7,"teacher_disagreement_score":0.6514475,"about_ca_system_score_codex":0.00005999289,"about_ca_system_score_gemma":0.000118973556,"threshold_uncertainty_score":0.19411561},"labels":[],"label_agreement":null},{"id":"W2943910961","doi":"10.1007/s10817-019-09524-0","title":"Automated Reasoning with Power Maps","year":2019,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Advanced Topics in Algebra","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Endomorphism; Mathematical proof; Mathematics; Abelian group; Automated theorem proving; Gas meter prover; Discrete mathematics; Algebra over a field; Torsion (gastropod); Pure mathematics; Algorithm","score_opus":0.012645934950046225,"score_gpt":0.2963992426726911,"score_spread":0.28375330772264484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943910961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98380667,0.00024784383,0.001993206,0.00019789326,0.0007124127,0.00026779645,0.0000045609154,0.0019538335,0.01081581],"genre_scores_gemma":[0.78404796,0.000014924186,0.21490568,0.00007584723,0.0001192683,0.0000026206653,0.00000278142,0.00011043485,0.0007205066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972501,0.0001415421,0.0009234719,0.0002850232,0.00083734497,0.000562508],"domain_scores_gemma":[0.9967031,0.0004979962,0.0015199144,0.0005263939,0.0005367898,0.00021580733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091945287,0.00036097737,0.0007564495,0.00032127192,0.00013558556,0.00011943588,0.00047133325,0.00021319305,0.00027126196],"category_scores_gemma":[0.0010349706,0.00027012438,0.0001794796,0.0005465937,0.00007266182,0.00062565034,0.00009591887,0.00077363977,0.00009446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025529573,0.0020258068,0.07507745,0.0015963938,0.005659749,0.0069042956,0.015617149,0.012212318,0.045189597,0.74011666,0.0887553,0.0042923284],"study_design_scores_gemma":[0.04256415,0.010690488,0.09055231,0.05166524,0.0026486393,0.05900485,0.0141093815,0.36282763,0.06236868,0.25399184,0.040252432,0.009324358],"about_ca_topic_score_codex":0.0000037280145,"about_ca_topic_score_gemma":0.0000018153712,"teacher_disagreement_score":0.4861248,"about_ca_system_score_codex":0.00025047487,"about_ca_system_score_gemma":0.00022286596,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W4231890083","doi":"10.1007/s10817-009-9141-x","title":"Preface","year":2009,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Historical Art and Culture Studies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Programming language","score_opus":0.012866011335541131,"score_gpt":0.23485084603943085,"score_spread":0.22198483470388972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231890083","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22587366,0.004942782,0.000055513956,0.0038440544,0.002218458,0.00008790884,0.0000024552285,0.0005934381,0.76238173],"genre_scores_gemma":[0.99471724,0.000031443593,0.00039685398,0.00019216165,0.00076396123,1.8855334e-7,3.5259856e-7,0.000004552432,0.0038932427],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994135,0.000017506649,0.00023445729,0.00004711597,0.0001658743,0.00012155347],"domain_scores_gemma":[0.9995105,0.000016131291,0.0001903415,0.000044259883,0.00018699776,0.000051744468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012035948,0.000074369644,0.0001720009,0.000047738104,0.00025250355,0.000062556916,0.00008934939,0.000020523637,0.00025405368],"category_scores_gemma":[0.0000674901,0.000047314978,0.00009090732,0.000031606694,0.000039526487,0.00018842584,0.000006454775,0.00013346355,0.000035436693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100551915,0.00031294426,0.00014712848,0.00002127741,0.00026755786,0.00018783844,0.1709723,0.00012635645,0.0025354868,0.2063679,0.59779215,0.021168526],"study_design_scores_gemma":[0.0002735645,0.00035546566,0.00092168985,0.00013748555,0.000045561505,0.000060813934,0.0023629414,0.0003282178,0.00014986977,0.0006775824,0.99456954,0.00011727996],"about_ca_topic_score_codex":0.0000033419612,"about_ca_topic_score_gemma":0.000007646972,"teacher_disagreement_score":0.7688436,"about_ca_system_score_codex":0.000036932932,"about_ca_system_score_gemma":0.000017405699,"threshold_uncertainty_score":0.27817094},"labels":[],"label_agreement":null},{"id":"W4399335583","doi":"10.1007/s10817-024-09696-4","title":"Formalized Functional Analysis with Semilinear Maps","year":2024,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Mathematics; Calculus (dental); Programming language; Medicine","score_opus":0.011845415772537267,"score_gpt":0.24757013554682306,"score_spread":0.2357247197742858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399335583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020853668,0.0020011314,0.97308064,0.00029042343,0.00091736036,0.00006798519,7.724239e-7,0.000774232,0.0020137958],"genre_scores_gemma":[0.97873986,0.00001954142,0.020677373,0.00004053808,0.00019948007,0.000001789773,0.000003893169,0.000009894985,0.00030765598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986498,0.00007074979,0.00039516555,0.00017343501,0.0004881939,0.00022270005],"domain_scores_gemma":[0.99914056,0.00008434685,0.00024821027,0.00018240603,0.00023272751,0.000111728354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000849547,0.00012519395,0.00029029293,0.00046480354,0.00010382675,0.00047052983,0.0003129758,0.00006494668,0.000026904054],"category_scores_gemma":[0.00003935278,0.00007732301,0.00022803871,0.0015766829,0.00002467498,0.0006961384,0.000047826128,0.00022931356,0.000025309257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004959608,0.0005828488,0.038516965,0.0007555885,0.027532859,0.00996029,0.012244246,0.10427427,0.004324982,0.6443504,0.064000905,0.09296067],"study_design_scores_gemma":[0.00055410934,0.00029539422,0.003396117,0.00008367983,0.00044554716,0.0021575943,0.00011488353,0.9704077,0.00040006242,0.0007913275,0.021150367,0.0002031786],"about_ca_topic_score_codex":0.000017324332,"about_ca_topic_score_gemma":0.0000046843024,"teacher_disagreement_score":0.95788616,"about_ca_system_score_codex":0.00006569507,"about_ca_system_score_gemma":0.00019187287,"threshold_uncertainty_score":0.453733},"labels":[],"label_agreement":null}]}