stealthhumanizer-corpus-style-model / corpus-style-model.json
Lynote's picture
StealthHumanizer corpus style model (10k Q1 OA papers, Lynote)
5ddcb14 verified
Raw
History Blame Contribute Delete
13.9 kB
{
"generatedAt": "2026-04-10T19:08:25.019Z",
"paperCount": 10000,
"global": {
"avgSentenceLength": 23,
"avgBurstiness": 0.426,
"avgVocabularyDiversity": 0.694,
"avgContractionFrequency": 0.91,
"avgPassiveVoiceRatio": 18.1,
"avgFirstPersonPronouns": 11.38,
"avgHedgingFrequency": 1.84,
"avgWordsPerParagraph": 192.3
},
"byDomain": {
"Physical Sciences": {
"paperCount": 1342,
"sentenceLengthMean": 23.5,
"burstinessMean": 0.394,
"vocabularyDiversityMean": 0.695,
"passiveVoiceMean": 21.8
},
"Medicine": {
"paperCount": 2868,
"sentenceLengthMean": 23.3,
"burstinessMean": 0.435,
"vocabularyDiversityMean": 0.69,
"passiveVoiceMean": 18.8
},
"Multidisciplinary": {
"paperCount": 1912,
"sentenceLengthMean": 22.4,
"burstinessMean": 0.45,
"vocabularyDiversityMean": 0.699,
"passiveVoiceMean": 17.2
},
"Computer Science": {
"paperCount": 1579,
"sentenceLengthMean": 22.6,
"burstinessMean": 0.414,
"vocabularyDiversityMean": 0.699,
"passiveVoiceMean": 17.4
},
"Social Sciences": {
"paperCount": 427,
"sentenceLengthMean": 24.8,
"burstinessMean": 0.419,
"vocabularyDiversityMean": 0.675,
"passiveVoiceMean": 17.7
},
"Education": {
"paperCount": 125,
"sentenceLengthMean": 23.7,
"burstinessMean": 0.38,
"vocabularyDiversityMean": 0.694,
"passiveVoiceMean": 17.3
},
"Mathematics": {
"paperCount": 96,
"sentenceLengthMean": 21.2,
"burstinessMean": 0.473,
"vocabularyDiversityMean": 0.679,
"passiveVoiceMean": 14.9
},
"Life Sciences": {
"paperCount": 1072,
"sentenceLengthMean": 22.5,
"burstinessMean": 0.422,
"vocabularyDiversityMean": 0.709,
"passiveVoiceMean": 14.7
},
"Engineering": {
"paperCount": 136,
"sentenceLengthMean": 24.7,
"burstinessMean": 0.4,
"vocabularyDiversityMean": 0.694,
"passiveVoiceMean": 21.9
},
"Economics & Business": {
"paperCount": 262,
"sentenceLengthMean": 24.3,
"burstinessMean": 0.421,
"vocabularyDiversityMean": 0.68,
"passiveVoiceMean": 17.1
},
"Environmental Science": {
"paperCount": 181,
"sentenceLengthMean": 22.6,
"burstinessMean": 0.452,
"vocabularyDiversityMean": 0.666,
"passiveVoiceMean": 19.6
}
},
"sentenceLengthDistribution": {
"mean": 20.5,
"median": 20,
"stddev": 9.4,
"min": 0,
"max": 2576,
"p10": 4,
"p25": 12,
"p75": 27,
"p90": 35
},
"burstinessProfile": {
"mean": 0.426,
"stddev": 0.244
},
"vocabularyDiversityRange": {
"min": 0.038,
"max": 1,
"mean": 0.694
},
"transitionWordFrequency": {
"however": 1.19,
"yet": 0.27,
"thus": 0.42,
"furthermore": 0.35,
"still": 0.35,
"therefore": 0.36,
"consequently": 0.08,
"otherwise": 0.03,
"instead": 0.09,
"moreover": 0.29,
"rather": 0.13,
"additionally": 0.15,
"subsequently": 0.05,
"nevertheless": 0.06,
"meanwhile": 0.04,
"hence": 0.09,
"accordingly": 0.04,
"similarly": 0.03,
"likewise": 0.01,
"conversely": 0.01
},
"aiPhraseFrequency": {
"state-of-the-art": 0.314,
"holistic": 0.049,
"robust": 0.309,
"it is crucial": 0.015,
"streamline": 0.017,
"has the potential to": 0.043,
"unprecedented": 0.118,
"synergy": 0.027,
"transformative": 0.027,
"seamless": 0.017,
"it is essential": 0.013,
"plays a crucial role": 0.009,
"plays a pivotal role": 0.01,
"paradigm shift": 0.011,
"underscore": 0.026,
"sheds light on": 0.015,
"in conclusion": 0.03,
"groundbreaking": 0.003,
"multifaceted": 0.018,
"a myriad of": 0.014,
"it is evident that": 0.006,
"it is clear that": 0.004,
"delve into": 0.006,
"cutting-edge": 0.015,
"it is worth mentioning": 0.001,
"it is important to note": 0,
"in the current landscape": 0
},
"contractionFrequency": {
"mean": 0.91,
"stddev": 3.4
},
"passiveVoiceRatio": {
"mean": 18.1,
"stddev": 19.4
},
"sentenceStarters": {
"the": 11.71,
"we": 5.6,
"in": 5.47,
"this": 4.6,
"however": 1.91,
"here": 1.58,
"a": 1.47,
"these": 1.45,
"it": 1.4,
"our": 1.12,
"to": 1.1,
"for": 0.86,
"finally": 0.82,
"as": 0.79,
"abstract": 0.7,
"furthermore": 0.69,
"g": 0.67,
"although": 0.63,
"moreover": 0.58,
"-": 0.56,
"there": 0.55,
"e": 0.48,
"therefore": 0.47,
"while": 0.44,
"with": 0.44,
"despite": 0.38,
"by": 0.35,
"thus": 0.33,
"an": 0.33,
"since": 0.32,
"recent": 0.31,
"among": 0.31,
"using": 0.31,
"based": 0.3,
"they": 0.28,
"additionally": 0.27,
"on": 0.27,
"all": 0.26,
"at": 0.25,
"org": 0.25,
"s": 0.25,
"w": 0.24,
"most": 0.24,
"results": 0.23,
"further": 0.23,
"overall": 0.23,
"many": 0.22,
"more": 0.21,
"herein": 0.21,
"first": 0.2,
"when": 0.18,
"due": 0.18,
"several": 0.18,
"after": 0.18,
"over": 0.17,
"given": 0.17,
"recently": 0.17,
"orgmathmathml": 0.17,
"during": 0.16,
"one": 0.16,
"some": 0.16,
"such": 0.16,
"then": 0.15,
"gov": 0.15,
"specifically": 0.15,
"funded": 0.14,
"because": 0.14,
"compared": 0.14,
"of": 0.14,
"from": 0.13,
"data": 0.13,
"hence": 0.13,
"both": 0.12,
"covid-": 0.12,
"through": 0.12,
"understanding": 0.12,
"patients": 0.12,
"nevertheless": 0.12,
"currently": 0.12,
"research": 0.11,
"second": 0.11,
"sub": 0.11,
"methods": 0.11,
"besides": 0.11,
"also": 0.11,
"et": 0.1,
"i": 0.1,
"importantly": 0.1,
"various": 0.1,
"consequently": 0.1,
"if": 0.09,
"future": 0.09,
"new": 0.09,
"yet": 0.09,
"other": 0.09,
"studies": 0.09,
"notably": 0.09,
"m": 0.09,
"deep": 0.08,
"their": 0.08
},
"humanWritingExamples": [
"Radiation resistant camera system was constructed for monitoring deuterium plasma discharges in the Large Helical Device (LHD).",
"Recommendations are made on the responsible use of Gaia EDR3 results.",
"1% faster ML gradient aggregation, all without specialized NICs or dedicated cores.",
"In silico prediction of resistomes and prevalence statistics of ARGs has been expanded to 377 pathogens, 21,079 chromosomes, 2,662 genomic islands, 41,828 plasmids and 155,606 whole-genome shotgun assemblies, resulting in collation of 322,710 unique ARG allele sequences.",
"Elevated or decreased NRF2 activity by pharmacological and genetic manipulations of NRF2 activation is associated with many metabolism- or inflammation-related diseases.",
"The current global plastics economy is highly linear, with the exceptional performance and low carbon footprint of polymeric materials at odds with dramatic increases in plastic waste.",
"Our experimental study compares different self-attention schemes and suggests that \"divided attention,\" where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered.",
"Our code and pre-trained models are released at https: //github.",
"Important questions regarding salt tolerance that need to be addressed in the future are discussed.",
"Mesenchymal tumours, haematolymphoid tumours and genetic tumour syndromes are covered in dedicated chapters in alignment with the approach being taken throughout this fifth edition of the series.",
"Using diverse assays for antibodies recognizing SARS-CoV-2 proteins, we detected preexisting humoral immunity.",
"They consist of a checklist of information to include in publications describing in vivo experiments to enable others to scrutinise the work adequately, evaluate its methodological rigour, and reproduce the methods and results.",
"Further subdivision by reaction class─either sp<sup>2</sup> or sp<sup>3</sup> C-H functionalization─lends perspective and tactical strategies for use of these methods in synthetic applications.",
"Current treatment options are limited to surgery, adjuvant chemotherapy and radiotherapy; however, a proportion of patients have missed the surgical window at the time of diagnosis.",
"Thus, our method has the significant potential to provide a rapid, sensitive, one-pot point-of-care assay for SARS-CoV-2.",
"003 to 150 ± 20 MJ m<sup>-3</sup> , elongation from 300 ± 100% to 2100 ± 300%, and modulus from 24 ± 2 to 2500 ± 140 kPa.",
"This paper reviews the evidence on the range of pathways linking the built environment to subjective well-being.",
"Can trust in AI be optimized to improve decision-making processes?",
"SIGNIFICANCE: ICTs induce durable antitumor responses for subsets of patients with cancer.",
"newspapers and televised network news from March to May 2020.",
"Nanoparticles (nanoparticles) have received much attention in biological application because of their unique physicochemical properties.",
"In Study 2, using data from a representative sample of the U.",
"Plant secondary metabolites (PSMs) play many roles including defense against pathogens, pests, and herbivores; response to environmental stresses, and mediating organismal interactions.",
"At advanced stages, guidelines recommend both methods.",
"These antibodies are also detected in 18% of the 1,124 deceased patients (aged 20 days-99 years; mean: 70 years).",
"In a nMOS graphene field effect transistor, the resistance between two electrodes can be transferred or controlled by a third electrode.",
"Transfer learning was used to learn biomarker features on larger datasets, previously successfully tested in our Lab on Alzheimer's, which significantly improves the COVID-19 discrimination accuracy of our architecture.",
"Based on secondary data, results also reveal the gap in implementing and customizing these technologies quickly in educational institutions.",
"Qualitative results on in-the-wild data demonstrate DECA's robustness and its ability to disentangle identity- and expression-dependent details enabling animation of reconstructed faces.",
"We show that the effect of temperature on labor is an important part of the explanation.",
"Once in water, chromium mainly occurs in two oxidation states Cr (III) and Cr (VI) and related ion forms depending on pH values, redox potential, and presence of natural reducing agents.",
"Mitochondria are major regulators of the SASP; however, the underlying mechanisms have not been elucidated<sup>2</sup>.",
"In the end, several open research problems specific to recognition and localization applications for fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.",
"It has become trivial to point out that algorithmic systems increasingly pervade the social sphere.",
"In the ongoing phase 2 MagnetisMM-3 trial, patients with relapsed or refractory multiple myeloma received subcutaneous elranatamab once weekly after two step-up priming doses.",
"Recent research in photonic matrix multiplication has flourished and may provide opportunities to develop applications that are unachievable at present by conventional electronic processors.",
"Our catalogue confirms the relative lack of old stellar clusters in the inner disc (with a few notable exceptions).",
"Thus, excessive or prolonged IFN production aggravates viral infection by impairing lung epithelial regeneration.",
"), University of California, San Diego, La Jolla, CA.",
"We show that an AbTAC can induce the lysosomal degradation of programmed death-ligand 1 by recruitment of the membrane-bound E3 ligase RNF43.",
"The recommendation rationales, informed by rigorous data evaluation, discussion by panelists, and input from patients, provide deeper insight into each recommendation.",
"A bibliometric analysis was deployed to map the focal field in terms of dominant topics and their evolution over time.",
"Here we sequenced 3,579 genomes from single cell-derived colonies of haematopoietic cells across 10 human subjects from 0 to 81 years of age.",
"However, interaction of miRNAs with other regions, including the 5' UTR, coding sequence, and gene promoters, have also been reported.",
"6 million) had high-impact chronic pain, with higher prevalences of both chronic pain and high-impact chronic pain reported among women, older adults, previously but not currently employed adults, adults living in poverty, adults with public health insurance, and rural residents.",
"We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration.",
"Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise.",
"In addition, high nighttime BP on ambulatory BP monitoring is associated with increased cardiovascular disease risk.",
"We show that while the overall normalization of [Eu/Fe] is susceptible to resolution and post-processing assumptions, the relatively large spread of [Eu/Fe] at low [Fe/H] when compared to that at high [Fe/H] is quite robust.",
"After polyploidization, Gossypium hirsutum L."
],
"punctuation": {
"emDashPer1000": {
"mean": 0.5,
"stddev": 2.59
},
"semicolonPer1000": {
"mean": 2.29,
"stddev": 13.58
},
"exclamationPer1000": {
"mean": 0.01,
"stddev": 0.3
}
}
}