Deploying to gh-pages from @ 8959e0a 🚀

pkgdown.yml

@@ -2,7 +2,7 @@ pandoc: 2.19.2
 pkgdown: 2.0.7
 pkgdown_sha: ~
 articles: {}
-last_built: 2023-10-26T13:59Z
+last_built: 2023-10-26T14:05Z
 urls:
  reference: https://simonpcouch.github.io/detectors/reference
  article: https://simonpcouch.github.io/detectors/articles

search.json

@@ -1 +1 @@
-[{"path":"https://simonpcouch.github.io/detectors/LICENSE.html","id":null,"dir":"","previous_headings":"","what":"MIT License","title":"MIT License","text":"Copyright (c) 2023 detectors authors Permission hereby granted, free charge, person obtaining copy software associated documentation files (“Software”), deal Software without restriction, including without limitation rights use, copy, modify, merge, publish, distribute, sublicense, /sell copies Software, permit persons Software furnished , subject following conditions: copyright notice permission notice shall included copies substantial portions Software. SOFTWARE PROVIDED “”, WITHOUT WARRANTY KIND, EXPRESS IMPLIED, INCLUDING LIMITED WARRANTIES MERCHANTABILITY, FITNESS PARTICULAR PURPOSE NONINFRINGEMENT. EVENT SHALL AUTHORS COPYRIGHT HOLDERS LIABLE CLAIM, DAMAGES LIABILITY, WHETHER ACTION CONTRACT, TORT OTHERWISE, ARISING , CONNECTION SOFTWARE USE DEALINGS SOFTWARE.","code":""},{"path":"https://simonpcouch.github.io/detectors/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Simon Couch. Maintainer, author.","code":""},{"path":"https://simonpcouch.github.io/detectors/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Couch S (2023). detectors: Prediction Data GPT Detectors. R package version 0.0.1, https://simonpcouch.github.io/detectors/.","code":"@Manual{, title = {detectors: Prediction Data from GPT Detectors}, author = {Simon Couch}, year = {2023}, note = {R package version 0.0.1}, url = {https://simonpcouch.github.io/detectors/}, }"},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"detectors","dir":"","previous_headings":"","what":"Prediction Data from GPT Detectors","title":"Prediction Data from GPT Detectors","text":"detectors R data package containing predictions various GPT detectors. data based paper: GPT Detectors Biased Non-Native English Writers. Weixin Liang, Mert Yuksekgonul, Yining Mao, Eric Wu, James Zou. CellPress Patterns. study authors carried series experiments passing number essays different GPT detection models. Juxtaposing detector predictions papers written native non-native English writers, authors argue GPT detectors disproportionately classify real writing non-native English writers AI-generated.","code":""},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"Prediction Data from GPT Detectors","text":"can install data package following code:","code":"require(pak) pak(\"simonpcouch/detectors\")"},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"example","dir":"","previous_headings":"","what":"Example","title":"Prediction Data from GPT Detectors","text":"Taking look data: example plot demonstrates distributions predicted probabilities text sample written AI depending GPT detector model lived experience writing English author: “ggplot side--side density plot showing distributions predicted probabilities text sample written AI depending GPT detector model lived experience writing English author. shown models classify samples written native English writers well, variably poorly non-native English writers.”","code":"library(ggplot2) library(detectors) detectors ## # A tibble: 6,185 × 9 ## kind .pred_AI .pred_class detector native name model document_id prompt ## <fct> <dbl> <fct> <chr> <chr> <chr> <chr> <dbl> <chr> ## 1 Human 1.00 AI Sapling No Real… Human 497 <NA> ## 2 Human 0.828 AI Crossplag No Real… Human 278 <NA> ## 3 Human 0.000214 Human Crossplag Yes Real… Human 294 <NA> ## 4 AI 0 Human ZeroGPT <NA> Fake… GPT3 671 Plain ## 5 AI 0.00178 Human Originality… <NA> Fake… GPT4 717 Eleva… ## 6 Human 0.000178 Human HFOpenAI Yes Real… Human 855 <NA> ## 7 AI 0.992 AI HFOpenAI <NA> Fake… GPT3 533 Plain ## 8 AI 0.0226 Human Crossplag <NA> Fake… GPT4 484 Eleva… ## 9 Human 0 Human ZeroGPT Yes Real… Human 781 <NA> ## 10 Human 1.00 AI Sapling No Real… Human 460 <NA> ## # ℹ 6,175 more rows detectors_plot <- detectors[!is.na(detectors$native), ] %>% ggplot() + aes(x = detector, y = .pred_AI, fill = native) + geom_violin(bw = .05) + labs( x = \"GPT Detector Tool\", y = \"Predicted Probability That\\nSample Was Written by AI\", fill = \"Native\\nEnglish\\nWriter\" ) + theme_minimal() + scale_fill_brewer(type = \"qual\") + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) detectors_plot"},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":null,"dir":"Reference","previous_headings":"","what":"Predictions from GPT Detectors — detectors","title":"Predictions from GPT Detectors — detectors","text":"Data derived paper GPT detectors biased non-native English writers. study authors carried series experiments passing number essays different GPT detection models. Juxtaposing detector predictions papers written native non-native English writers, authors argue GPT detectors disproportionately classify real writing non-native English writers AI-generated.","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Predictions from GPT Detectors — detectors","text":"","code":"detectors"},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Predictions from GPT Detectors — detectors","text":"data frame 6,185 rows 9 columns: kind Whether essay written \"Human\" \"AI\". .pred_AI class probability GPT detector inputted text written AI. .pred_class uncalibrated class prediction, encoded if_else(.pred_AI > .5, \"AI\", \"Human\") detector name detector used generate predictions. native essays written humans, whether essay written native English writer . categorizations coarse; values \"Yes\" may actually written people write English natively. NA indicates text written human. name label experiment predictions generated . model essays written AI, name model generated essay. document_id unique identifier supplied essay. essays supplied multiple detectors. Note essays AI-revised derivatives others. prompt essays written AI, descriptor form \"prompt engineering\" passed model. information data, see source paper.","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"source","dir":"Reference","previous_headings":"","what":"Source","title":"Predictions from GPT Detectors — detectors","text":"https://doi.org/10.1016/j.patter.2023.100779","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Predictions from GPT Detectors — detectors","text":"","code":"detectors #> # A tibble: 6,185 × 9 #> kind .pred_AI .pred_class detector native name model document_id prompt #> <fct> <dbl> <fct> <chr> <chr> <chr> <chr> <dbl> <chr> #> 1 Human 1.00 AI Sapling No Real… Human 497 NA #> 2 Human 0.828 AI Crossplag No Real… Human 278 NA #> 3 Human 0.000214 Human Crossplag Yes Real… Human 294 NA #> 4 AI 0 Human ZeroGPT NA Fake… GPT3 671 Plain #> 5 AI 0.00178 Human Originality… NA Fake… GPT4 717 Eleva… #> 6 Human 0.000178 Human HFOpenAI Yes Real… Human 855 NA #> 7 AI 0.992 AI HFOpenAI NA Fake… GPT3 533 Plain #> 8 AI 0.0226 Human Crossplag NA Fake… GPT4 484 Eleva… #> 9 Human 0 Human ZeroGPT Yes Real… Human 781 NA #> 10 Human 1.00 AI Sapling No Real… Human 460 NA #> # ℹ 6,175 more rows"}]
+[{"path":"https://simonpcouch.github.io/detectors/LICENSE.html","id":null,"dir":"","previous_headings":"","what":"MIT License","title":"MIT License","text":"Copyright (c) 2023 detectors authors Permission hereby granted, free charge, person obtaining copy software associated documentation files (“Software”), deal Software without restriction, including without limitation rights use, copy, modify, merge, publish, distribute, sublicense, /sell copies Software, permit persons Software furnished , subject following conditions: copyright notice permission notice shall included copies substantial portions Software. SOFTWARE PROVIDED “”, WITHOUT WARRANTY KIND, EXPRESS IMPLIED, INCLUDING LIMITED WARRANTIES MERCHANTABILITY, FITNESS PARTICULAR PURPOSE NONINFRINGEMENT. EVENT SHALL AUTHORS COPYRIGHT HOLDERS LIABLE CLAIM, DAMAGES LIABILITY, WHETHER ACTION CONTRACT, TORT OTHERWISE, ARISING , CONNECTION SOFTWARE USE DEALINGS SOFTWARE.","code":""},{"path":"https://simonpcouch.github.io/detectors/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Simon Couch. Maintainer, author.","code":""},{"path":"https://simonpcouch.github.io/detectors/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Couch S (2023). detectors: Prediction Data GPT Detectors. R package version 0.0.1, https://simonpcouch.github.io/detectors/.","code":"@Manual{, title = {detectors: Prediction Data from GPT Detectors}, author = {Simon Couch}, year = {2023}, note = {R package version 0.0.1}, url = {https://simonpcouch.github.io/detectors/}, }"},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"detectors","dir":"","previous_headings":"","what":"Prediction Data from GPT Detectors","title":"Prediction Data from GPT Detectors","text":"detectors R data package containing predictions various GPT detectors. data based paper: GPT Detectors Biased Non-Native English Writers. Weixin Liang, Mert Yuksekgonul, Yining Mao, Eric Wu, James Zou. CellPress Patterns. study authors carried series experiments passing number essays different GPT detection models. Juxtaposing detector predictions papers written native non-native English writers, authors argue GPT detectors disproportionately classify real writing non-native English writers AI-generated.","code":""},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"Prediction Data from GPT Detectors","text":"can install data package following code:","code":"require(pak) pak(\"simonpcouch/detectors\")"},{"path":"https://simonpcouch.github.io/detectors/index.html","id":"example","dir":"","previous_headings":"","what":"Example","title":"Prediction Data from GPT Detectors","text":"Taking look data: example plot demonstrates distributions predicted probabilities text sample written AI depending GPT detector model lived experience writing English author: “ggplot side--side density plot showing distributions predicted probabilities text sample written AI depending GPT detector model lived experience writing English author. shown models classify samples written native English writers well, variably poorly non-native English writers.”","code":"library(ggplot2) library(detectors) detectors ## # A tibble: 6,185 × 9 ## kind .pred_AI .pred_class detector native name model document_id prompt ## <fct> <dbl> <fct> <chr> <chr> <chr> <chr> <dbl> <chr> ## 1 Human 1.00 AI Sapling No Real… Human 497 <NA> ## 2 Human 0.828 AI Crossplag No Real… Human 278 <NA> ## 3 Human 0.000214 Human Crossplag Yes Real… Human 294 <NA> ## 4 AI 0 Human ZeroGPT <NA> Fake… GPT3 671 Plain ## 5 AI 0.00178 Human Originality… <NA> Fake… GPT4 717 Eleva… ## 6 Human 0.000178 Human HFOpenAI Yes Real… Human 855 <NA> ## 7 AI 0.992 AI HFOpenAI <NA> Fake… GPT3 533 Plain ## 8 AI 0.0226 Human Crossplag <NA> Fake… GPT4 484 Eleva… ## 9 Human 0 Human ZeroGPT Yes Real… Human 781 <NA> ## 10 Human 1.00 AI Sapling No Real… Human 460 <NA> ## # ℹ 6,175 more rows detectors_plot <- detectors[!is.na(detectors$native), ] %>% ggplot() + aes(x = detector, y = .pred_AI, fill = native) + geom_violin(bw = .05) + labs( x = \"GPT Detector Tool\", y = \"Predicted Probability That\\nSample Was Written by AI\", fill = \"Native\\nEnglish\\nWriter\" ) + theme_minimal() + scale_fill_brewer(type = \"qual\") + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) detectors_plot"},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":null,"dir":"Reference","previous_headings":"","what":"Predictions from GPT Detectors — detectors","title":"Predictions from GPT Detectors — detectors","text":"Data derived paper GPT detectors biased non-native English writers. study authors carried series experiments passing number essays different GPT detection models. Juxtaposing detector predictions papers written native non-native English writers, authors argue GPT detectors disproportionately classify real writing non-native English writers AI-generated.","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Predictions from GPT Detectors — detectors","text":"","code":"detectors"},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Predictions from GPT Detectors — detectors","text":"data frame 6,185 rows 9 columns: kind Whether essay written \"Human\" \"AI\". .pred_AI class probability GPT detector inputted text written AI. .pred_class uncalibrated class prediction, encoded if_else(.pred_AI > .5, \"AI\", \"Human\") detector name detector used generate predictions. native essays written humans, whether essay written native English writer . categorizations coarse; values \"Yes\" may actually written people write English natively. NA indicates text written human. name label experiment predictions generated . model essays written AI, name model generated essay. document_id unique identifier supplied essay. essays supplied multiple detectors. Note essays AI-revised derivatives others. prompt essays written AI, descriptor form \"prompt engineering\" passed model. information data, see source paper.","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"source","dir":"Reference","previous_headings":"","what":"Source","title":"Predictions from GPT Detectors — detectors","text":"doi:10.1016/j.patter.2023.100779","code":""},{"path":"https://simonpcouch.github.io/detectors/reference/detectors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Predictions from GPT Detectors — detectors","text":"","code":"detectors #> # A tibble: 6,185 × 9 #> kind .pred_AI .pred_class detector native name model document_id prompt #> <fct> <dbl> <fct> <chr> <chr> <chr> <chr> <dbl> <chr> #> 1 Human 1.00 AI Sapling No Real… Human 497 NA #> 2 Human 0.828 AI Crossplag No Real… Human 278 NA #> 3 Human 0.000214 Human Crossplag Yes Real… Human 294 NA #> 4 AI 0 Human ZeroGPT NA Fake… GPT3 671 Plain #> 5 AI 0.00178 Human Originality… NA Fake… GPT4 717 Eleva… #> 6 Human 0.000178 Human HFOpenAI Yes Real… Human 855 NA #> 7 AI 0.992 AI HFOpenAI NA Fake… GPT3 533 Plain #> 8 AI 0.0226 Human Crossplag NA Fake… GPT4 484 Eleva… #> 9 Human 0 Human ZeroGPT Yes Real… Human 781 NA #> 10 Human 1.00 AI Sapling No Real… Human 460 NA #> # ℹ 6,175 more rows"}]