{
"_id": "6a44ceab6ff6f2357551ba70",
"Type": "Package",
"Package": "pangoling",
"Title": "Access to Large Language Model Predictions",
"Version": "1.0.3",
"Authors@R": "c(\nperson(\"Bruno\", \"Nicenboim\", , \"b.nicenboim@tilburguniversity.edu\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-5176-3943\")),\nperson(\"Chris\", \"Emmerly\", role = \"ctb\"),\nperson(\"Giovanni\", \"Cassani\", role = \"ctb\"),\nperson(\"Lisa\", \"Levinson\", role = \"rev\"),\nperson(\"Utku\", \"Turk\", role = \"rev\")\n)",
"Description": "Provides access to word predictability estimates using\nlarge language models (LLMs) based on 'transformer'\narchitectures via integration with the 'Hugging Face' ecosystem\n. The package interfaces with\npre-trained neural networks and supports both\ncausal/auto-regressive LLMs (e.g., 'GPT-2') and\nmasked/bidirectional LLMs (e.g., 'BERT') to compute the\nprobability of words, phrases, or tokens given their linguistic\ncontext. For details on GPT-2 and causal models, see Radford et\nal. (2019)\n,\nfor details on BERT and masked models, see Devlin et al. (2019)\n. By enabling a straightforward\nestimation of word predictability, the package facilitates\nresearch in psycholinguistics, computational linguistics, and\nnatural language processing (NLP).",
"License": "MIT + file LICENSE",
"URL": "https://docs.ropensci.org/pangoling/,\nhttps://github.com/ropensci/pangoling",
"BugReports": "https://github.com/ropensci/pangoling/issues",
"Config/testthat/edition": "3",
"Encoding": "UTF-8",
"Language": "en-US",
"LazyData": "true",
"Roxygen": "list(markdown = TRUE)",
"RoxygenNote": "7.3.1",
"StagedInstall": "yes",
"VignetteBuilder": "knitr",
"Config/pak/sysreqs": "libpng-dev python3",
"Repository": "https://ropensci.r-universe.dev",
"Date/Publication": "2026-01-13 15:59:45 UTC",
"RemoteUrl": "https://github.com/ropensci/pangoling",
"RemoteRef": "main",
"RemoteSha": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"NeedsCompilation": "no",
"Packaged": {
"Date": "2026-07-01 08:16:06 UTC",
"User": "root"
},
"Author": "Bruno Nicenboim [aut, cre] (ORCID:\n),\nChris Emmerly [ctb],\nGiovanni Cassani [ctb],\nLisa Levinson [rev],\nUtku Turk [rev]",
"Maintainer": "Bruno Nicenboim ",
"_user": "ropensci",
"_type": "src",
"_file": "pangoling_1.0.3.tar.gz",
"_fileid": "https://r2.ropensci.org/dd785654033426e9214ce0e4d82352aeabd2e5fa62bf1016228b97540da4ce90",
"_filesize": 999302,
"_sha256": "dd785654033426e9214ce0e4d82352aeabd2e5fa62bf1016228b97540da4ce90",
"_expires": "2026-10-09T08:24:10.000Z",
"_created": "2026-07-01T08:16:06.000Z",
"_published": "2026-07-01T08:24:11.185Z",
"_jobs": [
{
"job": 84486391140,
"time": 190,
"config": "linux-devel-x86_64",
"r": "4.7.0",
"check": "OK",
"artifact": "8004099099"
},
{
"job": 84486391150,
"time": 189,
"config": "linux-release-x86_64",
"r": "4.6.1",
"check": "OK",
"artifact": "8004098517"
},
{
"job": 84486391173,
"time": 137,
"config": "macos-oldrel-arm64",
"r": "4.5.3",
"check": "OK",
"artifact": "8004137397"
},
{
"job": 84486391135,
"time": 187,
"config": "macos-release-arm64",
"r": "4.6.1",
"check": "OK",
"artifact": "8004153640"
},
{
"job": 84485695541,
"time": 163,
"config": "pkgdown",
"r": "4.6.0",
"check": "OK",
"artifact": "8004001468"
},
{
"job": 84485695561,
"time": 232,
"config": "source",
"r": "4.6.1",
"check": "OK",
"artifact": "8004026143"
},
{
"job": 84486391146,
"time": 188,
"config": "wasm-release",
"r": "4.6.0",
"check": "OK",
"artifact": "8004098264"
},
{
"job": 84486391175,
"time": 202,
"config": "windows-devel",
"r": "4.7.0",
"check": "OK",
"artifact": "8004102231"
},
{
"job": 84486391182,
"time": 195,
"config": "windows-oldrel",
"r": "4.5.3",
"check": "OK",
"artifact": "8004099448"
},
{
"job": 84486391156,
"time": 212,
"config": "windows-release",
"r": "4.6.1",
"check": "OK",
"artifact": "8004105143"
}
],
"_host": "GitHub-Actions",
"_buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880",
"_status": "success",
"_upstream": "https://github.com/ropensci/pangoling",
"_commit": {
"id": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"author": "Bruno Nicenboim ",
"committer": "GitHub ",
"message": "fix DOI",
"time": 1768319985
},
"_maintainer": {
"name": "Bruno Nicenboim",
"email": "b.nicenboim@tilburguniversity.edu",
"login": "bnicenboim",
"orcid": "0000-0002-5176-3943",
"twitter": "@bruno_nicenboim",
"description": "",
"uuid": 5982330
},
"_distro": "resolute",
"_registered": true,
"_dependencies": [
{
"package": "R",
"version": ">= 4.1.0",
"role": "Depends"
},
{
"package": "cachem",
"role": "Imports"
},
{
"package": "data.table",
"role": "Imports"
},
{
"package": "memoise",
"role": "Imports"
},
{
"package": "reticulate",
"role": "Imports"
},
{
"package": "rstudioapi",
"role": "Imports"
},
{
"package": "stats",
"role": "Imports"
},
{
"package": "tidyselect",
"role": "Imports"
},
{
"package": "tidytable",
"version": ">= 0.7.2",
"role": "Imports"
},
{
"package": "utils",
"role": "Imports"
},
{
"package": "brms",
"role": "Suggests"
},
{
"package": "knitr",
"role": "Suggests"
},
{
"package": "parallel",
"role": "Suggests"
},
{
"package": "rmarkdown",
"role": "Suggests"
},
{
"package": "spelling",
"role": "Suggests"
},
{
"package": "testthat",
"version": ">= 3.0.0",
"role": "Suggests"
},
{
"package": "tictoc",
"role": "Suggests"
},
{
"package": "covr",
"role": "Suggests"
}
],
"_owner": "ropensci",
"_selfowned": true,
"_usedby": 0,
"_updates": [
{
"week": "2026-03",
"n": 1
}
],
"_tags": [],
"_topics": [
"nlp",
"psycholinguistics",
"transformers"
],
"_stars": 12,
"_contributors": [
{
"user": "bnicenboim",
"count": 269,
"uuid": 5982330
}
],
"_userbio": {
"uuid": 1200269,
"type": "organization",
"name": "rOpenSci",
"followers": 1106,
"description": "Tools and R Packages for Open Science"
},
"_downloads": {
"count": 568,
"source": "https://cranlogs.r-pkg.org/downloads/total/last-month/pangoling"
},
"_devurl": "https://github.com/ropensci/pangoling",
"_pkgdown": "https://docs.ropensci.org/pangoling/",
"_searchresults": 16,
"_metadata": {
"review": {
"id": 575,
"status": "reviewed",
"version": "0.0.0.9005",
"organization": "rOpenSci Software Review",
"url": "https://github.com/ropensci/software-review/issues/575"
},
"ropensci_category": "scalereprod"
},
"_rbuild": "4.6.1",
"_assets": [
"extra/citation.cff",
"extra/citation.html",
"extra/citation.json",
"extra/citation.txt",
"extra/contents.json",
"extra/NEWS.html",
"extra/NEWS.txt",
"extra/pangoling.html",
"extra/readme.html",
"extra/readme.md",
"LICENSE",
"manual.pdf"
],
"_homeurl": "https://github.com/ropensci/pangoling",
"_realowner": "ropensci",
"_cranurl": true,
"_releases": [
{
"version": "1.0.3",
"date": "2025-04-07"
}
],
"_exports": [
"causal_config",
"causal_lp",
"causal_lp_mats",
"causal_next_tokens_pred_tbl",
"causal_next_tokens_tbl",
"causal_pred_mats",
"causal_preload",
"causal_targets_pred",
"causal_tokens_lp_tbl",
"causal_tokens_pred_lst",
"causal_words_pred",
"install_py_pangoling",
"installed_py_pangoling",
"masked_config",
"masked_lp",
"masked_preload",
"masked_targets_pred",
"masked_tokens_pred_tbl",
"masked_tokens_tbl",
"ntokens",
"perplexity_calc",
"set_cache_folder",
"tokenize_lst",
"transformer_vocab"
],
"_datasets": [
{
"name": "df_jaeger14",
"title": "Self-Paced Reading Dataset on Chinese Relative Clauses",
"object": "df_jaeger14",
"class": [
"tidytable",
"tbl",
"data.table",
"data.frame"
],
"fields": [
"subject",
"item",
"cond",
"word",
"wordn",
"rt",
"region",
"question",
"accuracy",
"correct_answer",
"question_type",
"experiment",
"list",
"sentence"
],
"rows": 8624,
"table": true,
"tojson": true
},
{
"name": "df_sent",
"title": "Example dataset: Two word-by-word sentences",
"object": "df_sent",
"class": [
"tidytable",
"tbl",
"data.table",
"data.frame"
],
"fields": [
"sent_n",
"word"
],
"rows": 15,
"table": true,
"tojson": true
}
],
"_help": [
{
"page": "causal_config",
"title": "Returns the configuration of a causal model",
"concept": [
"causal model helper functions"
],
"topics": [
"causal_config"
]
},
{
"page": "causal_next_tokens_pred_tbl",
"title": "Generate next tokens after a context and their predictability using a causal transformer model",
"concept": [
"causal model functions"
],
"topics": [
"causal_next_tokens_pred_tbl"
]
},
{
"page": "causal_pred_mats",
"title": "Generate a list of predictability matrices using a causal transformer model",
"concept": [
"causal model functions"
],
"topics": [
"causal_pred_mats"
]
},
{
"page": "causal_preload",
"title": "Preloads a causal language model",
"concept": [
"causal model helper functions"
],
"topics": [
"causal_preload"
]
},
{
"page": "causal_predictability",
"title": "Compute predictability using a causal transformer model",
"concept": [
"causal model functions"
],
"topics": [
"causal_targets_pred",
"causal_tokens_pred_lst",
"causal_words_pred"
]
},
{
"page": "df_jaeger14",
"title": "Self-Paced Reading Dataset on Chinese Relative Clauses",
"concept": [
"datasets"
],
"topics": [
"df_jaeger14"
]
},
{
"page": "df_sent",
"title": "Example dataset: Two word-by-word sentences",
"concept": [
"datasets"
],
"topics": [
"df_sent"
]
},
{
"page": "install_py_pangoling",
"title": "Install the Python packages needed for 'pangoling'",
"concept": [
"helper functions"
],
"topics": [
"install_py_pangoling"
]
},
{
"page": "installed_py_pangoling",
"title": "Check if the required Python dependencies for 'pangoling' are installed",
"concept": [
"helper functions"
],
"topics": [
"installed_py_pangoling"
]
},
{
"page": "masked_config",
"title": "Returns the configuration of a masked model",
"concept": [
"masked model helper functions"
],
"topics": [
"masked_config"
]
},
{
"page": "masked_preload",
"title": "Preloads a masked language model",
"concept": [
"masked model helper functions"
],
"topics": [
"masked_preload"
]
},
{
"page": "masked_targets_pred",
"title": "Get the predictability of a target word (or phrase) given a left and right context",
"concept": [
"masked model functions"
],
"topics": [
"masked_targets_pred"
]
},
{
"page": "masked_tokens_pred_tbl",
"title": "Get the possible tokens and their log probabilities for each mask in a sentence",
"concept": [
"masked model functions"
],
"topics": [
"masked_tokens_pred_tbl"
]
},
{
"page": "ntokens",
"title": "The number of tokens in a string or vector of strings",
"concept": [
"token-related functions"
],
"topics": [
"ntokens"
]
},
{
"page": "perplexity_calc",
"title": "Calculates perplexity",
"concept": [
"general functions"
],
"topics": [
"perplexity_calc"
]
},
{
"page": "set_cache_folder",
"title": "Set cache folder for HuggingFace transformers",
"concept": [
"helper functions"
],
"topics": [
"set_cache_folder"
]
},
{
"page": "tokenize_lst",
"title": "Tokenize an input",
"concept": [
"token-related functions"
],
"topics": [
"tokenize_lst"
]
},
{
"page": "transformer_vocab",
"title": "Returns the vocabulary of a model",
"concept": [
"token-related functions"
],
"topics": [
"transformer_vocab"
]
}
],
"_pkglogo": "https://github.com/ropensci/pangoling/raw/main/man/figures/logo.png",
"_readme": "https://github.com/ropensci/pangoling/raw/main/README.md",
"_rundeps": [
"cachem",
"cli",
"data.table",
"fastmap",
"glue",
"here",
"jsonlite",
"lattice",
"lifecycle",
"magrittr",
"Matrix",
"memoise",
"pillar",
"png",
"rappdirs",
"Rcpp",
"RcppTOML",
"reticulate",
"rlang",
"rprojroot",
"rstudioapi",
"tidyselect",
"tidytable",
"utf8",
"vctrs",
"withr"
],
"_vignettes": [
{
"source": "troubleshooting.Rmd",
"filename": "troubleshooting.html",
"title": "Troubleshooting the use of Python in R",
"engine": "knitr::rmarkdown",
"headings": [
"Module not found error in Rstudio",
"HTTPSConnectionPool error"
],
"created": "2025-03-11 08:53:06",
"modified": "2025-03-11 08:53:06",
"commits": 1
},
{
"source": "intro-bert.Rmd",
"filename": "intro-bert.html",
"title": "Using a Bert model to get the predictability of words in their context",
"engine": "knitr::rmarkdown",
"headings": [
"References"
],
"created": "2025-03-11 08:53:06",
"modified": "2025-03-11 08:53:06",
"commits": 1
},
{
"source": "intro-gpt2.Rmd",
"filename": "intro-gpt2.html",
"title": "Using a GPT2 transformer model to get word predictability",
"engine": "knitr::rmarkdown",
"headings": [
"References"
],
"created": "2025-03-11 08:53:06",
"modified": "2025-03-11 14:01:55",
"commits": 2
},
{
"source": "example.Rmd",
"filename": "example.html",
"title": "Worked-out example: Surprisal from a causal (GPT) model as a cognitive processing bottleneck in reading",
"engine": "knitr::rmarkdown",
"headings": [
"Data analysis",
"0. Preprocessing",
"1. Add surprisal values to the dataset",
"2. Analyze the dataset with a Bayesian hierarchical model",
"Conclusion",
"References"
],
"created": "2025-03-11 08:53:06",
"modified": "2025-03-11 20:22:12",
"commits": 2
}
],
"_score": 5.584331224367531,
"_indexed": true,
"_nocasepkg": "pangoling",
"_universes": [
"ropensci",
"bnicenboim"
],
"_binaries": [
{
"r": "4.7.0",
"os": "linux",
"version": "1.0.3",
"date": "2026-07-01T08:19:12.000Z",
"distro": "resolute",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/7deaf1b8c481bad62b4d572fae68a7363e7b96d54a430ddb820cfd7a4a7b8803",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.6.1",
"os": "linux",
"version": "1.0.3",
"date": "2026-07-01T08:19:11.000Z",
"distro": "resolute",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/9b4c57abb17cd1009a7c473fc9e266db73c85252cc4dace71a5ec4f60e47d4a8",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.5.3",
"os": "mac",
"version": "1.0.3",
"date": "2026-07-01T08:20:52.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/0a5db1dca203f0fc949721e7581381abbdef06b78214cbb638b900e1c60e935e",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.6.1",
"os": "mac",
"version": "1.0.3",
"date": "2026-07-01T08:21:20.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/59154670b6bb96eadb7e1af25e084c43e0f6703ddc86bea82a448fcdd94cb1a2",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.6.0",
"os": "wasm",
"version": "1.0.3",
"date": "2026-07-01T08:19:49.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/03cd34a6ad2f385d0310b75c40a3c1535cc0f32ae1205cc80fa83bef7924b5aa",
"status": "success",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.7.0",
"os": "win",
"version": "1.0.3",
"date": "2026-07-01T08:17:52.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/17720b2167d7f9f5cc8579f0dced76264bdd564be431d70081f2ff6a0498c8e1",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.5.3",
"os": "win",
"version": "1.0.3",
"date": "2026-07-01T08:17:50.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/18de7b9c5f285957b2aff0b4df4f8a854c132df6de29345b61a9abb8d6d33cd1",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
},
{
"r": "4.6.1",
"os": "win",
"version": "1.0.3",
"date": "2026-07-01T08:17:58.000Z",
"commit": "39916805ecb60c144f6a3bc531bfb7ff539f32d8",
"fileid": "https://r2.ropensci.org/5f859c92efd1ee8a59e31dbd63f68f05740093f6fab3be530c662fad274f68c3",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503336880"
}
]
}