1# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)2profile: corpus_all3ontology_version: '1.0'4built:5 timestamp: '2026-11-03T22:56:41+00:00'6 code_version: feb6c9e-dirty7 host:8 platform: macOS-27.0-arm64-arm-64bit9 python: 3.12.1310 machine: arm6411 node: MacBookPro-de-simon-pierre-2.local12selection_rule: all included train documents13n_documents: 22114split: train (heldout_v1 excluded)15caveat: Observed frequencies describe what published JoF articles did in 2017–2020; they are not evidence that these choices16 are editorially superior or required.17structure:18 pages:19 n: 22120 median: 43.021 q25: 38.022 q75: 47.023 mean: 42.67924 min: 1.025 max: 67.026 median_ci95_bootstrap:27 - 42.028 - 44.029 n_words_body:30 n: 22131 median: 11009.032 q25: 10035.033 q75: 12407.034 mean: 11137.87335 min: 25.036 max: 17348.037 median_ci95_bootstrap:38 - 10813.039 - 11256.040 n_words_appendix:41 n: 22142 median: 0.043 q25: 0.044 q75: 1599.045 mean: 934.44346 min: 0.047 max: 9912.048 median_ci95_bootstrap:49 - 0.050 - 23.051 abstract_words:52 n: 22153 median: 101.054 q25: 96.055 q75: 104.056 mean: 105.38557 min: 0.058 max: 535.059 median_ci95_bootstrap:60 - 100.061 - 102.062 n_sections:63 n: 22164 median: 5.065 q25: 5.066 q75: 6.067 mean: 5.47568 min: 0.069 max: 10.070 median_ci95_bootstrap:71 - 5.072 - 6.073 n_subsections:74 n: 22175 median: 14.076 q25: 10.077 q75: 19.078 mean: 14.8179 min: 0.080 max: 46.081 median_ci95_bootstrap:82 - 13.083 - 14.084 n_paragraphs:85 n: 22186 median: 132.087 q25: 89.088 q75: 218.089 mean: 185.11890 min: 2.091 max: 920.092 median_ci95_bootstrap:93 - 118.094 - 150.52595 n_equations:96 n: 22197 median: 10.098 q25: 4.099 q75: 23.0100 mean: 17.62101 min: 0.0102 max: 159.0103 median_ci95_bootstrap:104 - 8.0105 - 12.0106 n_tables:107 n: 221108 median: 8.0109 q25: 6.0110 q75: 11.0111 mean: 7.76112 min: 0.0113 max: 24.0114 median_ci95_bootstrap:115 - 7.0116 - 9.0117 n_figures:118 n: 221119 median: 4.0120 q25: 2.0121 q75: 7.0122 mean: 4.362123 min: 0.0124 max: 14.0125 median_ci95_bootstrap:126 - 3.0127 - 4.0128 n_footnotes:129 n: 221130 median: 37.0131 q25: 29.0132 q75: 48.0133 mean: 40.136134 min: 1.0135 max: 148.0136 median_ci95_bootstrap:137 - 35.0138 - 39.0139 n_references:140 n: 221141 median: 52.0142 q25: 41.0143 q75: 64.0144 mean: 54.158145 min: 0.0146 max: 198.0147 median_ci95_bootstrap:148 - 49.0149 - 56.0150 n_citations_in_text:151 n: 221152 median: 55.0153 q25: 38.0154 q75: 72.0155 mean: 59.995156 min: 0.0157 max: 205.0158 median_ci95_bootstrap:159 - 50.475160 - 61.0161 intro_words:162 n: 221163 median: 1804.0164 q25: 1568.0165 q75: 2132.0166 mean: 1831.249167 min: 25.0168 max: 3245.0169 median_ci95_bootstrap:170 - 1754.0171 - 1861.3172 intro_paragraphs:173 n: 221174 median: 7.0175 q25: 6.0176 q75: 9.0177 mean: 8.344178 min: 1.0179 max: 64.0180 median_ci95_bootstrap:181 - 7.0182 - 8.0183 intro_share:184 n: 221185 median: 0.164186 q25: 0.14187 q75: 0.192188 mean: 0.174189 min: 0.071190 max: 1.0191 median_ci95_bootstrap:192 - 0.16193 - 0.172194 conclusion_words:195 n: 221196 median: 358.0197 q25: 254.0198 q75: 511.0199 mean: 454.783200 min: 0.0201 max: 3986.0202 median_ci95_bootstrap:203 - 326.0204 - 393.525205 conclusion_share:206 n: 221207 median: 0.032208 q25: 0.023209 q75: 0.046210 mean: 0.042211 min: 0.0212 max: 0.427213 median_ci95_bootstrap:214 - 0.031215 - 0.035216 theory_share:217 n: 221218 median: 0.086219 q25: 0.0220 q75: 0.251221 mean: 0.148222 min: 0.0223 max: 0.817224 median_ci95_bootstrap:225 - 0.027226 - 0.137227 data_share:228 n: 221229 median: 0.0230 q25: 0.0231 q75: 0.116232 mean: 0.071233 min: 0.0234 max: 0.57235 median_ci95_bootstrap:236 - 0.0237 - 0.056238 results_share:239 n: 221240 median: 0.0241 q25: 0.0242 q75: 0.151243 mean: 0.099244 min: 0.0245 max: 0.627246 median_ci95_bootstrap:247 - 0.0248 - 0.0249 robustness_share:250 n: 221251 median: 0.0252 q25: 0.0253 q75: 0.053254 mean: 0.04255 min: 0.0256 max: 0.344257 median_ci95_bootstrap:258 - 0.0259 - 0.0260 words_per_table:261 n: 221262 median: 1354.5263 q25: 1006.375264 q75: 2017.571265 mean: 2712.665266 min: 25.0267 max: 17169.0268 median_ci95_bootstrap:269 - 1217.333270 - 1448.333271 refs_per_1000_words:272 n: 221273 median: 4.748274 q25: 3.675275 q75: 5.905276 mean: 4.882277 min: 0.0278 max: 13.377279 median_ci95_bootstrap:280 - 4.52281 - 5.017282 equations_per_1000_words:283 n: 221284 median: 0.886285 q25: 0.338286 q75: 2.248287 mean: 1.732288 min: 0.0289 max: 23.044290 median_ci95_bootstrap:291 - 0.688292 - 1.16293presence:294 has_robustness_section:295 n: 221296 share: 0.262297 has_literature_section:298 n: 221299 share: 0.172300 has_appendix:301 n: 221302 share: 0.498303 has_internet_appendix:304 n: 221305 share: 0.887306by_year:307 2017:308 n: 51309 n_words_body_median: 10858.0310 n_tables_median: 9.0311 2018:312 n: 52313 n_words_body_median: 11474.5314 n_tables_median: 7.0315 2019:316 n: 59317 n_words_body_median: 10823.0318 n_tables_median: 8.0319 2020:320 n: 59321 n_words_body_median: 11115.0322 n_tables_median: 9.0323