# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md) profile: corpus_all ontology_version: '1.0' built: timestamp: '2026-11-03T22:56:41+00:00' code_version: feb6c9e-dirty host: platform: macOS-27.0-arm64-arm-64bit python: 3.12.13 machine: arm64 node: MacBookPro-de-simon-pierre-2.local selection_rule: all included train documents n_documents: 221 split: train (heldout_v1 excluded) caveat: Observed frequencies describe what published JoF articles did in 2017–2020; they are not evidence that these choices are editorially superior or required. structure: pages: n: 221 median: 43.0 q25: 38.0 q75: 47.0 mean: 42.679 min: 1.0 max: 67.0 median_ci95_bootstrap: - 42.0 - 44.0 n_words_body: n: 221 median: 11009.0 q25: 10035.0 q75: 12407.0 mean: 11137.873 min: 25.0 max: 17348.0 median_ci95_bootstrap: - 10813.0 - 11256.0 n_words_appendix: n: 221 median: 0.0 q25: 0.0 q75: 1599.0 mean: 934.443 min: 0.0 max: 9912.0 median_ci95_bootstrap: - 0.0 - 23.0 abstract_words: n: 221 median: 101.0 q25: 96.0 q75: 104.0 mean: 105.385 min: 0.0 max: 535.0 median_ci95_bootstrap: - 100.0 - 102.0 n_sections: n: 221 median: 5.0 q25: 5.0 q75: 6.0 mean: 5.475 min: 0.0 max: 10.0 median_ci95_bootstrap: - 5.0 - 6.0 n_subsections: n: 221 median: 14.0 q25: 10.0 q75: 19.0 mean: 14.81 min: 0.0 max: 46.0 median_ci95_bootstrap: - 13.0 - 14.0 n_paragraphs: n: 221 median: 132.0 q25: 89.0 q75: 218.0 mean: 185.118 min: 2.0 max: 920.0 median_ci95_bootstrap: - 118.0 - 150.525 n_equations: n: 221 median: 10.0 q25: 4.0 q75: 23.0 mean: 17.62 min: 0.0 max: 159.0 median_ci95_bootstrap: - 8.0 - 12.0 n_tables: n: 221 median: 8.0 q25: 6.0 q75: 11.0 mean: 7.76 min: 0.0 max: 24.0 median_ci95_bootstrap: - 7.0 - 9.0 n_figures: n: 221 median: 4.0 q25: 2.0 q75: 7.0 mean: 4.362 min: 0.0 max: 14.0 median_ci95_bootstrap: - 3.0 - 4.0 n_footnotes: n: 221 median: 37.0 q25: 29.0 q75: 48.0 mean: 40.136 min: 1.0 max: 148.0 median_ci95_bootstrap: - 35.0 - 39.0 n_references: n: 221 median: 52.0 q25: 41.0 q75: 64.0 mean: 54.158 min: 0.0 max: 198.0 median_ci95_bootstrap: - 49.0 - 56.0 n_citations_in_text: n: 221 median: 55.0 q25: 38.0 q75: 72.0 mean: 59.995 min: 0.0 max: 205.0 median_ci95_bootstrap: - 50.475 - 61.0 intro_words: n: 221 median: 1804.0 q25: 1568.0 q75: 2132.0 mean: 1831.249 min: 25.0 max: 3245.0 median_ci95_bootstrap: - 1754.0 - 1861.3 intro_paragraphs: n: 221 median: 7.0 q25: 6.0 q75: 9.0 mean: 8.344 min: 1.0 max: 64.0 median_ci95_bootstrap: - 7.0 - 8.0 intro_share: n: 221 median: 0.164 q25: 0.14 q75: 0.192 mean: 0.174 min: 0.071 max: 1.0 median_ci95_bootstrap: - 0.16 - 0.172 conclusion_words: n: 221 median: 358.0 q25: 254.0 q75: 511.0 mean: 454.783 min: 0.0 max: 3986.0 median_ci95_bootstrap: - 326.0 - 393.525 conclusion_share: n: 221 median: 0.032 q25: 0.023 q75: 0.046 mean: 0.042 min: 0.0 max: 0.427 median_ci95_bootstrap: - 0.031 - 0.035 theory_share: n: 221 median: 0.086 q25: 0.0 q75: 0.251 mean: 0.148 min: 0.0 max: 0.817 median_ci95_bootstrap: - 0.027 - 0.137 data_share: n: 221 median: 0.0 q25: 0.0 q75: 0.116 mean: 0.071 min: 0.0 max: 0.57 median_ci95_bootstrap: - 0.0 - 0.056 results_share: n: 221 median: 0.0 q25: 0.0 q75: 0.151 mean: 0.099 min: 0.0 max: 0.627 median_ci95_bootstrap: - 0.0 - 0.0 robustness_share: n: 221 median: 0.0 q25: 0.0 q75: 0.053 mean: 0.04 min: 0.0 max: 0.344 median_ci95_bootstrap: - 0.0 - 0.0 words_per_table: n: 221 median: 1354.5 q25: 1006.375 q75: 2017.571 mean: 2712.665 min: 25.0 max: 17169.0 median_ci95_bootstrap: - 1217.333 - 1448.333 refs_per_1000_words: n: 221 median: 4.748 q25: 3.675 q75: 5.905 mean: 4.882 min: 0.0 max: 13.377 median_ci95_bootstrap: - 4.52 - 5.017 equations_per_1000_words: n: 221 median: 0.886 q25: 0.338 q75: 2.248 mean: 1.732 min: 0.0 max: 23.044 median_ci95_bootstrap: - 0.688 - 1.16 presence: has_robustness_section: n: 221 share: 0.262 has_literature_section: n: 221 share: 0.172 has_appendix: n: 221 share: 0.498 has_internet_appendix: n: 221 share: 0.887 by_year: 2017: n: 51 n_words_body_median: 10858.0 n_tables_median: 9.0 2018: n: 52 n_words_body_median: 11474.5 n_tables_median: 7.0 2019: n: 59 n_words_body_median: 10823.0 n_tables_median: 8.0 2020: n: 59 n_words_body_median: 11115.0 n_tables_median: 9.0