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: '2026-11-03T23:27:16+00:00'6 code_version: 87c73cd-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: 9.0323rhetoric:324 n_annotated: 221325 genre:326 n: 221327 empirical: 0.529328 mixed_theory_empirical: 0.253329 theoretical: 0.145330 replication_or_correction: 0.032331 methodological_econometric: 0.027332 survey_or_address: 0.014333 subfield:334 n: 221335 asset_pricing: 0.312336 corporate_finance: 0.176337 financial_intermediation_banking: 0.127338 household_finance: 0.1339 market_microstructure: 0.1340 behavioral_finance: 0.054341 macro_finance: 0.045342 entrepreneurial_finance_private_equity: 0.041343 primary_method:344 n: 221345 reduced_form_regression: 0.367346 theoretical_model_analytical: 0.195347 difference_in_differences: 0.1348 structural_estimation: 0.068349 calibration_simulation: 0.063350 instrumental_variables: 0.059351 other: 0.05352 survey_or_experiment: 0.036353 abstract_moves_present:354 question:355 n: 221356 share: 0.701357 gap:358 n: 221359 share: 0.14360 method:361 n: 221362 share: 0.828363 results:364 n: 221365 share: 0.991366 magnitude:367 n: 221368 share: 0.235369 contribution:370 n: 221371 share: 0.692372 abstract_move_order_median_sentence:373 question:374 n: 155375 median: 0.0376 q25: 0.0377 q75: 0.0378 mean: 0.174379 min: 0.0380 max: 4.0381 median_ci95_bootstrap:382 - 0.0383 - 0.0384 gap:385 n: 31386 median: 1.0387 q25: 0.0388 q75: 1.0389 mean: 0.871390 min: 0.0391 max: 4.0392 median_ci95_bootstrap:393 - 0.0394 - 1.0395 method:396 n: 183397 median: 1.0398 q25: 0.0399 q75: 2.0400 mean: 1.055401 min: 0.0402 max: 5.0403 median_ci95_bootstrap:404 - 1.0405 - 1.0406 results:407 n: 219408 median: 1.0409 q25: 1.0410 q75: 2.0411 mean: 1.626412 min: 0.0413 max: 5.0414 median_ci95_bootstrap:415 - 1.0416 - 2.0417 magnitude:418 n: 52419 median: 2.0420 q25: 1.0421 q75: 3.0422 mean: 2.115423 min: 0.0424 max: 5.0425 median_ci95_bootstrap:426 - 2.0427 - 2.0428 contribution:429 n: 153430 median: 3.0431 q25: 1.0432 q75: 4.0433 mean: 2.497434 min: 0.0435 max: 7.0436 median_ci95_bootstrap:437 - 2.0438 - 3.0439 abstract_sentences:440 n: 221441 median: 5.0442 q25: 4.0443 q75: 6.0444 mean: 5.29445 min: 0.0446 max: 16.0447 median_ci95_bootstrap:448 - 5.0449 - 5.0450 magnitude_in_abstract_regex:451 n: 221452 share: 0.176453 introduction:454 paragraphs:455 n: 221456 median: 7.0457 q25: 6.0458 q75: 9.0459 mean: 8.344460 min: 1.0461 max: 64.0462 median_ci95_bootstrap:463 - 7.0464 - 8.0465 words:466 n: 221467 median: 1087.0468 q25: 870.0469 q75: 1320.0470 mean: 1101.919471 min: 25.0472 max: 2771.0473 median_ci95_bootstrap:474 - 1015.0475 - 1140.0476 contribution_paragraph_index:477 n: 210478 median: 4.0479 q25: 1.0480 q75: 6.0481 mean: 4.314482 min: 0.0483 max: 56.0484 median_ci95_bootstrap:485 - 3.0486 - 5.0487 contribution_relative_position:488 n: 210489 median: 0.577490 q25: 0.129491 q75: 0.778492 mean: 0.474493 min: 0.0494 max: 0.941495 median_ci95_bootstrap:496 - 0.5497 - 0.625498 first_move:499 n: 221500 motivation: 0.887501 tension_or_puzzle: 0.027502 preview_of_approach: 0.027503 other: 0.023504 contribution_statement: 0.014505 literature_gap: 0.009506 related_literature_positioning: 0.009507 mechanism_or_theory_sketch: 0.005508 common_move_sequences:509 n: 221510 ? motivation > preview_of_approach > identification_defense > mechanism_or_theory_sketch > preview_of_approach > preview_of_results511 > robustness_mention > identification_defense > contribution_statement > related_literature_positioning > other >512 policy_or_broader_implication513 : 0.005514 ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning515 > literature_gap > contribution_statement > policy_or_broader_implication > roadmap516 : 0.005517 ? motivation > mechanism_or_theory_sketch > preview_of_results > preview_of_approach > preview_of_results > identification_defense518 > preview_of_results > robustness_mention > related_literature_positioning > contribution_statement519 : 0.005520 ? motivation > policy_or_broader_implication > mechanism_or_theory_sketch > tension_or_puzzle > preview_of_approach521 > preview_of_results > identification_defense > related_literature_positioning > contribution_statement > related_literature_positioning522 : 0.005523 ? motivation > literature_gap > policy_or_broader_implication > preview_of_approach > preview_of_results > robustness_mention524 > preview_of_results > contribution_statement > related_literature_positioning525 : 0.005526 ? tension_or_puzzle > literature_gap > contribution_statement > preview_of_approach > mechanism_or_theory_sketch > identification_defense527 > preview_of_approach > identification_defense > preview_of_results > preview_of_approach > preview_of_results > policy_or_broader_implication528 > related_literature_positioning > roadmap529 : 0.005530 roadmap_present_llm:531 n: 221532 share: 0.629533 roadmap_present_regex:534 n: 221535 share: 0.597536 literature_positioning_location:537 n: 221538 inside_introduction: 0.869539 both: 0.09540 separate_section: 0.027541 none: 0.014542 contribution_types:543 n: 438544 new_evidence: 0.411545 new_theory_or_model: 0.196546 new_data_or_measure: 0.162547 new_identification: 0.084548 resolution_of_puzzle: 0.071549 new_method: 0.05550 replication_or_correction: 0.018551 synthesis: 0.007552 identification:553 causal_language_strength:554 n: 221555 median: 3.0556 q25: 2.0557 q75: 3.0558 mean: 2.575559 min: 1.0560 max: 5.0561 median_ci95_bootstrap:562 - 2.0563 - 3.0564 uses_causal_claim:565 n: 221566 share: 0.498567 results:568 economic_significance_discussed:569 n: 221570 share: 0.787571 statistical_language:572 n: 221573 unclear: 0.787574 stars_and_tstats: 0.109575 mixed: 0.077576 confidence_intervals: 0.014577 p_values: 0.014578 magnitude_statements_in_intro:579 n: 221580 share: 0.57581 robustness:582 location:583 n: 221584 mixed: 0.367585 within_results: 0.235586 none_seen: 0.176587 main_text_section: 0.154588 appendix: 0.05589 internet_appendix: 0.018590 types:591 n: 607592 alternative_specification: 0.229593 other: 0.171594 subsample: 0.17595 alternative_measure: 0.16596 ? ''597 : 0.064598 alternative_sample_period: 0.058599 sensitivity_to_parameters: 0.056600 placebo: 0.048601 tables:602 standard_errors:603 n: 221604 unclear: 0.62605 none: 0.217606 clustered: 0.059607 mixed: 0.041608 newey_west: 0.032609 robust: 0.027610 bootstrap: 0.005611 units_in_notes:612 n: 221613 share: 0.679614 clustered_regex:615 n: 221616 share: 0.054617 figures:618 uncertainty_shown:619 n: 221620 unclear: 0.475621 'no': 0.317622 mixed: 0.095623 no_figures: 0.095624 'yes': 0.018625 conclusion:626 bounded_claims:627 n: 221628 share: 0.819629 policy_implications:630 n: 221631 share: 0.367632 open_questions:633 n: 221634 share: 0.371635 hedging:636 n: 221637 moderate: 0.873638 low: 0.127639 claims_with_stated_evidence_share:640 n: 221641 median: 1.0642 q25: 1.0643 q75: 1.0644 mean: 0.981645 min: 0.0646 max: 1.0647 median_ci95_bootstrap:648 - 1.0649 - 1.0650 llm_vs_rule_section_role_agreement:651 n: 221652 median: 1.0653 q25: 0.8654 q75: 1.0655 mean: 0.896656 min: 0.0657 max: 1.0658 median_ci95_bootstrap:659 - 0.91660 - 1.0661 llm_confidence:662 n: 221663 median: 0.8664 q25: 0.8665 q75: 0.85666 mean: 0.815667 min: 0.75668 max: 0.95669 median_ci95_bootstrap:670 - 0.8671 - 0.8672