1# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)2profile: corporate_finance3ontology_version: '1.0'4built:5 timestamp: '2026-11-03T23:27:17+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: annotation.subfield == corporate_finance and genre in {empirical, mixed_theory_empirical}13n_documents: 2814split: 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: 2820 median: 42.521 q25: 39.022 q75: 46.2523 mean: 43.7524 min: 35.025 max: 60.026 median_ci95_bootstrap:27 - 39.23728 - 45.029 n_words_body:30 n: 2831 median: 11150.532 q25: 10414.7533 q75: 11549.534 mean: 11186.42935 min: 7845.036 max: 15116.037 median_ci95_bootstrap:38 - 10597.039 - 11464.76340 n_words_appendix:41 n: 2842 median: 0.043 q25: 0.044 q75: 5.7545 mean: 422.14346 min: 0.047 max: 3982.048 median_ci95_bootstrap:49 - 0.050 - 0.051 abstract_words:52 n: 2853 median: 100.554 q25: 96.7555 q75: 103.056 mean: 128.057 min: 83.058 max: 535.059 median_ci95_bootstrap:60 - 97.561 - 102.562 n_sections:63 n: 2864 median: 6.065 q25: 5.066 q75: 6.2567 mean: 5.71468 min: 3.069 max: 9.070 median_ci95_bootstrap:71 - 5.072 - 6.073 n_subsections:74 n: 2875 median: 12.076 q25: 10.577 q75: 19.078 mean: 14.35779 min: 4.080 max: 36.081 median_ci95_bootstrap:82 - 11.083 - 16.084 n_paragraphs:85 n: 2886 median: 91.087 q25: 76.2588 q75: 117.2589 mean: 103.39390 min: 51.091 max: 203.092 median_ci95_bootstrap:93 - 80.094 - 108.095 n_equations:96 n: 2897 median: 5.098 q25: 2.099 q75: 8.25100 mean: 6.964101 min: 0.0102 max: 42.0103 median_ci95_bootstrap:104 - 3.0105 - 6.5106 n_tables:107 n: 28108 median: 10.0109 q25: 8.0110 q75: 12.0111 mean: 9.893112 min: 4.0113 max: 14.0114 median_ci95_bootstrap:115 - 9.0116 - 11.0117 n_figures:118 n: 28119 median: 3.0120 q25: 2.0121 q75: 5.25122 mean: 3.429123 min: 0.0124 max: 8.0125 median_ci95_bootstrap:126 - 2.0127 - 4.0128 n_footnotes:129 n: 28130 median: 36.5131 q25: 26.75132 q75: 41.25133 mean: 36.357134 min: 15.0135 max: 62.0136 median_ci95_bootstrap:137 - 30.5138 - 40.0139 n_references:140 n: 28141 median: 49.5142 q25: 35.75143 q75: 59.0144 mean: 50.857145 min: 19.0146 max: 115.0147 median_ci95_bootstrap:148 - 41.5149 - 57.0150 n_citations_in_text:151 n: 28152 median: 48.0153 q25: 30.5154 q75: 66.5155 mean: 54.321156 min: 18.0157 max: 148.0158 median_ci95_bootstrap:159 - 31.238160 - 63.525161 intro_words:162 n: 28163 median: 1927.0164 q25: 1738.25165 q75: 2119.25166 mean: 1937.143167 min: 1275.0168 max: 2758.0169 median_ci95_bootstrap:170 - 1837.0171 - 2019.5172 intro_paragraphs:173 n: 28174 median: 8.0175 q25: 6.0176 q75: 11.0177 mean: 11.143178 min: 4.0179 max: 64.0180 median_ci95_bootstrap:181 - 7.0182 - 9.5183 intro_share:184 n: 28185 median: 0.175186 q25: 0.154187 q75: 0.195188 mean: 0.175189 min: 0.105190 max: 0.242191 median_ci95_bootstrap:192 - 0.161193 - 0.191194 conclusion_words:195 n: 28196 median: 459.5197 q25: 268.0198 q75: 621.5199 mean: 508.714200 min: 142.0201 max: 2063.0202 median_ci95_bootstrap:203 - 308.588204 - 575.0205 conclusion_share:206 n: 28207 median: 0.045208 q25: 0.025209 q75: 0.056210 mean: 0.045211 min: 0.013212 max: 0.16213 median_ci95_bootstrap:214 - 0.028215 - 0.054216 theory_share:217 n: 28218 median: 0.0219 q25: 0.0220 q75: 0.131221 mean: 0.063222 min: 0.0223 max: 0.387224 median_ci95_bootstrap:225 - 0.0226 - 0.066227 data_share:228 n: 28229 median: 0.101230 q25: 0.044231 q75: 0.167232 mean: 0.129233 min: 0.0234 max: 0.528235 median_ci95_bootstrap:236 - 0.063237 - 0.141238 results_share:239 n: 28240 median: 0.0241 q25: 0.0242 q75: 0.247243 mean: 0.144244 min: 0.0245 max: 0.611246 median_ci95_bootstrap:247 - 0.0248 - 0.16249 robustness_share:250 n: 28251 median: 0.0252 q25: 0.0253 q75: 0.054254 mean: 0.028255 min: 0.0256 max: 0.165257 median_ci95_bootstrap:258 - 0.0259 - 0.0260 words_per_table:261 n: 28262 median: 1036.909263 q25: 929.825264 q75: 1373.292265 mean: 1249.262266 min: 778.929267 max: 3779.0268 median_ci95_bootstrap:269 - 949.545270 - 1203.778271 refs_per_1000_words:272 n: 28273 median: 4.69274 q25: 3.2275 q75: 5.946276 mean: 4.564277 min: 1.989278 max: 8.143279 median_ci95_bootstrap:280 - 3.678281 - 5.351282 equations_per_1000_words:283 n: 28284 median: 0.43285 q25: 0.184286 q75: 0.706287 mean: 0.599288 min: 0.0289 max: 2.779290 median_ci95_bootstrap:291 - 0.293292 - 0.579293presence:294 has_robustness_section:295 n: 28296 share: 0.286297 has_literature_section:298 n: 28299 share: 0.179300 has_appendix:301 n: 28302 share: 0.25303 has_internet_appendix:304 n: 28305 share: 0.893306by_year:307 2017:308 n: 7309 n_words_body_median: 11336.0310 n_tables_median: 11.0311 2018:312 n: 6313 n_words_body_median: 11215.5314 n_tables_median: 9.5315 2019:316 n: 6317 n_words_body_median: 11487.5318 n_tables_median: 8.5319 2020:320 n: 9321 n_words_body_median: 10703.0322 n_tables_median: 10.0323rhetoric:324 n_annotated: 28325 genre:326 n: 28327 empirical: 0.821328 mixed_theory_empirical: 0.179329 subfield:330 n: 28331 corporate_finance: 1.0332 primary_method:333 n: 28334 reduced_form_regression: 0.464335 difference_in_differences: 0.25336 instrumental_variables: 0.214337 theoretical_model_analytical: 0.036338 regression_discontinuity: 0.036339 abstract_moves_present:340 question:341 n: 28342 share: 0.571343 gap:344 n: 28345 share: 0.107346 method:347 n: 28348 share: 0.786349 results:350 n: 28351 share: 1.0352 magnitude:353 n: 28354 share: 0.286355 contribution:356 n: 28357 share: 0.714358 abstract_move_order_median_sentence:359 question:360 n: 16361 median: 0.0362 q25: 0.0363 q75: 0.0364 mean: 0.312365 min: 0.0366 max: 3.0367 median_ci95_bootstrap:368 - 0.0369 - 0.0370 gap:371 n: 3372 median: 0.0373 q25: 0.0374 q75: 0.5375 mean: 0.333376 min: 0.0377 max: 1.0378 median_ci95_bootstrap:379 - 0.0380 - 0.0381 method:382 n: 22383 median: 1.0384 q25: 0.0385 q75: 1.75386 mean: 0.909387 min: 0.0388 max: 2.0389 median_ci95_bootstrap:390 - 0.0391 - 1.5392 results:393 n: 28394 median: 1.0395 q25: 1.0396 q75: 2.0397 mean: 1.464398 min: 0.0399 max: 3.0400 median_ci95_bootstrap:401 - 1.0402 - 2.0403 magnitude:404 n: 8405 median: 2.0406 q25: 1.0407 q75: 2.0408 mean: 1.625409 min: 0.0410 max: 3.0411 median_ci95_bootstrap:412 - 1.0413 - 2.0414 contribution:415 n: 20416 median: 3.0417 q25: 1.0418 q75: 4.0419 mean: 2.45420 min: 0.0421 max: 7.0422 median_ci95_bootstrap:423 - 1.0424 - 3.5425 abstract_sentences:426 n: 28427 median: 5.0428 q25: 4.0429 q75: 6.0430 mean: 5.75431 min: 3.0432 max: 16.0433 median_ci95_bootstrap:434 - 4.5435 - 6.0436 magnitude_in_abstract_regex:437 n: 28438 share: 0.107439 introduction:440 paragraphs:441 n: 28442 median: 8.0443 q25: 6.0444 q75: 11.0445 mean: 11.143446 min: 4.0447 max: 64.0448 median_ci95_bootstrap:449 - 7.0450 - 9.5451 words:452 n: 28453 median: 1180.0454 q25: 1009.25455 q75: 1353.25456 mean: 1246.607457 min: 808.0458 max: 2477.0459 median_ci95_bootstrap:460 - 1103.425461 - 1322.937462 contribution_paragraph_index:463 n: 25464 median: 6.0465 q25: 4.0466 q75: 9.0467 mean: 8.88468 min: 0.0469 max: 56.0470 median_ci95_bootstrap:471 - 5.0472 - 8.0473 contribution_relative_position:474 n: 25475 median: 0.778476 q25: 0.636477 q75: 0.864478 mean: 0.703479 min: 0.0480 max: 0.941481 median_ci95_bootstrap:482 - 0.75483 - 0.833484 first_move:485 n: 28486 motivation: 0.929487 other: 0.036488 preview_of_approach: 0.036489 common_move_sequences:490 n: 28491 ? motivation > preview_of_approach > identification_defense > mechanism_or_theory_sketch > preview_of_approach > preview_of_results492 > robustness_mention > identification_defense > contribution_statement > related_literature_positioning > other >493 policy_or_broader_implication494 : 0.036495 ? motivation > tension_or_puzzle > related_literature_positioning > literature_gap > preview_of_approach > mechanism_or_theory_sketch496 > preview_of_approach > preview_of_results > robustness_mention > roadmap497 : 0.036498 ? motivation > tension_or_puzzle > preview_of_approach > mechanism_or_theory_sketch > preview_of_results > identification_defense499 > preview_of_results > robustness_mention > contribution_statement > related_literature_positioning > policy_or_broader_implication500 : 0.036501 ? motivation > literature_gap > tension_or_puzzle > contribution_statement > preview_of_approach > identification_defense502 > related_literature_positioning > other503 : 0.036504 ? motivation > literature_gap > identification_defense > preview_of_approach > preview_of_results > identification_defense505 > robustness_mention > identification_defense > preview_of_results > mechanism_or_theory_sketch > contribution_statement506 : 0.036507 ? motivation > mechanism_or_theory_sketch > preview_of_results > identification_defense > robustness_mention > preview_of_results508 > policy_or_broader_implication > roadmap509 : 0.036510 roadmap_present_llm:511 n: 28512 share: 0.571513 roadmap_present_regex:514 n: 28515 share: 0.571516 literature_positioning_location:517 n: 28518 inside_introduction: 0.857519 both: 0.071520 separate_section: 0.071521 contribution_types:522 n: 57523 new_evidence: 0.491524 new_data_or_measure: 0.211525 new_identification: 0.175526 new_theory_or_model: 0.088527 new_method: 0.018528 resolution_of_puzzle: 0.018529 identification:530 causal_language_strength:531 n: 28532 median: 3.0533 q25: 3.0534 q75: 4.0535 mean: 3.25536 min: 1.0537 max: 4.0538 median_ci95_bootstrap:539 - 3.0540 - 4.0541 uses_causal_claim:542 n: 28543 share: 0.857544 results:545 economic_significance_discussed:546 n: 28547 share: 0.929548 statistical_language:549 n: 28550 unclear: 0.929551 stars_and_tstats: 0.071552 magnitude_statements_in_intro:553 n: 28554 share: 0.714555 robustness:556 location:557 n: 28558 mixed: 0.464559 within_results: 0.321560 main_text_section: 0.107561 none_seen: 0.107562 types:563 n: 89564 alternative_specification: 0.236565 alternative_measure: 0.191566 subsample: 0.169567 placebo: 0.112568 other: 0.112569 falsification: 0.101570 alternative_sample_period: 0.034571 ? ''572 : 0.034573 tables:574 standard_errors:575 n: 28576 unclear: 0.964577 clustered: 0.036578 units_in_notes:579 n: 28580 share: 0.893581 clustered_regex:582 n: 28583 share: 0.036584 figures:585 uncertainty_shown:586 n: 28587 unclear: 0.607588 'no': 0.321589 no_figures: 0.036590 mixed: 0.036591 conclusion:592 bounded_claims:593 n: 28594 share: 0.893595 policy_implications:596 n: 28597 share: 0.429598 open_questions:599 n: 28600 share: 0.286601 hedging:602 n: 28603 moderate: 1.0604 claims_with_stated_evidence_share:605 n: 28606 median: 1.0607 q25: 1.0608 q75: 1.0609 mean: 0.988610 min: 0.833611 max: 1.0612 median_ci95_bootstrap:613 - 1.0614 - 1.0615 llm_vs_rule_section_role_agreement:616 n: 28617 median: 0.95618 q25: 0.75619 q75: 1.0620 mean: 0.871621 min: 0.5622 max: 1.0623 median_ci95_bootstrap:624 - 0.8625 - 1.0626 llm_confidence:627 n: 28628 median: 0.8629 q25: 0.8630 q75: 0.812631 mean: 0.813632 min: 0.8633 max: 0.85634 median_ci95_bootstrap:635 - 0.8636 - 0.8637