1# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)2profile: theoretical_finance3ontology_version: '1.0'4built:5 timestamp: '2026-11-03T23:29:47+00:00'6 code_version: f8b9e5a-dirty7 host:8 platform: macOS-27.0-arm64-arm-64bit9 python: 3.12.1310 machine: arm6411 node: MacBookPro-de-simon-pierre-2.local12selection_rule: genre == theoretical13n_documents: 3214split: 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: 3220 median: 45.021 q25: 37.7522 q75: 50.523 mean: 44.56224 min: 22.025 max: 67.026 median_ci95_bootstrap:27 - 40.528 - 50.029 n_words_body:30 n: 3231 median: 11064.532 q25: 10315.2533 q75: 13576.534 mean: 11815.7535 min: 5365.036 max: 17348.037 median_ci95_bootstrap:38 - 10653.039 - 13005.540 n_words_appendix:41 n: 3242 median: 3030.043 q25: 2434.544 q75: 4518.2545 mean: 3596.15646 min: 0.047 max: 9912.048 median_ci95_bootstrap:49 - 2738.67550 - 3719.051 abstract_words:52 n: 3253 median: 102.054 q25: 96.055 q75: 104.056 mean: 112.62557 min: 70.058 max: 515.059 median_ci95_bootstrap:60 - 97.061 - 103.062 n_sections:63 n: 3264 median: 6.065 q25: 5.066 q75: 6.2567 mean: 5.81268 min: 4.069 max: 9.070 median_ci95_bootstrap:71 - 5.072 - 6.073 n_subsections:74 n: 3275 median: 17.076 q25: 11.077 q75: 28.578 mean: 19.62579 min: 6.080 max: 46.081 median_ci95_bootstrap:82 - 12.583 - 24.76284 n_paragraphs:85 n: 3286 median: 409.087 q25: 298.7588 q75: 618.7589 mean: 441.56290 min: 136.091 max: 920.092 median_ci95_bootstrap:93 - 331.594 - 544.095 n_equations:96 n: 3297 median: 36.098 q25: 21.7599 q75: 62.75100 mean: 46.906101 min: 1.0102 max: 159.0103 median_ci95_bootstrap:104 - 24.0105 - 44.525106 n_tables:107 n: 32108 median: 0.0109 q25: 0.0110 q75: 2.0111 mean: 1.25112 min: 0.0113 max: 7.0114 median_ci95_bootstrap:115 - 0.0116 - 1.0117 n_figures:118 n: 32119 median: 4.5120 q25: 2.75121 q75: 7.0122 mean: 4.969123 min: 0.0124 max: 12.0125 median_ci95_bootstrap:126 - 3.0127 - 6.0128 n_footnotes:129 n: 32130 median: 49.5131 q25: 40.5132 q75: 64.5133 mean: 52.344134 min: 19.0135 max: 107.0136 median_ci95_bootstrap:137 - 44.0138 - 59.0139 n_references:140 n: 32141 median: 45.0142 q25: 38.0143 q75: 63.5144 mean: 50.75145 min: 20.0146 max: 87.0147 median_ci95_bootstrap:148 - 39.0149 - 55.0150 n_citations_in_text:151 n: 32152 median: 44.5153 q25: 39.0154 q75: 68.0155 mean: 51.406156 min: 12.0157 max: 108.0158 median_ci95_bootstrap:159 - 41.0160 - 55.0161 intro_words:162 n: 32163 median: 1895.5164 q25: 1672.75165 q75: 2359.0166 mean: 2013.219167 min: 1024.0168 max: 3245.0169 median_ci95_bootstrap:170 - 1763.5171 - 2157.25172 intro_paragraphs:173 n: 32174 median: 8.0175 q25: 4.75176 q75: 9.0177 mean: 7.344178 min: 1.0179 max: 17.0180 median_ci95_bootstrap:181 - 7.0182 - 9.0183 intro_share:184 n: 32185 median: 0.163186 q25: 0.134187 q75: 0.216188 mean: 0.175189 min: 0.092190 max: 0.301191 median_ci95_bootstrap:192 - 0.15193 - 0.182194 conclusion_words:195 n: 32196 median: 317.5197 q25: 159.25198 q75: 478.25199 mean: 463.469200 min: 54.0201 max: 2353.0202 median_ci95_bootstrap:203 - 255.475204 - 427.812205 conclusion_share:206 n: 32207 median: 0.027208 q25: 0.015209 q75: 0.042210 mean: 0.042211 min: 0.005212 max: 0.237213 median_ci95_bootstrap:214 - 0.019215 - 0.035216 theory_share:217 n: 32218 median: 0.296219 q25: 0.168220 q75: 0.491221 mean: 0.326222 min: 0.0223 max: 0.698224 median_ci95_bootstrap:225 - 0.199226 - 0.429227 data_share:228 n: 32229 median: 0.0230 q25: 0.0231 q75: 0.0232 mean: 0.0233 min: 0.0234 max: 0.0235 median_ci95_bootstrap:236 - 0.0237 - 0.0238 results_share:239 n: 32240 median: 0.0241 q25: 0.0242 q75: 0.0243 mean: 0.038244 min: 0.0245 max: 0.341246 median_ci95_bootstrap:247 - 0.0248 - 0.0249 robustness_share:250 n: 32251 median: 0.0252 q25: 0.0253 q75: 0.14254 mean: 0.079255 min: 0.0256 max: 0.344257 median_ci95_bootstrap:258 - 0.0259 - 0.079260 words_per_table:261 n: 32262 median: 10291.5263 q25: 5694.25264 q75: 12018.0265 mean: 9303.593266 min: 1199.0267 max: 17169.0268 median_ci95_bootstrap:269 - 7538.337270 - 11003.0271 refs_per_1000_words:272 n: 32273 median: 4.528274 q25: 3.225275 q75: 5.327276 mean: 4.39277 min: 1.683278 max: 7.692279 median_ci95_bootstrap:280 - 3.848281 - 5.087282 equations_per_1000_words:283 n: 32284 median: 3.075285 q25: 1.776286 q75: 5.812287 mean: 4.058288 min: 0.065289 max: 10.174290 median_ci95_bootstrap:291 - 2.271292 - 5.465293presence:294 has_robustness_section:295 n: 32296 share: 0.438297 has_literature_section:298 n: 32299 share: 0.188300 has_appendix:301 n: 32302 share: 0.875303 has_internet_appendix:304 n: 32305 share: 0.719306by_year:307 2017:308 n: 6309 n_words_body_median: 10824.5310 n_tables_median: 1.0311 2018:312 n: 7313 n_words_body_median: 14262.0314 n_tables_median: 0.0315 2019:316 n: 9317 n_words_body_median: 11016.0318 n_tables_median: 0.0319 2020:320 n: 10321 n_words_body_median: 10778.5322 n_tables_median: 0.0323rhetoric:324 n_annotated: 32325 genre:326 n: 32327 theoretical: 1.0328 subfield:329 n: 32330 corporate_finance: 0.25331 asset_pricing: 0.219332 financial_intermediation_banking: 0.188333 macro_finance: 0.156334 market_microstructure: 0.125335 behavioral_finance: 0.031336 entrepreneurial_finance_private_equity: 0.031337 primary_method:338 n: 32339 theoretical_model_analytical: 0.875340 calibration_simulation: 0.125341 abstract_moves_present:342 question:343 n: 32344 share: 0.719345 gap:346 n: 32347 share: 0.0348 method:349 n: 32350 share: 0.875351 results:352 n: 32353 share: 1.0354 magnitude:355 n: 32356 share: 0.0357 contribution:358 n: 32359 share: 0.812360 abstract_move_order_median_sentence:361 question:362 n: 23363 median: 0.0364 q25: 0.0365 q75: 0.0366 mean: 0.13367 min: 0.0368 max: 2.0369 median_ci95_bootstrap:370 - 0.0371 - 0.0372 gap:373 n: 0374 method:375 n: 28376 median: 0.0377 q25: 0.0378 q75: 1.0379 mean: 0.679380 min: 0.0381 max: 4.0382 median_ci95_bootstrap:383 - 0.0384 - 1.0385 results:386 n: 32387 median: 1.5388 q25: 1.0389 q75: 3.0390 mean: 1.906391 min: 0.0392 max: 5.0393 median_ci95_bootstrap:394 - 1.0395 - 3.0396 magnitude:397 n: 0398 contribution:399 n: 26400 median: 2.5401 q25: 0.0402 q75: 4.0403 mean: 2.154404 min: 0.0405 max: 5.0406 median_ci95_bootstrap:407 - 0.5408 - 4.0409 abstract_sentences:410 n: 32411 median: 5.0412 q25: 5.0413 q75: 6.0414 mean: 5.562415 min: 4.0416 max: 16.0417 median_ci95_bootstrap:418 - 5.0419 - 5.0420 magnitude_in_abstract_regex:421 n: 32422 share: 0.0423 introduction:424 paragraphs:425 n: 32426 median: 8.0427 q25: 4.75428 q75: 9.0429 mean: 7.344430 min: 1.0431 max: 17.0432 median_ci95_bootstrap:433 - 7.0434 - 9.0435 words:436 n: 32437 median: 1086.0438 q25: 822.75439 q75: 1270.75440 mean: 1035.938441 min: 213.0442 max: 1815.0443 median_ci95_bootstrap:444 - 891.0445 - 1232.5446 contribution_paragraph_index:447 n: 30448 median: 2.0449 q25: 0.0450 q75: 5.0451 mean: 2.8452 min: 0.0453 max: 9.0454 median_ci95_bootstrap:455 - 0.0456 - 4.5457 contribution_relative_position:458 n: 30459 median: 0.402460 q25: 0.0461 q75: 0.656462 mean: 0.354463 min: 0.0464 max: 0.9465 median_ci95_bootstrap:466 - 0.0467 - 0.56468 first_move:469 n: 32470 motivation: 0.875471 preview_of_approach: 0.062472 contribution_statement: 0.031473 tension_or_puzzle: 0.031474 move_prevalence:475 n: 32476 mechanism_or_theory_sketch:477 share: 0.938478 median_relative_position: 0.3479 motivation:480 share: 0.906481 median_relative_position: 0.0482 preview_of_results:483 share: 0.875484 median_relative_position: 0.39485 related_literature_positioning:486 share: 0.844487 median_relative_position: 0.7488 preview_of_approach:489 share: 0.844490 median_relative_position: 0.18491 contribution_statement:492 share: 0.562493 median_relative_position: 0.63494 roadmap:495 share: 0.5496 median_relative_position: 1.0497 policy_or_broader_implication:498 share: 0.5499 median_relative_position: 0.72500 tension_or_puzzle:501 share: 0.406502 median_relative_position: 0.09503 literature_gap:504 share: 0.219505 median_relative_position: 0.15506 other:507 share: 0.156508 median_relative_position: 0.7509 robustness_mention:510 share: 0.031511 median_relative_position: 1.0512 moves_per_intro:513 n: 32514 median: 11.0515 q25: 8.75516 q75: 13.0517 mean: 10.594518 min: 2.0519 max: 19.0520 median_ci95_bootstrap:521 - 10.0522 - 12.0523 common_move_sequences:524 n: 32525 ? motivation > tension_or_puzzle > contribution_statement > mechanism_or_theory_sketch > preview_of_approach > motivation526 > related_literature_positioning > preview_of_results > related_literature_positioning > roadmap527 : 0.031528 ? motivation > tension_or_puzzle > preview_of_approach > preview_of_results > policy_or_broader_implication > mechanism_or_theory_sketch529 > policy_or_broader_implication > contribution_statement > related_literature_positioning > literature_gap530 : 0.031531 ? motivation > preview_of_approach > motivation > preview_of_results > mechanism_or_theory_sketch > preview_of_results532 > policy_or_broader_implication > related_literature_positioning > roadmap533 : 0.031534 preview_of_approach > mechanism_or_theory_sketch > preview_of_results: 0.031535 ? motivation > tension_or_puzzle > preview_of_approach > mechanism_or_theory_sketch > other > mechanism_or_theory_sketch536 > preview_of_approach > preview_of_results > policy_or_broader_implication > preview_of_approach > preview_of_results537 > related_literature_positioning > roadmap538 : 0.031539 ? motivation > preview_of_approach > mechanism_or_theory_sketch > motivation > preview_of_results > related_literature_positioning540 > preview_of_results > policy_or_broader_implication > related_literature_positioning > contribution_statement > robustness_mention541 : 0.031542 roadmap_present_llm:543 n: 32544 share: 0.531545 roadmap_present_regex:546 n: 32547 share: 0.5548 literature_positioning_location:549 n: 32550 inside_introduction: 0.844551 both: 0.094552 separate_section: 0.062553 contribution_types:554 n: 40555 new_theory_or_model: 0.8556 resolution_of_puzzle: 0.15557 new_method: 0.05558 identification:559 causal_language_strength:560 n: 32561 median: 1.0562 q25: 1.0563 q75: 1.25564 mean: 1.594565 min: 1.0566 max: 4.0567 median_ci95_bootstrap:568 - 1.0569 - 1.0570 uses_causal_claim:571 n: 32572 share: 0.125573 results:574 economic_significance_discussed:575 n: 32576 share: 0.25577 statistical_language:578 n: 32579 unclear: 1.0580 magnitude_statements_in_intro:581 n: 32582 share: 0.062583 robustness:584 location:585 n: 32586 none_seen: 0.406587 main_text_section: 0.25588 mixed: 0.156589 appendix: 0.125590 internet_appendix: 0.031591 within_results: 0.031592 types:593 n: 40594 other: 0.4595 ? ''596 : 0.325597 sensitivity_to_parameters: 0.175598 alternative_specification: 0.1599 tables:600 standard_errors:601 n: 32602 none: 1.0603 units_in_notes:604 n: 32605 share: 0.125606 clustered_regex:607 n: 32608 share: 0.0609 figures:610 uncertainty_shown:611 n: 32612 'no': 0.812613 no_figures: 0.125614 mixed: 0.031615 unclear: 0.031616 conclusion:617 bounded_claims:618 n: 32619 share: 0.812620 policy_implications:621 n: 32622 share: 0.469623 open_questions:624 n: 32625 share: 0.281626 hedging:627 n: 32628 moderate: 0.688629 low: 0.312630 claims_with_stated_evidence_share:631 n: 32632 median: 1.0633 q25: 1.0634 q75: 1.0635 mean: 0.989636 min: 0.8637 max: 1.0638 median_ci95_bootstrap:639 - 1.0640 - 1.0641 llm_vs_rule_section_role_agreement:642 n: 32643 median: 1.0644 q25: 0.833645 q75: 1.0646 mean: 0.924647 min: 0.667648 max: 1.0649 median_ci95_bootstrap:650 - 0.857651 - 1.0652 llm_confidence:653 n: 32654 median: 0.85655 q25: 0.85656 q75: 0.85657 mean: 0.842658 min: 0.75659 max: 0.88660 median_ci95_bootstrap:661 - 0.85662 - 0.85663