# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: theoretical_finance
ontology_version: '1.0'
built:
  timestamp: '2026-11-03T23:29:47+00:00'
  code_version: f8b9e5a-dirty
  host:
    platform: macOS-27.0-arm64-arm-64bit
    python: 3.12.13
    machine: arm64
    node: MacBookPro-de-simon-pierre-2.local
selection_rule: genre == theoretical
n_documents: 32
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: 32
    median: 45.0
    q25: 37.75
    q75: 50.5
    mean: 44.562
    min: 22.0
    max: 67.0
    median_ci95_bootstrap:
    - 40.5
    - 50.0
  n_words_body:
    n: 32
    median: 11064.5
    q25: 10315.25
    q75: 13576.5
    mean: 11815.75
    min: 5365.0
    max: 17348.0
    median_ci95_bootstrap:
    - 10653.0
    - 13005.5
  n_words_appendix:
    n: 32
    median: 3030.0
    q25: 2434.5
    q75: 4518.25
    mean: 3596.156
    min: 0.0
    max: 9912.0
    median_ci95_bootstrap:
    - 2738.675
    - 3719.0
  abstract_words:
    n: 32
    median: 102.0
    q25: 96.0
    q75: 104.0
    mean: 112.625
    min: 70.0
    max: 515.0
    median_ci95_bootstrap:
    - 97.0
    - 103.0
  n_sections:
    n: 32
    median: 6.0
    q25: 5.0
    q75: 6.25
    mean: 5.812
    min: 4.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 32
    median: 17.0
    q25: 11.0
    q75: 28.5
    mean: 19.625
    min: 6.0
    max: 46.0
    median_ci95_bootstrap:
    - 12.5
    - 24.762
  n_paragraphs:
    n: 32
    median: 409.0
    q25: 298.75
    q75: 618.75
    mean: 441.562
    min: 136.0
    max: 920.0
    median_ci95_bootstrap:
    - 331.5
    - 544.0
  n_equations:
    n: 32
    median: 36.0
    q25: 21.75
    q75: 62.75
    mean: 46.906
    min: 1.0
    max: 159.0
    median_ci95_bootstrap:
    - 24.0
    - 44.525
  n_tables:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 2.0
    mean: 1.25
    min: 0.0
    max: 7.0
    median_ci95_bootstrap:
    - 0.0
    - 1.0
  n_figures:
    n: 32
    median: 4.5
    q25: 2.75
    q75: 7.0
    mean: 4.969
    min: 0.0
    max: 12.0
    median_ci95_bootstrap:
    - 3.0
    - 6.0
  n_footnotes:
    n: 32
    median: 49.5
    q25: 40.5
    q75: 64.5
    mean: 52.344
    min: 19.0
    max: 107.0
    median_ci95_bootstrap:
    - 44.0
    - 59.0
  n_references:
    n: 32
    median: 45.0
    q25: 38.0
    q75: 63.5
    mean: 50.75
    min: 20.0
    max: 87.0
    median_ci95_bootstrap:
    - 39.0
    - 55.0
  n_citations_in_text:
    n: 32
    median: 44.5
    q25: 39.0
    q75: 68.0
    mean: 51.406
    min: 12.0
    max: 108.0
    median_ci95_bootstrap:
    - 41.0
    - 55.0
  intro_words:
    n: 32
    median: 1895.5
    q25: 1672.75
    q75: 2359.0
    mean: 2013.219
    min: 1024.0
    max: 3245.0
    median_ci95_bootstrap:
    - 1763.5
    - 2157.25
  intro_paragraphs:
    n: 32
    median: 8.0
    q25: 4.75
    q75: 9.0
    mean: 7.344
    min: 1.0
    max: 17.0
    median_ci95_bootstrap:
    - 7.0
    - 9.0
  intro_share:
    n: 32
    median: 0.163
    q25: 0.134
    q75: 0.216
    mean: 0.175
    min: 0.092
    max: 0.301
    median_ci95_bootstrap:
    - 0.15
    - 0.182
  conclusion_words:
    n: 32
    median: 317.5
    q25: 159.25
    q75: 478.25
    mean: 463.469
    min: 54.0
    max: 2353.0
    median_ci95_bootstrap:
    - 255.475
    - 427.812
  conclusion_share:
    n: 32
    median: 0.027
    q25: 0.015
    q75: 0.042
    mean: 0.042
    min: 0.005
    max: 0.237
    median_ci95_bootstrap:
    - 0.019
    - 0.035
  theory_share:
    n: 32
    median: 0.296
    q25: 0.168
    q75: 0.491
    mean: 0.326
    min: 0.0
    max: 0.698
    median_ci95_bootstrap:
    - 0.199
    - 0.429
  data_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.0
    mean: 0.0
    min: 0.0
    max: 0.0
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  results_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.0
    mean: 0.038
    min: 0.0
    max: 0.341
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  robustness_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.14
    mean: 0.079
    min: 0.0
    max: 0.344
    median_ci95_bootstrap:
    - 0.0
    - 0.079
  words_per_table:
    n: 32
    median: 10291.5
    q25: 5694.25
    q75: 12018.0
    mean: 9303.593
    min: 1199.0
    max: 17169.0
    median_ci95_bootstrap:
    - 7538.337
    - 11003.0
  refs_per_1000_words:
    n: 32
    median: 4.528
    q25: 3.225
    q75: 5.327
    mean: 4.39
    min: 1.683
    max: 7.692
    median_ci95_bootstrap:
    - 3.848
    - 5.087
  equations_per_1000_words:
    n: 32
    median: 3.075
    q25: 1.776
    q75: 5.812
    mean: 4.058
    min: 0.065
    max: 10.174
    median_ci95_bootstrap:
    - 2.271
    - 5.465
presence:
  has_robustness_section:
    n: 32
    share: 0.438
  has_literature_section:
    n: 32
    share: 0.188
  has_appendix:
    n: 32
    share: 0.875
  has_internet_appendix:
    n: 32
    share: 0.719
by_year:
  2017:
    n: 6
    n_words_body_median: 10824.5
    n_tables_median: 1.0
  2018:
    n: 7
    n_words_body_median: 14262.0
    n_tables_median: 0.0
  2019:
    n: 9
    n_words_body_median: 11016.0
    n_tables_median: 0.0
  2020:
    n: 10
    n_words_body_median: 10778.5
    n_tables_median: 0.0
rhetoric:
  n_annotated: 32
  genre:
    n: 32
    theoretical: 1.0
  subfield:
    n: 32
    corporate_finance: 0.25
    asset_pricing: 0.219
    financial_intermediation_banking: 0.188
    macro_finance: 0.156
    market_microstructure: 0.125
    behavioral_finance: 0.031
    entrepreneurial_finance_private_equity: 0.031
  primary_method:
    n: 32
    theoretical_model_analytical: 0.875
    calibration_simulation: 0.125
  abstract_moves_present:
    question:
      n: 32
      share: 0.719
    gap:
      n: 32
      share: 0.0
    method:
      n: 32
      share: 0.875
    results:
      n: 32
      share: 1.0
    magnitude:
      n: 32
      share: 0.0
    contribution:
      n: 32
      share: 0.812
  abstract_move_order_median_sentence:
    question:
      n: 23
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.13
      min: 0.0
      max: 2.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 0
    method:
      n: 28
      median: 0.0
      q25: 0.0
      q75: 1.0
      mean: 0.679
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 1.0
    results:
      n: 32
      median: 1.5
      q25: 1.0
      q75: 3.0
      mean: 1.906
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 1.0
      - 3.0
    magnitude:
      n: 0
    contribution:
      n: 26
      median: 2.5
      q25: 0.0
      q75: 4.0
      mean: 2.154
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 0.5
      - 4.0
  abstract_sentences:
    n: 32
    median: 5.0
    q25: 5.0
    q75: 6.0
    mean: 5.562
    min: 4.0
    max: 16.0
    median_ci95_bootstrap:
    - 5.0
    - 5.0
  magnitude_in_abstract_regex:
    n: 32
    share: 0.0
  introduction:
    paragraphs:
      n: 32
      median: 8.0
      q25: 4.75
      q75: 9.0
      mean: 7.344
      min: 1.0
      max: 17.0
      median_ci95_bootstrap:
      - 7.0
      - 9.0
    words:
      n: 32
      median: 1086.0
      q25: 822.75
      q75: 1270.75
      mean: 1035.938
      min: 213.0
      max: 1815.0
      median_ci95_bootstrap:
      - 891.0
      - 1232.5
    contribution_paragraph_index:
      n: 30
      median: 2.0
      q25: 0.0
      q75: 5.0
      mean: 2.8
      min: 0.0
      max: 9.0
      median_ci95_bootstrap:
      - 0.0
      - 4.5
    contribution_relative_position:
      n: 30
      median: 0.402
      q25: 0.0
      q75: 0.656
      mean: 0.354
      min: 0.0
      max: 0.9
      median_ci95_bootstrap:
      - 0.0
      - 0.56
    first_move:
      n: 32
      motivation: 0.875
      preview_of_approach: 0.062
      contribution_statement: 0.031
      tension_or_puzzle: 0.031
    move_prevalence:
      n: 32
      mechanism_or_theory_sketch:
        share: 0.938
        median_relative_position: 0.3
      motivation:
        share: 0.906
        median_relative_position: 0.0
      preview_of_results:
        share: 0.875
        median_relative_position: 0.39
      related_literature_positioning:
        share: 0.844
        median_relative_position: 0.7
      preview_of_approach:
        share: 0.844
        median_relative_position: 0.18
      contribution_statement:
        share: 0.562
        median_relative_position: 0.63
      roadmap:
        share: 0.5
        median_relative_position: 1.0
      policy_or_broader_implication:
        share: 0.5
        median_relative_position: 0.72
      tension_or_puzzle:
        share: 0.406
        median_relative_position: 0.09
      literature_gap:
        share: 0.219
        median_relative_position: 0.15
      other:
        share: 0.156
        median_relative_position: 0.7
      robustness_mention:
        share: 0.031
        median_relative_position: 1.0
    moves_per_intro:
      n: 32
      median: 11.0
      q25: 8.75
      q75: 13.0
      mean: 10.594
      min: 2.0
      max: 19.0
      median_ci95_bootstrap:
      - 10.0
      - 12.0
    common_move_sequences:
      n: 32
      ? motivation > tension_or_puzzle > contribution_statement > mechanism_or_theory_sketch > preview_of_approach > motivation
        > related_literature_positioning > preview_of_results > related_literature_positioning > roadmap
      : 0.031
      ? motivation > tension_or_puzzle > preview_of_approach > preview_of_results > policy_or_broader_implication > mechanism_or_theory_sketch
        > policy_or_broader_implication > contribution_statement > related_literature_positioning > literature_gap
      : 0.031
      ? motivation > preview_of_approach > motivation > preview_of_results > mechanism_or_theory_sketch > preview_of_results
        > policy_or_broader_implication > related_literature_positioning > roadmap
      : 0.031
      preview_of_approach > mechanism_or_theory_sketch > preview_of_results: 0.031
      ? motivation > tension_or_puzzle > preview_of_approach > mechanism_or_theory_sketch > other > mechanism_or_theory_sketch
        > preview_of_approach > preview_of_results > policy_or_broader_implication > preview_of_approach > preview_of_results
        > related_literature_positioning > roadmap
      : 0.031
      ? motivation > preview_of_approach > mechanism_or_theory_sketch > motivation > preview_of_results > related_literature_positioning
        > preview_of_results > policy_or_broader_implication > related_literature_positioning > contribution_statement > robustness_mention
      : 0.031
    roadmap_present_llm:
      n: 32
      share: 0.531
    roadmap_present_regex:
      n: 32
      share: 0.5
    literature_positioning_location:
      n: 32
      inside_introduction: 0.844
      both: 0.094
      separate_section: 0.062
    contribution_types:
      n: 40
      new_theory_or_model: 0.8
      resolution_of_puzzle: 0.15
      new_method: 0.05
  identification:
    causal_language_strength:
      n: 32
      median: 1.0
      q25: 1.0
      q75: 1.25
      mean: 1.594
      min: 1.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 1.0
    uses_causal_claim:
      n: 32
      share: 0.125
  results:
    economic_significance_discussed:
      n: 32
      share: 0.25
    statistical_language:
      n: 32
      unclear: 1.0
    magnitude_statements_in_intro:
      n: 32
      share: 0.062
  robustness:
    location:
      n: 32
      none_seen: 0.406
      main_text_section: 0.25
      mixed: 0.156
      appendix: 0.125
      internet_appendix: 0.031
      within_results: 0.031
    types:
      n: 40
      other: 0.4
      ? ''
      : 0.325
      sensitivity_to_parameters: 0.175
      alternative_specification: 0.1
  tables:
    standard_errors:
      n: 32
      none: 1.0
    units_in_notes:
      n: 32
      share: 0.125
    clustered_regex:
      n: 32
      share: 0.0
  figures:
    uncertainty_shown:
      n: 32
      'no': 0.812
      no_figures: 0.125
      mixed: 0.031
      unclear: 0.031
  conclusion:
    bounded_claims:
      n: 32
      share: 0.812
    policy_implications:
      n: 32
      share: 0.469
    open_questions:
      n: 32
      share: 0.281
  hedging:
    n: 32
    moderate: 0.688
    low: 0.312
  claims_with_stated_evidence_share:
    n: 32
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.989
    min: 0.8
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 32
    median: 1.0
    q25: 0.833
    q75: 1.0
    mean: 0.924
    min: 0.667
    max: 1.0
    median_ci95_bootstrap:
    - 0.857
    - 1.0
  llm_confidence:
    n: 32
    median: 0.85
    q25: 0.85
    q75: 0.85
    mean: 0.842
    min: 0.75
    max: 0.88
    median_ci95_bootstrap:
    - 0.85
    - 0.85