# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: corporate_finance
ontology_version: '1.0'
built:
  timestamp: '2026-11-03T23:29:46+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: annotation.subfield == corporate_finance and genre in {empirical, mixed_theory_empirical}
n_documents: 28
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: 28
    median: 42.5
    q25: 39.0
    q75: 46.25
    mean: 43.75
    min: 35.0
    max: 60.0
    median_ci95_bootstrap:
    - 39.237
    - 45.0
  n_words_body:
    n: 28
    median: 11150.5
    q25: 10414.75
    q75: 11549.5
    mean: 11186.429
    min: 7845.0
    max: 15116.0
    median_ci95_bootstrap:
    - 10597.0
    - 11464.763
  n_words_appendix:
    n: 28
    median: 0.0
    q25: 0.0
    q75: 5.75
    mean: 422.143
    min: 0.0
    max: 3982.0
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  abstract_words:
    n: 28
    median: 100.5
    q25: 96.75
    q75: 103.0
    mean: 128.0
    min: 83.0
    max: 535.0
    median_ci95_bootstrap:
    - 97.5
    - 102.5
  n_sections:
    n: 28
    median: 6.0
    q25: 5.0
    q75: 6.25
    mean: 5.714
    min: 3.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 28
    median: 12.0
    q25: 10.5
    q75: 19.0
    mean: 14.357
    min: 4.0
    max: 36.0
    median_ci95_bootstrap:
    - 11.0
    - 16.0
  n_paragraphs:
    n: 28
    median: 91.0
    q25: 76.25
    q75: 117.25
    mean: 103.393
    min: 51.0
    max: 203.0
    median_ci95_bootstrap:
    - 80.0
    - 108.0
  n_equations:
    n: 28
    median: 5.0
    q25: 2.0
    q75: 8.25
    mean: 6.964
    min: 0.0
    max: 42.0
    median_ci95_bootstrap:
    - 3.0
    - 6.5
  n_tables:
    n: 28
    median: 10.0
    q25: 8.0
    q75: 12.0
    mean: 9.893
    min: 4.0
    max: 14.0
    median_ci95_bootstrap:
    - 9.0
    - 11.0
  n_figures:
    n: 28
    median: 3.0
    q25: 2.0
    q75: 5.25
    mean: 3.429
    min: 0.0
    max: 8.0
    median_ci95_bootstrap:
    - 2.0
    - 4.0
  n_footnotes:
    n: 28
    median: 36.5
    q25: 26.75
    q75: 41.25
    mean: 36.357
    min: 15.0
    max: 62.0
    median_ci95_bootstrap:
    - 30.5
    - 40.0
  n_references:
    n: 28
    median: 49.5
    q25: 35.75
    q75: 59.0
    mean: 50.857
    min: 19.0
    max: 115.0
    median_ci95_bootstrap:
    - 41.5
    - 57.0
  n_citations_in_text:
    n: 28
    median: 48.0
    q25: 30.5
    q75: 66.5
    mean: 54.321
    min: 18.0
    max: 148.0
    median_ci95_bootstrap:
    - 31.238
    - 63.525
  intro_words:
    n: 28
    median: 1927.0
    q25: 1738.25
    q75: 2119.25
    mean: 1937.143
    min: 1275.0
    max: 2758.0
    median_ci95_bootstrap:
    - 1837.0
    - 2019.5
  intro_paragraphs:
    n: 28
    median: 8.0
    q25: 6.0
    q75: 11.0
    mean: 11.143
    min: 4.0
    max: 64.0
    median_ci95_bootstrap:
    - 7.0
    - 9.5
  intro_share:
    n: 28
    median: 0.175
    q25: 0.154
    q75: 0.195
    mean: 0.175
    min: 0.105
    max: 0.242
    median_ci95_bootstrap:
    - 0.161
    - 0.191
  conclusion_words:
    n: 28
    median: 459.5
    q25: 268.0
    q75: 621.5
    mean: 508.714
    min: 142.0
    max: 2063.0
    median_ci95_bootstrap:
    - 308.588
    - 575.0
  conclusion_share:
    n: 28
    median: 0.045
    q25: 0.025
    q75: 0.056
    mean: 0.045
    min: 0.013
    max: 0.16
    median_ci95_bootstrap:
    - 0.028
    - 0.054
  theory_share:
    n: 28
    median: 0.0
    q25: 0.0
    q75: 0.131
    mean: 0.063
    min: 0.0
    max: 0.387
    median_ci95_bootstrap:
    - 0.0
    - 0.066
  data_share:
    n: 28
    median: 0.101
    q25: 0.044
    q75: 0.167
    mean: 0.129
    min: 0.0
    max: 0.528
    median_ci95_bootstrap:
    - 0.063
    - 0.141
  results_share:
    n: 28
    median: 0.0
    q25: 0.0
    q75: 0.247
    mean: 0.144
    min: 0.0
    max: 0.611
    median_ci95_bootstrap:
    - 0.0
    - 0.16
  robustness_share:
    n: 28
    median: 0.0
    q25: 0.0
    q75: 0.054
    mean: 0.028
    min: 0.0
    max: 0.165
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  words_per_table:
    n: 28
    median: 1036.909
    q25: 929.825
    q75: 1373.292
    mean: 1249.262
    min: 778.929
    max: 3779.0
    median_ci95_bootstrap:
    - 949.545
    - 1203.778
  refs_per_1000_words:
    n: 28
    median: 4.69
    q25: 3.2
    q75: 5.946
    mean: 4.564
    min: 1.989
    max: 8.143
    median_ci95_bootstrap:
    - 3.678
    - 5.351
  equations_per_1000_words:
    n: 28
    median: 0.43
    q25: 0.184
    q75: 0.706
    mean: 0.599
    min: 0.0
    max: 2.779
    median_ci95_bootstrap:
    - 0.293
    - 0.579
presence:
  has_robustness_section:
    n: 28
    share: 0.286
  has_literature_section:
    n: 28
    share: 0.179
  has_appendix:
    n: 28
    share: 0.25
  has_internet_appendix:
    n: 28
    share: 0.893
by_year:
  2017:
    n: 7
    n_words_body_median: 11336.0
    n_tables_median: 11.0
  2018:
    n: 6
    n_words_body_median: 11215.5
    n_tables_median: 9.5
  2019:
    n: 6
    n_words_body_median: 11487.5
    n_tables_median: 8.5
  2020:
    n: 9
    n_words_body_median: 10703.0
    n_tables_median: 10.0
rhetoric:
  n_annotated: 28
  genre:
    n: 28
    empirical: 0.821
    mixed_theory_empirical: 0.179
  subfield:
    n: 28
    corporate_finance: 1.0
  primary_method:
    n: 28
    reduced_form_regression: 0.464
    difference_in_differences: 0.25
    instrumental_variables: 0.214
    theoretical_model_analytical: 0.036
    regression_discontinuity: 0.036
  abstract_moves_present:
    question:
      n: 28
      share: 0.571
    gap:
      n: 28
      share: 0.107
    method:
      n: 28
      share: 0.786
    results:
      n: 28
      share: 1.0
    magnitude:
      n: 28
      share: 0.286
    contribution:
      n: 28
      share: 0.714
  abstract_move_order_median_sentence:
    question:
      n: 16
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.312
      min: 0.0
      max: 3.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 3
      median: 0.0
      q25: 0.0
      q75: 0.5
      mean: 0.333
      min: 0.0
      max: 1.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    method:
      n: 22
      median: 1.0
      q25: 0.0
      q75: 1.75
      mean: 0.909
      min: 0.0
      max: 2.0
      median_ci95_bootstrap:
      - 0.0
      - 1.5
    results:
      n: 28
      median: 1.0
      q25: 1.0
      q75: 2.0
      mean: 1.464
      min: 0.0
      max: 3.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    magnitude:
      n: 8
      median: 2.0
      q25: 1.0
      q75: 2.0
      mean: 1.625
      min: 0.0
      max: 3.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    contribution:
      n: 20
      median: 3.0
      q25: 1.0
      q75: 4.0
      mean: 2.45
      min: 0.0
      max: 7.0
      median_ci95_bootstrap:
      - 1.0
      - 3.5
  abstract_sentences:
    n: 28
    median: 5.0
    q25: 4.0
    q75: 6.0
    mean: 5.75
    min: 3.0
    max: 16.0
    median_ci95_bootstrap:
    - 4.5
    - 6.0
  magnitude_in_abstract_regex:
    n: 28
    share: 0.107
  introduction:
    paragraphs:
      n: 28
      median: 8.0
      q25: 6.0
      q75: 11.0
      mean: 11.143
      min: 4.0
      max: 64.0
      median_ci95_bootstrap:
      - 7.0
      - 9.5
    words:
      n: 28
      median: 1180.0
      q25: 1009.25
      q75: 1353.25
      mean: 1246.607
      min: 808.0
      max: 2477.0
      median_ci95_bootstrap:
      - 1103.425
      - 1322.937
    contribution_paragraph_index:
      n: 25
      median: 6.0
      q25: 4.0
      q75: 9.0
      mean: 8.88
      min: 0.0
      max: 56.0
      median_ci95_bootstrap:
      - 5.0
      - 8.0
    contribution_relative_position:
      n: 25
      median: 0.778
      q25: 0.636
      q75: 0.864
      mean: 0.703
      min: 0.0
      max: 0.941
      median_ci95_bootstrap:
      - 0.75
      - 0.833
    first_move:
      n: 28
      motivation: 0.929
      other: 0.036
      preview_of_approach: 0.036
    move_prevalence:
      n: 28
      motivation:
        share: 0.964
        median_relative_position: 0.0
      preview_of_results:
        share: 0.964
        median_relative_position: 0.3
      related_literature_positioning:
        share: 0.857
        median_relative_position: 0.78
      preview_of_approach:
        share: 0.857
        median_relative_position: 0.23
      contribution_statement:
        share: 0.821
        median_relative_position: 0.83
      identification_defense:
        share: 0.786
        median_relative_position: 0.45
      mechanism_or_theory_sketch:
        share: 0.679
        median_relative_position: 0.28
      literature_gap:
        share: 0.679
        median_relative_position: 0.1
      roadmap:
        share: 0.571
        median_relative_position: 1.0
      policy_or_broader_implication:
        share: 0.536
        median_relative_position: 0.91
      robustness_mention:
        share: 0.464
        median_relative_position: 0.7
      tension_or_puzzle:
        share: 0.429
        median_relative_position: 0.11
      other:
        share: 0.179
        median_relative_position: 0.91
    moves_per_intro:
      n: 28
      median: 12.0
      q25: 11.0
      q75: 14.0
      mean: 12.679
      min: 7.0
      max: 23.0
      median_ci95_bootstrap:
      - 11.5
      - 13.0
    common_move_sequences:
      n: 28
      ? motivation > preview_of_approach > identification_defense > mechanism_or_theory_sketch > preview_of_approach > preview_of_results
        > robustness_mention > identification_defense > contribution_statement > related_literature_positioning > other >
        policy_or_broader_implication
      : 0.036
      ? motivation > tension_or_puzzle > related_literature_positioning > literature_gap > preview_of_approach > mechanism_or_theory_sketch
        > preview_of_approach > preview_of_results > robustness_mention > roadmap
      : 0.036
      ? motivation > tension_or_puzzle > preview_of_approach > mechanism_or_theory_sketch > preview_of_results > identification_defense
        > preview_of_results > robustness_mention > contribution_statement > related_literature_positioning > policy_or_broader_implication
      : 0.036
      ? motivation > literature_gap > tension_or_puzzle > contribution_statement > preview_of_approach > identification_defense
        > related_literature_positioning > other
      : 0.036
      ? motivation > literature_gap > identification_defense > preview_of_approach > preview_of_results > identification_defense
        > robustness_mention > identification_defense > preview_of_results > mechanism_or_theory_sketch > contribution_statement
      : 0.036
      ? motivation > mechanism_or_theory_sketch > preview_of_results > identification_defense > robustness_mention > preview_of_results
        > policy_or_broader_implication > roadmap
      : 0.036
    roadmap_present_llm:
      n: 28
      share: 0.571
    roadmap_present_regex:
      n: 28
      share: 0.571
    literature_positioning_location:
      n: 28
      inside_introduction: 0.857
      both: 0.071
      separate_section: 0.071
    contribution_types:
      n: 57
      new_evidence: 0.491
      new_data_or_measure: 0.211
      new_identification: 0.175
      new_theory_or_model: 0.088
      new_method: 0.018
      resolution_of_puzzle: 0.018
  identification:
    causal_language_strength:
      n: 28
      median: 3.0
      q25: 3.0
      q75: 4.0
      mean: 3.25
      min: 1.0
      max: 4.0
      median_ci95_bootstrap:
      - 3.0
      - 4.0
    uses_causal_claim:
      n: 28
      share: 0.857
  results:
    economic_significance_discussed:
      n: 28
      share: 0.929
    statistical_language:
      n: 28
      unclear: 0.929
      stars_and_tstats: 0.071
    magnitude_statements_in_intro:
      n: 28
      share: 0.714
  robustness:
    location:
      n: 28
      mixed: 0.464
      within_results: 0.321
      main_text_section: 0.107
      none_seen: 0.107
    types:
      n: 89
      alternative_specification: 0.236
      alternative_measure: 0.191
      subsample: 0.169
      placebo: 0.112
      other: 0.112
      falsification: 0.101
      alternative_sample_period: 0.034
      ? ''
      : 0.034
  tables:
    standard_errors:
      n: 28
      unclear: 0.964
      clustered: 0.036
    units_in_notes:
      n: 28
      share: 0.893
    clustered_regex:
      n: 28
      share: 0.036
  figures:
    uncertainty_shown:
      n: 28
      unclear: 0.607
      'no': 0.321
      no_figures: 0.036
      mixed: 0.036
  conclusion:
    bounded_claims:
      n: 28
      share: 0.893
    policy_implications:
      n: 28
      share: 0.429
    open_questions:
      n: 28
      share: 0.286
  hedging:
    n: 28
    moderate: 1.0
  claims_with_stated_evidence_share:
    n: 28
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.988
    min: 0.833
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 28
    median: 0.95
    q25: 0.75
    q75: 1.0
    mean: 0.871
    min: 0.5
    max: 1.0
    median_ci95_bootstrap:
    - 0.8
    - 1.0
  llm_confidence:
    n: 28
    median: 0.8
    q25: 0.8
    q75: 0.812
    mean: 0.813
    min: 0.8
    max: 0.85
    median_ci95_bootstrap:
    - 0.8
    - 0.8