# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: empirical_all
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 in {empirical, mixed_theory_empirical}
n_documents: 173
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: 173
    median: 43.0
    q25: 39.0
    q75: 47.0
    mean: 43.127
    min: 25.0
    max: 65.0
    median_ci95_bootstrap:
    - 42.0
    - 44.0
  n_words_body:
    n: 173
    median: 11009.0
    q25: 10052.0
    q75: 12194.0
    mean: 11182.85
    min: 6623.0
    max: 17025.0
    median_ci95_bootstrap:
    - 10813.0
    - 11343.25
  n_words_appendix:
    n: 173
    median: 0.0
    q25: 0.0
    q75: 510.0
    mean: 442.561
    min: 0.0
    max: 3991.0
    median_ci95_bootstrap:
    - 0.0
    - 21.0
  abstract_words:
    n: 173
    median: 100.0
    q25: 96.0
    q75: 104.0
    mean: 103.977
    min: 49.0
    max: 535.0
    median_ci95_bootstrap:
    - 100.0
    - 101.0
  n_sections:
    n: 173
    median: 5.0
    q25: 5.0
    q75: 6.0
    mean: 5.526
    min: 3.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 173
    median: 13.0
    q25: 10.0
    q75: 18.0
    mean: 14.329
    min: 0.0
    max: 46.0
    median_ci95_bootstrap:
    - 13.0
    - 14.0
  n_paragraphs:
    n: 173
    median: 113.0
    q25: 82.0
    q75: 174.0
    mean: 137.197
    min: 51.0
    max: 649.0
    median_ci95_bootstrap:
    - 101.475
    - 127.0
  n_equations:
    n: 173
    median: 7.0
    q25: 2.0
    q75: 15.0
    mean: 11.491
    min: 0.0
    max: 78.0
    median_ci95_bootstrap:
    - 6.0
    - 9.0
  n_tables:
    n: 173
    median: 9.0
    q25: 7.0
    q75: 11.0
    mean: 9.347
    min: 0.0
    max: 24.0
    median_ci95_bootstrap:
    - 9.0
    - 10.0
  n_figures:
    n: 173
    median: 4.0
    q25: 2.0
    q75: 6.0
    mean: 4.289
    min: 0.0
    max: 14.0
    median_ci95_bootstrap:
    - 3.0
    - 4.0
  n_footnotes:
    n: 173
    median: 36.0
    q25: 28.0
    q75: 43.0
    mean: 38.035
    min: 10.0
    max: 148.0
    median_ci95_bootstrap:
    - 35.0
    - 38.0
  n_references:
    n: 173
    median: 53.0
    q25: 43.0
    q75: 64.0
    mean: 54.809
    min: 17.0
    max: 122.0
    median_ci95_bootstrap:
    - 50.0
    - 56.0
  n_citations_in_text:
    n: 173
    median: 56.0
    q25: 41.0
    q75: 76.0
    mean: 60.977
    min: 17.0
    max: 181.0
    median_ci95_bootstrap:
    - 51.475
    - 63.0
  intro_words:
    n: 173
    median: 1804.0
    q25: 1588.0
    q75: 2116.0
    mean: 1833.809
    min: 815.0
    max: 2846.0
    median_ci95_bootstrap:
    - 1713.0
    - 1853.0
  intro_paragraphs:
    n: 173
    median: 7.0
    q25: 6.0
    q75: 9.0
    mean: 8.393
    min: 2.0
    max: 64.0
    median_ci95_bootstrap:
    - 7.0
    - 8.0
  intro_share:
    n: 173
    median: 0.165
    q25: 0.143
    q75: 0.191
    mean: 0.167
    min: 0.071
    max: 0.276
    median_ci95_bootstrap:
    - 0.159
    - 0.174
  conclusion_words:
    n: 173
    median: 363.0
    q25: 265.0
    q75: 516.0
    mean: 460.272
    min: 91.0
    max: 3986.0
    median_ci95_bootstrap:
    - 329.0
    - 394.0
  conclusion_share:
    n: 173
    median: 0.033
    q25: 0.024
    q75: 0.047
    mean: 0.043
    min: 0.008
    max: 0.427
    median_ci95_bootstrap:
    - 0.031
    - 0.036
  theory_share:
    n: 173
    median: 0.036
    q25: 0.0
    q75: 0.192
    mean: 0.116
    min: 0.0
    max: 0.714
    median_ci95_bootstrap:
    - 0.0
    - 0.103
  data_share:
    n: 173
    median: 0.076
    q25: 0.0
    q75: 0.133
    mean: 0.09
    min: 0.0
    max: 0.57
    median_ci95_bootstrap:
    - 0.046
    - 0.095
  results_share:
    n: 173
    median: 0.0
    q25: 0.0
    q75: 0.203
    mean: 0.117
    min: 0.0
    max: 0.627
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  robustness_share:
    n: 173
    median: 0.0
    q25: 0.0
    q75: 0.0
    mean: 0.035
    min: 0.0
    max: 0.338
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  words_per_table:
    n: 173
    median: 1197.667
    q25: 957.875
    q75: 1635.667
    mean: 1424.985
    min: 371.917
    max: 13206.0
    median_ci95_bootstrap:
    - 1115.273
    - 1265.25
  refs_per_1000_words:
    n: 173
    median: 4.819
    q25: 3.784
    q75: 5.969
    mean: 4.997
    min: 1.075
    max: 10.145
    median_ci95_bootstrap:
    - 4.6
    - 5.214
  equations_per_1000_words:
    n: 173
    median: 0.608
    q25: 0.224
    q75: 1.439
    mean: 1.018
    min: 0.0
    max: 6.711
    median_ci95_bootstrap:
    - 0.522
    - 0.839
presence:
  has_robustness_section:
    n: 173
    share: 0.243
  has_literature_section:
    n: 173
    share: 0.185
  has_appendix:
    n: 173
    share: 0.428
  has_internet_appendix:
    n: 173
    share: 0.936
by_year:
  2017:
    n: 43
    n_words_body_median: 10952.0
    n_tables_median: 10.0
  2018:
    n: 42
    n_words_body_median: 11392.5
    n_tables_median: 9.5
  2019:
    n: 46
    n_words_body_median: 10853.5
    n_tables_median: 9.0
  2020:
    n: 42
    n_words_body_median: 11062.0
    n_tables_median: 10.0
rhetoric:
  n_annotated: 173
  genre:
    n: 173
    empirical: 0.676
    mixed_theory_empirical: 0.324
  subfield:
    n: 173
    asset_pricing: 0.335
    corporate_finance: 0.162
    household_finance: 0.127
    financial_intermediation_banking: 0.121
    market_microstructure: 0.092
    behavioral_finance: 0.058
    entrepreneurial_finance_private_equity: 0.04
    international_finance: 0.035
  primary_method:
    n: 173
    reduced_form_regression: 0.468
    difference_in_differences: 0.121
    structural_estimation: 0.081
    instrumental_variables: 0.075
    other: 0.052
    theoretical_model_analytical: 0.052
    survey_or_experiment: 0.046
    natural_experiment_event_study: 0.04
  abstract_moves_present:
    question:
      n: 173
      share: 0.717
    gap:
      n: 173
      share: 0.116
    method:
      n: 173
      share: 0.832
    results:
      n: 173
      share: 1.0
    magnitude:
      n: 173
      share: 0.289
    contribution:
      n: 173
      share: 0.647
  abstract_move_order_median_sentence:
    question:
      n: 124
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.161
      min: 0.0
      max: 3.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 20
      median: 1.0
      q25: 0.0
      q75: 1.0
      mean: 0.8
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 1.0
    method:
      n: 144
      median: 1.0
      q25: 0.0
      q75: 2.0
      mean: 1.069
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 1.0
    results:
      n: 173
      median: 1.0
      q25: 1.0
      q75: 2.0
      mean: 1.538
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    magnitude:
      n: 50
      median: 2.0
      q25: 1.0
      q75: 3.0
      mean: 2.12
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 2.0
      - 2.262
    contribution:
      n: 112
      median: 3.0
      q25: 1.0
      q75: 4.0
      mean: 2.589
      min: 0.0
      max: 7.0
      median_ci95_bootstrap:
      - 2.0
      - 3.0
  abstract_sentences:
    n: 173
    median: 5.0
    q25: 4.0
    q75: 6.0
    mean: 5.249
    min: 2.0
    max: 16.0
    median_ci95_bootstrap:
    - 5.0
    - 5.0
  magnitude_in_abstract_regex:
    n: 173
    share: 0.197
  introduction:
    paragraphs:
      n: 173
      median: 7.0
      q25: 6.0
      q75: 9.0
      mean: 8.393
      min: 2.0
      max: 64.0
      median_ci95_bootstrap:
      - 7.0
      - 8.0
    words:
      n: 173
      median: 1105.0
      q25: 893.0
      q75: 1325.0
      mean: 1132.249
      min: 446.0
      max: 2771.0
      median_ci95_bootstrap:
      - 1021.9
      - 1166.0
    contribution_paragraph_index:
      n: 165
      median: 4.0
      q25: 1.0
      q75: 6.0
      mean: 4.794
      min: 0.0
      max: 56.0
      median_ci95_bootstrap:
      - 3.0
      - 5.0
    contribution_relative_position:
      n: 165
      median: 0.625
      q25: 0.2
      q75: 0.8
      mean: 0.516
      min: 0.0
      max: 0.941
      median_ci95_bootstrap:
      - 0.571
      - 0.667
    first_move:
      n: 173
      motivation: 0.902
      tension_or_puzzle: 0.023
      preview_of_approach: 0.023
      other: 0.023
      literature_gap: 0.012
      contribution_statement: 0.006
      related_literature_positioning: 0.006
      mechanism_or_theory_sketch: 0.006
    move_prevalence:
      n: 173
      preview_of_results:
        share: 0.983
        median_relative_position: 0.36
      motivation:
        share: 0.948
        median_relative_position: 0.0
      preview_of_approach:
        share: 0.896
        median_relative_position: 0.25
      related_literature_positioning:
        share: 0.873
        median_relative_position: 0.75
      mechanism_or_theory_sketch:
        share: 0.838
        median_relative_position: 0.33
      contribution_statement:
        share: 0.809
        median_relative_position: 0.75
      roadmap:
        share: 0.653
        median_relative_position: 1.0
      literature_gap:
        share: 0.578
        median_relative_position: 0.12
      identification_defense:
        share: 0.543
        median_relative_position: 0.5
      tension_or_puzzle:
        share: 0.497
        median_relative_position: 0.11
      robustness_mention:
        share: 0.341
        median_relative_position: 0.62
      policy_or_broader_implication:
        share: 0.335
        median_relative_position: 0.79
      other:
        share: 0.15
        median_relative_position: 0.7
    moves_per_intro:
      n: 173
      median: 12.0
      q25: 10.0
      q75: 14.0
      mean: 12.127
      min: 7.0
      max: 23.0
      median_ci95_bootstrap:
      - 12.0
      - 12.0
    common_move_sequences:
      n: 173
      ? 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
      : 0.006
      ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning
        > literature_gap > contribution_statement > policy_or_broader_implication > roadmap
      : 0.006
      ? motivation > mechanism_or_theory_sketch > preview_of_results > preview_of_approach > preview_of_results > identification_defense
        > preview_of_results > robustness_mention > related_literature_positioning > contribution_statement
      : 0.006
      ? motivation > policy_or_broader_implication > mechanism_or_theory_sketch > tension_or_puzzle > preview_of_approach
        > preview_of_results > identification_defense > related_literature_positioning > contribution_statement > related_literature_positioning
      : 0.006
      ? motivation > literature_gap > policy_or_broader_implication > preview_of_approach > preview_of_results > robustness_mention
        > preview_of_results > contribution_statement > related_literature_positioning
      : 0.006
      ? tension_or_puzzle > literature_gap > contribution_statement > preview_of_approach > mechanism_or_theory_sketch > identification_defense
        > preview_of_approach > identification_defense > preview_of_results > preview_of_approach > preview_of_results > policy_or_broader_implication
        > related_literature_positioning > roadmap
      : 0.006
    roadmap_present_llm:
      n: 173
      share: 0.653
    roadmap_present_regex:
      n: 173
      share: 0.636
    literature_positioning_location:
      n: 173
      inside_introduction: 0.884
      both: 0.087
      separate_section: 0.023
      none: 0.006
    contribution_types:
      n: 365
      new_evidence: 0.474
      new_data_or_measure: 0.189
      new_theory_or_model: 0.137
      new_identification: 0.099
      resolution_of_puzzle: 0.066
      new_method: 0.036
  identification:
    causal_language_strength:
      n: 173
      median: 3.0
      q25: 2.0
      q75: 4.0
      mean: 2.861
      min: 1.0
      max: 5.0
      median_ci95_bootstrap:
      - 3.0
      - 3.0
    uses_causal_claim:
      n: 173
      share: 0.607
  results:
    economic_significance_discussed:
      n: 173
      share: 0.925
    statistical_language:
      n: 173
      unclear: 0.757
      stars_and_tstats: 0.133
      mixed: 0.081
      p_values: 0.017
      confidence_intervals: 0.012
    magnitude_statements_in_intro:
      n: 173
      share: 0.694
  robustness:
    location:
      n: 173
      mixed: 0.422
      within_results: 0.266
      main_text_section: 0.145
      none_seen: 0.11
      appendix: 0.04
      internet_appendix: 0.017
    types:
      n: 534
      alternative_specification: 0.24
      subsample: 0.187
      alternative_measure: 0.176
      other: 0.155
      alternative_sample_period: 0.064
      placebo: 0.054
      falsification: 0.051
      sensitivity_to_parameters: 0.037
  tables:
    standard_errors:
      n: 173
      unclear: 0.78
      clustered: 0.075
      newey_west: 0.04
      mixed: 0.04
      robust: 0.035
      none: 0.023
      bootstrap: 0.006
    units_in_notes:
      n: 173
      share: 0.803
    clustered_regex:
      n: 173
      share: 0.069
  figures:
    uncertainty_shown:
      n: 173
      unclear: 0.584
      'no': 0.22
      mixed: 0.104
      no_figures: 0.069
      'yes': 0.023
  conclusion:
    bounded_claims:
      n: 173
      share: 0.827
    policy_implications:
      n: 173
      share: 0.358
    open_questions:
      n: 173
      share: 0.393
  hedging:
    n: 173
    moderate: 0.931
    low: 0.069
  claims_with_stated_evidence_share:
    n: 173
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.989
    min: 0.75
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 173
    median: 1.0
    q25: 0.8
    q75: 1.0
    mean: 0.899
    min: 0.438
    max: 1.0
    median_ci95_bootstrap:
    - 0.9
    - 1.0
  llm_confidence:
    n: 173
    median: 0.8
    q25: 0.8
    q75: 0.82
    mean: 0.809
    min: 0.75
    max: 0.85
    median_ci95_bootstrap:
    - 0.8
    - 0.8