# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: empirical_asset_pricing
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 == asset_pricing and genre in {empirical, mixed_theory_empirical}
n_documents: 58
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: 58
    median: 42.0
    q25: 38.25
    q75: 47.75
    mean: 43.172
    min: 28.0
    max: 65.0
    median_ci95_bootstrap:
    - 41.0
    - 46.0
  n_words_body:
    n: 58
    median: 10919.5
    q25: 9900.75
    q75: 12249.5
    mean: 11089.121
    min: 6623.0
    max: 16634.0
    median_ci95_bootstrap:
    - 10566.7
    - 11492.763
  n_words_appendix:
    n: 58
    median: 22.0
    q25: 0.0
    q75: 1430.5
    mean: 597.845
    min: 0.0
    max: 2241.0
    median_ci95_bootstrap:
    - 0.0
    - 577.0
  abstract_words:
    n: 58
    median: 100.0
    q25: 93.0
    q75: 103.0
    mean: 95.983
    min: 49.0
    max: 114.0
    median_ci95_bootstrap:
    - 96.0
    - 102.0
  n_sections:
    n: 58
    median: 5.0
    q25: 5.0
    q75: 6.0
    mean: 5.448
    min: 3.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 58
    median: 13.0
    q25: 10.0
    q75: 18.0
    mean: 14.19
    min: 2.0
    max: 28.0
    median_ci95_bootstrap:
    - 12.5
    - 14.5
  n_paragraphs:
    n: 58
    median: 162.0
    q25: 119.25
    q75: 229.25
    mean: 173.586
    min: 64.0
    max: 320.0
    median_ci95_bootstrap:
    - 135.0
    - 187.5
  n_equations:
    n: 58
    median: 14.5
    q25: 9.0
    q75: 24.75
    mean: 17.983
    min: 0.0
    max: 78.0
    median_ci95_bootstrap:
    - 10.738
    - 19.0
  n_tables:
    n: 58
    median: 10.0
    q25: 8.0
    q75: 11.0
    mean: 9.517
    min: 2.0
    max: 19.0
    median_ci95_bootstrap:
    - 9.0
    - 11.0
  n_figures:
    n: 58
    median: 4.0
    q25: 2.0
    q75: 6.75
    mean: 4.517
    min: 0.0
    max: 12.0
    median_ci95_bootstrap:
    - 3.0
    - 5.0
  n_footnotes:
    n: 58
    median: 35.0
    q25: 27.0
    q75: 43.0
    mean: 37.621
    min: 13.0
    max: 90.0
    median_ci95_bootstrap:
    - 30.5
    - 39.0
  n_references:
    n: 58
    median: 53.0
    q25: 44.5
    q75: 68.5
    mean: 56.397
    min: 29.0
    max: 97.0
    median_ci95_bootstrap:
    - 49.737
    - 60.262
  n_citations_in_text:
    n: 58
    median: 68.5
    q25: 50.25
    q75: 86.25
    mean: 70.672
    min: 18.0
    max: 137.0
    median_ci95_bootstrap:
    - 64.5
    - 74.262
  intro_words:
    n: 58
    median: 1729.0
    q25: 1525.75
    q75: 2160.5
    mean: 1807.707
    min: 922.0
    max: 2846.0
    median_ci95_bootstrap:
    - 1637.537
    - 1870.5
  intro_paragraphs:
    n: 58
    median: 7.5
    q25: 6.0
    q75: 10.0
    mean: 8.293
    min: 2.0
    max: 19.0
    median_ci95_bootstrap:
    - 7.0
    - 8.0
  intro_share:
    n: 58
    median: 0.163
    q25: 0.139
    q75: 0.184
    mean: 0.165
    min: 0.079
    max: 0.276
    median_ci95_bootstrap:
    - 0.154
    - 0.176
  conclusion_words:
    n: 58
    median: 315.0
    q25: 231.0
    q75: 394.75
    mean: 361.793
    min: 91.0
    max: 1878.0
    median_ci95_bootstrap:
    - 266.0
    - 349.0
  conclusion_share:
    n: 58
    median: 0.029
    q25: 0.023
    q75: 0.035
    mean: 0.033
    min: 0.008
    max: 0.21
    median_ci95_bootstrap:
    - 0.024
    - 0.031
  theory_share:
    n: 58
    median: 0.148
    q25: 0.0
    q75: 0.276
    mean: 0.17
    min: 0.0
    max: 0.714
    median_ci95_bootstrap:
    - 0.089
    - 0.195
  data_share:
    n: 58
    median: 0.0
    q25: 0.0
    q75: 0.109
    mean: 0.065
    min: 0.0
    max: 0.381
    median_ci95_bootstrap:
    - 0.0
    - 0.08
  results_share:
    n: 58
    median: 0.0
    q25: 0.0
    q75: 0.224
    mean: 0.115
    min: 0.0
    max: 0.517
    median_ci95_bootstrap:
    - 0.0
    - 0.073
  robustness_share:
    n: 58
    median: 0.0
    q25: 0.0
    q75: 0.04
    mean: 0.034
    min: 0.0
    max: 0.259
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  words_per_table:
    n: 58
    median: 1117.591
    q25: 969.887
    q75: 1426.375
    mean: 1384.258
    min: 411.105
    max: 7367.0
    median_ci95_bootstrap:
    - 1059.098
    - 1275.714
  refs_per_1000_words:
    n: 58
    median: 4.989
    q25: 4.319
    q75: 6.01
    mean: 5.187
    min: 2.16
    max: 9.291
    median_ci95_bootstrap:
    - 4.488
    - 5.668
  equations_per_1000_words:
    n: 58
    median: 1.366
    q25: 0.841
    q75: 2.395
    mean: 1.629
    min: 0.0
    max: 6.711
    median_ci95_bootstrap:
    - 1.051
    - 1.812
presence:
  has_robustness_section:
    n: 58
    share: 0.259
  has_literature_section:
    n: 58
    share: 0.086
  has_appendix:
    n: 58
    share: 0.534
  has_internet_appendix:
    n: 58
    share: 0.914
by_year:
  2017:
    n: 13
    n_words_body_median: 11446.0
    n_tables_median: 9.0
  2018:
    n: 11
    n_words_body_median: 11622.0
    n_tables_median: 10.0
  2019:
    n: 22
    n_words_body_median: 10818.0
    n_tables_median: 9.5
  2020:
    n: 12
    n_words_body_median: 10748.5
    n_tables_median: 11.0
rhetoric:
  n_annotated: 58
  genre:
    n: 58
    mixed_theory_empirical: 0.534
    empirical: 0.466
  subfield:
    n: 58
    asset_pricing: 1.0
  primary_method:
    n: 58
    reduced_form_regression: 0.534
    structural_estimation: 0.138
    other: 0.086
    theoretical_model_analytical: 0.086
    survey_or_experiment: 0.052
    calibration_simulation: 0.034
    machine_learning_textual: 0.034
    instrumental_variables: 0.017
  abstract_moves_present:
    question:
      n: 58
      share: 0.655
    gap:
      n: 58
      share: 0.121
    method:
      n: 58
      share: 0.845
    results:
      n: 58
      share: 1.0
    magnitude:
      n: 58
      share: 0.207
    contribution:
      n: 58
      share: 0.69
  abstract_move_order_median_sentence:
    question:
      n: 38
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.132
      min: 0.0
      max: 1.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 7
      median: 0.0
      q25: 0.0
      q75: 1.0
      mean: 0.857
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 1.0
    method:
      n: 49
      median: 1.0
      q25: 0.0
      q75: 1.0
      mean: 0.939
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 1.0
    results:
      n: 58
      median: 1.0
      q25: 1.0
      q75: 2.0
      mean: 1.431
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    magnitude:
      n: 12
      median: 2.0
      q25: 1.0
      q75: 4.0
      mean: 2.333
      min: 1.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 4.0
    contribution:
      n: 40
      median: 2.5
      q25: 0.75
      q75: 3.25
      mean: 2.2
      min: 0.0
      max: 6.0
      median_ci95_bootstrap:
      - 1.0
      - 3.0
  abstract_sentences:
    n: 58
    median: 5.0
    q25: 4.0
    q75: 5.0
    mean: 4.862
    min: 2.0
    max: 8.0
    median_ci95_bootstrap:
    - 4.5
    - 5.0
  magnitude_in_abstract_regex:
    n: 58
    share: 0.19
  introduction:
    paragraphs:
      n: 58
      median: 7.5
      q25: 6.0
      q75: 10.0
      mean: 8.293
      min: 2.0
      max: 19.0
      median_ci95_bootstrap:
      - 7.0
      - 8.0
    words:
      n: 58
      median: 1036.0
      q25: 834.0
      q75: 1369.25
      mean: 1118.603
      min: 446.0
      max: 2771.0
      median_ci95_bootstrap:
      - 922.5
      - 1191.287
    contribution_paragraph_index:
      n: 56
      median: 4.0
      q25: 1.0
      q75: 6.0
      mean: 4.286
      min: 0.0
      max: 16.0
      median_ci95_bootstrap:
      - 2.0
      - 5.0
    contribution_relative_position:
      n: 56
      median: 0.6
      q25: 0.178
      q75: 0.8
      mean: 0.49
      min: 0.0
      max: 0.9
      median_ci95_bootstrap:
      - 0.296
      - 0.667
    first_move:
      n: 58
      motivation: 0.845
      preview_of_approach: 0.052
      tension_or_puzzle: 0.034
      contribution_statement: 0.017
      literature_gap: 0.017
      mechanism_or_theory_sketch: 0.017
      other: 0.017
    move_prevalence:
      n: 58
      preview_of_results:
        share: 0.966
        median_relative_position: 0.36
      mechanism_or_theory_sketch:
        share: 0.931
        median_relative_position: 0.3
      related_literature_positioning:
        share: 0.897
        median_relative_position: 0.71
      motivation:
        share: 0.897
        median_relative_position: 0.0
      preview_of_approach:
        share: 0.879
        median_relative_position: 0.22
      contribution_statement:
        share: 0.862
        median_relative_position: 0.75
      roadmap:
        share: 0.672
        median_relative_position: 1.0
      tension_or_puzzle:
        share: 0.569
        median_relative_position: 0.1
      literature_gap:
        share: 0.5
        median_relative_position: 0.13
      robustness_mention:
        share: 0.328
        median_relative_position: 0.6
      identification_defense:
        share: 0.276
        median_relative_position: 0.63
      policy_or_broader_implication:
        share: 0.155
        median_relative_position: 0.77
      other:
        share: 0.121
        median_relative_position: 0.86
    moves_per_intro:
      n: 58
      median: 12.0
      q25: 10.0
      q75: 13.0
      mean: 12.052
      min: 7.0
      max: 20.0
      median_ci95_bootstrap:
      - 11.0
      - 12.0
    common_move_sequences:
      n: 58
      ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning
        > literature_gap > contribution_statement > policy_or_broader_implication > roadmap
      : 0.017
      ? 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
      : 0.017
      ? motivation > related_literature_positioning > preview_of_approach > contribution_statement > preview_of_results >
        mechanism_or_theory_sketch > related_literature_positioning > contribution_statement > identification_defense > related_literature_positioning
      : 0.017
      ? motivation > preview_of_results > preview_of_approach > preview_of_results > related_literature_positioning > preview_of_results
        > policy_or_broader_implication > preview_of_results > related_literature_positioning > literature_gap > related_literature_positioning
        > contribution_statement > related_literature_positioning > roadmap
      : 0.017
      ? motivation > preview_of_approach > preview_of_results > preview_of_approach > mechanism_or_theory_sketch > related_literature_positioning
        > roadmap
      : 0.017
      ? motivation > tension_or_puzzle > literature_gap > contribution_statement > preview_of_results > related_literature_positioning
        > mechanism_or_theory_sketch > preview_of_results > robustness_mention > preview_of_approach > mechanism_or_theory_sketch
        > related_literature_positioning > other > roadmap
      : 0.017
    roadmap_present_llm:
      n: 58
      share: 0.672
    roadmap_present_regex:
      n: 58
      share: 0.638
    literature_positioning_location:
      n: 58
      inside_introduction: 0.931
      both: 0.069
    contribution_types:
      n: 129
      new_evidence: 0.45
      new_theory_or_model: 0.209
      new_data_or_measure: 0.163
      resolution_of_puzzle: 0.109
      new_method: 0.054
      new_identification: 0.016
  identification:
    causal_language_strength:
      n: 58
      median: 2.0
      q25: 2.0
      q75: 3.0
      mean: 2.414
      min: 1.0
      max: 4.0
      median_ci95_bootstrap:
      - 2.0
      - 2.0
    uses_causal_claim:
      n: 58
      share: 0.362
  results:
    economic_significance_discussed:
      n: 58
      share: 0.931
    statistical_language:
      n: 58
      unclear: 0.621
      stars_and_tstats: 0.19
      mixed: 0.138
      confidence_intervals: 0.034
      p_values: 0.017
    magnitude_statements_in_intro:
      n: 58
      share: 0.603
  robustness:
    location:
      n: 58
      mixed: 0.431
      within_results: 0.224
      main_text_section: 0.19
      none_seen: 0.086
      appendix: 0.052
      internet_appendix: 0.017
    types:
      n: 182
      alternative_specification: 0.264
      alternative_measure: 0.203
      subsample: 0.176
      other: 0.132
      alternative_sample_period: 0.104
      sensitivity_to_parameters: 0.055
      ? ''
      : 0.027
      placebo: 0.022
  tables:
    standard_errors:
      n: 58
      unclear: 0.672
      mixed: 0.103
      newey_west: 0.086
      clustered: 0.052
      none: 0.034
      robust: 0.034
      bootstrap: 0.017
    units_in_notes:
      n: 58
      share: 0.707
    clustered_regex:
      n: 58
      share: 0.052
  figures:
    uncertainty_shown:
      n: 58
      unclear: 0.517
      'no': 0.276
      mixed: 0.121
      no_figures: 0.052
      'yes': 0.034
  conclusion:
    bounded_claims:
      n: 58
      share: 0.793
    policy_implications:
      n: 58
      share: 0.086
    open_questions:
      n: 58
      share: 0.397
  hedging:
    n: 58
    moderate: 0.879
    low: 0.121
  claims_with_stated_evidence_share:
    n: 58
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.993
    min: 0.857
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 58
    median: 1.0
    q25: 0.833
    q75: 1.0
    mean: 0.915
    min: 0.5
    max: 1.0
    median_ci95_bootstrap:
    - 0.887
    - 1.0
  llm_confidence:
    n: 58
    median: 0.8
    q25: 0.8
    q75: 0.815
    mean: 0.806
    min: 0.75
    max: 0.85
    median_ci95_bootstrap:
    - 0.8
    - 0.8