SPB Git

spb/wp45_uqo

Public
12.9 KB · 665 lines yaml
1# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)2profile: empirical_all3ontology_version: '1.0'4built:5  timestamp: '2026-11-03T23:27:17+00:00'6  code_version: 87c73cd-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 in {empirical, mixed_theory_empirical}13n_documents: 17314split: 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: 17320    median: 43.021    q25: 39.022    q75: 47.023    mean: 43.12724    min: 25.025    max: 65.026    median_ci95_bootstrap:27    - 42.028    - 44.029  n_words_body:30    n: 17331    median: 11009.032    q25: 10052.033    q75: 12194.034    mean: 11182.8535    min: 6623.036    max: 17025.037    median_ci95_bootstrap:38    - 10813.039    - 11343.2540  n_words_appendix:41    n: 17342    median: 0.043    q25: 0.044    q75: 510.045    mean: 442.56146    min: 0.047    max: 3991.048    median_ci95_bootstrap:49    - 0.050    - 21.051  abstract_words:52    n: 17353    median: 100.054    q25: 96.055    q75: 104.056    mean: 103.97757    min: 49.058    max: 535.059    median_ci95_bootstrap:60    - 100.061    - 101.062  n_sections:63    n: 17364    median: 5.065    q25: 5.066    q75: 6.067    mean: 5.52668    min: 3.069    max: 9.070    median_ci95_bootstrap:71    - 5.072    - 6.073  n_subsections:74    n: 17375    median: 13.076    q25: 10.077    q75: 18.078    mean: 14.32979    min: 0.080    max: 46.081    median_ci95_bootstrap:82    - 13.083    - 14.084  n_paragraphs:85    n: 17386    median: 113.087    q25: 82.088    q75: 174.089    mean: 137.19790    min: 51.091    max: 649.092    median_ci95_bootstrap:93    - 101.47594    - 127.095  n_equations:96    n: 17397    median: 7.098    q25: 2.099    q75: 15.0100    mean: 11.491101    min: 0.0102    max: 78.0103    median_ci95_bootstrap:104    - 6.0105    - 9.0106  n_tables:107    n: 173108    median: 9.0109    q25: 7.0110    q75: 11.0111    mean: 9.347112    min: 0.0113    max: 24.0114    median_ci95_bootstrap:115    - 9.0116    - 10.0117  n_figures:118    n: 173119    median: 4.0120    q25: 2.0121    q75: 6.0122    mean: 4.289123    min: 0.0124    max: 14.0125    median_ci95_bootstrap:126    - 3.0127    - 4.0128  n_footnotes:129    n: 173130    median: 36.0131    q25: 28.0132    q75: 43.0133    mean: 38.035134    min: 10.0135    max: 148.0136    median_ci95_bootstrap:137    - 35.0138    - 38.0139  n_references:140    n: 173141    median: 53.0142    q25: 43.0143    q75: 64.0144    mean: 54.809145    min: 17.0146    max: 122.0147    median_ci95_bootstrap:148    - 50.0149    - 56.0150  n_citations_in_text:151    n: 173152    median: 56.0153    q25: 41.0154    q75: 76.0155    mean: 60.977156    min: 17.0157    max: 181.0158    median_ci95_bootstrap:159    - 51.475160    - 63.0161  intro_words:162    n: 173163    median: 1804.0164    q25: 1588.0165    q75: 2116.0166    mean: 1833.809167    min: 815.0168    max: 2846.0169    median_ci95_bootstrap:170    - 1713.0171    - 1853.0172  intro_paragraphs:173    n: 173174    median: 7.0175    q25: 6.0176    q75: 9.0177    mean: 8.393178    min: 2.0179    max: 64.0180    median_ci95_bootstrap:181    - 7.0182    - 8.0183  intro_share:184    n: 173185    median: 0.165186    q25: 0.143187    q75: 0.191188    mean: 0.167189    min: 0.071190    max: 0.276191    median_ci95_bootstrap:192    - 0.159193    - 0.174194  conclusion_words:195    n: 173196    median: 363.0197    q25: 265.0198    q75: 516.0199    mean: 460.272200    min: 91.0201    max: 3986.0202    median_ci95_bootstrap:203    - 329.0204    - 394.0205  conclusion_share:206    n: 173207    median: 0.033208    q25: 0.024209    q75: 0.047210    mean: 0.043211    min: 0.008212    max: 0.427213    median_ci95_bootstrap:214    - 0.031215    - 0.036216  theory_share:217    n: 173218    median: 0.036219    q25: 0.0220    q75: 0.192221    mean: 0.116222    min: 0.0223    max: 0.714224    median_ci95_bootstrap:225    - 0.0226    - 0.103227  data_share:228    n: 173229    median: 0.076230    q25: 0.0231    q75: 0.133232    mean: 0.09233    min: 0.0234    max: 0.57235    median_ci95_bootstrap:236    - 0.046237    - 0.095238  results_share:239    n: 173240    median: 0.0241    q25: 0.0242    q75: 0.203243    mean: 0.117244    min: 0.0245    max: 0.627246    median_ci95_bootstrap:247    - 0.0248    - 0.0249  robustness_share:250    n: 173251    median: 0.0252    q25: 0.0253    q75: 0.0254    mean: 0.035255    min: 0.0256    max: 0.338257    median_ci95_bootstrap:258    - 0.0259    - 0.0260  words_per_table:261    n: 173262    median: 1197.667263    q25: 957.875264    q75: 1635.667265    mean: 1424.985266    min: 371.917267    max: 13206.0268    median_ci95_bootstrap:269    - 1115.273270    - 1265.25271  refs_per_1000_words:272    n: 173273    median: 4.819274    q25: 3.784275    q75: 5.969276    mean: 4.997277    min: 1.075278    max: 10.145279    median_ci95_bootstrap:280    - 4.6281    - 5.214282  equations_per_1000_words:283    n: 173284    median: 0.608285    q25: 0.224286    q75: 1.439287    mean: 1.018288    min: 0.0289    max: 6.711290    median_ci95_bootstrap:291    - 0.522292    - 0.839293presence:294  has_robustness_section:295    n: 173296    share: 0.243297  has_literature_section:298    n: 173299    share: 0.185300  has_appendix:301    n: 173302    share: 0.428303  has_internet_appendix:304    n: 173305    share: 0.936306by_year:307  2017:308    n: 43309    n_words_body_median: 10952.0310    n_tables_median: 10.0311  2018:312    n: 42313    n_words_body_median: 11392.5314    n_tables_median: 9.5315  2019:316    n: 46317    n_words_body_median: 10853.5318    n_tables_median: 9.0319  2020:320    n: 42321    n_words_body_median: 11062.0322    n_tables_median: 10.0323rhetoric:324  n_annotated: 173325  genre:326    n: 173327    empirical: 0.676328    mixed_theory_empirical: 0.324329  subfield:330    n: 173331    asset_pricing: 0.335332    corporate_finance: 0.162333    household_finance: 0.127334    financial_intermediation_banking: 0.121335    market_microstructure: 0.092336    behavioral_finance: 0.058337    entrepreneurial_finance_private_equity: 0.04338    international_finance: 0.035339  primary_method:340    n: 173341    reduced_form_regression: 0.468342    difference_in_differences: 0.121343    structural_estimation: 0.081344    instrumental_variables: 0.075345    other: 0.052346    theoretical_model_analytical: 0.052347    survey_or_experiment: 0.046348    natural_experiment_event_study: 0.04349  abstract_moves_present:350    question:351      n: 173352      share: 0.717353    gap:354      n: 173355      share: 0.116356    method:357      n: 173358      share: 0.832359    results:360      n: 173361      share: 1.0362    magnitude:363      n: 173364      share: 0.289365    contribution:366      n: 173367      share: 0.647368  abstract_move_order_median_sentence:369    question:370      n: 124371      median: 0.0372      q25: 0.0373      q75: 0.0374      mean: 0.161375      min: 0.0376      max: 3.0377      median_ci95_bootstrap:378      - 0.0379      - 0.0380    gap:381      n: 20382      median: 1.0383      q25: 0.0384      q75: 1.0385      mean: 0.8386      min: 0.0387      max: 4.0388      median_ci95_bootstrap:389      - 0.0390      - 1.0391    method:392      n: 144393      median: 1.0394      q25: 0.0395      q75: 2.0396      mean: 1.069397      min: 0.0398      max: 4.0399      median_ci95_bootstrap:400      - 1.0401      - 1.0402    results:403      n: 173404      median: 1.0405      q25: 1.0406      q75: 2.0407      mean: 1.538408      min: 0.0409      max: 4.0410      median_ci95_bootstrap:411      - 1.0412      - 2.0413    magnitude:414      n: 50415      median: 2.0416      q25: 1.0417      q75: 3.0418      mean: 2.12419      min: 0.0420      max: 5.0421      median_ci95_bootstrap:422      - 2.0423      - 2.262424    contribution:425      n: 112426      median: 3.0427      q25: 1.0428      q75: 4.0429      mean: 2.589430      min: 0.0431      max: 7.0432      median_ci95_bootstrap:433      - 2.0434      - 3.0435  abstract_sentences:436    n: 173437    median: 5.0438    q25: 4.0439    q75: 6.0440    mean: 5.249441    min: 2.0442    max: 16.0443    median_ci95_bootstrap:444    - 5.0445    - 5.0446  magnitude_in_abstract_regex:447    n: 173448    share: 0.197449  introduction:450    paragraphs:451      n: 173452      median: 7.0453      q25: 6.0454      q75: 9.0455      mean: 8.393456      min: 2.0457      max: 64.0458      median_ci95_bootstrap:459      - 7.0460      - 8.0461    words:462      n: 173463      median: 1105.0464      q25: 893.0465      q75: 1325.0466      mean: 1132.249467      min: 446.0468      max: 2771.0469      median_ci95_bootstrap:470      - 1021.9471      - 1166.0472    contribution_paragraph_index:473      n: 165474      median: 4.0475      q25: 1.0476      q75: 6.0477      mean: 4.794478      min: 0.0479      max: 56.0480      median_ci95_bootstrap:481      - 3.0482      - 5.0483    contribution_relative_position:484      n: 165485      median: 0.625486      q25: 0.2487      q75: 0.8488      mean: 0.516489      min: 0.0490      max: 0.941491      median_ci95_bootstrap:492      - 0.571493      - 0.667494    first_move:495      n: 173496      motivation: 0.902497      tension_or_puzzle: 0.023498      preview_of_approach: 0.023499      other: 0.023500      literature_gap: 0.012501      contribution_statement: 0.006502      related_literature_positioning: 0.006503      mechanism_or_theory_sketch: 0.006504    common_move_sequences:505      n: 173506      ? motivation > preview_of_approach > identification_defense > mechanism_or_theory_sketch > preview_of_approach > preview_of_results507        > robustness_mention > identification_defense > contribution_statement > related_literature_positioning > other >508        policy_or_broader_implication509      : 0.006510      ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning511        > literature_gap > contribution_statement > policy_or_broader_implication > roadmap512      : 0.006513      ? motivation > mechanism_or_theory_sketch > preview_of_results > preview_of_approach > preview_of_results > identification_defense514        > preview_of_results > robustness_mention > related_literature_positioning > contribution_statement515      : 0.006516      ? motivation > policy_or_broader_implication > mechanism_or_theory_sketch > tension_or_puzzle > preview_of_approach517        > preview_of_results > identification_defense > related_literature_positioning > contribution_statement > related_literature_positioning518      : 0.006519      ? motivation > literature_gap > policy_or_broader_implication > preview_of_approach > preview_of_results > robustness_mention520        > preview_of_results > contribution_statement > related_literature_positioning521      : 0.006522      ? tension_or_puzzle > literature_gap > contribution_statement > preview_of_approach > mechanism_or_theory_sketch > identification_defense523        > preview_of_approach > identification_defense > preview_of_results > preview_of_approach > preview_of_results > policy_or_broader_implication524        > related_literature_positioning > roadmap525      : 0.006526    roadmap_present_llm:527      n: 173528      share: 0.653529    roadmap_present_regex:530      n: 173531      share: 0.636532    literature_positioning_location:533      n: 173534      inside_introduction: 0.884535      both: 0.087536      separate_section: 0.023537      none: 0.006538    contribution_types:539      n: 365540      new_evidence: 0.474541      new_data_or_measure: 0.189542      new_theory_or_model: 0.137543      new_identification: 0.099544      resolution_of_puzzle: 0.066545      new_method: 0.036546  identification:547    causal_language_strength:548      n: 173549      median: 3.0550      q25: 2.0551      q75: 4.0552      mean: 2.861553      min: 1.0554      max: 5.0555      median_ci95_bootstrap:556      - 3.0557      - 3.0558    uses_causal_claim:559      n: 173560      share: 0.607561  results:562    economic_significance_discussed:563      n: 173564      share: 0.925565    statistical_language:566      n: 173567      unclear: 0.757568      stars_and_tstats: 0.133569      mixed: 0.081570      p_values: 0.017571      confidence_intervals: 0.012572    magnitude_statements_in_intro:573      n: 173574      share: 0.694575  robustness:576    location:577      n: 173578      mixed: 0.422579      within_results: 0.266580      main_text_section: 0.145581      none_seen: 0.11582      appendix: 0.04583      internet_appendix: 0.017584    types:585      n: 534586      alternative_specification: 0.24587      subsample: 0.187588      alternative_measure: 0.176589      other: 0.155590      alternative_sample_period: 0.064591      placebo: 0.054592      falsification: 0.051593      sensitivity_to_parameters: 0.037594  tables:595    standard_errors:596      n: 173597      unclear: 0.78598      clustered: 0.075599      newey_west: 0.04600      mixed: 0.04601      robust: 0.035602      none: 0.023603      bootstrap: 0.006604    units_in_notes:605      n: 173606      share: 0.803607    clustered_regex:608      n: 173609      share: 0.069610  figures:611    uncertainty_shown:612      n: 173613      unclear: 0.584614      'no': 0.22615      mixed: 0.104616      no_figures: 0.069617      'yes': 0.023618  conclusion:619    bounded_claims:620      n: 173621      share: 0.827622    policy_implications:623      n: 173624      share: 0.358625    open_questions:626      n: 173627      share: 0.393628  hedging:629    n: 173630    moderate: 0.931631    low: 0.069632  claims_with_stated_evidence_share:633    n: 173634    median: 1.0635    q25: 1.0636    q75: 1.0637    mean: 0.989638    min: 0.75639    max: 1.0640    median_ci95_bootstrap:641    - 1.0642    - 1.0643  llm_vs_rule_section_role_agreement:644    n: 173645    median: 1.0646    q25: 0.8647    q75: 1.0648    mean: 0.899649    min: 0.438650    max: 1.0651    median_ci95_bootstrap:652    - 0.9653    - 1.0654  llm_confidence:655    n: 173656    median: 0.8657    q25: 0.8658    q75: 0.82659    mean: 0.809660    min: 0.75661    max: 0.85662    median_ci95_bootstrap:663    - 0.8664    - 0.8665
Files · 216d83691f0ad9cc600ca0b0c5fd81d346a2c6ad
Menu

Theme