SPB Git

spb/wp45_uqo

Public
13.9 KB · 708 lines yaml
1# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)2profile: empirical_asset_pricing3ontology_version: '1.0'4built:5  timestamp: '2026-11-03T23:29:46+00:00'6  code_version: f8b9e5a-dirty7  host:8    platform: macOS-27.0-arm64-arm-64bit9    python: 3.12.1310    machine: arm6411    node: MacBookPro-de-simon-pierre-2.local12selection_rule: annotation.subfield == asset_pricing and genre in {empirical, mixed_theory_empirical}13n_documents: 5814split: 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: 5820    median: 42.021    q25: 38.2522    q75: 47.7523    mean: 43.17224    min: 28.025    max: 65.026    median_ci95_bootstrap:27    - 41.028    - 46.029  n_words_body:30    n: 5831    median: 10919.532    q25: 9900.7533    q75: 12249.534    mean: 11089.12135    min: 6623.036    max: 16634.037    median_ci95_bootstrap:38    - 10566.739    - 11492.76340  n_words_appendix:41    n: 5842    median: 22.043    q25: 0.044    q75: 1430.545    mean: 597.84546    min: 0.047    max: 2241.048    median_ci95_bootstrap:49    - 0.050    - 577.051  abstract_words:52    n: 5853    median: 100.054    q25: 93.055    q75: 103.056    mean: 95.98357    min: 49.058    max: 114.059    median_ci95_bootstrap:60    - 96.061    - 102.062  n_sections:63    n: 5864    median: 5.065    q25: 5.066    q75: 6.067    mean: 5.44868    min: 3.069    max: 9.070    median_ci95_bootstrap:71    - 5.072    - 6.073  n_subsections:74    n: 5875    median: 13.076    q25: 10.077    q75: 18.078    mean: 14.1979    min: 2.080    max: 28.081    median_ci95_bootstrap:82    - 12.583    - 14.584  n_paragraphs:85    n: 5886    median: 162.087    q25: 119.2588    q75: 229.2589    mean: 173.58690    min: 64.091    max: 320.092    median_ci95_bootstrap:93    - 135.094    - 187.595  n_equations:96    n: 5897    median: 14.598    q25: 9.099    q75: 24.75100    mean: 17.983101    min: 0.0102    max: 78.0103    median_ci95_bootstrap:104    - 10.738105    - 19.0106  n_tables:107    n: 58108    median: 10.0109    q25: 8.0110    q75: 11.0111    mean: 9.517112    min: 2.0113    max: 19.0114    median_ci95_bootstrap:115    - 9.0116    - 11.0117  n_figures:118    n: 58119    median: 4.0120    q25: 2.0121    q75: 6.75122    mean: 4.517123    min: 0.0124    max: 12.0125    median_ci95_bootstrap:126    - 3.0127    - 5.0128  n_footnotes:129    n: 58130    median: 35.0131    q25: 27.0132    q75: 43.0133    mean: 37.621134    min: 13.0135    max: 90.0136    median_ci95_bootstrap:137    - 30.5138    - 39.0139  n_references:140    n: 58141    median: 53.0142    q25: 44.5143    q75: 68.5144    mean: 56.397145    min: 29.0146    max: 97.0147    median_ci95_bootstrap:148    - 49.737149    - 60.262150  n_citations_in_text:151    n: 58152    median: 68.5153    q25: 50.25154    q75: 86.25155    mean: 70.672156    min: 18.0157    max: 137.0158    median_ci95_bootstrap:159    - 64.5160    - 74.262161  intro_words:162    n: 58163    median: 1729.0164    q25: 1525.75165    q75: 2160.5166    mean: 1807.707167    min: 922.0168    max: 2846.0169    median_ci95_bootstrap:170    - 1637.537171    - 1870.5172  intro_paragraphs:173    n: 58174    median: 7.5175    q25: 6.0176    q75: 10.0177    mean: 8.293178    min: 2.0179    max: 19.0180    median_ci95_bootstrap:181    - 7.0182    - 8.0183  intro_share:184    n: 58185    median: 0.163186    q25: 0.139187    q75: 0.184188    mean: 0.165189    min: 0.079190    max: 0.276191    median_ci95_bootstrap:192    - 0.154193    - 0.176194  conclusion_words:195    n: 58196    median: 315.0197    q25: 231.0198    q75: 394.75199    mean: 361.793200    min: 91.0201    max: 1878.0202    median_ci95_bootstrap:203    - 266.0204    - 349.0205  conclusion_share:206    n: 58207    median: 0.029208    q25: 0.023209    q75: 0.035210    mean: 0.033211    min: 0.008212    max: 0.21213    median_ci95_bootstrap:214    - 0.024215    - 0.031216  theory_share:217    n: 58218    median: 0.148219    q25: 0.0220    q75: 0.276221    mean: 0.17222    min: 0.0223    max: 0.714224    median_ci95_bootstrap:225    - 0.089226    - 0.195227  data_share:228    n: 58229    median: 0.0230    q25: 0.0231    q75: 0.109232    mean: 0.065233    min: 0.0234    max: 0.381235    median_ci95_bootstrap:236    - 0.0237    - 0.08238  results_share:239    n: 58240    median: 0.0241    q25: 0.0242    q75: 0.224243    mean: 0.115244    min: 0.0245    max: 0.517246    median_ci95_bootstrap:247    - 0.0248    - 0.073249  robustness_share:250    n: 58251    median: 0.0252    q25: 0.0253    q75: 0.04254    mean: 0.034255    min: 0.0256    max: 0.259257    median_ci95_bootstrap:258    - 0.0259    - 0.0260  words_per_table:261    n: 58262    median: 1117.591263    q25: 969.887264    q75: 1426.375265    mean: 1384.258266    min: 411.105267    max: 7367.0268    median_ci95_bootstrap:269    - 1059.098270    - 1275.714271  refs_per_1000_words:272    n: 58273    median: 4.989274    q25: 4.319275    q75: 6.01276    mean: 5.187277    min: 2.16278    max: 9.291279    median_ci95_bootstrap:280    - 4.488281    - 5.668282  equations_per_1000_words:283    n: 58284    median: 1.366285    q25: 0.841286    q75: 2.395287    mean: 1.629288    min: 0.0289    max: 6.711290    median_ci95_bootstrap:291    - 1.051292    - 1.812293presence:294  has_robustness_section:295    n: 58296    share: 0.259297  has_literature_section:298    n: 58299    share: 0.086300  has_appendix:301    n: 58302    share: 0.534303  has_internet_appendix:304    n: 58305    share: 0.914306by_year:307  2017:308    n: 13309    n_words_body_median: 11446.0310    n_tables_median: 9.0311  2018:312    n: 11313    n_words_body_median: 11622.0314    n_tables_median: 10.0315  2019:316    n: 22317    n_words_body_median: 10818.0318    n_tables_median: 9.5319  2020:320    n: 12321    n_words_body_median: 10748.5322    n_tables_median: 11.0323rhetoric:324  n_annotated: 58325  genre:326    n: 58327    mixed_theory_empirical: 0.534328    empirical: 0.466329  subfield:330    n: 58331    asset_pricing: 1.0332  primary_method:333    n: 58334    reduced_form_regression: 0.534335    structural_estimation: 0.138336    other: 0.086337    theoretical_model_analytical: 0.086338    survey_or_experiment: 0.052339    calibration_simulation: 0.034340    machine_learning_textual: 0.034341    instrumental_variables: 0.017342  abstract_moves_present:343    question:344      n: 58345      share: 0.655346    gap:347      n: 58348      share: 0.121349    method:350      n: 58351      share: 0.845352    results:353      n: 58354      share: 1.0355    magnitude:356      n: 58357      share: 0.207358    contribution:359      n: 58360      share: 0.69361  abstract_move_order_median_sentence:362    question:363      n: 38364      median: 0.0365      q25: 0.0366      q75: 0.0367      mean: 0.132368      min: 0.0369      max: 1.0370      median_ci95_bootstrap:371      - 0.0372      - 0.0373    gap:374      n: 7375      median: 0.0376      q25: 0.0377      q75: 1.0378      mean: 0.857379      min: 0.0380      max: 4.0381      median_ci95_bootstrap:382      - 0.0383      - 1.0384    method:385      n: 49386      median: 1.0387      q25: 0.0388      q75: 1.0389      mean: 0.939390      min: 0.0391      max: 4.0392      median_ci95_bootstrap:393      - 0.0394      - 1.0395    results:396      n: 58397      median: 1.0398      q25: 1.0399      q75: 2.0400      mean: 1.431401      min: 0.0402      max: 4.0403      median_ci95_bootstrap:404      - 1.0405      - 2.0406    magnitude:407      n: 12408      median: 2.0409      q25: 1.0410      q75: 4.0411      mean: 2.333412      min: 1.0413      max: 4.0414      median_ci95_bootstrap:415      - 1.0416      - 4.0417    contribution:418      n: 40419      median: 2.5420      q25: 0.75421      q75: 3.25422      mean: 2.2423      min: 0.0424      max: 6.0425      median_ci95_bootstrap:426      - 1.0427      - 3.0428  abstract_sentences:429    n: 58430    median: 5.0431    q25: 4.0432    q75: 5.0433    mean: 4.862434    min: 2.0435    max: 8.0436    median_ci95_bootstrap:437    - 4.5438    - 5.0439  magnitude_in_abstract_regex:440    n: 58441    share: 0.19442  introduction:443    paragraphs:444      n: 58445      median: 7.5446      q25: 6.0447      q75: 10.0448      mean: 8.293449      min: 2.0450      max: 19.0451      median_ci95_bootstrap:452      - 7.0453      - 8.0454    words:455      n: 58456      median: 1036.0457      q25: 834.0458      q75: 1369.25459      mean: 1118.603460      min: 446.0461      max: 2771.0462      median_ci95_bootstrap:463      - 922.5464      - 1191.287465    contribution_paragraph_index:466      n: 56467      median: 4.0468      q25: 1.0469      q75: 6.0470      mean: 4.286471      min: 0.0472      max: 16.0473      median_ci95_bootstrap:474      - 2.0475      - 5.0476    contribution_relative_position:477      n: 56478      median: 0.6479      q25: 0.178480      q75: 0.8481      mean: 0.49482      min: 0.0483      max: 0.9484      median_ci95_bootstrap:485      - 0.296486      - 0.667487    first_move:488      n: 58489      motivation: 0.845490      preview_of_approach: 0.052491      tension_or_puzzle: 0.034492      contribution_statement: 0.017493      literature_gap: 0.017494      mechanism_or_theory_sketch: 0.017495      other: 0.017496    move_prevalence:497      n: 58498      preview_of_results:499        share: 0.966500        median_relative_position: 0.36501      mechanism_or_theory_sketch:502        share: 0.931503        median_relative_position: 0.3504      related_literature_positioning:505        share: 0.897506        median_relative_position: 0.71507      motivation:508        share: 0.897509        median_relative_position: 0.0510      preview_of_approach:511        share: 0.879512        median_relative_position: 0.22513      contribution_statement:514        share: 0.862515        median_relative_position: 0.75516      roadmap:517        share: 0.672518        median_relative_position: 1.0519      tension_or_puzzle:520        share: 0.569521        median_relative_position: 0.1522      literature_gap:523        share: 0.5524        median_relative_position: 0.13525      robustness_mention:526        share: 0.328527        median_relative_position: 0.6528      identification_defense:529        share: 0.276530        median_relative_position: 0.63531      policy_or_broader_implication:532        share: 0.155533        median_relative_position: 0.77534      other:535        share: 0.121536        median_relative_position: 0.86537    moves_per_intro:538      n: 58539      median: 12.0540      q25: 10.0541      q75: 13.0542      mean: 12.052543      min: 7.0544      max: 20.0545      median_ci95_bootstrap:546      - 11.0547      - 12.0548    common_move_sequences:549      n: 58550      ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning551        > literature_gap > contribution_statement > policy_or_broader_implication > roadmap552      : 0.017553      ? motivation > mechanism_or_theory_sketch > preview_of_results > preview_of_approach > preview_of_results > identification_defense554        > preview_of_results > robustness_mention > related_literature_positioning > contribution_statement555      : 0.017556      ? motivation > related_literature_positioning > preview_of_approach > contribution_statement > preview_of_results >557        mechanism_or_theory_sketch > related_literature_positioning > contribution_statement > identification_defense > related_literature_positioning558      : 0.017559      ? motivation > preview_of_results > preview_of_approach > preview_of_results > related_literature_positioning > preview_of_results560        > policy_or_broader_implication > preview_of_results > related_literature_positioning > literature_gap > related_literature_positioning561        > contribution_statement > related_literature_positioning > roadmap562      : 0.017563      ? motivation > preview_of_approach > preview_of_results > preview_of_approach > mechanism_or_theory_sketch > related_literature_positioning564        > roadmap565      : 0.017566      ? motivation > tension_or_puzzle > literature_gap > contribution_statement > preview_of_results > related_literature_positioning567        > mechanism_or_theory_sketch > preview_of_results > robustness_mention > preview_of_approach > mechanism_or_theory_sketch568        > related_literature_positioning > other > roadmap569      : 0.017570    roadmap_present_llm:571      n: 58572      share: 0.672573    roadmap_present_regex:574      n: 58575      share: 0.638576    literature_positioning_location:577      n: 58578      inside_introduction: 0.931579      both: 0.069580    contribution_types:581      n: 129582      new_evidence: 0.45583      new_theory_or_model: 0.209584      new_data_or_measure: 0.163585      resolution_of_puzzle: 0.109586      new_method: 0.054587      new_identification: 0.016588  identification:589    causal_language_strength:590      n: 58591      median: 2.0592      q25: 2.0593      q75: 3.0594      mean: 2.414595      min: 1.0596      max: 4.0597      median_ci95_bootstrap:598      - 2.0599      - 2.0600    uses_causal_claim:601      n: 58602      share: 0.362603  results:604    economic_significance_discussed:605      n: 58606      share: 0.931607    statistical_language:608      n: 58609      unclear: 0.621610      stars_and_tstats: 0.19611      mixed: 0.138612      confidence_intervals: 0.034613      p_values: 0.017614    magnitude_statements_in_intro:615      n: 58616      share: 0.603617  robustness:618    location:619      n: 58620      mixed: 0.431621      within_results: 0.224622      main_text_section: 0.19623      none_seen: 0.086624      appendix: 0.052625      internet_appendix: 0.017626    types:627      n: 182628      alternative_specification: 0.264629      alternative_measure: 0.203630      subsample: 0.176631      other: 0.132632      alternative_sample_period: 0.104633      sensitivity_to_parameters: 0.055634      ? ''635      : 0.027636      placebo: 0.022637  tables:638    standard_errors:639      n: 58640      unclear: 0.672641      mixed: 0.103642      newey_west: 0.086643      clustered: 0.052644      none: 0.034645      robust: 0.034646      bootstrap: 0.017647    units_in_notes:648      n: 58649      share: 0.707650    clustered_regex:651      n: 58652      share: 0.052653  figures:654    uncertainty_shown:655      n: 58656      unclear: 0.517657      'no': 0.276658      mixed: 0.121659      no_figures: 0.052660      'yes': 0.034661  conclusion:662    bounded_claims:663      n: 58664      share: 0.793665    policy_implications:666      n: 58667      share: 0.086668    open_questions:669      n: 58670      share: 0.397671  hedging:672    n: 58673    moderate: 0.879674    low: 0.121675  claims_with_stated_evidence_share:676    n: 58677    median: 1.0678    q25: 1.0679    q75: 1.0680    mean: 0.993681    min: 0.857682    max: 1.0683    median_ci95_bootstrap:684    - 1.0685    - 1.0686  llm_vs_rule_section_role_agreement:687    n: 58688    median: 1.0689    q25: 0.833690    q75: 1.0691    mean: 0.915692    min: 0.5693    max: 1.0694    median_ci95_bootstrap:695    - 0.887696    - 1.0697  llm_confidence:698    n: 58699    median: 0.8700    q25: 0.8701    q75: 0.815702    mean: 0.806703    min: 0.75704    max: 0.85705    median_ci95_bootstrap:706    - 0.8707    - 0.8708
Files · main
Menu

Theme