{
 "study": "SGR-019",
 "pilot": false,
 "generated": "2026-10-13T09:28:00.458Z",
 "seed": 20261013,
 "bootstrap_resamples": 1000,
 "corpora": {
  "arxiv": {
   "clusters": 150,
   "docs": 2059475,
   "words": 333063827
  },
  "brand": {
   "clusters": 100,
   "docs": 7464,
   "words": 8872701,
   "pages_kept_all_dates": 15941,
   "brands": 116
  },
  "homepages": {
   "clusters": 158,
   "docs": 2950,
   "words": 1614547
  },
  "gutenberg": {
   "books": 1276,
   "words": 108615578,
   "sgr005": 453,
   "sgr006_only": 823
  },
  "web2021": {
   "pages": 6600,
   "words": 7940154
  }
 },
 "exclusions": {
  "arxiv": {
   "revised_after_nov_2022": 62860,
   "under_30_words": 2
  },
  "brand": {
   "date_not_primary_or_before_2015": 3956,
   "under_150_words": 191,
   "info_pack_excluded": 149,
   "undated": 4521,
   "duplicate_text": 140,
   "list_like": 635
  }
 },
 "series_by_year": [
  {
   "corpus": "arxiv",
   "year": 2015,
   "docs": 98402,
   "words": 14286881,
   "dashes": 3270,
   "per1000": 0.229,
   "lo": 0.203,
   "hi": 0.256,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.02
  },
  {
   "corpus": "arxiv",
   "year": 2016,
   "docs": 106269,
   "words": 15689112,
   "dashes": 3815,
   "per1000": 0.243,
   "lo": 0.221,
   "hi": 0.268,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.022
  },
  {
   "corpus": "arxiv",
   "year": 2017,
   "docs": 116436,
   "words": 17444447,
   "dashes": 4503,
   "per1000": 0.258,
   "lo": 0.232,
   "hi": 0.285,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.023
  },
  {
   "corpus": "arxiv",
   "year": 2018,
   "docs": 132932,
   "words": 20304983,
   "dashes": 5431,
   "per1000": 0.267,
   "lo": 0.238,
   "hi": 0.299,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.024
  },
  {
   "corpus": "arxiv",
   "year": 2019,
   "docs": 147213,
   "words": 22772903,
   "dashes": 6348,
   "per1000": 0.279,
   "lo": 0.246,
   "hi": 0.311,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.026
  },
  {
   "corpus": "arxiv",
   "year": 2020,
   "docs": 167223,
   "words": 26659253,
   "dashes": 7531,
   "per1000": 0.282,
   "lo": 0.255,
   "hi": 0.31,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.027
  },
  {
   "corpus": "arxiv",
   "year": 2021,
   "docs": 163481,
   "words": 26464950,
   "dashes": 7785,
   "per1000": 0.294,
   "lo": 0.254,
   "hi": 0.333,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.028
  },
  {
   "corpus": "arxiv",
   "year": 2022,
   "docs": 139926,
   "words": 22854486,
   "dashes": 6257,
   "per1000": 0.274,
   "lo": 0.24,
   "hi": 0.308,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.027
  },
  {
   "corpus": "arxiv",
   "year": 2023,
   "docs": 203120,
   "words": 33559068,
   "dashes": 9329,
   "per1000": 0.278,
   "lo": 0.239,
   "hi": 0.313,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.027
  },
  {
   "corpus": "arxiv",
   "year": 2024,
   "docs": 238596,
   "words": 39733971,
   "dashes": 10942,
   "per1000": 0.275,
   "lo": 0.237,
   "hi": 0.31,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.027
  },
  {
   "corpus": "arxiv",
   "year": 2025,
   "docs": 279293,
   "words": 46845754,
   "dashes": 19022,
   "per1000": 0.406,
   "lo": 0.353,
   "hi": 0.45,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.037
  },
  {
   "corpus": "arxiv",
   "year": 2026,
   "docs": 266584,
   "words": 46448019,
   "dashes": 22875,
   "per1000": 0.492,
   "lo": 0.417,
   "hi": 0.56,
   "strict_per1000": 0,
   "share_docs_with_dash": 0.041
  },
  {
   "corpus": "brand",
   "year": 2015,
   "docs": 310,
   "words": 283711,
   "dashes": 752,
   "per1000": 2.651,
   "lo": 1.81,
   "hi": 3.4,
   "strict_per1000": 2.651,
   "share_docs_with_dash": 0.555
  },
  {
   "corpus": "brand",
   "year": 2016,
   "docs": 284,
   "words": 265258,
   "dashes": 544,
   "per1000": 2.051,
   "lo": 1.526,
   "hi": 2.751,
   "strict_per1000": 2.051,
   "share_docs_with_dash": 0.514
  },
  {
   "corpus": "brand",
   "year": 2017,
   "docs": 339,
   "words": 318181,
   "dashes": 949,
   "per1000": 2.983,
   "lo": 2.304,
   "hi": 3.836,
   "strict_per1000": 2.983,
   "share_docs_with_dash": 0.596
  },
  {
   "corpus": "brand",
   "year": 2018,
   "docs": 376,
   "words": 375664,
   "dashes": 1331,
   "per1000": 3.543,
   "lo": 2.697,
   "hi": 4.619,
   "strict_per1000": 3.543,
   "share_docs_with_dash": 0.654
  },
  {
   "corpus": "brand",
   "year": 2019,
   "docs": 719,
   "words": 664608,
   "dashes": 1940,
   "per1000": 2.919,
   "lo": 2.566,
   "hi": 3.232,
   "strict_per1000": 2.919,
   "share_docs_with_dash": 0.675
  },
  {
   "corpus": "brand",
   "year": 2020,
   "docs": 725,
   "words": 746387,
   "dashes": 2091,
   "per1000": 2.801,
   "lo": 2.363,
   "hi": 3.252,
   "strict_per1000": 2.801,
   "share_docs_with_dash": 0.657
  },
  {
   "corpus": "brand",
   "year": 2021,
   "docs": 1021,
   "words": 1016753,
   "dashes": 2520,
   "per1000": 2.478,
   "lo": 2.159,
   "hi": 2.788,
   "strict_per1000": 2.478,
   "share_docs_with_dash": 0.639
  },
  {
   "corpus": "brand",
   "year": 2022,
   "docs": 953,
   "words": 973279,
   "dashes": 2664,
   "per1000": 2.737,
   "lo": 2.295,
   "hi": 3.174,
   "strict_per1000": 2.737,
   "share_docs_with_dash": 0.655
  },
  {
   "corpus": "brand",
   "year": 2023,
   "docs": 499,
   "words": 590838,
   "dashes": 1589,
   "per1000": 2.689,
   "lo": 2.345,
   "hi": 3.176,
   "strict_per1000": 2.689,
   "share_docs_with_dash": 0.685
  },
  {
   "corpus": "brand",
   "year": 2024,
   "docs": 604,
   "words": 913118,
   "dashes": 2225,
   "per1000": 2.437,
   "lo": 2.038,
   "hi": 2.846,
   "strict_per1000": 2.437,
   "share_docs_with_dash": 0.697
  },
  {
   "corpus": "brand",
   "year": 2025,
   "docs": 690,
   "words": 1194221,
   "dashes": 3102,
   "per1000": 2.598,
   "lo": 2.222,
   "hi": 3.066,
   "strict_per1000": 2.598,
   "share_docs_with_dash": 0.741
  },
  {
   "corpus": "brand",
   "year": 2026,
   "docs": 944,
   "words": 1530683,
   "dashes": 2976,
   "per1000": 1.944,
   "lo": 1.511,
   "hi": 2.445,
   "strict_per1000": 1.944,
   "share_docs_with_dash": 0.579
  },
  {
   "corpus": "homepages",
   "year": 2000,
   "docs": 39,
   "words": 8887,
   "dashes": 1,
   "per1000": 0.112,
   "lo": 0,
   "hi": 0.384,
   "strict_per1000": 0.112,
   "share_docs_with_dash": 0.026
  },
  {
   "corpus": "homepages",
   "year": 2001,
   "docs": 54,
   "words": 13739,
   "dashes": 11,
   "per1000": 0.801,
   "lo": 0.073,
   "hi": 1.933,
   "strict_per1000": 0.801,
   "share_docs_with_dash": 0.074
  },
  {
   "corpus": "homepages",
   "year": 2002,
   "docs": 60,
   "words": 14154,
   "dashes": 11,
   "per1000": 0.777,
   "lo": 0.133,
   "hi": 1.627,
   "strict_per1000": 0.777,
   "share_docs_with_dash": 0.083
  },
  {
   "corpus": "homepages",
   "year": 2003,
   "docs": 63,
   "words": 16856,
   "dashes": 9,
   "per1000": 0.534,
   "lo": 0,
   "hi": 1.311,
   "strict_per1000": 0.534,
   "share_docs_with_dash": 0.048
  },
  {
   "corpus": "homepages",
   "year": 2004,
   "docs": 74,
   "words": 19746,
   "dashes": 20,
   "per1000": 1.013,
   "lo": 0.198,
   "hi": 2.307,
   "strict_per1000": 1.013,
   "share_docs_with_dash": 0.081
  },
  {
   "corpus": "homepages",
   "year": 2005,
   "docs": 82,
   "words": 22755,
   "dashes": 16,
   "per1000": 0.703,
   "lo": 0.233,
   "hi": 1.181,
   "strict_per1000": 0.703,
   "share_docs_with_dash": 0.098
  },
  {
   "corpus": "homepages",
   "year": 2006,
   "docs": 101,
   "words": 30145,
   "dashes": 22,
   "per1000": 0.73,
   "lo": 0.3,
   "hi": 1.275,
   "strict_per1000": 0.73,
   "share_docs_with_dash": 0.099
  },
  {
   "corpus": "homepages",
   "year": 2007,
   "docs": 103,
   "words": 31130,
   "dashes": 17,
   "per1000": 0.546,
   "lo": 0.198,
   "hi": 1.009,
   "strict_per1000": 0.546,
   "share_docs_with_dash": 0.087
  },
  {
   "corpus": "homepages",
   "year": 2008,
   "docs": 103,
   "words": 32888,
   "dashes": 28,
   "per1000": 0.851,
   "lo": 0.307,
   "hi": 1.518,
   "strict_per1000": 0.851,
   "share_docs_with_dash": 0.117
  },
  {
   "corpus": "homepages",
   "year": 2009,
   "docs": 117,
   "words": 46177,
   "dashes": 26,
   "per1000": 0.563,
   "lo": 0.228,
   "hi": 1.002,
   "strict_per1000": 0.563,
   "share_docs_with_dash": 0.103
  },
  {
   "corpus": "homepages",
   "year": 2010,
   "docs": 120,
   "words": 49756,
   "dashes": 45,
   "per1000": 0.904,
   "lo": 0.461,
   "hi": 1.462,
   "strict_per1000": 0.904,
   "share_docs_with_dash": 0.158
  },
  {
   "corpus": "homepages",
   "year": 2011,
   "docs": 122,
   "words": 58744,
   "dashes": 45,
   "per1000": 0.766,
   "lo": 0.424,
   "hi": 1.302,
   "strict_per1000": 0.766,
   "share_docs_with_dash": 0.18
  },
  {
   "corpus": "homepages",
   "year": 2012,
   "docs": 124,
   "words": 74359,
   "dashes": 40,
   "per1000": 0.538,
   "lo": 0.291,
   "hi": 0.906,
   "strict_per1000": 0.538,
   "share_docs_with_dash": 0.185
  },
  {
   "corpus": "homepages",
   "year": 2013,
   "docs": 124,
   "words": 59664,
   "dashes": 34,
   "per1000": 0.57,
   "lo": 0.309,
   "hi": 0.902,
   "strict_per1000": 0.57,
   "share_docs_with_dash": 0.161
  },
  {
   "corpus": "homepages",
   "year": 2014,
   "docs": 128,
   "words": 66738,
   "dashes": 62,
   "per1000": 0.929,
   "lo": 0.489,
   "hi": 1.453,
   "strict_per1000": 0.929,
   "share_docs_with_dash": 0.18
  },
  {
   "corpus": "homepages",
   "year": 2015,
   "docs": 136,
   "words": 74287,
   "dashes": 77,
   "per1000": 1.036,
   "lo": 0.554,
   "hi": 1.587,
   "strict_per1000": 1.036,
   "share_docs_with_dash": 0.213
  },
  {
   "corpus": "homepages",
   "year": 2016,
   "docs": 132,
   "words": 67377,
   "dashes": 58,
   "per1000": 0.861,
   "lo": 0.489,
   "hi": 1.323,
   "strict_per1000": 0.861,
   "share_docs_with_dash": 0.197
  },
  {
   "corpus": "homepages",
   "year": 2017,
   "docs": 126,
   "words": 70391,
   "dashes": 57,
   "per1000": 0.81,
   "lo": 0.518,
   "hi": 1.176,
   "strict_per1000": 0.81,
   "share_docs_with_dash": 0.23
  },
  {
   "corpus": "homepages",
   "year": 2018,
   "docs": 131,
   "words": 82910,
   "dashes": 71,
   "per1000": 0.856,
   "lo": 0.526,
   "hi": 1.244,
   "strict_per1000": 0.856,
   "share_docs_with_dash": 0.267
  },
  {
   "corpus": "homepages",
   "year": 2019,
   "docs": 133,
   "words": 85968,
   "dashes": 91,
   "per1000": 1.058,
   "lo": 0.618,
   "hi": 1.618,
   "strict_per1000": 1.058,
   "share_docs_with_dash": 0.286
  },
  {
   "corpus": "homepages",
   "year": 2020,
   "docs": 132,
   "words": 82358,
   "dashes": 96,
   "per1000": 1.165,
   "lo": 0.744,
   "hi": 1.674,
   "strict_per1000": 1.165,
   "share_docs_with_dash": 0.295
  },
  {
   "corpus": "homepages",
   "year": 2021,
   "docs": 136,
   "words": 101018,
   "dashes": 85,
   "per1000": 0.841,
   "lo": 0.546,
   "hi": 1.307,
   "strict_per1000": 0.841,
   "share_docs_with_dash": 0.279
  },
  {
   "corpus": "homepages",
   "year": 2022,
   "docs": 128,
   "words": 82534,
   "dashes": 74,
   "per1000": 0.897,
   "lo": 0.564,
   "hi": 1.323,
   "strict_per1000": 0.897,
   "share_docs_with_dash": 0.266
  },
  {
   "corpus": "homepages",
   "year": 2023,
   "docs": 129,
   "words": 88573,
   "dashes": 91,
   "per1000": 1.027,
   "lo": 0.684,
   "hi": 1.403,
   "strict_per1000": 1.027,
   "share_docs_with_dash": 0.318
  },
  {
   "corpus": "homepages",
   "year": 2024,
   "docs": 125,
   "words": 109922,
   "dashes": 77,
   "per1000": 0.7,
   "lo": 0.425,
   "hi": 1.025,
   "strict_per1000": 0.7,
   "share_docs_with_dash": 0.288
  },
  {
   "corpus": "homepages",
   "year": 2025,
   "docs": 121,
   "words": 111339,
   "dashes": 98,
   "per1000": 0.88,
   "lo": 0.588,
   "hi": 1.221,
   "strict_per1000": 0.88,
   "share_docs_with_dash": 0.347
  },
  {
   "corpus": "homepages",
   "year": 2026,
   "docs": 107,
   "words": 112132,
   "dashes": 128,
   "per1000": 1.142,
   "lo": 0.79,
   "hi": 1.681,
   "strict_per1000": 1.142,
   "share_docs_with_dash": 0.383
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1810,
   "docs": 8,
   "words": 1167037,
   "dashes": 9548,
   "per1000": 8.181,
   "lo": 8.181,
   "hi": 8.181,
   "strict_per1000": 2.354,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1820,
   "docs": 20,
   "words": 3253642,
   "dashes": 29990,
   "per1000": 9.217,
   "lo": 3.414,
   "hi": 11.701,
   "strict_per1000": 1.439,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1830,
   "docs": 8,
   "words": 1391143,
   "dashes": 10838,
   "per1000": 7.791,
   "lo": 5.019,
   "hi": 11.878,
   "strict_per1000": 1.43,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1840,
   "docs": 22,
   "words": 3430793,
   "dashes": 19721,
   "per1000": 5.748,
   "lo": 4.009,
   "hi": 10.164,
   "strict_per1000": 1.881,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1850,
   "docs": 12,
   "words": 2160545,
   "dashes": 12371,
   "per1000": 5.726,
   "lo": 2.965,
   "hi": 7.197,
   "strict_per1000": 2.087,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1860,
   "docs": 21,
   "words": 4009289,
   "dashes": 26258,
   "per1000": 6.549,
   "lo": 3.852,
   "hi": 7.539,
   "strict_per1000": 1.976,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1870,
   "docs": 37,
   "words": 5138206,
   "dashes": 37968,
   "per1000": 7.389,
   "lo": 5.354,
   "hi": 8.795,
   "strict_per1000": 1.933,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1880,
   "docs": 33,
   "words": 3693576,
   "dashes": 25151,
   "per1000": 6.809,
   "lo": 5.103,
   "hi": 8.411,
   "strict_per1000": 1.929,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1890,
   "docs": 47,
   "words": 4177130,
   "dashes": 29779,
   "per1000": 7.129,
   "lo": 4.546,
   "hi": 10.414,
   "strict_per1000": 3.387,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1900,
   "docs": 74,
   "words": 5741755,
   "dashes": 39934,
   "per1000": 6.955,
   "lo": 4.964,
   "hi": 8.915,
   "strict_per1000": 3.476,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1910,
   "docs": 99,
   "words": 7489709,
   "dashes": 42113,
   "per1000": 5.623,
   "lo": 4.723,
   "hi": 6.712,
   "strict_per1000": 2.262,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1920,
   "docs": 57,
   "words": 4760594,
   "dashes": 27447,
   "per1000": 5.765,
   "lo": 4.004,
   "hi": 8.174,
   "strict_per1000": 2.265,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1930,
   "docs": 11,
   "words": 830043,
   "dashes": 3698,
   "per1000": 4.455,
   "lo": 2.413,
   "hi": 9.707,
   "strict_per1000": 0.699,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1940,
   "docs": 2,
   "words": 182047,
   "dashes": 2089,
   "per1000": 11.475,
   "lo": 11.475,
   "hi": 11.475,
   "strict_per1000": 0,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1950,
   "docs": 1,
   "words": 97280,
   "dashes": 1300,
   "per1000": 13.363,
   "lo": 13.363,
   "hi": 13.363,
   "strict_per1000": 0,
   "share_docs_with_dash": null
  },
  {
   "corpus": "gutenberg_decades",
   "year": 1960,
   "docs": 1,
   "words": 51621,
   "dashes": 449,
   "per1000": 8.698,
   "lo": 8.698,
   "hi": 8.698,
   "strict_per1000": 0,
   "share_docs_with_dash": null
  }
 ],
 "gutenberg_bands": [
  {
   "band": "1700s",
   "books": 231,
   "words": 19930518,
   "per1000": 3.824,
   "lo": 2.875,
   "hi": 4.952,
   "strict_per1000": 0.919
  },
  {
   "band": "1800s",
   "books": 503,
   "words": 51716623,
   "per1000": 6.286,
   "lo": 5.446,
   "hi": 7.06,
   "strict_per1000": 1.589
  },
  {
   "band": "early 1900s",
   "books": 542,
   "words": 36968437,
   "per1000": 5.55,
   "lo": 4.878,
   "hi": 6.276,
   "strict_per1000": 1.737
  }
 ],
 "hypotheses": {
  "H1": {
   "corpus": "brand",
   "result": "not supported",
   "obs": 2.282,
   "proj": 2.694,
   "diff": -0.412,
   "diff_lo": -1.058,
   "diff_hi": 0.27,
   "ratio": 0.847,
   "ratio_lo": 0.668,
   "ratio_hi": 1.126,
   "clusters": 100,
   "post_words": 3638022
  },
  "H2": {
   "corpus": "arxiv",
   "result": "supported",
   "obs": 0.397,
   "proj": 0.317,
   "diff": 0.08,
   "diff_lo": 0.059,
   "diff_hi": 0.108,
   "ratio": 1.254,
   "ratio_lo": 1.18,
   "ratio_hi": 1.354,
   "clusters": 150,
   "post_words": 133027744
  },
  "H3": {
   "corpus": "homepages",
   "result": "not supported",
   "obs": 0.909,
   "proj": 0.943,
   "diff": -0.034,
   "diff_lo": -0.617,
   "diff_hi": 0.535,
   "ratio": 0.964,
   "ratio_lo": 0.579,
   "ratio_hi": 2.317,
   "clusters": 158,
   "post_words": 333393
  },
  "H4a": {
   "ratio": 0.467,
   "lo": 0.39,
   "hi": 0.567,
   "a": 2.282,
   "b": 4.89,
   "result": "supported",
   "name": "brand 2024-26 vs 19th-century non-fiction books"
  },
  "H4b": {
   "ratio": 0.075,
   "lo": 0.054,
   "hi": 0.119,
   "a": 0.397,
   "b": 5.321,
   "result": "supported",
   "name": "arXiv 2024-26 vs 19th-century science books"
  },
  "H5": {
   "corpus": "brand",
   "early": 2.877,
   "late": 2.715,
   "ratio": 0.944,
   "lo": 0.793,
   "hi": 1.169,
   "result": "not supported"
  },
  "H6": {
   "corpus": "brand",
   "brands": 52,
   "higher": 28,
   "share": 0.538,
   "lo": 0.405,
   "hi": 0.667,
   "result": "not supported"
  }
 },
 "exploratory": {
  "levels": {
   "brand_late": {
    "per1000": 2.715,
    "lo": 2.436,
    "hi": 2.992,
    "words": 3378329,
    "docs": 3402,
    "clusters": 100
   },
   "brand_after": {
    "per1000": 2.282,
    "lo": 1.993,
    "hi": 2.623,
    "words": 3638022,
    "docs": 2238,
    "clusters": 100
   },
   "brand_early": {
    "per1000": 2.877,
    "lo": 2.34,
    "hi": 3.482,
    "words": 1242814,
    "docs": 1309,
    "clusters": 100
   },
   "arxiv_late": {
    "per1000": 0.283,
    "lo": 0.253,
    "hi": 0.315,
    "words": 96420143,
    "docs": 603430,
    "clusters": 150
   },
   "arxiv_after": {
    "per1000": 0.397,
    "lo": 0.341,
    "hi": 0.45,
    "words": 133027744,
    "docs": 784473,
    "clusters": 150
   },
   "arxiv_early": {
    "per1000": 0.251,
    "lo": 0.229,
    "hi": 0.278,
    "words": 67725423,
    "docs": 454039,
    "clusters": 150
   },
   "gutenberg_1800s_all": {
    "per1000": 6.286,
    "lo": 5.442,
    "hi": 7.075,
    "words": 51716623,
    "docs": 503,
    "clusters": 271
   },
   "gutenberg_1800s_nonfiction": {
    "per1000": 4.89,
    "lo": 4.312,
    "hi": 5.56,
    "words": 18626633,
    "docs": 207,
    "clusters": 178
   },
   "gutenberg_1800s_science": {
    "per1000": 5.321,
    "lo": 3.44,
    "hi": 6.996,
    "words": 2229373,
    "docs": 29,
    "clusters": 26
   },
   "gutenberg_1800s_fiction_literary": {
    "per1000": 7.072,
    "lo": 5.814,
    "hi": 8.228,
    "words": 33089990,
    "docs": 296,
    "clusters": 102
   }
  },
  "change": {
   "brand_after_vs_late": {
    "ratio": 0.841,
    "lo": 0.721,
    "hi": 1.005,
    "a": 2.282,
    "b": 2.715
   },
   "arxiv_after_vs_late": {
    "ratio": 1.404,
    "lo": 1.183,
    "hi": 1.665,
    "a": 0.397,
    "b": 0.283
   },
   "brand_after_vs_gutenberg_1800s_fiction": {
    "ratio": 0.323,
    "lo": 0.261,
    "hi": 0.41,
    "a": 2.282,
    "b": 7.072
   },
   "brand_after_vs_gutenberg_1800s_all": {
    "ratio": 0.363,
    "lo": 0.306,
    "hi": 0.45,
    "a": 2.282,
    "b": 6.286
   }
  },
  "rank_of_today_among_gutenberg_books": {
   "brand_after_per1000": 2.282,
   "books_below": 345,
   "books": 1276
  },
  "arxiv_by_group": [
   {
    "group": "cs",
    "clusters": 39,
    "docs": 739630,
    "late": 0.339,
    "after": {
     "per1000": 0.445,
     "lo": 0.343,
     "hi": 0.539,
     "words": 64718474,
     "docs": 361020,
     "clusters": 39
    },
    "early": 0.318,
    "trend": {
     "result": "supported",
     "obs": 0.445,
     "proj": 0.348,
     "diff": 0.096,
     "diff_lo": 0.064,
     "diff_hi": 0.141,
     "ratio": 1.277,
     "ratio_lo": 1.164,
     "ratio_hi": 1.47,
     "clusters": 39,
     "post_words": 64718474
    }
   },
   {
    "group": "econ",
    "clusters": 3,
    "docs": 11729,
    "late": 0.434,
    "after": {
     "per1000": 0.829,
     "lo": 0.69,
     "hi": 1.15,
     "words": 934168,
     "docs": 6058,
     "clusters": 3
    },
    "early": 0.238,
    "trend": {
     "result": "supported",
     "obs": 0.829,
     "proj": 0.529,
     "diff": 0.3,
     "diff_lo": 0.029,
     "diff_hi": 0.346,
     "ratio": 1.567,
     "ratio_lo": 1.026,
     "ratio_hi": 1.878,
     "clusters": 3,
     "post_words": 934168
    }
   },
   {
    "group": "eess",
    "clusters": 4,
    "docs": 79127,
    "late": 0.13,
    "after": {
     "per1000": 0.175,
     "lo": 0.145,
     "hi": 0.209,
     "words": 5815401,
     "docs": 33645,
     "clusters": 4
    },
    "early": 0.145,
    "trend": {
     "result": "supported",
     "obs": 0.175,
     "proj": 0.116,
     "diff": 0.059,
     "diff_lo": 0.034,
     "diff_hi": 0.109,
     "ratio": 1.508,
     "ratio_lo": 1.246,
     "ratio_hi": 2.564,
     "clusters": 4,
     "post_words": 5815401
    }
   },
   {
    "group": "math",
    "clusters": 30,
    "docs": 348143,
    "late": 0.198,
    "after": {
     "per1000": 0.273,
     "lo": 0.235,
     "hi": 0.313,
     "words": 14774699,
     "docs": 115260,
     "clusters": 30
    },
    "early": 0.195,
    "trend": {
     "result": "supported",
     "obs": 0.273,
     "proj": 0.207,
     "diff": 0.066,
     "diff_lo": 0.042,
     "diff_hi": 0.096,
     "ratio": 1.317,
     "ratio_lo": 1.193,
     "ratio_hi": 1.496,
     "clusters": 30,
     "post_words": 14774699
    }
   },
   {
    "group": "physics",
    "clusters": 51,
    "docs": 791318,
    "late": 0.273,
    "after": {
     "per1000": 0.379,
     "lo": 0.33,
     "hi": 0.43,
     "words": 41315899,
     "docs": 237532,
     "clusters": 51
    },
    "early": 0.239,
    "trend": {
     "result": "supported",
     "obs": 0.379,
     "proj": 0.311,
     "diff": 0.068,
     "diff_lo": 0.037,
     "diff_hi": 0.098,
     "ratio": 1.22,
     "ratio_lo": 1.12,
     "ratio_hi": 1.317,
     "clusters": 51,
     "post_words": 41315899
    }
   },
   {
    "group": "q-bio",
    "clusters": 10,
    "docs": 25050,
    "late": 0.305,
    "after": {
     "per1000": 0.48,
     "lo": 0.25,
     "hi": 0.632,
     "words": 1507565,
     "docs": 8117,
     "clusters": 10
    },
    "early": 0.273,
    "trend": {
     "result": "not supported",
     "obs": 0.48,
     "proj": 0.358,
     "diff": 0.122,
     "diff_lo": -0.088,
     "diff_hi": 0.267,
     "ratio": 1.34,
     "ratio_lo": 0.747,
     "ratio_hi": 1.768,
     "clusters": 10,
     "post_words": 1507565
    }
   },
   {
    "group": "q-fin",
    "clusters": 8,
    "docs": 9724,
    "late": 0.311,
    "after": {
     "per1000": 0.484,
     "lo": 0.411,
     "hi": 0.567,
     "words": 553861,
     "docs": 3386,
     "clusters": 8
    },
    "early": 0.289,
    "trend": {
     "result": "supported",
     "obs": 0.484,
     "proj": 0.326,
     "diff": 0.158,
     "diff_lo": 0.023,
     "diff_hi": 0.33,
     "ratio": 1.484,
     "ratio_lo": 1.059,
     "ratio_hi": 2.505,
     "clusters": 8,
     "post_words": 553861
    }
   },
   {
    "group": "stat",
    "clusters": 5,
    "docs": 54754,
    "late": 0.347,
    "after": {
     "per1000": 0.462,
     "lo": 0.335,
     "hi": 0.603,
     "words": 3407677,
     "docs": 19455,
     "clusters": 5
    },
    "early": 0.325,
    "trend": {
     "result": "supported",
     "obs": 0.462,
     "proj": 0.386,
     "diff": 0.076,
     "diff_lo": 0.022,
     "diff_hi": 0.114,
     "ratio": 1.197,
     "ratio_lo": 1.056,
     "ratio_hi": 1.389,
     "clusters": 5,
     "post_words": 3407677
    }
   }
  ],
  "brand_by_sector": [
   {
    "group": "bank",
    "clusters": 16,
    "docs": 1087,
    "late": 2.27,
    "after": {
     "per1000": 3.309,
     "lo": 2.517,
     "hi": 4.59,
     "words": 168020,
     "docs": 164,
     "clusters": 16
    },
    "early": 2.609,
    "trend": {
     "result": "not supported",
     "obs": 3.309,
     "proj": 2.153,
     "diff": 1.156,
     "diff_lo": -0.562,
     "diff_hi": 3.638,
     "ratio": 1.537,
     "ratio_lo": 0.841,
     "ratio_hi": 8.448,
     "clusters": 16,
     "post_words": 168020
    }
   },
   {
    "group": "charity",
    "clusters": 9,
    "docs": 965,
    "late": 2.379,
    "after": {
     "per1000": 2.36,
     "lo": 1.692,
     "hi": 3.071,
     "words": 295736,
     "docs": 320,
     "clusters": 9
    },
    "early": 2.089,
    "trend": {
     "result": "not supported",
     "obs": 2.36,
     "proj": 2.613,
     "diff": -0.252,
     "diff_lo": -1.664,
     "diff_hi": 1.14,
     "ratio": 0.903,
     "ratio_lo": 0.51,
     "ratio_hi": 1.721,
     "clusters": 9,
     "post_words": 295736
    }
   },
   {
    "group": "energy",
    "clusters": 11,
    "docs": 841,
    "late": 2.982,
    "after": {
     "per1000": 1.724,
     "lo": 0.575,
     "hi": 3.807,
     "words": 407890,
     "docs": 321,
     "clusters": 11
    },
    "early": 3.752,
    "trend": {
     "result": "not supported",
     "obs": 1.724,
     "proj": 2.203,
     "diff": -0.479,
     "diff_lo": -2.929,
     "diff_hi": 2.175,
     "ratio": 0.782,
     "ratio_lo": 0.178,
     "ratio_hi": 3.417,
     "clusters": 11,
     "post_words": 407890
    }
   },
   {
    "group": "fashion",
    "clusters": 6,
    "docs": 76,
    "late": 3.039,
    "after": {
     "per1000": 1.461,
     "lo": 0.481,
     "hi": 1.472,
     "words": 184092,
     "docs": 10,
     "clusters": 6
    },
    "early": 11.19,
    "trend": {
     "result": "not supported",
     "obs": 1.461,
     "proj": -1.558,
     "diff": 3.019,
     "diff_lo": -3.058,
     "diff_hi": 5.61,
     "ratio": null,
     "ratio_lo": 0.176,
     "ratio_hi": 63.259,
     "clusters": 6,
     "post_words": 184092
    }
   },
   {
    "group": "food",
    "clusters": 6,
    "docs": 284,
    "late": 3.044,
    "after": {
     "per1000": 3.492,
     "lo": 1.066,
     "hi": 3.631,
     "words": 86200,
     "docs": 86,
     "clusters": 6
    },
    "early": 2.419,
    "trend": {
     "result": "not supported",
     "obs": 3.492,
     "proj": 1.676,
     "diff": 1.816,
     "diff_lo": -3.426,
     "diff_hi": 11.578,
     "ratio": 2.084,
     "ratio_lo": 0.243,
     "ratio_hi": 14.027,
     "clusters": 6,
     "post_words": 86200
    }
   },
   {
    "group": "grocery",
    "clusters": 8,
    "docs": 218,
    "late": 1.736,
    "after": {
     "per1000": 2.901,
     "lo": 1.385,
     "hi": 3.315,
     "words": 186800,
     "docs": 61,
     "clusters": 8
    },
    "early": 2.495,
    "trend": {
     "result": "not supported",
     "obs": 2.901,
     "proj": 1.734,
     "diff": 1.167,
     "diff_lo": -1.19,
     "diff_hi": 2.325,
     "ratio": 1.673,
     "ratio_lo": 0.573,
     "ratio_hi": 3.654,
     "clusters": 8,
     "post_words": 186800
    }
   },
   {
    "group": "insurance",
    "clusters": 10,
    "docs": 1205,
    "late": 2.507,
    "after": {
     "per1000": 2.186,
     "lo": 1.416,
     "hi": 2.679,
     "words": 540647,
     "docs": 469,
     "clusters": 10
    },
    "early": 1.799,
    "trend": {
     "result": "reversed",
     "obs": 2.186,
     "proj": 3.107,
     "diff": -0.921,
     "diff_lo": -1.308,
     "diff_hi": -0.298,
     "ratio": 0.704,
     "ratio_lo": 0.558,
     "ratio_hi": 0.872,
     "clusters": 10,
     "post_words": 540647
    }
   },
   {
    "group": "software",
    "clusters": 16,
    "docs": 1818,
    "late": 3.026,
    "after": {
     "per1000": 2.29,
     "lo": 2.022,
     "hi": 3.068,
     "words": 1566361,
     "docs": 605,
     "clusters": 16
    },
    "early": 3.221,
    "trend": {
     "result": "not supported",
     "obs": 2.29,
     "proj": 3.087,
     "diff": -0.797,
     "diff_lo": -1.927,
     "diff_hi": 0.226,
     "ratio": 0.742,
     "ratio_lo": 0.541,
     "ratio_hi": 1.106,
     "clusters": 16,
     "post_words": 1566361
    }
   },
   {
    "group": "telecom",
    "clusters": 13,
    "docs": 804,
    "late": 3.337,
    "after": {
     "per1000": 2.322,
     "lo": 1.59,
     "hi": 3.382,
     "words": 174451,
     "docs": 176,
     "clusters": 13
    },
    "early": 2.73,
    "trend": {
     "result": "not supported",
     "obs": 2.322,
     "proj": 3.679,
     "diff": -1.357,
     "diff_lo": -2.905,
     "diff_hi": 1.298,
     "ratio": 0.631,
     "ratio_lo": 0.376,
     "ratio_hi": 1.593,
     "clusters": 13,
     "post_words": 174451
    }
   },
   {
    "group": "travel",
    "clusters": 5,
    "docs": 166,
    "late": 1.479,
    "after": {
     "per1000": 2.156,
     "lo": 1.127,
     "hi": 4.667,
     "words": 27825,
     "docs": 26,
     "clusters": 5
    },
    "early": 1.496,
    "trend": {
     "result": "not supported",
     "obs": 2.156,
     "proj": 1.673,
     "diff": 0.483,
     "diff_lo": -12.08,
     "diff_hi": 3.226,
     "ratio": 1.289,
     "ratio_lo": 0.089,
     "ratio_hi": 3.466,
     "clusters": 5,
     "post_words": 27825
    }
   }
  ],
  "gutenberg_by_genre": [
   {
    "genre": "biography",
    "books": 89,
    "by_band": [
     {
      "band": "1700s",
      "books": 29,
      "per1000": 1.685
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 4.825
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 3.419
     }
    ]
   },
   {
    "genre": "children",
    "books": 60,
    "by_band": [
     {
      "band": "1700s",
      "books": 0,
      "per1000": null
     },
     {
      "band": "1800s",
      "books": 29,
      "per1000": 4.884
     },
     {
      "band": "early 1900s",
      "books": 31,
      "per1000": 3.988
     }
    ]
   },
   {
    "genre": "drama",
    "books": 90,
    "by_band": [
     {
      "band": "1700s",
      "books": 30,
      "per1000": 10.897
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 8.085
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 9.505
     }
    ]
   },
   {
    "genre": "essays",
    "books": 59,
    "by_band": [
     {
      "band": "1700s",
      "books": 0,
      "per1000": null
     },
     {
      "band": "1800s",
      "books": 29,
      "per1000": 4.512
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 5.303
     }
    ]
   },
   {
    "genre": "fiction",
    "books": 90,
    "by_band": [
     {
      "band": "1700s",
      "books": 30,
      "per1000": 4.47
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 7.313
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 6.821
     }
    ]
   },
   {
    "genre": "fiction_or_literary",
    "books": 450,
    "by_band": [
     {
      "band": "1700s",
      "books": 0,
      "per1000": null
     },
     {
      "band": "1800s",
      "books": 206,
      "per1000": 7.123
     },
     {
      "band": "early 1900s",
      "books": 244,
      "per1000": 6.118
     }
    ]
   },
   {
    "genre": "history",
    "books": 86,
    "by_band": [
     {
      "band": "1700s",
      "books": 26,
      "per1000": 2.594
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 4.587
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 4.586
     }
    ]
   },
   {
    "genre": "letters",
    "books": 89,
    "by_band": [
     {
      "band": "1700s",
      "books": 29,
      "per1000": 6.832
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 6.002
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 5.173
     }
    ]
   },
   {
    "genre": "philosophy_religion",
    "books": 85,
    "by_band": [
     {
      "band": "1700s",
      "books": 28,
      "per1000": 1.874
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 3.642
     },
     {
      "band": "early 1900s",
      "books": 27,
      "per1000": 2.67
     }
    ]
   },
   {
    "genre": "science",
    "books": 89,
    "by_band": [
     {
      "band": "1700s",
      "books": 30,
      "per1000": 2.18
     },
     {
      "band": "1800s",
      "books": 29,
      "per1000": 5.321
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 5.313
     }
    ]
   },
   {
    "genre": "travel",
    "books": 89,
    "by_band": [
     {
      "band": "1700s",
      "books": 29,
      "per1000": 2.688
     },
     {
      "band": "1800s",
      "books": 30,
      "per1000": 4.93
     },
     {
      "band": "early 1900s",
      "books": 30,
      "per1000": 4.331
     }
    ]
   }
  ],
  "gutenberg_convention": {
   "note": "Strict rate counts U+2014 and spaced en dashes only; the primary rule adds plain-text '--' and '---'.",
   "all_books_primary": 5.584,
   "all_books_strict": 1.517
  },
  "web2021": {
   "note": "Reused SGR-007 rows: U+2014 only (no spaced en dash). 2021 captures.",
   "all": {
    "per1000": 0.955,
    "lo": 0.608,
    "hi": 1.37,
    "pages": 6600
   },
   "groups": [
    {
     "group": "blogging_platform",
     "pages": 200,
     "per1000": 3.968,
     "lo": null,
     "hi": null
    },
    {
     "group": "careers_advice",
     "pages": 200,
     "per1000": 0.985,
     "lo": null,
     "hi": null
    },
    {
     "group": "essay_mills",
     "pages": 600,
     "per1000": 0.033,
     "lo": 0.023,
     "hi": 0.05
    },
    {
     "group": "government",
     "pages": 200,
     "per1000": 0,
     "lo": null,
     "hi": null
    },
    {
     "group": "how_to_content",
     "pages": 400,
     "per1000": 0.762,
     "lo": null,
     "hi": null
    },
    {
     "group": "marketing_seo_blogs",
     "pages": 600,
     "per1000": 0.995,
     "lo": 0.647,
     "hi": 1.765
    },
    {
     "group": "news_india",
     "pages": 400,
     "per1000": 0.906,
     "lo": null,
     "hi": null
    },
    {
     "group": "news_kenya",
     "pages": 600,
     "per1000": 0.366,
     "lo": 0.22,
     "hi": 0.55
    },
    {
     "group": "news_nigeria",
     "pages": 600,
     "per1000": 0.426,
     "lo": 0.361,
     "hi": 0.488
    },
    {
     "group": "news_philippines",
     "pages": 200,
     "per1000": 3.668,
     "lo": null,
     "hi": null
    },
    {
     "group": "news_uk",
     "pages": 400,
     "per1000": 0.108,
     "lo": null,
     "hi": null
    },
    {
     "group": "news_us",
     "pages": 600,
     "per1000": 2.438,
     "lo": 1.932,
     "hi": 3.318
    },
    {
     "group": "press_releases",
     "pages": 600,
     "per1000": 0.368,
     "lo": 0.288,
     "hi": 0.519
    },
    {
     "group": "qa_forum",
     "pages": 200,
     "per1000": 0.499,
     "lo": null,
     "hi": null
    },
    {
     "group": "self_help",
     "pages": 600,
     "per1000": 2.353,
     "lo": 1.15,
     "hi": 4.512
    },
    {
     "group": "wikipedia",
     "pages": 200,
     "per1000": 0.591,
     "lo": null,
     "hi": null
    }
   ]
  },
  "arxiv_ascii_only_note": "arXiv metadata is ASCII: its strict rate is zero by construction."
 },
 "runtime_seconds": 932
}