{
  "dataset": "BabyLM 2026 English",
  "status": "Acquired and audited; preparation and training recorded separately.",
  "acquisition_sha256": "b1e040fb0df288c5595341f1597f163c78f636a4a606c578525b2ac0e613c84a",
  "overlap_sha256": "cee4b8bd60623c153c2db58b8dd4dac11c49a8ec335fb82dfed8eacfe7d19a54",
  "files": [
    {
      "partition": "train-10m",
      "component": "bnc_spoken",
      "path": "data\\raw\\babylm-2026\\train-10m\\bnc_spoken.train.txt",
      "utf8_bytes": 4064608,
      "sha256": "8f3042f4104cf356052fda784682d8e8170fd1fd8c795a1c3e172f9eb2ebfa3c",
      "source_verified": true,
      "lines": 65220,
      "blank_lines": 0,
      "whitespace_words": 762073,
      "characters": 4063323,
      "crlf_lines": 0,
      "longest_line_bytes": 1570
    },
    {
      "partition": "train-10m",
      "component": "childes",
      "path": "data\\raw\\babylm-2026\\train-10m\\childes.train.txt",
      "utf8_bytes": 15159891,
      "sha256": "c898c0a44f4380ce7a66766acd01e70eebbbd9410a1701ddf89452ea6f5aea45",
      "source_verified": true,
      "lines": 531305,
      "blank_lines": 0,
      "whitespace_words": 2841101,
      "characters": 15159502,
      "crlf_lines": 0,
      "longest_line_bytes": 851
    },
    {
      "partition": "train-10m",
      "component": "gutenberg",
      "path": "data\\raw\\babylm-2026\\train-10m\\gutenberg.train.txt",
      "utf8_bytes": 14031163,
      "sha256": "4ddcf5774a7947293ceb56dc76774f553b534231e7ac636c071559229cf2cb9b",
      "source_verified": true,
      "lines": 59934,
      "blank_lines": 0,
      "whitespace_words": 2557721,
      "characters": 13978877,
      "crlf_lines": 0,
      "longest_line_bytes": 5306
    },
    {
      "partition": "train-10m",
      "component": "open_subtitles",
      "path": "data\\raw\\babylm-2026\\train-10m\\open_subtitles.train.txt",
      "utf8_bytes": 12159704,
      "sha256": "9b21adecf57dd97f611d9442a2f993d2f843278eb24fc98f4165322c1ba5670a",
      "source_verified": true,
      "lines": 386046,
      "blank_lines": 0,
      "whitespace_words": 2282877,
      "characters": 12144973,
      "crlf_lines": 0,
      "longest_line_bytes": 409
    },
    {
      "partition": "train-10m",
      "component": "simple_wiki",
      "path": "data\\raw\\babylm-2026\\train-10m\\simple_wiki.train.txt",
      "utf8_bytes": 8861946,
      "sha256": "0ac614aa069ea3908c07c9755bf80bb500d4cee15cd972e9f93cccf89639e9a7",
      "source_verified": true,
      "lines": 58709,
      "blank_lines": 0,
      "whitespace_words": 1531437,
      "characters": 8831742,
      "crlf_lines": 0,
      "longest_line_bytes": 4002
    },
    {
      "partition": "train-10m",
      "component": "switchboard",
      "path": "data\\raw\\babylm-2026\\train-10m\\switchboard.train.txt",
      "utf8_bytes": 122528,
      "sha256": "89c99649777be2f76f5054e9f1aa364b7e1a62844e219fe810205be6d99399b5",
      "source_verified": true,
      "lines": 2892,
      "blank_lines": 0,
      "whitespace_words": 24791,
      "characters": 122528,
      "crlf_lines": 0,
      "longest_line_bytes": 350
    },
    {
      "partition": "train-100m",
      "component": "bnc_spoken",
      "path": "data\\raw\\babylm-2026\\train-100m\\bnc_spoken.train.txt",
      "utf8_bytes": 39534314,
      "sha256": "4f6cc76f656d5666941852196e35fb5f060bcbb8abebb0b70fe17c3802428a0c",
      "source_verified": true,
      "lines": 803341,
      "blank_lines": 0,
      "whitespace_words": 7620671,
      "characters": 39529290,
      "crlf_lines": 0,
      "longest_line_bytes": 9878
    },
    {
      "partition": "train-100m",
      "component": "childes",
      "path": "data\\raw\\babylm-2026\\train-100m\\childes.train.txt",
      "utf8_bytes": 152297628,
      "sha256": "d6c0e39e2c283bfa5489cde80031a4fb9237ca8065a8301580df10e3b6843a98",
      "source_verified": true,
      "lines": 5638783,
      "blank_lines": 0,
      "whitespace_words": 28410878,
      "characters": 152192502,
      "crlf_lines": 0,
      "longest_line_bytes": 3024
    },
    {
      "partition": "train-100m",
      "component": "gutenberg",
      "path": "data\\raw\\babylm-2026\\train-100m\\gutenberg.train.txt",
      "utf8_bytes": 141116557,
      "sha256": "ee404a84c2f42e0cd52bdaa0366cf398328be1b038ede33d07851f69ea1c2837",
      "source_verified": true,
      "lines": 661928,
      "blank_lines": 0,
      "whitespace_words": 25576896,
      "characters": 140100247,
      "crlf_lines": 0,
      "longest_line_bytes": 20215
    },
    {
      "partition": "train-100m",
      "component": "open_subtitles",
      "path": "data\\raw\\babylm-2026\\train-100m\\open_subtitles.train.txt",
      "utf8_bytes": 121187495,
      "sha256": "9aa48a9448ce6450238868537e4aab43065cca5dae94c948a189e5b802911929",
      "source_verified": true,
      "lines": 3824550,
      "blank_lines": 0,
      "whitespace_words": 22828747,
      "characters": 121051142,
      "crlf_lines": 0,
      "longest_line_bytes": 3195
    },
    {
      "partition": "train-100m",
      "component": "simple_wiki",
      "path": "data\\raw\\babylm-2026\\train-100m\\simple_wiki.train.txt",
      "utf8_bytes": 87947184,
      "sha256": "b7cd8fd945d3986c673bf92fa28df44bf8e4ea655c37c2cacd97cdd8a9146cf2",
      "source_verified": true,
      "lines": 642735,
      "blank_lines": 0,
      "whitespace_words": 15314317,
      "characters": 87736492,
      "crlf_lines": 0,
      "longest_line_bytes": 4002
    },
    {
      "partition": "train-100m",
      "component": "switchboard",
      "path": "data\\raw\\babylm-2026\\train-100m\\switchboard.train.txt",
      "utf8_bytes": 1219017,
      "sha256": "2cb1ed1b47300893b29254081830899c80ac174278b1c1abcade2887821265b1",
      "source_verified": true,
      "lines": 30559,
      "blank_lines": 0,
      "whitespace_words": 248491,
      "characters": 1219017,
      "crlf_lines": 0,
      "longest_line_bytes": 434
    },
    {
      "partition": "validation",
      "component": "bnc_spoken",
      "path": "data\\raw\\babylm-2026\\validation\\bnc_spoken.dev",
      "utf8_bytes": 6539125,
      "sha256": "2c546720837b059da82634b5554a7694bbb9bdeef18f52734da11ba443795cd8",
      "source_verified": true,
      "lines": 130000,
      "blank_lines": 117,
      "whitespace_words": 1252593,
      "characters": 6538139,
      "crlf_lines": 0,
      "longest_line_bytes": 4963
    },
    {
      "partition": "validation",
      "component": "childes",
      "path": "data\\raw\\babylm-2026\\validation\\childes.dev",
      "utf8_bytes": 14684091,
      "sha256": "5823392e65a6da3344811845504c5d1ad9acec42315e2bd938be5eb01a8422a5",
      "source_verified": true,
      "lines": 520153,
      "blank_lines": 870,
      "whitespace_words": 2716591,
      "characters": 14638378,
      "crlf_lines": 0,
      "longest_line_bytes": 739
    },
    {
      "partition": "validation",
      "component": "gutenberg",
      "path": "data\\raw\\babylm-2026\\validation\\gutenberg.dev",
      "utf8_bytes": 15605575,
      "sha256": "760ebc4c697b91308dd21f643ae3c3071e3e1222960fcf8af04119addc50e99b",
      "source_verified": true,
      "lines": 65000,
      "blank_lines": 58,
      "whitespace_words": 2819070,
      "characters": 15490473,
      "crlf_lines": 0,
      "longest_line_bytes": 4216
    },
    {
      "partition": "validation",
      "component": "open_subtitles",
      "path": "data\\raw\\babylm-2026\\validation\\open_subtitles.dev",
      "utf8_bytes": 11029539,
      "sha256": "2e8038d3216c28d7319d0cb564011061d64e093e426b0ca816a9def481481e6b",
      "source_verified": true,
      "lines": 375000,
      "blank_lines": 405,
      "whitespace_words": 2077019,
      "characters": 11016133,
      "crlf_lines": 0,
      "longest_line_bytes": 527
    },
    {
      "partition": "validation",
      "component": "simple_wiki",
      "path": "data\\raw\\babylm-2026\\validation\\simple_wiki.dev",
      "utf8_bytes": 8170440,
      "sha256": "0ca18973a91069bf917bae9072ff511d39b474d590ab2241cb717221d8532c98",
      "source_verified": true,
      "lines": 60000,
      "blank_lines": 10637,
      "whitespace_words": 1405366,
      "characters": 8149513,
      "crlf_lines": 0,
      "longest_line_bytes": 3514
    },
    {
      "partition": "validation",
      "component": "switchboard",
      "path": "data\\raw\\babylm-2026\\validation\\switchboard.dev",
      "utf8_bytes": 724013,
      "sha256": "3dcd2a40051f8e90dadaa0ef656183c1ace7c62682f3306c86ed86aa8cfd057a",
      "source_verified": true,
      "lines": 18000,
      "blank_lines": 0,
      "whitespace_words": 148340,
      "characters": 724013,
      "crlf_lines": 0,
      "longest_line_bytes": 559
    },
    {
      "partition": "test",
      "component": "bnc_spoken",
      "path": "data\\raw\\babylm-2026\\test\\bnc_spoken.test",
      "utf8_bytes": 4889225,
      "sha256": "bdfc15bb70e1bd5f66d6a6113ef47995b7fe7fac247bd8afddfac87b86627b4b",
      "source_verified": true,
      "lines": 90000,
      "blank_lines": 96,
      "whitespace_words": 932334,
      "characters": 4888137,
      "crlf_lines": 0,
      "longest_line_bytes": 4839
    },
    {
      "partition": "test",
      "component": "childes",
      "path": "data\\raw\\babylm-2026\\test\\childes.test",
      "utf8_bytes": 14707424,
      "sha256": "c6b9e5d5479d003381a9a5ea8905ed82ac9c418cbc53395d4234bbb218ee8424",
      "source_verified": true,
      "lines": 540000,
      "blank_lines": 1020,
      "whitespace_words": 2700128,
      "characters": 14696551,
      "crlf_lines": 0,
      "longest_line_bytes": 629
    },
    {
      "partition": "test",
      "component": "gutenberg",
      "path": "data\\raw\\babylm-2026\\test\\gutenberg.test",
      "utf8_bytes": 13296106,
      "sha256": "df309abec59a9143cb5220d81438297d24526024608e6bb795ca8c1a7069c9bd",
      "source_verified": true,
      "lines": 55000,
      "blank_lines": 46,
      "whitespace_words": 2404516,
      "characters": 13206732,
      "crlf_lines": 0,
      "longest_line_bytes": 6236
    },
    {
      "partition": "test",
      "component": "open_subtitles",
      "path": "data\\raw\\babylm-2026\\test\\open_subtitles.test",
      "utf8_bytes": 10388196,
      "sha256": "59cf3e496921fb89f2581cae4f91ce5d2009513ad10778eb4181381d7ea44066",
      "source_verified": true,
      "lines": 345000,
      "blank_lines": 368,
      "whitespace_words": 1949898,
      "characters": 10371565,
      "crlf_lines": 0,
      "longest_line_bytes": 393
    },
    {
      "partition": "test",
      "component": "simple_wiki",
      "path": "data\\raw\\babylm-2026\\test\\simple_wiki.test",
      "utf8_bytes": 7618762,
      "sha256": "e3b1dec6f381115c82630b229ba427edd0f79553ccb9b40fdfc965e31bc7da70",
      "source_verified": true,
      "lines": 60000,
      "blank_lines": 10420,
      "whitespace_words": 1300077,
      "characters": 7595809,
      "crlf_lines": 0,
      "longest_line_bytes": 3063
    },
    {
      "partition": "test",
      "component": "switchboard",
      "path": "data\\raw\\babylm-2026\\test\\switchboard.test",
      "utf8_bytes": 823158,
      "sha256": "f30501f856a0f63571f81716b2e7f7420cfc9ca4b4705671111063065792e713",
      "source_verified": true,
      "lines": 20000,
      "blank_lines": 0,
      "whitespace_words": 167133,
      "characters": 823158,
      "crlf_lines": 0,
      "longest_line_bytes": 458
    }
  ],
  "overlap": [
    {
      "first": "train-10m",
      "second": "train-100m",
      "shared_unique_normalized_lines": 273981,
      "occurrences_in_first": 285251,
      "occurrences_in_second": 286383,
      "words_in_second_matching_first": 6684026
    },
    {
      "first": "train-10m",
      "second": "validation",
      "shared_unique_normalized_lines": 243,
      "occurrences_in_first": 590,
      "occurrences_in_second": 289,
      "words_in_second_matching_first": 3504
    },
    {
      "first": "train-10m",
      "second": "test",
      "shared_unique_normalized_lines": 471,
      "occurrences_in_first": 2934,
      "occurrences_in_second": 1995,
      "words_in_second_matching_first": 26085
    },
    {
      "first": "train-100m",
      "second": "validation",
      "shared_unique_normalized_lines": 8520,
      "occurrences_in_first": 11851,
      "occurrences_in_second": 9083,
      "words_in_second_matching_first": 112339
    },
    {
      "first": "train-100m",
      "second": "test",
      "shared_unique_normalized_lines": 4981,
      "occurrences_in_first": 11375,
      "occurrences_in_second": 7459,
      "words_in_second_matching_first": 120954
    },
    {
      "first": "validation",
      "second": "test",
      "shared_unique_normalized_lines": 236,
      "occurrences_in_first": 495,
      "occurrences_in_second": 635,
      "words_in_second_matching_first": 8425
    }
  ]
}