cards, loader and results

README.md

@@ -0,0 +1,31 @@
+---
+license: cc-by-nc-4.0
+language: en
+tags: [authorship, fine-tuned, book-of-mormon-authorship, 1780-1830]
+---
+
+# Candidate and control models (BOM-28)
+
+One fine-tuned copy of the time-locked model per candidate author's sample (`cand__...`) and per
+control group (`ctrl__...`), at 125M (`pilot/`), 297M (`base/`) and 590M (`mid/`), as scored on the
+sealed Book of Mormon text in the blind run (Amendment 30). Each `.pt` is a state dict for the
+base model's architecture (load with `torch.load(path, weights_only=True)` into the matching
+time-locked model); the `.json` beside it is its training record and held-out scores (numbers
+only). `alm_candidates_<size>.json` is each size's validation, `alm_candidates_plan.json` the
+units. Some candidate samples come from Joseph Smith Papers transcripts, which are not published;
+the models are (owner's decision, 2026-11-09).
+
+## About
+
+Part of an open, pre-registered study of the authorship, borrowing and dating of the
+earliest Book of Mormon text (https://github.com/lifehug/book-of-mormon-authorship; pre-registration https://osf.io/6ugxc/). The project does not argue for or
+against divine inspiration. Everything is published so it can be checked and redone; the corpus
+texts we agreed to keep private are not, and the repository's `docs/replication.md` gives the
+steps to obtain the same access.
+
+**Licence:** CC BY-NC 4.0. **Training data:** English printed 1780-1830 (Internet Archive, Harvard
+Institutional Books 1.0, HathiTrust public-domain volumes, Text Creation Partnership), with the
+Book of Mormon and everything after 1830 removed; see the base model cards
+(`etherfuse/timelocked-1830-125m`). Contains derivatives of Harvard Institutional Books 1.0,
+Institutional Data Initiative, Harvard Law School Library; used for noncommercial research.
+**Checksums:** every file's SHA-256 is in the GitHub repository, `data/manifests/hf_<repo>.jsonl`.

alm_candidates_plan.json

@@ -0,0 +1,704 @@
+{
+ "config_sha256": "def23cdbee0bb1306e49c3cd870d7a9588507833097801fb50cf64e63963b811",
+ "config_path": "/Users/ea/Workspace/book-of-mormon-authorship/config/preregistered.yaml",
+ "registered": true,
+ "git_commit": "9a95d0a88f9b29c380c296e431a2210c334ad103",
+ "block_words": 1000,
+ "test_words": 5000,
+ "units": [
+  {
+   "key": "cand__ethan-smith__printed_by_author__pre1830",
+   "kind": "candidate",
+   "candidate": "Ethan Smith",
+   "sample": "printed_by_author",
+   "period": "pre1830",
+   "confirmatory": true,
+   "docs": [
+    "cand:es-1809-sermon-newburyport",
+    "cand:es-1811-dissertation",
+    "cand:es-1815-death-of-gods-chosen",
+    "cand:es-1817-episcopacy",
+    "cand:es-1823-view-of-the-hebrews",
+    "cand:es-1824-treatise"
+   ],
+   "words": 277391,
+   "flag": "",
+   "train_words": 207000,
+   "train_tokens": 224245,
+   "holdout": {
+    "blocks": 70,
+    "of": 277,
+    "first_word": 207000,
+    "tests": [
+     "blocks 207-211 of 277",
+     "blocks 209-213 of 277",
+     "blocks 213-217 of 277",
+     "blocks 216-220 of 277",
+     "blocks 219-223 of 277",
+     "blocks 220-224 of 277",
+     "blocks 224-228 of 277",
+     "blocks 227-231 of 277",
+     "blocks 229-233 of 277",
+     "blocks 231-235 of 277",
+     "blocks 235-239 of 277",
+     "blocks 238-242 of 277",
+     "blocks 247-251 of 277",
+     "blocks 249-253 of 277",
+     "blocks 251-255 of 277",
+     "blocks 252-256 of 277",
+     "blocks 259-263 of 277",
+     "blocks 260-264 of 277",
+     "blocks 265-269 of 277",
+     "blocks 269-273 of 277"
+    ]
+   }
+  },
+  {
+   "key": "cand__gilbert-j-hunt__printed_by_author__pre1830",
+   "kind": "candidate",
+   "candidate": "Gilbert J. Hunt",
+   "sample": "printed_by_author",
+   "period": "pre1830",
+   "confirmatory": true,
+   "docs": [
+    "cand:gh-1816-late-war"
+   ],
+   "words": 56956,
+   "flag": "",
+   "train_words": 42000,
+   "train_tokens": 45828,
+   "holdout": {
+    "blocks": 14,
+    "of": 56,
+    "first_word": 42000,
+    "tests": [
+     "blocks 42-46 of 56",
+     "blocks 43-47 of 56",
+     "blocks 44-48 of 56",
+     "blocks 45-49 of 56",
+     "blocks 46-50 of 56",
+     "blocks 47-51 of 56",
+     "blocks 48-52 of 56",
+     "blocks 49-53 of 56",
+     "blocks 50-54 of 56",
+     "blocks 51-55 of 56"
+    ]
+   }
+  },
+  {
+   "key": "cand__joseph-smith__dictated__post1830",
+   "kind": "candidate",
+   "candidate": "Joseph Smith",
+   "sample": "dictated",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:joseph-smith__dictated__post1830"
+   ],
+   "words": 5039,
+   "flag": "unreliable sample",
+   "train_words": 5039,
+   "train_tokens": 5516,
+   "holdout": null
+  },
+  {
+   "key": "cand__joseph-smith__dictated__pre1830",
+   "kind": "candidate",
+   "candidate": "Joseph Smith",
+   "sample": "dictated",
+   "period": "pre1830",
+   "confirmatory": true,
+   "docs": [
+    "cand:joseph-smith__dictated__pre1830"
+   ],
+   "words": 2720,
+   "flag": "unreliable sample",
+   "train_words": 2720,
+   "train_tokens": 3039,
+   "holdout": null
+  },
+  {
+   "key": "cand__joseph-smith__handwritten__post1830",
+   "kind": "candidate",
+   "candidate": "Joseph Smith",
+   "sample": "handwritten",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:joseph-smith__handwritten__post1830"
+   ],
+   "words": 6363,
+   "flag": "unreliable sample",
+   "train_words": 6363,
+   "train_tokens": 7605,
+   "holdout": null
+  },
+  {
+   "key": "cand__oliver-cowdery__handwritten__pre1830",
+   "kind": "candidate",
+   "candidate": "Oliver Cowdery",
+   "sample": "handwritten",
+   "period": "pre1830",
+   "confirmatory": true,
+   "docs": [
+    "cand:oliver-cowdery__handwritten__pre1830"
+   ],
+   "words": 1310,
+   "flag": "unreliable sample",
+   "train_words": 1310,
+   "train_tokens": 1373,
+   "holdout": null
+  },
+  {
+   "key": "cand__oliver-cowdery__printed_by_author__post1830",
+   "kind": "candidate",
+   "candidate": "Oliver Cowdery",
+   "sample": "printed_by_author",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:oc-messenger-advocate__10945-11321",
+    "cand:oc-messenger-advocate__13486-13760",
+    "cand:oc-messenger-advocate__15698-16246",
+    "cand:oc-messenger-advocate__17352-17582",
+    "cand:oc-messenger-advocate__1769-2053",
+    "cand:oc-messenger-advocate__22250-22855",
+    "cand:oc-messenger-advocate__28490-29274",
+    "cand:oc-messenger-advocate__298-790",
+    "cand:oc-messenger-advocate__33620-34086",
+    "cand:oc-messenger-advocate__3812-4364",
+    "cand:oc-messenger-advocate__55195-55352",
+    "cand:oc-messenger-advocate__55361-56470",
+    "cand:oc-messenger-advocate__5777-6016",
+    "cand:oc-messenger-advocate__7-226",
+    "cand:oc-messenger-advocate__78204-78359",
+    "cand:wwp-evening-morning-star__34321-34533",
+    "cand:wwp-evening-morning-star__35147-35424"
+   ],
+   "words": 44338,
+   "flag": "",
+   "train_words": 33000,
+   "train_tokens": 35413,
+   "holdout": {
+    "blocks": 11,
+    "of": 44,
+    "first_word": 33000,
+    "tests": [
+     "blocks 33-37 of 44",
+     "blocks 34-38 of 44",
+     "blocks 35-39 of 44",
+     "blocks 36-40 of 44",
+     "blocks 37-41 of 44",
+     "blocks 38-42 of 44",
+     "blocks 39-43 of 44"
+    ]
+   }
+  },
+  {
+   "key": "cand__parley-p-pratt__printed_by_author__post1830",
+   "kind": "candidate",
+   "candidate": "Parley P. Pratt",
+   "sample": "printed_by_author",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:oc-messenger-advocate__45527-45712",
+    "cand:ppp-1837-voice-of-warning",
+    "cand:ppp-1838-mormonism-unveiled",
+    "cand:ppp-1840-late-persecution"
+   ],
+   "words": 91478,
+   "flag": "",
+   "train_words": 68000,
+   "train_tokens": 73406,
+   "holdout": {
+    "blocks": 23,
+    "of": 91,
+    "first_word": 68000,
+    "tests": [
+     "blocks 68-72 of 91",
+     "blocks 69-73 of 91",
+     "blocks 70-74 of 91",
+     "blocks 71-75 of 91",
+     "blocks 72-76 of 91",
+     "blocks 73-77 of 91",
+     "blocks 74-78 of 91",
+     "blocks 75-79 of 91",
+     "blocks 76-80 of 91",
+     "blocks 77-81 of 91",
+     "blocks 78-82 of 91",
+     "blocks 79-83 of 91",
+     "blocks 80-84 of 91",
+     "blocks 81-85 of 91",
+     "blocks 82-86 of 91",
+     "blocks 83-87 of 91",
+     "blocks 84-88 of 91",
+     "blocks 85-89 of 91",
+     "blocks 86-90 of 91"
+    ]
+   }
+  },
+  {
+   "key": "cand__sidney-rigdon__printed_by_author__post1830",
+   "kind": "candidate",
+   "candidate": "Sidney Rigdon",
+   "sample": "printed_by_author",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:oc-messenger-advocate__34667-35271",
+    "cand:oc-messenger-advocate__42671-42999",
+    "cand:oc-messenger-advocate__46700-47164",
+    "cand:oc-messenger-advocate__47890-47972",
+    "cand:oc-messenger-advocate__59630-60509",
+    "cand:oc-messenger-advocate__62411-62880",
+    "cand:sr-1838-oration",
+    "cand:wwp-evening-morning-star__27937-27973"
+   ],
+   "words": 21516,
+   "flag": "",
+   "train_words": 15000,
+   "train_tokens": 15953,
+   "holdout": {
+    "blocks": 6,
+    "of": 21,
+    "first_word": 15000,
+    "tests": [
+     "blocks 15-19 of 21",
+     "blocks 16-20 of 21"
+    ]
+   }
+  },
+  {
+   "key": "cand__solomon-spalding__posthumous__pre1830",
+   "kind": "candidate",
+   "candidate": "Solomon Spalding",
+   "sample": "posthumous",
+   "period": "pre1830",
+   "confirmatory": true,
+   "docs": [
+    "cand:ss-manuscript-story-1885"
+   ],
+   "words": 41833,
+   "flag": "",
+   "train_words": 30000,
+   "train_tokens": 33580,
+   "holdout": {
+    "blocks": 11,
+    "of": 41,
+    "first_word": 30000,
+    "tests": [
+     "blocks 30-34 of 41",
+     "blocks 31-35 of 41",
+     "blocks 32-36 of 41",
+     "blocks 33-37 of 41",
+     "blocks 34-38 of 41",
+     "blocks 35-39 of 41",
+     "blocks 36-40 of 41"
+    ]
+   }
+  },
+  {
+   "key": "cand__w-w-phelps__printed_by_author__post1830",
+   "kind": "candidate",
+   "candidate": "W. W. Phelps",
+   "sample": "printed_by_author",
+   "period": "post1830",
+   "confirmatory": false,
+   "docs": [
+    "cand:oc-messenger-advocate__11427-11748",
+    "cand:oc-messenger-advocate__13807-13943",
+    "cand:oc-messenger-advocate__16539-16764",
+    "cand:oc-messenger-advocate__18617-19000",
+    "cand:oc-messenger-advocate__20815-21159",
+    "cand:oc-messenger-advocate__25394-25765",
+    "cand:oc-messenger-advocate__28087-28487",
+    "cand:oc-messenger-advocate__3019-3327",
+    "cand:oc-messenger-advocate__31746-32139",
+    "cand:oc-messenger-advocate__33048-33588",
+    "cand:oc-messenger-advocate__4403-4736",
+    "cand:oc-messenger-advocate__48891-49037",
+    "cand:oc-messenger-advocate__6675-7007",
+    "cand:oc-messenger-advocate__75781-75857",
+    "cand:oc-messenger-advocate__9080-9386",
+    "cand:wwp-evening-morning-star__25834-25904",
+    "cand:wwp-evening-morning-star__29424-29458",
+    "cand:wwp-evening-morning-star__35427-35564"
+   ],
+   "words": 28479,
+   "flag": "",
+   "train_words": 21000,
+   "train_tokens": 22746,
+   "holdout": {
+    "blocks": 7,
+    "of": 28,
+    "first_word": 21000,
+    "tests": [
+     "blocks 21-25 of 28",
+     "blocks 22-26 of 28",
+     "blocks 23-27 of 28"
+    ]
+   }
+  },
+  {
+   "key": "ctrl__pseudo_biblical",
+   "kind": "control",
+   "group": "pseudo_biblical",
+   "docs": [
+    "internet_archive:bim_eighteenth-century_the-oriental-chronicles-_1785",
+    "internet_archive:bim_eighteenth-century_the-third-book-of-the-ch_zerubbabel-zonzinpohamo_1781",
+    "institutional_books:HNNNPA",
+    "internet_archive:bim_eighteenth-century_the-american-revolution_snowden-richard_1793_1",
+    "internet_archive:bim_eighteenth-century_the-acts-chap-i-now-w_1790",
+    "tcp:N10323",
+    "institutional_books:32044077888907",
+    "institutional_books:32044018948232",
+    "internet_archive:bim_eighteenth-century_the-chronicle-of-the-kin_dodsley-robert_1790",
+    "internet_archive:bim_eighteenth-century_the-oeconomy-of-human-li_dodsley-robert_1780",
+    "institutional_books:HH2NE7",
+    "internet_archive:bib_fict_1669729",
+    "hathitrust:aeu.ark:/13960/t82j72w7n",
+    "internet_archive:firstbookofremar00anno",
+    "internet_archive:bim_eighteenth-century_the-second-charter-of-th_1796",
+    "internet_archive:bim_eighteenth-century_the-acts-chap-ii-and-_1790",
+    "internet_archive:bim_eighteenth-century_the-first-book-of-the-ro_zerubbabel-ishmael-zaph_1788",
+    "tcp:N16488"
+   ],
+   "words": 197935,
+   "flag": "",
+   "train_words": 147000,
+   "train_tokens": 162136,
+   "holdout": {
+    "blocks": 50,
+    "of": 197,
+    "first_word": 147000,
+    "tests": [
+     "blocks 147-151 of 197",
+     "blocks 150-154 of 197",
+     "blocks 151-155 of 197",
+     "blocks 153-157 of 197",
+     "blocks 157-161 of 197",
+     "blocks 158-162 of 197",
+     "blocks 160-164 of 197",
+     "blocks 164-168 of 197",
+     "blocks 165-169 of 197",
+     "blocks 167-171 of 197",
+     "blocks 169-173 of 197",
+     "blocks 170-174 of 197",
+     "blocks 172-176 of 197",
+     "blocks 178-182 of 197",
+     "blocks 182-186 of 197",
+     "blocks 186-190 of 197",
+     "blocks 187-191 of 197",
+     "blocks 188-192 of 197",
+     "blocks 190-194 of 197",
+     "blocks 192-196 of 197"
+    ]
+   }
+  },
+  {
+   "key": "ctrl__sermons_1820s",
+   "kind": "control",
+   "group": "sermons_1820s",
+   "docs": [
+    "hathitrust:aeu.ark:/13960/t5z613w25",
+    "internet_archive:missionaryherald551amer",
+    "internet_archive:reflectionsagain00shar_1",
+    "institutional_books:AH68HF",
+    "hathitrust:loc.ark:/13960/t2q53xf35",
+    "institutional_books:AH65U2",
+    "internet_archive:sermondelivereda00john",
+    "hathitrust:uc2.ark:/13960/t1jh3nz2q",
+    "internet_archive:affectionatepare01horsiala",
+    "internet_archive:b21474023",
+    "internet_archive:isbn_1437051553",
+    "institutional_books:AH45Q6",
+    "internet_archive:missionaryherald826amer",
+    "hathitrust:ia.ark:/13960/t9q242m0w",
+    "internet_archive:missionaryherald526amer",
+    "internet_archive:utilityandimpor00semigoog",
+    "hathitrust:loc.ark:/13960/t8tb28g3p",
+    "internet_archive:missionaryherald6110amer",
+    "internet_archive:11777591bsb",
+    "internet_archive:missionaryherald891amer",
+    "institutional_books:AH4DLY",
+    "internet_archive:missionaryherald764amer",
+    "internet_archive:sermononnaturein00wood",
+    "institutional_books:HWJN8K",
+    "hathitrust:ia.ark:/13960/t4sj1m424",
+    "hathitrust:uc2.ark:/13960/t6rx96s18",
+    "hathitrust:uiuo.ark:/13960/t0ft8wm7b",
+    "hathitrust:yale.39002061264512",
+    "hathitrust:ia.ark:/13960/t9p27180t",
+    "internet_archive:sermonsfordiffe01whitgoog",
+    "internet_archive:missionaryheral22missgoog",
+    "hathitrust:nc01.ark:/13960/t50g4t18r",
+    "hathitrust:ia.ark:/13960/t2g73nx9j",
+    "hathitrust:ia.ark:/13960/t15m9sd04",
+    "internet_archive:christianreflect0005unse",
+    "internet_archive:pulpitassistant03hanngoog",
+    "institutional_books:HXTA2A",
+    "internet_archive:atreatiseonpray03bickgoog",
+    "institutional_books:HWJNXQ",
+    "hathitrust:ia.ark:/13960/t2j67qn1q",
+    "internet_archive:missionaryherald1114amer",
+    "institutional_books:HXJG7X",
+    "institutional_books:AH6KXZ",
+    "internet_archive:hymnsforinfants00taylgoog",
+    "institutional_books:32044072040108",
+    "internet_archive:missionaryheral1071amer_0",
+    "institutional_books:AH6KXE",
+    "institutional_books:32044011474509",
+    "institutional_books:AH4DI9",
+    "hathitrust:yale.39002005600391",
+    "institutional_books:HNPURG",
+    "internet_archive:magnaliachristia02math_0",
+    "internet_archive:missionaryherald916amer",
+    "hathitrust:aeu.ark:/13960/t6xw50s2z",
+    "internet_archive:theholybible00balt",
+    "hathitrust:ia.ark:/13960/t2m65162z",
+    "institutional_books:HX26ZG",
+    "hathitrust:ia.ark:/13960/t24b3ts9r",
+    "internet_archive:MN41700ucmf_1",
+    "internet_archive:questionsforyou00quesgoog",
+    "internet_archive:endearingrelatio00elya_0",
+    "hathitrust:uc2.ark:/13960/t8w953w99"
+   ],
+   "words": 300000,
+   "flag": "",
+   "train_words": 225000,
+   "train_tokens": 251789,
+   "holdout": {
+    "blocks": 75,
+    "of": 300,
+    "first_word": 225000,
+    "tests": [
+     "blocks 228-232 of 300",
+     "blocks 229-233 of 300",
+     "blocks 234-238 of 300",
+     "blocks 244-248 of 300",
+     "blocks 245-249 of 300",
+     "blocks 247-251 of 300",
+     "blocks 248-252 of 300",
+     "blocks 250-254 of 300",
+     "blocks 252-256 of 300",
+     "blocks 259-263 of 300",
+     "blocks 261-265 of 300",
+     "blocks 273-277 of 300",
+     "blocks 278-282 of 300",
+     "blocks 279-283 of 300",
+     "blocks 281-285 of 300",
+     "blocks 282-286 of 300",
+     "blocks 284-288 of 300",
+     "blocks 286-290 of 300",
+     "blocks 289-293 of 300",
+     "blocks 294-298 of 300"
+    ]
+   }
+  },
+  {
+   "key": "ctrl__history",
+   "kind": "control",
+   "group": "history",
+   "docs": [
+    "internet_archive:jacobiterelicss04hogggoog",
+    "hathitrust:nnc2.ark:/13960/t2p56s91k",
+    "institutional_books:HXG9WC",
+    "internet_archive:travelsintopola04coxegoog",
+    "internet_archive:b2877372x_0002",
+    "hathitrust:uc2.ark:/13960/t0ms3p70v",
+    "hathitrust:gri.ark:/13960/t78s53m48",
+    "institutional_books:HX5VIK",
+    "institutional_books:AH65X6",
+    "internet_archive:cihm_20657",
+    "hathitrust:coo.31924111566448",
+    "institutional_books:HXGEQ4",
+    "internet_archive:newrobinsoncruso12camp",
+    "internet_archive:generalcollectio16pink",
+    "internet_archive:generalhistoryof51822lath",
+    "internet_archive:b33520677_0001",
+    "hathitrust:gri.ark:/13960/t0zp8vr9z",
+    "internet_archive:someobservation00bryagoog",
+    "internet_archive:10000111bsb",
+    "hathitrust:loc.ark:/13960/t5h998915",
+    "institutional_books:HXDUEC",
+    "internet_archive:bim_eighteenth-century_narrative-of-m-de-chaum_chaumareix-jean-hugues-_1795",
+    "tcp:K058702.001",
+    "institutional_books:HXJ8AD",
+    "internet_archive:travelsinasiami00londgoog",
+    "hathitrust:aeu.ark:/13960/t8nc6r80n",
+    "hathitrust:aeu.ark:/13960/t89g6f12p",
+    "internet_archive:historycivilcomm01edwa",
+    "internet_archive:cihm_34637",
+    "internet_archive:addressdelivered00chiliala",
+    "hathitrust:uc2.ark:/13960/t7sn05b1f",
+    "institutional_books:32044014478143",
+    "hathitrust:gri.ark:/13960/t20c8h59z",
+    "internet_archive:b1455503",
+    "hathitrust:uc2.ark:/13960/t3zs2sw43",
+    "internet_archive:aharmonyfourgos03unkngoog",
+    "institutional_books:HWBB44",
+    "internet_archive:historyreignemp12robegoog",
+    "internet_archive:bim_eighteenth-century_a-short-account-of-the-p_masters-robert_1795",
+    "internet_archive:prayersforchildr00unse",
+    "internet_archive:s25id13211830",
+    "institutional_books:32044020175832",
+    "internet_archive:berktopographic00cookuoft",
+    "hathitrust:gri.ark:/13960/t6qz8t32w",
+    "institutional_books:HNUG2L",
+    "internet_archive:cihm_36116",
+    "hathitrust:uc2.ark:/13960/t0ht2hh88",
+    "internet_archive:historyofsirchar05richuoft",
+    "tcp:K113570.000",
+    "internet_archive:intrototheartoft00kameuoft",
+    "internet_archive:exemplarylifepi00broogoog",
+    "hathitrust:uc2.ark:/13960/t78s4p83z",
+    "institutional_books:HN2HCP",
+    "internet_archive:bim_eighteenth-century_the-tears-of-piety-an-e_philagathos_1785",
+    "internet_archive:historicalmemoir01wrax",
+    "internet_archive:walksthroughire00trotgoog",
+    "institutional_books:HXH31P",
+    "internet_archive:elementsoflogick00hedg_1",
+    "internet_archive:atourinswitzerl00willgoog",
+    "hathitrust:aeu.ark:/13960/t9t15w58t",
+    "internet_archive:10213200bsb",
+    "hathitrust:aeu.ark:/13960/t73v0qw51"
+   ],
+   "words": 300000,
+   "flag": "",
+   "train_words": 225000,
+   "train_tokens": 265984,
+   "holdout": {
+    "blocks": 75,
+    "of": 300,
+    "first_word": 225000,
+    "tests": [
+     "blocks 228-232 of 300",
+     "blocks 231-235 of 300",
+     "blocks 232-236 of 300",
+     "blocks 234-238 of 300",
+     "blocks 236-240 of 300",
+     "blocks 238-242 of 300",
+     "blocks 240-244 of 300",
+     "blocks 243-247 of 300",
+     "blocks 247-251 of 300",
+     "blocks 252-256 of 300",
+     "blocks 255-259 of 300",
+     "blocks 260-264 of 300",
+     "blocks 266-270 of 300",
+     "blocks 267-271 of 300",
+     "blocks 275-279 of 300",
+     "blocks 279-283 of 300",
+     "blocks 284-288 of 300",
+     "blocks 288-292 of 300",
+     "blocks 290-294 of 300",
+     "blocks 293-297 of 300"
+    ]
+   }
+  },
+  {
+   "key": "ctrl__general_prose",
+   "kind": "control",
+   "group": "general_prose",
+   "docs": [
+    "chronicling_america:sn84031604/1825-08-23-ed1-seq1",
+    "internet_archive:sim_port-folio_1808-03-12_5_11",
+    "chronicling_america:sn83021574/1828-11-19-ed1-seq2",
+    "chronicling_america:sn83025442/1813-10-29-ed1-seq3",
+    "chronicling_america:sn84031604/1824-07-16-ed1-seq2",
+    "hathitrust:mcg.ark:/13960/t7xm0w05g",
+    "chronicling_america:sn83026172/1826-10-23-ed1-seq4",
+    "chronicling_america:sn84023351/1804-04-17-ed1-seq1",
+    "institutional_books:32044102881901",
+    "internet_archive:persianadventur03frasgoog",
+    "hathitrust:loc.ark:/13960/t69323q15",
+    "internet_archive:sim_monthly-magazine_1808-06-01_25_171",
+    "internet_archive:literarymagnetb01unkngoog",
+    "institutional_books:HC4KJL",
+    "institutional_books:32044106374796",
+    "chronicling_america:sn84024505/1825-05-20-ed1-seq3",
+    "hathitrust:loc.ark:/13960/t8pc33j0j",
+    "internet_archive:elementsgeometr00haywgoog",
+    "internet_archive:per_london-gazette_the-london-gazette_december-6-9-1788_13049",
+    "internet_archive:10750424bsb",
+    "internet_archive:sim_philadelphia-repertory_1812-02-29_2_41",
+    "internet_archive:sim_philadelphia-repertory_1810-07-14_1_11",
+    "chronicling_america:sn85025815/1813-03-31-ed1-seq2",
+    "internet_archive:analecticmagazi05irvigoog",
+    "internet_archive:africanreposito2010amer_1",
+    "internet_archive:per_london-gazette_the-london-gazette_august-4-8-1789_13120",
+    "chronicling_america:sn85025815/1808-08-08-ed1-seq3",
+    "internet_archive:jstor-109832",
+    "internet_archive:sim_niles-national-register_1815-08-26_8_208",
+    "chronicling_america:sn83016082/1810-03-31-ed1-seq1",
+    "hathitrust:uc2.ark:/13960/t54f1nw8n",
+    "internet_archive:sim_belfast-monthly-magazine_1814-12-31_13_77",
+    "chronicling_america:sn83026172/1818-10-01-ed1-seq1",
+    "chronicling_america:sn82014782/1800-03-27-ed1-seq2",
+    "internet_archive:philosophicaltra1141roya",
+    "internet_archive:bim_eighteenth-century_the-false-friend-a-dome_robinson-mary_1799_3",
+    "chronicling_america:sn83026172/1822-05-21-ed1-seq4",
+    "chronicling_america:sn85025006/1826-10-23-ed1-seq1",
+    "internet_archive:sim_literary-gazette_1827-09-01_554",
+    "institutional_books:HW2C5I",
+    "internet_archive:amanualchemistr01brangoog",
+    "chronicling_america:sn85025006/1825-08-02-ed1-seq3",
+    "chronicling_america:sn83026172/1824-09-28-ed1-seq2",
+    "internet_archive:sim_repository-and-ladies-weekly-museum_1803-10-08_3_41",
+    "internet_archive:sim_caledonian-mercury_1799-06-24_12132",
+    "chronicling_america:sn83025442/1817-12-09-ed1-seq2",
+    "internet_archive:sketchesessaysa01quesgoog",
+    "internet_archive:newseriesannualr0000rrgi",
+    "institutional_books:HC4KJ1",
+    "internet_archive:aviewconstituti00stokgoog",
+    "institutional_books:HN2ZFG",
+    "internet_archive:notesonmineralo00stepgoog",
+    "hathitrust:mdp.39015096475085",
+    "chronicling_america:sn83021420/1830-06-01-ed1-seq1",
+    "internet_archive:bim_eighteenth-century_the-young-widow-or-the_ledwich-mrs_1785_2",
+    "internet_archive:complaint00youniala",
+    "hathitrust:mdp.39015096437481",
+    "chronicling_america:sn84031604/1826-06-02-ed1-seq4",
+    "chronicling_america:sn83045110/1829-05-19-ed1-seq3",
+    "chronicling_america:sn85025815/1813-05-22-ed1-seq3",
+    "internet_archive:per_alexandria-gazette-packet_alexandria-gazette-daily-advertiser_1818-08-05_19_5297",
+    "internet_archive:b30353889",
+    "internet_archive:playsshakspeare17reedgoog",
+    "chronicling_america:sn84038455/1823-11-27-ed1-seq2",
+    "internet_archive:sim_gentlemans-magazine_1809-09_79",
+    "internet_archive:bub_gb_VOWDERnvYo8C"
+   ],
+   "words": 300000,
+   "flag": "",
+   "train_words": 225000,
+   "train_tokens": 268814,
+   "holdout": {
+    "blocks": 75,
+    "of": 300,
+    "first_word": 225000,
+    "tests": [
+     "blocks 225-229 of 300",
+     "blocks 229-233 of 300",
+     "blocks 235-239 of 300",
+     "blocks 237-241 of 300",
+     "blocks 242-246 of 300",
+     "blocks 244-248 of 300",
+     "blocks 250-254 of 300",
+     "blocks 257-261 of 300",
+     "blocks 259-263 of 300",
+     "blocks 261-265 of 300",
+     "blocks 263-267 of 300",
+     "blocks 265-269 of 300",
+     "blocks 266-270 of 300",
+     "blocks 270-274 of 300",
+     "blocks 272-276 of 300",
+     "blocks 278-282 of 300",
+     "blocks 289-293 of 300",
+     "blocks 291-295 of 300",
+     "blocks 293-297 of 300",
+     "blocks 294-298 of 300"
+    ]
+   }
+  }
+ ]
+}