{ "test_id": "T-SEG-001", "date": "2026-09-17", "folio": "f1v", "status": "EXECUTED: descriptive segmentation and regression control", "normalization": "Split each raw locus at <-> before removing metadata tags. Keep left/right segments separate. Periods split tokens. Run comma uncertainty joined and split. Select first bracketed alternative only for counts; retain raw alternatives. No joining across a drawing or line boundary.", "limitations": [ "Tokens are operational transcription units, not proven words.", "IT and ZL are related scholarly transcriptions, not independent manuscript witnesses.", "No glyph-by-glyph adjudication or language model.", "No significance test; no Latin conversion, medical meaning, cipher key, or plaintext established.", "Cross-drawing continuity of reading is an editorial assumption, not deciphered syntax." ], "sources": { "IT": { "url": "https://voynich.nu/data/IT2a-n.txt", "version_header": [ "#=IVTFF EvaT 2.0 M 3", "# Extracted from LSI_ivtff_0d.txt", "# Version 2a of 02/02/2023 modified 25/06/2025", "#" ], "downloaded": "2026-09-17", "sha256": "7f27a8b0feed8f6de0a99900df6bf912dd1d295c38e5f830bac8b41c3f536fb5", "bytes": 342104, "loci": [ { "locus": 1, "code": "@P0", "raw": "<%>kchsy.chadaiin.ol<->oltchey.char.cfhar.am" }, { "locus": 2, "code": "+P0", "raw": "yteeay.char.or.ochy<->dcho.lkody.okodar.chody" }, { "locus": 3, "code": "+P0", "raw": "do.ckhy.ckho.ckhy.shy<->dksheey.cthy.kotchody.dal" }, { "locus": 4, "code": "+P0", "raw": "dol.chokeo.dair.dam<->sochey.chokody<$>" }, { "locus": 5, "code": "+P0", "raw": "<%>potoy.shol.dair.cphoal<->dar.chey.tody.otoaiin.shoshy" }, { "locus": 6, "code": "+P0", "raw": "choky.chol.cthol.shol.okal<->dolchey.chodo.lol.chy.cthy" }, { "locus": 7, "code": "+P0", "raw": "qo.ol.choeee.cheol.dol.cthey<->ykol.dol.dolo.ykol.do.lchody" }, { "locus": 8, "code": "+P0", "raw": "okol.shol.kol.kechy.chol.ky<->chol.cthol.chody.chol.daiin" }, { "locus": 9, "code": "+P0", "raw": "shor.okol.chol.dol.ky.dar<->shol.dchor.otcho.dar.shody" }, { "locus": 10, "code": "+P0", "raw": "taor.chotchey.dal.chody<->schody.pol.chodar<$>" } ], "paragraph_starts": [ 1, 5 ], "paragraph_lengths": [ 4, 6 ], "drawing_interruptions": 10 }, "ZL": { "url": "https://voynich.nu/data/ZL3b-n.txt", "version_header": [ "#=IVTFF Eva- 2.0 M 5", "# ZL transliteration file, updated from EVMT project", "# Version 3b of 13/05/2025", "#" ], "downloaded": "2026-09-17", "sha256": "bf5b6d4ac1e3a51b1847a9c388318d609020441ccd56984c901c32b09beccafc", "bytes": 411671, "loci": [ { "locus": 1, "code": "@P0", "raw": "<%>kchsy.chydaiin.ol<->o,l,tchey.char.cfhar,am" }, { "locus": 2, "code": "+P0", "raw": "yteey.char.or.ochy<->dcho.lkody.okodar.chody" }, { "locus": 3, "code": "+P0", "raw": "da,ckhy.ckhockhy.shy<->dksheey.cthy.kotchody.dal" }, { "locus": 4, "code": "+P0", "raw": "dol.chokeo.dair.dam<->sochey.chokody<$>" }, { "locus": 5, "code": "+P0", "raw": "<%>potoy.shol.dair.cphoal<->dar.chey.tody.otoaiin.shoshy" }, { "locus": 6, "code": "+P0", "raw": "choky.chol.ctho,l,shol.okal<->dolchey.chodo.lol.chy.cthy" }, { "locus": 7, "code": "+P0", "raw": "qo.ol,choees.cheol.dol.cthey<->ykol.dol.dolo.ykol.do,lchiody" }, { "locus": 8, "code": "+P0", "raw": "okolshol.kol,kechy.chol.ky<->chol.cthol.chody.chol.daiin" }, { "locus": 9, "code": "+P0", "raw": "shor.okol.chol.dol,ky.dar<->shol.dchor.o,tcho.dar.[sh:{@209;h}]ody" }, { "locus": 10, "code": "+P0", "raw": "taor.chotchey.dal.chody<->schody.pol.chodar<$>" } ], "paragraph_starts": [ 1, 5 ], "paragraph_lengths": [ 4, 6 ], "drawing_interruptions": 10 } }, "runs": { "IT_join": { "total_tokens": 90, "left_tokens": 47, "right_tokens": 43, "broken_strip_tags_total": 80, "tokens_lost_by_bad_gap_handling": 10, "rows": [ { "locus": 1, "left_tokens": [ "kchsy", "chadaiin", "ol" ], "right_tokens": [ "oltchey", "char", "cfhar", "am" ], "before_drawing": "ol", "after_drawing": "oltchey", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "ololtchey" }, { "locus": 2, "left_tokens": [ "yteeay", "char", "or", "ochy" ], "right_tokens": [ "dcho", "lkody", "okodar", "chody" ], "before_drawing": "ochy", "after_drawing": "dcho", "token_count": 8, "broken_strip_tags_count": 7, "spurious_fused_token": "ochydcho" }, { "locus": 3, "left_tokens": [ "do", "ckhy", "ckho", "ckhy", "shy" ], "right_tokens": [ "dksheey", "cthy", "kotchody", "dal" ], "before_drawing": "shy", "after_drawing": "dksheey", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "shydksheey" }, { "locus": 4, "left_tokens": [ "dol", "chokeo", "dair", "dam" ], "right_tokens": [ "sochey", "chokody" ], "before_drawing": "dam", "after_drawing": "sochey", "token_count": 6, "broken_strip_tags_count": 5, "spurious_fused_token": "damsochey" }, { "locus": 5, "left_tokens": [ "potoy", "shol", "dair", "cphoal" ], "right_tokens": [ "dar", "chey", "tody", "otoaiin", "shoshy" ], "before_drawing": "cphoal", "after_drawing": "dar", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "cphoaldar" }, { "locus": 6, "left_tokens": [ "choky", "chol", "cthol", "shol", "okal" ], "right_tokens": [ "dolchey", "chodo", "lol", "chy", "cthy" ], "before_drawing": "okal", "after_drawing": "dolchey", "token_count": 10, "broken_strip_tags_count": 9, "spurious_fused_token": "okaldolchey" }, { "locus": 7, "left_tokens": [ "qo", "ol", "choeee", "cheol", "dol", "cthey" ], "right_tokens": [ "ykol", "dol", "dolo", "ykol", "do", "lchody" ], "before_drawing": "cthey", "after_drawing": "ykol", "token_count": 12, "broken_strip_tags_count": 11, "spurious_fused_token": "ctheyykol" }, { "locus": 8, "left_tokens": [ "okol", "shol", "kol", "kechy", "chol", "ky" ], "right_tokens": [ "chol", "cthol", "chody", "chol", "daiin" ], "before_drawing": "ky", "after_drawing": "chol", "token_count": 11, "broken_strip_tags_count": 10, "spurious_fused_token": "kychol" }, { "locus": 9, "left_tokens": [ "shor", "okol", "chol", "dol", "ky", "dar" ], "right_tokens": [ "shol", "dchor", "otcho", "dar", "shody" ], "before_drawing": "dar", "after_drawing": "shol", "token_count": 11, "broken_strip_tags_count": 10, "spurious_fused_token": "darshol" }, { "locus": 10, "left_tokens": [ "taor", "chotchey", "dal", "chody" ], "right_tokens": [ "schody", "pol", "chodar" ], "before_drawing": "chody", "after_drawing": "schody", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "chodyschody" } ] }, "IT_split": { "total_tokens": 90, "left_tokens": 47, "right_tokens": 43, "broken_strip_tags_total": 80, "tokens_lost_by_bad_gap_handling": 10, "rows": [ { "locus": 1, "left_tokens": [ "kchsy", "chadaiin", "ol" ], "right_tokens": [ "oltchey", "char", "cfhar", "am" ], "before_drawing": "ol", "after_drawing": "oltchey", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "ololtchey" }, { "locus": 2, "left_tokens": [ "yteeay", "char", "or", "ochy" ], "right_tokens": [ "dcho", "lkody", "okodar", "chody" ], "before_drawing": "ochy", "after_drawing": "dcho", "token_count": 8, "broken_strip_tags_count": 7, "spurious_fused_token": "ochydcho" }, { "locus": 3, "left_tokens": [ "do", "ckhy", "ckho", "ckhy", "shy" ], "right_tokens": [ "dksheey", "cthy", "kotchody", "dal" ], "before_drawing": "shy", "after_drawing": "dksheey", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "shydksheey" }, { "locus": 4, "left_tokens": [ "dol", "chokeo", "dair", "dam" ], "right_tokens": [ "sochey", "chokody" ], "before_drawing": "dam", "after_drawing": "sochey", "token_count": 6, "broken_strip_tags_count": 5, "spurious_fused_token": "damsochey" }, { "locus": 5, "left_tokens": [ "potoy", "shol", "dair", "cphoal" ], "right_tokens": [ "dar", "chey", "tody", "otoaiin", "shoshy" ], "before_drawing": "cphoal", "after_drawing": "dar", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "cphoaldar" }, { "locus": 6, "left_tokens": [ "choky", "chol", "cthol", "shol", "okal" ], "right_tokens": [ "dolchey", "chodo", "lol", "chy", "cthy" ], "before_drawing": "okal", "after_drawing": "dolchey", "token_count": 10, "broken_strip_tags_count": 9, "spurious_fused_token": "okaldolchey" }, { "locus": 7, "left_tokens": [ "qo", "ol", "choeee", "cheol", "dol", "cthey" ], "right_tokens": [ "ykol", "dol", "dolo", "ykol", "do", "lchody" ], "before_drawing": "cthey", "after_drawing": "ykol", "token_count": 12, "broken_strip_tags_count": 11, "spurious_fused_token": "ctheyykol" }, { "locus": 8, "left_tokens": [ "okol", "shol", "kol", "kechy", "chol", "ky" ], "right_tokens": [ "chol", "cthol", "chody", "chol", "daiin" ], "before_drawing": "ky", "after_drawing": "chol", "token_count": 11, "broken_strip_tags_count": 10, "spurious_fused_token": "kychol" }, { "locus": 9, "left_tokens": [ "shor", "okol", "chol", "dol", "ky", "dar" ], "right_tokens": [ "shol", "dchor", "otcho", "dar", "shody" ], "before_drawing": "dar", "after_drawing": "shol", "token_count": 11, "broken_strip_tags_count": 10, "spurious_fused_token": "darshol" }, { "locus": 10, "left_tokens": [ "taor", "chotchey", "dal", "chody" ], "right_tokens": [ "schody", "pol", "chodar" ], "before_drawing": "chody", "after_drawing": "schody", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "chodyschody" } ] }, "ZL_join": { "total_tokens": 81, "left_tokens": 40, "right_tokens": 41, "broken_strip_tags_total": 71, "tokens_lost_by_bad_gap_handling": 10, "rows": [ { "locus": 1, "left_tokens": [ "kchsy", "chydaiin", "ol" ], "right_tokens": [ "oltchey", "char", "cfharam" ], "before_drawing": "ol", "after_drawing": "oltchey", "token_count": 6, "broken_strip_tags_count": 5, "spurious_fused_token": "ololtchey" }, { "locus": 2, "left_tokens": [ "yteey", "char", "or", "ochy" ], "right_tokens": [ "dcho", "lkody", "okodar", "chody" ], "before_drawing": "ochy", "after_drawing": "dcho", "token_count": 8, "broken_strip_tags_count": 7, "spurious_fused_token": "ochydcho" }, { "locus": 3, "left_tokens": [ "dackhy", "ckhockhy", "shy" ], "right_tokens": [ "dksheey", "cthy", "kotchody", "dal" ], "before_drawing": "shy", "after_drawing": "dksheey", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "shydksheey" }, { "locus": 4, "left_tokens": [ "dol", "chokeo", "dair", "dam" ], "right_tokens": [ "sochey", "chokody" ], "before_drawing": "dam", "after_drawing": "sochey", "token_count": 6, "broken_strip_tags_count": 5, "spurious_fused_token": "damsochey" }, { "locus": 5, "left_tokens": [ "potoy", "shol", "dair", "cphoal" ], "right_tokens": [ "dar", "chey", "tody", "otoaiin", "shoshy" ], "before_drawing": "cphoal", "after_drawing": "dar", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "cphoaldar" }, { "locus": 6, "left_tokens": [ "choky", "chol", "ctholshol", "okal" ], "right_tokens": [ "dolchey", "chodo", "lol", "chy", "cthy" ], "before_drawing": "okal", "after_drawing": "dolchey", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "okaldolchey" }, { "locus": 7, "left_tokens": [ "qo", "olchoees", "cheol", "dol", "cthey" ], "right_tokens": [ "ykol", "dol", "dolo", "ykol", "dolchiody" ], "before_drawing": "cthey", "after_drawing": "ykol", "token_count": 10, "broken_strip_tags_count": 9, "spurious_fused_token": "ctheyykol" }, { "locus": 8, "left_tokens": [ "okolshol", "kolkechy", "chol", "ky" ], "right_tokens": [ "chol", "cthol", "chody", "chol", "daiin" ], "before_drawing": "ky", "after_drawing": "chol", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "kychol" }, { "locus": 9, "left_tokens": [ "shor", "okol", "chol", "dolky", "dar" ], "right_tokens": [ "shol", "dchor", "otcho", "dar", "shody" ], "before_drawing": "dar", "after_drawing": "shol", "token_count": 10, "broken_strip_tags_count": 9, "spurious_fused_token": "darshol" }, { "locus": 10, "left_tokens": [ "taor", "chotchey", "dal", "chody" ], "right_tokens": [ "schody", "pol", "chodar" ], "before_drawing": "chody", "after_drawing": "schody", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "chodyschody" } ] }, "ZL_split": { "total_tokens": 92, "left_tokens": 46, "right_tokens": 46, "broken_strip_tags_total": 82, "tokens_lost_by_bad_gap_handling": 10, "rows": [ { "locus": 1, "left_tokens": [ "kchsy", "chydaiin", "ol" ], "right_tokens": [ "o", "l", "tchey", "char", "cfhar", "am" ], "before_drawing": "ol", "after_drawing": "o", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "olo" }, { "locus": 2, "left_tokens": [ "yteey", "char", "or", "ochy" ], "right_tokens": [ "dcho", "lkody", "okodar", "chody" ], "before_drawing": "ochy", "after_drawing": "dcho", "token_count": 8, "broken_strip_tags_count": 7, "spurious_fused_token": "ochydcho" }, { "locus": 3, "left_tokens": [ "da", "ckhy", "ckhockhy", "shy" ], "right_tokens": [ "dksheey", "cthy", "kotchody", "dal" ], "before_drawing": "shy", "after_drawing": "dksheey", "token_count": 8, "broken_strip_tags_count": 7, "spurious_fused_token": "shydksheey" }, { "locus": 4, "left_tokens": [ "dol", "chokeo", "dair", "dam" ], "right_tokens": [ "sochey", "chokody" ], "before_drawing": "dam", "after_drawing": "sochey", "token_count": 6, "broken_strip_tags_count": 5, "spurious_fused_token": "damsochey" }, { "locus": 5, "left_tokens": [ "potoy", "shol", "dair", "cphoal" ], "right_tokens": [ "dar", "chey", "tody", "otoaiin", "shoshy" ], "before_drawing": "cphoal", "after_drawing": "dar", "token_count": 9, "broken_strip_tags_count": 8, "spurious_fused_token": "cphoaldar" }, { "locus": 6, "left_tokens": [ "choky", "chol", "ctho", "l", "shol", "okal" ], "right_tokens": [ "dolchey", "chodo", "lol", "chy", "cthy" ], "before_drawing": "okal", "after_drawing": "dolchey", "token_count": 11, "broken_strip_tags_count": 10, "spurious_fused_token": "okaldolchey" }, { "locus": 7, "left_tokens": [ "qo", "ol", "choees", "cheol", "dol", "cthey" ], "right_tokens": [ "ykol", "dol", "dolo", "ykol", "do", "lchiody" ], "before_drawing": "cthey", "after_drawing": "ykol", "token_count": 12, "broken_strip_tags_count": 11, "spurious_fused_token": "ctheyykol" }, { "locus": 8, "left_tokens": [ "okolshol", "kol", "kechy", "chol", "ky" ], "right_tokens": [ "chol", "cthol", "chody", "chol", "daiin" ], "before_drawing": "ky", "after_drawing": "chol", "token_count": 10, "broken_strip_tags_count": 9, "spurious_fused_token": "kychol" }, { "locus": 9, "left_tokens": [ "shor", "okol", "chol", "dol", "ky", "dar" ], "right_tokens": [ "shol", "dchor", "o", "tcho", "dar", "shody" ], "before_drawing": "dar", "after_drawing": "shol", "token_count": 12, "broken_strip_tags_count": 11, "spurious_fused_token": "darshol" }, { "locus": 10, "left_tokens": [ "taor", "chotchey", "dal", "chody" ], "right_tokens": [ "schody", "pol", "chodar" ], "before_drawing": "chody", "after_drawing": "schody", "token_count": 7, "broken_strip_tags_count": 6, "spurious_fused_token": "chodyschody" } ] } }, "regression_checks": { "artificial_gap": { "input": "ol<->oltchey", "correct_segments": [ [ "ol" ], [ "oltchey" ] ], "wrong_generic_tag_removal": [ "ololtchey" ] }, "f1r_v005_gap_count": 0, "f1r_scope": "The new gap-preservation issue does not alter the f1r v005 counts: its stored input has no <-> markers." } }