gpt-5.5_v4_reasoning_high v1 Evaluation

Generated: 2026-09-20 11:22:32 UTC

Pairs100
Distinct lemmas100
Slope0.942
R^20.989
BLEU-456.7%
chrF++76.3%
METEOR80.8%
ROUGE-L80.8%
BERTScore96.9%
COMET81.1%
BLEURT78.7%

Profile version id: 1763

First translation using this version: 2026-06-24

Total usable AI runs for this version: 101 runs across 101 lemmas

Created: 2026-06-19 08:17:46.611841+10:00

Active: True

Notes: Approved-human-only v4 reasoning trial using Responses API reasoning.effort=high.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.942
Intercept1.683
R^20.989
P-value1.18e-98
Pearson r0.995
Mean source words30.400
Length fallback rows0
Mean human words44.150
Mean AI words43.250
Mean absolute length residual2.689
Mean absolute percent error5.9%

Metric vs Passage Length

These plots test whether score changes with source passage length for this prompt version. The dashed line is an ordinary least-squares fit; the annotation reports n, r, R^2, p-value, and slope.

BLEU-4 vs passage length
BLEU-4: significant negative; r = -0.415, R^2 = 0.173, p = 1.72e-05.
chrF++ vs passage length
chrF++: significant negative; r = -0.441, R^2 = 0.195, p = 4.36e-06.
METEOR vs passage length
METEOR: significant negative; r = -0.464, R^2 = 0.216, p = 1.14e-06.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.476, R^2 = 0.226, p = 5.74e-07.
BERTScore vs passage length
BERTScore: significant negative; r = -0.614, R^2 = 0.377, p = 1.07e-11.
COMET vs passage length
COMET: significant negative; r = -0.464, R^2 = 0.216, p = 1.14e-06.
BLEURT vs passage length
BLEURT: significant negative; r = -0.708, R^2 = 0.502, p = 1.65e-16.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.340, R^2 = 0.116, p = 0.0005.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.352, R^2 = 0.124, p = 0.0003.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.347, R^2 = 0.120, p = 0.0004.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.359, R^2 = 0.129, p = 0.0002.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.415 0.173 1.72e-05 -0.00289 ok
chrF++ 100 significant negative -0.441 0.195 4.36e-06 -0.00183 ok
METEOR 100 significant negative -0.464 0.216 1.14e-06 -0.00196 ok
ROUGE-L 100 significant negative -0.476 0.226 5.74e-07 -0.00189 ok
BERTScore 100 significant negative -0.614 0.377 1.07e-11 -0.00041 ok
COMET 100 significant negative -0.464 0.216 1.14e-06 -0.00087 ok
BLEURT 100 significant negative -0.708 0.502 1.65e-16 -0.00257 ok
Trigram precision 100 significant negative -0.340 0.116 0.0005 -0.00279 ok
Trigram recall 100 significant negative -0.352 0.124 0.0003 -0.00284 ok
Trigram F1 100 significant negative -0.347 0.120 0.0004 -0.00281 ok
Trigram Jaccard 100 significant negative -0.359 0.129 0.0002 -0.00316 ok

Translation Similarity Metrics

Mean BLEU-456.7%
Mean chrF++76.3%
Mean METEOR80.8%
Mean ROUGE-L80.8%
Mean BERTScore96.9%
Mean COMET81.1%
Mean BLEURT78.7%
Legacy smoothed corpus BLEU53.8%
Unigram F181.0%
Bigram F159.8%
Trigram precision47.6%
Trigram recall46.6%
Trigram F147.1%
Trigram Jaccard30.8%
4-gram F138.2%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
2604 Καρχηδών 117 131 19.161 34.1% 62.4% 66.4% 64.8% 93.2% 78.0% 62.6% reviewed/approved 20249 gpt-5.5
2484 Καρία 270 244 -11.889 39.7% 65.1% 64.9% 68.5% 92.8% 81.8% 56.3% reviewed/approved 19753 gpt-5.5
2465 Κάνωπος 83 89 9.173 46.0% 72.7% 77.0% 76.7% 96.3% 78.2% 73.5% reviewed/approved 19749 gpt-5.5
2056 Καβειρία 112 98 -9.131 42.8% 72.7% 68.7% 75.2% 96.3% 79.9% 67.3% reviewed/approved 10451 gpt-5.5
2119 Κάλλατις 65 72 9.120 27.4% 60.6% 69.6% 65.7% 94.6% 71.2% 68.7% reviewed/approved 17787 gpt-5.5
7260 Κυχρεῖος πάγος 61 66 6.886 45.5% 70.9% 78.6% 64.6% 95.9% 77.5% 63.1% reviewed/approved 20367 gpt-5.5
2468 Καπετώλιον 138 125 -6.610 32.2% 55.7% 60.3% 64.6% 92.9% 75.3% 58.3% reviewed/approved 19750 gpt-5.5
7255 Κυτέριον 22 29 6.604 50.5% 75.5% 73.2% 70.6% 96.8% 78.4% 80.6% reviewed/approved 20345 gpt-5.5
2603 Κάρυστος 175 173 6.554 44.9% 68.8% 73.3% 69.0% 94.6% 78.8% 63.7% reviewed/approved 20248 gpt-5.5
2605 Κάσιον 56 60 5.593 51.8% 75.5% 85.8% 77.6% 96.6% 79.8% 75.6% reviewed/approved 20250 gpt-5.5
3496 Κοτιάειον 71 63 -5.529 39.4% 58.8% 64.0% 64.2% 94.0% 75.1% 71.6% reviewed/approved 20286 gpt-5.5
2342 Κάμιρος 54 58 5.476 53.4% 78.4% 73.7% 78.6% 97.5% 81.7% 75.0% reviewed/approved 19577 gpt-5.5
2455 Κάναστρον 60 53 -5.173 28.8% 61.2% 52.0% 63.7% 94.8% 72.1% 63.3% reviewed/approved 19748 gpt-5.5
7253 Κυρτώνιος 18 23 4.370 31.4% 61.9% 72.7% 63.4% 95.7% 76.9% 78.1% reviewed/approved 20343 gpt-5.5
2055 Καβασσός 109 100 -4.307 32.7% 64.1% 64.1% 65.1% 95.1% 78.0% 58.7% reviewed/approved 6081 gpt-5.5
2470 Καππαδοκία 68 70 4.295 38.9% 69.3% 87.9% 82.6% 97.0% 78.0% 77.2% reviewed/approved 19751 gpt-5.5
7254 Κύτα 84 85 4.231 54.7% 72.7% 79.6% 78.1% 95.3% 78.9% 71.7% reviewed/approved 20344 gpt-5.5
2597 Καρπασία 112 103 -4.131 48.3% 72.9% 65.5% 70.7% 95.8% 77.1% 64.1% reviewed/approved 19754 gpt-5.5
2326 Καλλίαρος 47 50 4.067 64.8% 84.3% 94.2% 90.7% 97.9% 76.2% 77.6% reviewed/approved 17789 gpt-5.5
7266 Κώμη 79 80 3.939 18.7% 49.4% 52.9% 52.8% 93.5% 73.3% 56.4% reviewed/approved 20374 gpt-5.5
7264 Κωλιάς 61 63 3.886 53.3% 74.7% 80.9% 77.4% 96.6% 74.3% 64.3% reviewed/approved 20372 gpt-5.5
2328 Καλλίπολις 43 46 3.833 47.0% 65.5% 70.8% 67.4% 94.6% 74.3% 72.7% reviewed/approved 19569 gpt-5.5
3288 Κορώνεια 110 109 3.752 38.3% 67.9% 69.2% 70.9% 94.8% 77.3% 65.5% reviewed/approved 20285 gpt-5.5
7259 Κύφος 54 56 3.476 48.9% 75.7% 85.0% 81.8% 96.3% 76.5% 77.5% reviewed/approved 20349 gpt-5.5
2330 Καλύβη 24 21 -3.279 78.4% 89.3% 88.0% 93.3% 99.3% 83.8% 85.6% reviewed/approved 19571 gpt-5.5
3530 Κριώα 26 23 -3.162 38.0% 71.1% 65.7% 73.5% 96.9% 79.2% 76.9% reviewed/approved 20310 gpt-5.5
7258 Κύτωρος 30 33 3.072 68.3% 86.6% 97.7% 85.7% 98.0% 82.7% 85.0% reviewed/approved 20348 gpt-5.5
7249 Κύρρος 45 41 -3.050 49.7% 67.9% 74.6% 72.1% 95.6% 75.9% 68.9% reviewed/approved 20318 gpt-5.5
7267 Κωνώπη 64 59 -2.939 59.2% 76.1% 76.1% 81.3% 97.3% 79.0% 74.4% reviewed/approved 20375 gpt-5.5
2621 Κάστνιον 25 28 2.780 66.0% 85.4% 94.4% 83.0% 98.6% 82.4% 85.7% reviewed/approved 20254 gpt-5.5

Residual Predictors

Positive signed-residual terms are associated with AI translations longer than expected from the human length; negative signed-residual terms are associated with shorter AI translations. Absolute-residual models identify terms associated with larger AI-human length divergence.

Greek source terms predicting signed length residuals

Features: 176; ridge alpha: 8.377; cross-validated R^2: -0.235.

Positive termCoefficientDocsMean presentMean absent
απο 0.9274 27 2.043 -0.756
δε και 0.8343 8 2.901 -0.252
και 0.7564 66 0.200 -0.388
εν τη 0.6320 7 3.848 -0.290
εστι δε και 0.6122 3 7.582 -0.234
ος 0.5728 6 3.739 -0.239
οι 0.5333 11 2.401 -0.297
εκαλειτο δε 0.5294 3 4.609 -0.143
πολιτης 0.5269 18 2.547 -0.559
και το 0.5215 9 2.647 -0.262
τη 0.5207 15 1.670 -0.295
εστι δε 0.4717 5 3.135 -0.165
στραβων 0.4506 15 2.036 -0.359
εκαλειτο 0.4506 7 1.272 -0.096
εκληθη 0.4307 4 5.202 -0.217
ποσειδωνος 0.4162 3 5.710 -0.177
της χωρας 0.4157 3 3.211 -0.099
ου 0.4047 14 1.174 -0.191
χωρας 0.3919 4 2.324 -0.097
πολιχνιον 0.3877 3 4.925 -0.152
Negative termCoefficientDocsMean presentMean absent
το -0.7880 70 -0.235 0.549
οικητωρ -0.4129 6 -2.795 0.178
το εθνικον -0.4127 56 -0.402 0.512
εθνικον -0.4127 56 -0.402 0.512
θρακης -0.3989 5 -2.376 0.125
τα -0.3961 12 -1.428 0.195
πλησιον -0.3876 8 -1.115 0.097
εθνος -0.3729 8 -2.881 0.251
ης -0.3685 3 -3.565 0.110
γαρ -0.3533 9 -0.213 0.021
ηρωδιανος -0.3362 3 -6.945 0.215
πολις της -0.3085 3 -4.280 0.132
εκαταιος -0.2995 14 -0.731 0.119
και του -0.2959 4 -2.375 0.099
παυσανιας -0.2928 4 -3.167 0.132
μεταξυ -0.2888 5 -1.230 0.065
ως το -0.2861 3 -5.087 0.157
λυκιας -0.2820 3 -2.738 0.085
το θηλυκον -0.2660 6 -2.666 0.170
θηλυκον και -0.2617 3 -3.643 0.113

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 4.125; cross-validated R^2: -0.021.

Positive termCoefficientDocsMean presentMean absent
και 1.7987 66 3.217 1.664
ος 1.1781 6 7.785 2.364
δε 1.1491 46 3.638 1.881
εκαλειτο δε 1.0873 3 12.535 2.385
την 1.0786 13 6.216 2.162
δε και 1.0632 8 6.515 2.356
εκαλειτο 0.9713 7 6.568 2.397
δια 0.9581 16 5.276 2.196
απο 0.9389 27 4.859 1.887
της 0.7855 35 4.117 1.920
δια του 0.7298 10 6.110 2.309
αφ ου 0.7137 5 6.906 2.467
εστι δε και 0.7126 3 7.693 2.534
εστι δε 0.7002 5 6.855 2.470
αφ 0.6946 6 6.003 2.478
περι 0.6474 11 4.751 2.434
εκαλειτο δε και 0.6435 3 12.535 2.385
γαρ 0.5568 9 4.854 2.475
εστι 0.5476 24 4.026 2.267
ει 0.5420 4 7.530 2.487
Negative termCoefficientDocsMean presentMean absent
το εθνικον -0.6073 56 2.616 2.782
εθνικον -0.6073 56 2.616 2.782
τε -0.5116 5 2.090 2.721
οι -0.4940 11 2.401 2.725
προς -0.4750 15 2.577 2.709
προς τη -0.4567 4 1.456 2.741
ηροδοτος -0.4302 9 2.541 2.704
και πολις -0.4223 5 2.059 2.722
εκ -0.3851 6 2.089 2.728
του δε -0.3600 3 1.192 2.735
των -0.3394 17 3.678 2.487
πολις -0.3355 68 2.743 2.576
μια -0.3326 3 1.040 2.740
τεταρτω -0.3235 3 1.419 2.728
θεοπομπος -0.3150 5 1.789 2.737
πορρω -0.3106 3 0.850 2.746
ου πορρω -0.3106 3 0.850 2.746
νησος -0.3103 9 2.505 2.707
πλησιον -0.2664 8 1.850 2.762
εκαταιος ασια -0.2659 5 1.291 2.763

AI English terms predicting large absolute residuals

Features: 332; ridge alpha: 4.125; cross-validated R^2: -0.056.

Positive termCoefficientDocsMean presentMean absent
he 1.2366 4 10.866 2.348
was 0.9745 14 5.292 2.265
and 0.9072 58 3.477 1.601
to 0.8943 23 4.806 2.057
with 0.8773 17 4.900 2.236
who 0.8611 9 6.661 2.296
the 0.7025 94 2.777 1.310
on 0.6857 15 4.611 2.350
used 0.6803 10 6.333 2.284
at 0.6501 8 7.343 2.285
be 0.6455 12 5.747 2.272
also 0.6106 44 3.562 2.004
of 0.6084 62 3.235 1.798
there is 0.5946 26 4.240 2.144
used to 0.5870 4 8.511 2.447
used to be 0.5870 4 8.511 2.447
this 0.5855 12 6.313 2.195
when 0.5846 6 8.259 2.334
it 0.5764 39 3.810 1.973
there 0.5621 34 3.913 2.059
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.5306 53 2.486 2.918
the ethnonym -0.5056 56 2.485 2.949
ethnonym is -0.4596 54 2.609 2.783
a city -0.4470 65 2.774 2.532
ethnonym -0.4214 58 2.631 2.769
his -0.3701 29 2.274 2.859
city in -0.3694 43 2.840 2.575
a city in -0.3694 43 2.840 2.575
city -0.3576 68 2.743 2.576
one -0.3335 11 2.462 2.717
which the -0.3141 4 1.059 2.757
near -0.3125 20 2.643 2.701
not -0.3056 7 1.529 2.777
book of his -0.2929 13 2.448 2.725
book of -0.2929 13 2.448 2.725
it is also -0.2918 4 1.166 2.753
also a city -0.2863 4 1.456 2.741
herodotus -0.2733 4 1.370 2.744
in book of -0.2662 12 2.481 2.718
of his -0.2637 15 2.607 2.704

Human English terms predicting large absolute residuals

Features: 335; ridge alpha: 4.125; cross-validated R^2: -0.087.

Positive termCoefficientDocsMean presentMean absent
and 1.1856 52 3.488 1.824
who 0.8933 13 5.680 2.242
with 0.8160 16 4.654 2.315
also 0.8156 43 3.658 1.958
was 0.8126 20 4.439 2.252
the 0.7891 90 2.829 1.427
is with 0.7268 4 9.823 2.392
to 0.6959 31 3.983 2.108
there 0.6312 34 4.018 2.005
this 0.6156 15 5.790 2.142
like 0.5961 5 5.707 2.530
it 0.5796 37 3.640 2.131
who was 0.5728 3 10.118 2.459
their 0.5560 3 12.535 2.385
usage 0.5497 4 6.052 2.549
most 0.5030 4 9.590 2.402
local 0.5028 6 5.783 2.492
came 0.5000 4 8.633 2.442
from the 0.4925 13 4.656 2.395
at 0.4897 6 6.919 2.419
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.5932 52 2.381 3.023
ethnonym is -0.5932 52 2.381 3.023
a city -0.4772 64 2.738 2.603
the ethnonym -0.4233 56 2.639 2.753
ethnonym -0.4119 57 2.669 2.717
a city in -0.4040 40 2.873 2.566
city in -0.3614 41 2.940 2.515
one of -0.3445 5 1.212 2.767
herodotos book -0.3401 5 0.848 2.786
herodotos -0.3328 9 2.541 2.704
of his -0.3228 18 2.184 2.800
one of the -0.3213 4 1.061 2.757
an -0.3208 22 2.581 2.720
city -0.3051 70 2.829 2.363
in book of -0.2828 14 1.653 2.858
it is -0.2669 24 3.322 2.489
not -0.2590 8 1.807 2.766
near -0.2562 16 2.603 2.706
book of his -0.2514 16 2.318 2.760
book of -0.2514 16 2.318 2.760

Prompt Text

Show prompt text
You are an expert classical philologist and translator specialising in Stephanos of Byzantium's Ethnika.

Goal
- Produce a clear, scholarly English translation in the established reviewed house style.
- Stay close to the Greek while making Stephanos' compressed reference-work prose intelligible in English.
- Translate the Greek main text of the entry, not the modern apparatus, editorial locators, or later bibliographic explanation.

Priority order
- Follow the source Greek first.
- Apply the output and formatting rules below.
- Apply any entry-specific Additional translation context supplied with the entry, but only where the cited Greek evidence is relevant.
- Do not force a rule, gloss, or proper-noun convention when the local syntax or context contradicts it.

Output rules (required)
- Respond ONLY by calling the submit_translation tool with a single string field: {"translation": "..."}.
- The translation text must contain only the translation.
- Do not include analysis, commentary, alternative translations, uncertainty notes, or Markdown outside the translation itself.

A) Formatting + spelling
- Use Australasian spelling and punctuation conventions.
- Preserve paragraphing and line-breaks when they are present in the Greek source.
- For verse quotations, preserve line segmentation in English where the Greek source marks or implies individual verse lines.
- For lengthy prose quotations that function as a quoted block, allow paragraph/quotation separation so the quotation remains readable. Do not create stanza-like line breaks for ordinary short prose snippets.
- Use single quotes for quoted forms, cited snippets, translated quotations, appellations derived from or pertaining to the headword (such as ethnonyms and similar gentilics, but not divine epithets), and Greek forms rendered in Latin letters: '...'.
- Avoid double quotes.
- Use *italics* for titles of ancient works when they are actual work titles: *Cypriaka*, *Bassarika*, *Europe*, *Periegesis*, *Geography*.
- Do not italicise descriptive phrases that are not work titles, such as an epitome of another author's books.

B) Opening / structure
- Let the Greek structure control the opening. Do not force every entry into a single template.
- When the entry opens with the headword and a brief identification, normally begin with the headword transliterated into Latin letters without Greek diacritics, followed by the identification.
- Typical form where appropriate: Headword: ...
- Appositive openings like 'Karia, the country.' are acceptable when the entry is of that type.
- If the headword line gives both nominative and genitive, render it compactly as 'X, Y: ...' unless a grammatical tag is needed for clarity.
- Keep numbered or lettered sequences of homonymous places as inline numbered items like (2) ... (3) ..., matching the Greek's structure.
- When Greek ἔστι καὶ ἄλλη / ἕτερος introduces another place with the same name, use 'There is also another ...' when that is needed for sense.
- For appositional settlement descriptions of the type X (proper noun) + Y (settlement noun) + Z (genitive territory), translate the territory as location: 'X, a city/town/village in Z', not 'of Z', unless the Greek clearly expresses possession, origin, descent, or another non-locative relationship.

C) Transliteration + naming
- Do NOT use macrons or acute accents in ordinary transliteration: Karystos, not Kárystos.
- Prefer Greek-form transliteration when Stephanos is discussing Greek forms, derivation, spelling, ethnonyms, or other metalinguistic material.
- Use these general correspondences unless an established house-style exception is supplied: η = e, κ = k, φ = ph, ῥ = rh, ῤ = r, υ = y, χ = ch.
- Use Greek-style transliteration of diphthongs, especially ai for αι. Do not drift into Latinised forms such as ae or e where the Greek form matters.
- Use forms such as Karchedon, Chalkedon, Kapetolion, Kyrene, Kyrtos, Kappadokia, and Palaistine in Greek-form contexts.
- Avoid Latinised forms such as Carthage, Chalcedon, Capitolium, Cyrene, Cyrtos, Cappadocia, and Palestine in Greek-form contexts.
- Use established conventional English forms only when they are house-style exceptions or clearly ordinary geography, for example Rome, Cyprus, Egypt, Syria, India, Sicily, Thebes, Peloponnese, the Black Sea, the Red Sea, and the Persian Gulf.
- Treat conventional English-name exceptions as a conservative whitelist. Do not expand it by analogy without entry-specific guidance.
- Keep Greek-form transliteration for most ethnonyms and derived adjectives, and put the cited form in single quotes.
- Do not Latinise river, people, or place names merely because a familiar Latin or English form exists.

D) Citations (authors/works/books)
- Translate only the citation information that is present in the original Greek words of the lemma entry.
- Ignore modern/editorial locator codes and apparatus-like add-ons: omit RE/SH numbers, FGrHist numbers, fragment numbers, chapter/section locators, column references, and parenthetical references such as (12,1,2 [C 533,12]), (Op. 344), or (A. R. 2,403).
- Do not infer a book number from a modern parenthetical reference.
- If the Greek says only 'Strabo' plus a modern parenthetical locator, translate 'Strabo', not 'Strabo, book 12'.
- Use 'as per X' only where the Greek itself has ὡς + author/name or an equivalent example-marker construction that supports that rendering.
- If the Greek explicitly gives a Greek book numeral, translate it: 'Ktesias in book 3 of his *Persika*'.
- Keep citations compact, mirroring the source's incompleteness:
  - Author + work title: 'Hellanikos in his *Cypriaka*'
  - Author + book: 'Pausanias, book 9.'
  - Author + work + book: 'Dionysios in book 3 of his *Bassarika*: ...'
- Work-title guidance:
  - Γεωγραφούμενα / γεωγραφικά in citation contexts -> *Geography*, not *Geographoumena*, when this is the established house treatment for the cited work.
  - Περιήγησις / Περίοδος should normally preserve the transmitted title as *Periegesis* when that is what Stephanos gives.
  - If the Greek says an author is cited in an epitome of the eleven books, do not italicise *Epitome* as a work title; translate 'in an epitome of his eleven books'.
- If a citation is present in the source as bracketed main text and later syntax depends on it, translate it in brackets rather than omitting it.
- Do not add external citation labels like Iliad, Works and Days, or Argonautica unless the Greek itself names them.

E) Entry-specific guidance context
- Additional translation context may be supplied for the current entry.
- This context can include matched formula rules, glossary rules, proper-noun conventions, contextual vocabulary bias, and external source passages.
- Apply required or replacement guidance strongly when the evidence matches the current Greek.
- Apply formula and gloss guidance according to the local syntax; do not make it mechanical if the context requires a different construction.
- Apply proper-noun guidance for consistency where supplied, but do not overwrite the Greek's grammatical point.
- Apply contextual vocabulary bias as a preference, not as a one-to-one replacement. It should steer the wording when the stated semantic context is present.
- Use external source passages only for quoted or allusive material. Do not replace Stephanos' own wording with the external source translation.
- Do not mention which guidance rules fired in the translation output. The review interface should surface that separately.

F) Philological, grammatical, and orthographic discussion
- When the entry discusses spelling, letters, diphthongs, accents, stress, case, gender, number, dialect, or morphology, preserve the technical claim precisely.
- Preserve Greek letters or digraphs in Greek script when the letter or digraph itself is under discussion, for example ι, ει, οι, υ.
- Prefer transliteration for cited word-forms unless the point depends on Greek spelling, accentuation, a specific letter, or a visible dialectal/prosodic distinction.
- If accentuation or prosody is the topic:
  - τόνος -> stress or accentuation, according to context.
  - ὀξύς describing a word's τόνος -> oxytone, not merely 'acute'.
  - βαρύς describing a word's τόνος -> barytone, not merely 'grave'.
  - Keep the form in a representation that makes the contrast visible. Use Greek script where the Greek spelling or accent is the point.
- When Stephanos cites an inflected form, dialectal form, or poetic form as evidence for another form, do not normalise away the form being demonstrated.
- If the cited form is inflected or dialectal, translate using the English lemma derived from the appropriate Greek nominative where that is needed for consistency. For example, treat Κυταιέος as evidence for Kytaieus from Κυταιεύς, not as a different nominative such as Kytaios.
- Use brief grammatical tags only when they are necessary to make the philological point visible:
  - case: (nom.), (acc.), (gen.), (dat.), (voc.)
  - gender: (m.), (f.), (n.)
  - number: (sing.), (pl.)

G) Comparisons / derivational analogies
- For ὡς + X where X is an analogous form or etymologically related noun, use a form like "(as in 'X')" where this makes the analogy clear.
- For fuller derivational analogies, keep the relation explicit:
  - as 'Byzantios' is from the name Byzantion
  - as in 'Lykaones', from Lykaonia
- Avoid bare 'like X' when the point is morphological analogy.

H) ἀπό, ἀφ' οὗ, and naming/derivation formulae
- If ἀπό + genitive gives an eponym or naming source, prefer 'after X' or 'named after X' rather than a flat 'from X'.
- In entries with temporal naming contrast, ἐκαλεῖτο X ... κέκληται Y -> 'It used to be called X; it is now called/named Y.'
- For ἀφ' οὗ:
  - With a masculine personal antecedent in a naming context, translate 'after whom'.
  - With an explicit neuter antecedent, translate 'from which'.
  - With a dropped neuter antecedent or Stephanos' example-marker usage, translate naturally according to the syntax; use 'as per' only when the Greek construction supports an evidentiary/example sense.
- Avoid archaic 'whence' unless it is clearly the most natural scholarly English.

I) Syntax and restraint
- Translate directly; do not add background explanation, modern bibliography, or parenthetical glosses unless Stephanos gives them.
- Do not add glosses like (synoikia), (kalathos), or explanatory etymologies unless the Greek explicitly defines the term.
- Avoid gratuitous adversatives for δέ.
- Use 'however' only for a real contrast, such as a correction, opposition, exception, or contrastive second item that English needs to mark.
- Avoid 'on the other hand' unless the Greek contrast is strong and English needs it.
- Convert participles into natural English when strict literalness obscures the structure.
- Circumstantial participles may need 'because', 'as', 'when', or a relative clause.
- Preserve uncertainty when the Greek is uncertain, corrupt, or genuinely ambiguous; do not invent a resolution.
- If the source includes bracketed or braced text as part of the lemma main Greek text of the Meineke edition rather than apparatus, translate it and keep brackets if that best reflects the source.
- If the source gives indirect speech under φασί, do not automatically turn it into a formal quotation unless the source punctuation or reference-work style calls for it.

Now translate the provided entry accordingly, and submit it via submit_translation.