claude_opus_4_8 v3 Evaluation

Generated: 2026-09-20 11:19:40 UTC

Pairs100
Distinct lemmas100
Slope0.956
R^20.988
BLEU-454.2%
chrF++75.1%
METEOR80.9%
ROUGE-L81.6%
BERTScore96.8%
COMET80.9%
BLEURT77.4%

Profile version id: 2014

First translation using this version: 2026-07-05

Total usable AI runs for this version: 100 runs across 100 lemmas

Created: 2026-07-02 10:20:24.063701+10:00

Active: True

Notes: External-only Claude workspace variant for Claude Opus 4.8; copied from legacy_scholarly v3 (source profile_version_id=1101); source_active=True; uses_guidance_context=True.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.956
Intercept1.209
R^20.988
P-value2.63e-95
Pearson r0.994
Mean source words30.400
Length fallback rows0
Mean human words44.150
Mean AI words43.430
Mean absolute length residual2.671
Mean absolute percent error6.0%

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 = -0.414, R^2 = 0.172, p = 1.82e-05.
chrF++ vs passage length
chrF++: significant negative; r = -0.456, R^2 = 0.208, p = 1.82e-06.
METEOR vs passage length
METEOR: significant negative; r = -0.491, R^2 = 0.241, p = 2.12e-07.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.521, R^2 = 0.271, p = 2.77e-08.
BERTScore vs passage length
BERTScore: significant negative; r = -0.654, R^2 = 0.428, p = 1.57e-13.
COMET vs passage length
COMET: significant negative; r = -0.493, R^2 = 0.243, p = 1.94e-07.
BLEURT vs passage length
BLEURT: significant negative; r = -0.730, R^2 = 0.534, p = 6.41e-18.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.397, R^2 = 0.157, p = 4.39e-05.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.405, R^2 = 0.164, p = 2.87e-05.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.402, R^2 = 0.162, p = 3.40e-05.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.389, R^2 = 0.152, p = 6.25e-05.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.414 0.172 1.82e-05 -0.00281 ok
chrF++ 100 significant negative -0.456 0.208 1.82e-06 -0.00180 ok
METEOR 100 significant negative -0.491 0.241 2.12e-07 -0.00221 ok
ROUGE-L 100 significant negative -0.521 0.271 2.77e-08 -0.00208 ok
BERTScore 100 significant negative -0.654 0.428 1.57e-13 -0.00044 ok
COMET 100 significant negative -0.493 0.243 1.94e-07 -0.00091 ok
BLEURT 100 significant negative -0.730 0.534 6.41e-18 -0.00257 ok
Trigram precision 100 significant negative -0.397 0.157 4.39e-05 -0.00321 ok
Trigram recall 100 significant negative -0.405 0.164 2.87e-05 -0.00327 ok
Trigram F1 100 significant negative -0.402 0.162 3.40e-05 -0.00324 ok
Trigram Jaccard 100 significant negative -0.389 0.152 6.25e-05 -0.00344 ok

Translation Similarity Metrics

Mean BLEU-454.2%
Mean chrF++75.1%
Mean METEOR80.9%
Mean ROUGE-L81.6%
Mean BERTScore96.8%
Mean COMET80.9%
Mean BLEURT77.4%
Legacy smoothed corpus BLEU53.3%
Unigram F180.8%
Bigram F159.5%
Trigram precision46.7%
Trigram recall45.9%
Trigram F146.3%
Trigram Jaccard30.1%
4-gram F137.3%

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 117 136 22.902 39.1% 68.1% 78.5% 71.4% 93.9% 78.8% 64.5% reviewed/approved 6815 claude-opus-4.8
2484 Καρία 270 246 -13.414 36.7% 62.0% 59.2% 66.2% 92.3% 81.7% 53.5% reviewed/approved 6810 claude-opus-4.8
2603 Κάρυστος 175 179 10.436 41.6% 66.3% 73.0% 70.6% 94.9% 79.4% 62.4% reviewed/approved 6814 claude-opus-4.8
2342 Κάμιρος 54 63 10.150 43.9% 74.4% 75.7% 75.2% 96.2% 77.3% 68.1% reviewed/approved 6802 claude-opus-4.8
2470 Καππαδοκία 68 76 9.762 35.0% 66.2% 79.6% 76.4% 96.0% 76.4% 68.9% reviewed/approved 6808 claude-opus-4.8
2609 Κάσπειρος 135 139 8.689 47.5% 70.9% 74.0% 75.9% 92.7% 74.8% 66.1% reviewed/approved 6818 claude-opus-4.8
2465 Κάνωπος 83 89 8.417 43.1% 69.2% 79.8% 80.2% 95.8% 77.3% 72.2% reviewed/approved 6806 claude-opus-4.8
2056 Καβειρία 112 100 -8.316 28.8% 66.9% 58.2% 67.9% 95.5% 78.5% 61.6% reviewed/approved 6763 claude-opus-4.8
7259 Κύφος 54 60 7.150 58.1% 80.6% 90.6% 82.5% 96.6% 77.0% 74.2% reviewed/approved 6852 claude-opus-4.8
2468 Καπετώλιον 138 127 -6.180 23.7% 52.6% 51.6% 58.1% 89.8% 69.8% 52.5% reviewed/approved 6807 claude-opus-4.8
7255 Κυτέριον 22 28 5.752 48.5% 73.3% 70.6% 76.0% 97.1% 78.8% 77.5% reviewed/approved 6848 claude-opus-4.8
2055 Καβασσός 109 100 -5.447 38.1% 64.7% 71.1% 65.1% 95.4% 77.8% 59.3% reviewed/approved 6762 claude-opus-4.8
2326 Καλλίαρος 47 51 4.844 52.7% 76.0% 92.3% 83.7% 97.8% 75.6% 76.6% reviewed/approved 6792 claude-opus-4.8
2328 Καλλίπολις 43 47 4.670 40.0% 69.1% 73.5% 68.9% 95.0% 75.2% 73.3% reviewed/approved 6794 claude-opus-4.8
2115 Καλὴ ἀκτή 64 58 -4.413 19.6% 54.1% 64.1% 62.3% 94.1% 73.0% 56.0% reviewed/approved 6786 claude-opus-4.8
7267 Κωνώπη 64 58 -4.413 61.1% 76.8% 77.5% 83.6% 97.4% 79.0% 75.1% reviewed/approved 6860 claude-opus-4.8
2605 Κάσιον 56 59 4.238 50.3% 74.4% 85.5% 74.8% 96.0% 77.7% 70.4% reviewed/approved 6816 claude-opus-4.8
2081 Καλάθη 49 44 -4.068 48.8% 72.9% 75.0% 81.7% 97.1% 74.1% 74.7% reviewed/approved 6778 claude-opus-4.8
2059 Καδμεία 20 24 3.665 41.7% 73.5% 82.7% 81.8% 96.8% 83.9% 82.5% reviewed/approved 6766 claude-opus-4.8
2116 Κάληρος 40 36 -3.461 20.8% 56.1% 67.1% 60.5% 94.2% 78.3% 72.2% reviewed/approved 6787 claude-opus-4.8
7250 Κυρταία 40 36 -3.461 51.3% 71.0% 73.8% 76.3% 97.4% 73.9% 75.8% reviewed/approved 6843 claude-opus-4.8
7260 Κυχρεῖος πάγος 61 63 3.456 51.0% 71.3% 80.8% 69.4% 96.3% 77.0% 67.0% reviewed/approved 6853 claude-opus-4.8
2080 Καλαβρία 18 15 -3.422 24.1% 66.1% 53.5% 72.7% 96.2% 85.3% 81.4% reviewed/approved 6777 claude-opus-4.8
7251 Κύρτος 66 61 -3.326 40.4% 60.6% 73.5% 70.9% 93.6% 72.2% 63.6% reviewed/approved 6844 claude-opus-4.8
2597 Καρπασία 112 105 -3.316 49.3% 73.5% 74.1% 76.5% 96.2% 77.9% 70.0% reviewed/approved 6811 claude-opus-4.8
2330 Καλύβη 24 21 -3.160 70.2% 82.3% 87.0% 93.3% 97.7% 83.4% 80.1% reviewed/approved 6796 claude-opus-4.8
3496 Κοτιάειον 71 66 -3.107 32.2% 56.3% 62.3% 65.7% 94.7% 73.0% 72.4% reviewed/approved 6832 claude-opus-4.8
7258 Κύτωρος 30 33 3.102 58.0% 81.3% 87.8% 85.7% 97.7% 81.1% 82.3% reviewed/approved 6851 claude-opus-4.8
2335 Κάλυτις 26 23 -3.073 36.2% 61.9% 62.0% 69.4% 96.2% 80.1% 76.4% reviewed/approved 6801 claude-opus-4.8
7252 Κύρτωνες 27 30 2.971 44.3% 71.0% 74.9% 80.7% 97.6% 80.8% 80.7% reviewed/approved 6845 claude-opus-4.8

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: 17.013; cross-validated R^2: -0.338.

Positive termCoefficientDocsMean presentMean absent
δε και 0.4937 8 3.209 -0.279
απο 0.4226 27 1.645 -0.608
τε 0.4068 5 4.006 -0.211
εστι δε και 0.3891 3 8.723 -0.270
ος 0.3673 6 4.716 -0.301
οι 0.3580 11 2.750 -0.340
εκαλειτο δε 0.3527 3 6.641 -0.205
παιδος 0.3445 4 5.268 -0.220
τη 0.3402 15 2.009 -0.355
και 0.2991 66 0.068 -0.131
πολις 0.2852 68 0.337 -0.715
εκαλειτο 0.2619 7 1.486 -0.112
πολιτης 0.2414 18 2.189 -0.481
εστι δε 0.2268 5 2.688 -0.141
λεγεται 0.2163 9 2.159 -0.213
εν τη 0.2132 7 2.323 -0.175
εις 0.1979 7 -0.114 0.009
στραβων 0.1945 15 1.586 -0.280
λεγεται και 0.1930 8 2.095 -0.182
εδει 0.1872 3 5.663 -0.175
Negative termCoefficientDocsMean presentMean absent
το -0.3434 70 -0.229 0.535
εστι και -0.3309 20 -0.984 0.246
οικητωρ -0.3058 6 -4.223 0.270
γαρ -0.2982 9 -1.241 0.123
περι -0.2209 11 -2.094 0.259
οτι -0.1929 5 -1.950 0.103
της -0.1852 35 -0.674 0.363
θρακης -0.1813 5 -1.785 0.094
το θηλυκον -0.1776 6 -3.340 0.213
και του -0.1771 4 -3.112 0.130
ηρωδιανος -0.1742 3 -7.266 0.225
μεταξυ -0.1726 5 -1.980 0.104
παρα -0.1726 7 -3.206 0.241
δια -0.1704 16 0.556 -0.106
τους -0.1682 4 -1.982 0.083
ως το -0.1675 3 -5.696 0.176
εστι -0.1519 24 -0.285 0.090
πολις θρακης -0.1494 4 -1.584 0.066
πλησιον -0.1481 8 -0.853 0.074
καππαδοκιας -0.1405 3 -2.371 0.073

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 5.878; cross-validated R^2: -0.448.

Positive termCoefficientDocsMean presentMean absent
και 1.6269 66 3.481 1.099
δε 1.5371 46 4.041 1.504
εκαλειτο δε 1.0417 3 15.584 2.271
εκαλειτο 1.0263 7 8.069 2.265
δε και 0.9532 8 7.189 2.278
ος 0.8482 6 7.811 2.343
απο 0.7401 27 4.870 1.857
εστι δε 0.7364 5 7.780 2.402
εν 0.7217 37 3.550 2.155
εστι δε και 0.6808 3 8.723 2.484
εκαλειτο δε και 0.6414 3 15.584 2.271
δια 0.6396 16 5.287 2.173
εις 0.6256 7 6.473 2.385
εστι 0.5713 24 4.415 2.120
γαρ 0.5693 9 5.816 2.360
τη 0.5561 15 4.739 2.306
φησιν 0.4924 10 7.119 2.177
τε 0.4694 5 4.597 2.569
της 0.4672 35 3.889 2.015
την 0.4500 13 6.110 2.157
Negative termCoefficientDocsMean presentMean absent
το εθνικον -0.6386 56 2.715 2.615
εθνικον -0.6386 56 2.715 2.615
προς -0.5310 15 2.134 2.766
προς τη -0.3778 4 1.217 2.731
και πολις -0.3388 5 1.744 2.720
εθνος -0.3338 8 3.324 2.614
ως -0.3256 52 3.076 2.232
εκαταιος -0.3143 14 2.072 2.768
στραβων -0.2955 15 2.948 2.622
δευτερω -0.2726 3 1.112 2.719
εκαταιος ασια -0.2721 5 1.186 2.749
ασια -0.2721 5 1.186 2.749
νησος -0.2643 9 2.391 2.699
πολυβιος -0.2537 5 1.563 2.729
θεοπομπος -0.2510 5 1.451 2.735
τοις -0.2494 3 1.292 2.714
τις -0.2392 3 0.943 2.724
μια -0.2351 3 1.230 2.715
πελοποννησου -0.2216 3 0.828 2.728
τεταρτω -0.2195 3 1.985 2.692

AI English terms predicting large absolute residuals

Features: 344; ridge alpha: 4.125; cross-validated R^2: -0.385.

Positive termCoefficientDocsMean presentMean absent
and 2.1148 57 3.713 1.289
the 1.3984 96 2.744 0.919
there 1.0467 32 4.616 1.755
called 0.9923 25 4.966 1.906
by 0.8978 14 6.665 2.021
to 0.8331 20 4.832 2.130
used 0.8170 5 9.456 2.314
their 0.8050 5 11.120 2.226
of 0.7872 68 3.087 1.787
on 0.7521 17 4.853 2.224
with 0.7494 16 5.386 2.154
for 0.7249 11 6.078 2.250
there is 0.6873 25 4.518 2.055
be called 0.6841 4 9.380 2.391
to be called 0.6841 4 9.380 2.391
used to 0.6841 4 9.380 2.391
used to be 0.6841 4 9.380 2.391
and there 0.6746 5 8.484 2.365
after 0.6554 22 5.290 1.932
and there is 0.6548 4 9.979 2.366
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.5923 53 2.636 2.710
the ethnonym -0.5675 56 2.625 2.729
ethnonym is -0.5439 54 2.741 2.588
as in -0.5247 25 2.739 2.648
ethnonym -0.4919 58 2.772 2.531
near -0.4760 20 2.197 2.789
island -0.4072 14 2.222 2.744
some -0.3424 9 1.670 2.770
people -0.3204 10 2.947 2.640
one of -0.3174 4 1.651 2.713
book -0.3159 39 2.769 2.608
strabo -0.3049 15 2.948 2.622
a city -0.2871 63 3.139 1.874
city and -0.2784 4 1.301 2.728
a city and -0.2784 4 1.301 2.728
one -0.2723 15 2.875 2.635
say -0.2670 9 1.982 2.739
city in -0.2531 41 3.062 2.399
city -0.2483 68 3.075 1.812
an island -0.2403 10 2.259 2.717

Human English terms predicting large absolute residuals

Features: 335; ridge alpha: 4.125; cross-validated R^2: -0.399.

Positive termCoefficientDocsMean presentMean absent
and 2.1414 52 3.905 1.334
the 1.7397 90 2.850 1.058
says 1.0027 17 5.964 1.996
with 0.9974 16 5.198 2.189
was 0.8861 20 4.879 2.119
is with 0.8495 4 10.980 2.325
who 0.8407 13 5.613 2.231
there 0.7942 34 4.121 1.924
also 0.7644 43 3.834 1.793
to 0.7548 31 4.004 2.072
their 0.7304 3 15.584 2.271
to the 0.7147 10 6.707 2.222
too 0.6873 3 11.241 2.406
it was 0.6752 4 9.819 2.373
after 0.6639 22 5.167 1.967
used to be 0.6346 6 9.397 2.242
on 0.6038 16 4.272 2.366
into 0.5939 3 6.931 2.539
son 0.5913 17 5.661 2.058
son of 0.5913 17 5.661 2.058
Negative termCoefficientDocsMean presentMean absent
as in -0.7172 29 2.484 2.747
the ethnonym is -0.6471 52 2.479 2.879
ethnonym is -0.6471 52 2.479 2.879
an -0.4905 22 2.531 2.710
the ethnonym -0.4881 56 2.762 2.555
ethnonym -0.4681 57 2.809 2.488
people -0.3691 9 3.050 2.633
some -0.3535 10 1.706 2.778
a city in -0.3484 40 3.021 2.437
island -0.3423 14 2.222 2.744
city in -0.3285 41 3.051 2.407
a city -0.3113 64 3.123 1.866
strabo -0.2972 15 2.948 2.622
territory -0.2938 5 0.992 2.759
city and -0.2910 4 1.336 2.726
a city and -0.2910 4 1.336 2.726
near -0.2875 16 2.585 2.687
which -0.2683 20 2.979 2.594
book -0.2678 39 2.769 2.608
city -0.2531 70 3.028 1.837

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.