gpt-5.5_v4_mini_high v1 Evaluation

Generated: 2026-07-25 12:53:57 UTC

Pairs100
Distinct lemmas100
Slope0.892
R^20.985
BLEU-446.6%
chrF++70.0%
METEOR76.0%
ROUGE-L77.8%
BERTScoreN/A
COMETN/A
BLEURTN/A

Profile version id: 1766

First translation using this version: 2026-06-28

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 mini reasoning trial using gpt-5.4-mini and Responses API reasoning.effort=high.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.892
Intercept2.395
R^20.985
P-value1.38e-91
Pearson r0.993
Mean source words30.400
Length fallback rows0
Mean human words44.160
Mean AI words41.800
Mean absolute length residual2.990
Mean absolute percent error7.5%

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 = -0.367, R^2 = 0.135, p = 0.0002.
chrF++ vs passage length
chrF++: significant negative; r = -0.398, R^2 = 0.158, p = 4.10e-05.
METEOR vs passage length
METEOR: significant negative; r = -0.462, R^2 = 0.213, p = 1.34e-06.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.497, R^2 = 0.247, p = 1.49e-07.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.406, R^2 = 0.165, p = 2.74e-05.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.416, R^2 = 0.173, p = 1.64e-05.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.411, R^2 = 0.169, p = 2.12e-05.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.404, R^2 = 0.163, p = 3.06e-05.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.367 0.135 0.0002 -0.00253 ok
chrF++ 100 significant negative -0.398 0.158 4.10e-05 -0.00161 ok
METEOR 100 significant negative -0.462 0.213 1.34e-06 -0.00231 ok
ROUGE-L 100 significant negative -0.497 0.247 1.49e-07 -0.00221 ok
BERTScore 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
COMET 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
BLEURT 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
Trigram precision 100 significant negative -0.406 0.165 2.74e-05 -0.00336 ok
Trigram recall 100 significant negative -0.416 0.173 1.64e-05 -0.00335 ok
Trigram F1 100 significant negative -0.411 0.169 2.12e-05 -0.00334 ok
Trigram Jaccard 100 significant negative -0.404 0.163 3.06e-05 -0.00334 ok

Translation Similarity Metrics

Mean BLEU-446.6%
Mean chrF++70.0%
Mean METEOR76.0%
Mean ROUGE-L77.8%
Mean BERTScoreN/A
Mean COMETN/A
Mean BLEURTN/A
Legacy smoothed corpus BLEU46.1%
Unigram F177.5%
Bigram F153.4%
Trigram precision41.0%
Trigram recall38.7%
Trigram F139.8%
Trigram Jaccard24.8%
4-gram F130.6%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
2484 Καρία 270 226 -17.321 35.5% 59.9% 58.9% 64.1% N/A N/A N/A reviewed/approved 7294 gpt-5.4-mini
2604 Καρχηδών 117 122 15.204 36.9% 65.6% 69.0% 66.4% N/A N/A N/A reviewed/approved 7309 gpt-5.4-mini
2603 Κάρυστος 175 171 12.449 41.3% 63.7% 64.1% 67.6% N/A N/A N/A reviewed/approved 7306 gpt-5.4-mini
2342 Κάμιρος 54 60 9.420 37.6% 70.6% 71.2% 73.7% N/A N/A N/A reviewed/approved 7270 gpt-5.4-mini
7260 Κυχρεῖος πάγος 61 66 9.173 48.3% 71.7% 77.4% 67.7% N/A N/A N/A reviewed/approved 7423 gpt-5.4-mini
2056 Καβειρία 112 94 -8.335 26.2% 64.0% 51.6% 63.1% N/A N/A N/A reviewed/approved 7145 gpt-5.4-mini
7251 Κύρτος 66 53 -8.288 38.8% 61.4% 64.1% 68.3% N/A N/A N/A reviewed/approved 7396 gpt-5.4-mini
7255 Κυτέριον 22 30 7.974 28.6% 60.4% 61.6% 61.5% N/A N/A N/A reviewed/approved 7408 gpt-5.4-mini
2605 Κάσιον 56 60 7.635 43.0% 71.1% 80.1% 70.7% N/A N/A N/A reviewed/approved 7312 gpt-5.4-mini
2119 Κάλλατις 65 68 7.604 20.8% 53.6% 60.7% 58.6% N/A N/A N/A reviewed/approved 7234 gpt-5.4-mini
2468 Καπετώλιον 138 118 -7.535 13.5% 47.3% 51.7% 53.9% N/A N/A N/A reviewed/approved 7285 gpt-5.4-mini
2081 Καλάθη 49 39 -7.119 33.1% 63.2% 62.6% 77.3% N/A N/A N/A reviewed/approved 7198 gpt-5.4-mini
3288 Κορώνεια 110 107 6.450 32.0% 64.8% 65.8% 71.6% N/A N/A N/A reviewed/approved 7357 gpt-5.4-mini
2477 Καρδαμύλη 43 47 6.235 44.2% 72.1% 86.8% 75.6% N/A N/A N/A reviewed/approved 7291 gpt-5.4-mini
7254 Κύτα 84 83 5.650 31.5% 61.0% 59.4% 65.9% N/A N/A N/A reviewed/approved 7405 gpt-5.4-mini
2115 Καλὴ ἀκτή 64 65 5.496 24.8% 54.2% 57.8% 57.4% N/A N/A N/A reviewed/approved 7222 gpt-5.4-mini
2346 Κάναι 77 76 4.896 51.3% 67.2% 78.9% 79.2% N/A N/A N/A reviewed/approved 7276 gpt-5.4-mini
7264 Κωλιάς 61 52 -4.827 32.5% 60.1% 54.4% 63.2% N/A N/A N/A reviewed/approved 7435 gpt-5.4-mini
2326 Καλλίαρος 47 40 -4.334 42.6% 67.8% 74.9% 80.5% N/A N/A N/A reviewed/approved 7240 gpt-5.4-mini
2599 Καρπήσιοι 11 8 -4.211 22.4% 60.6% 55.0% 63.2% N/A N/A N/A reviewed/approved 7300 gpt-5.4-mini
2116 Κάληρος 40 34 -4.088 30.7% 58.6% 68.3% 64.9% N/A N/A N/A reviewed/approved 7225 gpt-5.4-mini
7245 Κύρης 13 18 4.005 28.0% 60.1% 83.3% 77.4% N/A N/A N/A reviewed/approved 7378 gpt-5.4-mini
7248 Κύρου πόλις 32 27 -3.949 22.3% 62.1% 56.6% 67.8% N/A N/A N/A reviewed/approved 7387 gpt-5.4-mini
2455 Κάναστρον 60 52 -3.934 23.9% 56.9% 51.7% 58.9% N/A N/A N/A reviewed/approved 7279 gpt-5.4-mini
2802 Κάδρεμα 24 20 -3.811 21.9% 52.9% 51.0% 63.6% N/A N/A N/A reviewed/approved 7171 gpt-5.4-mini
2054 Καβαλίς 65 64 3.604 56.8% 70.9% 70.8% 76.0% N/A N/A N/A reviewed/approved 5763 gpt-5.4-mini
7259 Κύφος 54 54 3.420 45.2% 74.5% 85.9% 85.2% N/A N/A N/A reviewed/approved 7420 gpt-5.4-mini
2329 Κάλπη 57 50 -3.257 45.0% 72.6% 76.9% 81.5% N/A N/A N/A reviewed/approved 7249 gpt-5.4-mini
3496 Κοτιάειον 71 69 3.250 24.8% 51.8% 56.0% 58.6% N/A N/A N/A reviewed/approved 7360 gpt-5.4-mini
2624 Κατάβαθμος 20 17 -3.242 39.9% 70.6% 74.0% 75.7% N/A N/A N/A reviewed/approved 7333 gpt-5.4-mini

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: 2.894; cross-validated R^2: -0.111.

Positive termCoefficientDocsMean presentMean absent
δε και 2.3891 8 4.054 -0.352
οι 1.9416 11 3.941 -0.487
ος 1.8537 6 4.778 -0.305
εστι δε και 1.7282 3 9.296 -0.288
εστι δε 1.6659 5 5.010 -0.264
απο 1.6590 27 1.840 -0.681
τη 1.5421 15 1.972 -0.348
εκληθη 1.5011 4 7.846 -0.327
εν τη 1.4992 7 4.075 -0.307
αφ ου 1.4370 5 4.204 -0.221
τε 1.2769 5 3.930 -0.207
λεγεται 1.2626 9 2.711 -0.268
δυο 1.2615 4 4.866 -0.203
αφ 1.1840 6 3.796 -0.242
στραβων 1.1657 15 2.369 -0.418
ου 1.1622 14 1.864 -0.304
δυναται 1.0938 3 4.589 -0.142
εκαλειτο δε 1.0811 3 3.444 -0.107
παιδος 1.0717 4 4.227 -0.176
των 1.0582 17 1.584 -0.324
Negative termCoefficientDocsMean presentMean absent
το -1.4286 70 0.040 -0.093
γαρ -1.2632 9 -0.499 0.049
εστι και -1.1751 20 -0.477 0.119
εθνος -1.1731 8 -3.654 0.318
εν τω -1.1649 6 -2.419 0.154
τω περι -1.0820 4 -6.235 0.260
εν τω περι -1.0820 4 -6.235 0.260
μεν -0.9411 4 -7.631 0.318
οικητωρ -0.9387 6 -4.124 0.263
ως το -0.8876 3 -5.760 0.178
και του -0.8557 4 -2.977 0.124
ουτως -0.8405 5 -4.378 0.230
τω -0.8122 16 -0.981 0.187
ηρωδιανος -0.7754 3 -8.592 0.266
δια του -0.7562 10 -0.788 0.088
πρωτη -0.7532 3 -7.463 0.231
εν πρωτη -0.7532 3 -7.463 0.231
ως ελλανικος -0.7147 3 -6.663 0.206
θρακης -0.7145 5 -2.085 0.110
ποταμου -0.7049 3 -0.683 0.021

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 1.425; cross-validated R^2: 0.025.

Positive termCoefficientDocsMean presentMean absent
την 2.8432 13 7.243 2.355
δε 2.7861 46 4.147 2.005
δε και 2.4068 8 8.683 2.495
εκαλειτο δε 2.2948 3 14.991 2.619
απο 2.1619 27 5.405 2.097
απο της 2.1276 6 9.699 2.562
τω 2.1048 16 5.150 2.579
γαρ 1.8924 9 6.441 2.649
εστι δε 1.8391 5 8.344 2.709
ος 1.8299 6 7.290 2.716
εκαλειτο 1.6683 7 7.471 2.653
εστι δε και 1.6170 3 9.296 2.795
εκαλειτο δε και 1.6045 3 14.991 2.619
αφ 1.5761 6 6.574 2.762
αφ ου 1.5755 5 7.538 2.751
εστι 1.5319 24 4.826 2.411
περι 1.2978 11 5.682 2.658
εν τω 1.2462 6 7.647 2.693
παρα 1.2266 7 7.096 2.681
λεγεται 1.2235 9 6.758 2.618
Negative termCoefficientDocsMean presentMean absent
τον -1.7820 10 2.357 3.061
καππαδοκιας -1.4287 3 1.014 3.051
προς τη -1.4102 4 1.169 3.066
μια -1.2667 3 0.994 3.052
νησος -1.2214 9 1.843 3.104
πολυβιος -1.2147 5 0.805 3.105
τους -1.1342 4 1.586 3.049
το εθνικον -1.0638 56 2.832 3.192
εθνικον -1.0638 56 2.832 3.192
φασι -0.8740 8 3.747 2.925
προς -0.8588 15 3.333 2.930
ειρηται -0.8207 3 2.127 3.017
εδει -0.7983 3 1.632 3.032
και νησος -0.7771 3 1.188 3.046
παυσανιας -0.7597 4 2.616 3.006
και το -0.7105 9 3.806 2.910
χωρα -0.7023 6 4.067 2.922
τριτω -0.6746 3 1.432 3.039
τινες -0.6325 6 2.015 3.053
στραβων -0.6283 15 3.612 2.881

AI English terms predicting large absolute residuals

Features: 317; ridge alpha: 2.894; cross-validated R^2: -0.094.

Positive termCoefficientDocsMean presentMean absent
of 1.7415 66 3.560 1.885
the 1.7355 93 3.096 1.580
was 1.3552 16 6.231 2.373
and 1.3182 58 3.880 1.762
there 1.0665 31 4.655 2.243
after 1.0439 22 5.275 2.346
too 0.9590 10 6.657 2.583
on 0.9466 16 4.913 2.624
is also 0.9372 31 4.489 2.317
renowned 0.9212 3 10.970 2.744
there is 0.9175 25 4.882 2.360
because of 0.9078 3 11.343 2.732
is 0.8369 89 3.079 2.277
there is also 0.8169 24 4.738 2.438
most 0.8009 4 11.299 2.644
diphthong 0.7995 3 8.840 2.809
it 0.7980 36 4.665 2.048
also 0.7966 42 4.076 2.204
place 0.7954 6 6.119 2.791
while 0.7623 3 13.620 2.662
Negative termCoefficientDocsMean presentMean absent
they -0.7342 7 1.498 3.103
the ethnonym -0.7124 57 2.793 3.252
ethnonym -0.6443 58 2.889 3.131
the ethnonym is -0.6428 55 2.869 3.138
one of the -0.6133 3 0.994 3.052
one of -0.6133 3 0.994 3.052
and the -0.5798 20 3.671 2.820
ethnonym is -0.5740 56 2.967 3.020
an island -0.5590 10 1.718 3.132
some -0.5298 9 2.229 3.066
book the ethnonym -0.4766 7 1.166 3.128
book -0.4758 40 3.003 2.982
been -0.4534 3 0.594 3.064
inhabitant is -0.4440 6 1.548 3.082
are called -0.4401 3 1.550 3.035
strabo book -0.4368 9 2.209 3.068
island -0.4341 14 2.612 3.052
polybios book -0.4339 5 0.805 3.105
polybios -0.4339 5 0.805 3.105
book the -0.4314 11 2.745 3.021

Human English terms predicting large absolute residuals

Features: 336; ridge alpha: 4.125; cross-validated R^2: -0.130.

Positive termCoefficientDocsMean presentMean absent
the 1.4425 90 3.122 1.806
and 1.0901 52 4.013 1.883
was 1.0647 20 5.072 2.470
there 0.8016 34 4.480 2.223
is with 0.7641 4 10.129 2.693
from the 0.7615 13 6.523 2.462
after 0.7583 22 5.160 2.378
he 0.7489 3 10.715 2.751
on 0.7486 16 5.198 2.570
called 0.7392 21 5.305 2.375
there is 0.7179 24 4.711 2.447
also 0.7037 43 4.036 2.202
with 0.7028 16 4.477 2.707
of 0.6854 66 3.507 1.987
to 0.6398 31 4.161 2.465
is also 0.6367 31 4.298 2.403
is 0.6184 87 3.080 2.392
because 0.6003 12 6.372 2.529
their 0.5900 3 14.991 2.619
there is also 0.5750 22 4.811 2.477
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.6232 52 2.618 3.393
ethnonym is -0.6232 52 2.618 3.393
an -0.5221 22 2.400 3.157
kappadokia -0.5182 3 1.591 3.034
a city in -0.5141 40 3.093 2.922
ethnonym -0.4649 57 2.918 3.087
city in -0.4420 41 3.204 2.842
the ethnonym -0.4368 56 2.958 3.032
one of the -0.4125 4 1.287 3.061
book -0.4090 39 2.844 3.084
polybios book -0.3820 5 0.805 3.105
polybios -0.3820 5 0.805 3.105
they -0.3814 12 3.245 2.956
some -0.3650 10 2.187 3.080
which -0.3498 20 3.137 2.954
an island -0.3403 9 1.724 3.116
is a city -0.3330 3 1.286 3.043
and the -0.3300 15 3.321 2.932
territory -0.2996 5 1.845 3.051
but -0.2991 12 2.512 3.056

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.