paper_guidance_ablation_gpt56 v2 Evaluation

Generated: 2026-07-25 12:54:22 UTC

Pairs100
Distinct lemmas100
Slope0.909
R^20.983
BLEU-451.4%
chrF++72.4%
METEOR76.6%
ROUGE-L77.3%
BERTScoreN/A
COMETN/A
BLEURTN/A

Profile version id: 2587

First translation using this version: 2026-07-18

Total usable AI runs for this version: 300 runs across 100 lemmas

Created: 2026-07-18 21:14:55.545407+10:00

Active: True

Notes: Arm B: Stephanos v3 static prompt shell with no matched entry-specific guidance. Model gpt-5.6-sol; Responses API; medium reasoning; top_p 1.0; three runs per Kappa-corpus entry.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.909
Intercept2.955
R^20.983
P-value2.24e-88
Pearson r0.991
Mean source words30.400
Length fallback rows0
Mean human words44.160
Mean AI words43.100
Mean absolute length residual3.072
Mean absolute percent error6.2%

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 = -0.451, R^2 = 0.203, p = 2.55e-06.
chrF++ vs passage length
chrF++: significant negative; r = -0.469, R^2 = 0.220, p = 8.44e-07.
METEOR vs passage length
METEOR: significant negative; r = -0.459, R^2 = 0.211, p = 1.57e-06.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.434, R^2 = 0.188, p = 6.53e-06.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.352, R^2 = 0.124, p = 0.0003.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.380, R^2 = 0.145, p = 9.48e-05.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.367, R^2 = 0.135, p = 0.0002.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.364, R^2 = 0.132, p = 0.0002.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.451 0.203 2.55e-06 -0.00292 ok
chrF++ 100 significant negative -0.469 0.220 8.44e-07 -0.00193 ok
METEOR 100 significant negative -0.459 0.211 1.57e-06 -0.00213 ok
ROUGE-L 100 significant negative -0.434 0.188 6.53e-06 -0.00184 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 -0.352 0.124 0.0003 -0.00258 ok
Trigram recall 100 significant negative -0.380 0.145 9.48e-05 -0.00276 ok
Trigram F1 100 significant negative -0.367 0.135 0.0002 -0.00266 ok
Trigram Jaccard 100 significant negative -0.364 0.132 0.0002 -0.00263 ok

Translation Similarity Metrics

Mean BLEU-451.4%
Mean chrF++72.4%
Mean METEOR76.6%
Mean ROUGE-L77.3%
Mean BERTScoreN/A
Mean COMETN/A
Mean BLEURTN/A
Legacy smoothed corpus BLEU48.1%
Unigram F177.7%
Bigram F154.6%
Trigram precision41.7%
Trigram recall40.6%
Trigram F141.1%
Trigram Jaccard25.9%
4-gram F132.0%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
2468 Καπετώλιον 138 108 -20.409 16.4% 40.6% 38.7% 46.3% N/A N/A N/A reviewed/approved 14826 gpt-5.6-sol
2484 Καρία 270 231 -17.408 37.8% 62.3% 60.3% 68.7% N/A N/A N/A reviewed/approved 14853 gpt-5.6-sol
2603 Κάρυστος 175 178 15.955 36.8% 62.3% 70.1% 68.0% N/A N/A N/A reviewed/approved 14889 gpt-5.6-sol
2604 Καρχηδών 117 125 15.682 32.3% 61.3% 68.9% 64.8% N/A N/A N/A reviewed/approved 14898 gpt-5.6-sol
2328 Καλλίπολις 43 53 10.955 30.1% 60.6% 66.7% 64.6% N/A N/A N/A reviewed/approved 14709 gpt-5.6-sol
2342 Κάμιρος 54 62 9.955 39.7% 69.4% 66.3% 67.2% N/A N/A N/A reviewed/approved 14781 gpt-5.6-sol
7260 Κυχρεῖος πάγος 61 67 8.591 48.2% 71.5% 80.8% 65.6% N/A N/A N/A reviewed/approved 15240 gpt-5.6-sol
2605 Κάσιον 56 61 7.136 47.6% 72.0% 77.4% 68.4% N/A N/A N/A reviewed/approved 14907 gpt-5.6-sol
2346 Κάναι 77 80 7.046 58.3% 71.3% 79.7% 80.3% N/A N/A N/A reviewed/approved 14799 gpt-5.6-sol
2455 Κάναστρον 60 51 -6.500 23.9% 55.9% 45.0% 55.9% N/A N/A N/A reviewed/approved 14808 gpt-5.6-sol
2597 Καρπασία 112 111 6.228 33.8% 63.0% 69.1% 68.2% N/A N/A N/A reviewed/approved 14862 gpt-5.6-sol
7255 Κυτέριον 22 29 6.045 44.6% 70.9% 64.7% 66.7% N/A N/A N/A reviewed/approved 15195 gpt-5.6-sol
2116 Κάληρος 40 34 -5.318 18.7% 53.8% 59.7% 56.8% N/A N/A N/A reviewed/approved 14646 gpt-5.6-sol
2470 Καππαδοκία 68 70 5.227 28.2% 58.9% 84.0% 81.2% N/A N/A N/A reviewed/approved 14835 gpt-5.6-sol
7259 Κύφος 54 57 4.955 46.5% 72.5% 86.7% 82.9% N/A N/A N/A reviewed/approved 15231 gpt-5.6-sol
7266 Κώμη 79 70 -4.773 20.1% 46.4% 41.0% 49.7% N/A N/A N/A reviewed/approved 15294 gpt-5.6-sol
2626 Κατάνη 95 94 4.682 36.0% 60.5% 64.0% 66.7% N/A N/A N/A reviewed/approved 14997 gpt-5.6-sol
7254 Κύτα 84 84 4.682 50.0% 74.0% 72.7% 76.2% N/A N/A N/A reviewed/approved 15186 gpt-5.6-sol
7257 Κυτώνιον 25 21 -4.682 70.8% 75.2% 71.8% 78.3% N/A N/A N/A reviewed/approved 15213 gpt-5.6-sol
2326 Καλλίαρος 47 50 4.318 58.5% 79.9% 90.5% 86.6% N/A N/A N/A reviewed/approved 14691 gpt-5.6-sol
2078 Καινύς 22 19 -3.955 62.3% 69.9% 73.2% 73.2% N/A N/A N/A reviewed/approved 14529 gpt-5.6-sol
7261 Κύψελα 34 30 -3.864 63.5% 74.5% 77.1% 81.2% N/A N/A N/A reviewed/approved 15249 gpt-5.6-sol
2330 Καλύβη 24 21 -3.773 60.2% 73.8% 81.7% 88.9% N/A N/A N/A reviewed/approved 14727 gpt-5.6-sol
2075 Καινίνη 15 13 -3.591 63.2% 80.1% 80.4% 85.7% N/A N/A N/A reviewed/approved 14511 gpt-5.6-sol
3530 Κριώα 26 23 -3.591 27.5% 54.1% 52.1% 61.2% N/A N/A N/A reviewed/approved 15069 gpt-5.6-sol
3496 Κοτιάειον 71 71 3.500 34.6% 60.4% 68.1% 59.2% N/A N/A N/A reviewed/approved 15051 gpt-5.6-sol
7247 Κύρνος 50 45 -3.409 31.2% 54.0% 64.4% 61.1% N/A N/A N/A reviewed/approved 15123 gpt-5.6-sol
7264 Κωλιάς 61 55 -3.409 32.5% 61.0% 56.1% 58.6% N/A N/A N/A reviewed/approved 15276 gpt-5.6-sol
2114 Κάλβιος 18 16 -3.318 35.8% 58.1% 66.2% 58.8% N/A N/A N/A reviewed/approved 14628 gpt-5.6-sol
7267 Κωνώπη 64 58 -3.136 39.7% 66.5% 62.5% 73.8% N/A N/A N/A reviewed/approved 15303 gpt-5.6-sol

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: -0.043.

Positive termCoefficientDocsMean presentMean absent
απο 2.3751 27 2.773 -1.026
δε και 2.1292 8 3.250 -0.283
οι 1.6263 11 3.938 -0.487
ος 1.5739 6 2.879 -0.184
εκληθη 1.5599 4 8.637 -0.360
πολις 1.5016 68 0.779 -1.656
αφ ου 1.4532 5 5.900 -0.311
εν τη 1.4100 7 4.422 -0.333
αφ 1.4001 6 5.227 -0.334
τη 1.3495 15 2.003 -0.353
πολιτης 1.3217 18 3.263 -0.716
εστι δε και 1.2964 3 6.561 -0.203
ου 1.2693 14 2.974 -0.484
εκαλειτο δε 1.2515 3 4.743 -0.147
στραβων 1.2382 15 2.906 -0.513
των 1.2336 17 1.885 -0.386
φησι 1.1920 12 2.068 -0.282
αλεξανδρος 1.1826 3 5.803 -0.179
πολιχνιον 1.1609 3 6.652 -0.206
ορος 1.1542 6 6.227 -0.397
Negative termCoefficientDocsMean presentMean absent
γαρ -3.6213 9 -3.358 0.332
δια του -2.0528 10 -2.882 0.320
το -1.7702 70 -0.173 0.403
δια -1.6716 16 0.250 -0.048
ηρωδιανος -1.5931 3 -13.560 0.419
ει -1.1790 4 -6.682 0.278
θρακης -1.1548 5 -3.391 0.178
το εθνικον -1.1299 56 -0.472 0.601
εθνικον -1.1299 56 -0.472 0.601
οικητωρ -1.1170 6 -4.894 0.312
τα -1.0315 12 -1.947 0.265
ζευς -0.9701 3 -10.257 0.317
μεταξυ -0.9563 5 -2.100 0.111
εθνος -0.9092 8 -2.841 0.247
πολις θρακης -0.7433 4 -2.614 0.109
τοπικα -0.7432 3 -3.348 0.104
τα τοπικα -0.7432 3 -3.348 0.104
το θηλυκον -0.7094 6 -2.030 0.130
τινες -0.6995 6 -1.379 0.088
περι -0.6778 11 -1.822 0.225

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 4.125; cross-validated R^2: -0.722.

Positive termCoefficientDocsMean presentMean absent
γαρ 2.0142 9 7.944 2.590
δια 1.5783 16 6.852 2.352
δε 1.4994 46 4.061 2.229
την 1.3912 13 7.850 2.358
ος 1.2643 6 9.682 2.650
και 1.2030 66 3.718 1.818
τα 1.1763 12 7.750 2.434
εκαλειτο δε 1.1439 3 16.348 2.661
εκαλειτο 1.1377 7 8.695 2.649
τω 1.1135 16 6.187 2.478
εν 1.0788 37 4.276 2.364
του 1.0471 37 4.522 2.220
απο 0.9520 27 5.268 2.260
περι 0.9334 11 6.558 2.641
δε και 0.9148 8 7.955 2.647
δια του 0.8697 10 6.682 2.671
εις 0.8543 7 9.630 2.578
ζευς 0.8227 3 14.954 2.704
υπο 0.8209 4 7.159 2.902
εκαλειτο δε και 0.8202 3 16.348 2.661
Negative termCoefficientDocsMean presentMean absent
ως -1.0596 52 3.003 3.146
προς τη -0.6292 4 1.295 3.146
εκαταιος -0.6263 14 2.052 3.238
καππαδοκιας -0.5373 3 1.561 3.119
το εθνικον -0.5174 56 3.232 2.868
εθνικον -0.5174 56 3.232 2.868
δευτερω -0.5140 3 1.045 3.135
εδει -0.4521 3 1.197 3.130
ης -0.4459 3 1.257 3.128
νησος -0.4343 9 2.369 3.141
του δε -0.4215 3 1.106 3.133
τις -0.4122 3 1.136 3.132
στραβων -0.4045 15 3.597 2.979
μια -0.3960 3 1.470 3.121
βοιωτιας -0.3882 3 1.439 3.122
πολιτης -0.3398 18 3.586 2.959
χωρα -0.3368 6 4.364 2.989
πορρω -0.3322 3 0.773 3.143
ου πορρω -0.3322 3 0.773 3.143
και του -0.3010 4 1.841 3.123

AI English terms predicting large absolute residuals

Features: 351; ridge alpha: 2.894; cross-validated R^2: -0.579.

Positive termCoefficientDocsMean presentMean absent
when 2.1416 7 12.500 2.362
the 1.7387 95 3.142 1.736
was 1.7198 20 5.527 2.458
he 1.6895 3 13.894 2.737
with 1.5854 22 5.306 2.442
by 1.5824 17 5.842 2.504
diphthong 1.3577 3 14.682 2.713
says 1.3271 18 6.975 2.215
since 1.2944 4 6.545 2.927
and 1.2826 57 3.932 1.931
forms 1.2651 10 7.473 2.583
zeus 1.1694 5 13.591 2.518
of 1.0884 67 3.552 2.098
is 1.0716 88 3.217 2.008
after 1.0629 21 5.439 2.442
is the 1.0250 3 12.712 2.774
was named 0.9635 5 9.682 2.724
it 0.9591 39 4.241 2.324
on 0.9563 14 5.052 2.750
gives 0.9350 3 13.106 2.762
Negative termCoefficientDocsMean presentMean absent
as in -1.0157 27 2.463 3.297
from -0.9826 35 3.095 3.059
is called -0.8764 21 2.058 3.341
as the -0.6667 4 0.863 3.164
is called a -0.6622 8 1.114 3.242
book -0.6036 39 2.819 3.233
hekataios -0.5913 14 2.052 3.238
ethnic is -0.5655 25 3.318 2.990
a city -0.5607 63 3.162 2.918
called a -0.5433 10 1.945 3.197
the ethnic is -0.5350 24 3.383 2.974
are also -0.4963 5 2.718 3.090
inhabitants -0.4754 4 1.477 3.138
some -0.4661 9 2.409 3.137
citizen is called -0.4614 11 2.393 3.156
kappadokia -0.4536 4 2.477 3.097
strabo book -0.4315 9 2.439 3.134
ethnic -0.4276 30 3.582 2.853
a city in -0.4251 45 3.399 2.804
it is also -0.4204 4 1.932 3.119

Human English terms predicting large absolute residuals

Features: 336; ridge alpha: 2.894; cross-validated R^2: -0.615.

Positive termCoefficientDocsMean presentMean absent
with 2.4135 16 5.381 2.632
the 1.9659 90 3.252 1.455
on 1.8341 16 5.568 2.596
is with 1.4632 4 14.204 2.608
when 1.3402 7 9.890 2.559
was 1.2980 20 5.814 2.386
and 1.2852 52 4.100 1.958
on the 1.1821 10 5.582 2.793
to 1.1769 31 4.787 2.301
diphthong 1.0652 3 14.682 2.713
zeus 1.0590 5 13.591 2.518
says 1.0412 17 6.441 2.382
forms 0.9960 4 11.204 2.733
sanctuary 0.9763 3 10.045 2.856
after 0.9462 22 5.376 2.422
named 0.9248 5 7.736 2.826
to the 0.8988 10 7.618 2.567
their 0.8650 3 16.348 2.661
because 0.8491 12 7.614 2.453
he 0.8453 3 10.227 2.851
Negative termCoefficientDocsMean presentMean absent
as in -1.3270 29 2.472 3.317
as -0.8592 60 3.109 3.016
the ethnonym is -0.7365 52 3.019 3.129
ethnonym is -0.7365 52 3.019 3.129
territory -0.6255 5 0.627 3.201
an -0.6047 22 2.583 3.210
ethnonym -0.5929 57 3.227 2.866
the ethnonym -0.5822 56 3.231 2.870
hekataios -0.5389 14 2.052 3.238
and the -0.5340 15 3.476 3.001
was from -0.5134 4 1.977 3.117
a city -0.5098 64 3.132 2.965
it is -0.5034 24 4.129 2.738
book -0.5014 39 2.819 3.233
some -0.4885 10 2.609 3.123
kappadokia -0.4493 3 2.833 3.079
one of -0.4486 5 1.918 3.133
is a -0.4400 31 3.553 2.856
should -0.4340 3 1.197 3.130
it should -0.4340 3 1.197 3.130

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.