Generated: 2026-09-20 11:19:44 UTC
Profile version id: 2009
First translation using this version: 2026-07-03
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 Sonnet 5; copied from legacy_scholarly v1 (source profile_version_id=1); source_active=False; uses_guidance_context=False.
| Formula | AI words = intercept + slope * human words |
|---|---|
| Slope | 1.023 |
| Intercept | 2.794 |
| R^2 | 0.979 |
| P-value | 2.53e-84 |
| Pearson r | 0.990 |
| Mean source words | 30.400 |
| Length fallback rows | 0 |
| Mean human words | 44.150 |
| Mean AI words | 47.970 |
| Mean absolute length residual | 3.822 |
| Mean absolute percent error | 12.2% |
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.
| Metric | Rows | Pattern | Pearson r | R^2 | P-value | Slope | Status |
|---|---|---|---|---|---|---|---|
| BLEU-4 | 100 | positive | 0.051 | 0.003 | 0.6145 | 0.00021 | ok |
| chrF++ | 100 | positive | 0.022 | 4.92e-04 | 0.8266 | 0.00007 | ok |
| METEOR | 100 | negative | -0.151 | 0.023 | 0.1332 | -0.00067 | ok |
| ROUGE-L | 100 | negative | -0.189 | 0.036 | 0.0599 | -0.00071 | ok |
| BERTScore | 100 | significant negative | -0.349 | 0.122 | 0.0004 | -0.00028 | ok |
| COMET | 100 | negative | -0.100 | 0.010 | 0.3239 | -0.00018 | ok |
| BLEURT | 100 | significant negative | -0.603 | 0.364 | 3.16e-11 | -0.00172 | ok |
| Trigram precision | 100 | positive | 0.002 | 2.77e-06 | 0.9869 | 7.62e-06 | ok |
| Trigram recall | 100 | negative | -0.023 | 5.40e-04 | 0.8185 | -0.00011 | ok |
| Trigram F1 | 100 | negative | -0.009 | 7.34e-05 | 0.9326 | -0.00004 | ok |
| Trigram Jaccard | 100 | negative | -0.024 | 5.66e-04 | 0.8142 | -0.00007 | ok |
| Mean BLEU-4 | 21.0% |
|---|---|
| Mean chrF++ | 53.0% |
| Mean METEOR | 62.3% |
| Mean ROUGE-L | 62.2% |
| Mean BERTScore | 92.7% |
| Mean COMET | 73.2% |
| Mean BLEURT | 66.0% |
| Legacy smoothed corpus BLEU | 27.7% |
| Unigram F1 | 65.8% |
| Bigram F1 | 36.4% |
| Trigram precision | 20.6% |
| Trigram recall | 22.5% |
| Trigram F1 | 21.5% |
| Trigram Jaccard | 12.1% |
| 4-gram F1 | 13.5% |
| Lemma ID | Headword | Human words | AI words | Residual | BLEU-4 | chrF++ | METEOR | ROUGE-L | BERTScore | COMET | BLEURT | Human | Run | Model |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2604 | Καρχηδών | 117 | 155 | 32.488 | 12.5% | 51.0% | 54.2% | 48.2% | 90.0% | 74.2% | 57.3% | reviewed/approved | 6229 | claude-sonnet-5 |
| 2484 | Καρία | 270 | 261 | -18.066 | 16.5% | 48.4% | 47.9% | 51.6% | 86.5% | 76.8% | 49.3% | reviewed/approved | 6224 | claude-sonnet-5 |
| 2119 | Κάλλατις | 65 | 85 | 15.696 | 12.7% | 48.3% | 56.2% | 48.0% | 91.3% | 63.3% | 60.1% | reviewed/approved | 6204 | claude-sonnet-5 |
| 2056 | Καβειρία | 112 | 103 | -14.396 | 14.1% | 50.7% | 56.3% | 56.7% | 92.3% | 75.0% | 59.4% | reviewed/approved | 6177 | claude-sonnet-5 |
| 2465 | Κάνωπος | 83 | 100 | 12.278 | 26.5% | 60.9% | 76.6% | 68.9% | 93.2% | 74.1% | 63.3% | reviewed/approved | 6220 | claude-sonnet-5 |
| 7266 | Κώμη | 79 | 95 | 11.370 | 3.9% | 34.6% | 37.0% | 32.2% | 89.9% | 65.6% | 43.5% | reviewed/approved | 6273 | claude-sonnet-5 |
| 7264 | Κωλιάς | 61 | 76 | 10.789 | 15.3% | 50.3% | 49.5% | 51.1% | 91.4% | 69.3% | 59.6% | reviewed/approved | 6271 | claude-sonnet-5 |
| 2115 | Καλὴ ἀκτή | 64 | 79 | 10.719 | 12.3% | 47.2% | 64.3% | 58.7% | 90.8% | 64.8% | 51.5% | reviewed/approved | 6200 | claude-sonnet-5 |
| 2328 | Καλλίπολις | 43 | 57 | 10.207 | 16.8% | 52.4% | 52.7% | 56.0% | 91.8% | 74.7% | 64.3% | reviewed/approved | 6208 | claude-sonnet-5 |
| 2116 | Κάληρος | 40 | 35 | -8.724 | 16.2% | 49.8% | 50.0% | 53.3% | 93.9% | 78.6% | 75.9% | reviewed/approved | 6201 | claude-sonnet-5 |
| 2342 | Κάμιρος | 54 | 66 | 7.951 | 25.3% | 62.9% | 78.7% | 68.3% | 93.9% | 74.8% | 66.1% | reviewed/approved | 6216 | claude-sonnet-5 |
| 2455 | Κάναστρον | 60 | 57 | -7.188 | 14.8% | 48.1% | 57.8% | 59.8% | 92.4% | 66.7% | 58.7% | reviewed/approved | 6219 | claude-sonnet-5 |
| 2625 | Κατακεκαυμένη | 46 | 57 | 7.137 | 18.7% | 55.6% | 65.9% | 62.1% | 93.8% | 74.8% | 69.9% | reviewed/approved | 6238 | claude-sonnet-5 |
| 2057 | Καβελλιών | 34 | 31 | -6.584 | 23.8% | 53.8% | 52.3% | 58.5% | 92.6% | 71.5% | 59.6% | reviewed/approved | 6178 | claude-sonnet-5 |
| 3530 | Κριώα | 26 | 23 | -6.398 | 10.9% | 40.4% | 43.4% | 57.1% | 91.6% | 62.9% | 61.6% | reviewed/approved | 6248 | claude-sonnet-5 |
| 7244 | Κυρήνη | 54 | 52 | -6.049 | 27.9% | 52.2% | 49.9% | 54.7% | 94.2% | 73.8% | 63.2% | reviewed/approved | 6251 | claude-sonnet-5 |
| 2468 | Καπετώλιον | 138 | 150 | 6.000 | 10.0% | 40.1% | 32.5% | 38.2% | 86.0% | 65.0% | 44.7% | reviewed/approved | 6221 | claude-sonnet-5 |
| 2627 | Κατάνειρα | 21 | 30 | 5.718 | 6.3% | 38.8% | 43.2% | 47.1% | 89.6% | 65.3% | 61.7% | reviewed/approved | 6239 | claude-sonnet-5 |
| 3288 | Κορώνεια | 110 | 121 | 5.650 | 23.0% | 56.1% | 59.4% | 62.1% | 92.1% | 71.1% | 58.3% | reviewed/approved | 6245 | claude-sonnet-5 |
| 7248 | Κύρου πόλις | 32 | 41 | 5.462 | 11.4% | 48.0% | 41.8% | 43.8% | 88.2% | 67.2% | 61.7% | reviewed/approved | 6255 | claude-sonnet-5 |
| 2059 | Καδμεία | 20 | 28 | 4.741 | 25.6% | 53.4% | 41.0% | 50.0% | 93.6% | 74.8% | 66.8% | reviewed/approved | 6180 | claude-sonnet-5 |
| 7261 | Κύψελα | 34 | 33 | -4.584 | 30.9% | 57.6% | 72.5% | 68.7% | 96.2% | 74.7% | 71.5% | reviewed/approved | 6268 | claude-sonnet-5 |
| 3496 | Κοτιάειον | 71 | 71 | -4.444 | 16.5% | 46.5% | 56.7% | 59.2% | 91.1% | 68.2% | 63.8% | reviewed/approved | 6246 | claude-sonnet-5 |
| 7257 | Κυτώνιον | 25 | 24 | -4.375 | 31.4% | 57.6% | 61.6% | 65.3% | 92.8% | 71.4% | 64.6% | reviewed/approved | 6264 | claude-sonnet-5 |
| 2078 | Καινύς | 22 | 21 | -4.305 | 52.8% | 67.8% | 76.6% | 74.4% | 95.2% | 80.5% | 75.6% | reviewed/approved | 6188 | claude-sonnet-5 |
| 2075 | Καινίνη | 15 | 14 | -4.143 | 39.8% | 57.7% | 73.1% | 75.9% | 95.2% | 80.5% | 75.9% | reviewed/approved | 6186 | claude-sonnet-5 |
| 2081 | Καλάθη | 49 | 49 | -3.933 | 26.5% | 53.7% | 54.8% | 63.3% | 93.1% | 67.5% | 65.4% | reviewed/approved | 6192 | claude-sonnet-5 |
| 2603 | Κάρυστος | 175 | 178 | -3.860 | 30.6% | 57.3% | 68.0% | 61.2% | 92.8% | 75.8% | 52.9% | reviewed/approved | 6228 | claude-sonnet-5 |
| 2117 | Καλησία | 19 | 26 | 3.764 | 11.8% | 48.8% | 70.2% | 57.8% | 92.6% | 74.4% | 67.8% | reviewed/approved | 6202 | claude-sonnet-5 |
| 2079 | Καισάρεια | 39 | 39 | -3.700 | 25.0% | 53.0% | 60.6% | 61.5% | 91.8% | 72.2% | 63.8% | reviewed/approved | 6190 | claude-sonnet-5 |
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.
Features: 176; ridge alpha: 24.245; cross-validated R^2: -0.184.
| Positive term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| και | 0.4650 | 66 | 0.201 | -0.391 |
| δια του | 0.3703 | 10 | 5.219 | -0.580 |
| εστι δε και | 0.3620 | 3 | 12.115 | -0.375 |
| εστι δε | 0.3590 | 5 | 6.533 | -0.344 |
| δε και | 0.3551 | 8 | 1.665 | -0.145 |
| εν τη | 0.3486 | 7 | 5.373 | -0.404 |
| ος | 0.3269 | 6 | 6.619 | -0.422 |
| κωμη | 0.2808 | 3 | 6.765 | -0.209 |
| πολιτης | 0.2802 | 18 | 3.456 | -0.759 |
| εκαλειτο δε | 0.2688 | 3 | 3.521 | -0.109 |
| πολιχνιον | 0.2634 | 3 | 8.106 | -0.251 |
| του | 0.2595 | 37 | 1.569 | -0.921 |
| και το | 0.2420 | 9 | 2.241 | -0.222 |
| ως | 0.2342 | 52 | 0.839 | -0.909 |
| εν | 0.2241 | 37 | 1.502 | -0.882 |
| τοις | 0.2231 | 3 | 5.921 | -0.183 |
| γαρ | 0.2100 | 9 | 1.994 | -0.197 |
| απο | 0.1974 | 27 | 1.151 | -0.426 |
| τοπος | 0.1903 | 4 | 4.987 | -0.208 |
| δε | 0.1887 | 46 | 0.351 | -0.299 |
| Negative term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| το | -0.4559 | 70 | -0.519 | 1.211 |
| το εθνικον | -0.4185 | 56 | -1.309 | 1.666 |
| εθνικον | -0.4185 | 56 | -1.309 | 1.666 |
| εθνος | -0.2606 | 8 | -5.229 | 0.455 |
| τω | -0.2545 | 16 | -1.460 | 0.278 |
| οτι | -0.2380 | 5 | -2.727 | 0.144 |
| θρακης | -0.2379 | 5 | -3.752 | 0.197 |
| τα | -0.2176 | 12 | -1.995 | 0.272 |
| εστι και | -0.2059 | 20 | -0.889 | 0.222 |
| υπο | -0.2027 | 4 | -2.490 | 0.104 |
| κατα | -0.1944 | 10 | 0.177 | -0.020 |
| πλησιον | -0.1844 | 8 | -2.090 | 0.182 |
| αυτην | -0.1829 | 9 | -2.263 | 0.224 |
| πολις θρακης | -0.1703 | 4 | -2.893 | 0.121 |
| ηροδοτος | -0.1650 | 9 | -2.692 | 0.266 |
| το θηλυκον | -0.1628 | 6 | -5.117 | 0.327 |
| εκαταιος ασια | -0.1509 | 5 | -1.966 | 0.103 |
| ασια | -0.1509 | 5 | -1.966 | 0.103 |
| πολις της | -0.1464 | 3 | -6.808 | 0.211 |
| εκει | -0.1454 | 3 | -4.753 | 0.147 |
Features: 176; ridge alpha: 4.125; cross-validated R^2: -0.005.
| Positive term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| και | 2.7450 | 66 | 4.301 | 2.892 |
| εκαλειτο | 2.2696 | 7 | 10.060 | 3.352 |
| εστι δε | 1.7890 | 5 | 13.009 | 3.338 |
| εκαλειτο δε | 1.7333 | 3 | 18.138 | 3.379 |
| κατα | 1.5709 | 10 | 9.454 | 3.196 |
| εστι | 1.5635 | 24 | 6.685 | 2.917 |
| δε και | 1.3823 | 8 | 8.520 | 3.413 |
| εστι δε και | 1.3815 | 3 | 13.310 | 3.528 |
| δε | 1.3502 | 46 | 4.741 | 3.039 |
| δια του | 1.2932 | 10 | 9.946 | 3.141 |
| ει | 1.1941 | 4 | 13.080 | 3.436 |
| της | 1.0463 | 35 | 5.505 | 2.915 |
| γαρ | 1.0298 | 9 | 7.296 | 3.478 |
| δια | 0.9582 | 16 | 6.921 | 3.232 |
| εκαλειτο δε και | 0.9572 | 3 | 18.138 | 3.379 |
| ος | 0.9483 | 6 | 8.100 | 3.549 |
| πολιχνιον | 0.8820 | 3 | 9.162 | 3.657 |
| απο | 0.8422 | 27 | 6.296 | 2.907 |
| λιβυης | 0.8319 | 4 | 13.291 | 3.427 |
| ιβηριας | 0.8084 | 3 | 13.932 | 3.509 |
| Negative term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| το εθνικον | -1.0245 | 56 | 3.447 | 4.298 |
| εθνικον | -1.0245 | 56 | 3.447 | 4.298 |
| οι | -0.7665 | 11 | 3.053 | 3.917 |
| και πολις | -0.7506 | 5 | 2.224 | 3.906 |
| ηροδοτος | -0.7389 | 9 | 3.409 | 3.863 |
| δευτερω | -0.6968 | 3 | 1.280 | 3.900 |
| τους | -0.6815 | 4 | 1.368 | 3.924 |
| εκαταιος | -0.6563 | 14 | 2.533 | 4.032 |
| φασι | -0.6257 | 8 | 2.846 | 3.907 |
| αιγυπτου | -0.5956 | 3 | 1.110 | 3.906 |
| ορος | -0.5593 | 6 | 2.349 | 3.916 |
| αυτην | -0.5319 | 9 | 2.733 | 3.929 |
| λυκιας | -0.5115 | 3 | 1.746 | 3.886 |
| δια το | -0.5111 | 3 | 1.502 | 3.894 |
| καππαδοκιας | -0.5047 | 3 | 2.341 | 3.868 |
| εκληθη | -0.5012 | 4 | 2.081 | 3.894 |
| προς τη | -0.5002 | 4 | 2.513 | 3.876 |
| του δε | -0.4839 | 3 | 1.544 | 3.892 |
| το | -0.4504 | 70 | 3.459 | 4.669 |
| και του | -0.4470 | 4 | 2.367 | 3.882 |
Features: 421; ridge alpha: 2.894; cross-validated R^2: -0.023.
| Positive term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| and | 2.2055 | 58 | 4.644 | 2.687 |
| was | 1.9262 | 16 | 7.410 | 3.138 |
| with | 1.7840 | 19 | 6.894 | 3.101 |
| on | 1.7738 | 22 | 5.383 | 3.381 |
| was also called | 1.4806 | 3 | 13.280 | 3.529 |
| is a | 1.3254 | 7 | 11.441 | 3.248 |
| written with | 1.2969 | 4 | 15.911 | 3.318 |
| name in | 1.2945 | 3 | 15.403 | 3.464 |
| by | 1.2233 | 17 | 7.081 | 3.154 |
| for | 1.2202 | 11 | 6.874 | 3.445 |
| there is | 1.2055 | 25 | 6.267 | 3.007 |
| written | 1.1989 | 5 | 13.617 | 3.306 |
| from | 1.1562 | 42 | 5.499 | 2.607 |
| this | 1.1348 | 18 | 7.732 | 2.963 |
| city and | 1.1217 | 5 | 8.374 | 3.582 |
| while | 1.0807 | 3 | 16.435 | 3.432 |
| states | 1.0441 | 3 | 16.348 | 3.434 |
| come | 1.0385 | 5 | 12.288 | 3.376 |
| it | 1.0363 | 41 | 5.151 | 2.898 |
| likewise | 1.0250 | 3 | 18.851 | 3.357 |
| Negative term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| one | -0.9282 | 11 | 2.881 | 3.938 |
| a city | -0.8446 | 63 | 3.923 | 3.650 |
| the ethnic | -0.8402 | 58 | 3.471 | 4.306 |
| ethnic | -0.7798 | 66 | 3.659 | 4.137 |
| the ethnic is | -0.7721 | 11 | 2.736 | 3.956 |
| ethnic name | -0.7557 | 37 | 3.308 | 4.124 |
| ethnic name is | -0.7269 | 34 | 3.345 | 4.067 |
| river | -0.7102 | 6 | 1.962 | 3.940 |
| near | -0.6853 | 19 | 2.905 | 4.037 |
| cappadocia | -0.6758 | 4 | 2.412 | 3.881 |
| the ethnic name | -0.6752 | 36 | 3.361 | 4.081 |
| call | -0.6746 | 5 | 2.145 | 3.910 |
| ethnic is | -0.6726 | 16 | 3.532 | 3.877 |
| two | -0.6634 | 3 | 0.767 | 3.916 |
| herodotus | -0.6321 | 9 | 3.409 | 3.863 |
| name is | -0.6140 | 37 | 3.569 | 3.970 |
| in the feminine | -0.6129 | 4 | 1.447 | 3.921 |
| feminine form is | -0.6109 | 6 | 1.689 | 3.958 |
| to the | -0.5853 | 7 | 1.944 | 3.963 |
| inhabitants | -0.5349 | 3 | 1.179 | 3.903 |
Features: 335; ridge alpha: 4.125; cross-validated R^2: -0.037.
| Positive term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| and | 1.7943 | 52 | 4.737 | 2.830 |
| like | 1.3782 | 5 | 10.421 | 3.474 |
| for | 1.2578 | 11 | 7.327 | 3.389 |
| is with | 1.2296 | 4 | 14.942 | 3.358 |
| also | 1.1644 | 43 | 4.850 | 3.046 |
| with | 1.0665 | 16 | 7.054 | 3.206 |
| it | 1.0456 | 37 | 5.361 | 2.918 |
| called | 1.0169 | 21 | 5.499 | 3.376 |
| there | 1.0129 | 34 | 6.147 | 2.624 |
| used | 0.9813 | 8 | 10.602 | 3.232 |
| used to | 0.9813 | 8 | 10.602 | 3.232 |
| on | 0.9509 | 16 | 5.541 | 3.494 |
| the | 0.9463 | 90 | 4.004 | 2.181 |
| used to be | 0.9204 | 6 | 11.155 | 3.354 |
| came | 0.9180 | 4 | 13.819 | 3.405 |
| to | 0.9121 | 31 | 5.313 | 3.152 |
| this | 0.8617 | 15 | 7.968 | 3.090 |
| to be called | 0.8607 | 5 | 12.614 | 3.359 |
| their | 0.8473 | 3 | 18.138 | 3.379 |
| there is | 0.8456 | 24 | 5.777 | 3.204 |
| Negative term | Coefficient | Docs | Mean present | Mean absent |
|---|---|---|---|---|
| the ethnonym is | -0.9796 | 52 | 3.175 | 4.522 |
| ethnonym is | -0.9796 | 52 | 3.175 | 4.522 |
| ethnonym | -0.8106 | 57 | 3.427 | 4.346 |
| the ethnonym | -0.7850 | 56 | 3.458 | 4.285 |
| herodotos | -0.6419 | 9 | 3.409 | 3.863 |
| kappadokia | -0.6150 | 4 | 2.412 | 3.881 |
| herodotos book | -0.5726 | 5 | 1.169 | 3.961 |
| a city | -0.5611 | 64 | 3.918 | 3.650 |
| city in | -0.5452 | 41 | 3.878 | 3.782 |
| the river | -0.5413 | 6 | 1.962 | 3.940 |
| river | -0.5413 | 6 | 1.962 | 3.940 |
| a city in | -0.5185 | 40 | 3.928 | 3.751 |
| egypt | -0.4957 | 3 | 1.110 | 3.906 |
| the possessive is | -0.4932 | 4 | 1.582 | 3.915 |
| possessive is | -0.4932 | 4 | 1.582 | 3.915 |
| near | -0.4924 | 16 | 2.881 | 4.001 |
| just as | -0.4770 | 5 | 1.503 | 3.944 |
| hekataios | -0.4360 | 14 | 2.533 | 4.032 |
| they | -0.4209 | 12 | 3.907 | 3.810 |
| say that | -0.4206 | 9 | 2.668 | 3.936 |
You are an expert classical philologist and translator specializing in Byzantine Greek geographical texts. You will receive Greek text from a lemma entry in Stephanos of Byzantium's Ethnika. Translate the Greek text into clear, scholarly English. Preserve technical terminology and place names appropriately.