Stephanos Pipeline Progress

Last updated: 2026-08-27 21:46:26

Stage Done Total Progress % Rate ETA
AI Translation
Publication target 20 entries/day after guidance lookahead; the weekly rate remains observed completions.
 460 3,677
12.5% 139/week 5.4 months
Human Review 202 460
43.9% 0/week stalled
Meineke Page OCR
Queued missing-page OCR for the public Meineke source text
 835 835
100.0% 0/week complete
Proper Noun Extraction 461 461
100.0% 84/week complete
Structured Source Citations
3,087 current texts with citations; 483 completed with zero units; 0 failed without a later completed run; 831,875 tokens recorded, 0 in the last 7 days
 3,570 3,570
100.0% 0/week complete
Wikidata Sources 474 474
100.0% 50/week complete
Etymology Extraction 461 461
100.0% 84/week complete
Alias Extraction 1,457 1,457
100.0% 84/week complete
Spelling Variants 10,263 10,263
100.0% 676/week complete
Human Entity Review 4,158 10,428
39.9% 0/week stalled
Wikidata Places 3,084 3,084
100.0% 22/week complete
Meineke Difference Analysis 2,001 2,001
100.0% 0/week complete
Text Pair Sync 3,569 3,569
100.0% 3,569/week complete
Translation Risk Sync 460 460
100.0% 461/week complete
Prompt Guidance Checks
3,683 current Meineke headwords x 101 prompt guidance rules (formula, gloss, contextual_bias; translation_guidance_scan_v4); default nightly limit 2,000 checks; queue pending/running/completed/failed/cancelled: 105,170/0/113,934/3/0; 68,851,765 guidance AI tokens recorded, 12,270,739 in the last 7 days
 113,881 371,983
30.6% 20,998/week 2.9 months
Stylometric Fingerprinting
Broad UMAP-ready formula vectors require 21/32 active formula rules: 3,570 entries (320 Kappa, 19 Parisinus); complete formula coverage: 1,077 entries (19 Parisinus); see statistics/fingerprinting.html; sentence grammar rows: sentence_grammar_runs=8, sentence_grammar_evaluations=111, sentence_grammar_tokens=495
 3,570 3,570
100.0% 212/week complete
German Reference Page OCR
Internal reference lane only; statuses entries/no-headword/not-German/other: 288/9/11/25; default nightly limit 3 pages; 1,904,282 OCR tokens recorded
 333 941
35.4% 19/week 6.8 months
German Reference Translation
Internal reference lane only; not public and not part of the main translation queue; failed: 0; default nightly limit 5 refs; 290,275 tokens recorded, 18,999 in the last 7 days
 536 750
71.5% 35/week 1.4 months
Meineke Word Lemmatization
status pending/processing/error: 0/0/0; 13,183,339 tokens recorded, 0 in the last 7 days
 3,683 3,683
100.0% 0/week complete
Paper Translation Model Coverage
52 tracked paper/evaluation model variants; Responses worker limit 10 generated run(s) per pipeline run; experiment enqueue limit 10 new request(s) per profile per run
 5,600 5,600
100.0% 100/week see model table
nodegoat Sync 3,660 3,677
99.5% 0/week stalled

Paper Translation Model Coverage

This table uses the same 100-row Kappa paper corpus as the prompt-evaluation page. Claude rows are external imports; OpenAI rows are generated by the daily pipeline.

Model / prompt API / reasoning Kappa rows Runs Open Runs 7d Latest Projection
claude_fable_5 v1 chat_completions 100/100 100/100 0 0 2026-07-05 complete
claude_fable_5 v2 chat_completions 100/100 100/100 0 0 2026-07-05 complete
claude_fable_5 v3 chat_completions 100/100 100/100 0 0 2026-07-03 complete
claude_opus_4_8 v1 chat_completions 100/100 100/100 0 0 2026-07-05 complete
claude_opus_4_8 v2 chat_completions 100/100 100/100 0 100 2026-08-22 complete
claude_opus_4_8 v3 chat_completions 100/100 100/100 0 0 2026-07-05 complete
claude_sonnet_5 v1 chat_completions 100/100 100/100 0 0 2026-07-03 complete
claude_sonnet_5 v2 chat_completions 100/100 100/100 0 0 2026-07-03 complete
claude_sonnet_5 v3 chat_completions 100/100 100/100 0 0 2026-07-05 complete
gpt-4.1-2025-04-14 v1 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4.1-2025-04-14 v2 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4.1-2025-04-14 v3 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-05-13 v1 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-05-13 v2 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-05-13 v3 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-08-06 v1 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-08-06 v2 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-08-06 v3 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-11-20 v1 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-11-20 v2 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4o-2024-11-20 v3 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4-turbo-2024-04-09 v1 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4-turbo-2024-04-09 v2 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-4-turbo-2024-04-09 v3 chat_completions 100/100 100/100 0 0 2026-07-16 complete
gpt-5 v1 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5 v2 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5 v3 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.1 v1 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.1 v2 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.1 v3 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.2 v1 chat_completions 100/100 104/100 0 0 2026-07-15 complete
gpt-5.2 v2 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.2 v3 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.3-chat-latest v1 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.3-chat-latest v2 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.3-chat-latest v3 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.4 v1 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.4 v2 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.4 v3 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.5 v1 chat_completions 100/100 100/100 0 0 2026-07-15 complete
gpt-5.5 v2 chat_completions 100/100 100/100 0 0 2026-06-21 complete
gpt-5.5 v3 chat_completions 100/100 116/100 0 0 2026-06-20 complete
gpt-5.5_v3_repeat v1 chat_completions 100/100 500/500 0 0 2026-07-30 complete
gpt-5.5_v4_mini v1 responses / low 100/100 100/100 0 0 2026-07-08 complete
gpt-5.5_v4_mini_high v1 responses / high 100/100 100/100 0 0 2026-07-08 complete
gpt-5.5_v4_mini_medium v1 responses / medium 100/100 100/100 0 0 2026-07-08 complete
gpt-5.5_v4_reasoning v1 responses / low 100/100 100/100 0 0 2026-08-12 complete
gpt-5.5_v4_reasoning_high v1 responses / high 100/100 100/100 0 0 2026-08-14 complete
gpt-5.5_v4_reasoning_medium v1 responses / medium 100/100 100/100 0 0 2026-08-13 complete
gpt-5.6-sol v1 responses / medium 100/100 100/100 0 0 2026-07-14 complete
gpt-5.6-sol v2 responses / medium 100/100 100/100 0 0 2026-07-14 complete
gpt-5.6-sol v3 responses / medium 100/100 100/100 0 0 2026-07-14 complete
Note: ETA estimates use the faster of the observed 7-day rate and any configured nightly cron limit known to this page. "Stalled" means no observed progress and no configured nightly rate is known. Proper-noun and etymology extraction are measured over translated lemmas, matching the nightly jobs. Wikidata stages count rows once they have a recorded outcome, including not-found, ambiguous, and human-reviewed cases. Retired legacy Greek OCR stages are intentionally omitted; the active German-reference lane is internal and reported separately when present.