pyaegean
Copyright 2026 Ryan Pavlicek

This product includes software developed by Ryan Pavlicek, licensed under the
Apache License, Version 2.0.

================================================================================
Third-party data and attributions
================================================================================

Linear A corpus (bundled text JSON: src/aegean/data/bundled/lineara/)
  Derived from the GORILA edition — Godart, L. & Olivier, J.-P. (1976–1985),
  "Recueil des inscriptions en linéaire A" (Études Crétoises) — via the
  open dataset at https://github.com/mwenge/lineara.xyz.
  The GORILA volumes are digitized in the École française d'Athènes'
  CEFAEL library:
  https://cefael.efa.gr/result.php?serie_title_operator=con&volume_number_operator=%3D&issue_year_operator=%3D&section_title=Recueil+des+inscriptions+en+lin%C3%A9aire+A&section_title_operator=con&author_lastname_operator=con&publisher_name_operator=con&site_id=1&actionID=advanced&operator=AND
  Used as a scholarly reference corpus. Transliterations and structured
  metadata only; no facsimile imagery is bundled or redistributed.

Cypriot syllabic inscriptions — Inscriptiones Graecae XV 1
  (bundled text JSON: src/aegean/data/bundled/cypriot/ig_inscriptions.json)
  Inscriptiones Graecae XV 1 (Cypriot syllabic inscriptions), digital edition by the
  Berlin-Brandenburg Academy of Sciences and Humanities (TELOTA), https://telota.bbaw.de/ig,
  licensed CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). A point-in-time snapshot
  is bundled and redistributed here under that license; each inscription record keeps its
  source URL for the required attribution / link-back. Transliterations, translations, and
  structured metadata only.

Linear A facsimile / photographic imagery (fetched on demand, NOT redistributed)
  © École Française d'Athènes and respective rights holders. Downloaded by the
  user on demand from the linearaworkbench repository for academic reference;
  never re-hosted by this package.

Ancient Greek Dependency Treebank — AGDT v2.1 (fetched on demand, NOT redistributed)
  Perseus Ancient Greek Dependency Treebank, v2.1
  (https://github.com/PerseusDL/treebank_data), licensed CC BY-SA 3.0. Downloaded
  by the user on demand via aegean.greek.use_treebank() / use_parser() / use_tagger() /
  use_lemmatizer(); pyaegean builds derived artifacts (a lemma/morphology lexicon, a
  dependency-parser model, a POS-tagger model, and a lemmatizer model) in the local cache
  and neither bundles nor re-hosts the treebank itself. Attribute the AGDT in academic
  work that relies on it.
  For convenience the project also hosts these derived artifacts as the
  pyaegean release asset "agdt-derived" (the lexicon + the three trained models, ~15 MB);
  the Greek backends fetch it on demand instead of downloading the AGDT and training
  locally, falling back to build-from-source if it is unreachable. The derived artifacts
  are CC BY-SA 3.0 (a derivative of the AGDT); fetched to the cache, never bundled.

Liddell-Scott-Jones lexicon — Perseus LSJ (fetched on demand, NOT redistributed)
  A Greek-English Lexicon (Liddell, Scott, Jones), digitized by the Perseus Digital
  Library (https://github.com/PerseusDL/lexica), licensed CC BY-SA 4.0. Text provided
  under a CC BY-SA license by Perseus Digital Library, http://www.perseus.tufts.edu,
  with funding from The National Endowment for the Humanities. Data accessed from
  https://github.com/PerseusDL/lexica/. Downloaded by the user on demand via
  aegean.greek.use_lsj(); pyaegean builds a derived index in the local cache and
  neither bundles nor re-hosts the lexicon. For convenience the project also hosts that
  derived lemma->entry index as the pyaegean release asset "lsj-index" (~15 MB, CC BY-SA
  4.0 — a derivative of the Perseus LSJ); use_lsj() fetches it on demand instead of
  downloading the ~270 MB TEI and building locally, falling back to build-from-source if
  it is unreachable. Fetched to the cache, never bundled.

Middle Liddell, Cunliffe, Abbott-Smith, and Autenrieth lexica — derived indexes (fetched on demand, NOT bundled)
  An Intermediate Greek-English Lexicon (Liddell & Scott, 1889; public domain), digitized by the
  Perseus Digital Library (CC BY-SA) with structured data from the Scaife Viewer's
  scaife-viewer/atlas-data-prep (MIT); A Lexicon of the Homeric Dialect (Cunliffe, 1924; public
  domain; Scaife structured data, MIT); and A Manual Greek Lexicon of the New Testament
  (Abbott-Smith, 1922; public domain), TEI markup from translatable-exegetical-tools/Abbott-Smith.
  pyaegean hosts derived lemma->entry indexes as the release assets "middle-liddell-index",
  "cunliffe-index", "abbott-smith-index", and "autenrieth-index" (A Homeric Dictionary,
  Autenrieth, 1891; public domain; Perseus digitization CC BY-SA); downloaded by the user on demand via
  aegean.greek.use_lexicon(), which falls back to fetching the source data and building the index
  locally if an asset is unreachable; fetched to the local cache, never bundled. Attribute the
  digitizers (Perseus Digital Library / Scaife Viewer / translatable-exegetical-tools) in academic
  work that relies on them.

Neural Greek lemmatizer model (fetched on demand, NOT bundled)
  An ONNX seq2seq lemmatizer fine-tuned from bowphs/GreTa (Riemenschneider & Frank,
  "Exploring Large Language Models for Classical Philology", Apache-2.0;
  arXiv:2305.13698) on the AGDT (CC BY-SA 3.0), the Pedalion treebanks (CC BY-SA 4.0),
  and the Gorman Ancient Greek treebanks (CC BY-SA 4.0 — the repository's TREEBANK
  LICENSE; an earlier revision of this notice misstated it as CC0). The resulting model — ONNX weights plus a
  derived gold lemma lookup — is licensed CC BY-SA 4.0. Downloaded by the user on demand
  via aegean.greek.use_neural_lemmatizer() (the [neural] extra); fetched to the local cache,
  never bundled in the Apache-2.0 wheel. Attribute GreTa and the treebanks in academic work.

Neural joint Greek pipeline model (fetched on demand, NOT bundled)
  One GreBerta-based model (Riemenschneider & Frank's encoder, Apache-2.0;
  arXiv:2305.13698) for UPOS,
  AGDT-positional morphology (rendered as UD FEATS), UD dependency trees, and lemmas,
  fine-tuned on the AGDT (CC BY-SA 3.0), the Gorman treebanks (CC BY-SA 4.0), and the
  Pedalion treebanks (CC BY-SA 4.0) with the UD-Perseus dev/test and PROIEL evaluation
  texts excluded from training. The resulting model bundle (ONNX + tokenizer + label
  maps + lemma scripts/lookup) is licensed CC BY-SA 4.0; downloaded by the user on
  demand via aegean.greek.use_neural_pipeline() (the [neural] extra), fetched to the
  local cache, never bundled in the Apache-2.0 wheel. Attribute the treebanks in
  academic work.

Greek literary works — Perseus canonical-greekLit / First1KGreek (fetched on demand, NOT redistributed)
  TEI editions of Ancient Greek works from PerseusDL/canonical-greekLit (Perseus Digital
  Library) and OpenGreekAndLatin/First1KGreek (Open Greek and Latin), both CC BY-SA.
  Downloaded by the user on demand via aegean.greek.load_work() — one work at a time,
  pinned to an upstream commit (recorded as Provenance.data_version) — into the local
  cache; pyaegean neither bundles nor re-hosts the texts. Attribute the Perseus Digital
  Library / Open Greek and Latin and the underlying print edition (see each file's TEI
  header) in academic work.

PROIEL treebank — Ancient Greek (fetched on demand, NOT redistributed)
  The PROIEL treebank (https://github.com/proiel/proiel-treebank) — the Greek New Testament
  and Herodotus — licensed CC BY-NC-SA 3.0. Downloaded by the user on demand via
  aegean.greek.evaluate_on_proiel() as a neutral, out-of-AGDT evaluation set; pyaegean reads it
  locally in the cache and neither bundles nor re-hosts it (NonCommercial + ShareAlike). Cite:
  Dag T. T. Haug and Marius L. Jøhndal (2008), "Creating a Parallel Treebank of the Old
  Indo-European Bible Translations", Proc. LaTeCH 2008, pp. 27–34.

Universal Dependencies — Ancient Greek treebanks (fetched on demand, NOT redistributed)
  UD_Ancient_Greek-Perseus and UD_Ancient_Greek-PROIEL
  (https://github.com/UniversalDependencies/), licensed CC BY-NC-SA 2.5 (Perseus) and
  CC BY-NC-SA 3.0 (PROIEL), per each treebank's README. Downloaded by the
  user on demand via aegean.greek.evaluate_on_ud() as cross-tool-comparable EVALUATION sets
  only — pyaegean reads them locally in the cache, never bundles or re-hosts them, and never
  trains on them (NonCommercial + ShareAlike; the AGDT↔UD overlap manifest built by
  aegean.greek.agdt_ud_overlap() additionally excludes their sentences from AGDT-side
  training). Cite the treebanks and the UD framework in academic work that relies on them.

CoNLL 2018 shared-task evaluator (fetched on demand, NOT redistributed)
  conll18_ud_eval.py (https://universaldependencies.org/conll18/), Mozilla Public
  License 2.0. Downloaded by the user on demand (sha256-pinned) into the local cache and
  imported from there by aegean.greek.evaluate_on_ud(); not bundled in the wheel.

Aegean syllabic sign data — Unicode Character Database (bundled)
  The Linear B (src/aegean/data/bundled/linearb/), Cypriot (.../cypriot/), and Cypro-Minoan
  (.../cyprominoan/) sign inventories — and the phonetic maps for the two deciphered scripts —
  are derived from the Unicode Character Database (UnicodeData.txt — the "Linear B Syllabary",
  "Linear B Ideograms", "Cypriot Syllabary", and "Cypro-Minoan" blocks), Copyright
  © 1991–present Unicode, Inc., distributed under the Unicode License v3
  (https://www.unicode.org/license.txt); the only obligation is to retain this notice. Cypro-Minoan
  is undeciphered, so its signs carry conventional numbers (CM001 …) and no phonetic values. The
  bundled illustrative samples of transliterations and sign sequences are scholarly fact (after
  Ventris & Chadwick, Documents in Mycenaean Greek; Masson, Les inscriptions chypriotes syllabiques;
  Chadwick, Linear B and Related Scripts, for the Idalion readings; and Ferrara, Cypro-Minoan
  Inscriptions), included as excerpts, not corpora. The expanded Linear B Greek-bridge lexicon
  entries and sample-tablet excerpts were extracted from Wiktionary's Mycenaean Greek entries via
  the kaikki.org machine-readable dump (Wiktionary text is dual-licensed CC BY-SA 4.0 / GFDL —
  attribution to the Wiktionary contributors; only entries stating an Ancient Greek equation,
  and quotations citing their tablet, were taken; scripts/build_linearb_lexicon.py and
  build_linearb_samples.py document the method), layered under the hand-curated readings.

Find-site coordinates (bundled: src/aegean/data/bundled/geo/site_coordinates.json)
  Approximate site-level latitude/longitude for the find-sites attested in the corpora. The Aegean
  rows are compiled from standard archaeological references (GORILA, Younger, and public gazetteers)
  via the Linear A Research Workbench (https://github.com/ryanpavlicek/linearaworkbench, Apache-2.0);
  the Greek-epigraphy find-place rows carry representative points and place identifiers from
  Pleiades: A Gazetteer of Past Places (https://pleiades.stoa.org), used under CC BY 3.0 —
  attribution: Pleiades contributors. Rounded to ~1 km — for mapping, not survey work.

PapyGreek Treebanks — documentary-Koine evaluation fold (fetched on demand, NOT bundled)
  The papygreek-fold and papygreek-fold-orig assets are UD conversions of the PapyGreek Treebanks
  (Vierros et al., https://github.com/ezhenrik/papygreek-treebanks), CC BY-SA 4.0,
  used for evaluation only; the derived folds (the regularized reg fold and the raw-diplomatic
  orig surface layer) are redistributed under the same CC BY-SA terms. Cite PapyGreek in academic
  work that relies on the fold.

DBBE gold standard — Byzantine book-epigram tagging fold (fetched on demand, NOT bundled)
  The dbbe-lingann-fold asset is a UD conversion of the DBBE linguistic-annotation gold standard
  (lingAnn_GS_medievalGreek.tsv, https://github.com/coswaele/ByzantineGreekDatasets), by
  C. Swaelens, I. De Vos & E. Lefever / Database of Byzantine Book Epigrams (DBBE), Ghent
  University, CC BY 4.0. Gold POS + morphology + lemma over unedited (scribal-orthography)
  Byzantine verse; used for evaluation only (tagging-only, no dependency trees), the derived
  fold redistributed under the same CC BY terms. Cite Swaelens, De Vos & Lefever (2025),
  "Linguistic annotation of Byzantine book epigrams", Language Resources and Evaluation
  59(1):109-134, doi:10.1007/s10579-023-09703-x, in academic work that relies on the fold.

UNESP Trees — verse (tragedy) evaluation fold (fetched on demand, NOT bundled)
  The verse-fold asset is a UD conversion of gold manual annotation from unesp-trees
  (perseids-publications/unesp-trees, https://github.com/perseids-publications/unesp-trees),
  the Perseids/Arethusa teaching project of Prof. Anise D'Orange Ferreira (UNESP,
  Universidade Estadual Paulista), TREEBANK_LICENSE CC BY-SA 4.0. Gold AGDT-scheme annotation
  of Euripides, Bacchae 1-169 (with a small hexameter sample); used for evaluation only, the
  derived fold redistributed under the same CC BY-SA ShareAlike terms. Cite the UNESP Trees
  project (Ferreira / Perseids / Arethusa) in academic work that relies on the fold.

Greek nominal paradigm table (fetched on demand, NOT bundled: grc-paradigms)
  Derived from UniMorph Ancient Greek (https://github.com/unimorph/grc), CC BY-SA 3.0,
  itself sourced from Wiktionary. The derived form->analysis table is redistributed under
  the same CC BY-SA terms as a fetched release asset.

DAMOS — Database of Mycenaean at Oslo (fetched on demand, NOT bundled)
  DAMOS (F. Aurora, University of Oslo; https://damos.hf.uio.no), the most complete edition
  of the Mycenaean (Linear B) corpus, published under CC BY-NC-SA 4.0. pyaegean's
  `damos-corpus` release asset is the transliterations and core metadata (site, series,
  chronology, Trismegistos id) for ~5,900 tablets, decoded from the DAMOS public web API
  into compact JSON (scripts/build_damos_corpus.py; attribution, citation, source URL, and
  generation date in the file's _meta; no imagery). Downloaded by the user on demand via
  aegean.load("damos"); the NonCommercial + ShareAlike obligations pass through to the user,
  and the data is never bundled in or redistributed with the Apache-2.0 wheel. Cite DAMOS:
  Aurora, F. (2015), "DAMOS (Database of Mycenaean at Oslo). Annotating a fragmentarily
  attested language", Procedia - Social and Behavioral Sciences 198: 21-31.

I.Sicily — Inscriptions of ancient Sicily (project-hosted, fetched on demand, NOT bundled)
  I.Sicily (J. Prag et al., University of Oxford; https://sicily.classics.ox.ac.uk,
  https://github.com/ISicily/ISicily), an EpiDoc corpus of the inscriptions of ancient Sicily,
  published under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). pyaegean's
  `isicily-corpus` release asset is the 2,855 primary-Greek texts, their Greek reading extracted
  from each inscription's primary edition with the find-place, date, and coordinates, decoded into
  compact JSON (scripts/build_isicily_corpus.py) from a pinned source commit; attribution, source
  URL, and licence travel in the corpus provenance. CC BY permits the redistribution with
  attribution, so the asset is project-hosted; it is still fetched on demand via
  aegean.load("isicily"), never bundled in the wheel. Cite I.Sicily (Prag et al.) in academic work.

IIP — Inscriptions of Israel/Palestine (project-hosted, fetched on demand, NOT bundled)
  IIP (Michael L. Satlow, ed., Brown University; https://www.inscriptionsisraelpalestine.org,
  https://github.com/Brown-University-Library/iip-texts), a multilingual EpiDoc corpus, licensed
  CC BY-NC 4.0 (https://www.inscriptionsisraelpalestine.org/copyright/). pyaegean's `iip-corpus`
  release asset is the 2,113 primary-Greek inscriptions, their Greek reading extracted with find-
  place and coordinates, decoded into compact JSON (scripts/build_iip_corpus.py) from a pinned
  source commit. CC BY-NC permits redistribution with attribution; the NonCommercial obligation
  passes to the user; fetched on demand via aegean.load("iip"), never bundled in the wheel. Cite
  IIP: Michael L. Satlow, ed., Inscriptions of Israel/Palestine (Brown University),
  DOI 10.26300/pz1d-st89.

IOSPE — Ancient Inscriptions of the Northern Black Sea (project-hosted, fetched on demand, NOT bundled)
  IOSPE³ (King's College London, Dept. of Digital Humanities; https://iospe.kcl.ac.uk,
  https://github.com/kingsdigitallab/iospe). The repository code is MIT-licensed; the inscription
  data is published under CC BY. pyaegean's `iospe-corpus` release asset is the 1,194 Greek
  inscriptions (Tyras, Olbia, Chersonesos, Byzantine), their Greek reading extracted with find-place
  and date, decoded into compact JSON (scripts/build_iospe_corpus.py) from a pinned source commit;
  attributed to IOSPE / King's College London. Fetched on demand via aegean.load("iospe"), never
  bundled in the wheel. Cite IOSPE (Ancient Inscriptions of the Northern Black Sea, King's College
  London).

IGCyr/GVCyr — Greek inscriptions of Cyrenaica (project-hosted, fetched on demand, NOT bundled)
  IGCyr²/GVCyr² (eds. Catherine Dobias-Lalou, Alice Bencivenni, Hugues Berthelot, et al.,
  Alma Mater Studiorum Università di Bologna, 2024; AMS Acta eprint 7796,
  https://doi.org/10.6092/unibo/amsacta/7796), the EpiDoc corpus of the Greek inscriptions of
  ancient Cyrenaica, licensed CC BY-NC-SA 4.0. pyaegean's `igcyr-corpus` release asset is the 997
  inscriptions (incl. archaic Doric and the GVCyr verse subset), their Greek reading extracted with
  title, find-place, and date, decoded into compact JSON (scripts/build_igcyr_corpus.py) from the
  AMS Acta EpiDoc release. CC BY-NC-SA permits redistribution with attribution; the NonCommercial +
  ShareAlike obligations pass to the user; fetched on demand via aegean.load("igcyr"), never bundled.
  Cite IGCyr/GVCyr (Dobias-Lalou et al., Università di Bologna).

EDH — Epigraphic Database Heidelberg (project-hosted, fetched on demand, NOT bundled)
  EDH (Epigraphic Database Heidelberg; Heidelberg Academy of Sciences and Humanities;
  https://edh.ub.uni-heidelberg.de, https://github.com/epigraphic-database-heidelberg/data), a
  database of the Latin and bilingual inscriptions of the Roman Empire, licensed CC BY-SA 4.0
  (https://creativecommons.org/licenses/by-sa/4.0/). The data dump is frozen (the project closed in
  2021). pyaegean's `edh-corpus` release asset is the pure Ancient-Greek subset (the 1,286 inscriptions
  whose edition is xml:lang="grc"; the mostly-Latin bilingual records are excluded), their Greek
  reading extracted with the ancient place, date, modern find-place, and Trismegistos id, decoded into
  compact JSON (scripts/build_edh_corpus.py) from a pinned source commit. CC BY-SA permits
  redistribution with attribution; the ShareAlike obligation passes to the user; fetched on demand via
  aegean.load("edh"), never bundled. Cite EDH (Epigraphic Database Heidelberg, Heidelberg Academy of
  Sciences and Humanities).

DDbDP — Duke Databank of Documentary Papyri (project-hosted, fetched on demand, NOT bundled)
  The DDbDP (Duke Databank of Documentary Papyri), via papyri.info (Duke Collaboratory for Classics
  Computing; https://papyri.info, https://github.com/papyri/idp.data), the corpus of Greek (and some
  Latin) documentary papyri, licensed CC BY 3.0 (https://creativecommons.org/licenses/by/3.0/; stated
  repo-wide in the README and per-file in each edition's <availability>). pyaegean's `ddbdp-corpus`
  release asset is the 57,329 Greek documentary papyri (~4.4M tokens), their Greek reading extracted
  from each edition (resolving the papyrological apparatus) with the citation, date, place, and
  Trismegistos/HGV ids, decoded into a SQLite database with full-text search
  (scripts/build_ddbdp_corpus.py) from a pinned source commit. CC BY permits redistribution with
  attribution; fetched on demand via aegean.load("ddbdp") / aegean.db.search(ddbdp_db(), ...), never
  bundled. Cite the DDbDP (Duke Databank of Documentary Papyri) / papyri.info in academic work.

LiBER — Linear B Electronic Resources (NOT bundled, NOT fetched)
  LiBER (CNR, https://liber.cnr.it) is © CNR Edizioni, all rights reserved. pyaegean neither
  bundles nor fetches it; to work with a LiBER selection, set PYAEGEAN_LINEARB_CORPUS to your
  own licensed export, which pyaegean parses locally and never re-hosts.

SigLA — the Linear A paleographical database (fetched on demand, NOT bundled)
  Salgarella, E. & Castellan, S., SigLA: The Signs of Linear A — a palaeographical
  database (https://sigla.phis.me). Dataset and drawings are published under
  CC BY-NC-SA 4.0, and the SigLA paper notes that copies of SigLA can be hosted and
  the data used outside the interface. pyaegean's `sigla-corpus` release asset is
  that dataset decoded from the published web-app payload into the JSON form the
  paper describes (scripts/build_sigla_corpus.py; attribution, citation, source
  sha256, and generation date in the file's _meta; drawings are NOT included and
  remain at sigla.phis.me). Downloaded by the user on demand via
  aegean.load("sigla") / aegean.scripts.lineara.load_sigla(); the NonCommercial +
  ShareAlike obligations pass through to the user, and the data is never bundled
  in or redistributed with the Apache-2.0 wheel. Cite SigLA in academic work.

Greek New Testament — Nestle 1904 morphology (one book bundled; full corpus fetched on demand)
  The Nestle 1904 Greek New Testament with per-token lemma, Robinson-style morphology, and
  Strong's numbers, from biblicalhumanities/Nestle1904
  (https://github.com/biblicalhumanities/Nestle1904). The base Greek text (Eberhard Nestle
  1904; digital edition by Diego Santos) is public domain; the morphology, lemmas, and
  Strong's numbers (Ulrik Sandborg-Petersen, largely derived from Maurice A. Robinson's
  analysis) are dedicated to the public domain under CC0 1.0. Because CC0 imposes no
  attribution or share-alike obligation, pyaegean both bundles one book as an offline sample
  (src/aegean/data/bundled/greek/nt_sample.json) and hosts the full 27-book corpus as the
  `nt-corpus` release asset, fetched on demand via aegean.greek.load_nt() /
  aegean.load("nt") (built by scripts/build_nt_corpus.py).

Dodson Greek Lexicon (bundled: src/aegean/data/bundled/greek/dodson.json)
  John Jeffrey Dodson, "A Public Domain Greek-English Lexicon of the New Testament", digital
  edition by biblicalhumanities (https://github.com/biblicalhumanities/Dodson-Greek-Lexicon),
  dedicated to the public domain under CC0 1.0. Strong's-keyed Koine glosses; bundled and used
  by aegean.greek.use_dodson() / gloss_nt() / gloss_strongs() (built by
  scripts/build_dodson_lexicon.py).

The structured-data layer of this package is licensed Apache-2.0; underlying
scholarly editions and imagery remain under their respective rights. Cite the
original editions in academic work (see Corpus.provenance.cite()).
