1# WP35 source registry (inputs). Retrieval dates, sizes and SHA-256 are written by2# src/wp35/acquisition/fetch.py into data/metadata/source_registry.json. Nothing here is a3# coverage count: coverage is computed from the parsed files (Phase 2).4sources:5 seshat_polaris2026:6 dataset: "Seshat Global History Databank — Polaris-2026 snapshot"7 publisher: "Seshat: Global History Databank (University of Oxford / Complexity Science Hub)"8 release: "Polaris-2026 (repository commit 55ca5fbc2b, 2026-02-25, 'final version')"9 url: "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Polaris2026.xlsx"10 landing_page: "https://seshatdatabank.info/data/"11 license: "MIT (repository LICENSE, Copyright (c) 2025 Seshat Global History Databank); data citation requested"12 citation: "Seshat: Global History Databank, Polaris-2026 data release, https://seshatdatabank.info/data/ (see also Turchin et al. 2018 PNAS; Turchin et al. 2015 Cliodynamics)"13 filename: "Polaris2026.xlsx"14 units: "polity-time rows; variables coded 0/1 (absent/present) or numeric with uncertainty ranges; see sheets"15 role: "historical polity panel: coordination demand (population, territory, hierarchy), capacity (administration, writing, records, infrastructure), and outcomes"16 seshat_equinox2020:17 dataset: "Seshat Global History Databank — Equinox-2020 snapshot (spreadsheet copy stored in the Polaris repository)"18 publisher: "Seshat: Global History Databank"19 release: "Equinox-2020, spreadsheet dated 05.2023 (repository commit 55ca5fbc2b)"20 url: "https://raw.githubusercontent.com/Seshat-Global-History-Databank/build_polaris_dataset/55ca5fbc2b/Equinox2020.05.2023.xlsx"21 landing_page: "https://seshatdatabank.info/data/"22 license: "MIT (repository LICENSE); original Equinox release on Zenodo (record 6629022) is labelled AGPL-3.0"23 citation: "Seshat: Global History Databank, Equinox-2020 data release"24 filename: "Equinox2020.05.2023.xlsx"25 units: "polity-time rows"26 role: "robustness: alternative Seshat release"27 seshat_equinox_continuous_polities:28 dataset: "Seshat Databank: Equinox Release with Culturally and Institutionally Continuous Polities (Timescale SM data)"29 publisher: "Seshat / Zenodo record 8120128"30 release: "Zenodo 8120128 (2023-07-06)"31 url: "https://zenodo.org/api/records/8120128/files/Timescale.SM_Data.xlsx/content"32 landing_page: "https://zenodo.org/records/8120128"33 license: "CC-BY-4.0"34 citation: "Zenodo record 8120128 (Seshat Equinox release with continuous polities), DOI 10.5281/zenodo.8120128"35 filename: "Timescale.SM_Data.xlsx"36 units: "polity sequences with start/end dates"37 role: "polity continuity / sequence boundaries (candidate for event definitions)"38 maddison_2023_xlsx:39 dataset: "Maddison Project Database 2023"40 publisher: "Groningen Growth and Development Centre, University of Groningen"41 release: "MPD 2023 (Bolt & van Zanden 2024)"42 url: "https://dataverse.nl/api/access/datafile/421302"43 landing_page: "https://www.rug.nl/ggdc/historicaldevelopment/maddison/releases/maddison-project-database-2023"44 license: "Free for academic use with citation (GGDC terms); check landing page"45 citation: "Bolt, J. and J. L. van Zanden (2024), 'Maddison-style estimates of the evolution of the world economy: A new 2023 update', Journal of Economic Surveys, 1-41."46 filename: "mpd2023_web.xlsx"47 units: "country-year; GDP per capita in 2011 international USD; population in thousands"48 role: "modern/long-run economic outcomes and population (country-year panel; NOT mapped onto ancient polities)"49 maddison_2023_dta:50 dataset: "Maddison Project Database 2023 (Stata file)"51 publisher: "GGDC"52 release: "MPD 2023"53 url: "https://dataverse.nl/api/access/datafile/421303"54 landing_page: "https://www.rug.nl/ggdc/historicaldevelopment/maddison/releases/maddison-project-database-2023"55 license: "Free for academic use with citation"56 citation: "Bolt & van Zanden (2024)"57 filename: "mpd2023_web.dta"58 units: "country-year"59 role: "cross-check of the xlsx parse"60 dplace_ea_v3_3:61 dataset: "D-PLACE dataset derived from Murdock et al. 1999 'Ethnographic Atlas' (CLDF)"62 publisher: "D-PLACE (Kirby et al. 2016) / GitHub D-PLACE/dplace-dataset-ea"63 release: "v3.3 (2025-12-19)"64 url: "https://api.github.com/repos/D-PLACE/dplace-dataset-ea/zipball/v3.3"65 landing_page: "https://d-place.org/"66 license: "CC BY-NC 4.0"67 citation: "Kirby, K. R. et al. (2016). D-PLACE: A Global Database of Cultural, Linguistic and Environmental Diversity. PLoS ONE 11(7): e0158391. Murdock, G. P. et al. (1999) Ethnographic Atlas (World Cultures)."68 filename: "dplace-dataset-ea-v3.3.zip"69 units: "one row per society (~1,290 societies expected per documentation; actual count computed in Phase 2); coded categorical variables EA001-EA114 + environmental"70 role: "ethnographic cross-section: political integration (EA033), jurisdictional hierarchy, settlement size (EA031), class stratification; Galton's problem handled with language family / region"71 vdem_v16_rdata:72 dataset: "V-Dem Country-Year Dataset v16 (vdemdata R package copy)"73 publisher: "Varieties of Democracy Institute, University of Gothenburg (official GitHub package vdeminstitute/vdemdata)"74 release: "v16 (package commit f4dd26922e, 2026-03-17 'v16 release')"75 url: "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/vdem.RData"76 landing_page: "https://www.v-dem.net/data/the-v-dem-dataset/"77 license: "V-Dem data: free for non-commercial use with citation (V-Dem terms of use); package GPL-3"78 citation: "Coppedge, M. et al. (2026). V-Dem [Country-Year/Country-Date] Dataset v16. Varieties of Democracy (V-Dem) Project. https://doi.org/10.23696/vdemds26 (DOI to be verified in Phase 2 against the codebook)"79 filename: "vdem_v16.RData"80 units: "country-year, 1789-2025 (to be verified)"81 role: "modern institutional panel: state capacity proxies (rigorous and impartial public administration v2clrspct, legislature, civil service, census, etc.) and regime instability outcomes; democracy indices NOT used as capacity"82 vdem_v16_codebook:83 dataset: "V-Dem codebook (R object)"84 publisher: "V-Dem Institute"85 release: "v16"86 url: "https://raw.githubusercontent.com/vdeminstitute/vdemdata/f4dd26922e/data/codebook.RData"87 landing_page: "https://www.v-dem.net/data/the-v-dem-dataset/"88 license: "GPL-3 (package)"89 citation: "Coppedge et al. (2026) V-Dem Codebook v16"90 filename: "vdem_v16_codebook.RData"91 units: "variable metadata"92 role: "data dictionary for V-Dem"93 glottolog_cldf_languages:94 dataset: "Glottolog CLDF languages table (language family for Galton controls)"95 publisher: "Glottolog (Hammarström, Forkel, Haspelmath, Bank), MPI-EVA"96 release: "glottolog-cldf v5.3 (2026-03-02)"97 url: "https://raw.githubusercontent.com/glottolog/glottolog-cldf/v5.3/cldf/languages.csv"98 landing_page: "https://glottolog.org/"99 license: "CC BY 4.0"100 citation: "Hammarström, H., Forkel, R., Haspelmath, M. & Bank, S. Glottolog 5.3. Leipzig: Max Planck Institute for Evolutionary Anthropology. https://glottolog.org"101 filename: "glottolog_v5.3_languages.csv"102 units: "one row per languoid; Family_ID"103 role: "map D-PLACE Glottocodes to language families (non-independence control)"104